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

61 files changed, 9136 insertions, 3308 deletions

diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt
index 9f59fcbf5d8..ba046b8fa92 100644
--- a/Documentation/crypto/async-tx-api.txt
+++ b/Documentation/crypto/async-tx-api.txt
@@ -54,20 +54,23 @@ features surfaced as a result:
 
 3.1 General format of the API:
 struct dma_async_tx_descriptor *
-async_<operation>(<op specific parameters>,
-		  enum async_tx_flags flags,
-        	  struct dma_async_tx_descriptor *dependency,
-        	  dma_async_tx_callback callback_routine,
-		  void *callback_parameter);
+async_<operation>(<op specific parameters>, struct async_submit ctl *submit)
 
 3.2 Supported operations:
-memcpy       - memory copy between a source and a destination buffer
-memset       - fill a destination buffer with a byte value
-xor          - xor a series of source buffers and write the result to a
-	       destination buffer
-xor_zero_sum - xor a series of source buffers and set a flag if the
-	       result is zero.  The implementation attempts to prevent
-	       writes to memory
+memcpy  - memory copy between a source and a destination buffer
+memset  - fill a destination buffer with a byte value
+xor     - xor a series of source buffers and write the result to a
+	  destination buffer
+xor_val - xor a series of source buffers and set a flag if the
+	  result is zero.  The implementation attempts to prevent
+	  writes to memory
+pq	- generate the p+q (raid6 syndrome) from a series of source buffers
+pq_val  - validate that a p and or q buffer are in sync with a given series of
+	  sources
+datap	- (raid6_datap_recov) recover a raid6 data block and the p block
+	  from the given sources
+2data	- (raid6_2data_recov) recover 2 raid6 data blocks from the given
+	  sources
 
 3.3 Descriptor management:
 The return value is non-NULL and points to a 'descriptor' when the operation
@@ -80,8 +83,8 @@ acknowledged by the application before the offload engine driver is allowed to
 recycle (or free) the descriptor.  A descriptor can be acked by one of the
 following methods:
 1/ setting the ASYNC_TX_ACK flag if no child operations are to be submitted
-2/ setting the ASYNC_TX_DEP_ACK flag to acknowledge the parent
-   descriptor of a new operation.
+2/ submitting an unacknowledged descriptor as a dependency to another
+   async_tx call will implicitly set the acknowledged state.
 3/ calling async_tx_ack() on the descriptor.
 
 3.4 When does the operation execute?
@@ -119,30 +122,42 @@ of an operation.
 Perform a xor->copy->xor operation where each operation depends on the
 result from the previous operation:
 
-void complete_xor_copy_xor(void *param)
+void callback(void *param)
 {
-	printk("complete\n");
+	struct completion *cmp = param;
+
+	complete(cmp);
 }
 
-int run_xor_copy_xor(struct page **xor_srcs,
-		     int xor_src_cnt,
-		     struct page *xor_dest,
-		     size_t xor_len,
-		     struct page *copy_src,
-		     struct page *copy_dest,
-		     size_t copy_len)
+void run_xor_copy_xor(struct page **xor_srcs,
+		      int xor_src_cnt,
+		      struct page *xor_dest,
+		      size_t xor_len,
+		      struct page *copy_src,
+		      struct page *copy_dest,
+		      size_t copy_len)
 {
 	struct dma_async_tx_descriptor *tx;
+	addr_conv_t addr_conv[xor_src_cnt];
+	struct async_submit_ctl submit;
+	addr_conv_t addr_conv[NDISKS];
+	struct completion cmp;
+
+	init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL,
+			  addr_conv);
+	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit)
 
-	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
-		       ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL);
-	tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len,
-			  ASYNC_TX_DEP_ACK, tx, NULL, NULL);
-	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
-		       ASYNC_TX_XOR_DROP_DST | ASYNC_TX_DEP_ACK | ASYNC_TX_ACK,
-		       tx, complete_xor_copy_xor, NULL);
+	submit->depend_tx = tx;
+	tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, &submit);
+
+	init_completion(&cmp);
+	init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST | ASYNC_TX_ACK, tx,
+			  callback, &cmp, addr_conv);
+	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit);
 
 	async_tx_issue_pending_all();
+
+	wait_for_completion(&cmp);
 }
 
 See include/linux/async_tx.h for more information on the flags.  See the
diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h
index 83e6ba338e2..1a8c7279a28 100644
--- a/arch/arm/include/asm/hardware/iop3xx-adma.h
+++ b/arch/arm/include/asm/hardware/iop3xx-adma.h
@@ -187,11 +187,74 @@ union iop3xx_desc {
 	void *ptr;
 };
 
+/* No support for p+q operations */
+static inline int
+iop_chan_pq_slot_count(size_t len, int src_cnt, int *slots_per_op)
+{
+	BUG();
+	return 0;
+}
+
+static inline void
+iop_desc_init_pq(struct iop_adma_desc_slot *desc, int src_cnt,
+		  unsigned long flags)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_addr(struct iop_adma_desc_slot *desc, dma_addr_t *addr)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_src_addr(struct iop_adma_desc_slot *desc, int src_idx,
+			 dma_addr_t addr, unsigned char coef)
+{
+	BUG();
+}
+
+static inline int
+iop_chan_pq_zero_sum_slot_count(size_t len, int src_cnt, int *slots_per_op)
+{
+	BUG();
+	return 0;
+}
+
+static inline void
+iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
+			  unsigned long flags)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
+{
+	BUG();
+}
+
+#define iop_desc_set_pq_zero_sum_src_addr iop_desc_set_pq_src_addr
+
+static inline void
+iop_desc_set_pq_zero_sum_addr(struct iop_adma_desc_slot *desc, int pq_idx,
+			      dma_addr_t *src)
+{
+	BUG();
+}
+
 static inline int iop_adma_get_max_xor(void)
 {
 	return 32;
 }
 
+static inline int iop_adma_get_max_pq(void)
+{
+	BUG();
+	return 0;
+}
+
 static inline u32 iop_chan_get_current_descriptor(struct iop_adma_chan *chan)
 {
 	int id = chan->device->id;
@@ -332,6 +395,11 @@ static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt,
 	return slot_cnt;
 }
 
+static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
+{
+	return 0;
+}
+
 static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
@@ -349,6 +417,14 @@ static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
 	return 0;
 }
 
+
+static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
+					  struct iop_adma_chan *chan)
+{
+	BUG();
+	return 0;
+}
+
 static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
@@ -756,13 +832,14 @@ static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc,
 	hw_desc->src[0] = val;
 }
 
-static inline int iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
+static inline enum sum_check_flags
+iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
 {
 	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
 	struct iop3xx_aau_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field;
 
 	iop_paranoia(!(desc_ctrl.tx_complete && desc_ctrl.zero_result_en));
-	return desc_ctrl.zero_result_err;
+	return desc_ctrl.zero_result_err << SUM_CHECK_P;
 }
 
 static inline void iop_chan_append(struct iop_adma_chan *chan)
diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h
index 385c6e8cbbd..59b8c3892f7 100644
--- a/arch/arm/include/asm/hardware/iop_adma.h
+++ b/arch/arm/include/asm/hardware/iop_adma.h
@@ -86,6 +86,7 @@ struct iop_adma_chan {
  * @idx: pool index
  * @unmap_src_cnt: number of xor sources
  * @unmap_len: transaction bytecount
+ * @tx_list: list of descriptors that are associated with one operation
  * @async_tx: support for the async_tx api
  * @group_list: list of slots that make up a multi-descriptor transaction
  *	for example transfer lengths larger than the supported hw max
@@ -102,10 +103,12 @@ struct iop_adma_desc_slot {
 	u16 idx;
 	u16 unmap_src_cnt;
 	size_t unmap_len;
+	struct list_head tx_list;
 	struct dma_async_tx_descriptor async_tx;
 	union {
 		u32 *xor_check_result;
 		u32 *crc32_result;
+		u32 *pq_check_result;
 	};
 };
 
diff --git a/arch/arm/mach-iop13xx/include/mach/adma.h b/arch/arm/mach-iop13xx/include/mach/adma.h
index 5722e86f217..6d3782d85a9 100644
--- a/arch/arm/mach-iop13xx/include/mach/adma.h
+++ b/arch/arm/mach-iop13xx/include/mach/adma.h
@@ -150,6 +150,8 @@ static inline int iop_adma_get_max_xor(void)
 	return 16;
 }
 
+#define iop_adma_get_max_pq iop_adma_get_max_xor
+
 static inline u32 iop_chan_get_current_descriptor(struct iop_adma_chan *chan)
 {
 	return __raw_readl(ADMA_ADAR(chan));
@@ -211,7 +213,10 @@ iop_chan_xor_slot_count(size_t len, int src_cnt, int *slots_per_op)
 #define IOP_ADMA_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
 #define IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
 #define IOP_ADMA_XOR_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
+#define IOP_ADMA_PQ_MAX_BYTE_COUNT ADMA_MAX_BYTE_COUNT
 #define iop_chan_zero_sum_slot_count(l, s, o) iop_chan_xor_slot_count(l, s, o)
+#define iop_chan_pq_slot_count iop_chan_xor_slot_count
+#define iop_chan_pq_zero_sum_slot_count iop_chan_xor_slot_count
 
 static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
@@ -220,6 +225,13 @@ static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
 	return hw_desc->dest_addr;
 }
 
+static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
+					  struct iop_adma_chan *chan)
+{
+	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
+	return hw_desc->q_dest_addr;
+}
+
 static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
@@ -319,6 +331,58 @@ iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
 	return 1;
 }
 
+static inline void
+iop_desc_init_pq(struct iop_adma_desc_slot *desc, int src_cnt,
+		  unsigned long flags)
+{
+	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
+	union {
+		u32 value;
+		struct iop13xx_adma_desc_ctrl field;
+	} u_desc_ctrl;
+
+	u_desc_ctrl.value = 0;
+	u_desc_ctrl.field.src_select = src_cnt - 1;
+	u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
+	u_desc_ctrl.field.pq_xfer_en = 1;
+	u_desc_ctrl.field.p_xfer_dis = !!(flags & DMA_PREP_PQ_DISABLE_P);
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
+	hw_desc->desc_ctrl = u_desc_ctrl.value;
+}
+
+static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
+{
+	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
+	union {
+		u32 value;
+		struct iop13xx_adma_desc_ctrl field;
+	} u_desc_ctrl;
+
+	u_desc_ctrl.value = hw_desc->desc_ctrl;
+	return u_desc_ctrl.field.pq_xfer_en;
+}
+
+static inline void
+iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
+			  unsigned long flags)
+{
+	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
+	union {
+		u32 value;
+		struct iop13xx_adma_desc_ctrl field;
+	} u_desc_ctrl;
+
+	u_desc_ctrl.value = 0;
+	u_desc_ctrl.field.src_select = src_cnt - 1;
+	u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
+	u_desc_ctrl.field.zero_result = 1;
+	u_desc_ctrl.field.status_write_back_en = 1;
+	u_desc_ctrl.field.pq_xfer_en = 1;
+	u_desc_ctrl.field.p_xfer_dis = !!(flags & DMA_PREP_PQ_DISABLE_P);
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
+	hw_desc->desc_ctrl = u_desc_ctrl.value;
+}
+
 static inline void iop_desc_set_byte_count(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan,
 					u32 byte_count)
@@ -351,6 +415,7 @@ iop_desc_set_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
 	}
 }
 
+#define iop_desc_set_pq_zero_sum_byte_count iop_desc_set_zero_sum_byte_count
 
 static inline void iop_desc_set_dest_addr(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan,
@@ -361,6 +426,16 @@ static inline void iop_desc_set_dest_addr(struct iop_adma_desc_slot *desc,
 	hw_desc->upper_dest_addr = 0;
 }
 
+static inline void
+iop_desc_set_pq_addr(struct iop_adma_desc_slot *desc, dma_addr_t *addr)
+{
+	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
+
+	hw_desc->dest_addr = addr[0];
+	hw_desc->q_dest_addr = addr[1];
+	hw_desc->upper_dest_addr = 0;
+}
+
 static inline void iop_desc_set_memcpy_src_addr(struct iop_adma_desc_slot *desc,
 					dma_addr_t addr)
 {
@@ -389,6 +464,29 @@ static inline void iop_desc_set_xor_src_addr(struct iop_adma_desc_slot *desc,
 }
 
 static inline void
+iop_desc_set_pq_src_addr(struct iop_adma_desc_slot *desc, int src_idx,
+			 dma_addr_t addr, unsigned char coef)
+{
+	int slot_cnt = desc->slot_cnt, slots_per_op = desc->slots_per_op;
+	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc, *iter;
+	struct iop13xx_adma_src *src;
+	int i = 0;
+
+	do {
+		iter = iop_hw_desc_slot_idx(hw_desc, i);
+		src = &iter->src[src_idx];
+		src->src_addr = addr;
+		src->pq_upper_src_addr = 0;
+		src->pq_dmlt = coef;
+		slot_cnt -= slots_per_op;
+		if (slot_cnt) {
+			i += slots_per_op;
+			addr += IOP_ADMA_PQ_MAX_BYTE_COUNT;
+		}
+	} while (slot_cnt);
+}
+
+static inline void
 iop_desc_init_interrupt(struct iop_adma_desc_slot *desc,
 	struct iop_adma_chan *chan)
 {
@@ -399,6 +497,15 @@ iop_desc_init_interrupt(struct iop_adma_desc_slot *desc,
 }
 
 #define iop_desc_set_zero_sum_src_addr iop_desc_set_xor_src_addr
+#define iop_desc_set_pq_zero_sum_src_addr iop_desc_set_pq_src_addr
+
+static inline void
+iop_desc_set_pq_zero_sum_addr(struct iop_adma_desc_slot *desc, int pq_idx,
+			      dma_addr_t *src)
+{
+	iop_desc_set_xor_src_addr(desc, pq_idx, src[pq_idx]);
+	iop_desc_set_xor_src_addr(desc, pq_idx+1, src[pq_idx+1]);
+}
 
 static inline void iop_desc_set_next_desc(struct iop_adma_desc_slot *desc,
 					u32 next_desc_addr)
@@ -428,18 +535,20 @@ static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc,
 	hw_desc->block_fill_data = val;
 }
 
-static inline int iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
+static inline enum sum_check_flags
+iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
 {
 	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
 	struct iop13xx_adma_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field;
 	struct iop13xx_adma_byte_count byte_count = hw_desc->byte_count_field;
+	enum sum_check_flags flags;
 
 	BUG_ON(!(byte_count.tx_complete && desc_ctrl.zero_result));
 
-	if (desc_ctrl.pq_xfer_en)
-		return byte_count.zero_result_err_q;
-	else
-		return byte_count.zero_result_err;
+	flags = byte_count.zero_result_err_q << SUM_CHECK_Q;
+	flags |= byte_count.zero_result_err << SUM_CHECK_P;
+
+	return flags;
 }
 
 static inline void iop_chan_append(struct iop_adma_chan *chan)
diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c
index bee42c609df..5c147fb66a0 100644
--- a/arch/arm/mach-iop13xx/setup.c
+++ b/arch/arm/mach-iop13xx/setup.c
@@ -477,10 +477,8 @@ void __init iop13xx_platform_init(void)
 			plat_data = &iop13xx_adma_0_data;
 			dma_cap_set(DMA_MEMCPY, plat_data->cap_mask);
 			dma_cap_set(DMA_XOR, plat_data->cap_mask);
-			dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask);
-			dma_cap_set(DMA_ZERO_SUM, plat_data->cap_mask);
+			dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask);
 			dma_cap_set(DMA_MEMSET, plat_data->cap_mask);
-			dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask);
 			dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask);
 			break;
 		case IOP13XX_INIT_ADMA_1:
@@ -489,10 +487,8 @@ void __init iop13xx_platform_init(void)
 			plat_data = &iop13xx_adma_1_data;
 			dma_cap_set(DMA_MEMCPY, plat_data->cap_mask);
 			dma_cap_set(DMA_XOR, plat_data->cap_mask);
-			dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask);
-			dma_cap_set(DMA_ZERO_SUM, plat_data->cap_mask);
+			dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask);
 			dma_cap_set(DMA_MEMSET, plat_data->cap_mask);
-			dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask);
 			dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask);
 			break;
 		case IOP13XX_INIT_ADMA_2:
@@ -501,14 +497,11 @@ void __init iop13xx_platform_init(void)
 			plat_data = &iop13xx_adma_2_data;
 			dma_cap_set(DMA_MEMCPY, plat_data->cap_mask);
 			dma_cap_set(DMA_XOR, plat_data->cap_mask);
-			dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask);
-			dma_cap_set(DMA_ZERO_SUM, plat_data->cap_mask);
+			dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask);
 			dma_cap_set(DMA_MEMSET, plat_data->cap_mask);
-			dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask);
 			dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask);
-			dma_cap_set(DMA_PQ_XOR, plat_data->cap_mask);
-			dma_cap_set(DMA_PQ_UPDATE, plat_data->cap_mask);
-			dma_cap_set(DMA_PQ_ZERO_SUM, plat_data->cap_mask);
+			dma_cap_set(DMA_PQ, plat_data->cap_mask);
+			dma_cap_set(DMA_PQ_VAL, plat_data->cap_mask);
 			break;
 		}
 	}
diff --git a/arch/arm/plat-iop/adma.c b/arch/arm/plat-iop/adma.c
index 3c127aabe21..1ff6a37e893 100644
--- a/arch/arm/plat-iop/adma.c
+++ b/arch/arm/plat-iop/adma.c
@@ -179,7 +179,6 @@ static int __init iop3xx_adma_cap_init(void)
 	dma_cap_set(DMA_INTERRUPT, iop3xx_dma_0_data.cap_mask);
 	#else
 	dma_cap_set(DMA_MEMCPY, iop3xx_dma_0_data.cap_mask);
-	dma_cap_set(DMA_MEMCPY_CRC32C, iop3xx_dma_0_data.cap_mask);
 	dma_cap_set(DMA_INTERRUPT, iop3xx_dma_0_data.cap_mask);
 	#endif
 
@@ -188,7 +187,6 @@ static int __init iop3xx_adma_cap_init(void)
 	dma_cap_set(DMA_INTERRUPT, iop3xx_dma_1_data.cap_mask);
 	#else
 	dma_cap_set(DMA_MEMCPY, iop3xx_dma_1_data.cap_mask);
-	dma_cap_set(DMA_MEMCPY_CRC32C, iop3xx_dma_1_data.cap_mask);
 	dma_cap_set(DMA_INTERRUPT, iop3xx_dma_1_data.cap_mask);
 	#endif
 
@@ -198,7 +196,7 @@ static int __init iop3xx_adma_cap_init(void)
 	dma_cap_set(DMA_INTERRUPT, iop3xx_aau_data.cap_mask);
 	#else
 	dma_cap_set(DMA_XOR, iop3xx_aau_data.cap_mask);
-	dma_cap_set(DMA_ZERO_SUM, iop3xx_aau_data.cap_mask);
+	dma_cap_set(DMA_XOR_VAL, iop3xx_aau_data.cap_mask);
 	dma_cap_set(DMA_MEMSET, iop3xx_aau_data.cap_mask);
 	dma_cap_set(DMA_INTERRUPT, iop3xx_aau_data.cap_mask);
 	#endif
diff --git a/arch/powerpc/include/asm/fsldma.h b/arch/powerpc/include/asm/fsldma.h
new file mode 100644
index 00000000000..a67aeed17d4
--- /dev/null
+++ b/arch/powerpc/include/asm/fsldma.h
@@ -0,0 +1,136 @@
+/*
+ * Freescale MPC83XX / MPC85XX DMA Controller
+ *
+ * Copyright (c) 2009 Ira W. Snyder <iws@ovro.caltech.edu>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ARCH_POWERPC_ASM_FSLDMA_H__
+#define __ARCH_POWERPC_ASM_FSLDMA_H__
+
+#include <linux/dmaengine.h>
+
+/*
+ * Definitions for the Freescale DMA controller's DMA_SLAVE implemention
+ *
+ * The Freescale DMA_SLAVE implementation was designed to handle many-to-many
+ * transfers. An example usage would be an accelerated copy between two
+ * scatterlists. Another example use would be an accelerated copy from
+ * multiple non-contiguous device buffers into a single scatterlist.
+ *
+ * A DMA_SLAVE transaction is defined by a struct fsl_dma_slave. This
+ * structure contains a list of hardware addresses that should be copied
+ * to/from the scatterlist passed into device_prep_slave_sg(). The structure
+ * also has some fields to enable hardware-specific features.
+ */
+
+/**
+ * struct fsl_dma_hw_addr
+ * @entry: linked list entry
+ * @address: the hardware address
+ * @length: length to transfer
+ *
+ * Holds a single physical hardware address / length pair for use
+ * with the DMAEngine DMA_SLAVE API.
+ */
+struct fsl_dma_hw_addr {
+	struct list_head entry;
+
+	dma_addr_t address;
+	size_t length;
+};
+
+/**
+ * struct fsl_dma_slave
+ * @addresses: a linked list of struct fsl_dma_hw_addr structures
+ * @request_count: value for DMA request count
+ * @src_loop_size: setup and enable constant source-address DMA transfers
+ * @dst_loop_size: setup and enable constant destination address DMA transfers
+ * @external_start: enable externally started DMA transfers
+ * @external_pause: enable externally paused DMA transfers
+ *
+ * Holds a list of address / length pairs for use with the DMAEngine
+ * DMA_SLAVE API implementation for the Freescale DMA controller.
+ */
+struct fsl_dma_slave {
+
+	/* List of hardware address/length pairs */
+	struct list_head addresses;
+
+	/* Support for extra controller features */
+	unsigned int request_count;
+	unsigned int src_loop_size;
+	unsigned int dst_loop_size;
+	bool external_start;
+	bool external_pause;
+};
+
+/**
+ * fsl_dma_slave_append - add an address/length pair to a struct fsl_dma_slave
+ * @slave: the &struct fsl_dma_slave to add to
+ * @address: the hardware address to add
+ * @length: the length of bytes to transfer from @address
+ *
+ * Add a hardware address/length pair to a struct fsl_dma_slave. Returns 0 on
+ * success, -ERRNO otherwise.
+ */
+static inline int fsl_dma_slave_append(struct fsl_dma_slave *slave,
+				       dma_addr_t address, size_t length)
+{
+	struct fsl_dma_hw_addr *addr;
+
+	addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
+	if (!addr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&addr->entry);
+	addr->address = address;
+	addr->length = length;
+
+	list_add_tail(&addr->entry, &slave->addresses);
+	return 0;
+}
+
+/**
+ * fsl_dma_slave_free - free a struct fsl_dma_slave
+ * @slave: the struct fsl_dma_slave to free
+ *
+ * Free a struct fsl_dma_slave and all associated address/length pairs
+ */
+static inline void fsl_dma_slave_free(struct fsl_dma_slave *slave)
+{
+	struct fsl_dma_hw_addr *addr, *tmp;
+
+	if (slave) {
+		list_for_each_entry_safe(addr, tmp, &slave->addresses, entry) {
+			list_del(&addr->entry);
+			kfree(addr);
+		}
+
+		kfree(slave);
+	}
+}
+
+/**
+ * fsl_dma_slave_alloc - allocate a struct fsl_dma_slave
+ * @gfp: the flags to pass to kmalloc when allocating this structure
+ *
+ * Allocate a struct fsl_dma_slave for use by the DMA_SLAVE API. Returns a new
+ * struct fsl_dma_slave on success, or NULL on failure.
+ */
+static inline struct fsl_dma_slave *fsl_dma_slave_alloc(gfp_t gfp)
+{
+	struct fsl_dma_slave *slave;
+
+	slave = kzalloc(sizeof(*slave), gfp);
+	if (!slave)
+		return NULL;
+
+	INIT_LIST_HEAD(&slave->addresses);
+	return slave;
+}
+
+#endif /* __ARCH_POWERPC_ASM_FSLDMA_H__ */
diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig
index b91fa8dbf04..4d58eb0973d 100644
--- a/arch/sh/drivers/dma/Kconfig
+++ b/arch/sh/drivers/dma/Kconfig
@@ -1,12 +1,9 @@
 menu "DMA support"
 
-config SH_DMA_API
-	bool
 
 config SH_DMA
 	bool "SuperH on-chip DMA controller (DMAC) support"
 	depends on CPU_SH3 || CPU_SH4
-	select SH_DMA_API
 	default n
 
 config SH_DMA_IRQ_MULTI
@@ -19,6 +16,15 @@ config SH_DMA_IRQ_MULTI
 		     CPU_SUBTYPE_SH7780  || CPU_SUBTYPE_SH7785  || \
 		     CPU_SUBTYPE_SH7760
 
+config SH_DMA_API
+	depends on SH_DMA
+	bool "SuperH DMA API support"
+	default n
+	help
+	  SH_DMA_API always enabled DMA API of used SuperH.
+	  If you want to use DMA ENGINE, you must not enable this.
+	  Please enable DMA_ENGINE and SH_DMAE.
+
 config NR_ONCHIP_DMA_CHANNELS
 	int
 	depends on SH_DMA
diff --git a/arch/sh/drivers/dma/Makefile b/arch/sh/drivers/dma/Makefile
index c6068137b46..d88c9484762 100644
--- a/arch/sh/drivers/dma/Makefile
+++ b/arch/sh/drivers/dma/Makefile
@@ -2,8 +2,7 @@
 # Makefile for the SuperH DMA specific kernel interface routines under Linux.
 #
 
-obj-$(CONFIG_SH_DMA_API)	+= dma-api.o dma-sysfs.o
-obj-$(CONFIG_SH_DMA)		+= dma-sh.o
+obj-$(CONFIG_SH_DMA_API)	+= dma-sh.o dma-api.o dma-sysfs.o
 obj-$(CONFIG_PVR2_DMA)		+= dma-pvr2.o
 obj-$(CONFIG_G2_DMA)		+= dma-g2.o
 obj-$(CONFIG_SH_DMABRG)		+= dmabrg.o
diff --git a/arch/sh/include/asm/dma-sh.h b/arch/sh/include/asm/dma-sh.h
index 68a5f4cb034..78eed3e0bdf 100644
--- a/arch/sh/include/asm/dma-sh.h
+++ b/arch/sh/include/asm/dma-sh.h
@@ -116,4 +116,17 @@ static u32 dma_base_addr[] __maybe_unused = {
 #define CHCR    0x0C
 #define DMAOR	0x40
 
+/*
+ * for dma engine
+ *
+ * SuperH DMA mode
+ */
+#define SHDMA_MIX_IRQ	(1 << 1)
+#define SHDMA_DMAOR1	(1 << 2)
+#define SHDMA_DMAE1		(1 << 3)
+
+struct sh_dmae_pdata {
+	unsigned int mode;
+};
+
 #endif /* __DMA_SH_H */
diff --git a/crypto/async_tx/Kconfig b/crypto/async_tx/Kconfig
index d8fb3914598..e5aeb2b79e6 100644
--- a/crypto/async_tx/Kconfig
+++ b/crypto/async_tx/Kconfig
@@ -14,3 +14,12 @@ config ASYNC_MEMSET
 	tristate
 	select ASYNC_CORE
 
+config ASYNC_PQ
+	tristate
+	select ASYNC_CORE
+
+config ASYNC_RAID6_RECOV
+	tristate
+	select ASYNC_CORE
+	select ASYNC_PQ
+
diff --git a/crypto/async_tx/Makefile b/crypto/async_tx/Makefile
index 27baa7d52fb..d1e0e6f72bc 100644
--- a/crypto/async_tx/Makefile
+++ b/crypto/async_tx/Makefile
@@ -2,3 +2,6 @@ obj-$(CONFIG_ASYNC_CORE) += async_tx.o
 obj-$(CONFIG_ASYNC_MEMCPY) += async_memcpy.o
 obj-$(CONFIG_ASYNC_MEMSET) += async_memset.o
 obj-$(CONFIG_ASYNC_XOR) += async_xor.o
+obj-$(CONFIG_ASYNC_PQ) += async_pq.o
+obj-$(CONFIG_ASYNC_RAID6_RECOV) += async_raid6_recov.o
+obj-$(CONFIG_ASYNC_RAID6_TEST) += raid6test.o
diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index ddccfb01c41..0ec1fb69d4e 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -33,28 +33,31 @@
  * async_memcpy - attempt to copy memory with a dma engine.
  * @dest: destination page
  * @src: src page
- * @offset: offset in pages to start transaction
+ * @dest_offset: offset into 'dest' to start transaction
+ * @src_offset: offset into 'src' to start transaction
  * @len: length in bytes
- * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK,
- * @depend_tx: memcpy depends on the result of this transaction
- * @cb_fn: function to call when the memcpy completes
- * @cb_param: parameter to pass to the callback routine
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK
  */
 struct dma_async_tx_descriptor *
 async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
-	unsigned int src_offset, size_t len, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_param)
+	     unsigned int src_offset, size_t len,
+	     struct async_submit_ctl *submit)
 {
-	struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMCPY,
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMCPY,
 						      &dest, 1, &src, 1, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
 
-	if (device) {
+	if (device && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
 		dma_addr_t dma_dest, dma_src;
-		unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
+		unsigned long dma_prep_flags = 0;
 
+		if (submit->cb_fn)
+			dma_prep_flags |= DMA_PREP_INTERRUPT;
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_prep_flags |= DMA_PREP_FENCE;
 		dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
 					DMA_FROM_DEVICE);
 
@@ -67,13 +70,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 
 	if (tx) {
 		pr_debug("%s: (async) len: %zu\n", __func__, len);
-		async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
+		async_tx_submit(chan, tx, submit);
 	} else {
 		void *dest_buf, *src_buf;
 		pr_debug("%s: (sync) len: %zu\n", __func__, len);
 
 		/* wait for any prerequisite operations */
-		async_tx_quiesce(&depend_tx);
+		async_tx_quiesce(&submit->depend_tx);
 
 		dest_buf = kmap_atomic(dest, KM_USER0) + dest_offset;
 		src_buf = kmap_atomic(src, KM_USER1) + src_offset;
@@ -83,26 +86,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 		kunmap_atomic(dest_buf, KM_USER0);
 		kunmap_atomic(src_buf, KM_USER1);
 
-		async_tx_sync_epilog(cb_fn, cb_param);
+		async_tx_sync_epilog(submit);
 	}
 
 	return tx;
 }
 EXPORT_SYMBOL_GPL(async_memcpy);
 
-static int __init async_memcpy_init(void)
-{
-	return 0;
-}
-
-static void __exit async_memcpy_exit(void)
-{
-	do { } while (0);
-}
-
-module_init(async_memcpy_init);
-module_exit(async_memcpy_exit);
-
 MODULE_AUTHOR("Intel Corporation");
 MODULE_DESCRIPTION("asynchronous memcpy api");
 MODULE_LICENSE("GPL");
diff --git a/crypto/async_tx/async_memset.c b/crypto/async_tx/async_memset.c
index 5b5eb99bb24..58e4a8752ae 100644
--- a/crypto/async_tx/async_memset.c
+++ b/crypto/async_tx/async_memset.c
@@ -35,26 +35,26 @@
  * @val: fill value
  * @offset: offset in pages to start transaction
  * @len: length in bytes
- * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
- * @depend_tx: memset depends on the result of this transaction
- * @cb_fn: function to call when the memcpy completes
- * @cb_param: parameter to pass to the callback routine
+ *
+ * honored flags: ASYNC_TX_ACK
  */
 struct dma_async_tx_descriptor *
-async_memset(struct page *dest, int val, unsigned int offset,
-	size_t len, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_param)
+async_memset(struct page *dest, int val, unsigned int offset, size_t len,
+	     struct async_submit_ctl *submit)
 {
-	struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMSET,
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMSET,
 						      &dest, 1, NULL, 0, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
 
-	if (device) {
+	if (device && is_dma_fill_aligned(device, offset, 0, len)) {
 		dma_addr_t dma_dest;
-		unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
+		unsigned long dma_prep_flags = 0;
 
+		if (submit->cb_fn)
+			dma_prep_flags |= DMA_PREP_INTERRUPT;
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_prep_flags |= DMA_PREP_FENCE;
 		dma_dest = dma_map_page(device->dev, dest, offset, len,
 					DMA_FROM_DEVICE);
 
@@ -64,38 +64,25 @@ async_memset(struct page *dest, int val, unsigned int offset,
 
 	if (tx) {
 		pr_debug("%s: (async) len: %zu\n", __func__, len);
-		async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
+		async_tx_submit(chan, tx, submit);
 	} else { /* run the memset synchronously */
 		void *dest_buf;
 		pr_debug("%s: (sync) len: %zu\n", __func__, len);
 
-		dest_buf = (void *) (((char *) page_address(dest)) + offset);
+		dest_buf = page_address(dest) + offset;
 
 		/* wait for any prerequisite operations */
-		async_tx_quiesce(&depend_tx);
+		async_tx_quiesce(&submit->depend_tx);
 
 		memset(dest_buf, val, len);
 
-		async_tx_sync_epilog(cb_fn, cb_param);
+		async_tx_sync_epilog(submit);
 	}
 
 	return tx;
 }
 EXPORT_SYMBOL_GPL(async_memset);
 
-static int __init async_memset_init(void)
-{
-	return 0;
-}
-
-static void __exit async_memset_exit(void)
-{
-	do { } while (0);
-}
-
-module_init(async_memset_init);
-module_exit(async_memset_exit);
-
 MODULE_AUTHOR("Intel Corporation");
 MODULE_DESCRIPTION("asynchronous memset api");
 MODULE_LICENSE("GPL");
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
new file mode 100644
index 00000000000..b88db6d1dc6
--- /dev/null
+++ b/crypto/async_tx/async_pq.c
@@ -0,0 +1,395 @@
+/*
+ * Copyright(c) 2007 Yuri Tikhonov <yur@emcraft.com>
+ * Copyright(c) 2009 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
+ */
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
+#include <linux/raid/pq.h>
+#include <linux/async_tx.h>
+
+/**
+ * scribble - space to hold throwaway P buffer for synchronous gen_syndrome
+ */
+static struct page *scribble;
+
+static bool is_raid6_zero_block(struct page *p)
+{
+	return p == (void *) raid6_empty_zero_page;
+}
+
+/* the struct page *blocks[] parameter passed to async_gen_syndrome()
+ * and async_syndrome_val() contains the 'P' destination address at
+ * blocks[disks-2] and the 'Q' destination address at blocks[disks-1]
+ *
+ * note: these are macros as they are used as lvalues
+ */
+#define P(b, d) (b[d-2])
+#define Q(b, d) (b[d-1])
+
+/**
+ * do_async_gen_syndrome - asynchronously calculate P and/or Q
+ */
+static __async_inline struct dma_async_tx_descriptor *
+do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
+		      const unsigned char *scfs, unsigned int offset, int disks,
+		      size_t len, dma_addr_t *dma_src,
+		      struct async_submit_ctl *submit)
+{
+	struct dma_async_tx_descriptor *tx = NULL;
+	struct dma_device *dma = chan->device;
+	enum dma_ctrl_flags dma_flags = 0;
+	enum async_tx_flags flags_orig = submit->flags;
+	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
+	dma_async_tx_callback cb_param_orig = submit->cb_param;
+	int src_cnt = disks - 2;
+	unsigned char coefs[src_cnt];
+	unsigned short pq_src_cnt;
+	dma_addr_t dma_dest[2];
+	int src_off = 0;
+	int idx;
+	int i;
+
+	/* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */
+	if (P(blocks, disks))
+		dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset,
+					   len, DMA_BIDIRECTIONAL);
+	else
+		dma_flags |= DMA_PREP_PQ_DISABLE_P;
+	if (Q(blocks, disks))
+		dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset,
+					   len, DMA_BIDIRECTIONAL);
+	else
+		dma_flags |= DMA_PREP_PQ_DISABLE_Q;
+
+	/* convert source addresses being careful to collapse 'empty'
+	 * sources and update the coefficients accordingly
+	 */
+	for (i = 0, idx = 0; i < src_cnt; i++) {
+		if (is_raid6_zero_block(blocks[i]))
+			continue;
+		dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len,
+					    DMA_TO_DEVICE);
+		coefs[idx] = scfs[i];
+		idx++;
+	}
+	src_cnt = idx;
+
+	while (src_cnt > 0) {
+		submit->flags = flags_orig;
+		pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
+		/* if we are submitting additional pqs, leave the chain open,
+		 * clear the callback parameters, and leave the destination
+		 * buffers mapped
+		 */
+		if (src_cnt > pq_src_cnt) {
+			submit->flags &= ~ASYNC_TX_ACK;
+			submit->flags |= ASYNC_TX_FENCE;
+			dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP;
+			submit->cb_fn = NULL;
+			submit->cb_param = NULL;
+		} else {
+			dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP;
+			submit->cb_fn = cb_fn_orig;
+			submit->cb_param = cb_param_orig;
+			if (cb_fn_orig)
+				dma_flags |= DMA_PREP_INTERRUPT;
+		}
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_flags |= DMA_PREP_FENCE;
+
+		/* Since we have clobbered the src_list we are committed
+		 * to doing this asynchronously.  Drivers force forward
+		 * progress in case they can not provide a descriptor
+		 */
+		for (;;) {
+			tx = dma->device_prep_dma_pq(chan, dma_dest,
+						     &dma_src[src_off],
+						     pq_src_cnt,
+						     &coefs[src_off], len,
+						     dma_flags);
+			if (likely(tx))
+				break;
+			async_tx_quiesce(&submit->depend_tx);
+			dma_async_issue_pending(chan);
+		}
+
+		async_tx_submit(chan, tx, submit);
+		submit->depend_tx = tx;
+
+		/* drop completed sources */
+		src_cnt -= pq_src_cnt;
+		src_off += pq_src_cnt;
+
+		dma_flags |= DMA_PREP_CONTINUE;
+	}
+
+	return tx;
+}
+
+/**
+ * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
+ */
+static void
+do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+		     size_t len, struct async_submit_ctl *submit)
+{
+	void **srcs;
+	int i;
+
+	if (submit->scribble)
+		srcs = submit->scribble;
+	else
+		srcs = (void **) blocks;
+
+	for (i = 0; i < disks; i++) {
+		if (is_raid6_zero_block(blocks[i])) {
+			BUG_ON(i > disks - 3); /* P or Q can't be zero */
+			srcs[i] = blocks[i];
+		} else
+			srcs[i] = page_address(blocks[i]) + offset;
+	}
+	raid6_call.gen_syndrome(disks, len, srcs);
+	async_tx_sync_epilog(submit);
+}
+
+/**
+ * async_gen_syndrome - asynchronously calculate a raid6 syndrome
+ * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
+ * @offset: common offset into each block (src and dest) to start transaction
+ * @disks: number of blocks (including missing P or Q, see below)
+ * @len: length of operation in bytes
+ * @submit: submission/completion modifiers
+ *
+ * General note: This routine assumes a field of GF(2^8) with a
+ * primitive polynomial of 0x11d and a generator of {02}.
+ *
+ * 'disks' note: callers can optionally omit either P or Q (but not
+ * both) from the calculation by setting blocks[disks-2] or
+ * blocks[disks-1] to NULL.  When P or Q is omitted 'len' must be <=
+ * PAGE_SIZE as a temporary buffer of this size is used in the
+ * synchronous path.  'disks' always accounts for both destination
+ * buffers.
+ *
+ * 'blocks' note: if submit->scribble is NULL then the contents of
+ * 'blocks' may be overridden
+ */
+struct dma_async_tx_descriptor *
+async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+		   size_t len, struct async_submit_ctl *submit)
+{
+	int src_cnt = disks - 2;
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
+						      &P(blocks, disks), 2,
+						      blocks, src_cnt, len);
+	struct dma_device *device = chan ? chan->device : NULL;
+	dma_addr_t *dma_src = NULL;
+
+	BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
+
+	if (submit->scribble)
+		dma_src = submit->scribble;
+	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
+		dma_src = (dma_addr_t *) blocks;
+
+	if (dma_src && device &&
+	    (src_cnt <= dma_maxpq(device, 0) ||
+	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
+	    is_dma_pq_aligned(device, offset, 0, len)) {
+		/* run the p+q asynchronously */
+		pr_debug("%s: (async) disks: %d len: %zu\n",
+			 __func__, disks, len);
+		return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset,
+					     disks, len, dma_src, submit);
+	}
+
+	/* run the pq synchronously */
+	pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len);
+
+	/* wait for any prerequisite operations */
+	async_tx_quiesce(&submit->depend_tx);
+
+	if (!P(blocks, disks)) {
+		P(blocks, disks) = scribble;
+		BUG_ON(len + offset > PAGE_SIZE);
+	}
+	if (!Q(blocks, disks)) {
+		Q(blocks, disks) = scribble;
+		BUG_ON(len + offset > PAGE_SIZE);
+	}
+	do_sync_gen_syndrome(blocks, offset, disks, len, submit);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(async_gen_syndrome);
+
+/**
+ * async_syndrome_val - asynchronously validate a raid6 syndrome
+ * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
+ * @offset: common offset into each block (src and dest) to start transaction
+ * @disks: number of blocks (including missing P or Q, see below)
+ * @len: length of operation in bytes
+ * @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
+ * @spare: temporary result buffer for the synchronous case
+ * @submit: submission / completion modifiers
+ *
+ * The same notes from async_gen_syndrome apply to the 'blocks',
+ * and 'disks' parameters of this routine.  The synchronous path
+ * requires a temporary result buffer and submit->scribble to be
+ * specified.
+ */
+struct dma_async_tx_descriptor *
+async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
+		   size_t len, enum sum_check_flags *pqres, struct page *spare,
+		   struct async_submit_ctl *submit)
+{
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ_VAL,
+						      NULL, 0,  blocks, disks,
+						      len);
+	struct dma_device *device = chan ? chan->device : NULL;
+	struct dma_async_tx_descriptor *tx;
+	enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
+	dma_addr_t *dma_src = NULL;
+
+	BUG_ON(disks < 4);
+
+	if (submit->scribble)
+		dma_src = submit->scribble;
+	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
+		dma_src = (dma_addr_t *) blocks;
+
+	if (dma_src && device && disks <= dma_maxpq(device, 0) &&
+	    is_dma_pq_aligned(device, offset, 0, len)) {
+		struct device *dev = device->dev;
+		dma_addr_t *pq = &dma_src[disks-2];
+		int i;
+
+		pr_debug("%s: (async) disks: %d len: %zu\n",
+			 __func__, disks, len);
+		if (!P(blocks, disks))
+			dma_flags |= DMA_PREP_PQ_DISABLE_P;
+		if (!Q(blocks, disks))
+			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_flags |= DMA_PREP_FENCE;
+		for (i = 0; i < disks; i++)
+			if (likely(blocks[i])) {
+				BUG_ON(is_raid6_zero_block(blocks[i]));
+				dma_src[i] = dma_map_page(dev, blocks[i],
+							  offset, len,
+							  DMA_TO_DEVICE);
+			}
+
+		for (;;) {
+			tx = device->device_prep_dma_pq_val(chan, pq, dma_src,
+							    disks - 2,
+							    raid6_gfexp,
+							    len, pqres,
+							    dma_flags);
+			if (likely(tx))
+				break;
+			async_tx_quiesce(&submit->depend_tx);
+			dma_async_issue_pending(chan);
+		}
+		async_tx_submit(chan, tx, submit);
+
+		return tx;
+	} else {
+		struct page *p_src = P(blocks, disks);
+		struct page *q_src = Q(blocks, disks);
+		enum async_tx_flags flags_orig = submit->flags;
+		dma_async_tx_callback cb_fn_orig = submit->cb_fn;
+		void *scribble = submit->scribble;
+		void *cb_param_orig = submit->cb_param;
+		void *p, *q, *s;
+
+		pr_debug("%s: (sync) disks: %d len: %zu\n",
+			 __func__, disks, len);
+
+		/* caller must provide a temporary result buffer and
+		 * allow the input parameters to be preserved
+		 */
+		BUG_ON(!spare || !scribble);
+
+		/* wait for any prerequisite operations */
+		async_tx_quiesce(&submit->depend_tx);
+
+		/* recompute p and/or q into the temporary buffer and then
+		 * check to see the result matches the current value
+		 */
+		tx = NULL;
+		*pqres = 0;
+		if (p_src) {
+			init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
+					  NULL, NULL, scribble);
+			tx = async_xor(spare, blocks, offset, disks-2, len, submit);
+			async_tx_quiesce(&tx);
+			p = page_address(p_src) + offset;
+			s = page_address(spare) + offset;
+			*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
+		}
+
+		if (q_src) {
+			P(blocks, disks) = NULL;
+			Q(blocks, disks) = spare;
+			init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
+			tx = async_gen_syndrome(blocks, offset, disks, len, submit);
+			async_tx_quiesce(&tx);
+			q = page_address(q_src) + offset;
+			s = page_address(spare) + offset;
+			*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
+		}
+
+		/* restore P, Q and submit */
+		P(blocks, disks) = p_src;
+		Q(blocks, disks) = q_src;
+
+		submit->cb_fn = cb_fn_orig;
+		submit->cb_param = cb_param_orig;
+		submit->flags = flags_orig;
+		async_tx_sync_epilog(submit);
+
+		return NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(async_syndrome_val);
+
+static int __init async_pq_init(void)
+{
+	scribble = alloc_page(GFP_KERNEL);
+
+	if (scribble)
+		return 0;
+
+	pr_err("%s: failed to allocate required spare page\n", __func__);
+
+	return -ENOMEM;
+}
+
+static void __exit async_pq_exit(void)
+{
+	put_page(scribble);
+}
+
+module_init(async_pq_init);
+module_exit(async_pq_exit);
+
+MODULE_DESCRIPTION("asynchronous raid6 syndrome generation/validation");
+MODULE_LICENSE("GPL");
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
new file mode 100644
index 00000000000..6d73dde4786
--- /dev/null
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -0,0 +1,468 @@
+/*
+ * Asynchronous RAID-6 recovery calculations ASYNC_TX API.
+ * Copyright(c) 2009 Intel Corporation
+ *
+ * based on raid6recov.c:
+ *   Copyright 2002 H. Peter Anvin
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 51
+ * Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
+#include <linux/raid/pq.h>
+#include <linux/async_tx.h>
+
+static struct dma_async_tx_descriptor *
+async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
+		  size_t len, struct async_submit_ctl *submit)
+{
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
+						      &dest, 1, srcs, 2, len);
+	struct dma_device *dma = chan ? chan->device : NULL;
+	const u8 *amul, *bmul;
+	u8 ax, bx;
+	u8 *a, *b, *c;
+
+	if (dma) {
+		dma_addr_t dma_dest[2];
+		dma_addr_t dma_src[2];
+		struct device *dev = dma->dev;
+		struct dma_async_tx_descriptor *tx;
+		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
+
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_flags |= DMA_PREP_FENCE;
+		dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		dma_src[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
+		dma_src[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
+		tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 2, coef,
+					     len, dma_flags);
+		if (tx) {
+			async_tx_submit(chan, tx, submit);
+			return tx;
+		}
+
+		/* could not get a descriptor, unmap and fall through to
+		 * the synchronous path
+		 */
+		dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
+		dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
+		dma_unmap_page(dev, dma_src[1], len, DMA_TO_DEVICE);
+	}
+
+	/* run the operation synchronously */
+	async_tx_quiesce(&submit->depend_tx);
+	amul = raid6_gfmul[coef[0]];
+	bmul = raid6_gfmul[coef[1]];
+	a = page_address(srcs[0]);
+	b = page_address(srcs[1]);
+	c = page_address(dest);
+
+	while (len--) {
+		ax    = amul[*a++];
+		bx    = bmul[*b++];
+		*c++ = ax ^ bx;
+	}
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *
+async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
+	   struct async_submit_ctl *submit)
+{
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
+						      &dest, 1, &src, 1, len);
+	struct dma_device *dma = chan ? chan->device : NULL;
+	const u8 *qmul; /* Q multiplier table */
+	u8 *d, *s;
+
+	if (dma) {
+		dma_addr_t dma_dest[2];
+		dma_addr_t dma_src[1];
+		struct device *dev = dma->dev;
+		struct dma_async_tx_descriptor *tx;
+		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
+
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_flags |= DMA_PREP_FENCE;
+		dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		dma_src[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
+		tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 1, &coef,
+					     len, dma_flags);
+		if (tx) {
+			async_tx_submit(chan, tx, submit);
+			return tx;
+		}
+
+		/* could not get a descriptor, unmap and fall through to
+		 * the synchronous path
+		 */
+		dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
+		dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
+	}
+
+	/* no channel available, or failed to allocate a descriptor, so
+	 * perform the operation synchronously
+	 */
+	async_tx_quiesce(&submit->depend_tx);
+	qmul  = raid6_gfmul[coef];
+	d = page_address(dest);
+	s = page_address(src);
+
+	while (len--)
+		*d++ = qmul[*s++];
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *
+__2data_recov_4(size_t bytes, int faila, int failb, struct page **blocks,
+	      struct async_submit_ctl *submit)
+{
+	struct dma_async_tx_descriptor *tx = NULL;
+	struct page *p, *q, *a, *b;
+	struct page *srcs[2];
+	unsigned char coef[2];
+	enum async_tx_flags flags = submit->flags;
+	dma_async_tx_callback cb_fn = submit->cb_fn;
+	void *cb_param = submit->cb_param;
+	void *scribble = submit->scribble;
+
+	p = blocks[4-2];
+	q = blocks[4-1];
+
+	a = blocks[faila];
+	b = blocks[failb];
+
+	/* in the 4 disk case P + Pxy == P and Q + Qxy == Q */
+	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
+	srcs[0] = p;
+	srcs[1] = q;
+	coef[0] = raid6_gfexi[failb-faila];
+	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
+	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
+	tx = async_sum_product(b, srcs, coef, bytes, submit);
+
+	/* Dy = P+Pxy+Dx */
+	srcs[0] = p;
+	srcs[1] = b;
+	init_async_submit(submit, flags | ASYNC_TX_XOR_ZERO_DST, tx, cb_fn,
+			  cb_param, scribble);
+	tx = async_xor(a, srcs, 0, 2, bytes, submit);
+
+	return tx;
+
+}
+
+static struct dma_async_tx_descriptor *
+__2data_recov_5(size_t bytes, int faila, int failb, struct page **blocks,
+	      struct async_submit_ctl *submit)
+{
+	struct dma_async_tx_descriptor *tx = NULL;
+	struct page *p, *q, *g, *dp, *dq;
+	struct page *srcs[2];
+	unsigned char coef[2];
+	enum async_tx_flags flags = submit->flags;
+	dma_async_tx_callback cb_fn = submit->cb_fn;
+	void *cb_param = submit->cb_param;
+	void *scribble = submit->scribble;
+	int uninitialized_var(good);
+	int i;
+
+	for (i = 0; i < 3; i++) {
+		if (i == faila || i == failb)
+			continue;
+		else {
+			good = i;
+			break;
+		}
+	}
+	BUG_ON(i >= 3);
+
+	p = blocks[5-2];
+	q = blocks[5-1];
+	g = blocks[good];
+
+	/* Compute syndrome with zero for the missing data pages
+	 * Use the dead data pages as temporary storage for delta p and
+	 * delta q
+	 */
+	dp = blocks[faila];
+	dq = blocks[failb];
+
+	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
+	tx = async_memcpy(dp, g, 0, 0, bytes, submit);
+	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
+	tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+
+	/* compute P + Pxy */
+	srcs[0] = dp;
+	srcs[1] = p;
+	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
+			  NULL, NULL, scribble);
+	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+
+	/* compute Q + Qxy */
+	srcs[0] = dq;
+	srcs[1] = q;
+	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
+			  NULL, NULL, scribble);
+	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+
+	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
+	srcs[0] = dp;
+	srcs[1] = dq;
+	coef[0] = raid6_gfexi[failb-faila];
+	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
+	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
+	tx = async_sum_product(dq, srcs, coef, bytes, submit);
+
+	/* Dy = P+Pxy+Dx */
+	srcs[0] = dp;
+	srcs[1] = dq;
+	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
+			  cb_param, scribble);
+	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+
+	return tx;
+}
+
+static struct dma_async_tx_descriptor *
+__2data_recov_n(int disks, size_t bytes, int faila, int failb,
+	      struct page **blocks, struct async_submit_ctl *submit)
+{
+	struct dma_async_tx_descriptor *tx = NULL;
+	struct page *p, *q, *dp, *dq;
+	struct page *srcs[2];
+	unsigned char coef[2];
+	enum async_tx_flags flags = submit->flags;
+	dma_async_tx_callback cb_fn = submit->cb_fn;
+	void *cb_param = submit->cb_param;
+	void *scribble = submit->scribble;
+
+	p = blocks[disks-2];
+	q = blocks[disks-1];
+
+	/* Compute syndrome with zero for the missing data pages
+	 * Use the dead data pages as temporary storage for
+	 * delta p and delta q
+	 */
+	dp = blocks[faila];
+	blocks[faila] = (void *)raid6_empty_zero_page;
+	blocks[disks-2] = dp;
+	dq = blocks[failb];
+	blocks[failb] = (void *)raid6_empty_zero_page;
+	blocks[disks-1] = dq;
+
+	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
+	tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+
+	/* Restore pointer table */
+	blocks[faila]   = dp;
+	blocks[failb]   = dq;
+	blocks[disks-2] = p;
+	blocks[disks-1] = q;
+
+	/* compute P + Pxy */
+	srcs[0] = dp;
+	srcs[1] = p;
+	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
+			  NULL, NULL, scribble);
+	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+
+	/* compute Q + Qxy */
+	srcs[0] = dq;
+	srcs[1] = q;
+	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
+			  NULL, NULL, scribble);
+	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+
+	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
+	srcs[0] = dp;
+	srcs[1] = dq;
+	coef[0] = raid6_gfexi[failb-faila];
+	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
+	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
+	tx = async_sum_product(dq, srcs, coef, bytes, submit);
+
+	/* Dy = P+Pxy+Dx */
+	srcs[0] = dp;
+	srcs[1] = dq;
+	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
+			  cb_param, scribble);
+	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+
+	return tx;
+}
+
+/**
+ * async_raid6_2data_recov - asynchronously calculate two missing data blocks
+ * @disks: number of disks in the RAID-6 array
+ * @bytes: block size
+ * @faila: first failed drive index
+ * @failb: second failed drive index
+ * @blocks: array of source pointers where the last two entries are p and q
+ * @submit: submission/completion modifiers
+ */
+struct dma_async_tx_descriptor *
+async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
+			struct page **blocks, struct async_submit_ctl *submit)
+{
+	BUG_ON(faila == failb);
+	if (failb < faila)
+		swap(faila, failb);
+
+	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
+
+	/* we need to preserve the contents of 'blocks' for the async
+	 * case, so punt to synchronous if a scribble buffer is not available
+	 */
+	if (!submit->scribble) {
+		void **ptrs = (void **) blocks;
+		int i;
+
+		async_tx_quiesce(&submit->depend_tx);
+		for (i = 0; i < disks; i++)
+			ptrs[i] = page_address(blocks[i]);
+
+		raid6_2data_recov(disks, bytes, faila, failb, ptrs);
+
+		async_tx_sync_epilog(submit);
+
+		return NULL;
+	}
+
+	switch (disks) {
+	case 4:
+		/* dma devices do not uniformly understand a zero source pq
+		 * operation (in contrast to the synchronous case), so
+		 * explicitly handle the 4 disk special case
+		 */
+		return __2data_recov_4(bytes, faila, failb, blocks, submit);
+	case 5:
+		/* dma devices do not uniformly understand a single
+		 * source pq operation (in contrast to the synchronous
+		 * case), so explicitly handle the 5 disk special case
+		 */
+		return __2data_recov_5(bytes, faila, failb, blocks, submit);
+	default:
+		return __2data_recov_n(disks, bytes, faila, failb, blocks, submit);
+	}
+}
+EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
+
+/**
+ * async_raid6_datap_recov - asynchronously calculate a data and the 'p' block
+ * @disks: number of disks in the RAID-6 array
+ * @bytes: block size
+ * @faila: failed drive index
+ * @blocks: array of source pointers where the last two entries are p and q
+ * @submit: submission/completion modifiers
+ */
+struct dma_async_tx_descriptor *
+async_raid6_datap_recov(int disks, size_t bytes, int faila,
+			struct page **blocks, struct async_submit_ctl *submit)
+{
+	struct dma_async_tx_descriptor *tx = NULL;
+	struct page *p, *q, *dq;
+	u8 coef;
+	enum async_tx_flags flags = submit->flags;
+	dma_async_tx_callback cb_fn = submit->cb_fn;
+	void *cb_param = submit->cb_param;
+	void *scribble = submit->scribble;
+	struct page *srcs[2];
+
+	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
+
+	/* we need to preserve the contents of 'blocks' for the async
+	 * case, so punt to synchronous if a scribble buffer is not available
+	 */
+	if (!scribble) {
+		void **ptrs = (void **) blocks;
+		int i;
+
+		async_tx_quiesce(&submit->depend_tx);
+		for (i = 0; i < disks; i++)
+			ptrs[i] = page_address(blocks[i]);
+
+		raid6_datap_recov(disks, bytes, faila, ptrs);
+
+		async_tx_sync_epilog(submit);
+
+		return NULL;
+	}
+
+	p = blocks[disks-2];
+	q = blocks[disks-1];
+
+	/* Compute syndrome with zero for the missing data page
+	 * Use the dead data page as temporary storage for delta q
+	 */
+	dq = blocks[faila];
+	blocks[faila] = (void *)raid6_empty_zero_page;
+	blocks[disks-1] = dq;
+
+	/* in the 4 disk case we only need to perform a single source
+	 * multiplication
+	 */
+	if (disks == 4) {
+		int good = faila == 0 ? 1 : 0;
+		struct page *g = blocks[good];
+
+		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
+				  scribble);
+		tx = async_memcpy(p, g, 0, 0, bytes, submit);
+
+		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
+				  scribble);
+		tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+	} else {
+		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
+				  scribble);
+		tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+	}
+
+	/* Restore pointer table */
+	blocks[faila]   = dq;
+	blocks[disks-1] = q;
+
+	/* calculate g^{-faila} */
+	coef = raid6_gfinv[raid6_gfexp[faila]];
+
+	srcs[0] = dq;
+	srcs[1] = q;
+	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
+			  NULL, NULL, scribble);
+	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+
+	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
+	tx = async_mult(dq, dq, coef, bytes, submit);
+
+	srcs[0] = p;
+	srcs[1] = dq;
+	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
+			  cb_param, scribble);
+	tx = async_xor(p, srcs, 0, 2, bytes, submit);
+
+	return tx;
+}
+EXPORT_SYMBOL_GPL(async_raid6_datap_recov);
+
+MODULE_AUTHOR("Dan Williams <dan.j.williams@intel.com>");
+MODULE_DESCRIPTION("asynchronous RAID-6 recovery api");
+MODULE_LICENSE("GPL");
diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c
index 06eb6cc09fe..f9cdf04fe7c 100644
--- a/crypto/async_tx/async_tx.c
+++ b/crypto/async_tx/async_tx.c
@@ -42,16 +42,21 @@ static void __exit async_tx_exit(void)
 	async_dmaengine_put();
 }
 
+module_init(async_tx_init);
+module_exit(async_tx_exit);
+
 /**
  * __async_tx_find_channel - find a channel to carry out the operation or let
  *	the transaction execute synchronously
- * @depend_tx: transaction dependency
+ * @submit: transaction dependency and submission modifiers
  * @tx_type: transaction type
  */
 struct dma_chan *
-__async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
-	enum dma_transaction_type tx_type)
+__async_tx_find_channel(struct async_submit_ctl *submit,
+			enum dma_transaction_type tx_type)
 {
+	struct dma_async_tx_descriptor *depend_tx = submit->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))
@@ -59,17 +64,6 @@ __async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
 	return async_dma_find_channel(tx_type);
 }
 EXPORT_SYMBOL_GPL(__async_tx_find_channel);
-#else
-static int __init async_tx_init(void)
-{
-	printk(KERN_INFO "async_tx: api initialized (sync-only)\n");
-	return 0;
-}
-
-static void __exit async_tx_exit(void)
-{
-	do { } while (0);
-}
 #endif
 
 
@@ -83,10 +77,14 @@ static void
 async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
 			struct dma_async_tx_descriptor *tx)
 {
-	struct dma_chan *chan;
-	struct dma_device *device;
+	struct dma_chan *chan = depend_tx->chan;
+	struct dma_device *device = chan->device;
 	struct dma_async_tx_descriptor *intr_tx = (void *) ~0;
 
+	#ifdef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH
+	BUG();
+	#endif
+
 	/* first check to see if we can still append to depend_tx */
 	spin_lock_bh(&depend_tx->lock);
 	if (depend_tx->parent && depend_tx->chan == tx->chan) {
@@ -96,11 +94,11 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
 	}
 	spin_unlock_bh(&depend_tx->lock);
 
-	if (!intr_tx)
+	/* attached dependency, flush the parent channel */
+	if (!intr_tx) {
+		device->device_issue_pending(chan);
 		return;
-
-	chan = depend_tx->chan;
-	device = chan->device;
+	}
 
 	/* see if we can schedule an interrupt
 	 * otherwise poll for completion
@@ -134,6 +132,7 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
 			intr_tx->tx_submit(intr_tx);
 			async_tx_ack(intr_tx);
 		}
+		device->device_issue_pending(chan);
 	} else {
 		if (dma_wait_for_async_tx(depend_tx) == DMA_ERROR)
 			panic("%s: DMA_ERROR waiting for depend_tx\n",
@@ -144,13 +143,14 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx,
 
 
 /**
- * submit_disposition - while holding depend_tx->lock we must avoid submitting
- * 	new operations to prevent a circular locking dependency with
- * 	drivers that already hold a channel lock when calling
- * 	async_tx_run_dependencies.
+ * submit_disposition - flags for routing an incoming operation
  * @ASYNC_TX_SUBMITTED: we were able to append the new operation under the lock
  * @ASYNC_TX_CHANNEL_SWITCH: when the lock is dropped schedule a channel switch
  * @ASYNC_TX_DIRECT_SUBMIT: when the lock is dropped submit directly
+ *
+ * while holding depend_tx->lock we must avoid submitting new operations
+ * to prevent a circular locking dependency with drivers that already
+ * hold a channel lock when calling async_tx_run_dependencies.
  */
 enum submit_disposition {
 	ASYNC_TX_SUBMITTED,
@@ -160,11 +160,12 @@ enum submit_disposition {
 
 void
 async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx,
-	enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_param)
+		struct async_submit_ctl *submit)
 {
-	tx->callback = cb_fn;
-	tx->callback_param = cb_param;
+	struct dma_async_tx_descriptor *depend_tx = submit->depend_tx;
+
+	tx->callback = submit->cb_fn;
+	tx->callback_param = submit->cb_param;
 
 	if (depend_tx) {
 		enum submit_disposition s;
@@ -220,30 +221,29 @@ async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx,
 		tx->tx_submit(tx);
 	}
 
-	if (flags & ASYNC_TX_ACK)
+	if (submit->flags & ASYNC_TX_ACK)
 		async_tx_ack(tx);
 
-	if (depend_tx && (flags & ASYNC_TX_DEP_ACK))
+	if (depend_tx)
 		async_tx_ack(depend_tx);
 }
 EXPORT_SYMBOL_GPL(async_tx_submit);
 
 /**
- * async_trigger_callback - schedules the callback function to be run after
- * any dependent operations have been completed.
- * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
- * @depend_tx: 'callback' requires the completion of this transaction
- * @cb_fn: function to call after depend_tx completes
- * @cb_param: parameter to pass to the callback routine
+ * async_trigger_callback - schedules the callback function to be run
+ * @submit: submission and completion parameters
+ *
+ * honored flags: ASYNC_TX_ACK
+ *
+ * The callback is run after any dependent operations have completed.
  */
 struct dma_async_tx_descriptor *
-async_trigger_callback(enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_param)
+async_trigger_callback(struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan;
 	struct dma_device *device;
 	struct dma_async_tx_descriptor *tx;
+	struct dma_async_tx_descriptor *depend_tx = submit->depend_tx;
 
 	if (depend_tx) {
 		chan = depend_tx->chan;
@@ -262,14 +262,14 @@ async_trigger_callback(enum async_tx_flags flags,
 	if (tx) {
 		pr_debug("%s: (async)\n", __func__);
 
-		async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
+		async_tx_submit(chan, tx, submit);
 	} else {
 		pr_debug("%s: (sync)\n", __func__);
 
 		/* wait for any prerequisite operations */
-		async_tx_quiesce(&depend_tx);
+		async_tx_quiesce(&submit->depend_tx);
 
-		async_tx_sync_epilog(cb_fn, cb_param);
+		async_tx_sync_epilog(submit);
 	}
 
 	return tx;
@@ -295,9 +295,6 @@ void async_tx_quiesce(struct dma_async_tx_descriptor **tx)
 }
 EXPORT_SYMBOL_GPL(async_tx_quiesce);
 
-module_init(async_tx_init);
-module_exit(async_tx_exit);
-
 MODULE_AUTHOR("Intel Corporation");
 MODULE_DESCRIPTION("Asynchronous Bulk Memory Transactions API");
 MODULE_LICENSE("GPL");
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 90dd3f8bd28..b459a9034aa 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -33,19 +33,16 @@
 /* do_async_xor - dma map the pages and perform the xor with an engine */
 static __async_inline struct dma_async_tx_descriptor *
 do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
-	     unsigned int offset, int src_cnt, size_t len,
-	     enum async_tx_flags flags,
-	     struct dma_async_tx_descriptor *depend_tx,
-	     dma_async_tx_callback cb_fn, void *cb_param)
+	     unsigned int offset, int src_cnt, size_t len, dma_addr_t *dma_src,
+	     struct async_submit_ctl *submit)
 {
 	struct dma_device *dma = chan->device;
-	dma_addr_t *dma_src = (dma_addr_t *) src_list;
 	struct dma_async_tx_descriptor *tx = NULL;
 	int src_off = 0;
 	int i;
-	dma_async_tx_callback _cb_fn;
-	void *_cb_param;
-	enum async_tx_flags async_flags;
+	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
+	void *cb_param_orig = submit->cb_param;
+	enum async_tx_flags flags_orig = submit->flags;
 	enum dma_ctrl_flags dma_flags;
 	int xor_src_cnt;
 	dma_addr_t dma_dest;
@@ -63,25 +60,27 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
 	}
 
 	while (src_cnt) {
-		async_flags = flags;
+		submit->flags = flags_orig;
 		dma_flags = 0;
-		xor_src_cnt = min(src_cnt, dma->max_xor);
+		xor_src_cnt = min(src_cnt, (int)dma->max_xor);
 		/* if we are submitting additional xors, leave the chain open,
 		 * clear the callback parameters, and leave the destination
 		 * buffer mapped
 		 */
 		if (src_cnt > xor_src_cnt) {
-			async_flags &= ~ASYNC_TX_ACK;
+			submit->flags &= ~ASYNC_TX_ACK;
+			submit->flags |= ASYNC_TX_FENCE;
 			dma_flags = DMA_COMPL_SKIP_DEST_UNMAP;
-			_cb_fn = NULL;
-			_cb_param = NULL;
+			submit->cb_fn = NULL;
+			submit->cb_param = NULL;
 		} else {
-			_cb_fn = cb_fn;
-			_cb_param = cb_param;
+			submit->cb_fn = cb_fn_orig;
+			submit->cb_param = cb_param_orig;
 		}
-		if (_cb_fn)
+		if (submit->cb_fn)
 			dma_flags |= DMA_PREP_INTERRUPT;
-
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_flags |= DMA_PREP_FENCE;
 		/* Since we have clobbered the src_list we are committed
 		 * to doing this asynchronously.  Drivers force forward progress
 		 * in case they can not provide a descriptor
@@ -90,7 +89,7 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
 					      xor_src_cnt, len, dma_flags);
 
 		if (unlikely(!tx))
-			async_tx_quiesce(&depend_tx);
+			async_tx_quiesce(&submit->depend_tx);
 
 		/* spin wait for the preceeding transactions to complete */
 		while (unlikely(!tx)) {
@@ -101,11 +100,8 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
 						      dma_flags);
 		}
 
-		async_tx_submit(chan, tx, async_flags, depend_tx, _cb_fn,
-				_cb_param);
-
-		depend_tx = tx;
-		flags |= ASYNC_TX_DEP_ACK;
+		async_tx_submit(chan, tx, submit);
+		submit->depend_tx = tx;
 
 		if (src_cnt > xor_src_cnt) {
 			/* drop completed sources */
@@ -124,23 +120,27 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
 
 static void
 do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
-	    int src_cnt, size_t len, enum async_tx_flags flags,
-	    dma_async_tx_callback cb_fn, void *cb_param)
+	    int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
 	int i;
 	int xor_src_cnt;
 	int src_off = 0;
 	void *dest_buf;
-	void **srcs = (void **) src_list;
+	void **srcs;
+
+	if (submit->scribble)
+		srcs = submit->scribble;
+	else
+		srcs = (void **) src_list;
 
-	/* reuse the 'src_list' array to convert to buffer pointers */
+	/* convert to buffer pointers */
 	for (i = 0; i < src_cnt; i++)
 		srcs[i] = page_address(src_list[i]) + offset;
 
 	/* set destination address */
 	dest_buf = page_address(dest) + offset;
 
-	if (flags & ASYNC_TX_XOR_ZERO_DST)
+	if (submit->flags & ASYNC_TX_XOR_ZERO_DST)
 		memset(dest_buf, 0, len);
 
 	while (src_cnt > 0) {
@@ -153,61 +153,70 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
 		src_off += xor_src_cnt;
 	}
 
-	async_tx_sync_epilog(cb_fn, cb_param);
+	async_tx_sync_epilog(submit);
 }
 
 /**
  * async_xor - attempt to xor a set of blocks with a dma engine.
- *	xor_blocks always uses the dest as a source so the ASYNC_TX_XOR_ZERO_DST
- *	flag must be set to not include dest data in the calculation.  The
- *	assumption with dma eninges is that they only use the destination
- *	buffer as a source when it is explicity specified in the source list.
  * @dest: destination page
- * @src_list: array of source pages (if the dest is also a source it must be
- *	at index zero).  The contents of this array may be overwritten.
- * @offset: offset in pages to start transaction
+ * @src_list: array of source pages
+ * @offset: common src/dst offset to start transaction
  * @src_cnt: number of source pages
  * @len: length in bytes
- * @flags: ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DEST,
- *	ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
- * @depend_tx: xor depends on the result of this transaction.
- * @cb_fn: function to call when the xor completes
- * @cb_param: parameter to pass to the callback routine
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK, ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DST
+ *
+ * xor_blocks always uses the dest as a source so the
+ * ASYNC_TX_XOR_ZERO_DST flag must be set to not include dest data in
+ * the calculation.  The assumption with dma eninges is that they only
+ * use the destination buffer as a source when it is explicity specified
+ * in the source list.
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
  */
 struct dma_async_tx_descriptor *
 async_xor(struct page *dest, struct page **src_list, unsigned int offset,
-	int src_cnt, size_t len, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_param)
+	  int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
-	struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_XOR,
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
 						      &dest, 1, src_list,
 						      src_cnt, len);
+	dma_addr_t *dma_src = NULL;
+
 	BUG_ON(src_cnt <= 1);
 
-	if (chan) {
+	if (submit->scribble)
+		dma_src = submit->scribble;
+	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
+		dma_src = (dma_addr_t *) src_list;
+
+	if (dma_src && chan && is_dma_xor_aligned(chan->device, offset, 0, len)) {
 		/* run the xor asynchronously */
 		pr_debug("%s (async): len: %zu\n", __func__, len);
 
 		return do_async_xor(chan, dest, src_list, offset, src_cnt, len,
-				    flags, depend_tx, cb_fn, cb_param);
+				    dma_src, submit);
 	} else {
 		/* run the xor synchronously */
 		pr_debug("%s (sync): len: %zu\n", __func__, len);
+		WARN_ONCE(chan, "%s: no space for dma address conversion\n",
+			  __func__);
 
 		/* in the sync case the dest is an implied source
 		 * (assumes the dest is the first source)
 		 */
-		if (flags & ASYNC_TX_XOR_DROP_DST) {
+		if (submit->flags & ASYNC_TX_XOR_DROP_DST) {
 			src_cnt--;
 			src_list++;
 		}
 
 		/* wait for any prerequisite operations */
-		async_tx_quiesce(&depend_tx);
+		async_tx_quiesce(&submit->depend_tx);
 
-		do_sync_xor(dest, src_list, offset, src_cnt, len,
-			    flags, cb_fn, cb_param);
+		do_sync_xor(dest, src_list, offset, src_cnt, len, submit);
 
 		return NULL;
 	}
@@ -222,104 +231,94 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len)
 }
 
 /**
- * async_xor_zero_sum - attempt a xor parity check with a dma engine.
+ * async_xor_val - attempt a xor parity check with a dma engine.
  * @dest: destination page used if the xor is performed synchronously
- * @src_list: array of source pages.  The dest page must be listed as a source
- * 	at index zero.  The contents of this array may be overwritten.
+ * @src_list: array of source pages
  * @offset: offset in pages to start transaction
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @result: 0 if sum == 0 else non-zero
- * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
- * @depend_tx: xor depends on the result of this transaction.
- * @cb_fn: function to call when the xor completes
- * @cb_param: parameter to pass to the callback routine
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
  */
 struct dma_async_tx_descriptor *
-async_xor_zero_sum(struct page *dest, struct page **src_list,
-	unsigned int offset, int src_cnt, size_t len,
-	u32 *result, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_param)
+async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
+	      int src_cnt, size_t len, enum sum_check_flags *result,
+	      struct async_submit_ctl *submit)
 {
-	struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_ZERO_SUM,
+	struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR_VAL,
 						      &dest, 1, src_list,
 						      src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
+	dma_addr_t *dma_src = NULL;
 
 	BUG_ON(src_cnt <= 1);
 
-	if (device && src_cnt <= device->max_xor) {
-		dma_addr_t *dma_src = (dma_addr_t *) src_list;
-		unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
+	if (submit->scribble)
+		dma_src = submit->scribble;
+	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
+		dma_src = (dma_addr_t *) src_list;
+
+	if (dma_src && device && src_cnt <= device->max_xor &&
+	    is_dma_xor_aligned(device, offset, 0, len)) {
+		unsigned long dma_prep_flags = 0;
 		int i;
 
 		pr_debug("%s: (async) len: %zu\n", __func__, len);
 
+		if (submit->cb_fn)
+			dma_prep_flags |= DMA_PREP_INTERRUPT;
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_prep_flags |= DMA_PREP_FENCE;
 		for (i = 0; i < src_cnt; i++)
 			dma_src[i] = dma_map_page(device->dev, src_list[i],
 						  offset, len, DMA_TO_DEVICE);
 
-		tx = device->device_prep_dma_zero_sum(chan, dma_src, src_cnt,
-						      len, result,
-						      dma_prep_flags);
+		tx = device->device_prep_dma_xor_val(chan, dma_src, src_cnt,
+						     len, result,
+						     dma_prep_flags);
 		if (unlikely(!tx)) {
-			async_tx_quiesce(&depend_tx);
+			async_tx_quiesce(&submit->depend_tx);
 
 			while (!tx) {
 				dma_async_issue_pending(chan);
-				tx = device->device_prep_dma_zero_sum(chan,
+				tx = device->device_prep_dma_xor_val(chan,
 					dma_src, src_cnt, len, result,
 					dma_prep_flags);
 			}
 		}
 
-		async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
+		async_tx_submit(chan, tx, submit);
 	} else {
-		unsigned long xor_flags = flags;
+		enum async_tx_flags flags_orig = submit->flags;
 
 		pr_debug("%s: (sync) len: %zu\n", __func__, len);
+		WARN_ONCE(device && src_cnt <= device->max_xor,
+			  "%s: no space for dma address conversion\n",
+			  __func__);
 
-		xor_flags |= ASYNC_TX_XOR_DROP_DST;
-		xor_flags &= ~ASYNC_TX_ACK;
+		submit->flags |= ASYNC_TX_XOR_DROP_DST;
+		submit->flags &= ~ASYNC_TX_ACK;
 
-		tx = async_xor(dest, src_list, offset, src_cnt, len, xor_flags,
-			depend_tx, NULL, NULL);
+		tx = async_xor(dest, src_list, offset, src_cnt, len, submit);
 
 		async_tx_quiesce(&tx);
 
-		*result = page_is_zero(dest, offset, len) ? 0 : 1;
+		*result = !page_is_zero(dest, offset, len) << SUM_CHECK_P;
 
-		async_tx_sync_epilog(cb_fn, cb_param);
+		async_tx_sync_epilog(submit);
+		submit->flags = flags_orig;
 	}
 
 	return tx;
 }
-EXPORT_SYMBOL_GPL(async_xor_zero_sum);
-
-static int __init async_xor_init(void)
-{
-	#ifdef CONFIG_ASYNC_TX_DMA
-	/* To conserve stack space the input src_list (array of page pointers)
-	 * is reused to hold the array of dma addresses passed to the driver.
-	 * This conversion is only possible when dma_addr_t is less than the
-	 * the size of a pointer.  HIGHMEM64G is known to violate this
-	 * assumption.
-	 */
-	BUILD_BUG_ON(sizeof(dma_addr_t) > sizeof(struct page *));
-	#endif
-
-	return 0;
-}
-
-static void __exit async_xor_exit(void)
-{
-	do { } while (0);
-}
-
-module_init(async_xor_init);
-module_exit(async_xor_exit);
+EXPORT_SYMBOL_GPL(async_xor_val);
 
 MODULE_AUTHOR("Intel Corporation");
 MODULE_DESCRIPTION("asynchronous xor/xor-zero-sum api");
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
new file mode 100644
index 00000000000..3ec27c7e62e
--- /dev/null
+++ b/crypto/async_tx/raid6test.c
@@ -0,0 +1,240 @@
+/*
+ * asynchronous raid6 recovery self test
+ * Copyright (c) 2009, Intel Corporation.
+ *
+ * based on drivers/md/raid6test/test.c:
+ * 	Copyright 2002-2007 H. Peter Anvin
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#include <linux/async_tx.h>
+#include <linux/random.h>
+
+#undef pr
+#define pr(fmt, args...) pr_info("raid6test: " fmt, ##args)
+
+#define NDISKS 16 /* Including P and Q */
+
+static struct page *dataptrs[NDISKS];
+static addr_conv_t addr_conv[NDISKS];
+static struct page *data[NDISKS+3];
+static struct page *spare;
+static struct page *recovi;
+static struct page *recovj;
+
+static void callback(void *param)
+{
+	struct completion *cmp = param;
+
+	complete(cmp);
+}
+
+static void makedata(int disks)
+{
+	int i, j;
+
+	for (i = 0; i < disks; i++) {
+		for (j = 0; j < PAGE_SIZE/sizeof(u32); j += sizeof(u32)) {
+			u32 *p = page_address(data[i]) + j;
+
+			*p = random32();
+		}
+
+		dataptrs[i] = data[i];
+	}
+}
+
+static char disk_type(int d, int disks)
+{
+	if (d == disks - 2)
+		return 'P';
+	else if (d == disks - 1)
+		return 'Q';
+	else
+		return 'D';
+}
+
+/* Recover two failed blocks. */
+static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, struct page **ptrs)
+{
+	struct async_submit_ctl submit;
+	struct completion cmp;
+	struct dma_async_tx_descriptor *tx = NULL;
+	enum sum_check_flags result = ~0;
+
+	if (faila > failb)
+		swap(faila, failb);
+
+	if (failb == disks-1) {
+		if (faila == disks-2) {
+			/* P+Q failure.  Just rebuild the syndrome. */
+			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
+			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+		} else {
+			struct page *blocks[disks];
+			struct page *dest;
+			int count = 0;
+			int i;
+
+			/* data+Q failure.  Reconstruct data from P,
+			 * then rebuild syndrome
+			 */
+			for (i = disks; i-- ; ) {
+				if (i == faila || i == failb)
+					continue;
+				blocks[count++] = ptrs[i];
+			}
+			dest = ptrs[faila];
+			init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL,
+					  NULL, NULL, addr_conv);
+			tx = async_xor(dest, blocks, 0, count, bytes, &submit);
+
+			init_async_submit(&submit, 0, tx, NULL, NULL, addr_conv);
+			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+		}
+	} else {
+		if (failb == disks-2) {
+			/* data+P failure. */
+			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
+			tx = async_raid6_datap_recov(disks, bytes, faila, ptrs, &submit);
+		} else {
+			/* data+data failure. */
+			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
+			tx = async_raid6_2data_recov(disks, bytes, faila, failb, ptrs, &submit);
+		}
+	}
+	init_completion(&cmp);
+	init_async_submit(&submit, ASYNC_TX_ACK, tx, callback, &cmp, addr_conv);
+	tx = async_syndrome_val(ptrs, 0, disks, bytes, &result, spare, &submit);
+	async_tx_issue_pending(tx);
+
+	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0)
+		pr("%s: timeout! (faila: %d failb: %d disks: %d)\n",
+		   __func__, faila, failb, disks);
+
+	if (result != 0)
+		pr("%s: validation failure! faila: %d failb: %d sum_check_flags: %x\n",
+		   __func__, faila, failb, result);
+}
+
+static int test_disks(int i, int j, int disks)
+{
+	int erra, errb;
+
+	memset(page_address(recovi), 0xf0, PAGE_SIZE);
+	memset(page_address(recovj), 0xba, PAGE_SIZE);
+
+	dataptrs[i] = recovi;
+	dataptrs[j] = recovj;
+
+	raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs);
+
+	erra = memcmp(page_address(data[i]), page_address(recovi), PAGE_SIZE);
+	errb = memcmp(page_address(data[j]), page_address(recovj), PAGE_SIZE);
+
+	pr("%s(%d, %d): faila=%3d(%c)  failb=%3d(%c)  %s\n",
+	   __func__, i, j, i, disk_type(i, disks), j, disk_type(j, disks),
+	   (!erra && !errb) ? "OK" : !erra ? "ERRB" : !errb ? "ERRA" : "ERRAB");
+
+	dataptrs[i] = data[i];
+	dataptrs[j] = data[j];
+
+	return erra || errb;
+}
+
+static int test(int disks, int *tests)
+{
+	struct dma_async_tx_descriptor *tx;
+	struct async_submit_ctl submit;
+	struct completion cmp;
+	int err = 0;
+	int i, j;
+
+	recovi = data[disks];
+	recovj = data[disks+1];
+	spare  = data[disks+2];
+
+	makedata(disks);
+
+	/* Nuke syndromes */
+	memset(page_address(data[disks-2]), 0xee, PAGE_SIZE);
+	memset(page_address(data[disks-1]), 0xee, PAGE_SIZE);
+
+	/* Generate assumed good syndrome */
+	init_completion(&cmp);
+	init_async_submit(&submit, ASYNC_TX_ACK, NULL, callback, &cmp, addr_conv);
+	tx = async_gen_syndrome(dataptrs, 0, disks, PAGE_SIZE, &submit);
+	async_tx_issue_pending(tx);
+
+	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0) {
+		pr("error: initial gen_syndrome(%d) timed out\n", disks);
+		return 1;
+	}
+
+	pr("testing the %d-disk case...\n", disks);
+	for (i = 0; i < disks-1; i++)
+		for (j = i+1; j < disks; j++) {
+			(*tests)++;
+			err += test_disks(i, j, disks);
+		}
+
+	return err;
+}
+
+
+static int raid6_test(void)
+{
+	int err = 0;
+	int tests = 0;
+	int i;
+
+	for (i = 0; i < NDISKS+3; i++) {
+		data[i] = alloc_page(GFP_KERNEL);
+		if (!data[i]) {
+			while (i--)
+				put_page(data[i]);
+			return -ENOMEM;
+		}
+	}
+
+	/* the 4-disk and 5-disk cases are special for the recovery code */
+	if (NDISKS > 4)
+		err += test(4, &tests);
+	if (NDISKS > 5)
+		err += test(5, &tests);
+	err += test(NDISKS, &tests);
+
+	pr("\n");
+	pr("complete (%d tests, %d failure%s)\n",
+	   tests, err, err == 1 ? "" : "s");
+
+	for (i = 0; i < NDISKS+3; i++)
+		put_page(data[i]);
+
+	return 0;
+}
+
+static void raid6_test_exit(void)
+{
+}
+
+/* when compiled-in wait for drivers to load first (assumes dma drivers
+ * are also compliled-in)
+ */
+late_initcall(raid6_test);
+module_exit(raid6_test_exit);
+MODULE_AUTHOR("Dan Williams <dan.j.williams@intel.com>");
+MODULE_DESCRIPTION("asynchronous RAID-6 recovery self tests");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c
index 25b743abfb5..52e6bb70a49 100644
--- a/drivers/dca/dca-core.c
+++ b/drivers/dca/dca-core.c
@@ -28,7 +28,7 @@
 #include <linux/device.h>
 #include <linux/dca.h>
 
-#define DCA_VERSION "1.8"
+#define DCA_VERSION "1.12.1"
 
 MODULE_VERSION(DCA_VERSION);
 MODULE_LICENSE("GPL");
@@ -36,20 +36,92 @@ MODULE_AUTHOR("Intel Corporation");
 
 static DEFINE_SPINLOCK(dca_lock);
 
-static LIST_HEAD(dca_providers);
+static LIST_HEAD(dca_domains);
 
-static struct dca_provider *dca_find_provider_by_dev(struct device *dev)
+static struct pci_bus *dca_pci_rc_from_dev(struct device *dev)
 {
-	struct dca_provider *dca, *ret = NULL;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_bus *bus = pdev->bus;
 
-	list_for_each_entry(dca, &dca_providers, node) {
-		if ((!dev) || (dca->ops->dev_managed(dca, dev))) {
-			ret = dca;
-			break;
-		}
+	while (bus->parent)
+		bus = bus->parent;
+
+	return bus;
+}
+
+static struct dca_domain *dca_allocate_domain(struct pci_bus *rc)
+{
+	struct dca_domain *domain;
+
+	domain = kzalloc(sizeof(*domain), GFP_NOWAIT);
+	if (!domain)
+		return NULL;
+
+	INIT_LIST_HEAD(&domain->dca_providers);
+	domain->pci_rc = rc;
+
+	return domain;
+}
+
+static void dca_free_domain(struct dca_domain *domain)
+{
+	list_del(&domain->node);
+	kfree(domain);
+}
+
+static struct dca_domain *dca_find_domain(struct pci_bus *rc)
+{
+	struct dca_domain *domain;
+
+	list_for_each_entry(domain, &dca_domains, node)
+		if (domain->pci_rc == rc)
+			return domain;
+
+	return NULL;
+}
+
+static struct dca_domain *dca_get_domain(struct device *dev)
+{
+	struct pci_bus *rc;
+	struct dca_domain *domain;
+
+	rc = dca_pci_rc_from_dev(dev);
+	domain = dca_find_domain(rc);
+
+	if (!domain) {
+		domain = dca_allocate_domain(rc);
+		if (domain)
+			list_add(&domain->node, &dca_domains);
+	}
+
+	return domain;
+}
+
+static struct dca_provider *dca_find_provider_by_dev(struct device *dev)
+{
+	struct dca_provider *dca;
+	struct pci_bus *rc;
+	struct dca_domain *domain;
+
+	if (dev) {
+		rc = dca_pci_rc_from_dev(dev);
+		domain = dca_find_domain(rc);
+		if (!domain)
+			return NULL;
+	} else {
+		if (!list_empty(&dca_domains))
+			domain = list_first_entry(&dca_domains,
+						  struct dca_domain,
+						  node);
+		else
+			return NULL;
 	}
 
-	return ret;
+	list_for_each_entry(dca, &domain->dca_providers, node)
+		if ((!dev) || (dca->ops->dev_managed(dca, dev)))
+			return dca;
+
+	return NULL;
 }
 
 /**
@@ -61,6 +133,8 @@ int dca_add_requester(struct device *dev)
 	struct dca_provider *dca;
 	int err, slot = -ENODEV;
 	unsigned long flags;
+	struct pci_bus *pci_rc;
+	struct dca_domain *domain;
 
 	if (!dev)
 		return -EFAULT;
@@ -74,7 +148,14 @@ int dca_add_requester(struct device *dev)
 		return -EEXIST;
 	}
 
-	list_for_each_entry(dca, &dca_providers, node) {
+	pci_rc = dca_pci_rc_from_dev(dev);
+	domain = dca_find_domain(pci_rc);
+	if (!domain) {
+		spin_unlock_irqrestore(&dca_lock, flags);
+		return -ENODEV;
+	}
+
+	list_for_each_entry(dca, &domain->dca_providers, node) {
 		slot = dca->ops->add_requester(dca, dev);
 		if (slot >= 0)
 			break;
@@ -222,13 +303,19 @@ int register_dca_provider(struct dca_provider *dca, struct device *dev)
 {
 	int err;
 	unsigned long flags;
+	struct dca_domain *domain;
 
 	err = dca_sysfs_add_provider(dca, dev);
 	if (err)
 		return err;
 
 	spin_lock_irqsave(&dca_lock, flags);
-	list_add(&dca->node, &dca_providers);
+	domain = dca_get_domain(dev);
+	if (!domain) {
+		spin_unlock_irqrestore(&dca_lock, flags);
+		return -ENODEV;
+	}
+	list_add(&dca->node, &domain->dca_providers);
 	spin_unlock_irqrestore(&dca_lock, flags);
 
 	blocking_notifier_call_chain(&dca_provider_chain,
@@ -241,15 +328,24 @@ EXPORT_SYMBOL_GPL(register_dca_provider);
  * unregister_dca_provider - remove a dca provider
  * @dca - struct created by alloc_dca_provider()
  */
-void unregister_dca_provider(struct dca_provider *dca)
+void unregister_dca_provider(struct dca_provider *dca, struct device *dev)
 {
 	unsigned long flags;
+	struct pci_bus *pci_rc;
+	struct dca_domain *domain;
 
 	blocking_notifier_call_chain(&dca_provider_chain,
 				     DCA_PROVIDER_REMOVE, NULL);
 
 	spin_lock_irqsave(&dca_lock, flags);
+
 	list_del(&dca->node);
+
+	pci_rc = dca_pci_rc_from_dev(dev);
+	domain = dca_find_domain(pci_rc);
+	if (list_empty(&domain->dca_providers))
+		dca_free_domain(domain);
+
 	spin_unlock_irqrestore(&dca_lock, flags);
 
 	dca_sysfs_remove_provider(dca);
@@ -276,7 +372,7 @@ EXPORT_SYMBOL_GPL(dca_unregister_notify);
 
 static int __init dca_init(void)
 {
-	printk(KERN_ERR "dca service started, version %s\n", DCA_VERSION);
+	pr_info("dca service started, version %s\n", DCA_VERSION);
 	return dca_sysfs_init();
 }
 
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 81e1020fb51..5903a88351b 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -17,11 +17,15 @@ if DMADEVICES
 
 comment "DMA Devices"
 
+config ASYNC_TX_DISABLE_CHANNEL_SWITCH
+	bool
+
 config INTEL_IOATDMA
 	tristate "Intel I/OAT DMA support"
 	depends on PCI && X86
 	select DMA_ENGINE
 	select DCA
+	select ASYNC_TX_DISABLE_CHANNEL_SWITCH
 	help
 	  Enable support for the Intel(R) I/OAT DMA engine present
 	  in recent Intel Xeon chipsets.
@@ -97,6 +101,14 @@ config TXX9_DMAC
 	  Support the TXx9 SoC internal DMA controller.  This can be
 	  integrated in chips such as the Toshiba TX4927/38/39.
 
+config SH_DMAE
+	tristate "Renesas SuperH DMAC support"
+	depends on SUPERH && SH_DMA
+	depends on !SH_DMA_API
+	select DMA_ENGINE
+	help
+	  Enable support for the Renesas SuperH DMA controllers.
+
 config DMA_ENGINE
 	bool
 
@@ -116,7 +128,7 @@ config NET_DMA
 
 config ASYNC_TX_DMA
 	bool "Async_tx: Offload support for the async_tx api"
-	depends on DMA_ENGINE && !HIGHMEM64G
+	depends on DMA_ENGINE
 	help
 	  This allows the async_tx api to take advantage of offload engines for
 	  memcpy, memset, xor, and raid6 p+q operations.  If your platform has
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 40e1e008357..eca71ba78ae 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -1,8 +1,7 @@
 obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
 obj-$(CONFIG_NET_DMA) += iovlock.o
 obj-$(CONFIG_DMATEST) += dmatest.o
-obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o
-ioatdma-objs := ioat.o ioat_dma.o ioat_dca.o
+obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_MV_XOR) += mv_xor.o
@@ -10,3 +9,4 @@ obj-$(CONFIG_DW_DMAC) += dw_dmac.o
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_MX3_IPU) += ipu/
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
+obj-$(CONFIG_SH_DMAE) += shdma.o
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index c8522e6f1ad..7585c4164bd 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -87,6 +87,7 @@ static struct at_desc *atc_alloc_descriptor(struct dma_chan *chan,
 	desc = dma_pool_alloc(atdma->dma_desc_pool, gfp_flags, &phys);
 	if (desc) {
 		memset(desc, 0, sizeof(struct at_desc));
+		INIT_LIST_HEAD(&desc->tx_list);
 		dma_async_tx_descriptor_init(&desc->txd, chan);
 		/* txd.flags will be overwritten in prep functions */
 		desc->txd.flags = DMA_CTRL_ACK;
@@ -150,11 +151,11 @@ static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
 		struct at_desc *child;
 
 		spin_lock_bh(&atchan->lock);
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&atchan->chan_common),
 					"moving child desc %p to freelist\n",
 					child);
-		list_splice_init(&desc->txd.tx_list, &atchan->free_list);
+		list_splice_init(&desc->tx_list, &atchan->free_list);
 		dev_vdbg(chan2dev(&atchan->chan_common),
 			 "moving desc %p to freelist\n", desc);
 		list_add(&desc->desc_node, &atchan->free_list);
@@ -247,30 +248,33 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	param = txd->callback_param;
 
 	/* move children to free_list */
-	list_splice_init(&txd->tx_list, &atchan->free_list);
+	list_splice_init(&desc->tx_list, &atchan->free_list);
 	/* move myself to free_list */
 	list_move(&desc->desc_node, &atchan->free_list);
 
 	/* unmap dma addresses */
-	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			dma_unmap_single(chan2parent(&atchan->chan_common),
-					desc->lli.daddr,
-					desc->len, DMA_FROM_DEVICE);
-		else
-			dma_unmap_page(chan2parent(&atchan->chan_common),
-					desc->lli.daddr,
-					desc->len, DMA_FROM_DEVICE);
-	}
-	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			dma_unmap_single(chan2parent(&atchan->chan_common),
-					desc->lli.saddr,
-					desc->len, DMA_TO_DEVICE);
-		else
-			dma_unmap_page(chan2parent(&atchan->chan_common),
-					desc->lli.saddr,
-					desc->len, DMA_TO_DEVICE);
+	if (!atchan->chan_common.private) {
+		struct device *parent = chan2parent(&atchan->chan_common);
+		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+				dma_unmap_single(parent,
+						desc->lli.daddr,
+						desc->len, DMA_FROM_DEVICE);
+			else
+				dma_unmap_page(parent,
+						desc->lli.daddr,
+						desc->len, DMA_FROM_DEVICE);
+		}
+		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+				dma_unmap_single(parent,
+						desc->lli.saddr,
+						desc->len, DMA_TO_DEVICE);
+			else
+				dma_unmap_page(parent,
+						desc->lli.saddr,
+						desc->len, DMA_TO_DEVICE);
+		}
 	}
 
 	/*
@@ -334,7 +338,7 @@ static void atc_cleanup_descriptors(struct at_dma_chan *atchan)
 			/* This one is currently in progress */
 			return;
 
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			if (!(child->lli.ctrla & ATC_DONE))
 				/* Currently in progress */
 				return;
@@ -407,7 +411,7 @@ static void atc_handle_error(struct at_dma_chan *atchan)
 	dev_crit(chan2dev(&atchan->chan_common),
 			"  cookie: %d\n", bad_desc->txd.cookie);
 	atc_dump_lli(atchan, &bad_desc->lli);
-	list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		atc_dump_lli(atchan, &child->lli);
 
 	/* Pretend the descriptor completed successfully */
@@ -587,7 +591,7 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			prev->lli.dscr = desc->txd.phys;
 			/* insert the link descriptor to the LD ring */
 			list_add_tail(&desc->desc_node,
-					&first->txd.tx_list);
+					&first->tx_list);
 		}
 		prev = desc;
 	}
@@ -646,8 +650,6 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	reg_width = atslave->reg_width;
 
-	sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
-
 	ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
 	ctrlb = ATC_DEFAULT_CTRLB | ATC_IEN;
 
@@ -687,7 +689,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				prev->lli.dscr = desc->txd.phys;
 				/* insert the link descriptor to the LD ring */
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
@@ -729,7 +731,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				prev->lli.dscr = desc->txd.phys;
 				/* insert the link descriptor to the LD ring */
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 4c972afc49e..495457e3dc4 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -165,6 +165,7 @@ struct at_desc {
 	struct at_lli			lli;
 
 	/* THEN values for driver housekeeping */
+	struct list_head		tx_list;
 	struct dma_async_tx_descriptor	txd;
 	struct list_head		desc_node;
 	size_t				len;
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 5a87384ea4f..bd0b248de2c 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -608,6 +608,40 @@ void dmaengine_put(void)
 }
 EXPORT_SYMBOL(dmaengine_put);
 
+static bool device_has_all_tx_types(struct dma_device *device)
+{
+	/* A device that satisfies this test has channels that will never cause
+	 * an async_tx channel switch event as all possible operation types can
+	 * be handled.
+	 */
+	#ifdef CONFIG_ASYNC_TX_DMA
+	if (!dma_has_cap(DMA_INTERRUPT, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_MEMCPY) || defined(CONFIG_ASYNC_MEMCPY_MODULE)
+	if (!dma_has_cap(DMA_MEMCPY, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_MEMSET) || defined(CONFIG_ASYNC_MEMSET_MODULE)
+	if (!dma_has_cap(DMA_MEMSET, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE)
+	if (!dma_has_cap(DMA_XOR, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE)
+	if (!dma_has_cap(DMA_PQ, device->cap_mask))
+		return false;
+	#endif
+
+	return true;
+}
+
 static int get_dma_id(struct dma_device *device)
 {
 	int rc;
@@ -644,8 +678,12 @@ int dma_async_device_register(struct dma_device *device)
 		!device->device_prep_dma_memcpy);
 	BUG_ON(dma_has_cap(DMA_XOR, device->cap_mask) &&
 		!device->device_prep_dma_xor);
-	BUG_ON(dma_has_cap(DMA_ZERO_SUM, device->cap_mask) &&
-		!device->device_prep_dma_zero_sum);
+	BUG_ON(dma_has_cap(DMA_XOR_VAL, device->cap_mask) &&
+		!device->device_prep_dma_xor_val);
+	BUG_ON(dma_has_cap(DMA_PQ, device->cap_mask) &&
+		!device->device_prep_dma_pq);
+	BUG_ON(dma_has_cap(DMA_PQ_VAL, device->cap_mask) &&
+		!device->device_prep_dma_pq_val);
 	BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) &&
 		!device->device_prep_dma_memset);
 	BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) &&
@@ -661,6 +699,12 @@ int dma_async_device_register(struct dma_device *device)
 	BUG_ON(!device->device_issue_pending);
 	BUG_ON(!device->dev);
 
+	/* note: this only matters in the
+	 * CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH=y case
+	 */
+	if (device_has_all_tx_types(device))
+		dma_cap_set(DMA_ASYNC_TX, device->cap_mask);
+
 	idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
 	if (!idr_ref)
 		return -ENOMEM;
@@ -933,55 +977,29 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 {
 	tx->chan = chan;
 	spin_lock_init(&tx->lock);
-	INIT_LIST_HEAD(&tx->tx_list);
 }
 EXPORT_SYMBOL(dma_async_tx_descriptor_init);
 
 /* dma_wait_for_async_tx - spin wait for a transaction to complete
  * @tx: in-flight transaction to wait on
- *
- * This routine assumes that tx was obtained from a call to async_memcpy,
- * async_xor, async_memset, etc which ensures that tx is "in-flight" (prepped
- * and submitted).  Walking the parent chain is only meant to cover for DMA
- * drivers that do not implement the DMA_INTERRUPT capability and may race with
- * the driver's descriptor cleanup routine.
  */
 enum dma_status
 dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 {
-	enum dma_status status;
-	struct dma_async_tx_descriptor *iter;
-	struct dma_async_tx_descriptor *parent;
+	unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);
 
 	if (!tx)
 		return DMA_SUCCESS;
 
-	WARN_ONCE(tx->parent, "%s: speculatively walking dependency chain for"
-		  " %s\n", __func__, dma_chan_name(tx->chan));
-
-	/* poll through the dependency chain, return when tx is complete */
-	do {
-		iter = tx;
-
-		/* find the root of the unsubmitted dependency chain */
-		do {
-			parent = iter->parent;
-			if (!parent)
-				break;
-			else
-				iter = parent;
-		} while (parent);
-
-		/* there is a small window for ->parent == NULL and
-		 * ->cookie == -EBUSY
-		 */
-		while (iter->cookie == -EBUSY)
-			cpu_relax();
-
-		status = dma_sync_wait(iter->chan, iter->cookie);
-	} while (status == DMA_IN_PROGRESS || (iter != tx));
-
-	return status;
+	while (tx->cookie == -EBUSY) {
+		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
+			pr_err("%s timeout waiting for descriptor submission\n",
+				__func__);
+			return DMA_ERROR;
+		}
+		cpu_relax();
+	}
+	return dma_sync_wait(tx->chan, tx->cookie);
 }
 EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index d93017fc787..a32a4cf7b1e 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -48,6 +48,11 @@ module_param(xor_sources, uint, S_IRUGO);
 MODULE_PARM_DESC(xor_sources,
 		"Number of xor source buffers (default: 3)");
 
+static unsigned int pq_sources = 3;
+module_param(pq_sources, uint, S_IRUGO);
+MODULE_PARM_DESC(pq_sources,
+		"Number of p+q source buffers (default: 3)");
+
 /*
  * Initialization patterns. All bytes in the source buffer has bit 7
  * set, all bytes in the destination buffer has bit 7 cleared.
@@ -232,6 +237,7 @@ static int dmatest_func(void *data)
 	dma_cookie_t		cookie;
 	enum dma_status		status;
 	enum dma_ctrl_flags 	flags;
+	u8			pq_coefs[pq_sources];
 	int			ret;
 	int			src_cnt;
 	int			dst_cnt;
@@ -248,6 +254,11 @@ static int dmatest_func(void *data)
 	else if (thread->type == DMA_XOR) {
 		src_cnt = xor_sources | 1; /* force odd to ensure dst = src */
 		dst_cnt = 1;
+	} else if (thread->type == DMA_PQ) {
+		src_cnt = pq_sources | 1; /* force odd to ensure dst = src */
+		dst_cnt = 2;
+		for (i = 0; i < pq_sources; i++)
+			pq_coefs[i] = 1;
 	} else
 		goto err_srcs;
 
@@ -283,6 +294,7 @@ static int dmatest_func(void *data)
 		dma_addr_t dma_dsts[dst_cnt];
 		struct completion cmp;
 		unsigned long tmo = msecs_to_jiffies(3000);
+		u8 align = 0;
 
 		total_tests++;
 
@@ -290,6 +302,18 @@ static int dmatest_func(void *data)
 		src_off = dmatest_random() % (test_buf_size - len + 1);
 		dst_off = dmatest_random() % (test_buf_size - len + 1);
 
+		/* honor alignment restrictions */
+		if (thread->type == DMA_MEMCPY)
+			align = dev->copy_align;
+		else if (thread->type == DMA_XOR)
+			align = dev->xor_align;
+		else if (thread->type == DMA_PQ)
+			align = dev->pq_align;
+
+		len = (len >> align) << align;
+		src_off = (src_off >> align) << align;
+		dst_off = (dst_off >> align) << align;
+
 		dmatest_init_srcs(thread->srcs, src_off, len);
 		dmatest_init_dsts(thread->dsts, dst_off, len);
 
@@ -306,6 +330,7 @@ static int dmatest_func(void *data)
 						     DMA_BIDIRECTIONAL);
 		}
 
+
 		if (thread->type == DMA_MEMCPY)
 			tx = dev->device_prep_dma_memcpy(chan,
 							 dma_dsts[0] + dst_off,
@@ -316,6 +341,15 @@ static int dmatest_func(void *data)
 						      dma_dsts[0] + dst_off,
 						      dma_srcs, xor_sources,
 						      len, flags);
+		else if (thread->type == DMA_PQ) {
+			dma_addr_t dma_pq[dst_cnt];
+
+			for (i = 0; i < dst_cnt; i++)
+				dma_pq[i] = dma_dsts[i] + dst_off;
+			tx = dev->device_prep_dma_pq(chan, dma_pq, dma_srcs,
+						     pq_sources, pq_coefs,
+						     len, flags);
+		}
 
 		if (!tx) {
 			for (i = 0; i < src_cnt; i++)
@@ -459,6 +493,8 @@ static int dmatest_add_threads(struct dmatest_chan *dtc, enum dma_transaction_ty
 		op = "copy";
 	else if (type == DMA_XOR)
 		op = "xor";
+	else if (type == DMA_PQ)
+		op = "pq";
 	else
 		return -EINVAL;
 
@@ -514,6 +550,10 @@ static int dmatest_add_channel(struct dma_chan *chan)
 		cnt = dmatest_add_threads(dtc, DMA_XOR);
 		thread_count += cnt > 0 ? cnt : 0;
 	}
+	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
+		cnt = dmatest_add_threads(dtc, DMA_PQ);
+		thread_count += cnt > 0 ?: 0;
+	}
 
 	pr_info("dmatest: Started %u threads using %s\n",
 		thread_count, dma_chan_name(chan));
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 933c143b6a7..2eea823516a 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -116,7 +116,7 @@ static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
 {
 	struct dw_desc	*child;
 
-	list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &desc->tx_list, desc_node)
 		dma_sync_single_for_cpu(chan2parent(&dwc->chan),
 				child->txd.phys, sizeof(child->lli),
 				DMA_TO_DEVICE);
@@ -137,11 +137,11 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 		dwc_sync_desc_for_cpu(dwc, desc);
 
 		spin_lock_bh(&dwc->lock);
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&dwc->chan),
 					"moving child desc %p to freelist\n",
 					child);
-		list_splice_init(&desc->txd.tx_list, &dwc->free_list);
+		list_splice_init(&desc->tx_list, &dwc->free_list);
 		dev_vdbg(chan2dev(&dwc->chan), "moving desc %p to freelist\n", desc);
 		list_add(&desc->desc_node, &dwc->free_list);
 		spin_unlock_bh(&dwc->lock);
@@ -209,19 +209,28 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	param = txd->callback_param;
 
 	dwc_sync_desc_for_cpu(dwc, desc);
-	list_splice_init(&txd->tx_list, &dwc->free_list);
+	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
-	/*
-	 * We use dma_unmap_page() regardless of how the buffers were
-	 * mapped before they were submitted...
-	 */
-	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP))
-		dma_unmap_page(chan2parent(&dwc->chan), desc->lli.dar,
-			       desc->len, DMA_FROM_DEVICE);
-	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
-		dma_unmap_page(chan2parent(&dwc->chan), desc->lli.sar,
-			       desc->len, DMA_TO_DEVICE);
+	if (!dwc->chan.private) {
+		struct device *parent = chan2parent(&dwc->chan);
+		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+				dma_unmap_single(parent, desc->lli.dar,
+						desc->len, DMA_FROM_DEVICE);
+			else
+				dma_unmap_page(parent, desc->lli.dar,
+						desc->len, DMA_FROM_DEVICE);
+		}
+		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+				dma_unmap_single(parent, desc->lli.sar,
+						desc->len, DMA_TO_DEVICE);
+			else
+				dma_unmap_page(parent, desc->lli.sar,
+						desc->len, DMA_TO_DEVICE);
+		}
+	}
 
 	/*
 	 * The API requires that no submissions are done from a
@@ -289,7 +298,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 			/* This one is currently in progress */
 			return;
 
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			if (child->lli.llp == llp)
 				/* Currently in progress */
 				return;
@@ -356,7 +365,7 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	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)
+	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		dwc_dump_lli(dwc, &child->lli);
 
 	/* Pretend the descriptor completed successfully */
@@ -608,7 +617,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 					prev->txd.phys, sizeof(prev->lli),
 					DMA_TO_DEVICE);
 			list_add_tail(&desc->desc_node,
-					&first->txd.tx_list);
+					&first->tx_list);
 		}
 		prev = desc;
 	}
@@ -658,8 +667,6 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	reg_width = dws->reg_width;
 	prev = first = NULL;
 
-	sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
-
 	switch (direction) {
 	case DMA_TO_DEVICE:
 		ctllo = (DWC_DEFAULT_CTLLO
@@ -700,7 +707,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 						sizeof(prev->lli),
 						DMA_TO_DEVICE);
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
@@ -746,7 +753,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 						sizeof(prev->lli),
 						DMA_TO_DEVICE);
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
@@ -902,6 +909,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 			break;
 		}
 
+		INIT_LIST_HEAD(&desc->tx_list);
 		dma_async_tx_descriptor_init(&desc->txd, chan);
 		desc->txd.tx_submit = dwc_tx_submit;
 		desc->txd.flags = DMA_CTRL_ACK;
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index 13a58076703..d9a939f67f4 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -217,6 +217,7 @@ struct dw_desc {
 
 	/* THEN values for driver housekeeping */
 	struct list_head		desc_node;
+	struct list_head		tx_list;
 	struct dma_async_tx_descriptor	txd;
 	size_t				len;
 };
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index ef87a898414..296f9e747fa 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -34,6 +34,7 @@
 #include <linux/dmapool.h>
 #include <linux/of_platform.h>
 
+#include <asm/fsldma.h>
 #include "fsldma.h"
 
 static void dma_init(struct fsl_dma_chan *fsl_chan)
@@ -280,28 +281,40 @@ static void fsl_chan_set_dest_loop_size(struct fsl_dma_chan *fsl_chan, int size)
 }
 
 /**
- * fsl_chan_toggle_ext_pause - Toggle channel external pause status
+ * fsl_chan_set_request_count - Set DMA Request Count for external control
  * @fsl_chan : Freescale DMA channel
- * @size     : Pause control size, 0 for disable external pause control.
- *             The maximum is 1024.
+ * @size     : Number of bytes to transfer in a single request
+ *
+ * The Freescale DMA channel can be controlled by the external signal DREQ#.
+ * The DMA request count is how many bytes are allowed to transfer before
+ * pausing the channel, after which a new assertion of DREQ# resumes channel
+ * operation.
  *
- * The Freescale DMA channel can be controlled by the external
- * signal DREQ#. The pause control size is how many bytes are allowed
- * to transfer before pausing the channel, after which a new assertion
- * of DREQ# resumes channel operation.
+ * A size of 0 disables external pause control. The maximum size is 1024.
  */
-static void fsl_chan_toggle_ext_pause(struct fsl_dma_chan *fsl_chan, int size)
+static void fsl_chan_set_request_count(struct fsl_dma_chan *fsl_chan, int size)
 {
-	if (size > 1024)
-		return;
+	BUG_ON(size > 1024);
+	DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr,
+		DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32)
+			| ((__ilog2(size) << 24) & 0x0f000000),
+		32);
+}
 
-	if (size) {
-		DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr,
-			DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32)
-				| ((__ilog2(size) << 24) & 0x0f000000),
-			32);
+/**
+ * fsl_chan_toggle_ext_pause - Toggle channel external pause status
+ * @fsl_chan : Freescale DMA channel
+ * @enable   : 0 is disabled, 1 is enabled.
+ *
+ * The Freescale DMA channel can be controlled by the external signal DREQ#.
+ * The DMA Request Count feature should be used in addition to this feature
+ * to set the number of bytes to transfer before pausing the channel.
+ */
+static void fsl_chan_toggle_ext_pause(struct fsl_dma_chan *fsl_chan, int enable)
+{
+	if (enable)
 		fsl_chan->feature |= FSL_DMA_CHAN_PAUSE_EXT;
-	} else
+	else
 		fsl_chan->feature &= ~FSL_DMA_CHAN_PAUSE_EXT;
 }
 
@@ -326,7 +339,8 @@ static void fsl_chan_toggle_ext_start(struct fsl_dma_chan *fsl_chan, int enable)
 static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct fsl_dma_chan *fsl_chan = to_fsl_chan(tx->chan);
-	struct fsl_desc_sw *desc;
+	struct fsl_desc_sw *desc = tx_to_fsl_desc(tx);
+	struct fsl_desc_sw *child;
 	unsigned long flags;
 	dma_cookie_t cookie;
 
@@ -334,7 +348,7 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&fsl_chan->desc_lock, flags);
 
 	cookie = fsl_chan->common.cookie;
-	list_for_each_entry(desc, &tx->tx_list, node) {
+	list_for_each_entry(child, &desc->tx_list, node) {
 		cookie++;
 		if (cookie < 0)
 			cookie = 1;
@@ -343,8 +357,8 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	}
 
 	fsl_chan->common.cookie = cookie;
-	append_ld_queue(fsl_chan, tx_to_fsl_desc(tx));
-	list_splice_init(&tx->tx_list, fsl_chan->ld_queue.prev);
+	append_ld_queue(fsl_chan, desc);
+	list_splice_init(&desc->tx_list, fsl_chan->ld_queue.prev);
 
 	spin_unlock_irqrestore(&fsl_chan->desc_lock, flags);
 
@@ -366,6 +380,7 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(
 	desc_sw = dma_pool_alloc(fsl_chan->desc_pool, GFP_ATOMIC, &pdesc);
 	if (desc_sw) {
 		memset(desc_sw, 0, sizeof(struct fsl_desc_sw));
+		INIT_LIST_HEAD(&desc_sw->tx_list);
 		dma_async_tx_descriptor_init(&desc_sw->async_tx,
 						&fsl_chan->common);
 		desc_sw->async_tx.tx_submit = fsl_dma_tx_submit;
@@ -455,7 +470,7 @@ fsl_dma_prep_interrupt(struct dma_chan *chan, unsigned long flags)
 	new->async_tx.flags = flags;
 
 	/* Insert the link descriptor to the LD ring */
-	list_add_tail(&new->node, &new->async_tx.tx_list);
+	list_add_tail(&new->node, &new->tx_list);
 
 	/* Set End-of-link to the last link descriptor of new list*/
 	set_ld_eol(fsl_chan, new);
@@ -513,7 +528,7 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
 		dma_dest += copy;
 
 		/* Insert the link descriptor to the LD ring */
-		list_add_tail(&new->node, &first->async_tx.tx_list);
+		list_add_tail(&new->node, &first->tx_list);
 	} while (len);
 
 	new->async_tx.flags = flags; /* client is in control of this ack */
@@ -528,7 +543,7 @@ fail:
 	if (!first)
 		return NULL;
 
-	list = &first->async_tx.tx_list;
+	list = &first->tx_list;
 	list_for_each_entry_safe_reverse(new, prev, list, node) {
 		list_del(&new->node);
 		dma_pool_free(fsl_chan->desc_pool, new, new->async_tx.phys);
@@ -538,6 +553,229 @@ fail:
 }
 
 /**
+ * fsl_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @chan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: DMAEngine flags
+ *
+ * Prepare a set of descriptors for a DMA_SLAVE transaction. Following the
+ * DMA_SLAVE API, this gets the device-specific information from the
+ * chan->private variable.
+ */
+static struct dma_async_tx_descriptor *fsl_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
+	enum dma_data_direction direction, unsigned long flags)
+{
+	struct fsl_dma_chan *fsl_chan;
+	struct fsl_desc_sw *first = NULL, *prev = NULL, *new = NULL;
+	struct fsl_dma_slave *slave;
+	struct list_head *tx_list;
+	size_t copy;
+
+	int i;
+	struct scatterlist *sg;
+	size_t sg_used;
+	size_t hw_used;
+	struct fsl_dma_hw_addr *hw;
+	dma_addr_t dma_dst, dma_src;
+
+	if (!chan)
+		return NULL;
+
+	if (!chan->private)
+		return NULL;
+
+	fsl_chan = to_fsl_chan(chan);
+	slave = chan->private;
+
+	if (list_empty(&slave->addresses))
+		return NULL;
+
+	hw = list_first_entry(&slave->addresses, struct fsl_dma_hw_addr, entry);
+	hw_used = 0;
+
+	/*
+	 * Build the hardware transaction to copy from the scatterlist to
+	 * the hardware, or from the hardware to the scatterlist
+	 *
+	 * If you are copying from the hardware to the scatterlist and it
+	 * takes two hardware entries to fill an entire page, then both
+	 * hardware entries will be coalesced into the same page
+	 *
+	 * If you are copying from the scatterlist to the hardware and a
+	 * single page can fill two hardware entries, then the data will
+	 * be read out of the page into the first hardware entry, and so on
+	 */
+	for_each_sg(sgl, sg, sg_len, i) {
+		sg_used = 0;
+
+		/* Loop until the entire scatterlist entry is used */
+		while (sg_used < sg_dma_len(sg)) {
+
+			/*
+			 * If we've used up the current hardware address/length
+			 * pair, we need to load a new one
+			 *
+			 * This is done in a while loop so that descriptors with
+			 * length == 0 will be skipped
+			 */
+			while (hw_used >= hw->length) {
+
+				/*
+				 * If the current hardware entry is the last
+				 * entry in the list, we're finished
+				 */
+				if (list_is_last(&hw->entry, &slave->addresses))
+					goto finished;
+
+				/* Get the next hardware address/length pair */
+				hw = list_entry(hw->entry.next,
+						struct fsl_dma_hw_addr, entry);
+				hw_used = 0;
+			}
+
+			/* Allocate the link descriptor from DMA pool */
+			new = fsl_dma_alloc_descriptor(fsl_chan);
+			if (!new) {
+				dev_err(fsl_chan->dev, "No free memory for "
+						       "link descriptor\n");
+				goto fail;
+			}
+#ifdef FSL_DMA_LD_DEBUG
+			dev_dbg(fsl_chan->dev, "new link desc alloc %p\n", new);
+#endif
+
+			/*
+			 * Calculate the maximum number of bytes to transfer,
+			 * making sure it is less than the DMA controller limit
+			 */
+			copy = min_t(size_t, sg_dma_len(sg) - sg_used,
+					     hw->length - hw_used);
+			copy = min_t(size_t, copy, FSL_DMA_BCR_MAX_CNT);
+
+			/*
+			 * DMA_FROM_DEVICE
+			 * from the hardware to the scatterlist
+			 *
+			 * DMA_TO_DEVICE
+			 * from the scatterlist to the hardware
+			 */
+			if (direction == DMA_FROM_DEVICE) {
+				dma_src = hw->address + hw_used;
+				dma_dst = sg_dma_address(sg) + sg_used;
+			} else {
+				dma_src = sg_dma_address(sg) + sg_used;
+				dma_dst = hw->address + hw_used;
+			}
+
+			/* Fill in the descriptor */
+			set_desc_cnt(fsl_chan, &new->hw, copy);
+			set_desc_src(fsl_chan, &new->hw, dma_src);
+			set_desc_dest(fsl_chan, &new->hw, dma_dst);
+
+			/*
+			 * If this is not the first descriptor, chain the
+			 * current descriptor after the previous descriptor
+			 */
+			if (!first) {
+				first = new;
+			} else {
+				set_desc_next(fsl_chan, &prev->hw,
+					      new->async_tx.phys);
+			}
+
+			new->async_tx.cookie = 0;
+			async_tx_ack(&new->async_tx);
+
+			prev = new;
+			sg_used += copy;
+			hw_used += copy;
+
+			/* Insert the link descriptor into the LD ring */
+			list_add_tail(&new->node, &first->tx_list);
+		}
+	}
+
+finished:
+
+	/* All of the hardware address/length pairs had length == 0 */
+	if (!first || !new)
+		return NULL;
+
+	new->async_tx.flags = flags;
+	new->async_tx.cookie = -EBUSY;
+
+	/* Set End-of-link to the last link descriptor of new list */
+	set_ld_eol(fsl_chan, new);
+
+	/* Enable extra controller features */
+	if (fsl_chan->set_src_loop_size)
+		fsl_chan->set_src_loop_size(fsl_chan, slave->src_loop_size);
+
+	if (fsl_chan->set_dest_loop_size)
+		fsl_chan->set_dest_loop_size(fsl_chan, slave->dst_loop_size);
+
+	if (fsl_chan->toggle_ext_start)
+		fsl_chan->toggle_ext_start(fsl_chan, slave->external_start);
+
+	if (fsl_chan->toggle_ext_pause)
+		fsl_chan->toggle_ext_pause(fsl_chan, slave->external_pause);
+
+	if (fsl_chan->set_request_count)
+		fsl_chan->set_request_count(fsl_chan, slave->request_count);
+
+	return &first->async_tx;
+
+fail:
+	/* If first was not set, then we failed to allocate the very first
+	 * descriptor, and we're done */
+	if (!first)
+		return NULL;
+
+	/*
+	 * First is set, so all of the descriptors we allocated have been added
+	 * to first->tx_list, INCLUDING "first" itself. Therefore we
+	 * must traverse the list backwards freeing each descriptor in turn
+	 *
+	 * We're re-using variables for the loop, oh well
+	 */
+	tx_list = &first->tx_list;
+	list_for_each_entry_safe_reverse(new, prev, tx_list, node) {
+		list_del_init(&new->node);
+		dma_pool_free(fsl_chan->desc_pool, new, new->async_tx.phys);
+	}
+
+	return NULL;
+}
+
+static void fsl_dma_device_terminate_all(struct dma_chan *chan)
+{
+	struct fsl_dma_chan *fsl_chan;
+	struct fsl_desc_sw *desc, *tmp;
+	unsigned long flags;
+
+	if (!chan)
+		return;
+
+	fsl_chan = to_fsl_chan(chan);
+
+	/* Halt the DMA engine */
+	dma_halt(fsl_chan);
+
+	spin_lock_irqsave(&fsl_chan->desc_lock, flags);
+
+	/* Remove and free all of the descriptors in the LD queue */
+	list_for_each_entry_safe(desc, tmp, &fsl_chan->ld_queue, node) {
+		list_del(&desc->node);
+		dma_pool_free(fsl_chan->desc_pool, desc, desc->async_tx.phys);
+	}
+
+	spin_unlock_irqrestore(&fsl_chan->desc_lock, flags);
+}
+
+/**
  * fsl_dma_update_completed_cookie - Update the completed cookie.
  * @fsl_chan : Freescale DMA channel
  */
@@ -883,6 +1121,7 @@ static int __devinit fsl_dma_chan_probe(struct fsl_dma_device *fdev,
 		new_fsl_chan->toggle_ext_start = fsl_chan_toggle_ext_start;
 		new_fsl_chan->set_src_loop_size = fsl_chan_set_src_loop_size;
 		new_fsl_chan->set_dest_loop_size = fsl_chan_set_dest_loop_size;
+		new_fsl_chan->set_request_count = fsl_chan_set_request_count;
 	}
 
 	spin_lock_init(&new_fsl_chan->desc_lock);
@@ -962,12 +1201,15 @@ static int __devinit of_fsl_dma_probe(struct of_device *dev,
 
 	dma_cap_set(DMA_MEMCPY, fdev->common.cap_mask);
 	dma_cap_set(DMA_INTERRUPT, fdev->common.cap_mask);
+	dma_cap_set(DMA_SLAVE, fdev->common.cap_mask);
 	fdev->common.device_alloc_chan_resources = fsl_dma_alloc_chan_resources;
 	fdev->common.device_free_chan_resources = fsl_dma_free_chan_resources;
 	fdev->common.device_prep_dma_interrupt = fsl_dma_prep_interrupt;
 	fdev->common.device_prep_dma_memcpy = fsl_dma_prep_memcpy;
 	fdev->common.device_is_tx_complete = fsl_dma_is_complete;
 	fdev->common.device_issue_pending = fsl_dma_memcpy_issue_pending;
+	fdev->common.device_prep_slave_sg = fsl_dma_prep_slave_sg;
+	fdev->common.device_terminate_all = fsl_dma_device_terminate_all;
 	fdev->common.dev = &dev->dev;
 
 	fdev->irq = irq_of_parse_and_map(dev->node, 0);
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index dc7f2686579..0df14cbb8ca 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -90,6 +90,7 @@ struct fsl_dma_ld_hw {
 struct fsl_desc_sw {
 	struct fsl_dma_ld_hw hw;
 	struct list_head node;
+	struct list_head tx_list;
 	struct dma_async_tx_descriptor async_tx;
 	struct list_head *ld;
 	void *priv;
@@ -143,10 +144,11 @@ struct fsl_dma_chan {
 	struct tasklet_struct tasklet;
 	u32 feature;
 
-	void (*toggle_ext_pause)(struct fsl_dma_chan *fsl_chan, int size);
+	void (*toggle_ext_pause)(struct fsl_dma_chan *fsl_chan, int enable);
 	void (*toggle_ext_start)(struct fsl_dma_chan *fsl_chan, int enable);
 	void (*set_src_loop_size)(struct fsl_dma_chan *fsl_chan, int size);
 	void (*set_dest_loop_size)(struct fsl_dma_chan *fsl_chan, int size);
+	void (*set_request_count)(struct fsl_dma_chan *fsl_chan, int size);
 };
 
 #define to_fsl_chan(chan) container_of(chan, struct fsl_dma_chan, common)
diff --git a/drivers/dma/ioat.c b/drivers/dma/ioat.c
deleted file mode 100644
index 2225bb6ba3d..00000000000
--- a/drivers/dma/ioat.c
+++ /dev/null
@@ -1,202 +0,0 @@
-/*
- * Intel I/OAT DMA Linux driver
- * Copyright(c) 2007 - 2009 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- */
-
-/*
- * This driver supports an Intel I/OAT DMA engine, which does asynchronous
- * copy operations.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/dca.h>
-#include "ioatdma.h"
-#include "ioatdma_registers.h"
-#include "ioatdma_hw.h"
-
-MODULE_VERSION(IOAT_DMA_VERSION);
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Intel Corporation");
-
-static struct pci_device_id ioat_pci_tbl[] = {
-	/* I/OAT v1 platforms */
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_CNB)  },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SCNB) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_UNISYS, PCI_DEVICE_ID_UNISYS_DMA_DIRECTOR) },
-
-	/* I/OAT v2 platforms */
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB) },
-
-	/* I/OAT v3 platforms */
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG0) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG1) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG2) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG3) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG4) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG5) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG6) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG7) },
-	{ 0, }
-};
-
-struct ioat_device {
-	struct pci_dev		*pdev;
-	void __iomem		*iobase;
-	struct ioatdma_device	*dma;
-	struct dca_provider	*dca;
-};
-
-static int __devinit ioat_probe(struct pci_dev *pdev,
-				const struct pci_device_id *id);
-static void __devexit ioat_remove(struct pci_dev *pdev);
-
-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 struct pci_driver ioat_pci_driver = {
-	.name		= "ioatdma",
-	.id_table	= ioat_pci_tbl,
-	.probe		= ioat_probe,
-	.remove		= __devexit_p(ioat_remove),
-};
-
-static int __devinit ioat_probe(struct pci_dev *pdev,
-				const struct pci_device_id *id)
-{
-	void __iomem *iobase;
-	struct ioat_device *device;
-	unsigned long mmio_start, mmio_len;
-	int err;
-
-	err = pci_enable_device(pdev);
-	if (err)
-		goto err_enable_device;
-
-	err = pci_request_regions(pdev, ioat_pci_driver.name);
-	if (err)
-		goto err_request_regions;
-
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err)
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (err)
-		goto err_set_dma_mask;
-
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (err)
-		goto err_set_dma_mask;
-
-	mmio_start = pci_resource_start(pdev, 0);
-	mmio_len = pci_resource_len(pdev, 0);
-	iobase = ioremap(mmio_start, mmio_len);
-	if (!iobase) {
-		err = -ENOMEM;
-		goto err_ioremap;
-	}
-
-	device = kzalloc(sizeof(*device), GFP_KERNEL);
-	if (!device) {
-		err = -ENOMEM;
-		goto err_kzalloc;
-	}
-	device->pdev = pdev;
-	pci_set_drvdata(pdev, device);
-	device->iobase = iobase;
-
-	pci_set_master(pdev);
-
-	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;
-
-	return 0;
-
-err_version:
-	kfree(device);
-err_kzalloc:
-	iounmap(iobase);
-err_ioremap:
-err_set_dma_mask:
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-err_request_regions:
-err_enable_device:
-	return err;
-}
-
-static void __devexit ioat_remove(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;
-	}
-
-	kfree(device);
-}
-
-static int __init ioat_init_module(void)
-{
-	return pci_register_driver(&ioat_pci_driver);
-}
-module_init(ioat_init_module);
-
-static void __exit ioat_exit_module(void)
-{
-	pci_unregister_driver(&ioat_pci_driver);
-}
-module_exit(ioat_exit_module);
diff --git a/drivers/dma/ioat/Makefile b/drivers/dma/ioat/Makefile
new file mode 100644
index 00000000000..8997d3fb905
--- /dev/null
+++ b/drivers/dma/ioat/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o
+ioatdma-objs := pci.o dma.o dma_v2.o dma_v3.o dca.o
diff --git a/drivers/dma/ioat_dca.c b/drivers/dma/ioat/dca.c
index c012a1e1504..69d02615c4d 100644
--- a/drivers/dma/ioat_dca.c
+++ b/drivers/dma/ioat/dca.c
@@ -33,8 +33,8 @@
 #define cpu_physical_id(cpu) (cpuid_ebx(1) >> 24)
 #endif
 
-#include "ioatdma.h"
-#include "ioatdma_registers.h"
+#include "dma.h"
+#include "registers.h"
 
 /*
  * Bit 7 of a tag map entry is the "valid" bit, if it is set then bits 0:6
@@ -242,7 +242,8 @@ static struct dca_ops ioat_dca_ops = {
 };
 
 
-struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
+struct dca_provider * __devinit
+ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
 {
 	struct dca_provider *dca;
 	struct ioat_dca_priv *ioatdca;
@@ -407,7 +408,8 @@ static int ioat2_dca_count_dca_slots(void __iomem *iobase, u16 dca_offset)
 	return slots;
 }
 
-struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase)
+struct dca_provider * __devinit
+ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase)
 {
 	struct dca_provider *dca;
 	struct ioat_dca_priv *ioatdca;
@@ -602,7 +604,8 @@ static int ioat3_dca_count_dca_slots(void *iobase, u16 dca_offset)
 	return slots;
 }
 
-struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase)
+struct dca_provider * __devinit
+ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase)
 {
 	struct dca_provider *dca;
 	struct ioat_dca_priv *ioatdca;
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
new file mode 100644
index 00000000000..c524d36d3c2
--- /dev/null
+++ b/drivers/dma/ioat/dma.c
@@ -0,0 +1,1238 @@
+/*
+ * Intel I/OAT DMA Linux driver
+ * Copyright(c) 2004 - 2009 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+
+/*
+ * This driver supports an Intel I/OAT DMA engine, which does asynchronous
+ * copy operations.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
+#include <linux/i7300_idle.h>
+#include "dma.h"
+#include "registers.h"
+#include "hw.h"
+
+int ioat_pending_level = 4;
+module_param(ioat_pending_level, int, 0644);
+MODULE_PARM_DESC(ioat_pending_level,
+		 "high-water mark for pushing ioat descriptors (default: 4)");
+
+/* internal functions */
+static void ioat1_cleanup(struct ioat_dma_chan *ioat);
+static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat);
+
+/**
+ * ioat_dma_do_interrupt - handler used for single vector interrupt mode
+ * @irq: interrupt id
+ * @data: interrupt data
+ */
+static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
+{
+	struct ioatdma_device *instance = data;
+	struct ioat_chan_common *chan;
+	unsigned long attnstatus;
+	int bit;
+	u8 intrctrl;
+
+	intrctrl = readb(instance->reg_base + IOAT_INTRCTRL_OFFSET);
+
+	if (!(intrctrl & IOAT_INTRCTRL_MASTER_INT_EN))
+		return IRQ_NONE;
+
+	if (!(intrctrl & IOAT_INTRCTRL_INT_STATUS)) {
+		writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
+		return IRQ_NONE;
+	}
+
+	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
+	for_each_bit(bit, &attnstatus, BITS_PER_LONG) {
+		chan = ioat_chan_by_index(instance, bit);
+		tasklet_schedule(&chan->cleanup_task);
+	}
+
+	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
+	return IRQ_HANDLED;
+}
+
+/**
+ * ioat_dma_do_interrupt_msix - handler used for vector-per-channel interrupt mode
+ * @irq: interrupt id
+ * @data: interrupt data
+ */
+static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data)
+{
+	struct ioat_chan_common *chan = data;
+
+	tasklet_schedule(&chan->cleanup_task);
+
+	return IRQ_HANDLED;
+}
+
+static void ioat1_cleanup_tasklet(unsigned long data);
+
+/* common channel initialization */
+void ioat_init_channel(struct ioatdma_device *device,
+		       struct ioat_chan_common *chan, int idx,
+		       void (*timer_fn)(unsigned long),
+		       void (*tasklet)(unsigned long),
+		       unsigned long ioat)
+{
+	struct dma_device *dma = &device->common;
+
+	chan->device = device;
+	chan->reg_base = device->reg_base + (0x80 * (idx + 1));
+	spin_lock_init(&chan->cleanup_lock);
+	chan->common.device = dma;
+	list_add_tail(&chan->common.device_node, &dma->channels);
+	device->idx[idx] = chan;
+	init_timer(&chan->timer);
+	chan->timer.function = timer_fn;
+	chan->timer.data = ioat;
+	tasklet_init(&chan->cleanup_task, tasklet, ioat);
+	tasklet_disable(&chan->cleanup_task);
+}
+
+static void ioat1_timer_event(unsigned long data);
+
+/**
+ * ioat1_dma_enumerate_channels - find and initialize the device's channels
+ * @device: the device to be enumerated
+ */
+static int ioat1_enumerate_channels(struct ioatdma_device *device)
+{
+	u8 xfercap_scale;
+	u32 xfercap;
+	int i;
+	struct ioat_dma_chan *ioat;
+	struct device *dev = &device->pdev->dev;
+	struct dma_device *dma = &device->common;
+
+	INIT_LIST_HEAD(&dma->channels);
+	dma->chancnt = readb(device->reg_base + IOAT_CHANCNT_OFFSET);
+	dma->chancnt &= 0x1f; /* bits [4:0] valid */
+	if (dma->chancnt > ARRAY_SIZE(device->idx)) {
+		dev_warn(dev, "(%d) exceeds max supported channels (%zu)\n",
+			 dma->chancnt, ARRAY_SIZE(device->idx));
+		dma->chancnt = ARRAY_SIZE(device->idx);
+	}
+	xfercap_scale = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
+	xfercap_scale &= 0x1f; /* bits [4:0] valid */
+	xfercap = (xfercap_scale == 0 ? -1 : (1UL << xfercap_scale));
+	dev_dbg(dev, "%s: xfercap = %d\n", __func__, xfercap);
+
+#ifdef  CONFIG_I7300_IDLE_IOAT_CHANNEL
+	if (i7300_idle_platform_probe(NULL, NULL, 1) == 0)
+		dma->chancnt--;
+#endif
+	for (i = 0; i < dma->chancnt; i++) {
+		ioat = devm_kzalloc(dev, sizeof(*ioat), GFP_KERNEL);
+		if (!ioat)
+			break;
+
+		ioat_init_channel(device, &ioat->base, i,
+				  ioat1_timer_event,
+				  ioat1_cleanup_tasklet,
+				  (unsigned long) ioat);
+		ioat->xfercap = xfercap;
+		spin_lock_init(&ioat->desc_lock);
+		INIT_LIST_HEAD(&ioat->free_desc);
+		INIT_LIST_HEAD(&ioat->used_desc);
+	}
+	dma->chancnt = i;
+	return i;
+}
+
+/**
+ * ioat_dma_memcpy_issue_pending - push potentially unrecognized appended
+ *                                 descriptors to hw
+ * @chan: DMA channel handle
+ */
+static inline void
+__ioat1_dma_memcpy_issue_pending(struct ioat_dma_chan *ioat)
+{
+	void __iomem *reg_base = ioat->base.reg_base;
+
+	dev_dbg(to_dev(&ioat->base), "%s: pending: %d\n",
+		__func__, ioat->pending);
+	ioat->pending = 0;
+	writeb(IOAT_CHANCMD_APPEND, reg_base + IOAT1_CHANCMD_OFFSET);
+}
+
+static void ioat1_dma_memcpy_issue_pending(struct dma_chan *chan)
+{
+	struct ioat_dma_chan *ioat = to_ioat_chan(chan);
+
+	if (ioat->pending > 0) {
+		spin_lock_bh(&ioat->desc_lock);
+		__ioat1_dma_memcpy_issue_pending(ioat);
+		spin_unlock_bh(&ioat->desc_lock);
+	}
+}
+
+/**
+ * ioat1_reset_channel - restart a channel
+ * @ioat: IOAT DMA channel handle
+ */
+static void ioat1_reset_channel(struct ioat_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	void __iomem *reg_base = chan->reg_base;
+	u32 chansts, chanerr;
+
+	dev_warn(to_dev(chan), "reset\n");
+	chanerr = readl(reg_base + IOAT_CHANERR_OFFSET);
+	chansts = *chan->completion & IOAT_CHANSTS_STATUS;
+	if (chanerr) {
+		dev_err(to_dev(chan),
+			"chan%d, CHANSTS = 0x%08x CHANERR = 0x%04x, clearing\n",
+			chan_num(chan), chansts, chanerr);
+		writel(chanerr, reg_base + IOAT_CHANERR_OFFSET);
+	}
+
+	/*
+	 * whack it upside the head with a reset
+	 * and wait for things to settle out.
+	 * force the pending count to a really big negative
+	 * to make sure no one forces an issue_pending
+	 * while we're waiting.
+	 */
+
+	ioat->pending = INT_MIN;
+	writeb(IOAT_CHANCMD_RESET,
+	       reg_base + IOAT_CHANCMD_OFFSET(chan->device->version));
+	set_bit(IOAT_RESET_PENDING, &chan->state);
+	mod_timer(&chan->timer, jiffies + RESET_DELAY);
+}
+
+static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct dma_chan *c = tx->chan;
+	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+	struct ioat_desc_sw *desc = tx_to_ioat_desc(tx);
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioat_desc_sw *first;
+	struct ioat_desc_sw *chain_tail;
+	dma_cookie_t cookie;
+
+	spin_lock_bh(&ioat->desc_lock);
+	/* cookie incr and addition to used_list must be atomic */
+	cookie = c->cookie;
+	cookie++;
+	if (cookie < 0)
+		cookie = 1;
+	c->cookie = cookie;
+	tx->cookie = cookie;
+	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
+
+	/* write address into NextDescriptor field of last desc in chain */
+	first = to_ioat_desc(desc->tx_list.next);
+	chain_tail = to_ioat_desc(ioat->used_desc.prev);
+	/* make descriptor updates globally visible before chaining */
+	wmb();
+	chain_tail->hw->next = first->txd.phys;
+	list_splice_tail_init(&desc->tx_list, &ioat->used_desc);
+	dump_desc_dbg(ioat, chain_tail);
+	dump_desc_dbg(ioat, first);
+
+	if (!test_and_set_bit(IOAT_COMPLETION_PENDING, &chan->state))
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+
+	ioat->active += desc->hw->tx_cnt;
+	ioat->pending += desc->hw->tx_cnt;
+	if (ioat->pending >= ioat_pending_level)
+		__ioat1_dma_memcpy_issue_pending(ioat);
+	spin_unlock_bh(&ioat->desc_lock);
+
+	return cookie;
+}
+
+/**
+ * ioat_dma_alloc_descriptor - allocate and return a sw and hw descriptor pair
+ * @ioat: the channel supplying the memory pool for the descriptors
+ * @flags: allocation flags
+ */
+static struct ioat_desc_sw *
+ioat_dma_alloc_descriptor(struct ioat_dma_chan *ioat, gfp_t flags)
+{
+	struct ioat_dma_descriptor *desc;
+	struct ioat_desc_sw *desc_sw;
+	struct ioatdma_device *ioatdma_device;
+	dma_addr_t phys;
+
+	ioatdma_device = ioat->base.device;
+	desc = pci_pool_alloc(ioatdma_device->dma_pool, flags, &phys);
+	if (unlikely(!desc))
+		return NULL;
+
+	desc_sw = kzalloc(sizeof(*desc_sw), flags);
+	if (unlikely(!desc_sw)) {
+		pci_pool_free(ioatdma_device->dma_pool, desc, phys);
+		return NULL;
+	}
+
+	memset(desc, 0, sizeof(*desc));
+
+	INIT_LIST_HEAD(&desc_sw->tx_list);
+	dma_async_tx_descriptor_init(&desc_sw->txd, &ioat->base.common);
+	desc_sw->txd.tx_submit = ioat1_tx_submit;
+	desc_sw->hw = desc;
+	desc_sw->txd.phys = phys;
+	set_desc_id(desc_sw, -1);
+
+	return desc_sw;
+}
+
+static int ioat_initial_desc_count = 256;
+module_param(ioat_initial_desc_count, int, 0644);
+MODULE_PARM_DESC(ioat_initial_desc_count,
+		 "ioat1: initial descriptors per channel (default: 256)");
+/**
+ * ioat1_dma_alloc_chan_resources - returns the number of allocated descriptors
+ * @chan: the channel to be filled out
+ */
+static int ioat1_dma_alloc_chan_resources(struct dma_chan *c)
+{
+	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioat_desc_sw *desc;
+	u32 chanerr;
+	int i;
+	LIST_HEAD(tmp_list);
+
+	/* have we already been set up? */
+	if (!list_empty(&ioat->free_desc))
+		return ioat->desccount;
+
+	/* Setup register to interrupt and write completion status on error */
+	writew(IOAT_CHANCTRL_RUN, chan->reg_base + IOAT_CHANCTRL_OFFSET);
+
+	chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+	if (chanerr) {
+		dev_err(to_dev(chan), "CHANERR = %x, clearing\n", chanerr);
+		writel(chanerr, chan->reg_base + IOAT_CHANERR_OFFSET);
+	}
+
+	/* Allocate descriptors */
+	for (i = 0; i < ioat_initial_desc_count; i++) {
+		desc = ioat_dma_alloc_descriptor(ioat, GFP_KERNEL);
+		if (!desc) {
+			dev_err(to_dev(chan), "Only %d initial descriptors\n", i);
+			break;
+		}
+		set_desc_id(desc, i);
+		list_add_tail(&desc->node, &tmp_list);
+	}
+	spin_lock_bh(&ioat->desc_lock);
+	ioat->desccount = i;
+	list_splice(&tmp_list, &ioat->free_desc);
+	spin_unlock_bh(&ioat->desc_lock);
+
+	/* allocate a completion writeback area */
+	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
+	chan->completion = pci_pool_alloc(chan->device->completion_pool,
+					  GFP_KERNEL, &chan->completion_dma);
+	memset(chan->completion, 0, sizeof(*chan->completion));
+	writel(((u64) chan->completion_dma) & 0x00000000FFFFFFFF,
+	       chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
+	writel(((u64) chan->completion_dma) >> 32,
+	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
+
+	tasklet_enable(&chan->cleanup_task);
+	ioat1_dma_start_null_desc(ioat);  /* give chain to dma device */
+	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
+		__func__, ioat->desccount);
+	return ioat->desccount;
+}
+
+/**
+ * ioat1_dma_free_chan_resources - release all the descriptors
+ * @chan: the channel to be cleaned
+ */
+static void ioat1_dma_free_chan_resources(struct dma_chan *c)
+{
+	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioatdma_device *ioatdma_device = chan->device;
+	struct ioat_desc_sw *desc, *_desc;
+	int in_use_descs = 0;
+
+	/* Before freeing channel resources first check
+	 * if they have been previously allocated for this channel.
+	 */
+	if (ioat->desccount == 0)
+		return;
+
+	tasklet_disable(&chan->cleanup_task);
+	del_timer_sync(&chan->timer);
+	ioat1_cleanup(ioat);
+
+	/* Delay 100ms after reset to allow internal DMA logic to quiesce
+	 * before removing DMA descriptor resources.
+	 */
+	writeb(IOAT_CHANCMD_RESET,
+	       chan->reg_base + IOAT_CHANCMD_OFFSET(chan->device->version));
+	mdelay(100);
+
+	spin_lock_bh(&ioat->desc_lock);
+	list_for_each_entry_safe(desc, _desc, &ioat->used_desc, node) {
+		dev_dbg(to_dev(chan), "%s: freeing %d from used list\n",
+			__func__, desc_id(desc));
+		dump_desc_dbg(ioat, desc);
+		in_use_descs++;
+		list_del(&desc->node);
+		pci_pool_free(ioatdma_device->dma_pool, desc->hw,
+			      desc->txd.phys);
+		kfree(desc);
+	}
+	list_for_each_entry_safe(desc, _desc,
+				 &ioat->free_desc, node) {
+		list_del(&desc->node);
+		pci_pool_free(ioatdma_device->dma_pool, desc->hw,
+			      desc->txd.phys);
+		kfree(desc);
+	}
+	spin_unlock_bh(&ioat->desc_lock);
+
+	pci_pool_free(ioatdma_device->completion_pool,
+		      chan->completion,
+		      chan->completion_dma);
+
+	/* one is ok since we left it on there on purpose */
+	if (in_use_descs > 1)
+		dev_err(to_dev(chan), "Freeing %d in use descriptors!\n",
+			in_use_descs - 1);
+
+	chan->last_completion = 0;
+	chan->completion_dma = 0;
+	ioat->pending = 0;
+	ioat->desccount = 0;
+}
+
+/**
+ * ioat1_dma_get_next_descriptor - return the next available descriptor
+ * @ioat: IOAT DMA channel handle
+ *
+ * Gets the next descriptor from the chain, and must be called with the
+ * channel's desc_lock held.  Allocates more descriptors if the channel
+ * has run out.
+ */
+static struct ioat_desc_sw *
+ioat1_dma_get_next_descriptor(struct ioat_dma_chan *ioat)
+{
+	struct ioat_desc_sw *new;
+
+	if (!list_empty(&ioat->free_desc)) {
+		new = to_ioat_desc(ioat->free_desc.next);
+		list_del(&new->node);
+	} else {
+		/* try to get another desc */
+		new = ioat_dma_alloc_descriptor(ioat, GFP_ATOMIC);
+		if (!new) {
+			dev_err(to_dev(&ioat->base), "alloc failed\n");
+			return NULL;
+		}
+	}
+	dev_dbg(to_dev(&ioat->base), "%s: allocated: %d\n",
+		__func__, desc_id(new));
+	prefetch(new->hw);
+	return new;
+}
+
+static struct dma_async_tx_descriptor *
+ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
+		      dma_addr_t dma_src, size_t len, unsigned long flags)
+{
+	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+	struct ioat_desc_sw *desc;
+	size_t copy;
+	LIST_HEAD(chain);
+	dma_addr_t src = dma_src;
+	dma_addr_t dest = dma_dest;
+	size_t total_len = len;
+	struct ioat_dma_descriptor *hw = NULL;
+	int tx_cnt = 0;
+
+	spin_lock_bh(&ioat->desc_lock);
+	desc = ioat1_dma_get_next_descriptor(ioat);
+	do {
+		if (!desc)
+			break;
+
+		tx_cnt++;
+		copy = min_t(size_t, len, ioat->xfercap);
+
+		hw = desc->hw;
+		hw->size = copy;
+		hw->ctl = 0;
+		hw->src_addr = src;
+		hw->dst_addr = dest;
+
+		list_add_tail(&desc->node, &chain);
+
+		len -= copy;
+		dest += copy;
+		src += copy;
+		if (len) {
+			struct ioat_desc_sw *next;
+
+			async_tx_ack(&desc->txd);
+			next = ioat1_dma_get_next_descriptor(ioat);
+			hw->next = next ? next->txd.phys : 0;
+			dump_desc_dbg(ioat, desc);
+			desc = next;
+		} else
+			hw->next = 0;
+	} while (len);
+
+	if (!desc) {
+		struct ioat_chan_common *chan = &ioat->base;
+
+		dev_err(to_dev(chan),
+			"chan%d - get_next_desc failed\n", chan_num(chan));
+		list_splice(&chain, &ioat->free_desc);
+		spin_unlock_bh(&ioat->desc_lock);
+		return NULL;
+	}
+	spin_unlock_bh(&ioat->desc_lock);
+
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	list_splice(&chain, &desc->tx_list);
+	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	hw->ctl_f.compl_write = 1;
+	hw->tx_cnt = tx_cnt;
+	dump_desc_dbg(ioat, desc);
+
+	return &desc->txd;
+}
+
+static void ioat1_cleanup_tasklet(unsigned long data)
+{
+	struct ioat_dma_chan *chan = (void *)data;
+
+	ioat1_cleanup(chan);
+	writew(IOAT_CHANCTRL_RUN, chan->base.reg_base + IOAT_CHANCTRL_OFFSET);
+}
+
+void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
+		    size_t len, struct ioat_dma_descriptor *hw)
+{
+	struct pci_dev *pdev = chan->device->pdev;
+	size_t offset = len - hw->size;
+
+	if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
+		ioat_unmap(pdev, hw->dst_addr - offset, len,
+			   PCI_DMA_FROMDEVICE, flags, 1);
+
+	if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP))
+		ioat_unmap(pdev, hw->src_addr - offset, len,
+			   PCI_DMA_TODEVICE, flags, 0);
+}
+
+unsigned long ioat_get_current_completion(struct ioat_chan_common *chan)
+{
+	unsigned long phys_complete;
+	u64 completion;
+
+	completion = *chan->completion;
+	phys_complete = ioat_chansts_to_addr(completion);
+
+	dev_dbg(to_dev(chan), "%s: phys_complete: %#llx\n", __func__,
+		(unsigned long long) phys_complete);
+
+	if (is_ioat_halted(completion)) {
+		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+		dev_err(to_dev(chan), "Channel halted, chanerr = %x\n",
+			chanerr);
+
+		/* TODO do something to salvage the situation */
+	}
+
+	return phys_complete;
+}
+
+bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
+			   unsigned long *phys_complete)
+{
+	*phys_complete = ioat_get_current_completion(chan);
+	if (*phys_complete == chan->last_completion)
+		return false;
+	clear_bit(IOAT_COMPLETION_ACK, &chan->state);
+	mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+
+	return true;
+}
+
+static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	struct list_head *_desc, *n;
+	struct dma_async_tx_descriptor *tx;
+
+	dev_dbg(to_dev(chan), "%s: phys_complete: %lx\n",
+		 __func__, phys_complete);
+	list_for_each_safe(_desc, n, &ioat->used_desc) {
+		struct ioat_desc_sw *desc;
+
+		prefetch(n);
+		desc = list_entry(_desc, typeof(*desc), node);
+		tx = &desc->txd;
+		/*
+		 * Incoming DMA requests may use multiple descriptors,
+		 * due to exceeding xfercap, perhaps. If so, only the
+		 * last one will have a cookie, and require unmapping.
+		 */
+		dump_desc_dbg(ioat, desc);
+		if (tx->cookie) {
+			chan->completed_cookie = tx->cookie;
+			tx->cookie = 0;
+			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
+			ioat->active -= desc->hw->tx_cnt;
+			if (tx->callback) {
+				tx->callback(tx->callback_param);
+				tx->callback = NULL;
+			}
+		}
+
+		if (tx->phys != phys_complete) {
+			/*
+			 * a completed entry, but not the last, so clean
+			 * up if the client is done with the descriptor
+			 */
+			if (async_tx_test_ack(tx))
+				list_move_tail(&desc->node, &ioat->free_desc);
+		} else {
+			/*
+			 * last used desc. Do not remove, so we can
+			 * append from it.
+			 */
+
+			/* if nothing else is pending, cancel the
+			 * completion timeout
+			 */
+			if (n == &ioat->used_desc) {
+				dev_dbg(to_dev(chan),
+					"%s cancel completion timeout\n",
+					__func__);
+				clear_bit(IOAT_COMPLETION_PENDING, &chan->state);
+			}
+
+			/* TODO check status bits? */
+			break;
+		}
+	}
+
+	chan->last_completion = phys_complete;
+}
+
+/**
+ * ioat1_cleanup - cleanup up finished descriptors
+ * @chan: ioat channel to be cleaned up
+ *
+ * To prevent lock contention we defer cleanup when the locks are
+ * contended with a terminal timeout that forces cleanup and catches
+ * completion notification errors.
+ */
+static void ioat1_cleanup(struct ioat_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	unsigned long phys_complete;
+
+	prefetch(chan->completion);
+
+	if (!spin_trylock_bh(&chan->cleanup_lock))
+		return;
+
+	if (!ioat_cleanup_preamble(chan, &phys_complete)) {
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	}
+
+	if (!spin_trylock_bh(&ioat->desc_lock)) {
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	}
+
+	__cleanup(ioat, phys_complete);
+
+	spin_unlock_bh(&ioat->desc_lock);
+	spin_unlock_bh(&chan->cleanup_lock);
+}
+
+static void ioat1_timer_event(unsigned long data)
+{
+	struct ioat_dma_chan *ioat = (void *) data;
+	struct ioat_chan_common *chan = &ioat->base;
+
+	dev_dbg(to_dev(chan), "%s: state: %lx\n", __func__, chan->state);
+
+	spin_lock_bh(&chan->cleanup_lock);
+	if (test_and_clear_bit(IOAT_RESET_PENDING, &chan->state)) {
+		struct ioat_desc_sw *desc;
+
+		spin_lock_bh(&ioat->desc_lock);
+
+		/* restart active descriptors */
+		desc = to_ioat_desc(ioat->used_desc.prev);
+		ioat_set_chainaddr(ioat, desc->txd.phys);
+		ioat_start(chan);
+
+		ioat->pending = 0;
+		set_bit(IOAT_COMPLETION_PENDING, &chan->state);
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+		spin_unlock_bh(&ioat->desc_lock);
+	} else if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
+		unsigned long phys_complete;
+
+		spin_lock_bh(&ioat->desc_lock);
+		/* if we haven't made progress and we have already
+		 * acknowledged a pending completion once, then be more
+		 * forceful with a restart
+		 */
+		if (ioat_cleanup_preamble(chan, &phys_complete))
+			__cleanup(ioat, phys_complete);
+		else if (test_bit(IOAT_COMPLETION_ACK, &chan->state))
+			ioat1_reset_channel(ioat);
+		else {
+			u64 status = ioat_chansts(chan);
+
+			/* manually update the last completion address */
+			if (ioat_chansts_to_addr(status) != 0)
+				*chan->completion = status;
+
+			set_bit(IOAT_COMPLETION_ACK, &chan->state);
+			mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+		}
+		spin_unlock_bh(&ioat->desc_lock);
+	}
+	spin_unlock_bh(&chan->cleanup_lock);
+}
+
+static enum dma_status
+ioat1_dma_is_complete(struct dma_chan *c, dma_cookie_t cookie,
+		      dma_cookie_t *done, dma_cookie_t *used)
+{
+	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+
+	if (ioat_is_complete(c, cookie, done, used) == DMA_SUCCESS)
+		return DMA_SUCCESS;
+
+	ioat1_cleanup(ioat);
+
+	return ioat_is_complete(c, cookie, done, used);
+}
+
+static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioat_desc_sw *desc;
+	struct ioat_dma_descriptor *hw;
+
+	spin_lock_bh(&ioat->desc_lock);
+
+	desc = ioat1_dma_get_next_descriptor(ioat);
+
+	if (!desc) {
+		dev_err(to_dev(chan),
+			"Unable to start null desc - get next desc failed\n");
+		spin_unlock_bh(&ioat->desc_lock);
+		return;
+	}
+
+	hw = desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = 1;
+	hw->ctl_f.compl_write = 1;
+	/* set size to non-zero value (channel returns error when size is 0) */
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	hw->src_addr = 0;
+	hw->dst_addr = 0;
+	async_tx_ack(&desc->txd);
+	hw->next = 0;
+	list_add_tail(&desc->node, &ioat->used_desc);
+	dump_desc_dbg(ioat, desc);
+
+	ioat_set_chainaddr(ioat, desc->txd.phys);
+	ioat_start(chan);
+	spin_unlock_bh(&ioat->desc_lock);
+}
+
+/*
+ * Perform a IOAT transaction to verify the HW works.
+ */
+#define IOAT_TEST_SIZE 2000
+
+static void __devinit ioat_dma_test_callback(void *dma_async_param)
+{
+	struct completion *cmp = dma_async_param;
+
+	complete(cmp);
+}
+
+/**
+ * ioat_dma_self_test - Perform a IOAT transaction to verify the HW works.
+ * @device: device to be tested
+ */
+int __devinit ioat_dma_self_test(struct ioatdma_device *device)
+{
+	int i;
+	u8 *src;
+	u8 *dest;
+	struct dma_device *dma = &device->common;
+	struct device *dev = &device->pdev->dev;
+	struct dma_chan *dma_chan;
+	struct dma_async_tx_descriptor *tx;
+	dma_addr_t dma_dest, dma_src;
+	dma_cookie_t cookie;
+	int err = 0;
+	struct completion cmp;
+	unsigned long tmo;
+	unsigned long flags;
+
+	src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
+	if (!src)
+		return -ENOMEM;
+	dest = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
+	if (!dest) {
+		kfree(src);
+		return -ENOMEM;
+	}
+
+	/* Fill in src buffer */
+	for (i = 0; i < IOAT_TEST_SIZE; i++)
+		src[i] = (u8)i;
+
+	/* Start copy, using first DMA channel */
+	dma_chan = container_of(dma->channels.next, struct dma_chan,
+				device_node);
+	if (dma->device_alloc_chan_resources(dma_chan) < 1) {
+		dev_err(dev, "selftest cannot allocate chan resource\n");
+		err = -ENODEV;
+		goto out;
+	}
+
+	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
+	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+	flags = DMA_COMPL_SRC_UNMAP_SINGLE | DMA_COMPL_DEST_UNMAP_SINGLE |
+		DMA_PREP_INTERRUPT;
+	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
+						   IOAT_TEST_SIZE, flags);
+	if (!tx) {
+		dev_err(dev, "Self-test prep failed, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test setup failed, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (tmo == 0 ||
+	    dma->device_is_tx_complete(dma_chan, cookie, NULL, NULL)
+					!= DMA_SUCCESS) {
+		dev_err(dev, "Self-test copy timed out, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
+		dev_err(dev, "Self-test copy failed compare, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+free_resources:
+	dma->device_free_chan_resources(dma_chan);
+out:
+	kfree(src);
+	kfree(dest);
+	return err;
+}
+
+static char ioat_interrupt_style[32] = "msix";
+module_param_string(ioat_interrupt_style, ioat_interrupt_style,
+		    sizeof(ioat_interrupt_style), 0644);
+MODULE_PARM_DESC(ioat_interrupt_style,
+		 "set ioat interrupt style: msix (default), "
+		 "msix-single-vector, msi, intx)");
+
+/**
+ * ioat_dma_setup_interrupts - setup interrupt handler
+ * @device: ioat device
+ */
+static int ioat_dma_setup_interrupts(struct ioatdma_device *device)
+{
+	struct ioat_chan_common *chan;
+	struct pci_dev *pdev = device->pdev;
+	struct device *dev = &pdev->dev;
+	struct msix_entry *msix;
+	int i, j, msixcnt;
+	int err = -EINVAL;
+	u8 intrctrl = 0;
+
+	if (!strcmp(ioat_interrupt_style, "msix"))
+		goto msix;
+	if (!strcmp(ioat_interrupt_style, "msix-single-vector"))
+		goto msix_single_vector;
+	if (!strcmp(ioat_interrupt_style, "msi"))
+		goto msi;
+	if (!strcmp(ioat_interrupt_style, "intx"))
+		goto intx;
+	dev_err(dev, "invalid ioat_interrupt_style %s\n", ioat_interrupt_style);
+	goto err_no_irq;
+
+msix:
+	/* The number of MSI-X vectors should equal the number of channels */
+	msixcnt = device->common.chancnt;
+	for (i = 0; i < msixcnt; i++)
+		device->msix_entries[i].entry = i;
+
+	err = pci_enable_msix(pdev, device->msix_entries, msixcnt);
+	if (err < 0)
+		goto msi;
+	if (err > 0)
+		goto msix_single_vector;
+
+	for (i = 0; i < msixcnt; i++) {
+		msix = &device->msix_entries[i];
+		chan = ioat_chan_by_index(device, i);
+		err = devm_request_irq(dev, msix->vector,
+				       ioat_dma_do_interrupt_msix, 0,
+				       "ioat-msix", chan);
+		if (err) {
+			for (j = 0; j < i; j++) {
+				msix = &device->msix_entries[j];
+				chan = ioat_chan_by_index(device, j);
+				devm_free_irq(dev, msix->vector, chan);
+			}
+			goto msix_single_vector;
+		}
+	}
+	intrctrl |= IOAT_INTRCTRL_MSIX_VECTOR_CONTROL;
+	goto done;
+
+msix_single_vector:
+	msix = &device->msix_entries[0];
+	msix->entry = 0;
+	err = pci_enable_msix(pdev, device->msix_entries, 1);
+	if (err)
+		goto msi;
+
+	err = devm_request_irq(dev, msix->vector, ioat_dma_do_interrupt, 0,
+			       "ioat-msix", device);
+	if (err) {
+		pci_disable_msix(pdev);
+		goto msi;
+	}
+	goto done;
+
+msi:
+	err = pci_enable_msi(pdev);
+	if (err)
+		goto intx;
+
+	err = devm_request_irq(dev, pdev->irq, ioat_dma_do_interrupt, 0,
+			       "ioat-msi", device);
+	if (err) {
+		pci_disable_msi(pdev);
+		goto intx;
+	}
+	goto done;
+
+intx:
+	err = devm_request_irq(dev, pdev->irq, ioat_dma_do_interrupt,
+			       IRQF_SHARED, "ioat-intx", device);
+	if (err)
+		goto err_no_irq;
+
+done:
+	if (device->intr_quirk)
+		device->intr_quirk(device);
+	intrctrl |= IOAT_INTRCTRL_MASTER_INT_EN;
+	writeb(intrctrl, device->reg_base + IOAT_INTRCTRL_OFFSET);
+	return 0;
+
+err_no_irq:
+	/* Disable all interrupt generation */
+	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
+	dev_err(dev, "no usable interrupts\n");
+	return err;
+}
+
+static void ioat_disable_interrupts(struct ioatdma_device *device)
+{
+	/* Disable all interrupt generation */
+	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
+}
+
+int __devinit ioat_probe(struct ioatdma_device *device)
+{
+	int err = -ENODEV;
+	struct dma_device *dma = &device->common;
+	struct pci_dev *pdev = device->pdev;
+	struct device *dev = &pdev->dev;
+
+	/* DMA coherent memory pool for DMA descriptor allocations */
+	device->dma_pool = pci_pool_create("dma_desc_pool", pdev,
+					   sizeof(struct ioat_dma_descriptor),
+					   64, 0);
+	if (!device->dma_pool) {
+		err = -ENOMEM;
+		goto err_dma_pool;
+	}
+
+	device->completion_pool = pci_pool_create("completion_pool", pdev,
+						  sizeof(u64), SMP_CACHE_BYTES,
+						  SMP_CACHE_BYTES);
+
+	if (!device->completion_pool) {
+		err = -ENOMEM;
+		goto err_completion_pool;
+	}
+
+	device->enumerate_channels(device);
+
+	dma_cap_set(DMA_MEMCPY, dma->cap_mask);
+	dma->dev = &pdev->dev;
+
+	if (!dma->chancnt) {
+		dev_err(dev, "zero channels detected\n");
+		goto err_setup_interrupts;
+	}
+
+	err = ioat_dma_setup_interrupts(device);
+	if (err)
+		goto err_setup_interrupts;
+
+	err = device->self_test(device);
+	if (err)
+		goto err_self_test;
+
+	return 0;
+
+err_self_test:
+	ioat_disable_interrupts(device);
+err_setup_interrupts:
+	pci_pool_destroy(device->completion_pool);
+err_completion_pool:
+	pci_pool_destroy(device->dma_pool);
+err_dma_pool:
+	return err;
+}
+
+int __devinit ioat_register(struct ioatdma_device *device)
+{
+	int err = dma_async_device_register(&device->common);
+
+	if (err) {
+		ioat_disable_interrupts(device);
+		pci_pool_destroy(device->completion_pool);
+		pci_pool_destroy(device->dma_pool);
+	}
+
+	return err;
+}
+
+/* ioat1_intr_quirk - fix up dma ctrl register to enable / disable msi */
+static void ioat1_intr_quirk(struct ioatdma_device *device)
+{
+	struct pci_dev *pdev = device->pdev;
+	u32 dmactrl;
+
+	pci_read_config_dword(pdev, IOAT_PCI_DMACTRL_OFFSET, &dmactrl);
+	if (pdev->msi_enabled)
+		dmactrl |= IOAT_PCI_DMACTRL_MSI_EN;
+	else
+		dmactrl &= ~IOAT_PCI_DMACTRL_MSI_EN;
+	pci_write_config_dword(pdev, IOAT_PCI_DMACTRL_OFFSET, dmactrl);
+}
+
+static ssize_t ring_size_show(struct dma_chan *c, char *page)
+{
+	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+
+	return sprintf(page, "%d\n", ioat->desccount);
+}
+static struct ioat_sysfs_entry ring_size_attr = __ATTR_RO(ring_size);
+
+static ssize_t ring_active_show(struct dma_chan *c, char *page)
+{
+	struct ioat_dma_chan *ioat = to_ioat_chan(c);
+
+	return sprintf(page, "%d\n", ioat->active);
+}
+static struct ioat_sysfs_entry ring_active_attr = __ATTR_RO(ring_active);
+
+static ssize_t cap_show(struct dma_chan *c, char *page)
+{
+	struct dma_device *dma = c->device;
+
+	return sprintf(page, "copy%s%s%s%s%s%s\n",
+		       dma_has_cap(DMA_PQ, dma->cap_mask) ? " pq" : "",
+		       dma_has_cap(DMA_PQ_VAL, dma->cap_mask) ? " pq_val" : "",
+		       dma_has_cap(DMA_XOR, dma->cap_mask) ? " xor" : "",
+		       dma_has_cap(DMA_XOR_VAL, dma->cap_mask) ? " xor_val" : "",
+		       dma_has_cap(DMA_MEMSET, dma->cap_mask)  ? " fill" : "",
+		       dma_has_cap(DMA_INTERRUPT, dma->cap_mask) ? " intr" : "");
+
+}
+struct ioat_sysfs_entry ioat_cap_attr = __ATTR_RO(cap);
+
+static ssize_t version_show(struct dma_chan *c, char *page)
+{
+	struct dma_device *dma = c->device;
+	struct ioatdma_device *device = to_ioatdma_device(dma);
+
+	return sprintf(page, "%d.%d\n",
+		       device->version >> 4, device->version & 0xf);
+}
+struct ioat_sysfs_entry ioat_version_attr = __ATTR_RO(version);
+
+static struct attribute *ioat1_attrs[] = {
+	&ring_size_attr.attr,
+	&ring_active_attr.attr,
+	&ioat_cap_attr.attr,
+	&ioat_version_attr.attr,
+	NULL,
+};
+
+static ssize_t
+ioat_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct ioat_sysfs_entry *entry;
+	struct ioat_chan_common *chan;
+
+	entry = container_of(attr, struct ioat_sysfs_entry, attr);
+	chan = container_of(kobj, struct ioat_chan_common, kobj);
+
+	if (!entry->show)
+		return -EIO;
+	return entry->show(&chan->common, page);
+}
+
+struct sysfs_ops ioat_sysfs_ops = {
+	.show	= ioat_attr_show,
+};
+
+static struct kobj_type ioat1_ktype = {
+	.sysfs_ops = &ioat_sysfs_ops,
+	.default_attrs = ioat1_attrs,
+};
+
+void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type)
+{
+	struct dma_device *dma = &device->common;
+	struct dma_chan *c;
+
+	list_for_each_entry(c, &dma->channels, device_node) {
+		struct ioat_chan_common *chan = to_chan_common(c);
+		struct kobject *parent = &c->dev->device.kobj;
+		int err;
+
+		err = kobject_init_and_add(&chan->kobj, type, parent, "quickdata");
+		if (err) {
+			dev_warn(to_dev(chan),
+				 "sysfs init error (%d), continuing...\n", err);
+			kobject_put(&chan->kobj);
+			set_bit(IOAT_KOBJ_INIT_FAIL, &chan->state);
+		}
+	}
+}
+
+void ioat_kobject_del(struct ioatdma_device *device)
+{
+	struct dma_device *dma = &device->common;
+	struct dma_chan *c;
+
+	list_for_each_entry(c, &dma->channels, device_node) {
+		struct ioat_chan_common *chan = to_chan_common(c);
+
+		if (!test_bit(IOAT_KOBJ_INIT_FAIL, &chan->state)) {
+			kobject_del(&chan->kobj);
+			kobject_put(&chan->kobj);
+		}
+	}
+}
+
+int __devinit ioat1_dma_probe(struct ioatdma_device *device, int dca)
+{
+	struct pci_dev *pdev = device->pdev;
+	struct dma_device *dma;
+	int err;
+
+	device->intr_quirk = ioat1_intr_quirk;
+	device->enumerate_channels = ioat1_enumerate_channels;
+	device->self_test = ioat_dma_self_test;
+	dma = &device->common;
+	dma->device_prep_dma_memcpy = ioat1_dma_prep_memcpy;
+	dma->device_issue_pending = ioat1_dma_memcpy_issue_pending;
+	dma->device_alloc_chan_resources = ioat1_dma_alloc_chan_resources;
+	dma->device_free_chan_resources = ioat1_dma_free_chan_resources;
+	dma->device_is_tx_complete = ioat1_dma_is_complete;
+
+	err = ioat_probe(device);
+	if (err)
+		return err;
+	ioat_set_tcp_copy_break(4096);
+	err = ioat_register(device);
+	if (err)
+		return err;
+	ioat_kobject_add(device, &ioat1_ktype);
+
+	if (dca)
+		device->dca = ioat_dca_init(pdev, device->reg_base);
+
+	return err;
+}
+
+void __devexit ioat_dma_remove(struct ioatdma_device *device)
+{
+	struct dma_device *dma = &device->common;
+
+	ioat_disable_interrupts(device);
+
+	ioat_kobject_del(device);
+
+	dma_async_device_unregister(dma);
+
+	pci_pool_destroy(device->dma_pool);
+	pci_pool_destroy(device->completion_pool);
+
+	INIT_LIST_HEAD(&dma->channels);
+}
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
new file mode 100644
index 00000000000..c14fdfeb7f3
--- /dev/null
+++ b/drivers/dma/ioat/dma.h
@@ -0,0 +1,337 @@
+/*
+ * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
+ */
+#ifndef IOATDMA_H
+#define IOATDMA_H
+
+#include <linux/dmaengine.h>
+#include "hw.h"
+#include "registers.h"
+#include <linux/init.h>
+#include <linux/dmapool.h>
+#include <linux/cache.h>
+#include <linux/pci_ids.h>
+#include <net/tcp.h>
+
+#define IOAT_DMA_VERSION  "4.00"
+
+#define IOAT_LOW_COMPLETION_MASK	0xffffffc0
+#define IOAT_DMA_DCA_ANY_CPU		~0
+
+#define to_ioatdma_device(dev) container_of(dev, struct ioatdma_device, common)
+#define to_ioat_desc(lh) container_of(lh, struct ioat_desc_sw, node)
+#define tx_to_ioat_desc(tx) container_of(tx, struct ioat_desc_sw, txd)
+#define to_dev(ioat_chan) (&(ioat_chan)->device->pdev->dev)
+
+#define chan_num(ch) ((int)((ch)->reg_base - (ch)->device->reg_base) / 0x80)
+
+/*
+ * workaround for IOAT ver.3.0 null descriptor issue
+ * (channel returns error when size is 0)
+ */
+#define NULL_DESC_BUFFER_SIZE 1
+
+/**
+ * struct ioatdma_device - internal representation of a IOAT device
+ * @pdev: PCI-Express device
+ * @reg_base: MMIO register space base address
+ * @dma_pool: for allocating DMA descriptors
+ * @common: embedded struct dma_device
+ * @version: version of ioatdma device
+ * @msix_entries: irq handlers
+ * @idx: per channel data
+ * @dca: direct cache access context
+ * @intr_quirk: interrupt setup quirk (for ioat_v1 devices)
+ * @enumerate_channels: hw version specific channel enumeration
+ * @cleanup_tasklet: select between the v2 and v3 cleanup routines
+ * @timer_fn: select between the v2 and v3 timer watchdog routines
+ * @self_test: hardware version specific self test for each supported op type
+ *
+ * Note: the v3 cleanup routine supports raid operations
+ */
+struct ioatdma_device {
+	struct pci_dev *pdev;
+	void __iomem *reg_base;
+	struct pci_pool *dma_pool;
+	struct pci_pool *completion_pool;
+	struct dma_device common;
+	u8 version;
+	struct msix_entry msix_entries[4];
+	struct ioat_chan_common *idx[4];
+	struct dca_provider *dca;
+	void (*intr_quirk)(struct ioatdma_device *device);
+	int (*enumerate_channels)(struct ioatdma_device *device);
+	void (*cleanup_tasklet)(unsigned long data);
+	void (*timer_fn)(unsigned long data);
+	int (*self_test)(struct ioatdma_device *device);
+};
+
+struct ioat_chan_common {
+	struct dma_chan common;
+	void __iomem *reg_base;
+	unsigned long last_completion;
+	spinlock_t cleanup_lock;
+	dma_cookie_t completed_cookie;
+	unsigned long state;
+	#define IOAT_COMPLETION_PENDING 0
+	#define IOAT_COMPLETION_ACK 1
+	#define IOAT_RESET_PENDING 2
+	#define IOAT_KOBJ_INIT_FAIL 3
+	struct timer_list timer;
+	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
+	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
+	#define RESET_DELAY msecs_to_jiffies(100)
+	struct ioatdma_device *device;
+	dma_addr_t completion_dma;
+	u64 *completion;
+	struct tasklet_struct cleanup_task;
+	struct kobject kobj;
+};
+
+struct ioat_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct dma_chan *, char *);
+};
+
+/**
+ * struct ioat_dma_chan - internal representation of a DMA channel
+ */
+struct ioat_dma_chan {
+	struct ioat_chan_common base;
+
+	size_t xfercap;	/* XFERCAP register value expanded out */
+
+	spinlock_t desc_lock;
+	struct list_head free_desc;
+	struct list_head used_desc;
+
+	int pending;
+	u16 desccount;
+	u16 active;
+};
+
+static inline struct ioat_chan_common *to_chan_common(struct dma_chan *c)
+{
+	return container_of(c, struct ioat_chan_common, common);
+}
+
+static inline struct ioat_dma_chan *to_ioat_chan(struct dma_chan *c)
+{
+	struct ioat_chan_common *chan = to_chan_common(c);
+
+	return container_of(chan, struct ioat_dma_chan, base);
+}
+
+/**
+ * ioat_is_complete - poll the status of an ioat transaction
+ * @c: channel handle
+ * @cookie: transaction identifier
+ * @done: if set, updated with last completed transaction
+ * @used: if set, updated with last used transaction
+ */
+static inline enum dma_status
+ioat_is_complete(struct dma_chan *c, dma_cookie_t cookie,
+		 dma_cookie_t *done, dma_cookie_t *used)
+{
+	struct ioat_chan_common *chan = to_chan_common(c);
+	dma_cookie_t last_used;
+	dma_cookie_t last_complete;
+
+	last_used = c->cookie;
+	last_complete = chan->completed_cookie;
+
+	if (done)
+		*done = last_complete;
+	if (used)
+		*used = last_used;
+
+	return dma_async_is_complete(cookie, last_complete, last_used);
+}
+
+/* wrapper around hardware descriptor format + additional software fields */
+
+/**
+ * struct ioat_desc_sw - wrapper around hardware descriptor
+ * @hw: hardware DMA descriptor (for memcpy)
+ * @node: this descriptor will either be on the free list,
+ *     or attached to a transaction list (tx_list)
+ * @txd: the generic software descriptor for all engines
+ * @id: identifier for debug
+ */
+struct ioat_desc_sw {
+	struct ioat_dma_descriptor *hw;
+	struct list_head node;
+	size_t len;
+	struct list_head tx_list;
+	struct dma_async_tx_descriptor txd;
+	#ifdef DEBUG
+	int id;
+	#endif
+};
+
+#ifdef DEBUG
+#define set_desc_id(desc, i) ((desc)->id = (i))
+#define desc_id(desc) ((desc)->id)
+#else
+#define set_desc_id(desc, i)
+#define desc_id(desc) (0)
+#endif
+
+static inline void
+__dump_desc_dbg(struct ioat_chan_common *chan, struct ioat_dma_descriptor *hw,
+		struct dma_async_tx_descriptor *tx, int id)
+{
+	struct device *dev = to_dev(chan);
+
+	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) cookie: %d flags: %#x"
+		" ctl: %#x (op: %d int_en: %d compl: %d)\n", id,
+		(unsigned long long) tx->phys,
+		(unsigned long long) hw->next, tx->cookie, tx->flags,
+		hw->ctl, hw->ctl_f.op, hw->ctl_f.int_en, hw->ctl_f.compl_write);
+}
+
+#define dump_desc_dbg(c, d) \
+	({ if (d) __dump_desc_dbg(&c->base, d->hw, &d->txd, desc_id(d)); 0; })
+
+static inline void ioat_set_tcp_copy_break(unsigned long copybreak)
+{
+	#ifdef CONFIG_NET_DMA
+	sysctl_tcp_dma_copybreak = copybreak;
+	#endif
+}
+
+static inline struct ioat_chan_common *
+ioat_chan_by_index(struct ioatdma_device *device, int index)
+{
+	return device->idx[index];
+}
+
+static inline u64 ioat_chansts(struct ioat_chan_common *chan)
+{
+	u8 ver = chan->device->version;
+	u64 status;
+	u32 status_lo;
+
+	/* We need to read the low address first as this causes the
+	 * chipset to latch the upper bits for the subsequent read
+	 */
+	status_lo = readl(chan->reg_base + IOAT_CHANSTS_OFFSET_LOW(ver));
+	status = readl(chan->reg_base + IOAT_CHANSTS_OFFSET_HIGH(ver));
+	status <<= 32;
+	status |= status_lo;
+
+	return status;
+}
+
+static inline void ioat_start(struct ioat_chan_common *chan)
+{
+	u8 ver = chan->device->version;
+
+	writeb(IOAT_CHANCMD_START, chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
+}
+
+static inline u64 ioat_chansts_to_addr(u64 status)
+{
+	return status & IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;
+}
+
+static inline u32 ioat_chanerr(struct ioat_chan_common *chan)
+{
+	return readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+}
+
+static inline void ioat_suspend(struct ioat_chan_common *chan)
+{
+	u8 ver = chan->device->version;
+
+	writeb(IOAT_CHANCMD_SUSPEND, chan->reg_base + IOAT_CHANCMD_OFFSET(ver));
+}
+
+static inline void ioat_set_chainaddr(struct ioat_dma_chan *ioat, u64 addr)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+
+	writel(addr & 0x00000000FFFFFFFF,
+	       chan->reg_base + IOAT1_CHAINADDR_OFFSET_LOW);
+	writel(addr >> 32,
+	       chan->reg_base + IOAT1_CHAINADDR_OFFSET_HIGH);
+}
+
+static inline bool is_ioat_active(unsigned long status)
+{
+	return ((status & IOAT_CHANSTS_STATUS) == IOAT_CHANSTS_ACTIVE);
+}
+
+static inline bool is_ioat_idle(unsigned long status)
+{
+	return ((status & IOAT_CHANSTS_STATUS) == IOAT_CHANSTS_DONE);
+}
+
+static inline bool is_ioat_halted(unsigned long status)
+{
+	return ((status & IOAT_CHANSTS_STATUS) == IOAT_CHANSTS_HALTED);
+}
+
+static inline bool is_ioat_suspended(unsigned long status)
+{
+	return ((status & IOAT_CHANSTS_STATUS) == IOAT_CHANSTS_SUSPENDED);
+}
+
+/* channel was fatally programmed */
+static inline bool is_ioat_bug(unsigned long err)
+{
+	return !!(err & (IOAT_CHANERR_SRC_ADDR_ERR|IOAT_CHANERR_DEST_ADDR_ERR|
+			 IOAT_CHANERR_NEXT_ADDR_ERR|IOAT_CHANERR_CONTROL_ERR|
+			 IOAT_CHANERR_LENGTH_ERR));
+}
+
+static inline void ioat_unmap(struct pci_dev *pdev, dma_addr_t addr, size_t len,
+			      int direction, enum dma_ctrl_flags flags, bool dst)
+{
+	if ((dst && (flags & DMA_COMPL_DEST_UNMAP_SINGLE)) ||
+	    (!dst && (flags & DMA_COMPL_SRC_UNMAP_SINGLE)))
+		pci_unmap_single(pdev, addr, len, direction);
+	else
+		pci_unmap_page(pdev, addr, len, direction);
+}
+
+int __devinit ioat_probe(struct ioatdma_device *device);
+int __devinit ioat_register(struct ioatdma_device *device);
+int __devinit ioat1_dma_probe(struct ioatdma_device *dev, int dca);
+int __devinit ioat_dma_self_test(struct ioatdma_device *device);
+void __devexit ioat_dma_remove(struct ioatdma_device *device);
+struct dca_provider * __devinit ioat_dca_init(struct pci_dev *pdev,
+					      void __iomem *iobase);
+unsigned long ioat_get_current_completion(struct ioat_chan_common *chan);
+void ioat_init_channel(struct ioatdma_device *device,
+		       struct ioat_chan_common *chan, int idx,
+		       void (*timer_fn)(unsigned long),
+		       void (*tasklet)(unsigned long),
+		       unsigned long ioat);
+void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
+		    size_t len, struct ioat_dma_descriptor *hw);
+bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
+			   unsigned long *phys_complete);
+void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
+void ioat_kobject_del(struct ioatdma_device *device);
+extern struct sysfs_ops ioat_sysfs_ops;
+extern struct ioat_sysfs_entry ioat_version_attr;
+extern struct ioat_sysfs_entry ioat_cap_attr;
+#endif /* IOATDMA_H */
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
new file mode 100644
index 00000000000..96ffab7d37a
--- /dev/null
+++ b/drivers/dma/ioat/dma_v2.c
@@ -0,0 +1,871 @@
+/*
+ * Intel I/OAT DMA Linux driver
+ * Copyright(c) 2004 - 2009 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+
+/*
+ * This driver supports an Intel I/OAT DMA engine (versions >= 2), which
+ * does asynchronous data movement and checksumming operations.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
+#include <linux/i7300_idle.h>
+#include "dma.h"
+#include "dma_v2.h"
+#include "registers.h"
+#include "hw.h"
+
+int ioat_ring_alloc_order = 8;
+module_param(ioat_ring_alloc_order, int, 0644);
+MODULE_PARM_DESC(ioat_ring_alloc_order,
+		 "ioat2+: allocate 2^n descriptors per channel"
+		 " (default: 8 max: 16)");
+static int ioat_ring_max_alloc_order = IOAT_MAX_ORDER;
+module_param(ioat_ring_max_alloc_order, int, 0644);
+MODULE_PARM_DESC(ioat_ring_max_alloc_order,
+		 "ioat2+: upper limit for ring size (default: 16)");
+
+void __ioat2_issue_pending(struct ioat2_dma_chan *ioat)
+{
+	void * __iomem reg_base = ioat->base.reg_base;
+
+	ioat->pending = 0;
+	ioat->dmacount += ioat2_ring_pending(ioat);
+	ioat->issued = ioat->head;
+	/* make descriptor updates globally visible before notifying channel */
+	wmb();
+	writew(ioat->dmacount, reg_base + IOAT_CHAN_DMACOUNT_OFFSET);
+	dev_dbg(to_dev(&ioat->base),
+		"%s: head: %#x tail: %#x issued: %#x count: %#x\n",
+		__func__, ioat->head, ioat->tail, ioat->issued, ioat->dmacount);
+}
+
+void ioat2_issue_pending(struct dma_chan *chan)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(chan);
+
+	spin_lock_bh(&ioat->ring_lock);
+	if (ioat->pending == 1)
+		__ioat2_issue_pending(ioat);
+	spin_unlock_bh(&ioat->ring_lock);
+}
+
+/**
+ * ioat2_update_pending - log pending descriptors
+ * @ioat: ioat2+ channel
+ *
+ * set pending to '1' unless pending is already set to '2', pending == 2
+ * indicates that submission is temporarily blocked due to an in-flight
+ * reset.  If we are already above the ioat_pending_level threshold then
+ * just issue pending.
+ *
+ * called with ring_lock held
+ */
+static void ioat2_update_pending(struct ioat2_dma_chan *ioat)
+{
+	if (unlikely(ioat->pending == 2))
+		return;
+	else if (ioat2_ring_pending(ioat) > ioat_pending_level)
+		__ioat2_issue_pending(ioat);
+	else
+		ioat->pending = 1;
+}
+
+static void __ioat2_start_null_desc(struct ioat2_dma_chan *ioat)
+{
+	struct ioat_ring_ent *desc;
+	struct ioat_dma_descriptor *hw;
+	int idx;
+
+	if (ioat2_ring_space(ioat) < 1) {
+		dev_err(to_dev(&ioat->base),
+			"Unable to start null desc - ring full\n");
+		return;
+	}
+
+	dev_dbg(to_dev(&ioat->base), "%s: head: %#x tail: %#x issued: %#x\n",
+		__func__, ioat->head, ioat->tail, ioat->issued);
+	idx = ioat2_desc_alloc(ioat, 1);
+	desc = ioat2_get_ring_ent(ioat, idx);
+
+	hw = desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = 1;
+	hw->ctl_f.compl_write = 1;
+	/* set size to non-zero value (channel returns error when size is 0) */
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	hw->src_addr = 0;
+	hw->dst_addr = 0;
+	async_tx_ack(&desc->txd);
+	ioat2_set_chainaddr(ioat, desc->txd.phys);
+	dump_desc_dbg(ioat, desc);
+	__ioat2_issue_pending(ioat);
+}
+
+static void ioat2_start_null_desc(struct ioat2_dma_chan *ioat)
+{
+	spin_lock_bh(&ioat->ring_lock);
+	__ioat2_start_null_desc(ioat);
+	spin_unlock_bh(&ioat->ring_lock);
+}
+
+static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	struct dma_async_tx_descriptor *tx;
+	struct ioat_ring_ent *desc;
+	bool seen_current = false;
+	u16 active;
+	int i;
+
+	dev_dbg(to_dev(chan), "%s: head: %#x tail: %#x issued: %#x\n",
+		__func__, ioat->head, ioat->tail, ioat->issued);
+
+	active = ioat2_ring_active(ioat);
+	for (i = 0; i < active && !seen_current; i++) {
+		prefetch(ioat2_get_ring_ent(ioat, ioat->tail + i + 1));
+		desc = ioat2_get_ring_ent(ioat, ioat->tail + i);
+		tx = &desc->txd;
+		dump_desc_dbg(ioat, desc);
+		if (tx->cookie) {
+			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
+			chan->completed_cookie = tx->cookie;
+			tx->cookie = 0;
+			if (tx->callback) {
+				tx->callback(tx->callback_param);
+				tx->callback = NULL;
+			}
+		}
+
+		if (tx->phys == phys_complete)
+			seen_current = true;
+	}
+	ioat->tail += i;
+	BUG_ON(!seen_current); /* no active descs have written a completion? */
+
+	chan->last_completion = phys_complete;
+	if (ioat->head == ioat->tail) {
+		dev_dbg(to_dev(chan), "%s: cancel completion timeout\n",
+			__func__);
+		clear_bit(IOAT_COMPLETION_PENDING, &chan->state);
+		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
+	}
+}
+
+/**
+ * ioat2_cleanup - clean finished descriptors (advance tail pointer)
+ * @chan: ioat channel to be cleaned up
+ */
+static void ioat2_cleanup(struct ioat2_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	unsigned long phys_complete;
+
+	prefetch(chan->completion);
+
+	if (!spin_trylock_bh(&chan->cleanup_lock))
+		return;
+
+	if (!ioat_cleanup_preamble(chan, &phys_complete)) {
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	}
+
+	if (!spin_trylock_bh(&ioat->ring_lock)) {
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	}
+
+	__cleanup(ioat, phys_complete);
+
+	spin_unlock_bh(&ioat->ring_lock);
+	spin_unlock_bh(&chan->cleanup_lock);
+}
+
+void ioat2_cleanup_tasklet(unsigned long data)
+{
+	struct ioat2_dma_chan *ioat = (void *) data;
+
+	ioat2_cleanup(ioat);
+	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
+}
+
+void __ioat2_restart_chan(struct ioat2_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+
+	/* set the tail to be re-issued */
+	ioat->issued = ioat->tail;
+	ioat->dmacount = 0;
+	set_bit(IOAT_COMPLETION_PENDING, &chan->state);
+	mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+
+	dev_dbg(to_dev(chan),
+		"%s: head: %#x tail: %#x issued: %#x count: %#x\n",
+		__func__, ioat->head, ioat->tail, ioat->issued, ioat->dmacount);
+
+	if (ioat2_ring_pending(ioat)) {
+		struct ioat_ring_ent *desc;
+
+		desc = ioat2_get_ring_ent(ioat, ioat->tail);
+		ioat2_set_chainaddr(ioat, desc->txd.phys);
+		__ioat2_issue_pending(ioat);
+	} else
+		__ioat2_start_null_desc(ioat);
+}
+
+static void ioat2_restart_channel(struct ioat2_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	unsigned long phys_complete;
+	u32 status;
+
+	status = ioat_chansts(chan);
+	if (is_ioat_active(status) || is_ioat_idle(status))
+		ioat_suspend(chan);
+	while (is_ioat_active(status) || is_ioat_idle(status)) {
+		status = ioat_chansts(chan);
+		cpu_relax();
+	}
+
+	if (ioat_cleanup_preamble(chan, &phys_complete))
+		__cleanup(ioat, phys_complete);
+
+	__ioat2_restart_chan(ioat);
+}
+
+void ioat2_timer_event(unsigned long data)
+{
+	struct ioat2_dma_chan *ioat = (void *) data;
+	struct ioat_chan_common *chan = &ioat->base;
+
+	spin_lock_bh(&chan->cleanup_lock);
+	if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
+		unsigned long phys_complete;
+		u64 status;
+
+		spin_lock_bh(&ioat->ring_lock);
+		status = ioat_chansts(chan);
+
+		/* when halted due to errors check for channel
+		 * programming errors before advancing the completion state
+		 */
+		if (is_ioat_halted(status)) {
+			u32 chanerr;
+
+			chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+			BUG_ON(is_ioat_bug(chanerr));
+		}
+
+		/* if we haven't made progress and we have already
+		 * acknowledged a pending completion once, then be more
+		 * forceful with a restart
+		 */
+		if (ioat_cleanup_preamble(chan, &phys_complete))
+			__cleanup(ioat, phys_complete);
+		else if (test_bit(IOAT_COMPLETION_ACK, &chan->state))
+			ioat2_restart_channel(ioat);
+		else {
+			set_bit(IOAT_COMPLETION_ACK, &chan->state);
+			mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+		}
+		spin_unlock_bh(&ioat->ring_lock);
+	} else {
+		u16 active;
+
+		/* if the ring is idle, empty, and oversized try to step
+		 * down the size
+		 */
+		spin_lock_bh(&ioat->ring_lock);
+		active = ioat2_ring_active(ioat);
+		if (active == 0 && ioat->alloc_order > ioat_get_alloc_order())
+			reshape_ring(ioat, ioat->alloc_order-1);
+		spin_unlock_bh(&ioat->ring_lock);
+
+		/* keep shrinking until we get back to our minimum
+		 * default size
+		 */
+		if (ioat->alloc_order > ioat_get_alloc_order())
+			mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
+	}
+	spin_unlock_bh(&chan->cleanup_lock);
+}
+
+/**
+ * ioat2_enumerate_channels - find and initialize the device's channels
+ * @device: the device to be enumerated
+ */
+int ioat2_enumerate_channels(struct ioatdma_device *device)
+{
+	struct ioat2_dma_chan *ioat;
+	struct device *dev = &device->pdev->dev;
+	struct dma_device *dma = &device->common;
+	u8 xfercap_log;
+	int i;
+
+	INIT_LIST_HEAD(&dma->channels);
+	dma->chancnt = readb(device->reg_base + IOAT_CHANCNT_OFFSET);
+	dma->chancnt &= 0x1f; /* bits [4:0] valid */
+	if (dma->chancnt > ARRAY_SIZE(device->idx)) {
+		dev_warn(dev, "(%d) exceeds max supported channels (%zu)\n",
+			 dma->chancnt, ARRAY_SIZE(device->idx));
+		dma->chancnt = ARRAY_SIZE(device->idx);
+	}
+	xfercap_log = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
+	xfercap_log &= 0x1f; /* bits [4:0] valid */
+	if (xfercap_log == 0)
+		return 0;
+	dev_dbg(dev, "%s: xfercap = %d\n", __func__, 1 << xfercap_log);
+
+	/* FIXME which i/oat version is i7300? */
+#ifdef CONFIG_I7300_IDLE_IOAT_CHANNEL
+	if (i7300_idle_platform_probe(NULL, NULL, 1) == 0)
+		dma->chancnt--;
+#endif
+	for (i = 0; i < dma->chancnt; i++) {
+		ioat = devm_kzalloc(dev, sizeof(*ioat), GFP_KERNEL);
+		if (!ioat)
+			break;
+
+		ioat_init_channel(device, &ioat->base, i,
+				  device->timer_fn,
+				  device->cleanup_tasklet,
+				  (unsigned long) ioat);
+		ioat->xfercap_log = xfercap_log;
+		spin_lock_init(&ioat->ring_lock);
+	}
+	dma->chancnt = i;
+	return i;
+}
+
+static dma_cookie_t ioat2_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
+{
+	struct dma_chan *c = tx->chan;
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_chan_common *chan = &ioat->base;
+	dma_cookie_t cookie = c->cookie;
+
+	cookie++;
+	if (cookie < 0)
+		cookie = 1;
+	tx->cookie = cookie;
+	c->cookie = cookie;
+	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
+
+	if (!test_and_set_bit(IOAT_COMPLETION_PENDING, &chan->state))
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+	ioat2_update_pending(ioat);
+	spin_unlock_bh(&ioat->ring_lock);
+
+	return cookie;
+}
+
+static struct ioat_ring_ent *ioat2_alloc_ring_ent(struct dma_chan *chan, gfp_t flags)
+{
+	struct ioat_dma_descriptor *hw;
+	struct ioat_ring_ent *desc;
+	struct ioatdma_device *dma;
+	dma_addr_t phys;
+
+	dma = to_ioatdma_device(chan->device);
+	hw = pci_pool_alloc(dma->dma_pool, flags, &phys);
+	if (!hw)
+		return NULL;
+	memset(hw, 0, sizeof(*hw));
+
+	desc = kmem_cache_alloc(ioat2_cache, flags);
+	if (!desc) {
+		pci_pool_free(dma->dma_pool, hw, phys);
+		return NULL;
+	}
+	memset(desc, 0, sizeof(*desc));
+
+	dma_async_tx_descriptor_init(&desc->txd, chan);
+	desc->txd.tx_submit = ioat2_tx_submit_unlock;
+	desc->hw = hw;
+	desc->txd.phys = phys;
+	return desc;
+}
+
+static void ioat2_free_ring_ent(struct ioat_ring_ent *desc, struct dma_chan *chan)
+{
+	struct ioatdma_device *dma;
+
+	dma = to_ioatdma_device(chan->device);
+	pci_pool_free(dma->dma_pool, desc->hw, desc->txd.phys);
+	kmem_cache_free(ioat2_cache, desc);
+}
+
+static struct ioat_ring_ent **ioat2_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
+{
+	struct ioat_ring_ent **ring;
+	int descs = 1 << order;
+	int i;
+
+	if (order > ioat_get_max_alloc_order())
+		return NULL;
+
+	/* allocate the array to hold the software ring */
+	ring = kcalloc(descs, sizeof(*ring), flags);
+	if (!ring)
+		return NULL;
+	for (i = 0; i < descs; i++) {
+		ring[i] = ioat2_alloc_ring_ent(c, flags);
+		if (!ring[i]) {
+			while (i--)
+				ioat2_free_ring_ent(ring[i], c);
+			kfree(ring);
+			return NULL;
+		}
+		set_desc_id(ring[i], i);
+	}
+
+	/* link descs */
+	for (i = 0; i < descs-1; i++) {
+		struct ioat_ring_ent *next = ring[i+1];
+		struct ioat_dma_descriptor *hw = ring[i]->hw;
+
+		hw->next = next->txd.phys;
+	}
+	ring[i]->hw->next = ring[0]->txd.phys;
+
+	return ring;
+}
+
+/* ioat2_alloc_chan_resources - allocate/initialize ioat2 descriptor ring
+ * @chan: channel to be initialized
+ */
+int ioat2_alloc_chan_resources(struct dma_chan *c)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioat_ring_ent **ring;
+	u32 chanerr;
+	int order;
+
+	/* have we already been set up? */
+	if (ioat->ring)
+		return 1 << ioat->alloc_order;
+
+	/* Setup register to interrupt and write completion status on error */
+	writew(IOAT_CHANCTRL_RUN, chan->reg_base + IOAT_CHANCTRL_OFFSET);
+
+	chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+	if (chanerr) {
+		dev_err(to_dev(chan), "CHANERR = %x, clearing\n", chanerr);
+		writel(chanerr, chan->reg_base + IOAT_CHANERR_OFFSET);
+	}
+
+	/* allocate a completion writeback area */
+	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
+	chan->completion = pci_pool_alloc(chan->device->completion_pool,
+					  GFP_KERNEL, &chan->completion_dma);
+	if (!chan->completion)
+		return -ENOMEM;
+
+	memset(chan->completion, 0, sizeof(*chan->completion));
+	writel(((u64) chan->completion_dma) & 0x00000000FFFFFFFF,
+	       chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
+	writel(((u64) chan->completion_dma) >> 32,
+	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
+
+	order = ioat_get_alloc_order();
+	ring = ioat2_alloc_ring(c, order, GFP_KERNEL);
+	if (!ring)
+		return -ENOMEM;
+
+	spin_lock_bh(&ioat->ring_lock);
+	ioat->ring = ring;
+	ioat->head = 0;
+	ioat->issued = 0;
+	ioat->tail = 0;
+	ioat->pending = 0;
+	ioat->alloc_order = order;
+	spin_unlock_bh(&ioat->ring_lock);
+
+	tasklet_enable(&chan->cleanup_task);
+	ioat2_start_null_desc(ioat);
+
+	return 1 << ioat->alloc_order;
+}
+
+bool reshape_ring(struct ioat2_dma_chan *ioat, int order)
+{
+	/* reshape differs from normal ring allocation in that we want
+	 * to allocate a new software ring while only
+	 * extending/truncating the hardware ring
+	 */
+	struct ioat_chan_common *chan = &ioat->base;
+	struct dma_chan *c = &chan->common;
+	const u16 curr_size = ioat2_ring_mask(ioat) + 1;
+	const u16 active = ioat2_ring_active(ioat);
+	const u16 new_size = 1 << order;
+	struct ioat_ring_ent **ring;
+	u16 i;
+
+	if (order > ioat_get_max_alloc_order())
+		return false;
+
+	/* double check that we have at least 1 free descriptor */
+	if (active == curr_size)
+		return false;
+
+	/* when shrinking, verify that we can hold the current active
+	 * set in the new ring
+	 */
+	if (active >= new_size)
+		return false;
+
+	/* allocate the array to hold the software ring */
+	ring = kcalloc(new_size, sizeof(*ring), GFP_NOWAIT);
+	if (!ring)
+		return false;
+
+	/* allocate/trim descriptors as needed */
+	if (new_size > curr_size) {
+		/* copy current descriptors to the new ring */
+		for (i = 0; i < curr_size; i++) {
+			u16 curr_idx = (ioat->tail+i) & (curr_size-1);
+			u16 new_idx = (ioat->tail+i) & (new_size-1);
+
+			ring[new_idx] = ioat->ring[curr_idx];
+			set_desc_id(ring[new_idx], new_idx);
+		}
+
+		/* add new descriptors to the ring */
+		for (i = curr_size; i < new_size; i++) {
+			u16 new_idx = (ioat->tail+i) & (new_size-1);
+
+			ring[new_idx] = ioat2_alloc_ring_ent(c, GFP_NOWAIT);
+			if (!ring[new_idx]) {
+				while (i--) {
+					u16 new_idx = (ioat->tail+i) & (new_size-1);
+
+					ioat2_free_ring_ent(ring[new_idx], c);
+				}
+				kfree(ring);
+				return false;
+			}
+			set_desc_id(ring[new_idx], new_idx);
+		}
+
+		/* hw link new descriptors */
+		for (i = curr_size-1; i < new_size; i++) {
+			u16 new_idx = (ioat->tail+i) & (new_size-1);
+			struct ioat_ring_ent *next = ring[(new_idx+1) & (new_size-1)];
+			struct ioat_dma_descriptor *hw = ring[new_idx]->hw;
+
+			hw->next = next->txd.phys;
+		}
+	} else {
+		struct ioat_dma_descriptor *hw;
+		struct ioat_ring_ent *next;
+
+		/* copy current descriptors to the new ring, dropping the
+		 * removed descriptors
+		 */
+		for (i = 0; i < new_size; i++) {
+			u16 curr_idx = (ioat->tail+i) & (curr_size-1);
+			u16 new_idx = (ioat->tail+i) & (new_size-1);
+
+			ring[new_idx] = ioat->ring[curr_idx];
+			set_desc_id(ring[new_idx], new_idx);
+		}
+
+		/* free deleted descriptors */
+		for (i = new_size; i < curr_size; i++) {
+			struct ioat_ring_ent *ent;
+
+			ent = ioat2_get_ring_ent(ioat, ioat->tail+i);
+			ioat2_free_ring_ent(ent, c);
+		}
+
+		/* fix up hardware ring */
+		hw = ring[(ioat->tail+new_size-1) & (new_size-1)]->hw;
+		next = ring[(ioat->tail+new_size) & (new_size-1)];
+		hw->next = next->txd.phys;
+	}
+
+	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
+		__func__, new_size);
+
+	kfree(ioat->ring);
+	ioat->ring = ring;
+	ioat->alloc_order = order;
+
+	return true;
+}
+
+/**
+ * ioat2_alloc_and_lock - common descriptor alloc boilerplate for ioat2,3 ops
+ * @idx: gets starting descriptor index on successful allocation
+ * @ioat: ioat2,3 channel (ring) to operate on
+ * @num_descs: allocation length
+ */
+int ioat2_alloc_and_lock(u16 *idx, struct ioat2_dma_chan *ioat, int num_descs)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+
+	spin_lock_bh(&ioat->ring_lock);
+	/* never allow the last descriptor to be consumed, we need at
+	 * least one free at all times to allow for on-the-fly ring
+	 * resizing.
+	 */
+	while (unlikely(ioat2_ring_space(ioat) <= num_descs)) {
+		if (reshape_ring(ioat, ioat->alloc_order + 1) &&
+		    ioat2_ring_space(ioat) > num_descs)
+				break;
+
+		if (printk_ratelimit())
+			dev_dbg(to_dev(chan),
+				"%s: ring full! num_descs: %d (%x:%x:%x)\n",
+				__func__, num_descs, ioat->head, ioat->tail,
+				ioat->issued);
+		spin_unlock_bh(&ioat->ring_lock);
+
+		/* progress reclaim in the allocation failure case we
+		 * may be called under bh_disabled so we need to trigger
+		 * the timer event directly
+		 */
+		spin_lock_bh(&chan->cleanup_lock);
+		if (jiffies > chan->timer.expires &&
+		    timer_pending(&chan->timer)) {
+			struct ioatdma_device *device = chan->device;
+
+			mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+			spin_unlock_bh(&chan->cleanup_lock);
+			device->timer_fn((unsigned long) ioat);
+		} else
+			spin_unlock_bh(&chan->cleanup_lock);
+		return -ENOMEM;
+	}
+
+	dev_dbg(to_dev(chan), "%s: num_descs: %d (%x:%x:%x)\n",
+		__func__, num_descs, ioat->head, ioat->tail, ioat->issued);
+
+	*idx = ioat2_desc_alloc(ioat, num_descs);
+	return 0;  /* with ioat->ring_lock held */
+}
+
+struct dma_async_tx_descriptor *
+ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
+			   dma_addr_t dma_src, size_t len, unsigned long flags)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_dma_descriptor *hw;
+	struct ioat_ring_ent *desc;
+	dma_addr_t dst = dma_dest;
+	dma_addr_t src = dma_src;
+	size_t total_len = len;
+	int num_descs;
+	u16 idx;
+	int i;
+
+	num_descs = ioat2_xferlen_to_descs(ioat, len);
+	if (likely(num_descs) &&
+	    ioat2_alloc_and_lock(&idx, ioat, num_descs) == 0)
+		/* pass */;
+	else
+		return NULL;
+	i = 0;
+	do {
+		size_t copy = min_t(size_t, len, 1 << ioat->xfercap_log);
+
+		desc = ioat2_get_ring_ent(ioat, idx + i);
+		hw = desc->hw;
+
+		hw->size = copy;
+		hw->ctl = 0;
+		hw->src_addr = src;
+		hw->dst_addr = dst;
+
+		len -= copy;
+		dst += copy;
+		src += copy;
+		dump_desc_dbg(ioat, desc);
+	} while (++i < num_descs);
+
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+	hw->ctl_f.compl_write = 1;
+	dump_desc_dbg(ioat, desc);
+	/* we leave the channel locked to ensure in order submission */
+
+	return &desc->txd;
+}
+
+/**
+ * ioat2_free_chan_resources - release all the descriptors
+ * @chan: the channel to be cleaned
+ */
+void ioat2_free_chan_resources(struct dma_chan *c)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioatdma_device *device = chan->device;
+	struct ioat_ring_ent *desc;
+	const u16 total_descs = 1 << ioat->alloc_order;
+	int descs;
+	int i;
+
+	/* Before freeing channel resources first check
+	 * if they have been previously allocated for this channel.
+	 */
+	if (!ioat->ring)
+		return;
+
+	tasklet_disable(&chan->cleanup_task);
+	del_timer_sync(&chan->timer);
+	device->cleanup_tasklet((unsigned long) ioat);
+
+	/* Delay 100ms after reset to allow internal DMA logic to quiesce
+	 * before removing DMA descriptor resources.
+	 */
+	writeb(IOAT_CHANCMD_RESET,
+	       chan->reg_base + IOAT_CHANCMD_OFFSET(chan->device->version));
+	mdelay(100);
+
+	spin_lock_bh(&ioat->ring_lock);
+	descs = ioat2_ring_space(ioat);
+	dev_dbg(to_dev(chan), "freeing %d idle descriptors\n", descs);
+	for (i = 0; i < descs; i++) {
+		desc = ioat2_get_ring_ent(ioat, ioat->head + i);
+		ioat2_free_ring_ent(desc, c);
+	}
+
+	if (descs < total_descs)
+		dev_err(to_dev(chan), "Freeing %d in use descriptors!\n",
+			total_descs - descs);
+
+	for (i = 0; i < total_descs - descs; i++) {
+		desc = ioat2_get_ring_ent(ioat, ioat->tail + i);
+		dump_desc_dbg(ioat, desc);
+		ioat2_free_ring_ent(desc, c);
+	}
+
+	kfree(ioat->ring);
+	ioat->ring = NULL;
+	ioat->alloc_order = 0;
+	pci_pool_free(device->completion_pool, chan->completion,
+		      chan->completion_dma);
+	spin_unlock_bh(&ioat->ring_lock);
+
+	chan->last_completion = 0;
+	chan->completion_dma = 0;
+	ioat->pending = 0;
+	ioat->dmacount = 0;
+}
+
+enum dma_status
+ioat2_is_complete(struct dma_chan *c, dma_cookie_t cookie,
+		     dma_cookie_t *done, dma_cookie_t *used)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioatdma_device *device = ioat->base.device;
+
+	if (ioat_is_complete(c, cookie, done, used) == DMA_SUCCESS)
+		return DMA_SUCCESS;
+
+	device->cleanup_tasklet((unsigned long) ioat);
+
+	return ioat_is_complete(c, cookie, done, used);
+}
+
+static ssize_t ring_size_show(struct dma_chan *c, char *page)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+
+	return sprintf(page, "%d\n", (1 << ioat->alloc_order) & ~1);
+}
+static struct ioat_sysfs_entry ring_size_attr = __ATTR_RO(ring_size);
+
+static ssize_t ring_active_show(struct dma_chan *c, char *page)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+
+	/* ...taken outside the lock, no need to be precise */
+	return sprintf(page, "%d\n", ioat2_ring_active(ioat));
+}
+static struct ioat_sysfs_entry ring_active_attr = __ATTR_RO(ring_active);
+
+static struct attribute *ioat2_attrs[] = {
+	&ring_size_attr.attr,
+	&ring_active_attr.attr,
+	&ioat_cap_attr.attr,
+	&ioat_version_attr.attr,
+	NULL,
+};
+
+struct kobj_type ioat2_ktype = {
+	.sysfs_ops = &ioat_sysfs_ops,
+	.default_attrs = ioat2_attrs,
+};
+
+int __devinit ioat2_dma_probe(struct ioatdma_device *device, int dca)
+{
+	struct pci_dev *pdev = device->pdev;
+	struct dma_device *dma;
+	struct dma_chan *c;
+	struct ioat_chan_common *chan;
+	int err;
+
+	device->enumerate_channels = ioat2_enumerate_channels;
+	device->cleanup_tasklet = ioat2_cleanup_tasklet;
+	device->timer_fn = ioat2_timer_event;
+	device->self_test = ioat_dma_self_test;
+	dma = &device->common;
+	dma->device_prep_dma_memcpy = ioat2_dma_prep_memcpy_lock;
+	dma->device_issue_pending = ioat2_issue_pending;
+	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
+	dma->device_free_chan_resources = ioat2_free_chan_resources;
+	dma->device_is_tx_complete = ioat2_is_complete;
+
+	err = ioat_probe(device);
+	if (err)
+		return err;
+	ioat_set_tcp_copy_break(2048);
+
+	list_for_each_entry(c, &dma->channels, device_node) {
+		chan = to_chan_common(c);
+		writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE | IOAT_DMA_DCA_ANY_CPU,
+		       chan->reg_base + IOAT_DCACTRL_OFFSET);
+	}
+
+	err = ioat_register(device);
+	if (err)
+		return err;
+
+	ioat_kobject_add(device, &ioat2_ktype);
+
+	if (dca)
+		device->dca = ioat2_dca_init(pdev, device->reg_base);
+
+	return err;
+}
diff --git a/drivers/dma/ioat/dma_v2.h b/drivers/dma/ioat/dma_v2.h
new file mode 100644
index 00000000000..1d849ef74d5
--- /dev/null
+++ b/drivers/dma/ioat/dma_v2.h
@@ -0,0 +1,190 @@
+/*
+ * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
+ */
+#ifndef IOATDMA_V2_H
+#define IOATDMA_V2_H
+
+#include <linux/dmaengine.h>
+#include "dma.h"
+#include "hw.h"
+
+
+extern int ioat_pending_level;
+extern int ioat_ring_alloc_order;
+
+/*
+ * workaround for IOAT ver.3.0 null descriptor issue
+ * (channel returns error when size is 0)
+ */
+#define NULL_DESC_BUFFER_SIZE 1
+
+#define IOAT_MAX_ORDER 16
+#define ioat_get_alloc_order() \
+	(min(ioat_ring_alloc_order, IOAT_MAX_ORDER))
+#define ioat_get_max_alloc_order() \
+	(min(ioat_ring_max_alloc_order, IOAT_MAX_ORDER))
+
+/* struct ioat2_dma_chan - ioat v2 / v3 channel attributes
+ * @base: common ioat channel parameters
+ * @xfercap_log; log2 of channel max transfer length (for fast division)
+ * @head: allocated index
+ * @issued: hardware notification point
+ * @tail: cleanup index
+ * @pending: lock free indicator for issued != head
+ * @dmacount: identical to 'head' except for occasionally resetting to zero
+ * @alloc_order: log2 of the number of allocated descriptors
+ * @ring: software ring buffer implementation of hardware ring
+ * @ring_lock: protects ring attributes
+ */
+struct ioat2_dma_chan {
+	struct ioat_chan_common base;
+	size_t xfercap_log;
+	u16 head;
+	u16 issued;
+	u16 tail;
+	u16 dmacount;
+	u16 alloc_order;
+	int pending;
+	struct ioat_ring_ent **ring;
+	spinlock_t ring_lock;
+};
+
+static inline struct ioat2_dma_chan *to_ioat2_chan(struct dma_chan *c)
+{
+	struct ioat_chan_common *chan = to_chan_common(c);
+
+	return container_of(chan, struct ioat2_dma_chan, base);
+}
+
+static inline u16 ioat2_ring_mask(struct ioat2_dma_chan *ioat)
+{
+	return (1 << ioat->alloc_order) - 1;
+}
+
+/* count of descriptors in flight with the engine */
+static inline u16 ioat2_ring_active(struct ioat2_dma_chan *ioat)
+{
+	return (ioat->head - ioat->tail) & ioat2_ring_mask(ioat);
+}
+
+/* count of descriptors pending submission to hardware */
+static inline u16 ioat2_ring_pending(struct ioat2_dma_chan *ioat)
+{
+	return (ioat->head - ioat->issued) & ioat2_ring_mask(ioat);
+}
+
+static inline u16 ioat2_ring_space(struct ioat2_dma_chan *ioat)
+{
+	u16 num_descs = ioat2_ring_mask(ioat) + 1;
+	u16 active = ioat2_ring_active(ioat);
+
+	BUG_ON(active > num_descs);
+
+	return num_descs - active;
+}
+
+/* assumes caller already checked space */
+static inline u16 ioat2_desc_alloc(struct ioat2_dma_chan *ioat, u16 len)
+{
+	ioat->head += len;
+	return ioat->head - len;
+}
+
+static inline u16 ioat2_xferlen_to_descs(struct ioat2_dma_chan *ioat, size_t len)
+{
+	u16 num_descs = len >> ioat->xfercap_log;
+
+	num_descs += !!(len & ((1 << ioat->xfercap_log) - 1));
+	return num_descs;
+}
+
+/**
+ * struct ioat_ring_ent - wrapper around hardware descriptor
+ * @hw: hardware DMA descriptor (for memcpy)
+ * @fill: hardware fill descriptor
+ * @xor: hardware xor descriptor
+ * @xor_ex: hardware xor extension descriptor
+ * @pq: hardware pq descriptor
+ * @pq_ex: hardware pq extension descriptor
+ * @pqu: hardware pq update descriptor
+ * @raw: hardware raw (un-typed) descriptor
+ * @txd: the generic software descriptor for all engines
+ * @len: total transaction length for unmap
+ * @result: asynchronous result of validate operations
+ * @id: identifier for debug
+ */
+
+struct ioat_ring_ent {
+	union {
+		struct ioat_dma_descriptor *hw;
+		struct ioat_fill_descriptor *fill;
+		struct ioat_xor_descriptor *xor;
+		struct ioat_xor_ext_descriptor *xor_ex;
+		struct ioat_pq_descriptor *pq;
+		struct ioat_pq_ext_descriptor *pq_ex;
+		struct ioat_pq_update_descriptor *pqu;
+		struct ioat_raw_descriptor *raw;
+	};
+	size_t len;
+	struct dma_async_tx_descriptor txd;
+	enum sum_check_flags *result;
+	#ifdef DEBUG
+	int id;
+	#endif
+};
+
+static inline struct ioat_ring_ent *
+ioat2_get_ring_ent(struct ioat2_dma_chan *ioat, u16 idx)
+{
+	return ioat->ring[idx & ioat2_ring_mask(ioat)];
+}
+
+static inline void ioat2_set_chainaddr(struct ioat2_dma_chan *ioat, u64 addr)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+
+	writel(addr & 0x00000000FFFFFFFF,
+	       chan->reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
+	writel(addr >> 32,
+	       chan->reg_base + IOAT2_CHAINADDR_OFFSET_HIGH);
+}
+
+int __devinit ioat2_dma_probe(struct ioatdma_device *dev, int dca);
+int __devinit ioat3_dma_probe(struct ioatdma_device *dev, int dca);
+struct dca_provider * __devinit ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase);
+struct dca_provider * __devinit ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase);
+int ioat2_alloc_and_lock(u16 *idx, struct ioat2_dma_chan *ioat, int num_descs);
+int ioat2_enumerate_channels(struct ioatdma_device *device);
+struct dma_async_tx_descriptor *
+ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
+			   dma_addr_t dma_src, size_t len, unsigned long flags);
+void ioat2_issue_pending(struct dma_chan *chan);
+int ioat2_alloc_chan_resources(struct dma_chan *c);
+void ioat2_free_chan_resources(struct dma_chan *c);
+enum dma_status ioat2_is_complete(struct dma_chan *c, dma_cookie_t cookie,
+				  dma_cookie_t *done, dma_cookie_t *used);
+void __ioat2_restart_chan(struct ioat2_dma_chan *ioat);
+bool reshape_ring(struct ioat2_dma_chan *ioat, int order);
+void __ioat2_issue_pending(struct ioat2_dma_chan *ioat);
+void ioat2_cleanup_tasklet(unsigned long data);
+void ioat2_timer_event(unsigned long data);
+extern struct kobj_type ioat2_ktype;
+extern struct kmem_cache *ioat2_cache;
+#endif /* IOATDMA_V2_H */
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
new file mode 100644
index 00000000000..35d1e33afd5
--- /dev/null
+++ b/drivers/dma/ioat/dma_v3.c
@@ -0,0 +1,1223 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2004-2009 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/*
+ * Support routines for v3+ hardware
+ */
+
+#include <linux/pci.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include "registers.h"
+#include "hw.h"
+#include "dma.h"
+#include "dma_v2.h"
+
+/* ioat hardware assumes at least two sources for raid operations */
+#define src_cnt_to_sw(x) ((x) + 2)
+#define src_cnt_to_hw(x) ((x) - 2)
+
+/* provide a lookup table for setting the source address in the base or
+ * extended descriptor of an xor or pq descriptor
+ */
+static const u8 xor_idx_to_desc __read_mostly = 0xd0;
+static const u8 xor_idx_to_field[] __read_mostly = { 1, 4, 5, 6, 7, 0, 1, 2 };
+static const u8 pq_idx_to_desc __read_mostly = 0xf8;
+static const u8 pq_idx_to_field[] __read_mostly = { 1, 4, 5, 0, 1, 2, 4, 5 };
+
+static dma_addr_t xor_get_src(struct ioat_raw_descriptor *descs[2], int idx)
+{
+	struct ioat_raw_descriptor *raw = descs[xor_idx_to_desc >> idx & 1];
+
+	return raw->field[xor_idx_to_field[idx]];
+}
+
+static void xor_set_src(struct ioat_raw_descriptor *descs[2],
+			dma_addr_t addr, u32 offset, int idx)
+{
+	struct ioat_raw_descriptor *raw = descs[xor_idx_to_desc >> idx & 1];
+
+	raw->field[xor_idx_to_field[idx]] = addr + offset;
+}
+
+static dma_addr_t pq_get_src(struct ioat_raw_descriptor *descs[2], int idx)
+{
+	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];
+
+	return raw->field[pq_idx_to_field[idx]];
+}
+
+static void pq_set_src(struct ioat_raw_descriptor *descs[2],
+		       dma_addr_t addr, u32 offset, u8 coef, int idx)
+{
+	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *) descs[0];
+	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];
+
+	raw->field[pq_idx_to_field[idx]] = addr + offset;
+	pq->coef[idx] = coef;
+}
+
+static void ioat3_dma_unmap(struct ioat2_dma_chan *ioat,
+			    struct ioat_ring_ent *desc, int idx)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	struct pci_dev *pdev = chan->device->pdev;
+	size_t len = desc->len;
+	size_t offset = len - desc->hw->size;
+	struct dma_async_tx_descriptor *tx = &desc->txd;
+	enum dma_ctrl_flags flags = tx->flags;
+
+	switch (desc->hw->ctl_f.op) {
+	case IOAT_OP_COPY:
+		if (!desc->hw->ctl_f.null) /* skip 'interrupt' ops */
+			ioat_dma_unmap(chan, flags, len, desc->hw);
+		break;
+	case IOAT_OP_FILL: {
+		struct ioat_fill_descriptor *hw = desc->fill;
+
+		if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
+			ioat_unmap(pdev, hw->dst_addr - offset, len,
+				   PCI_DMA_FROMDEVICE, flags, 1);
+		break;
+	}
+	case IOAT_OP_XOR_VAL:
+	case IOAT_OP_XOR: {
+		struct ioat_xor_descriptor *xor = desc->xor;
+		struct ioat_ring_ent *ext;
+		struct ioat_xor_ext_descriptor *xor_ex = NULL;
+		int src_cnt = src_cnt_to_sw(xor->ctl_f.src_cnt);
+		struct ioat_raw_descriptor *descs[2];
+		int i;
+
+		if (src_cnt > 5) {
+			ext = ioat2_get_ring_ent(ioat, idx + 1);
+			xor_ex = ext->xor_ex;
+		}
+
+		if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+			descs[0] = (struct ioat_raw_descriptor *) xor;
+			descs[1] = (struct ioat_raw_descriptor *) xor_ex;
+			for (i = 0; i < src_cnt; i++) {
+				dma_addr_t src = xor_get_src(descs, i);
+
+				ioat_unmap(pdev, src - offset, len,
+					   PCI_DMA_TODEVICE, flags, 0);
+			}
+
+			/* dest is a source in xor validate operations */
+			if (xor->ctl_f.op == IOAT_OP_XOR_VAL) {
+				ioat_unmap(pdev, xor->dst_addr - offset, len,
+					   PCI_DMA_TODEVICE, flags, 1);
+				break;
+			}
+		}
+
+		if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
+			ioat_unmap(pdev, xor->dst_addr - offset, len,
+				   PCI_DMA_FROMDEVICE, flags, 1);
+		break;
+	}
+	case IOAT_OP_PQ_VAL:
+	case IOAT_OP_PQ: {
+		struct ioat_pq_descriptor *pq = desc->pq;
+		struct ioat_ring_ent *ext;
+		struct ioat_pq_ext_descriptor *pq_ex = NULL;
+		int src_cnt = src_cnt_to_sw(pq->ctl_f.src_cnt);
+		struct ioat_raw_descriptor *descs[2];
+		int i;
+
+		if (src_cnt > 3) {
+			ext = ioat2_get_ring_ent(ioat, idx + 1);
+			pq_ex = ext->pq_ex;
+		}
+
+		/* in the 'continue' case don't unmap the dests as sources */
+		if (dmaf_p_disabled_continue(flags))
+			src_cnt--;
+		else if (dmaf_continue(flags))
+			src_cnt -= 3;
+
+		if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+			descs[0] = (struct ioat_raw_descriptor *) pq;
+			descs[1] = (struct ioat_raw_descriptor *) pq_ex;
+			for (i = 0; i < src_cnt; i++) {
+				dma_addr_t src = pq_get_src(descs, i);
+
+				ioat_unmap(pdev, src - offset, len,
+					   PCI_DMA_TODEVICE, flags, 0);
+			}
+
+			/* the dests are sources in pq validate operations */
+			if (pq->ctl_f.op == IOAT_OP_XOR_VAL) {
+				if (!(flags & DMA_PREP_PQ_DISABLE_P))
+					ioat_unmap(pdev, pq->p_addr - offset,
+						   len, PCI_DMA_TODEVICE, flags, 0);
+				if (!(flags & DMA_PREP_PQ_DISABLE_Q))
+					ioat_unmap(pdev, pq->q_addr - offset,
+						   len, PCI_DMA_TODEVICE, flags, 0);
+				break;
+			}
+		}
+
+		if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+			if (!(flags & DMA_PREP_PQ_DISABLE_P))
+				ioat_unmap(pdev, pq->p_addr - offset, len,
+					   PCI_DMA_BIDIRECTIONAL, flags, 1);
+			if (!(flags & DMA_PREP_PQ_DISABLE_Q))
+				ioat_unmap(pdev, pq->q_addr - offset, len,
+					   PCI_DMA_BIDIRECTIONAL, flags, 1);
+		}
+		break;
+	}
+	default:
+		dev_err(&pdev->dev, "%s: unknown op type: %#x\n",
+			__func__, desc->hw->ctl_f.op);
+	}
+}
+
+static bool desc_has_ext(struct ioat_ring_ent *desc)
+{
+	struct ioat_dma_descriptor *hw = desc->hw;
+
+	if (hw->ctl_f.op == IOAT_OP_XOR ||
+	    hw->ctl_f.op == IOAT_OP_XOR_VAL) {
+		struct ioat_xor_descriptor *xor = desc->xor;
+
+		if (src_cnt_to_sw(xor->ctl_f.src_cnt) > 5)
+			return true;
+	} else if (hw->ctl_f.op == IOAT_OP_PQ ||
+		   hw->ctl_f.op == IOAT_OP_PQ_VAL) {
+		struct ioat_pq_descriptor *pq = desc->pq;
+
+		if (src_cnt_to_sw(pq->ctl_f.src_cnt) > 3)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * __cleanup - reclaim used descriptors
+ * @ioat: channel (ring) to clean
+ *
+ * The difference from the dma_v2.c __cleanup() is that this routine
+ * handles extended descriptors and dma-unmapping raid operations.
+ */
+static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioat_ring_ent *desc;
+	bool seen_current = false;
+	u16 active;
+	int i;
+
+	dev_dbg(to_dev(chan), "%s: head: %#x tail: %#x issued: %#x\n",
+		__func__, ioat->head, ioat->tail, ioat->issued);
+
+	active = ioat2_ring_active(ioat);
+	for (i = 0; i < active && !seen_current; i++) {
+		struct dma_async_tx_descriptor *tx;
+
+		prefetch(ioat2_get_ring_ent(ioat, ioat->tail + i + 1));
+		desc = ioat2_get_ring_ent(ioat, ioat->tail + i);
+		dump_desc_dbg(ioat, desc);
+		tx = &desc->txd;
+		if (tx->cookie) {
+			chan->completed_cookie = tx->cookie;
+			ioat3_dma_unmap(ioat, desc, ioat->tail + i);
+			tx->cookie = 0;
+			if (tx->callback) {
+				tx->callback(tx->callback_param);
+				tx->callback = NULL;
+			}
+		}
+
+		if (tx->phys == phys_complete)
+			seen_current = true;
+
+		/* skip extended descriptors */
+		if (desc_has_ext(desc)) {
+			BUG_ON(i + 1 >= active);
+			i++;
+		}
+	}
+	ioat->tail += i;
+	BUG_ON(!seen_current); /* no active descs have written a completion? */
+	chan->last_completion = phys_complete;
+	if (ioat->head == ioat->tail) {
+		dev_dbg(to_dev(chan), "%s: cancel completion timeout\n",
+			__func__);
+		clear_bit(IOAT_COMPLETION_PENDING, &chan->state);
+		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
+	}
+}
+
+static void ioat3_cleanup(struct ioat2_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	unsigned long phys_complete;
+
+	prefetch(chan->completion);
+
+	if (!spin_trylock_bh(&chan->cleanup_lock))
+		return;
+
+	if (!ioat_cleanup_preamble(chan, &phys_complete)) {
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	}
+
+	if (!spin_trylock_bh(&ioat->ring_lock)) {
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	}
+
+	__cleanup(ioat, phys_complete);
+
+	spin_unlock_bh(&ioat->ring_lock);
+	spin_unlock_bh(&chan->cleanup_lock);
+}
+
+static void ioat3_cleanup_tasklet(unsigned long data)
+{
+	struct ioat2_dma_chan *ioat = (void *) data;
+
+	ioat3_cleanup(ioat);
+	writew(IOAT_CHANCTRL_RUN | IOAT3_CHANCTRL_COMPL_DCA_EN,
+	       ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
+}
+
+static void ioat3_restart_channel(struct ioat2_dma_chan *ioat)
+{
+	struct ioat_chan_common *chan = &ioat->base;
+	unsigned long phys_complete;
+	u32 status;
+
+	status = ioat_chansts(chan);
+	if (is_ioat_active(status) || is_ioat_idle(status))
+		ioat_suspend(chan);
+	while (is_ioat_active(status) || is_ioat_idle(status)) {
+		status = ioat_chansts(chan);
+		cpu_relax();
+	}
+
+	if (ioat_cleanup_preamble(chan, &phys_complete))
+		__cleanup(ioat, phys_complete);
+
+	__ioat2_restart_chan(ioat);
+}
+
+static void ioat3_timer_event(unsigned long data)
+{
+	struct ioat2_dma_chan *ioat = (void *) data;
+	struct ioat_chan_common *chan = &ioat->base;
+
+	spin_lock_bh(&chan->cleanup_lock);
+	if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
+		unsigned long phys_complete;
+		u64 status;
+
+		spin_lock_bh(&ioat->ring_lock);
+		status = ioat_chansts(chan);
+
+		/* when halted due to errors check for channel
+		 * programming errors before advancing the completion state
+		 */
+		if (is_ioat_halted(status)) {
+			u32 chanerr;
+
+			chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+			BUG_ON(is_ioat_bug(chanerr));
+		}
+
+		/* if we haven't made progress and we have already
+		 * acknowledged a pending completion once, then be more
+		 * forceful with a restart
+		 */
+		if (ioat_cleanup_preamble(chan, &phys_complete))
+			__cleanup(ioat, phys_complete);
+		else if (test_bit(IOAT_COMPLETION_ACK, &chan->state))
+			ioat3_restart_channel(ioat);
+		else {
+			set_bit(IOAT_COMPLETION_ACK, &chan->state);
+			mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+		}
+		spin_unlock_bh(&ioat->ring_lock);
+	} else {
+		u16 active;
+
+		/* if the ring is idle, empty, and oversized try to step
+		 * down the size
+		 */
+		spin_lock_bh(&ioat->ring_lock);
+		active = ioat2_ring_active(ioat);
+		if (active == 0 && ioat->alloc_order > ioat_get_alloc_order())
+			reshape_ring(ioat, ioat->alloc_order-1);
+		spin_unlock_bh(&ioat->ring_lock);
+
+		/* keep shrinking until we get back to our minimum
+		 * default size
+		 */
+		if (ioat->alloc_order > ioat_get_alloc_order())
+			mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
+	}
+	spin_unlock_bh(&chan->cleanup_lock);
+}
+
+static enum dma_status
+ioat3_is_complete(struct dma_chan *c, dma_cookie_t cookie,
+		  dma_cookie_t *done, dma_cookie_t *used)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+
+	if (ioat_is_complete(c, cookie, done, used) == DMA_SUCCESS)
+		return DMA_SUCCESS;
+
+	ioat3_cleanup(ioat);
+
+	return ioat_is_complete(c, cookie, done, used);
+}
+
+static struct dma_async_tx_descriptor *
+ioat3_prep_memset_lock(struct dma_chan *c, dma_addr_t dest, int value,
+		       size_t len, unsigned long flags)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_ring_ent *desc;
+	size_t total_len = len;
+	struct ioat_fill_descriptor *fill;
+	int num_descs;
+	u64 src_data = (0x0101010101010101ULL) * (value & 0xff);
+	u16 idx;
+	int i;
+
+	num_descs = ioat2_xferlen_to_descs(ioat, len);
+	if (likely(num_descs) &&
+	    ioat2_alloc_and_lock(&idx, ioat, num_descs) == 0)
+		/* pass */;
+	else
+		return NULL;
+	i = 0;
+	do {
+		size_t xfer_size = min_t(size_t, len, 1 << ioat->xfercap_log);
+
+		desc = ioat2_get_ring_ent(ioat, idx + i);
+		fill = desc->fill;
+
+		fill->size = xfer_size;
+		fill->src_data = src_data;
+		fill->dst_addr = dest;
+		fill->ctl = 0;
+		fill->ctl_f.op = IOAT_OP_FILL;
+
+		len -= xfer_size;
+		dest += xfer_size;
+		dump_desc_dbg(ioat, desc);
+	} while (++i < num_descs);
+
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	fill->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	fill->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+	fill->ctl_f.compl_write = 1;
+	dump_desc_dbg(ioat, desc);
+
+	/* we leave the channel locked to ensure in order submission */
+	return &desc->txd;
+}
+
+static struct dma_async_tx_descriptor *
+__ioat3_prep_xor_lock(struct dma_chan *c, enum sum_check_flags *result,
+		      dma_addr_t dest, dma_addr_t *src, unsigned int src_cnt,
+		      size_t len, unsigned long flags)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_ring_ent *compl_desc;
+	struct ioat_ring_ent *desc;
+	struct ioat_ring_ent *ext;
+	size_t total_len = len;
+	struct ioat_xor_descriptor *xor;
+	struct ioat_xor_ext_descriptor *xor_ex = NULL;
+	struct ioat_dma_descriptor *hw;
+	u32 offset = 0;
+	int num_descs;
+	int with_ext;
+	int i;
+	u16 idx;
+	u8 op = result ? IOAT_OP_XOR_VAL : IOAT_OP_XOR;
+
+	BUG_ON(src_cnt < 2);
+
+	num_descs = ioat2_xferlen_to_descs(ioat, len);
+	/* we need 2x the number of descriptors to cover greater than 5
+	 * sources
+	 */
+	if (src_cnt > 5) {
+		with_ext = 1;
+		num_descs *= 2;
+	} else
+		with_ext = 0;
+
+	/* completion writes from the raid engine may pass completion
+	 * writes from the legacy engine, so we need one extra null
+	 * (legacy) descriptor to ensure all completion writes arrive in
+	 * order.
+	 */
+	if (likely(num_descs) &&
+	    ioat2_alloc_and_lock(&idx, ioat, num_descs+1) == 0)
+		/* pass */;
+	else
+		return NULL;
+	i = 0;
+	do {
+		struct ioat_raw_descriptor *descs[2];
+		size_t xfer_size = min_t(size_t, len, 1 << ioat->xfercap_log);
+		int s;
+
+		desc = ioat2_get_ring_ent(ioat, idx + i);
+		xor = desc->xor;
+
+		/* save a branch by unconditionally retrieving the
+		 * extended descriptor xor_set_src() knows to not write
+		 * to it in the single descriptor case
+		 */
+		ext = ioat2_get_ring_ent(ioat, idx + i + 1);
+		xor_ex = ext->xor_ex;
+
+		descs[0] = (struct ioat_raw_descriptor *) xor;
+		descs[1] = (struct ioat_raw_descriptor *) xor_ex;
+		for (s = 0; s < src_cnt; s++)
+			xor_set_src(descs, src[s], offset, s);
+		xor->size = xfer_size;
+		xor->dst_addr = dest + offset;
+		xor->ctl = 0;
+		xor->ctl_f.op = op;
+		xor->ctl_f.src_cnt = src_cnt_to_hw(src_cnt);
+
+		len -= xfer_size;
+		offset += xfer_size;
+		dump_desc_dbg(ioat, desc);
+	} while ((i += 1 + with_ext) < num_descs);
+
+	/* last xor descriptor carries the unmap parameters and fence bit */
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	if (result)
+		desc->result = result;
+	xor->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+
+	/* completion descriptor carries interrupt bit */
+	compl_desc = ioat2_get_ring_ent(ioat, idx + i);
+	compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
+	hw = compl_desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	hw->ctl_f.compl_write = 1;
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	dump_desc_dbg(ioat, compl_desc);
+
+	/* we leave the channel locked to ensure in order submission */
+	return &desc->txd;
+}
+
+static struct dma_async_tx_descriptor *
+ioat3_prep_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
+	       unsigned int src_cnt, size_t len, unsigned long flags)
+{
+	return __ioat3_prep_xor_lock(chan, NULL, dest, src, src_cnt, len, flags);
+}
+
+struct dma_async_tx_descriptor *
+ioat3_prep_xor_val(struct dma_chan *chan, dma_addr_t *src,
+		    unsigned int src_cnt, size_t len,
+		    enum sum_check_flags *result, unsigned long flags)
+{
+	/* the cleanup routine only sets bits on validate failure, it
+	 * does not clear bits on validate success... so clear it here
+	 */
+	*result = 0;
+
+	return __ioat3_prep_xor_lock(chan, result, src[0], &src[1],
+				     src_cnt - 1, len, flags);
+}
+
+static void
+dump_pq_desc_dbg(struct ioat2_dma_chan *ioat, struct ioat_ring_ent *desc, struct ioat_ring_ent *ext)
+{
+	struct device *dev = to_dev(&ioat->base);
+	struct ioat_pq_descriptor *pq = desc->pq;
+	struct ioat_pq_ext_descriptor *pq_ex = ext ? ext->pq_ex : NULL;
+	struct ioat_raw_descriptor *descs[] = { (void *) pq, (void *) pq_ex };
+	int src_cnt = src_cnt_to_sw(pq->ctl_f.src_cnt);
+	int i;
+
+	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) flags: %#x"
+		" sz: %#x ctl: %#x (op: %d int: %d compl: %d pq: '%s%s' src_cnt: %d)\n",
+		desc_id(desc), (unsigned long long) desc->txd.phys,
+		(unsigned long long) (pq_ex ? pq_ex->next : pq->next),
+		desc->txd.flags, pq->size, pq->ctl, pq->ctl_f.op, pq->ctl_f.int_en,
+		pq->ctl_f.compl_write,
+		pq->ctl_f.p_disable ? "" : "p", pq->ctl_f.q_disable ? "" : "q",
+		pq->ctl_f.src_cnt);
+	for (i = 0; i < src_cnt; i++)
+		dev_dbg(dev, "\tsrc[%d]: %#llx coef: %#x\n", i,
+			(unsigned long long) pq_get_src(descs, i), pq->coef[i]);
+	dev_dbg(dev, "\tP: %#llx\n", pq->p_addr);
+	dev_dbg(dev, "\tQ: %#llx\n", pq->q_addr);
+}
+
+static struct dma_async_tx_descriptor *
+__ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
+		     const dma_addr_t *dst, const dma_addr_t *src,
+		     unsigned int src_cnt, const unsigned char *scf,
+		     size_t len, unsigned long flags)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_chan_common *chan = &ioat->base;
+	struct ioat_ring_ent *compl_desc;
+	struct ioat_ring_ent *desc;
+	struct ioat_ring_ent *ext;
+	size_t total_len = len;
+	struct ioat_pq_descriptor *pq;
+	struct ioat_pq_ext_descriptor *pq_ex = NULL;
+	struct ioat_dma_descriptor *hw;
+	u32 offset = 0;
+	int num_descs;
+	int with_ext;
+	int i, s;
+	u16 idx;
+	u8 op = result ? IOAT_OP_PQ_VAL : IOAT_OP_PQ;
+
+	dev_dbg(to_dev(chan), "%s\n", __func__);
+	/* the engine requires at least two sources (we provide
+	 * at least 1 implied source in the DMA_PREP_CONTINUE case)
+	 */
+	BUG_ON(src_cnt + dmaf_continue(flags) < 2);
+
+	num_descs = ioat2_xferlen_to_descs(ioat, len);
+	/* we need 2x the number of descriptors to cover greater than 3
+	 * sources
+	 */
+	if (src_cnt > 3 || flags & DMA_PREP_CONTINUE) {
+		with_ext = 1;
+		num_descs *= 2;
+	} else
+		with_ext = 0;
+
+	/* completion writes from the raid engine may pass completion
+	 * writes from the legacy engine, so we need one extra null
+	 * (legacy) descriptor to ensure all completion writes arrive in
+	 * order.
+	 */
+	if (likely(num_descs) &&
+	    ioat2_alloc_and_lock(&idx, ioat, num_descs+1) == 0)
+		/* pass */;
+	else
+		return NULL;
+	i = 0;
+	do {
+		struct ioat_raw_descriptor *descs[2];
+		size_t xfer_size = min_t(size_t, len, 1 << ioat->xfercap_log);
+
+		desc = ioat2_get_ring_ent(ioat, idx + i);
+		pq = desc->pq;
+
+		/* save a branch by unconditionally retrieving the
+		 * extended descriptor pq_set_src() knows to not write
+		 * to it in the single descriptor case
+		 */
+		ext = ioat2_get_ring_ent(ioat, idx + i + with_ext);
+		pq_ex = ext->pq_ex;
+
+		descs[0] = (struct ioat_raw_descriptor *) pq;
+		descs[1] = (struct ioat_raw_descriptor *) pq_ex;
+
+		for (s = 0; s < src_cnt; s++)
+			pq_set_src(descs, src[s], offset, scf[s], s);
+
+		/* see the comment for dma_maxpq in include/linux/dmaengine.h */
+		if (dmaf_p_disabled_continue(flags))
+			pq_set_src(descs, dst[1], offset, 1, s++);
+		else if (dmaf_continue(flags)) {
+			pq_set_src(descs, dst[0], offset, 0, s++);
+			pq_set_src(descs, dst[1], offset, 1, s++);
+			pq_set_src(descs, dst[1], offset, 0, s++);
+		}
+		pq->size = xfer_size;
+		pq->p_addr = dst[0] + offset;
+		pq->q_addr = dst[1] + offset;
+		pq->ctl = 0;
+		pq->ctl_f.op = op;
+		pq->ctl_f.src_cnt = src_cnt_to_hw(s);
+		pq->ctl_f.p_disable = !!(flags & DMA_PREP_PQ_DISABLE_P);
+		pq->ctl_f.q_disable = !!(flags & DMA_PREP_PQ_DISABLE_Q);
+
+		len -= xfer_size;
+		offset += xfer_size;
+	} while ((i += 1 + with_ext) < num_descs);
+
+	/* last pq descriptor carries the unmap parameters and fence bit */
+	desc->txd.flags = flags;
+	desc->len = total_len;
+	if (result)
+		desc->result = result;
+	pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+	dump_pq_desc_dbg(ioat, desc, ext);
+
+	/* completion descriptor carries interrupt bit */
+	compl_desc = ioat2_get_ring_ent(ioat, idx + i);
+	compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
+	hw = compl_desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	hw->ctl_f.compl_write = 1;
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	dump_desc_dbg(ioat, compl_desc);
+
+	/* we leave the channel locked to ensure in order submission */
+	return &desc->txd;
+}
+
+static struct dma_async_tx_descriptor *
+ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
+	      unsigned int src_cnt, const unsigned char *scf, size_t len,
+	      unsigned long flags)
+{
+	/* handle the single source multiply case from the raid6
+	 * recovery path
+	 */
+	if (unlikely((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1)) {
+		dma_addr_t single_source[2];
+		unsigned char single_source_coef[2];
+
+		BUG_ON(flags & DMA_PREP_PQ_DISABLE_Q);
+		single_source[0] = src[0];
+		single_source[1] = src[0];
+		single_source_coef[0] = scf[0];
+		single_source_coef[1] = 0;
+
+		return __ioat3_prep_pq_lock(chan, NULL, dst, single_source, 2,
+					    single_source_coef, len, flags);
+	} else
+		return __ioat3_prep_pq_lock(chan, NULL, dst, src, src_cnt, scf,
+					    len, flags);
+}
+
+struct dma_async_tx_descriptor *
+ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
+		  unsigned int src_cnt, const unsigned char *scf, size_t len,
+		  enum sum_check_flags *pqres, unsigned long flags)
+{
+	/* the cleanup routine only sets bits on validate failure, it
+	 * does not clear bits on validate success... so clear it here
+	 */
+	*pqres = 0;
+
+	return __ioat3_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
+				    flags);
+}
+
+static struct dma_async_tx_descriptor *
+ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
+		 unsigned int src_cnt, size_t len, unsigned long flags)
+{
+	unsigned char scf[src_cnt];
+	dma_addr_t pq[2];
+
+	memset(scf, 0, src_cnt);
+	flags |= DMA_PREP_PQ_DISABLE_Q;
+	pq[0] = dst;
+	pq[1] = ~0;
+
+	return __ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
+				    flags);
+}
+
+struct dma_async_tx_descriptor *
+ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
+		     unsigned int src_cnt, size_t len,
+		     enum sum_check_flags *result, unsigned long flags)
+{
+	unsigned char scf[src_cnt];
+	dma_addr_t pq[2];
+
+	/* the cleanup routine only sets bits on validate failure, it
+	 * does not clear bits on validate success... so clear it here
+	 */
+	*result = 0;
+
+	memset(scf, 0, src_cnt);
+	flags |= DMA_PREP_PQ_DISABLE_Q;
+	pq[0] = src[0];
+	pq[1] = ~0;
+
+	return __ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1, scf,
+				    len, flags);
+}
+
+static struct dma_async_tx_descriptor *
+ioat3_prep_interrupt_lock(struct dma_chan *c, unsigned long flags)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
+	struct ioat_ring_ent *desc;
+	struct ioat_dma_descriptor *hw;
+	u16 idx;
+
+	if (ioat2_alloc_and_lock(&idx, ioat, 1) == 0)
+		desc = ioat2_get_ring_ent(ioat, idx);
+	else
+		return NULL;
+
+	hw = desc->hw;
+	hw->ctl = 0;
+	hw->ctl_f.null = 1;
+	hw->ctl_f.int_en = 1;
+	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
+	hw->ctl_f.compl_write = 1;
+	hw->size = NULL_DESC_BUFFER_SIZE;
+	hw->src_addr = 0;
+	hw->dst_addr = 0;
+
+	desc->txd.flags = flags;
+	desc->len = 1;
+
+	dump_desc_dbg(ioat, desc);
+
+	/* we leave the channel locked to ensure in order submission */
+	return &desc->txd;
+}
+
+static void __devinit ioat3_dma_test_callback(void *dma_async_param)
+{
+	struct completion *cmp = dma_async_param;
+
+	complete(cmp);
+}
+
+#define IOAT_NUM_SRC_TEST 6 /* must be <= 8 */
+static int __devinit ioat_xor_val_self_test(struct ioatdma_device *device)
+{
+	int i, src_idx;
+	struct page *dest;
+	struct page *xor_srcs[IOAT_NUM_SRC_TEST];
+	struct page *xor_val_srcs[IOAT_NUM_SRC_TEST + 1];
+	dma_addr_t dma_srcs[IOAT_NUM_SRC_TEST + 1];
+	dma_addr_t dma_addr, dest_dma;
+	struct dma_async_tx_descriptor *tx;
+	struct dma_chan *dma_chan;
+	dma_cookie_t cookie;
+	u8 cmp_byte = 0;
+	u32 cmp_word;
+	u32 xor_val_result;
+	int err = 0;
+	struct completion cmp;
+	unsigned long tmo;
+	struct device *dev = &device->pdev->dev;
+	struct dma_device *dma = &device->common;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	if (!dma_has_cap(DMA_XOR, dma->cap_mask))
+		return 0;
+
+	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++) {
+		xor_srcs[src_idx] = alloc_page(GFP_KERNEL);
+		if (!xor_srcs[src_idx]) {
+			while (src_idx--)
+				__free_page(xor_srcs[src_idx]);
+			return -ENOMEM;
+		}
+	}
+
+	dest = alloc_page(GFP_KERNEL);
+	if (!dest) {
+		while (src_idx--)
+			__free_page(xor_srcs[src_idx]);
+		return -ENOMEM;
+	}
+
+	/* Fill in src buffers */
+	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++) {
+		u8 *ptr = page_address(xor_srcs[src_idx]);
+		for (i = 0; i < PAGE_SIZE; i++)
+			ptr[i] = (1 << src_idx);
+	}
+
+	for (src_idx = 0; src_idx < IOAT_NUM_SRC_TEST; src_idx++)
+		cmp_byte ^= (u8) (1 << src_idx);
+
+	cmp_word = (cmp_byte << 24) | (cmp_byte << 16) |
+			(cmp_byte << 8) | cmp_byte;
+
+	memset(page_address(dest), 0, PAGE_SIZE);
+
+	dma_chan = container_of(dma->channels.next, struct dma_chan,
+				device_node);
+	if (dma->device_alloc_chan_resources(dma_chan) < 1) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	/* test xor */
+	dest_dma = dma_map_page(dev, dest, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+		dma_srcs[i] = dma_map_page(dev, xor_srcs[i], 0, PAGE_SIZE,
+					   DMA_TO_DEVICE);
+	tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
+				      IOAT_NUM_SRC_TEST, PAGE_SIZE,
+				      DMA_PREP_INTERRUPT);
+
+	if (!tx) {
+		dev_err(dev, "Self-test xor prep failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat3_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test xor setup failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (dma->device_is_tx_complete(dma_chan, cookie, NULL, NULL) != DMA_SUCCESS) {
+		dev_err(dev, "Self-test xor timed out\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	dma_sync_single_for_cpu(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+	for (i = 0; i < (PAGE_SIZE / sizeof(u32)); i++) {
+		u32 *ptr = page_address(dest);
+		if (ptr[i] != cmp_word) {
+			dev_err(dev, "Self-test xor failed compare\n");
+			err = -ENODEV;
+			goto free_resources;
+		}
+	}
+	dma_sync_single_for_device(dev, dest_dma, PAGE_SIZE, DMA_TO_DEVICE);
+
+	/* skip validate if the capability is not present */
+	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
+		goto free_resources;
+
+	/* validate the sources with the destintation page */
+	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+		xor_val_srcs[i] = xor_srcs[i];
+	xor_val_srcs[i] = dest;
+
+	xor_val_result = 1;
+
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
+					   DMA_TO_DEVICE);
+	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
+					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
+					  &xor_val_result, DMA_PREP_INTERRUPT);
+	if (!tx) {
+		dev_err(dev, "Self-test zero prep failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat3_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test zero setup failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (dma->device_is_tx_complete(dma_chan, cookie, NULL, NULL) != DMA_SUCCESS) {
+		dev_err(dev, "Self-test validate timed out\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	if (xor_val_result != 0) {
+		dev_err(dev, "Self-test validate failed compare\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	/* skip memset if the capability is not present */
+	if (!dma_has_cap(DMA_MEMSET, dma_chan->device->cap_mask))
+		goto free_resources;
+
+	/* test memset */
+	dma_addr = dma_map_page(dev, dest, 0,
+			PAGE_SIZE, DMA_FROM_DEVICE);
+	tx = dma->device_prep_dma_memset(dma_chan, dma_addr, 0, PAGE_SIZE,
+					 DMA_PREP_INTERRUPT);
+	if (!tx) {
+		dev_err(dev, "Self-test memset prep failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat3_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test memset setup failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (dma->device_is_tx_complete(dma_chan, cookie, NULL, NULL) != DMA_SUCCESS) {
+		dev_err(dev, "Self-test memset timed out\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	for (i = 0; i < PAGE_SIZE/sizeof(u32); i++) {
+		u32 *ptr = page_address(dest);
+		if (ptr[i]) {
+			dev_err(dev, "Self-test memset failed compare\n");
+			err = -ENODEV;
+			goto free_resources;
+		}
+	}
+
+	/* test for non-zero parity sum */
+	xor_val_result = 0;
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
+					   DMA_TO_DEVICE);
+	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
+					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
+					  &xor_val_result, DMA_PREP_INTERRUPT);
+	if (!tx) {
+		dev_err(dev, "Self-test 2nd zero prep failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	async_tx_ack(tx);
+	init_completion(&cmp);
+	tx->callback = ioat3_dma_test_callback;
+	tx->callback_param = &cmp;
+	cookie = tx->tx_submit(tx);
+	if (cookie < 0) {
+		dev_err(dev, "Self-test  2nd zero setup failed\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+	dma->device_issue_pending(dma_chan);
+
+	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+	if (dma->device_is_tx_complete(dma_chan, cookie, NULL, NULL) != DMA_SUCCESS) {
+		dev_err(dev, "Self-test 2nd validate timed out\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	if (xor_val_result != SUM_CHECK_P_RESULT) {
+		dev_err(dev, "Self-test validate failed compare\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+free_resources:
+	dma->device_free_chan_resources(dma_chan);
+out:
+	src_idx = IOAT_NUM_SRC_TEST;
+	while (src_idx--)
+		__free_page(xor_srcs[src_idx]);
+	__free_page(dest);
+	return err;
+}
+
+static int __devinit ioat3_dma_self_test(struct ioatdma_device *device)
+{
+	int rc = ioat_dma_self_test(device);
+
+	if (rc)
+		return rc;
+
+	rc = ioat_xor_val_self_test(device);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca)
+{
+	struct pci_dev *pdev = device->pdev;
+	struct dma_device *dma;
+	struct dma_chan *c;
+	struct ioat_chan_common *chan;
+	bool is_raid_device = false;
+	int err;
+	u16 dev_id;
+	u32 cap;
+
+	device->enumerate_channels = ioat2_enumerate_channels;
+	device->self_test = ioat3_dma_self_test;
+	dma = &device->common;
+	dma->device_prep_dma_memcpy = ioat2_dma_prep_memcpy_lock;
+	dma->device_issue_pending = ioat2_issue_pending;
+	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
+	dma->device_free_chan_resources = ioat2_free_chan_resources;
+
+	dma_cap_set(DMA_INTERRUPT, dma->cap_mask);
+	dma->device_prep_dma_interrupt = ioat3_prep_interrupt_lock;
+
+	cap = readl(device->reg_base + IOAT_DMA_CAP_OFFSET);
+	if (cap & IOAT_CAP_XOR) {
+		is_raid_device = true;
+		dma->max_xor = 8;
+		dma->xor_align = 2;
+
+		dma_cap_set(DMA_XOR, dma->cap_mask);
+		dma->device_prep_dma_xor = ioat3_prep_xor;
+
+		dma_cap_set(DMA_XOR_VAL, dma->cap_mask);
+		dma->device_prep_dma_xor_val = ioat3_prep_xor_val;
+	}
+	if (cap & IOAT_CAP_PQ) {
+		is_raid_device = true;
+		dma_set_maxpq(dma, 8, 0);
+		dma->pq_align = 2;
+
+		dma_cap_set(DMA_PQ, dma->cap_mask);
+		dma->device_prep_dma_pq = ioat3_prep_pq;
+
+		dma_cap_set(DMA_PQ_VAL, dma->cap_mask);
+		dma->device_prep_dma_pq_val = ioat3_prep_pq_val;
+
+		if (!(cap & IOAT_CAP_XOR)) {
+			dma->max_xor = 8;
+			dma->xor_align = 2;
+
+			dma_cap_set(DMA_XOR, dma->cap_mask);
+			dma->device_prep_dma_xor = ioat3_prep_pqxor;
+
+			dma_cap_set(DMA_XOR_VAL, dma->cap_mask);
+			dma->device_prep_dma_xor_val = ioat3_prep_pqxor_val;
+		}
+	}
+	if (is_raid_device && (cap & IOAT_CAP_FILL_BLOCK)) {
+		dma_cap_set(DMA_MEMSET, dma->cap_mask);
+		dma->device_prep_dma_memset = ioat3_prep_memset_lock;
+	}
+
+
+	if (is_raid_device) {
+		dma->device_is_tx_complete = ioat3_is_complete;
+		device->cleanup_tasklet = ioat3_cleanup_tasklet;
+		device->timer_fn = ioat3_timer_event;
+	} else {
+		dma->device_is_tx_complete = ioat2_is_complete;
+		device->cleanup_tasklet = ioat2_cleanup_tasklet;
+		device->timer_fn = ioat2_timer_event;
+	}
+
+	/* -= IOAT ver.3 workarounds =- */
+	/* Write CHANERRMSK_INT with 3E07h to mask out the errors
+	 * that can cause stability issues for IOAT ver.3
+	 */
+	pci_write_config_dword(pdev, IOAT_PCI_CHANERRMASK_INT_OFFSET, 0x3e07);
+
+	/* Clear DMAUNCERRSTS Cfg-Reg Parity Error status bit
+	 * (workaround for spurious config parity error after restart)
+	 */
+	pci_read_config_word(pdev, IOAT_PCI_DEVICE_ID_OFFSET, &dev_id);
+	if (dev_id == PCI_DEVICE_ID_INTEL_IOAT_TBG0)
+		pci_write_config_dword(pdev, IOAT_PCI_DMAUNCERRSTS_OFFSET, 0x10);
+
+	err = ioat_probe(device);
+	if (err)
+		return err;
+	ioat_set_tcp_copy_break(262144);
+
+	list_for_each_entry(c, &dma->channels, device_node) {
+		chan = to_chan_common(c);
+		writel(IOAT_DMA_DCA_ANY_CPU,
+		       chan->reg_base + IOAT_DCACTRL_OFFSET);
+	}
+
+	err = ioat_register(device);
+	if (err)
+		return err;
+
+	ioat_kobject_add(device, &ioat2_ktype);
+
+	if (dca)
+		device->dca = ioat3_dca_init(pdev, device->reg_base);
+
+	return 0;
+}
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
new file mode 100644
index 00000000000..99afb12bd40
--- /dev/null
+++ b/drivers/dma/ioat/hw.h
@@ -0,0 +1,215 @@
+/*
+ * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
+ */
+#ifndef _IOAT_HW_H_
+#define _IOAT_HW_H_
+
+/* PCI Configuration Space Values */
+#define IOAT_PCI_VID            0x8086
+#define IOAT_MMIO_BAR		0
+
+/* CB device ID's */
+#define IOAT_PCI_DID_5000       0x1A38
+#define IOAT_PCI_DID_CNB        0x360B
+#define IOAT_PCI_DID_SCNB       0x65FF
+#define IOAT_PCI_DID_SNB        0x402F
+
+#define IOAT_PCI_RID            0x00
+#define IOAT_PCI_SVID           0x8086
+#define IOAT_PCI_SID            0x8086
+#define IOAT_VER_1_2            0x12    /* Version 1.2 */
+#define IOAT_VER_2_0            0x20    /* Version 2.0 */
+#define IOAT_VER_3_0            0x30    /* Version 3.0 */
+#define IOAT_VER_3_2            0x32    /* Version 3.2 */
+
+struct ioat_dma_descriptor {
+	uint32_t	size;
+	union {
+		uint32_t ctl;
+		struct {
+			unsigned int int_en:1;
+			unsigned int src_snoop_dis:1;
+			unsigned int dest_snoop_dis:1;
+			unsigned int compl_write:1;
+			unsigned int fence:1;
+			unsigned int null:1;
+			unsigned int src_brk:1;
+			unsigned int dest_brk:1;
+			unsigned int bundle:1;
+			unsigned int dest_dca:1;
+			unsigned int hint:1;
+			unsigned int rsvd2:13;
+			#define IOAT_OP_COPY 0x00
+			unsigned int op:8;
+		} ctl_f;
+	};
+	uint64_t	src_addr;
+	uint64_t	dst_addr;
+	uint64_t	next;
+	uint64_t	rsv1;
+	uint64_t	rsv2;
+	/* store some driver data in an unused portion of the descriptor */
+	union {
+		uint64_t	user1;
+		uint64_t	tx_cnt;
+	};
+	uint64_t	user2;
+};
+
+struct ioat_fill_descriptor {
+	uint32_t	size;
+	union {
+		uint32_t ctl;
+		struct {
+			unsigned int int_en:1;
+			unsigned int rsvd:1;
+			unsigned int dest_snoop_dis:1;
+			unsigned int compl_write:1;
+			unsigned int fence:1;
+			unsigned int rsvd2:2;
+			unsigned int dest_brk:1;
+			unsigned int bundle:1;
+			unsigned int rsvd4:15;
+			#define IOAT_OP_FILL 0x01
+			unsigned int op:8;
+		} ctl_f;
+	};
+	uint64_t	src_data;
+	uint64_t	dst_addr;
+	uint64_t	next;
+	uint64_t	rsv1;
+	uint64_t	next_dst_addr;
+	uint64_t	user1;
+	uint64_t	user2;
+};
+
+struct ioat_xor_descriptor {
+	uint32_t	size;
+	union {
+		uint32_t ctl;
+		struct {
+			unsigned int int_en:1;
+			unsigned int src_snoop_dis:1;
+			unsigned int dest_snoop_dis:1;
+			unsigned int compl_write:1;
+			unsigned int fence:1;
+			unsigned int src_cnt:3;
+			unsigned int bundle:1;
+			unsigned int dest_dca:1;
+			unsigned int hint:1;
+			unsigned int rsvd:13;
+			#define IOAT_OP_XOR 0x87
+			#define IOAT_OP_XOR_VAL 0x88
+			unsigned int op:8;
+		} ctl_f;
+	};
+	uint64_t	src_addr;
+	uint64_t	dst_addr;
+	uint64_t	next;
+	uint64_t	src_addr2;
+	uint64_t	src_addr3;
+	uint64_t	src_addr4;
+	uint64_t	src_addr5;
+};
+
+struct ioat_xor_ext_descriptor {
+	uint64_t	src_addr6;
+	uint64_t	src_addr7;
+	uint64_t	src_addr8;
+	uint64_t	next;
+	uint64_t	rsvd[4];
+};
+
+struct ioat_pq_descriptor {
+	uint32_t	size;
+	union {
+		uint32_t ctl;
+		struct {
+			unsigned int int_en:1;
+			unsigned int src_snoop_dis:1;
+			unsigned int dest_snoop_dis:1;
+			unsigned int compl_write:1;
+			unsigned int fence:1;
+			unsigned int src_cnt:3;
+			unsigned int bundle:1;
+			unsigned int dest_dca:1;
+			unsigned int hint:1;
+			unsigned int p_disable:1;
+			unsigned int q_disable:1;
+			unsigned int rsvd:11;
+			#define IOAT_OP_PQ 0x89
+			#define IOAT_OP_PQ_VAL 0x8a
+			unsigned int op:8;
+		} ctl_f;
+	};
+	uint64_t	src_addr;
+	uint64_t	p_addr;
+	uint64_t	next;
+	uint64_t	src_addr2;
+	uint64_t	src_addr3;
+	uint8_t		coef[8];
+	uint64_t	q_addr;
+};
+
+struct ioat_pq_ext_descriptor {
+	uint64_t	src_addr4;
+	uint64_t	src_addr5;
+	uint64_t	src_addr6;
+	uint64_t	next;
+	uint64_t	src_addr7;
+	uint64_t	src_addr8;
+	uint64_t	rsvd[2];
+};
+
+struct ioat_pq_update_descriptor {
+	uint32_t	size;
+	union {
+		uint32_t ctl;
+		struct {
+			unsigned int int_en:1;
+			unsigned int src_snoop_dis:1;
+			unsigned int dest_snoop_dis:1;
+			unsigned int compl_write:1;
+			unsigned int fence:1;
+			unsigned int src_cnt:3;
+			unsigned int bundle:1;
+			unsigned int dest_dca:1;
+			unsigned int hint:1;
+			unsigned int p_disable:1;
+			unsigned int q_disable:1;
+			unsigned int rsvd:3;
+			unsigned int coef:8;
+			#define IOAT_OP_PQ_UP 0x8b
+			unsigned int op:8;
+		} ctl_f;
+	};
+	uint64_t	src_addr;
+	uint64_t	p_addr;
+	uint64_t	next;
+	uint64_t	src_addr2;
+	uint64_t	p_src;
+	uint64_t	q_src;
+	uint64_t	q_addr;
+};
+
+struct ioat_raw_descriptor {
+	uint64_t	field[8];
+};
+#endif
diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c
new file mode 100644
index 00000000000..d545fae30f3
--- /dev/null
+++ b/drivers/dma/ioat/pci.c
@@ -0,0 +1,210 @@
+/*
+ * Intel I/OAT DMA Linux driver
+ * Copyright(c) 2007 - 2009 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+
+/*
+ * This driver supports an Intel I/OAT DMA engine, which does asynchronous
+ * copy operations.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/dca.h>
+#include "dma.h"
+#include "dma_v2.h"
+#include "registers.h"
+#include "hw.h"
+
+MODULE_VERSION(IOAT_DMA_VERSION);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel Corporation");
+
+static struct pci_device_id ioat_pci_tbl[] = {
+	/* I/OAT v1 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_CNB)  },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SCNB) },
+	{ PCI_VDEVICE(UNISYS, PCI_DEVICE_ID_UNISYS_DMA_DIRECTOR) },
+
+	/* I/OAT v2 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB) },
+
+	/* I/OAT v3 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG7) },
+
+	/* I/OAT v3.2 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF7) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF8) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF9) },
+
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, ioat_pci_tbl);
+
+static int __devinit ioat_pci_probe(struct pci_dev *pdev,
+				    const struct pci_device_id *id);
+static void __devexit ioat_remove(struct pci_dev *pdev);
+
+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)");
+
+struct kmem_cache *ioat2_cache;
+
+#define DRV_NAME "ioatdma"
+
+static struct pci_driver ioat_pci_driver = {
+	.name		= DRV_NAME,
+	.id_table	= ioat_pci_tbl,
+	.probe		= ioat_pci_probe,
+	.remove		= __devexit_p(ioat_remove),
+};
+
+static struct ioatdma_device *
+alloc_ioatdma(struct pci_dev *pdev, void __iomem *iobase)
+{
+	struct device *dev = &pdev->dev;
+	struct ioatdma_device *d = devm_kzalloc(dev, sizeof(*d), GFP_KERNEL);
+
+	if (!d)
+		return NULL;
+	d->pdev = pdev;
+	d->reg_base = iobase;
+	return d;
+}
+
+static int __devinit ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	void __iomem * const *iomap;
+	struct device *dev = &pdev->dev;
+	struct ioatdma_device *device;
+	int err;
+
+	err = pcim_enable_device(pdev);
+	if (err)
+		return err;
+
+	err = pcim_iomap_regions(pdev, 1 << IOAT_MMIO_BAR, DRV_NAME);
+	if (err)
+		return err;
+	iomap = pcim_iomap_table(pdev);
+	if (!iomap)
+		return -ENOMEM;
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err)
+		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err)
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	device = devm_kzalloc(dev, sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return -ENOMEM;
+
+	pci_set_master(pdev);
+
+	device = alloc_ioatdma(pdev, iomap[IOAT_MMIO_BAR]);
+	if (!device)
+		return -ENOMEM;
+	pci_set_drvdata(pdev, device);
+
+	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
+	if (device->version == IOAT_VER_1_2)
+		err = ioat1_dma_probe(device, ioat_dca_enabled);
+	else if (device->version == IOAT_VER_2_0)
+		err = ioat2_dma_probe(device, ioat_dca_enabled);
+	else if (device->version >= IOAT_VER_3_0)
+		err = ioat3_dma_probe(device, ioat_dca_enabled);
+	else
+		return -ENODEV;
+
+	if (err) {
+		dev_err(dev, "Intel(R) I/OAT DMA Engine init failed\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void __devexit ioat_remove(struct pci_dev *pdev)
+{
+	struct ioatdma_device *device = pci_get_drvdata(pdev);
+
+	if (!device)
+		return;
+
+	dev_err(&pdev->dev, "Removing dma and dca services\n");
+	if (device->dca) {
+		unregister_dca_provider(device->dca, &pdev->dev);
+		free_dca_provider(device->dca);
+		device->dca = NULL;
+	}
+	ioat_dma_remove(device);
+}
+
+static int __init ioat_init_module(void)
+{
+	int err;
+
+	pr_info("%s: Intel(R) QuickData Technology Driver %s\n",
+		DRV_NAME, IOAT_DMA_VERSION);
+
+	ioat2_cache = kmem_cache_create("ioat2", sizeof(struct ioat_ring_ent),
+					0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!ioat2_cache)
+		return -ENOMEM;
+
+	err = pci_register_driver(&ioat_pci_driver);
+	if (err)
+		kmem_cache_destroy(ioat2_cache);
+
+	return err;
+}
+module_init(ioat_init_module);
+
+static void __exit ioat_exit_module(void)
+{
+	pci_unregister_driver(&ioat_pci_driver);
+	kmem_cache_destroy(ioat2_cache);
+}
+module_exit(ioat_exit_module);
diff --git a/drivers/dma/ioatdma_registers.h b/drivers/dma/ioat/registers.h
index 49bc277424f..63038e18ab0 100644
--- a/drivers/dma/ioatdma_registers.h
+++ b/drivers/dma/ioat/registers.h
@@ -64,18 +64,37 @@
 
 #define IOAT_DEVICE_STATUS_OFFSET		0x0E	/* 16-bit */
 #define IOAT_DEVICE_STATUS_DEGRADED_MODE	0x0001
+#define IOAT_DEVICE_MMIO_RESTRICTED		0x0002
+#define IOAT_DEVICE_MEMORY_BYPASS		0x0004
+#define IOAT_DEVICE_ADDRESS_REMAPPING		0x0008
+
+#define IOAT_DMA_CAP_OFFSET			0x10	/* 32-bit */
+#define IOAT_CAP_PAGE_BREAK			0x00000001
+#define IOAT_CAP_CRC				0x00000002
+#define IOAT_CAP_SKIP_MARKER			0x00000004
+#define IOAT_CAP_DCA				0x00000010
+#define IOAT_CAP_CRC_MOVE			0x00000020
+#define IOAT_CAP_FILL_BLOCK			0x00000040
+#define IOAT_CAP_APIC				0x00000080
+#define IOAT_CAP_XOR				0x00000100
+#define IOAT_CAP_PQ				0x00000200
 
 #define IOAT_CHANNEL_MMIO_SIZE			0x80	/* Each Channel MMIO space is this size */
 
 /* DMA Channel Registers */
 #define IOAT_CHANCTRL_OFFSET			0x00	/* 16-bit Channel Control Register */
 #define IOAT_CHANCTRL_CHANNEL_PRIORITY_MASK	0xF000
+#define IOAT3_CHANCTRL_COMPL_DCA_EN		0x0200
 #define IOAT_CHANCTRL_CHANNEL_IN_USE		0x0100
 #define IOAT_CHANCTRL_DESCRIPTOR_ADDR_SNOOP_CONTROL	0x0020
 #define IOAT_CHANCTRL_ERR_INT_EN		0x0010
 #define IOAT_CHANCTRL_ANY_ERR_ABORT_EN		0x0008
 #define IOAT_CHANCTRL_ERR_COMPLETION_EN		0x0004
-#define IOAT_CHANCTRL_INT_DISABLE		0x0001
+#define IOAT_CHANCTRL_INT_REARM			0x0001
+#define IOAT_CHANCTRL_RUN			(IOAT_CHANCTRL_INT_REARM |\
+						 IOAT_CHANCTRL_ERR_COMPLETION_EN |\
+						 IOAT_CHANCTRL_ANY_ERR_ABORT_EN |\
+						 IOAT_CHANCTRL_ERR_INT_EN)
 
 #define IOAT_DMA_COMP_OFFSET			0x02	/* 16-bit DMA channel compatibility */
 #define IOAT_DMA_COMP_V1			0x0001	/* Compatibility with DMA version 1 */
@@ -94,14 +113,14 @@
 #define IOAT2_CHANSTS_OFFSET_HIGH	0x0C
 #define IOAT_CHANSTS_OFFSET_HIGH(ver)		((ver) < IOAT_VER_2_0 \
 						? IOAT1_CHANSTS_OFFSET_HIGH : IOAT2_CHANSTS_OFFSET_HIGH)
-#define IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR	~0x3F
-#define IOAT_CHANSTS_SOFT_ERR			0x0000000000000010
-#define IOAT_CHANSTS_UNAFFILIATED_ERR		0x0000000000000008
-#define IOAT_CHANSTS_DMA_TRANSFER_STATUS	0x0000000000000007
-#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE	0x0
-#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_DONE	0x1
-#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_SUSPENDED	0x2
-#define IOAT_CHANSTS_DMA_TRANSFER_STATUS_HALTED	0x3
+#define IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR	(~0x3fULL)
+#define IOAT_CHANSTS_SOFT_ERR			0x10ULL
+#define IOAT_CHANSTS_UNAFFILIATED_ERR		0x8ULL
+#define IOAT_CHANSTS_STATUS	0x7ULL
+#define IOAT_CHANSTS_ACTIVE	0x0
+#define IOAT_CHANSTS_DONE	0x1
+#define IOAT_CHANSTS_SUSPENDED	0x2
+#define IOAT_CHANSTS_HALTED	0x3
 
 
 
@@ -204,22 +223,27 @@
 #define IOAT_CDAR_OFFSET_HIGH			0x24
 
 #define IOAT_CHANERR_OFFSET			0x28	/* 32-bit Channel Error Register */
-#define IOAT_CHANERR_DMA_TRANSFER_SRC_ADDR_ERR	0x0001
-#define IOAT_CHANERR_DMA_TRANSFER_DEST_ADDR_ERR	0x0002
-#define IOAT_CHANERR_NEXT_DESCRIPTOR_ADDR_ERR	0x0004
-#define IOAT_CHANERR_NEXT_DESCRIPTOR_ALIGNMENT_ERR	0x0008
+#define IOAT_CHANERR_SRC_ADDR_ERR	0x0001
+#define IOAT_CHANERR_DEST_ADDR_ERR	0x0002
+#define IOAT_CHANERR_NEXT_ADDR_ERR	0x0004
+#define IOAT_CHANERR_NEXT_DESC_ALIGN_ERR	0x0008
 #define IOAT_CHANERR_CHAIN_ADDR_VALUE_ERR	0x0010
 #define IOAT_CHANERR_CHANCMD_ERR		0x0020
 #define IOAT_CHANERR_CHIPSET_UNCORRECTABLE_DATA_INTEGRITY_ERR	0x0040
 #define IOAT_CHANERR_DMA_UNCORRECTABLE_DATA_INTEGRITY_ERR	0x0080
 #define IOAT_CHANERR_READ_DATA_ERR		0x0100
 #define IOAT_CHANERR_WRITE_DATA_ERR		0x0200
-#define IOAT_CHANERR_DESCRIPTOR_CONTROL_ERR	0x0400
-#define IOAT_CHANERR_DESCRIPTOR_LENGTH_ERR	0x0800
+#define IOAT_CHANERR_CONTROL_ERR	0x0400
+#define IOAT_CHANERR_LENGTH_ERR	0x0800
 #define IOAT_CHANERR_COMPLETION_ADDR_ERR	0x1000
 #define IOAT_CHANERR_INT_CONFIGURATION_ERR	0x2000
 #define IOAT_CHANERR_SOFT_ERR			0x4000
 #define IOAT_CHANERR_UNAFFILIATED_ERR		0x8000
+#define IOAT_CHANERR_XOR_P_OR_CRC_ERR		0x10000
+#define IOAT_CHANERR_XOR_Q_ERR			0x20000
+#define IOAT_CHANERR_DESCRIPTOR_COUNT_ERR	0x40000
+
+#define IOAT_CHANERR_HANDLE_MASK (IOAT_CHANERR_XOR_P_OR_CRC_ERR | IOAT_CHANERR_XOR_Q_ERR)
 
 #define IOAT_CHANERR_MASK_OFFSET		0x2C	/* 32-bit Channel Error Register */
 
diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c
deleted file mode 100644
index a600fc0f796..00000000000
--- a/drivers/dma/ioat_dma.c
+++ /dev/null
@@ -1,1741 +0,0 @@
-/*
- * Intel I/OAT DMA Linux driver
- * Copyright(c) 2004 - 2009 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- */
-
-/*
- * This driver supports an Intel I/OAT DMA engine, which does asynchronous
- * copy operations.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/dmaengine.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-#include <linux/workqueue.h>
-#include <linux/i7300_idle.h>
-#include "ioatdma.h"
-#include "ioatdma_registers.h"
-#include "ioatdma_hw.h"
-
-#define to_ioat_chan(chan) container_of(chan, struct ioat_dma_chan, common)
-#define to_ioatdma_device(dev) container_of(dev, struct ioatdma_device, common)
-#define to_ioat_desc(lh) container_of(lh, struct ioat_desc_sw, node)
-#define tx_to_ioat_desc(tx) container_of(tx, struct ioat_desc_sw, async_tx)
-
-#define chan_num(ch) ((int)((ch)->reg_base - (ch)->device->reg_base) / 0x80)
-static int ioat_pending_level = 4;
-module_param(ioat_pending_level, int, 0644);
-MODULE_PARM_DESC(ioat_pending_level,
-		 "high-water mark for pushing ioat descriptors (default: 4)");
-
-#define RESET_DELAY  msecs_to_jiffies(100)
-#define WATCHDOG_DELAY  round_jiffies(msecs_to_jiffies(2000))
-static void ioat_dma_chan_reset_part2(struct work_struct *work);
-static void ioat_dma_chan_watchdog(struct work_struct *work);
-
-/*
- * workaround for IOAT ver.3.0 null descriptor issue
- * (channel returns error when size is 0)
- */
-#define NULL_DESC_BUFFER_SIZE 1
-
-/* internal functions */
-static void ioat_dma_start_null_desc(struct ioat_dma_chan *ioat_chan);
-static void ioat_dma_memcpy_cleanup(struct ioat_dma_chan *ioat_chan);
-
-static struct ioat_desc_sw *
-ioat1_dma_get_next_descriptor(struct ioat_dma_chan *ioat_chan);
-static struct ioat_desc_sw *
-ioat2_dma_get_next_descriptor(struct ioat_dma_chan *ioat_chan);
-
-static inline struct ioat_dma_chan *ioat_lookup_chan_by_index(
-						struct ioatdma_device *device,
-						int index)
-{
-	return device->idx[index];
-}
-
-/**
- * ioat_dma_do_interrupt - handler used for single vector interrupt mode
- * @irq: interrupt id
- * @data: interrupt data
- */
-static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
-{
-	struct ioatdma_device *instance = data;
-	struct ioat_dma_chan *ioat_chan;
-	unsigned long attnstatus;
-	int bit;
-	u8 intrctrl;
-
-	intrctrl = readb(instance->reg_base + IOAT_INTRCTRL_OFFSET);
-
-	if (!(intrctrl & IOAT_INTRCTRL_MASTER_INT_EN))
-		return IRQ_NONE;
-
-	if (!(intrctrl & IOAT_INTRCTRL_INT_STATUS)) {
-		writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
-		return IRQ_NONE;
-	}
-
-	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
-	for_each_bit(bit, &attnstatus, BITS_PER_LONG) {
-		ioat_chan = ioat_lookup_chan_by_index(instance, bit);
-		tasklet_schedule(&ioat_chan->cleanup_task);
-	}
-
-	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
-	return IRQ_HANDLED;
-}
-
-/**
- * ioat_dma_do_interrupt_msix - handler used for vector-per-channel interrupt mode
- * @irq: interrupt id
- * @data: interrupt data
- */
-static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data)
-{
-	struct ioat_dma_chan *ioat_chan = data;
-
-	tasklet_schedule(&ioat_chan->cleanup_task);
-
-	return IRQ_HANDLED;
-}
-
-static void ioat_dma_cleanup_tasklet(unsigned long data);
-
-/**
- * ioat_dma_enumerate_channels - find and initialize the device's channels
- * @device: the device to be enumerated
- */
-static int ioat_dma_enumerate_channels(struct ioatdma_device *device)
-{
-	u8 xfercap_scale;
-	u32 xfercap;
-	int i;
-	struct ioat_dma_chan *ioat_chan;
-
-	/*
-	 * IOAT ver.3 workarounds
-	 */
-	if (device->version == IOAT_VER_3_0) {
-		u32 chan_err_mask;
-		u16 dev_id;
-		u32 dmauncerrsts;
-
-		/*
-		 * Write CHANERRMSK_INT with 3E07h to mask out the errors
-		 * that can cause stability issues for IOAT ver.3
-		 */
-		chan_err_mask = 0x3E07;
-		pci_write_config_dword(device->pdev,
-			IOAT_PCI_CHANERRMASK_INT_OFFSET,
-			chan_err_mask);
-
-		/*
-		 * Clear DMAUNCERRSTS Cfg-Reg Parity Error status bit
-		 * (workaround for spurious config parity error after restart)
-		 */
-		pci_read_config_word(device->pdev,
-			IOAT_PCI_DEVICE_ID_OFFSET,
-			&dev_id);
-		if (dev_id == PCI_DEVICE_ID_INTEL_IOAT_TBG0) {
-			dmauncerrsts = 0x10;
-			pci_write_config_dword(device->pdev,
-				IOAT_PCI_DMAUNCERRSTS_OFFSET,
-				dmauncerrsts);
-		}
-	}
-
-	device->common.chancnt = readb(device->reg_base + IOAT_CHANCNT_OFFSET);
-	xfercap_scale = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
-	xfercap = (xfercap_scale == 0 ? -1 : (1UL << xfercap_scale));
-
-#ifdef  CONFIG_I7300_IDLE_IOAT_CHANNEL
-	if (i7300_idle_platform_probe(NULL, NULL, 1) == 0) {
-		device->common.chancnt--;
-	}
-#endif
-	for (i = 0; i < device->common.chancnt; i++) {
-		ioat_chan = kzalloc(sizeof(*ioat_chan), GFP_KERNEL);
-		if (!ioat_chan) {
-			device->common.chancnt = i;
-			break;
-		}
-
-		ioat_chan->device = device;
-		ioat_chan->reg_base = device->reg_base + (0x80 * (i + 1));
-		ioat_chan->xfercap = xfercap;
-		ioat_chan->desccount = 0;
-		INIT_DELAYED_WORK(&ioat_chan->work, ioat_dma_chan_reset_part2);
-		if (ioat_chan->device->version == IOAT_VER_2_0)
-			writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE |
-			       IOAT_DMA_DCA_ANY_CPU,
-			       ioat_chan->reg_base + IOAT_DCACTRL_OFFSET);
-		else if (ioat_chan->device->version == IOAT_VER_3_0)
-			writel(IOAT_DMA_DCA_ANY_CPU,
-			       ioat_chan->reg_base + IOAT_DCACTRL_OFFSET);
-		spin_lock_init(&ioat_chan->cleanup_lock);
-		spin_lock_init(&ioat_chan->desc_lock);
-		INIT_LIST_HEAD(&ioat_chan->free_desc);
-		INIT_LIST_HEAD(&ioat_chan->used_desc);
-		/* This should be made common somewhere in dmaengine.c */
-		ioat_chan->common.device = &device->common;
-		list_add_tail(&ioat_chan->common.device_node,
-			      &device->common.channels);
-		device->idx[i] = ioat_chan;
-		tasklet_init(&ioat_chan->cleanup_task,
-			     ioat_dma_cleanup_tasklet,
-			     (unsigned long) ioat_chan);
-		tasklet_disable(&ioat_chan->cleanup_task);
-	}
-	return device->common.chancnt;
-}
-
-/**
- * ioat_dma_memcpy_issue_pending - push potentially unrecognized appended
- *                                 descriptors to hw
- * @chan: DMA channel handle
- */
-static inline void __ioat1_dma_memcpy_issue_pending(
-						struct ioat_dma_chan *ioat_chan)
-{
-	ioat_chan->pending = 0;
-	writeb(IOAT_CHANCMD_APPEND, ioat_chan->reg_base + IOAT1_CHANCMD_OFFSET);
-}
-
-static void ioat1_dma_memcpy_issue_pending(struct dma_chan *chan)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
-
-	if (ioat_chan->pending > 0) {
-		spin_lock_bh(&ioat_chan->desc_lock);
-		__ioat1_dma_memcpy_issue_pending(ioat_chan);
-		spin_unlock_bh(&ioat_chan->desc_lock);
-	}
-}
-
-static inline void __ioat2_dma_memcpy_issue_pending(
-						struct ioat_dma_chan *ioat_chan)
-{
-	ioat_chan->pending = 0;
-	writew(ioat_chan->dmacount,
-	       ioat_chan->reg_base + IOAT_CHAN_DMACOUNT_OFFSET);
-}
-
-static void ioat2_dma_memcpy_issue_pending(struct dma_chan *chan)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
-
-	if (ioat_chan->pending > 0) {
-		spin_lock_bh(&ioat_chan->desc_lock);
-		__ioat2_dma_memcpy_issue_pending(ioat_chan);
-		spin_unlock_bh(&ioat_chan->desc_lock);
-	}
-}
-
-
-/**
- * ioat_dma_chan_reset_part2 - reinit the channel after a reset
- */
-static void ioat_dma_chan_reset_part2(struct work_struct *work)
-{
-	struct ioat_dma_chan *ioat_chan =
-		container_of(work, struct ioat_dma_chan, work.work);
-	struct ioat_desc_sw *desc;
-
-	spin_lock_bh(&ioat_chan->cleanup_lock);
-	spin_lock_bh(&ioat_chan->desc_lock);
-
-	ioat_chan->completion_virt->low = 0;
-	ioat_chan->completion_virt->high = 0;
-	ioat_chan->pending = 0;
-
-	/*
-	 * count the descriptors waiting, and be sure to do it
-	 * right for both the CB1 line and the CB2 ring
-	 */
-	ioat_chan->dmacount = 0;
-	if (ioat_chan->used_desc.prev) {
-		desc = to_ioat_desc(ioat_chan->used_desc.prev);
-		do {
-			ioat_chan->dmacount++;
-			desc = to_ioat_desc(desc->node.next);
-		} while (&desc->node != ioat_chan->used_desc.next);
-	}
-
-	/*
-	 * write the new starting descriptor address
-	 * this puts channel engine into ARMED state
-	 */
-	desc = to_ioat_desc(ioat_chan->used_desc.prev);
-	switch (ioat_chan->device->version) {
-	case IOAT_VER_1_2:
-		writel(((u64) desc->async_tx.phys) & 0x00000000FFFFFFFF,
-		       ioat_chan->reg_base + IOAT1_CHAINADDR_OFFSET_LOW);
-		writel(((u64) desc->async_tx.phys) >> 32,
-		       ioat_chan->reg_base + IOAT1_CHAINADDR_OFFSET_HIGH);
-
-		writeb(IOAT_CHANCMD_START, ioat_chan->reg_base
-			+ IOAT_CHANCMD_OFFSET(ioat_chan->device->version));
-		break;
-	case IOAT_VER_2_0:
-		writel(((u64) desc->async_tx.phys) & 0x00000000FFFFFFFF,
-		       ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
-		writel(((u64) desc->async_tx.phys) >> 32,
-		       ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_HIGH);
-
-		/* tell the engine to go with what's left to be done */
-		writew(ioat_chan->dmacount,
-		       ioat_chan->reg_base + IOAT_CHAN_DMACOUNT_OFFSET);
-
-		break;
-	}
-	dev_err(&ioat_chan->device->pdev->dev,
-		"chan%d reset - %d descs waiting, %d total desc\n",
-		chan_num(ioat_chan), ioat_chan->dmacount, ioat_chan->desccount);
-
-	spin_unlock_bh(&ioat_chan->desc_lock);
-	spin_unlock_bh(&ioat_chan->cleanup_lock);
-}
-
-/**
- * ioat_dma_reset_channel - restart a channel
- * @ioat_chan: IOAT DMA channel handle
- */
-static void ioat_dma_reset_channel(struct ioat_dma_chan *ioat_chan)
-{
-	u32 chansts, chanerr;
-
-	if (!ioat_chan->used_desc.prev)
-		return;
-
-	chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
-	chansts = (ioat_chan->completion_virt->low
-					& IOAT_CHANSTS_DMA_TRANSFER_STATUS);
-	if (chanerr) {
-		dev_err(&ioat_chan->device->pdev->dev,
-			"chan%d, CHANSTS = 0x%08x CHANERR = 0x%04x, clearing\n",
-			chan_num(ioat_chan), chansts, chanerr);
-		writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
-	}
-
-	/*
-	 * whack it upside the head with a reset
-	 * and wait for things to settle out.
-	 * force the pending count to a really big negative
-	 * to make sure no one forces an issue_pending
-	 * while we're waiting.
-	 */
-
-	spin_lock_bh(&ioat_chan->desc_lock);
-	ioat_chan->pending = INT_MIN;
-	writeb(IOAT_CHANCMD_RESET,
-	       ioat_chan->reg_base
-	       + IOAT_CHANCMD_OFFSET(ioat_chan->device->version));
-	spin_unlock_bh(&ioat_chan->desc_lock);
-
-	/* schedule the 2nd half instead of sleeping a long time */
-	schedule_delayed_work(&ioat_chan->work, RESET_DELAY);
-}
-
-/**
- * ioat_dma_chan_watchdog - watch for stuck channels
- */
-static void ioat_dma_chan_watchdog(struct work_struct *work)
-{
-	struct ioatdma_device *device =
-		container_of(work, struct ioatdma_device, work.work);
-	struct ioat_dma_chan *ioat_chan;
-	int i;
-
-	union {
-		u64 full;
-		struct {
-			u32 low;
-			u32 high;
-		};
-	} completion_hw;
-	unsigned long compl_desc_addr_hw;
-
-	for (i = 0; i < device->common.chancnt; i++) {
-		ioat_chan = ioat_lookup_chan_by_index(device, i);
-
-		if (ioat_chan->device->version == IOAT_VER_1_2
-			/* have we started processing anything yet */
-		    && ioat_chan->last_completion
-			/* have we completed any since last watchdog cycle? */
-		    && (ioat_chan->last_completion ==
-				ioat_chan->watchdog_completion)
-			/* has TCP stuck on one cookie since last watchdog? */
-		    && (ioat_chan->watchdog_tcp_cookie ==
-				ioat_chan->watchdog_last_tcp_cookie)
-		    && (ioat_chan->watchdog_tcp_cookie !=
-				ioat_chan->completed_cookie)
-			/* is there something in the chain to be processed? */
-			/* CB1 chain always has at least the last one processed */
-		    && (ioat_chan->used_desc.prev != ioat_chan->used_desc.next)
-		    && ioat_chan->pending == 0) {
-
-			/*
-			 * check CHANSTS register for completed
-			 * descriptor address.
-			 * if it is different than completion writeback,
-			 * it is not zero
-			 * and it has changed since the last watchdog
-			 *     we can assume that channel
-			 *     is still working correctly
-			 *     and the problem is in completion writeback.
-			 *     update completion writeback
-			 *     with actual CHANSTS value
-			 * else
-			 *     try resetting the channel
-			 */
-
-			completion_hw.low = readl(ioat_chan->reg_base +
-				IOAT_CHANSTS_OFFSET_LOW(ioat_chan->device->version));
-			completion_hw.high = readl(ioat_chan->reg_base +
-				IOAT_CHANSTS_OFFSET_HIGH(ioat_chan->device->version));
-#if (BITS_PER_LONG == 64)
-			compl_desc_addr_hw =
-				completion_hw.full
-				& IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;
-#else
-			compl_desc_addr_hw =
-				completion_hw.low & IOAT_LOW_COMPLETION_MASK;
-#endif
-
-			if ((compl_desc_addr_hw != 0)
-			   && (compl_desc_addr_hw != ioat_chan->watchdog_completion)
-			   && (compl_desc_addr_hw != ioat_chan->last_compl_desc_addr_hw)) {
-				ioat_chan->last_compl_desc_addr_hw = compl_desc_addr_hw;
-				ioat_chan->completion_virt->low = completion_hw.low;
-				ioat_chan->completion_virt->high = completion_hw.high;
-			} else {
-				ioat_dma_reset_channel(ioat_chan);
-				ioat_chan->watchdog_completion = 0;
-				ioat_chan->last_compl_desc_addr_hw = 0;
-			}
-
-		/*
-		 * for version 2.0 if there are descriptors yet to be processed
-		 * and the last completed hasn't changed since the last watchdog
-		 *      if they haven't hit the pending level
-		 *          issue the pending to push them through
-		 *      else
-		 *          try resetting the channel
-		 */
-		} else if (ioat_chan->device->version == IOAT_VER_2_0
-		    && ioat_chan->used_desc.prev
-		    && ioat_chan->last_completion
-		    && ioat_chan->last_completion == ioat_chan->watchdog_completion) {
-
-			if (ioat_chan->pending < ioat_pending_level)
-				ioat2_dma_memcpy_issue_pending(&ioat_chan->common);
-			else {
-				ioat_dma_reset_channel(ioat_chan);
-				ioat_chan->watchdog_completion = 0;
-			}
-		} else {
-			ioat_chan->last_compl_desc_addr_hw = 0;
-			ioat_chan->watchdog_completion
-					= ioat_chan->last_completion;
-		}
-
-		ioat_chan->watchdog_last_tcp_cookie =
-			ioat_chan->watchdog_tcp_cookie;
-	}
-
-	schedule_delayed_work(&device->work, WATCHDOG_DELAY);
-}
-
-static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(tx->chan);
-	struct ioat_desc_sw *first = tx_to_ioat_desc(tx);
-	struct ioat_desc_sw *prev, *new;
-	struct ioat_dma_descriptor *hw;
-	dma_cookie_t cookie;
-	LIST_HEAD(new_chain);
-	u32 copy;
-	size_t len;
-	dma_addr_t src, dst;
-	unsigned long orig_flags;
-	unsigned int desc_count = 0;
-
-	/* src and dest and len are stored in the initial descriptor */
-	len = first->len;
-	src = first->src;
-	dst = first->dst;
-	orig_flags = first->async_tx.flags;
-	new = first;
-
-	spin_lock_bh(&ioat_chan->desc_lock);
-	prev = to_ioat_desc(ioat_chan->used_desc.prev);
-	prefetch(prev->hw);
-	do {
-		copy = min_t(size_t, len, ioat_chan->xfercap);
-
-		async_tx_ack(&new->async_tx);
-
-		hw = new->hw;
-		hw->size = copy;
-		hw->ctl = 0;
-		hw->src_addr = src;
-		hw->dst_addr = dst;
-		hw->next = 0;
-
-		/* chain together the physical address list for the HW */
-		wmb();
-		prev->hw->next = (u64) new->async_tx.phys;
-
-		len -= copy;
-		dst += copy;
-		src += copy;
-
-		list_add_tail(&new->node, &new_chain);
-		desc_count++;
-		prev = new;
-	} while (len && (new = ioat1_dma_get_next_descriptor(ioat_chan)));
-
-	if (!new) {
-		dev_err(&ioat_chan->device->pdev->dev,
-			"tx submit failed\n");
-		spin_unlock_bh(&ioat_chan->desc_lock);
-		return -ENOMEM;
-	}
-
-	hw->ctl = IOAT_DMA_DESCRIPTOR_CTL_CP_STS;
-	if (first->async_tx.callback) {
-		hw->ctl |= IOAT_DMA_DESCRIPTOR_CTL_INT_GN;
-		if (first != new) {
-			/* move callback into to last desc */
-			new->async_tx.callback = first->async_tx.callback;
-			new->async_tx.callback_param
-					= first->async_tx.callback_param;
-			first->async_tx.callback = NULL;
-			first->async_tx.callback_param = NULL;
-		}
-	}
-
-	new->tx_cnt = desc_count;
-	new->async_tx.flags = orig_flags; /* client is in control of this ack */
-
-	/* store the original values for use in later cleanup */
-	if (new != first) {
-		new->src = first->src;
-		new->dst = first->dst;
-		new->len = first->len;
-	}
-
-	/* cookie incr and addition to used_list must be atomic */
-	cookie = ioat_chan->common.cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	ioat_chan->common.cookie = new->async_tx.cookie = cookie;
-
-	/* write address into NextDescriptor field of last desc in chain */
-	to_ioat_desc(ioat_chan->used_desc.prev)->hw->next =
-							first->async_tx.phys;
-	list_splice_tail(&new_chain, &ioat_chan->used_desc);
-
-	ioat_chan->dmacount += desc_count;
-	ioat_chan->pending += desc_count;
-	if (ioat_chan->pending >= ioat_pending_level)
-		__ioat1_dma_memcpy_issue_pending(ioat_chan);
-	spin_unlock_bh(&ioat_chan->desc_lock);
-
-	return cookie;
-}
-
-static dma_cookie_t ioat2_tx_submit(struct dma_async_tx_descriptor *tx)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(tx->chan);
-	struct ioat_desc_sw *first = tx_to_ioat_desc(tx);
-	struct ioat_desc_sw *new;
-	struct ioat_dma_descriptor *hw;
-	dma_cookie_t cookie;
-	u32 copy;
-	size_t len;
-	dma_addr_t src, dst;
-	unsigned long orig_flags;
-	unsigned int desc_count = 0;
-
-	/* src and dest and len are stored in the initial descriptor */
-	len = first->len;
-	src = first->src;
-	dst = first->dst;
-	orig_flags = first->async_tx.flags;
-	new = first;
-
-	/*
-	 * ioat_chan->desc_lock is still in force in version 2 path
-	 * it gets unlocked at end of this function
-	 */
-	do {
-		copy = min_t(size_t, len, ioat_chan->xfercap);
-
-		async_tx_ack(&new->async_tx);
-
-		hw = new->hw;
-		hw->size = copy;
-		hw->ctl = 0;
-		hw->src_addr = src;
-		hw->dst_addr = dst;
-
-		len -= copy;
-		dst += copy;
-		src += copy;
-		desc_count++;
-	} while (len && (new = ioat2_dma_get_next_descriptor(ioat_chan)));
-
-	if (!new) {
-		dev_err(&ioat_chan->device->pdev->dev,
-			"tx submit failed\n");
-		spin_unlock_bh(&ioat_chan->desc_lock);
-		return -ENOMEM;
-	}
-
-	hw->ctl |= IOAT_DMA_DESCRIPTOR_CTL_CP_STS;
-	if (first->async_tx.callback) {
-		hw->ctl |= IOAT_DMA_DESCRIPTOR_CTL_INT_GN;
-		if (first != new) {
-			/* move callback into to last desc */
-			new->async_tx.callback = first->async_tx.callback;
-			new->async_tx.callback_param
-					= first->async_tx.callback_param;
-			first->async_tx.callback = NULL;
-			first->async_tx.callback_param = NULL;
-		}
-	}
-
-	new->tx_cnt = desc_count;
-	new->async_tx.flags = orig_flags; /* client is in control of this ack */
-
-	/* store the original values for use in later cleanup */
-	if (new != first) {
-		new->src = first->src;
-		new->dst = first->dst;
-		new->len = first->len;
-	}
-
-	/* cookie incr and addition to used_list must be atomic */
-	cookie = ioat_chan->common.cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	ioat_chan->common.cookie = new->async_tx.cookie = cookie;
-
-	ioat_chan->dmacount += desc_count;
-	ioat_chan->pending += desc_count;
-	if (ioat_chan->pending >= ioat_pending_level)
-		__ioat2_dma_memcpy_issue_pending(ioat_chan);
-	spin_unlock_bh(&ioat_chan->desc_lock);
-
-	return cookie;
-}
-
-/**
- * ioat_dma_alloc_descriptor - allocate and return a sw and hw descriptor pair
- * @ioat_chan: the channel supplying the memory pool for the descriptors
- * @flags: allocation flags
- */
-static struct ioat_desc_sw *ioat_dma_alloc_descriptor(
-					struct ioat_dma_chan *ioat_chan,
-					gfp_t flags)
-{
-	struct ioat_dma_descriptor *desc;
-	struct ioat_desc_sw *desc_sw;
-	struct ioatdma_device *ioatdma_device;
-	dma_addr_t phys;
-
-	ioatdma_device = to_ioatdma_device(ioat_chan->common.device);
-	desc = pci_pool_alloc(ioatdma_device->dma_pool, flags, &phys);
-	if (unlikely(!desc))
-		return NULL;
-
-	desc_sw = kzalloc(sizeof(*desc_sw), flags);
-	if (unlikely(!desc_sw)) {
-		pci_pool_free(ioatdma_device->dma_pool, desc, phys);
-		return NULL;
-	}
-
-	memset(desc, 0, sizeof(*desc));
-	dma_async_tx_descriptor_init(&desc_sw->async_tx, &ioat_chan->common);
-	switch (ioat_chan->device->version) {
-	case IOAT_VER_1_2:
-		desc_sw->async_tx.tx_submit = ioat1_tx_submit;
-		break;
-	case IOAT_VER_2_0:
-	case IOAT_VER_3_0:
-		desc_sw->async_tx.tx_submit = ioat2_tx_submit;
-		break;
-	}
-
-	desc_sw->hw = desc;
-	desc_sw->async_tx.phys = phys;
-
-	return desc_sw;
-}
-
-static int ioat_initial_desc_count = 256;
-module_param(ioat_initial_desc_count, int, 0644);
-MODULE_PARM_DESC(ioat_initial_desc_count,
-		 "initial descriptors per channel (default: 256)");
-
-/**
- * ioat2_dma_massage_chan_desc - link the descriptors into a circle
- * @ioat_chan: the channel to be massaged
- */
-static void ioat2_dma_massage_chan_desc(struct ioat_dma_chan *ioat_chan)
-{
-	struct ioat_desc_sw *desc, *_desc;
-
-	/* setup used_desc */
-	ioat_chan->used_desc.next = ioat_chan->free_desc.next;
-	ioat_chan->used_desc.prev = NULL;
-
-	/* pull free_desc out of the circle so that every node is a hw
-	 * descriptor, but leave it pointing to the list
-	 */
-	ioat_chan->free_desc.prev->next = ioat_chan->free_desc.next;
-	ioat_chan->free_desc.next->prev = ioat_chan->free_desc.prev;
-
-	/* circle link the hw descriptors */
-	desc = to_ioat_desc(ioat_chan->free_desc.next);
-	desc->hw->next = to_ioat_desc(desc->node.next)->async_tx.phys;
-	list_for_each_entry_safe(desc, _desc, ioat_chan->free_desc.next, node) {
-		desc->hw->next = to_ioat_desc(desc->node.next)->async_tx.phys;
-	}
-}
-
-/**
- * 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 ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
-	struct ioat_desc_sw *desc;
-	u16 chanctrl;
-	u32 chanerr;
-	int i;
-	LIST_HEAD(tmp_list);
-
-	/* have we already been set up? */
-	if (!list_empty(&ioat_chan->free_desc))
-		return ioat_chan->desccount;
-
-	/* Setup register to interrupt and write completion status on error */
-	chanctrl = IOAT_CHANCTRL_ERR_INT_EN |
-		IOAT_CHANCTRL_ANY_ERR_ABORT_EN |
-		IOAT_CHANCTRL_ERR_COMPLETION_EN;
-	writew(chanctrl, ioat_chan->reg_base + IOAT_CHANCTRL_OFFSET);
-
-	chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
-	if (chanerr) {
-		dev_err(&ioat_chan->device->pdev->dev,
-			"CHANERR = %x, clearing\n", chanerr);
-		writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
-	}
-
-	/* Allocate descriptors */
-	for (i = 0; i < ioat_initial_desc_count; i++) {
-		desc = ioat_dma_alloc_descriptor(ioat_chan, GFP_KERNEL);
-		if (!desc) {
-			dev_err(&ioat_chan->device->pdev->dev,
-				"Only %d initial descriptors\n", i);
-			break;
-		}
-		list_add_tail(&desc->node, &tmp_list);
-	}
-	spin_lock_bh(&ioat_chan->desc_lock);
-	ioat_chan->desccount = i;
-	list_splice(&tmp_list, &ioat_chan->free_desc);
-	if (ioat_chan->device->version != IOAT_VER_1_2)
-		ioat2_dma_massage_chan_desc(ioat_chan);
-	spin_unlock_bh(&ioat_chan->desc_lock);
-
-	/* allocate a completion writeback area */
-	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
-	ioat_chan->completion_virt =
-		pci_pool_alloc(ioat_chan->device->completion_pool,
-			       GFP_KERNEL,
-			       &ioat_chan->completion_addr);
-	memset(ioat_chan->completion_virt, 0,
-	       sizeof(*ioat_chan->completion_virt));
-	writel(((u64) ioat_chan->completion_addr) & 0x00000000FFFFFFFF,
-	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
-	writel(((u64) ioat_chan->completion_addr) >> 32,
-	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
-
-	tasklet_enable(&ioat_chan->cleanup_task);
-	ioat_dma_start_null_desc(ioat_chan);  /* give chain to dma device */
-	return ioat_chan->desccount;
-}
-
-/**
- * ioat_dma_free_chan_resources - release all the descriptors
- * @chan: the channel to be cleaned
- */
-static void ioat_dma_free_chan_resources(struct dma_chan *chan)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
-	struct ioatdma_device *ioatdma_device = to_ioatdma_device(chan->device);
-	struct ioat_desc_sw *desc, *_desc;
-	int in_use_descs = 0;
-
-	/* Before freeing channel resources first check
-	 * if they have been previously allocated for this channel.
-	 */
-	if (ioat_chan->desccount == 0)
-		return;
-
-	tasklet_disable(&ioat_chan->cleanup_task);
-	ioat_dma_memcpy_cleanup(ioat_chan);
-
-	/* Delay 100ms after reset to allow internal DMA logic to quiesce
-	 * before removing DMA descriptor resources.
-	 */
-	writeb(IOAT_CHANCMD_RESET,
-	       ioat_chan->reg_base
-			+ IOAT_CHANCMD_OFFSET(ioat_chan->device->version));
-	mdelay(100);
-
-	spin_lock_bh(&ioat_chan->desc_lock);
-	switch (ioat_chan->device->version) {
-	case IOAT_VER_1_2:
-		list_for_each_entry_safe(desc, _desc,
-					 &ioat_chan->used_desc, node) {
-			in_use_descs++;
-			list_del(&desc->node);
-			pci_pool_free(ioatdma_device->dma_pool, desc->hw,
-				      desc->async_tx.phys);
-			kfree(desc);
-		}
-		list_for_each_entry_safe(desc, _desc,
-					 &ioat_chan->free_desc, node) {
-			list_del(&desc->node);
-			pci_pool_free(ioatdma_device->dma_pool, desc->hw,
-				      desc->async_tx.phys);
-			kfree(desc);
-		}
-		break;
-	case IOAT_VER_2_0:
-	case IOAT_VER_3_0:
-		list_for_each_entry_safe(desc, _desc,
-					 ioat_chan->free_desc.next, node) {
-			list_del(&desc->node);
-			pci_pool_free(ioatdma_device->dma_pool, desc->hw,
-				      desc->async_tx.phys);
-			kfree(desc);
-		}
-		desc = to_ioat_desc(ioat_chan->free_desc.next);
-		pci_pool_free(ioatdma_device->dma_pool, desc->hw,
-			      desc->async_tx.phys);
-		kfree(desc);
-		INIT_LIST_HEAD(&ioat_chan->free_desc);
-		INIT_LIST_HEAD(&ioat_chan->used_desc);
-		break;
-	}
-	spin_unlock_bh(&ioat_chan->desc_lock);
-
-	pci_pool_free(ioatdma_device->completion_pool,
-		      ioat_chan->completion_virt,
-		      ioat_chan->completion_addr);
-
-	/* one is ok since we left it on there on purpose */
-	if (in_use_descs > 1)
-		dev_err(&ioat_chan->device->pdev->dev,
-			"Freeing %d in use descriptors!\n",
-			in_use_descs - 1);
-
-	ioat_chan->last_completion = ioat_chan->completion_addr = 0;
-	ioat_chan->pending = 0;
-	ioat_chan->dmacount = 0;
-	ioat_chan->desccount = 0;
-	ioat_chan->watchdog_completion = 0;
-	ioat_chan->last_compl_desc_addr_hw = 0;
-	ioat_chan->watchdog_tcp_cookie =
-		ioat_chan->watchdog_last_tcp_cookie = 0;
-}
-
-/**
- * ioat_dma_get_next_descriptor - return the next available descriptor
- * @ioat_chan: IOAT DMA channel handle
- *
- * Gets the next descriptor from the chain, and must be called with the
- * channel's desc_lock held.  Allocates more descriptors if the channel
- * has run out.
- */
-static struct ioat_desc_sw *
-ioat1_dma_get_next_descriptor(struct ioat_dma_chan *ioat_chan)
-{
-	struct ioat_desc_sw *new;
-
-	if (!list_empty(&ioat_chan->free_desc)) {
-		new = to_ioat_desc(ioat_chan->free_desc.next);
-		list_del(&new->node);
-	} else {
-		/* try to get another desc */
-		new = ioat_dma_alloc_descriptor(ioat_chan, GFP_ATOMIC);
-		if (!new) {
-			dev_err(&ioat_chan->device->pdev->dev,
-				"alloc failed\n");
-			return NULL;
-		}
-	}
-
-	prefetch(new->hw);
-	return new;
-}
-
-static struct ioat_desc_sw *
-ioat2_dma_get_next_descriptor(struct ioat_dma_chan *ioat_chan)
-{
-	struct ioat_desc_sw *new;
-
-	/*
-	 * used.prev points to where to start processing
-	 * used.next points to next free descriptor
-	 * if used.prev == NULL, there are none waiting to be processed
-	 * if used.next == used.prev.prev, there is only one free descriptor,
-	 *      and we need to use it to as a noop descriptor before
-	 *      linking in a new set of descriptors, since the device
-	 *      has probably already read the pointer to it
-	 */
-	if (ioat_chan->used_desc.prev &&
-	    ioat_chan->used_desc.next == ioat_chan->used_desc.prev->prev) {
-
-		struct ioat_desc_sw *desc;
-		struct ioat_desc_sw *noop_desc;
-		int i;
-
-		/* set up the noop descriptor */
-		noop_desc = to_ioat_desc(ioat_chan->used_desc.next);
-		/* set size to non-zero value (channel returns error when size is 0) */
-		noop_desc->hw->size = NULL_DESC_BUFFER_SIZE;
-		noop_desc->hw->ctl = IOAT_DMA_DESCRIPTOR_NUL;
-		noop_desc->hw->src_addr = 0;
-		noop_desc->hw->dst_addr = 0;
-
-		ioat_chan->used_desc.next = ioat_chan->used_desc.next->next;
-		ioat_chan->pending++;
-		ioat_chan->dmacount++;
-
-		/* try to get a few more descriptors */
-		for (i = 16; i; i--) {
-			desc = ioat_dma_alloc_descriptor(ioat_chan, GFP_ATOMIC);
-			if (!desc) {
-				dev_err(&ioat_chan->device->pdev->dev,
-					"alloc failed\n");
-				break;
-			}
-			list_add_tail(&desc->node, ioat_chan->used_desc.next);
-
-			desc->hw->next
-				= to_ioat_desc(desc->node.next)->async_tx.phys;
-			to_ioat_desc(desc->node.prev)->hw->next
-				= desc->async_tx.phys;
-			ioat_chan->desccount++;
-		}
-
-		ioat_chan->used_desc.next = noop_desc->node.next;
-	}
-	new = to_ioat_desc(ioat_chan->used_desc.next);
-	prefetch(new);
-	ioat_chan->used_desc.next = new->node.next;
-
-	if (ioat_chan->used_desc.prev == NULL)
-		ioat_chan->used_desc.prev = &new->node;
-
-	prefetch(new->hw);
-	return new;
-}
-
-static struct ioat_desc_sw *ioat_dma_get_next_descriptor(
-						struct ioat_dma_chan *ioat_chan)
-{
-	if (!ioat_chan)
-		return NULL;
-
-	switch (ioat_chan->device->version) {
-	case IOAT_VER_1_2:
-		return ioat1_dma_get_next_descriptor(ioat_chan);
-	case IOAT_VER_2_0:
-	case IOAT_VER_3_0:
-		return ioat2_dma_get_next_descriptor(ioat_chan);
-	}
-	return NULL;
-}
-
-static struct dma_async_tx_descriptor *ioat1_dma_prep_memcpy(
-						struct dma_chan *chan,
-						dma_addr_t dma_dest,
-						dma_addr_t dma_src,
-						size_t len,
-						unsigned long flags)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
-	struct ioat_desc_sw *new;
-
-	spin_lock_bh(&ioat_chan->desc_lock);
-	new = ioat_dma_get_next_descriptor(ioat_chan);
-	spin_unlock_bh(&ioat_chan->desc_lock);
-
-	if (new) {
-		new->len = len;
-		new->dst = dma_dest;
-		new->src = dma_src;
-		new->async_tx.flags = flags;
-		return &new->async_tx;
-	} else {
-		dev_err(&ioat_chan->device->pdev->dev,
-			"chan%d - get_next_desc failed: %d descs waiting, %d total desc\n",
-			chan_num(ioat_chan), ioat_chan->dmacount, ioat_chan->desccount);
-		return NULL;
-	}
-}
-
-static struct dma_async_tx_descriptor *ioat2_dma_prep_memcpy(
-						struct dma_chan *chan,
-						dma_addr_t dma_dest,
-						dma_addr_t dma_src,
-						size_t len,
-						unsigned long flags)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
-	struct ioat_desc_sw *new;
-
-	spin_lock_bh(&ioat_chan->desc_lock);
-	new = ioat2_dma_get_next_descriptor(ioat_chan);
-
-	/*
-	 * leave ioat_chan->desc_lock set in ioat 2 path
-	 * it will get unlocked at end of tx_submit
-	 */
-
-	if (new) {
-		new->len = len;
-		new->dst = dma_dest;
-		new->src = dma_src;
-		new->async_tx.flags = flags;
-		return &new->async_tx;
-	} else {
-		spin_unlock_bh(&ioat_chan->desc_lock);
-		dev_err(&ioat_chan->device->pdev->dev,
-			"chan%d - get_next_desc failed: %d descs waiting, %d total desc\n",
-			chan_num(ioat_chan), ioat_chan->dmacount, ioat_chan->desccount);
-		return NULL;
-	}
-}
-
-static void ioat_dma_cleanup_tasklet(unsigned long data)
-{
-	struct ioat_dma_chan *chan = (void *)data;
-	ioat_dma_memcpy_cleanup(chan);
-	writew(IOAT_CHANCTRL_INT_DISABLE,
-	       chan->reg_base + IOAT_CHANCTRL_OFFSET);
-}
-
-static void
-ioat_dma_unmap(struct ioat_dma_chan *ioat_chan, struct ioat_desc_sw *desc)
-{
-	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (desc->async_tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			pci_unmap_single(ioat_chan->device->pdev,
-					 pci_unmap_addr(desc, dst),
-					 pci_unmap_len(desc, len),
-					 PCI_DMA_FROMDEVICE);
-		else
-			pci_unmap_page(ioat_chan->device->pdev,
-				       pci_unmap_addr(desc, dst),
-				       pci_unmap_len(desc, len),
-				       PCI_DMA_FROMDEVICE);
-	}
-
-	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (desc->async_tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			pci_unmap_single(ioat_chan->device->pdev,
-					 pci_unmap_addr(desc, src),
-					 pci_unmap_len(desc, len),
-					 PCI_DMA_TODEVICE);
-		else
-			pci_unmap_page(ioat_chan->device->pdev,
-				       pci_unmap_addr(desc, src),
-				       pci_unmap_len(desc, len),
-				       PCI_DMA_TODEVICE);
-	}
-}
-
-/**
- * ioat_dma_memcpy_cleanup - cleanup up finished descriptors
- * @chan: ioat channel to be cleaned up
- */
-static void ioat_dma_memcpy_cleanup(struct ioat_dma_chan *ioat_chan)
-{
-	unsigned long phys_complete;
-	struct ioat_desc_sw *desc, *_desc;
-	dma_cookie_t cookie = 0;
-	unsigned long desc_phys;
-	struct ioat_desc_sw *latest_desc;
-
-	prefetch(ioat_chan->completion_virt);
-
-	if (!spin_trylock_bh(&ioat_chan->cleanup_lock))
-		return;
-
-	/* The completion writeback can happen at any time,
-	   so reads by the driver need to be atomic operations
-	   The descriptor physical addresses are limited to 32-bits
-	   when the CPU can only do a 32-bit mov */
-
-#if (BITS_PER_LONG == 64)
-	phys_complete =
-		ioat_chan->completion_virt->full
-		& IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;
-#else
-	phys_complete =
-		ioat_chan->completion_virt->low & IOAT_LOW_COMPLETION_MASK;
-#endif
-
-	if ((ioat_chan->completion_virt->full
-		& IOAT_CHANSTS_DMA_TRANSFER_STATUS) ==
-				IOAT_CHANSTS_DMA_TRANSFER_STATUS_HALTED) {
-		dev_err(&ioat_chan->device->pdev->dev,
-			"Channel halted, chanerr = %x\n",
-			readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET));
-
-		/* TODO do something to salvage the situation */
-	}
-
-	if (phys_complete == ioat_chan->last_completion) {
-		spin_unlock_bh(&ioat_chan->cleanup_lock);
-		/*
-		 * perhaps we're stuck so hard that the watchdog can't go off?
-		 * try to catch it after 2 seconds
-		 */
-		if (ioat_chan->device->version != IOAT_VER_3_0) {
-			if (time_after(jiffies,
-				       ioat_chan->last_completion_time + HZ*WATCHDOG_DELAY)) {
-				ioat_dma_chan_watchdog(&(ioat_chan->device->work.work));
-				ioat_chan->last_completion_time = jiffies;
-			}
-		}
-		return;
-	}
-	ioat_chan->last_completion_time = jiffies;
-
-	cookie = 0;
-	if (!spin_trylock_bh(&ioat_chan->desc_lock)) {
-		spin_unlock_bh(&ioat_chan->cleanup_lock);
-		return;
-	}
-
-	switch (ioat_chan->device->version) {
-	case IOAT_VER_1_2:
-		list_for_each_entry_safe(desc, _desc,
-					 &ioat_chan->used_desc, node) {
-
-			/*
-			 * Incoming DMA requests may use multiple descriptors,
-			 * due to exceeding xfercap, perhaps. If so, only the
-			 * last one will have a cookie, and require unmapping.
-			 */
-			if (desc->async_tx.cookie) {
-				cookie = desc->async_tx.cookie;
-				ioat_dma_unmap(ioat_chan, desc);
-				if (desc->async_tx.callback) {
-					desc->async_tx.callback(desc->async_tx.callback_param);
-					desc->async_tx.callback = NULL;
-				}
-			}
-
-			if (desc->async_tx.phys != phys_complete) {
-				/*
-				 * a completed entry, but not the last, so clean
-				 * up if the client is done with the descriptor
-				 */
-				if (async_tx_test_ack(&desc->async_tx)) {
-					list_move_tail(&desc->node,
-						       &ioat_chan->free_desc);
-				} else
-					desc->async_tx.cookie = 0;
-			} else {
-				/*
-				 * last used desc. Do not remove, so we can
-				 * append from it, but don't look at it next
-				 * time, either
-				 */
-				desc->async_tx.cookie = 0;
-
-				/* TODO check status bits? */
-				break;
-			}
-		}
-		break;
-	case IOAT_VER_2_0:
-	case IOAT_VER_3_0:
-		/* has some other thread has already cleaned up? */
-		if (ioat_chan->used_desc.prev == NULL)
-			break;
-
-		/* work backwards to find latest finished desc */
-		desc = to_ioat_desc(ioat_chan->used_desc.next);
-		latest_desc = NULL;
-		do {
-			desc = to_ioat_desc(desc->node.prev);
-			desc_phys = (unsigned long)desc->async_tx.phys
-				       & IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;
-			if (desc_phys == phys_complete) {
-				latest_desc = desc;
-				break;
-			}
-		} while (&desc->node != ioat_chan->used_desc.prev);
-
-		if (latest_desc != NULL) {
-
-			/* work forwards to clear finished descriptors */
-			for (desc = to_ioat_desc(ioat_chan->used_desc.prev);
-			     &desc->node != latest_desc->node.next &&
-			     &desc->node != ioat_chan->used_desc.next;
-			     desc = to_ioat_desc(desc->node.next)) {
-				if (desc->async_tx.cookie) {
-					cookie = desc->async_tx.cookie;
-					desc->async_tx.cookie = 0;
-					ioat_dma_unmap(ioat_chan, desc);
-					if (desc->async_tx.callback) {
-						desc->async_tx.callback(desc->async_tx.callback_param);
-						desc->async_tx.callback = NULL;
-					}
-				}
-			}
-
-			/* move used.prev up beyond those that are finished */
-			if (&desc->node == ioat_chan->used_desc.next)
-				ioat_chan->used_desc.prev = NULL;
-			else
-				ioat_chan->used_desc.prev = &desc->node;
-		}
-		break;
-	}
-
-	spin_unlock_bh(&ioat_chan->desc_lock);
-
-	ioat_chan->last_completion = phys_complete;
-	if (cookie != 0)
-		ioat_chan->completed_cookie = cookie;
-
-	spin_unlock_bh(&ioat_chan->cleanup_lock);
-}
-
-/**
- * ioat_dma_is_complete - poll the status of a IOAT DMA transaction
- * @chan: IOAT DMA channel handle
- * @cookie: DMA transaction identifier
- * @done: if not %NULL, updated with last completed transaction
- * @used: if not %NULL, updated with last used transaction
- */
-static enum dma_status ioat_dma_is_complete(struct dma_chan *chan,
-					    dma_cookie_t cookie,
-					    dma_cookie_t *done,
-					    dma_cookie_t *used)
-{
-	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
-	dma_cookie_t last_used;
-	dma_cookie_t last_complete;
-	enum dma_status ret;
-
-	last_used = chan->cookie;
-	last_complete = ioat_chan->completed_cookie;
-	ioat_chan->watchdog_tcp_cookie = cookie;
-
-	if (done)
-		*done = last_complete;
-	if (used)
-		*used = last_used;
-
-	ret = dma_async_is_complete(cookie, last_complete, last_used);
-	if (ret == DMA_SUCCESS)
-		return ret;
-
-	ioat_dma_memcpy_cleanup(ioat_chan);
-
-	last_used = chan->cookie;
-	last_complete = ioat_chan->completed_cookie;
-
-	if (done)
-		*done = last_complete;
-	if (used)
-		*used = last_used;
-
-	return dma_async_is_complete(cookie, last_complete, last_used);
-}
-
-static void ioat_dma_start_null_desc(struct ioat_dma_chan *ioat_chan)
-{
-	struct ioat_desc_sw *desc;
-
-	spin_lock_bh(&ioat_chan->desc_lock);
-
-	desc = ioat_dma_get_next_descriptor(ioat_chan);
-
-	if (!desc) {
-		dev_err(&ioat_chan->device->pdev->dev,
-			"Unable to start null desc - get next desc failed\n");
-		spin_unlock_bh(&ioat_chan->desc_lock);
-		return;
-	}
-
-	desc->hw->ctl = IOAT_DMA_DESCRIPTOR_NUL
-				| IOAT_DMA_DESCRIPTOR_CTL_INT_GN
-				| IOAT_DMA_DESCRIPTOR_CTL_CP_STS;
-	/* set size to non-zero value (channel returns error when size is 0) */
-	desc->hw->size = NULL_DESC_BUFFER_SIZE;
-	desc->hw->src_addr = 0;
-	desc->hw->dst_addr = 0;
-	async_tx_ack(&desc->async_tx);
-	switch (ioat_chan->device->version) {
-	case IOAT_VER_1_2:
-		desc->hw->next = 0;
-		list_add_tail(&desc->node, &ioat_chan->used_desc);
-
-		writel(((u64) desc->async_tx.phys) & 0x00000000FFFFFFFF,
-		       ioat_chan->reg_base + IOAT1_CHAINADDR_OFFSET_LOW);
-		writel(((u64) desc->async_tx.phys) >> 32,
-		       ioat_chan->reg_base + IOAT1_CHAINADDR_OFFSET_HIGH);
-
-		writeb(IOAT_CHANCMD_START, ioat_chan->reg_base
-			+ IOAT_CHANCMD_OFFSET(ioat_chan->device->version));
-		break;
-	case IOAT_VER_2_0:
-	case IOAT_VER_3_0:
-		writel(((u64) desc->async_tx.phys) & 0x00000000FFFFFFFF,
-		       ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
-		writel(((u64) desc->async_tx.phys) >> 32,
-		       ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_HIGH);
-
-		ioat_chan->dmacount++;
-		__ioat2_dma_memcpy_issue_pending(ioat_chan);
-		break;
-	}
-	spin_unlock_bh(&ioat_chan->desc_lock);
-}
-
-/*
- * Perform a IOAT transaction to verify the HW works.
- */
-#define IOAT_TEST_SIZE 2000
-
-static void ioat_dma_test_callback(void *dma_async_param)
-{
-	struct completion *cmp = dma_async_param;
-
-	complete(cmp);
-}
-
-/**
- * ioat_dma_self_test - Perform a IOAT transaction to verify the HW works.
- * @device: device to be tested
- */
-static int ioat_dma_self_test(struct ioatdma_device *device)
-{
-	int i;
-	u8 *src;
-	u8 *dest;
-	struct dma_chan *dma_chan;
-	struct dma_async_tx_descriptor *tx;
-	dma_addr_t dma_dest, dma_src;
-	dma_cookie_t cookie;
-	int err = 0;
-	struct completion cmp;
-	unsigned long tmo;
-	unsigned long flags;
-
-	src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
-	if (!src)
-		return -ENOMEM;
-	dest = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
-	if (!dest) {
-		kfree(src);
-		return -ENOMEM;
-	}
-
-	/* Fill in src buffer */
-	for (i = 0; i < IOAT_TEST_SIZE; i++)
-		src[i] = (u8)i;
-
-	/* Start copy, using first DMA channel */
-	dma_chan = container_of(device->common.channels.next,
-				struct dma_chan,
-				device_node);
-	if (device->common.device_alloc_chan_resources(dma_chan) < 1) {
-		dev_err(&device->pdev->dev,
-			"selftest cannot allocate chan resource\n");
-		err = -ENODEV;
-		goto out;
-	}
-
-	dma_src = dma_map_single(dma_chan->device->dev, src, IOAT_TEST_SIZE,
-				 DMA_TO_DEVICE);
-	dma_dest = dma_map_single(dma_chan->device->dev, dest, IOAT_TEST_SIZE,
-				  DMA_FROM_DEVICE);
-	flags = DMA_COMPL_SRC_UNMAP_SINGLE | DMA_COMPL_DEST_UNMAP_SINGLE;
-	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
-						   IOAT_TEST_SIZE, flags);
-	if (!tx) {
-		dev_err(&device->pdev->dev,
-			"Self-test prep failed, disabling\n");
-		err = -ENODEV;
-		goto free_resources;
-	}
-
-	async_tx_ack(tx);
-	init_completion(&cmp);
-	tx->callback = ioat_dma_test_callback;
-	tx->callback_param = &cmp;
-	cookie = tx->tx_submit(tx);
-	if (cookie < 0) {
-		dev_err(&device->pdev->dev,
-			"Self-test setup failed, disabling\n");
-		err = -ENODEV;
-		goto free_resources;
-	}
-	device->common.device_issue_pending(dma_chan);
-
-	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
-
-	if (tmo == 0 ||
-	    device->common.device_is_tx_complete(dma_chan, cookie, NULL, NULL)
-					!= DMA_SUCCESS) {
-		dev_err(&device->pdev->dev,
-			"Self-test copy timed out, disabling\n");
-		err = -ENODEV;
-		goto free_resources;
-	}
-	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
-		dev_err(&device->pdev->dev,
-			"Self-test copy failed compare, disabling\n");
-		err = -ENODEV;
-		goto free_resources;
-	}
-
-free_resources:
-	device->common.device_free_chan_resources(dma_chan);
-out:
-	kfree(src);
-	kfree(dest);
-	return err;
-}
-
-static char ioat_interrupt_style[32] = "msix";
-module_param_string(ioat_interrupt_style, ioat_interrupt_style,
-		    sizeof(ioat_interrupt_style), 0644);
-MODULE_PARM_DESC(ioat_interrupt_style,
-		 "set ioat interrupt style: msix (default), "
-		 "msix-single-vector, msi, intx)");
-
-/**
- * ioat_dma_setup_interrupts - setup interrupt handler
- * @device: ioat device
- */
-static int ioat_dma_setup_interrupts(struct ioatdma_device *device)
-{
-	struct ioat_dma_chan *ioat_chan;
-	int err, i, j, msixcnt;
-	u8 intrctrl = 0;
-
-	if (!strcmp(ioat_interrupt_style, "msix"))
-		goto msix;
-	if (!strcmp(ioat_interrupt_style, "msix-single-vector"))
-		goto msix_single_vector;
-	if (!strcmp(ioat_interrupt_style, "msi"))
-		goto msi;
-	if (!strcmp(ioat_interrupt_style, "intx"))
-		goto intx;
-	dev_err(&device->pdev->dev, "invalid ioat_interrupt_style %s\n",
-		ioat_interrupt_style);
-	goto err_no_irq;
-
-msix:
-	/* The number of MSI-X vectors should equal the number of channels */
-	msixcnt = device->common.chancnt;
-	for (i = 0; i < msixcnt; i++)
-		device->msix_entries[i].entry = i;
-
-	err = pci_enable_msix(device->pdev, device->msix_entries, msixcnt);
-	if (err < 0)
-		goto msi;
-	if (err > 0)
-		goto msix_single_vector;
-
-	for (i = 0; i < msixcnt; i++) {
-		ioat_chan = ioat_lookup_chan_by_index(device, i);
-		err = request_irq(device->msix_entries[i].vector,
-				  ioat_dma_do_interrupt_msix,
-				  0, "ioat-msix", ioat_chan);
-		if (err) {
-			for (j = 0; j < i; j++) {
-				ioat_chan =
-					ioat_lookup_chan_by_index(device, j);
-				free_irq(device->msix_entries[j].vector,
-					 ioat_chan);
-			}
-			goto msix_single_vector;
-		}
-	}
-	intrctrl |= IOAT_INTRCTRL_MSIX_VECTOR_CONTROL;
-	device->irq_mode = msix_multi_vector;
-	goto done;
-
-msix_single_vector:
-	device->msix_entries[0].entry = 0;
-	err = pci_enable_msix(device->pdev, device->msix_entries, 1);
-	if (err)
-		goto msi;
-
-	err = request_irq(device->msix_entries[0].vector, ioat_dma_do_interrupt,
-			  0, "ioat-msix", device);
-	if (err) {
-		pci_disable_msix(device->pdev);
-		goto msi;
-	}
-	device->irq_mode = msix_single_vector;
-	goto done;
-
-msi:
-	err = pci_enable_msi(device->pdev);
-	if (err)
-		goto intx;
-
-	err = request_irq(device->pdev->irq, ioat_dma_do_interrupt,
-			  0, "ioat-msi", device);
-	if (err) {
-		pci_disable_msi(device->pdev);
-		goto intx;
-	}
-	/*
-	 * CB 1.2 devices need a bit set in configuration space to enable MSI
-	 */
-	if (device->version == IOAT_VER_1_2) {
-		u32 dmactrl;
-		pci_read_config_dword(device->pdev,
-				      IOAT_PCI_DMACTRL_OFFSET, &dmactrl);
-		dmactrl |= IOAT_PCI_DMACTRL_MSI_EN;
-		pci_write_config_dword(device->pdev,
-				       IOAT_PCI_DMACTRL_OFFSET, dmactrl);
-	}
-	device->irq_mode = msi;
-	goto done;
-
-intx:
-	err = request_irq(device->pdev->irq, ioat_dma_do_interrupt,
-			  IRQF_SHARED, "ioat-intx", device);
-	if (err)
-		goto err_no_irq;
-	device->irq_mode = intx;
-
-done:
-	intrctrl |= IOAT_INTRCTRL_MASTER_INT_EN;
-	writeb(intrctrl, device->reg_base + IOAT_INTRCTRL_OFFSET);
-	return 0;
-
-err_no_irq:
-	/* Disable all interrupt generation */
-	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
-	dev_err(&device->pdev->dev, "no usable interrupts\n");
-	device->irq_mode = none;
-	return -1;
-}
-
-/**
- * ioat_dma_remove_interrupts - remove whatever interrupts were set
- * @device: ioat device
- */
-static void ioat_dma_remove_interrupts(struct ioatdma_device *device)
-{
-	struct ioat_dma_chan *ioat_chan;
-	int i;
-
-	/* Disable all interrupt generation */
-	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
-
-	switch (device->irq_mode) {
-	case msix_multi_vector:
-		for (i = 0; i < device->common.chancnt; i++) {
-			ioat_chan = ioat_lookup_chan_by_index(device, i);
-			free_irq(device->msix_entries[i].vector, ioat_chan);
-		}
-		pci_disable_msix(device->pdev);
-		break;
-	case msix_single_vector:
-		free_irq(device->msix_entries[0].vector, device);
-		pci_disable_msix(device->pdev);
-		break;
-	case msi:
-		free_irq(device->pdev->irq, device);
-		pci_disable_msi(device->pdev);
-		break;
-	case intx:
-		free_irq(device->pdev->irq, device);
-		break;
-	case none:
-		dev_warn(&device->pdev->dev,
-			 "call to %s without interrupts setup\n", __func__);
-	}
-	device->irq_mode = none;
-}
-
-struct ioatdma_device *ioat_dma_probe(struct pci_dev *pdev,
-				      void __iomem *iobase)
-{
-	int err;
-	struct ioatdma_device *device;
-
-	device = kzalloc(sizeof(*device), GFP_KERNEL);
-	if (!device) {
-		err = -ENOMEM;
-		goto err_kzalloc;
-	}
-	device->pdev = pdev;
-	device->reg_base = iobase;
-	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
-
-	/* DMA coherent memory pool for DMA descriptor allocations */
-	device->dma_pool = pci_pool_create("dma_desc_pool", pdev,
-					   sizeof(struct ioat_dma_descriptor),
-					   64, 0);
-	if (!device->dma_pool) {
-		err = -ENOMEM;
-		goto err_dma_pool;
-	}
-
-	device->completion_pool = pci_pool_create("completion_pool", pdev,
-						  sizeof(u64), SMP_CACHE_BYTES,
-						  SMP_CACHE_BYTES);
-	if (!device->completion_pool) {
-		err = -ENOMEM;
-		goto err_completion_pool;
-	}
-
-	INIT_LIST_HEAD(&device->common.channels);
-	ioat_dma_enumerate_channels(device);
-
-	device->common.device_alloc_chan_resources =
-						ioat_dma_alloc_chan_resources;
-	device->common.device_free_chan_resources =
-						ioat_dma_free_chan_resources;
-	device->common.dev = &pdev->dev;
-
-	dma_cap_set(DMA_MEMCPY, device->common.cap_mask);
-	device->common.device_is_tx_complete = ioat_dma_is_complete;
-	switch (device->version) {
-	case IOAT_VER_1_2:
-		device->common.device_prep_dma_memcpy = ioat1_dma_prep_memcpy;
-		device->common.device_issue_pending =
-						ioat1_dma_memcpy_issue_pending;
-		break;
-	case IOAT_VER_2_0:
-	case IOAT_VER_3_0:
-		device->common.device_prep_dma_memcpy = ioat2_dma_prep_memcpy;
-		device->common.device_issue_pending =
-						ioat2_dma_memcpy_issue_pending;
-		break;
-	}
-
-	dev_err(&device->pdev->dev,
-		"Intel(R) I/OAT DMA Engine found,"
-		" %d channels, device version 0x%02x, driver version %s\n",
-		device->common.chancnt, device->version, IOAT_DMA_VERSION);
-
-	if (!device->common.chancnt) {
-		dev_err(&device->pdev->dev,
-			"Intel(R) I/OAT DMA Engine problem found: "
-			"zero channels detected\n");
-		goto err_setup_interrupts;
-	}
-
-	err = ioat_dma_setup_interrupts(device);
-	if (err)
-		goto err_setup_interrupts;
-
-	err = ioat_dma_self_test(device);
-	if (err)
-		goto err_self_test;
-
-	ioat_set_tcp_copy_break(device);
-
-	dma_async_device_register(&device->common);
-
-	if (device->version != IOAT_VER_3_0) {
-		INIT_DELAYED_WORK(&device->work, ioat_dma_chan_watchdog);
-		schedule_delayed_work(&device->work,
-				      WATCHDOG_DELAY);
-	}
-
-	return device;
-
-err_self_test:
-	ioat_dma_remove_interrupts(device);
-err_setup_interrupts:
-	pci_pool_destroy(device->completion_pool);
-err_completion_pool:
-	pci_pool_destroy(device->dma_pool);
-err_dma_pool:
-	kfree(device);
-err_kzalloc:
-	dev_err(&pdev->dev,
-		"Intel(R) I/OAT DMA Engine initialization failed\n");
-	return NULL;
-}
-
-void ioat_dma_remove(struct ioatdma_device *device)
-{
-	struct dma_chan *chan, *_chan;
-	struct ioat_dma_chan *ioat_chan;
-
-	if (device->version != IOAT_VER_3_0)
-		cancel_delayed_work(&device->work);
-
-	ioat_dma_remove_interrupts(device);
-
-	dma_async_device_unregister(&device->common);
-
-	pci_pool_destroy(device->dma_pool);
-	pci_pool_destroy(device->completion_pool);
-
-	iounmap(device->reg_base);
-	pci_release_regions(device->pdev);
-	pci_disable_device(device->pdev);
-
-	list_for_each_entry_safe(chan, _chan,
-				 &device->common.channels, device_node) {
-		ioat_chan = to_ioat_chan(chan);
-		list_del(&chan->device_node);
-		kfree(ioat_chan);
-	}
-	kfree(device);
-}
-
diff --git a/drivers/dma/ioatdma.h b/drivers/dma/ioatdma.h
deleted file mode 100644
index a52ff4bd460..00000000000
--- a/drivers/dma/ioatdma.h
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
- */
-#ifndef IOATDMA_H
-#define IOATDMA_H
-
-#include <linux/dmaengine.h>
-#include "ioatdma_hw.h"
-#include <linux/init.h>
-#include <linux/dmapool.h>
-#include <linux/cache.h>
-#include <linux/pci_ids.h>
-#include <net/tcp.h>
-
-#define IOAT_DMA_VERSION  "3.64"
-
-enum ioat_interrupt {
-	none = 0,
-	msix_multi_vector = 1,
-	msix_single_vector = 2,
-	msi = 3,
-	intx = 4,
-};
-
-#define IOAT_LOW_COMPLETION_MASK	0xffffffc0
-#define IOAT_DMA_DCA_ANY_CPU		~0
-#define IOAT_WATCHDOG_PERIOD		(2 * HZ)
-
-
-/**
- * struct ioatdma_device - internal representation of a IOAT device
- * @pdev: PCI-Express device
- * @reg_base: MMIO register space base address
- * @dma_pool: for allocating DMA descriptors
- * @common: embedded struct dma_device
- * @version: version of ioatdma device
- * @irq_mode: which style irq to use
- * @msix_entries: irq handlers
- * @idx: per channel data
- */
-
-struct ioatdma_device {
-	struct pci_dev *pdev;
-	void __iomem *reg_base;
-	struct pci_pool *dma_pool;
-	struct pci_pool *completion_pool;
-	struct dma_device common;
-	u8 version;
-	enum ioat_interrupt irq_mode;
-	struct delayed_work work;
-	struct msix_entry msix_entries[4];
-	struct ioat_dma_chan *idx[4];
-};
-
-/**
- * struct ioat_dma_chan - internal representation of a DMA channel
- */
-struct ioat_dma_chan {
-
-	void __iomem *reg_base;
-
-	dma_cookie_t completed_cookie;
-	unsigned long last_completion;
-	unsigned long last_completion_time;
-
-	size_t xfercap;	/* XFERCAP register value expanded out */
-
-	spinlock_t cleanup_lock;
-	spinlock_t desc_lock;
-	struct list_head free_desc;
-	struct list_head used_desc;
-	unsigned long watchdog_completion;
-	int watchdog_tcp_cookie;
-	u32 watchdog_last_tcp_cookie;
-	struct delayed_work work;
-
-	int pending;
-	int dmacount;
-	int desccount;
-
-	struct ioatdma_device *device;
-	struct dma_chan common;
-
-	dma_addr_t completion_addr;
-	union {
-		u64 full; /* HW completion writeback */
-		struct {
-			u32 low;
-			u32 high;
-		};
-	} *completion_virt;
-	unsigned long last_compl_desc_addr_hw;
-	struct tasklet_struct cleanup_task;
-};
-
-/* wrapper around hardware descriptor format + additional software fields */
-
-/**
- * struct ioat_desc_sw - wrapper around hardware descriptor
- * @hw: hardware DMA descriptor
- * @node: this descriptor will either be on the free list,
- *     or attached to a transaction list (async_tx.tx_list)
- * @tx_cnt: number of descriptors required to complete the transaction
- * @async_tx: the generic software descriptor for all engines
- */
-struct ioat_desc_sw {
-	struct ioat_dma_descriptor *hw;
-	struct list_head node;
-	int tx_cnt;
-	size_t len;
-	dma_addr_t src;
-	dma_addr_t dst;
-	struct dma_async_tx_descriptor async_tx;
-};
-
-static inline void ioat_set_tcp_copy_break(struct ioatdma_device *dev)
-{
-	#ifdef CONFIG_NET_DMA
-	switch (dev->version) {
-	case IOAT_VER_1_2:
-		sysctl_tcp_dma_copybreak = 4096;
-		break;
-	case IOAT_VER_2_0:
-		sysctl_tcp_dma_copybreak = 2048;
-		break;
-	case IOAT_VER_3_0:
-		sysctl_tcp_dma_copybreak = 262144;
-		break;
-	}
-	#endif
-}
-
-#if defined(CONFIG_INTEL_IOATDMA) || defined(CONFIG_INTEL_IOATDMA_MODULE)
-struct ioatdma_device *ioat_dma_probe(struct pci_dev *pdev,
-				      void __iomem *iobase);
-void ioat_dma_remove(struct ioatdma_device *device);
-struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase);
-struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase);
-struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase);
-#else
-#define ioat_dma_probe(pdev, iobase)    NULL
-#define ioat_dma_remove(device)         do { } while (0)
-#define ioat_dca_init(pdev, iobase)	NULL
-#define ioat2_dca_init(pdev, iobase)	NULL
-#define ioat3_dca_init(pdev, iobase)	NULL
-#endif
-
-#endif /* IOATDMA_H */
diff --git a/drivers/dma/ioatdma_hw.h b/drivers/dma/ioatdma_hw.h
deleted file mode 100644
index afa57eef86c..00000000000
--- a/drivers/dma/ioatdma_hw.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Copyright(c) 2004 - 2009 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
- */
-#ifndef _IOAT_HW_H_
-#define _IOAT_HW_H_
-
-/* PCI Configuration Space Values */
-#define IOAT_PCI_VID            0x8086
-
-/* CB device ID's */
-#define IOAT_PCI_DID_5000       0x1A38
-#define IOAT_PCI_DID_CNB        0x360B
-#define IOAT_PCI_DID_SCNB       0x65FF
-#define IOAT_PCI_DID_SNB        0x402F
-
-#define IOAT_PCI_RID            0x00
-#define IOAT_PCI_SVID           0x8086
-#define IOAT_PCI_SID            0x8086
-#define IOAT_VER_1_2            0x12    /* Version 1.2 */
-#define IOAT_VER_2_0            0x20    /* Version 2.0 */
-#define IOAT_VER_3_0            0x30    /* Version 3.0 */
-
-struct ioat_dma_descriptor {
-	uint32_t	size;
-	uint32_t	ctl;
-	uint64_t	src_addr;
-	uint64_t	dst_addr;
-	uint64_t	next;
-	uint64_t	rsv1;
-	uint64_t	rsv2;
-	uint64_t	user1;
-	uint64_t	user2;
-};
-
-#define IOAT_DMA_DESCRIPTOR_CTL_INT_GN	0x00000001
-#define IOAT_DMA_DESCRIPTOR_CTL_SRC_SN	0x00000002
-#define IOAT_DMA_DESCRIPTOR_CTL_DST_SN	0x00000004
-#define IOAT_DMA_DESCRIPTOR_CTL_CP_STS	0x00000008
-#define IOAT_DMA_DESCRIPTOR_CTL_FRAME	0x00000010
-#define IOAT_DMA_DESCRIPTOR_NUL		0x00000020
-#define IOAT_DMA_DESCRIPTOR_CTL_SP_BRK	0x00000040
-#define IOAT_DMA_DESCRIPTOR_CTL_DP_BRK	0x00000080
-#define IOAT_DMA_DESCRIPTOR_CTL_BNDL	0x00000100
-#define IOAT_DMA_DESCRIPTOR_CTL_DCA	0x00000200
-#define IOAT_DMA_DESCRIPTOR_CTL_BUFHINT	0x00000400
-
-#define IOAT_DMA_DESCRIPTOR_CTL_OPCODE_CONTEXT	0xFF000000
-#define IOAT_DMA_DESCRIPTOR_CTL_OPCODE_DMA	0x00000000
-
-#define IOAT_DMA_DESCRIPTOR_CTL_CONTEXT_DCA	0x00000001
-#define IOAT_DMA_DESCRIPTOR_CTL_OPCODE_MASK	0xFF000000
-
-#endif
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 2f052265122..645ca8d54ec 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -31,6 +31,7 @@
 #include <linux/platform_device.h>
 #include <linux/memory.h>
 #include <linux/ioport.h>
+#include <linux/raid/pq.h>
 
 #include <mach/adma.h>
 
@@ -57,65 +58,110 @@ static void iop_adma_free_slots(struct iop_adma_desc_slot *slot)
 	}
 }
 
+static void
+iop_desc_unmap(struct iop_adma_chan *iop_chan, struct iop_adma_desc_slot *desc)
+{
+	struct dma_async_tx_descriptor *tx = &desc->async_tx;
+	struct iop_adma_desc_slot *unmap = desc->group_head;
+	struct device *dev = &iop_chan->device->pdev->dev;
+	u32 len = unmap->unmap_len;
+	enum dma_ctrl_flags flags = tx->flags;
+	u32 src_cnt;
+	dma_addr_t addr;
+	dma_addr_t dest;
+
+	src_cnt = unmap->unmap_src_cnt;
+	dest = iop_desc_get_dest_addr(unmap, iop_chan);
+	if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+		enum dma_data_direction dir;
+
+		if (src_cnt > 1) /* is xor? */
+			dir = DMA_BIDIRECTIONAL;
+		else
+			dir = DMA_FROM_DEVICE;
+
+		dma_unmap_page(dev, dest, len, dir);
+	}
+
+	if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+		while (src_cnt--) {
+			addr = iop_desc_get_src_addr(unmap, iop_chan, src_cnt);
+			if (addr == dest)
+				continue;
+			dma_unmap_page(dev, addr, len, DMA_TO_DEVICE);
+		}
+	}
+	desc->group_head = NULL;
+}
+
+static void
+iop_desc_unmap_pq(struct iop_adma_chan *iop_chan, struct iop_adma_desc_slot *desc)
+{
+	struct dma_async_tx_descriptor *tx = &desc->async_tx;
+	struct iop_adma_desc_slot *unmap = desc->group_head;
+	struct device *dev = &iop_chan->device->pdev->dev;
+	u32 len = unmap->unmap_len;
+	enum dma_ctrl_flags flags = tx->flags;
+	u32 src_cnt = unmap->unmap_src_cnt;
+	dma_addr_t pdest = iop_desc_get_dest_addr(unmap, iop_chan);
+	dma_addr_t qdest = iop_desc_get_qdest_addr(unmap, iop_chan);
+	int i;
+
+	if (tx->flags & DMA_PREP_CONTINUE)
+		src_cnt -= 3;
+
+	if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP) && !desc->pq_check_result) {
+		dma_unmap_page(dev, pdest, len, DMA_BIDIRECTIONAL);
+		dma_unmap_page(dev, qdest, len, DMA_BIDIRECTIONAL);
+	}
+
+	if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+		dma_addr_t addr;
+
+		for (i = 0; i < src_cnt; i++) {
+			addr = iop_desc_get_src_addr(unmap, iop_chan, i);
+			dma_unmap_page(dev, addr, len, DMA_TO_DEVICE);
+		}
+		if (desc->pq_check_result) {
+			dma_unmap_page(dev, pdest, len, DMA_TO_DEVICE);
+			dma_unmap_page(dev, qdest, len, DMA_TO_DEVICE);
+		}
+	}
+
+	desc->group_head = NULL;
+}
+
+
 static dma_cookie_t
 iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
 	struct iop_adma_chan *iop_chan, dma_cookie_t cookie)
 {
-	BUG_ON(desc->async_tx.cookie < 0);
-	if (desc->async_tx.cookie > 0) {
-		cookie = desc->async_tx.cookie;
-		desc->async_tx.cookie = 0;
+	struct dma_async_tx_descriptor *tx = &desc->async_tx;
+
+	BUG_ON(tx->cookie < 0);
+	if (tx->cookie > 0) {
+		cookie = tx->cookie;
+		tx->cookie = 0;
 
 		/* call the callback (must not sleep or submit new
 		 * operations to this channel)
 		 */
-		if (desc->async_tx.callback)
-			desc->async_tx.callback(
-				desc->async_tx.callback_param);
+		if (tx->callback)
+			tx->callback(tx->callback_param);
 
 		/* unmap dma addresses
 		 * (unmap_single vs unmap_page?)
 		 */
 		if (desc->group_head && desc->unmap_len) {
-			struct iop_adma_desc_slot *unmap = desc->group_head;
-			struct device *dev =
-				&iop_chan->device->pdev->dev;
-			u32 len = unmap->unmap_len;
-			enum dma_ctrl_flags flags = desc->async_tx.flags;
-			u32 src_cnt;
-			dma_addr_t addr;
-			dma_addr_t dest;
-
-			src_cnt = unmap->unmap_src_cnt;
-			dest = iop_desc_get_dest_addr(unmap, iop_chan);
-			if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-				enum dma_data_direction dir;
-
-				if (src_cnt > 1) /* is xor? */
-					dir = DMA_BIDIRECTIONAL;
-				else
-					dir = DMA_FROM_DEVICE;
-
-				dma_unmap_page(dev, dest, len, dir);
-			}
-
-			if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-				while (src_cnt--) {
-					addr = iop_desc_get_src_addr(unmap,
-								     iop_chan,
-								     src_cnt);
-					if (addr == dest)
-						continue;
-					dma_unmap_page(dev, addr, len,
-						       DMA_TO_DEVICE);
-				}
-			}
-			desc->group_head = NULL;
+			if (iop_desc_is_pq(desc))
+				iop_desc_unmap_pq(iop_chan, desc);
+			else
+				iop_desc_unmap(iop_chan, desc);
 		}
 	}
 
 	/* run dependent operations */
-	dma_run_dependencies(&desc->async_tx);
+	dma_run_dependencies(tx);
 
 	return cookie;
 }
@@ -287,7 +333,12 @@ static void iop_adma_tasklet(unsigned long data)
 {
 	struct iop_adma_chan *iop_chan = (struct iop_adma_chan *) data;
 
-	spin_lock(&iop_chan->lock);
+	/* lockdep will flag depedency submissions as potentially
+	 * recursive locking, this is not the case as a dependency
+	 * submission will never recurse a channels submit routine.
+	 * There are checks in async_tx.c to prevent this.
+	 */
+	spin_lock_nested(&iop_chan->lock, SINGLE_DEPTH_NESTING);
 	__iop_adma_slot_cleanup(iop_chan);
 	spin_unlock(&iop_chan->lock);
 }
@@ -370,7 +421,7 @@ retry:
 			}
 			alloc_tail->group_head = alloc_start;
 			alloc_tail->async_tx.cookie = -EBUSY;
-			list_splice(&chain, &alloc_tail->async_tx.tx_list);
+			list_splice(&chain, &alloc_tail->tx_list);
 			iop_chan->last_used = last_used;
 			iop_desc_clear_next_desc(alloc_start);
 			iop_desc_clear_next_desc(alloc_tail);
@@ -429,7 +480,7 @@ iop_adma_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	old_chain_tail = list_entry(iop_chan->chain.prev,
 		struct iop_adma_desc_slot, chain_node);
-	list_splice_init(&sw_desc->async_tx.tx_list,
+	list_splice_init(&sw_desc->tx_list,
 			 &old_chain_tail->chain_node);
 
 	/* fix up the hardware chain */
@@ -496,6 +547,7 @@ static int iop_adma_alloc_chan_resources(struct dma_chan *chan)
 
 		dma_async_tx_descriptor_init(&slot->async_tx, chan);
 		slot->async_tx.tx_submit = iop_adma_tx_submit;
+		INIT_LIST_HEAD(&slot->tx_list);
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
 		hw_desc = (char *) iop_chan->device->dma_desc_pool;
@@ -660,9 +712,9 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 }
 
 static struct dma_async_tx_descriptor *
-iop_adma_prep_dma_zero_sum(struct dma_chan *chan, dma_addr_t *dma_src,
-			   unsigned int src_cnt, size_t len, u32 *result,
-			   unsigned long flags)
+iop_adma_prep_dma_xor_val(struct dma_chan *chan, dma_addr_t *dma_src,
+			  unsigned int src_cnt, size_t len, u32 *result,
+			  unsigned long flags)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
 	struct iop_adma_desc_slot *sw_desc, *grp_start;
@@ -696,6 +748,118 @@ iop_adma_prep_dma_zero_sum(struct dma_chan *chan, dma_addr_t *dma_src,
 	return sw_desc ? &sw_desc->async_tx : NULL;
 }
 
+static struct dma_async_tx_descriptor *
+iop_adma_prep_dma_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
+		     unsigned int src_cnt, const unsigned char *scf, size_t len,
+		     unsigned long flags)
+{
+	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
+	struct iop_adma_desc_slot *sw_desc, *g;
+	int slot_cnt, slots_per_op;
+	int continue_srcs;
+
+	if (unlikely(!len))
+		return NULL;
+	BUG_ON(len > IOP_ADMA_XOR_MAX_BYTE_COUNT);
+
+	dev_dbg(iop_chan->device->common.dev,
+		"%s src_cnt: %d len: %u flags: %lx\n",
+		__func__, src_cnt, len, flags);
+
+	if (dmaf_p_disabled_continue(flags))
+		continue_srcs = 1+src_cnt;
+	else if (dmaf_continue(flags))
+		continue_srcs = 3+src_cnt;
+	else
+		continue_srcs = 0+src_cnt;
+
+	spin_lock_bh(&iop_chan->lock);
+	slot_cnt = iop_chan_pq_slot_count(len, continue_srcs, &slots_per_op);
+	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
+	if (sw_desc) {
+		int i;
+
+		g = sw_desc->group_head;
+		iop_desc_set_byte_count(g, iop_chan, len);
+
+		/* even if P is disabled its destination address (bits
+		 * [3:0]) must match Q.  It is ok if P points to an
+		 * invalid address, it won't be written.
+		 */
+		if (flags & DMA_PREP_PQ_DISABLE_P)
+			dst[0] = dst[1] & 0x7;
+
+		iop_desc_set_pq_addr(g, dst);
+		sw_desc->unmap_src_cnt = src_cnt;
+		sw_desc->unmap_len = len;
+		sw_desc->async_tx.flags = flags;
+		for (i = 0; i < src_cnt; i++)
+			iop_desc_set_pq_src_addr(g, i, src[i], scf[i]);
+
+		/* if we are continuing a previous operation factor in
+		 * the old p and q values, see the comment for dma_maxpq
+		 * in include/linux/dmaengine.h
+		 */
+		if (dmaf_p_disabled_continue(flags))
+			iop_desc_set_pq_src_addr(g, i++, dst[1], 1);
+		else if (dmaf_continue(flags)) {
+			iop_desc_set_pq_src_addr(g, i++, dst[0], 0);
+			iop_desc_set_pq_src_addr(g, i++, dst[1], 1);
+			iop_desc_set_pq_src_addr(g, i++, dst[1], 0);
+		}
+		iop_desc_init_pq(g, i, flags);
+	}
+	spin_unlock_bh(&iop_chan->lock);
+
+	return sw_desc ? &sw_desc->async_tx : NULL;
+}
+
+static struct dma_async_tx_descriptor *
+iop_adma_prep_dma_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
+			 unsigned int src_cnt, const unsigned char *scf,
+			 size_t len, enum sum_check_flags *pqres,
+			 unsigned long flags)
+{
+	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
+	struct iop_adma_desc_slot *sw_desc, *g;
+	int slot_cnt, slots_per_op;
+
+	if (unlikely(!len))
+		return NULL;
+	BUG_ON(len > IOP_ADMA_XOR_MAX_BYTE_COUNT);
+
+	dev_dbg(iop_chan->device->common.dev, "%s src_cnt: %d len: %u\n",
+		__func__, src_cnt, len);
+
+	spin_lock_bh(&iop_chan->lock);
+	slot_cnt = iop_chan_pq_zero_sum_slot_count(len, src_cnt + 2, &slots_per_op);
+	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
+	if (sw_desc) {
+		/* for validate operations p and q are tagged onto the
+		 * end of the source list
+		 */
+		int pq_idx = src_cnt;
+
+		g = sw_desc->group_head;
+		iop_desc_init_pq_zero_sum(g, src_cnt+2, flags);
+		iop_desc_set_pq_zero_sum_byte_count(g, len);
+		g->pq_check_result = pqres;
+		pr_debug("\t%s: g->pq_check_result: %p\n",
+			__func__, g->pq_check_result);
+		sw_desc->unmap_src_cnt = src_cnt+2;
+		sw_desc->unmap_len = len;
+		sw_desc->async_tx.flags = flags;
+		while (src_cnt--)
+			iop_desc_set_pq_zero_sum_src_addr(g, src_cnt,
+							  src[src_cnt],
+							  scf[src_cnt]);
+		iop_desc_set_pq_zero_sum_addr(g, pq_idx, src);
+	}
+	spin_unlock_bh(&iop_chan->lock);
+
+	return sw_desc ? &sw_desc->async_tx : NULL;
+}
+
 static void iop_adma_free_chan_resources(struct dma_chan *chan)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
@@ -906,7 +1070,7 @@ out:
 
 #define IOP_ADMA_NUM_SRC_TEST 4 /* must be <= 15 */
 static int __devinit
-iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
+iop_adma_xor_val_self_test(struct iop_adma_device *device)
 {
 	int i, src_idx;
 	struct page *dest;
@@ -1002,7 +1166,7 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		PAGE_SIZE, DMA_TO_DEVICE);
 
 	/* skip zero sum if the capability is not present */
-	if (!dma_has_cap(DMA_ZERO_SUM, dma_chan->device->cap_mask))
+	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
 		goto free_resources;
 
 	/* zero sum the sources with the destintation page */
@@ -1016,10 +1180,10 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		dma_srcs[i] = dma_map_page(dma_chan->device->dev,
 					   zero_sum_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-	tx = iop_adma_prep_dma_zero_sum(dma_chan, dma_srcs,
-					IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
-					&zero_sum_result,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	tx = iop_adma_prep_dma_xor_val(dma_chan, dma_srcs,
+				       IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
+				       &zero_sum_result,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
 	cookie = iop_adma_tx_submit(tx);
 	iop_adma_issue_pending(dma_chan);
@@ -1072,10 +1236,10 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		dma_srcs[i] = dma_map_page(dma_chan->device->dev,
 					   zero_sum_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-	tx = iop_adma_prep_dma_zero_sum(dma_chan, dma_srcs,
-					IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
-					&zero_sum_result,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	tx = iop_adma_prep_dma_xor_val(dma_chan, dma_srcs,
+				       IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
+				       &zero_sum_result,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
 	cookie = iop_adma_tx_submit(tx);
 	iop_adma_issue_pending(dma_chan);
@@ -1105,6 +1269,170 @@ out:
 	return err;
 }
 
+#ifdef CONFIG_MD_RAID6_PQ
+static int __devinit
+iop_adma_pq_zero_sum_self_test(struct iop_adma_device *device)
+{
+	/* combined sources, software pq results, and extra hw pq results */
+	struct page *pq[IOP_ADMA_NUM_SRC_TEST+2+2];
+	/* ptr to the extra hw pq buffers defined above */
+	struct page **pq_hw = &pq[IOP_ADMA_NUM_SRC_TEST+2];
+	/* address conversion buffers (dma_map / page_address) */
+	void *pq_sw[IOP_ADMA_NUM_SRC_TEST+2];
+	dma_addr_t pq_src[IOP_ADMA_NUM_SRC_TEST];
+	dma_addr_t pq_dest[2];
+
+	int i;
+	struct dma_async_tx_descriptor *tx;
+	struct dma_chan *dma_chan;
+	dma_cookie_t cookie;
+	u32 zero_sum_result;
+	int err = 0;
+	struct device *dev;
+
+	dev_dbg(device->common.dev, "%s\n", __func__);
+
+	for (i = 0; i < ARRAY_SIZE(pq); i++) {
+		pq[i] = alloc_page(GFP_KERNEL);
+		if (!pq[i]) {
+			while (i--)
+				__free_page(pq[i]);
+			return -ENOMEM;
+		}
+	}
+
+	/* Fill in src buffers */
+	for (i = 0; i < IOP_ADMA_NUM_SRC_TEST; i++) {
+		pq_sw[i] = page_address(pq[i]);
+		memset(pq_sw[i], 0x11111111 * (1<<i), PAGE_SIZE);
+	}
+	pq_sw[i] = page_address(pq[i]);
+	pq_sw[i+1] = page_address(pq[i+1]);
+
+	dma_chan = container_of(device->common.channels.next,
+				struct dma_chan,
+				device_node);
+	if (iop_adma_alloc_chan_resources(dma_chan) < 1) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	dev = dma_chan->device->dev;
+
+	/* initialize the dests */
+	memset(page_address(pq_hw[0]), 0 , PAGE_SIZE);
+	memset(page_address(pq_hw[1]), 0 , PAGE_SIZE);
+
+	/* test pq */
+	pq_dest[0] = dma_map_page(dev, pq_hw[0], 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	pq_dest[1] = dma_map_page(dev, pq_hw[1], 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	for (i = 0; i < IOP_ADMA_NUM_SRC_TEST; i++)
+		pq_src[i] = dma_map_page(dev, pq[i], 0, PAGE_SIZE,
+					 DMA_TO_DEVICE);
+
+	tx = iop_adma_prep_dma_pq(dma_chan, pq_dest, pq_src,
+				  IOP_ADMA_NUM_SRC_TEST, (u8 *)raid6_gfexp,
+				  PAGE_SIZE,
+				  DMA_PREP_INTERRUPT |
+				  DMA_CTRL_ACK);
+
+	cookie = iop_adma_tx_submit(tx);
+	iop_adma_issue_pending(dma_chan);
+	msleep(8);
+
+	if (iop_adma_is_complete(dma_chan, cookie, NULL, NULL) !=
+		DMA_SUCCESS) {
+		dev_err(dev, "Self-test pq timed out, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	raid6_call.gen_syndrome(IOP_ADMA_NUM_SRC_TEST+2, PAGE_SIZE, pq_sw);
+
+	if (memcmp(pq_sw[IOP_ADMA_NUM_SRC_TEST],
+		   page_address(pq_hw[0]), PAGE_SIZE) != 0) {
+		dev_err(dev, "Self-test p failed compare, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+	if (memcmp(pq_sw[IOP_ADMA_NUM_SRC_TEST+1],
+		   page_address(pq_hw[1]), PAGE_SIZE) != 0) {
+		dev_err(dev, "Self-test q failed compare, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	/* test correct zero sum using the software generated pq values */
+	for (i = 0; i < IOP_ADMA_NUM_SRC_TEST + 2; i++)
+		pq_src[i] = dma_map_page(dev, pq[i], 0, PAGE_SIZE,
+					 DMA_TO_DEVICE);
+
+	zero_sum_result = ~0;
+	tx = iop_adma_prep_dma_pq_val(dma_chan, &pq_src[IOP_ADMA_NUM_SRC_TEST],
+				      pq_src, IOP_ADMA_NUM_SRC_TEST,
+				      raid6_gfexp, PAGE_SIZE, &zero_sum_result,
+				      DMA_PREP_INTERRUPT|DMA_CTRL_ACK);
+
+	cookie = iop_adma_tx_submit(tx);
+	iop_adma_issue_pending(dma_chan);
+	msleep(8);
+
+	if (iop_adma_is_complete(dma_chan, cookie, NULL, NULL) !=
+		DMA_SUCCESS) {
+		dev_err(dev, "Self-test pq-zero-sum timed out, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	if (zero_sum_result != 0) {
+		dev_err(dev, "Self-test pq-zero-sum failed to validate: %x\n",
+			zero_sum_result);
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	/* test incorrect zero sum */
+	i = IOP_ADMA_NUM_SRC_TEST;
+	memset(pq_sw[i] + 100, 0, 100);
+	memset(pq_sw[i+1] + 200, 0, 200);
+	for (i = 0; i < IOP_ADMA_NUM_SRC_TEST + 2; i++)
+		pq_src[i] = dma_map_page(dev, pq[i], 0, PAGE_SIZE,
+					 DMA_TO_DEVICE);
+
+	zero_sum_result = 0;
+	tx = iop_adma_prep_dma_pq_val(dma_chan, &pq_src[IOP_ADMA_NUM_SRC_TEST],
+				      pq_src, IOP_ADMA_NUM_SRC_TEST,
+				      raid6_gfexp, PAGE_SIZE, &zero_sum_result,
+				      DMA_PREP_INTERRUPT|DMA_CTRL_ACK);
+
+	cookie = iop_adma_tx_submit(tx);
+	iop_adma_issue_pending(dma_chan);
+	msleep(8);
+
+	if (iop_adma_is_complete(dma_chan, cookie, NULL, NULL) !=
+		DMA_SUCCESS) {
+		dev_err(dev, "Self-test !pq-zero-sum timed out, disabling\n");
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+	if (zero_sum_result != (SUM_CHECK_P_RESULT | SUM_CHECK_Q_RESULT)) {
+		dev_err(dev, "Self-test !pq-zero-sum failed to validate: %x\n",
+			zero_sum_result);
+		err = -ENODEV;
+		goto free_resources;
+	}
+
+free_resources:
+	iop_adma_free_chan_resources(dma_chan);
+out:
+	i = ARRAY_SIZE(pq);
+	while (i--)
+		__free_page(pq[i]);
+	return err;
+}
+#endif
+
 static int __devexit iop_adma_remove(struct platform_device *dev)
 {
 	struct iop_adma_device *device = platform_get_drvdata(dev);
@@ -1192,9 +1520,16 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 		dma_dev->max_xor = iop_adma_get_max_xor();
 		dma_dev->device_prep_dma_xor = iop_adma_prep_dma_xor;
 	}
-	if (dma_has_cap(DMA_ZERO_SUM, dma_dev->cap_mask))
-		dma_dev->device_prep_dma_zero_sum =
-			iop_adma_prep_dma_zero_sum;
+	if (dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask))
+		dma_dev->device_prep_dma_xor_val =
+			iop_adma_prep_dma_xor_val;
+	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
+		dma_set_maxpq(dma_dev, iop_adma_get_max_pq(), 0);
+		dma_dev->device_prep_dma_pq = iop_adma_prep_dma_pq;
+	}
+	if (dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask))
+		dma_dev->device_prep_dma_pq_val =
+			iop_adma_prep_dma_pq_val;
 	if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask))
 		dma_dev->device_prep_dma_interrupt =
 			iop_adma_prep_dma_interrupt;
@@ -1248,23 +1583,35 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 	}
 
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask) ||
-		dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)) {
-		ret = iop_adma_xor_zero_sum_self_test(adev);
+	    dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)) {
+		ret = iop_adma_xor_val_self_test(adev);
 		dev_dbg(&pdev->dev, "xor self test returned %d\n", ret);
 		if (ret)
 			goto err_free_iop_chan;
 	}
 
+	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask) &&
+	    dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask)) {
+		#ifdef CONFIG_MD_RAID6_PQ
+		ret = iop_adma_pq_zero_sum_self_test(adev);
+		dev_dbg(&pdev->dev, "pq self test returned %d\n", ret);
+		#else
+		/* can not test raid6, so do not publish capability */
+		dma_cap_clear(DMA_PQ, dma_dev->cap_mask);
+		dma_cap_clear(DMA_PQ_VAL, dma_dev->cap_mask);
+		ret = 0;
+		#endif
+		if (ret)
+			goto err_free_iop_chan;
+	}
+
 	dev_printk(KERN_INFO, &pdev->dev, "Intel(R) IOP: "
-	  "( %s%s%s%s%s%s%s%s%s%s)\n",
-	  dma_has_cap(DMA_PQ_XOR, dma_dev->cap_mask) ? "pq_xor " : "",
-	  dma_has_cap(DMA_PQ_UPDATE, dma_dev->cap_mask) ? "pq_update " : "",
-	  dma_has_cap(DMA_PQ_ZERO_SUM, dma_dev->cap_mask) ? "pq_zero_sum " : "",
+	  "( %s%s%s%s%s%s%s)\n",
+	  dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "",
+	  dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "",
 	  dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
-	  dma_has_cap(DMA_DUAL_XOR, dma_dev->cap_mask) ? "dual_xor " : "",
-	  dma_has_cap(DMA_ZERO_SUM, dma_dev->cap_mask) ? "xor_zero_sum " : "",
+	  dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask) ? "xor_val " : "",
 	  dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
-	  dma_has_cap(DMA_MEMCPY_CRC32C, dma_dev->cap_mask) ? "cpy+crc " : "",
 	  dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
 	  dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
 
@@ -1296,7 +1643,7 @@ static void iop_chan_start_null_memcpy(struct iop_adma_chan *iop_chan)
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
 
-		list_splice_init(&sw_desc->async_tx.tx_list, &iop_chan->chain);
+		list_splice_init(&sw_desc->tx_list, &iop_chan->chain);
 		async_tx_ack(&sw_desc->async_tx);
 		iop_desc_init_memcpy(grp_start, 0);
 		iop_desc_set_byte_count(grp_start, iop_chan, 0);
@@ -1352,7 +1699,7 @@ static void iop_chan_start_null_xor(struct iop_adma_chan *iop_chan)
 	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
-		list_splice_init(&sw_desc->async_tx.tx_list, &iop_chan->chain);
+		list_splice_init(&sw_desc->tx_list, &iop_chan->chain);
 		async_tx_ack(&sw_desc->async_tx);
 		iop_desc_init_null_xor(grp_start, 2, 0);
 		iop_desc_set_byte_count(grp_start, iop_chan, 0);
diff --git a/drivers/dma/iovlock.c b/drivers/dma/iovlock.c
index 9f6fe46a9b8..c0a272c7368 100644
--- a/drivers/dma/iovlock.c
+++ b/drivers/dma/iovlock.c
@@ -183,6 +183,11 @@ dma_cookie_t dma_memcpy_to_iovec(struct dma_chan *chan, struct iovec *iov,
 					iov_byte_offset,
 					kdata,
 					copy);
+			/* poll for a descriptor slot */
+			if (unlikely(dma_cookie < 0)) {
+				dma_async_issue_pending(chan);
+				continue;
+			}
 
 			len -= copy;
 			iov[iovec_idx].iov_len -= copy;
@@ -248,6 +253,11 @@ dma_cookie_t dma_memcpy_pg_to_iovec(struct dma_chan *chan, struct iovec *iov,
 					page,
 					offset,
 					copy);
+			/* poll for a descriptor slot */
+			if (unlikely(dma_cookie < 0)) {
+				dma_async_issue_pending(chan);
+				continue;
+			}
 
 			len -= copy;
 			iov[iovec_idx].iov_len -= copy;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 3f23eabe09f..466ab10c1ff 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -517,7 +517,7 @@ retry:
 			}
 			alloc_tail->group_head = alloc_start;
 			alloc_tail->async_tx.cookie = -EBUSY;
-			list_splice(&chain, &alloc_tail->async_tx.tx_list);
+			list_splice(&chain, &alloc_tail->tx_list);
 			mv_chan->last_used = last_used;
 			mv_desc_clear_next_desc(alloc_start);
 			mv_desc_clear_next_desc(alloc_tail);
@@ -565,14 +565,14 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 	cookie = mv_desc_assign_cookie(mv_chan, sw_desc);
 
 	if (list_empty(&mv_chan->chain))
-		list_splice_init(&sw_desc->async_tx.tx_list, &mv_chan->chain);
+		list_splice_init(&sw_desc->tx_list, &mv_chan->chain);
 	else {
 		new_hw_chain = 0;
 
 		old_chain_tail = list_entry(mv_chan->chain.prev,
 					    struct mv_xor_desc_slot,
 					    chain_node);
-		list_splice_init(&grp_start->async_tx.tx_list,
+		list_splice_init(&grp_start->tx_list,
 				 &old_chain_tail->chain_node);
 
 		if (!mv_can_chain(grp_start))
@@ -632,6 +632,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 		slot->async_tx.tx_submit = mv_xor_tx_submit;
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
+		INIT_LIST_HEAD(&slot->tx_list);
 		hw_desc = (char *) mv_chan->device->dma_desc_pool;
 		slot->async_tx.phys =
 			(dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE];
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index 06cafe1ef52..977b592e976 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -126,9 +126,8 @@ struct mv_xor_chan {
  * @idx: pool index
  * @unmap_src_cnt: number of xor sources
  * @unmap_len: transaction bytecount
+ * @tx_list: list of slots that make up a multi-descriptor transaction
  * @async_tx: support for the async_tx api
- * @group_list: list of slots that make up a multi-descriptor transaction
- *	for example transfer lengths larger than the supported hw max
  * @xor_check_result: result of zero sum
  * @crc32_result: result crc calculation
  */
@@ -145,6 +144,7 @@ struct mv_xor_desc_slot {
 	u16			unmap_src_cnt;
 	u32			value;
 	size_t			unmap_len;
+	struct list_head	tx_list;
 	struct dma_async_tx_descriptor	async_tx;
 	union {
 		u32		*xor_check_result;
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
new file mode 100644
index 00000000000..b3b065c4e5c
--- /dev/null
+++ b/drivers/dma/shdma.c
@@ -0,0 +1,786 @@
+/*
+ * Renesas SuperH DMA Engine support
+ *
+ * base is drivers/dma/flsdma.c
+ *
+ * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
+ * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * - DMA of SuperH does not have Hardware DMA chain mode.
+ * - MAX DMA size is 16MB.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/platform_device.h>
+#include <cpu/dma.h>
+#include <asm/dma-sh.h>
+#include "shdma.h"
+
+/* DMA descriptor control */
+#define DESC_LAST	(-1)
+#define DESC_COMP	(1)
+#define DESC_NCOMP	(0)
+
+#define NR_DESCS_PER_CHANNEL 32
+/*
+ * Define the default configuration for dual address memory-memory transfer.
+ * The 0x400 value represents auto-request, external->external.
+ *
+ * And this driver set 4byte burst mode.
+ * If you want to change mode, you need to change RS_DEFAULT of value.
+ * (ex 1byte burst mode -> (RS_DUAL & ~TS_32)
+ */
+#define RS_DEFAULT  (RS_DUAL)
+
+#define SH_DMAC_CHAN_BASE(id) (dma_base_addr[id])
+static void sh_dmae_writel(struct sh_dmae_chan *sh_dc, u32 data, u32 reg)
+{
+	ctrl_outl(data, (SH_DMAC_CHAN_BASE(sh_dc->id) + reg));
+}
+
+static u32 sh_dmae_readl(struct sh_dmae_chan *sh_dc, u32 reg)
+{
+	return ctrl_inl((SH_DMAC_CHAN_BASE(sh_dc->id) + reg));
+}
+
+static void dmae_init(struct sh_dmae_chan *sh_chan)
+{
+	u32 chcr = RS_DEFAULT; /* default is DUAL mode */
+	sh_dmae_writel(sh_chan, chcr, CHCR);
+}
+
+/*
+ * Reset DMA controller
+ *
+ * SH7780 has two DMAOR register
+ */
+static void sh_dmae_ctl_stop(int id)
+{
+	unsigned short dmaor = dmaor_read_reg(id);
+
+	dmaor &= ~(DMAOR_NMIF | DMAOR_AE);
+	dmaor_write_reg(id, dmaor);
+}
+
+static int sh_dmae_rst(int id)
+{
+	unsigned short dmaor;
+
+	sh_dmae_ctl_stop(id);
+	dmaor = (dmaor_read_reg(id)|DMAOR_INIT);
+
+	dmaor_write_reg(id, dmaor);
+	if ((dmaor_read_reg(id) & (DMAOR_AE | DMAOR_NMIF))) {
+		pr_warning(KERN_ERR "dma-sh: Can't initialize DMAOR.\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int dmae_is_idle(struct sh_dmae_chan *sh_chan)
+{
+	u32 chcr = sh_dmae_readl(sh_chan, CHCR);
+	if (chcr & CHCR_DE) {
+		if (!(chcr & CHCR_TE))
+			return -EBUSY; /* working */
+	}
+	return 0; /* waiting */
+}
+
+static inline unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan)
+{
+	u32 chcr = sh_dmae_readl(sh_chan, CHCR);
+	return ts_shift[(chcr & CHCR_TS_MASK) >> CHCR_TS_SHIFT];
+}
+
+static void dmae_set_reg(struct sh_dmae_chan *sh_chan, struct sh_dmae_regs hw)
+{
+	sh_dmae_writel(sh_chan, hw.sar, SAR);
+	sh_dmae_writel(sh_chan, hw.dar, DAR);
+	sh_dmae_writel(sh_chan,
+		(hw.tcr >> calc_xmit_shift(sh_chan)), TCR);
+}
+
+static void dmae_start(struct sh_dmae_chan *sh_chan)
+{
+	u32 chcr = sh_dmae_readl(sh_chan, CHCR);
+
+	chcr |= (CHCR_DE|CHCR_IE);
+	sh_dmae_writel(sh_chan, chcr, CHCR);
+}
+
+static void dmae_halt(struct sh_dmae_chan *sh_chan)
+{
+	u32 chcr = sh_dmae_readl(sh_chan, CHCR);
+
+	chcr &= ~(CHCR_DE | CHCR_TE | CHCR_IE);
+	sh_dmae_writel(sh_chan, chcr, CHCR);
+}
+
+static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val)
+{
+	int ret = dmae_is_idle(sh_chan);
+	/* When DMA was working, can not set data to CHCR */
+	if (ret)
+		return ret;
+
+	sh_dmae_writel(sh_chan, val, CHCR);
+	return 0;
+}
+
+#define DMARS1_ADDR	0x04
+#define DMARS2_ADDR	0x08
+#define DMARS_SHIFT 8
+#define DMARS_CHAN_MSK 0x01
+static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val)
+{
+	u32 addr;
+	int shift = 0;
+	int ret = dmae_is_idle(sh_chan);
+	if (ret)
+		return ret;
+
+	if (sh_chan->id & DMARS_CHAN_MSK)
+		shift = DMARS_SHIFT;
+
+	switch (sh_chan->id) {
+	/* DMARS0 */
+	case 0:
+	case 1:
+		addr = SH_DMARS_BASE;
+		break;
+	/* DMARS1 */
+	case 2:
+	case 3:
+		addr = (SH_DMARS_BASE + DMARS1_ADDR);
+		break;
+	/* DMARS2 */
+	case 4:
+	case 5:
+		addr = (SH_DMARS_BASE + DMARS2_ADDR);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ctrl_outw((val << shift) |
+		(ctrl_inw(addr) & (shift ? 0xFF00 : 0x00FF)),
+		addr);
+
+	return 0;
+}
+
+static dma_cookie_t sh_dmae_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct sh_desc *desc = tx_to_sh_desc(tx);
+	struct sh_dmae_chan *sh_chan = to_sh_chan(tx->chan);
+	dma_cookie_t cookie;
+
+	spin_lock_bh(&sh_chan->desc_lock);
+
+	cookie = sh_chan->common.cookie;
+	cookie++;
+	if (cookie < 0)
+		cookie = 1;
+
+	/* If desc only in the case of 1 */
+	if (desc->async_tx.cookie != -EBUSY)
+		desc->async_tx.cookie = cookie;
+	sh_chan->common.cookie = desc->async_tx.cookie;
+
+	list_splice_init(&desc->tx_list, sh_chan->ld_queue.prev);
+
+	spin_unlock_bh(&sh_chan->desc_lock);
+
+	return cookie;
+}
+
+static struct sh_desc *sh_dmae_get_desc(struct sh_dmae_chan *sh_chan)
+{
+	struct sh_desc *desc, *_desc, *ret = NULL;
+
+	spin_lock_bh(&sh_chan->desc_lock);
+	list_for_each_entry_safe(desc, _desc, &sh_chan->ld_free, node) {
+		if (async_tx_test_ack(&desc->async_tx)) {
+			list_del(&desc->node);
+			ret = desc;
+			break;
+		}
+	}
+	spin_unlock_bh(&sh_chan->desc_lock);
+
+	return ret;
+}
+
+static void sh_dmae_put_desc(struct sh_dmae_chan *sh_chan, struct sh_desc *desc)
+{
+	if (desc) {
+		spin_lock_bh(&sh_chan->desc_lock);
+
+		list_splice_init(&desc->tx_list, &sh_chan->ld_free);
+		list_add(&desc->node, &sh_chan->ld_free);
+
+		spin_unlock_bh(&sh_chan->desc_lock);
+	}
+}
+
+static int sh_dmae_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
+	struct sh_desc *desc;
+
+	spin_lock_bh(&sh_chan->desc_lock);
+	while (sh_chan->descs_allocated < NR_DESCS_PER_CHANNEL) {
+		spin_unlock_bh(&sh_chan->desc_lock);
+		desc = kzalloc(sizeof(struct sh_desc), GFP_KERNEL);
+		if (!desc) {
+			spin_lock_bh(&sh_chan->desc_lock);
+			break;
+		}
+		dma_async_tx_descriptor_init(&desc->async_tx,
+					&sh_chan->common);
+		desc->async_tx.tx_submit = sh_dmae_tx_submit;
+		desc->async_tx.flags = DMA_CTRL_ACK;
+		INIT_LIST_HEAD(&desc->tx_list);
+		sh_dmae_put_desc(sh_chan, desc);
+
+		spin_lock_bh(&sh_chan->desc_lock);
+		sh_chan->descs_allocated++;
+	}
+	spin_unlock_bh(&sh_chan->desc_lock);
+
+	return sh_chan->descs_allocated;
+}
+
+/*
+ * sh_dma_free_chan_resources - Free all resources of the channel.
+ */
+static void sh_dmae_free_chan_resources(struct dma_chan *chan)
+{
+	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
+	struct sh_desc *desc, *_desc;
+	LIST_HEAD(list);
+
+	BUG_ON(!list_empty(&sh_chan->ld_queue));
+	spin_lock_bh(&sh_chan->desc_lock);
+
+	list_splice_init(&sh_chan->ld_free, &list);
+	sh_chan->descs_allocated = 0;
+
+	spin_unlock_bh(&sh_chan->desc_lock);
+
+	list_for_each_entry_safe(desc, _desc, &list, node)
+		kfree(desc);
+}
+
+static struct dma_async_tx_descriptor *sh_dmae_prep_memcpy(
+	struct dma_chan *chan, dma_addr_t dma_dest, dma_addr_t dma_src,
+	size_t len, unsigned long flags)
+{
+	struct sh_dmae_chan *sh_chan;
+	struct sh_desc *first = NULL, *prev = NULL, *new;
+	size_t copy_size;
+
+	if (!chan)
+		return NULL;
+
+	if (!len)
+		return NULL;
+
+	sh_chan = to_sh_chan(chan);
+
+	do {
+		/* Allocate the link descriptor from DMA pool */
+		new = sh_dmae_get_desc(sh_chan);
+		if (!new) {
+			dev_err(sh_chan->dev,
+					"No free memory for link descriptor\n");
+			goto err_get_desc;
+		}
+
+		copy_size = min(len, (size_t)SH_DMA_TCR_MAX);
+
+		new->hw.sar = dma_src;
+		new->hw.dar = dma_dest;
+		new->hw.tcr = copy_size;
+		if (!first)
+			first = new;
+
+		new->mark = DESC_NCOMP;
+		async_tx_ack(&new->async_tx);
+
+		prev = new;
+		len -= copy_size;
+		dma_src += copy_size;
+		dma_dest += copy_size;
+		/* Insert the link descriptor to the LD ring */
+		list_add_tail(&new->node, &first->tx_list);
+	} while (len);
+
+	new->async_tx.flags = flags; /* client is in control of this ack */
+	new->async_tx.cookie = -EBUSY; /* Last desc */
+
+	return &first->async_tx;
+
+err_get_desc:
+	sh_dmae_put_desc(sh_chan, first);
+	return NULL;
+
+}
+
+/*
+ * sh_chan_ld_cleanup - Clean up link descriptors
+ *
+ * This function clean up the ld_queue of DMA channel.
+ */
+static void sh_dmae_chan_ld_cleanup(struct sh_dmae_chan *sh_chan)
+{
+	struct sh_desc *desc, *_desc;
+
+	spin_lock_bh(&sh_chan->desc_lock);
+	list_for_each_entry_safe(desc, _desc, &sh_chan->ld_queue, node) {
+		dma_async_tx_callback callback;
+		void *callback_param;
+
+		/* non send data */
+		if (desc->mark == DESC_NCOMP)
+			break;
+
+		/* send data sesc */
+		callback = desc->async_tx.callback;
+		callback_param = desc->async_tx.callback_param;
+
+		/* Remove from ld_queue list */
+		list_splice_init(&desc->tx_list, &sh_chan->ld_free);
+
+		dev_dbg(sh_chan->dev, "link descriptor %p will be recycle.\n",
+				desc);
+
+		list_move(&desc->node, &sh_chan->ld_free);
+		/* Run the link descriptor callback function */
+		if (callback) {
+			spin_unlock_bh(&sh_chan->desc_lock);
+			dev_dbg(sh_chan->dev, "link descriptor %p callback\n",
+					desc);
+			callback(callback_param);
+			spin_lock_bh(&sh_chan->desc_lock);
+		}
+	}
+	spin_unlock_bh(&sh_chan->desc_lock);
+}
+
+static void sh_chan_xfer_ld_queue(struct sh_dmae_chan *sh_chan)
+{
+	struct list_head *ld_node;
+	struct sh_dmae_regs hw;
+
+	/* DMA work check */
+	if (dmae_is_idle(sh_chan))
+		return;
+
+	/* Find the first un-transfer desciptor */
+	for (ld_node = sh_chan->ld_queue.next;
+		(ld_node != &sh_chan->ld_queue)
+			&& (to_sh_desc(ld_node)->mark == DESC_COMP);
+		ld_node = ld_node->next)
+		cpu_relax();
+
+	if (ld_node != &sh_chan->ld_queue) {
+		/* Get the ld start address from ld_queue */
+		hw = to_sh_desc(ld_node)->hw;
+		dmae_set_reg(sh_chan, hw);
+		dmae_start(sh_chan);
+	}
+}
+
+static void sh_dmae_memcpy_issue_pending(struct dma_chan *chan)
+{
+	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
+	sh_chan_xfer_ld_queue(sh_chan);
+}
+
+static enum dma_status sh_dmae_is_complete(struct dma_chan *chan,
+					dma_cookie_t cookie,
+					dma_cookie_t *done,
+					dma_cookie_t *used)
+{
+	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
+	dma_cookie_t last_used;
+	dma_cookie_t last_complete;
+
+	sh_dmae_chan_ld_cleanup(sh_chan);
+
+	last_used = chan->cookie;
+	last_complete = sh_chan->completed_cookie;
+	if (last_complete == -EBUSY)
+		last_complete = last_used;
+
+	if (done)
+		*done = last_complete;
+
+	if (used)
+		*used = last_used;
+
+	return dma_async_is_complete(cookie, last_complete, last_used);
+}
+
+static irqreturn_t sh_dmae_interrupt(int irq, void *data)
+{
+	irqreturn_t ret = IRQ_NONE;
+	struct sh_dmae_chan *sh_chan = (struct sh_dmae_chan *)data;
+	u32 chcr = sh_dmae_readl(sh_chan, CHCR);
+
+	if (chcr & CHCR_TE) {
+		/* DMA stop */
+		dmae_halt(sh_chan);
+
+		ret = IRQ_HANDLED;
+		tasklet_schedule(&sh_chan->tasklet);
+	}
+
+	return ret;
+}
+
+#if defined(CONFIG_CPU_SH4)
+static irqreturn_t sh_dmae_err(int irq, void *data)
+{
+	int err = 0;
+	struct sh_dmae_device *shdev = (struct sh_dmae_device *)data;
+
+	/* IRQ Multi */
+	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
+		int cnt = 0;
+		switch (irq) {
+#if defined(DMTE6_IRQ) && defined(DMAE1_IRQ)
+		case DMTE6_IRQ:
+			cnt++;
+#endif
+		case DMTE0_IRQ:
+			if (dmaor_read_reg(cnt) & (DMAOR_NMIF | DMAOR_AE)) {
+				disable_irq(irq);
+				return IRQ_HANDLED;
+			}
+		default:
+			return IRQ_NONE;
+		}
+	} else {
+		/* reset dma controller */
+		err = sh_dmae_rst(0);
+		if (err)
+			return err;
+		if (shdev->pdata.mode & SHDMA_DMAOR1) {
+			err = sh_dmae_rst(1);
+			if (err)
+				return err;
+		}
+		disable_irq(irq);
+		return IRQ_HANDLED;
+	}
+}
+#endif
+
+static void dmae_do_tasklet(unsigned long data)
+{
+	struct sh_dmae_chan *sh_chan = (struct sh_dmae_chan *)data;
+	struct sh_desc *desc, *_desc, *cur_desc = NULL;
+	u32 sar_buf = sh_dmae_readl(sh_chan, SAR);
+	list_for_each_entry_safe(desc, _desc,
+					&sh_chan->ld_queue, node) {
+		if ((desc->hw.sar + desc->hw.tcr) == sar_buf) {
+			cur_desc = desc;
+			break;
+		}
+	}
+
+	if (cur_desc) {
+		switch (cur_desc->async_tx.cookie) {
+		case 0: /* other desc data */
+			break;
+		case -EBUSY: /* last desc */
+		sh_chan->completed_cookie =
+				cur_desc->async_tx.cookie;
+			break;
+		default: /* first desc ( 0 < )*/
+			sh_chan->completed_cookie =
+				cur_desc->async_tx.cookie - 1;
+			break;
+		}
+		cur_desc->mark = DESC_COMP;
+	}
+	/* Next desc */
+	sh_chan_xfer_ld_queue(sh_chan);
+	sh_dmae_chan_ld_cleanup(sh_chan);
+}
+
+static unsigned int get_dmae_irq(unsigned int id)
+{
+	unsigned int irq = 0;
+	if (id < ARRAY_SIZE(dmte_irq_map))
+		irq = dmte_irq_map[id];
+	return irq;
+}
+
+static int __devinit sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id)
+{
+	int err;
+	unsigned int irq = get_dmae_irq(id);
+	unsigned long irqflags = IRQF_DISABLED;
+	struct sh_dmae_chan *new_sh_chan;
+
+	/* alloc channel */
+	new_sh_chan = kzalloc(sizeof(struct sh_dmae_chan), GFP_KERNEL);
+	if (!new_sh_chan) {
+		dev_err(shdev->common.dev, "No free memory for allocating "
+				"dma channels!\n");
+		return -ENOMEM;
+	}
+
+	new_sh_chan->dev = shdev->common.dev;
+	new_sh_chan->id = id;
+
+	/* Init DMA tasklet */
+	tasklet_init(&new_sh_chan->tasklet, dmae_do_tasklet,
+			(unsigned long)new_sh_chan);
+
+	/* Init the channel */
+	dmae_init(new_sh_chan);
+
+	spin_lock_init(&new_sh_chan->desc_lock);
+
+	/* Init descripter manage list */
+	INIT_LIST_HEAD(&new_sh_chan->ld_queue);
+	INIT_LIST_HEAD(&new_sh_chan->ld_free);
+
+	/* copy struct dma_device */
+	new_sh_chan->common.device = &shdev->common;
+
+	/* Add the channel to DMA device channel list */
+	list_add_tail(&new_sh_chan->common.device_node,
+			&shdev->common.channels);
+	shdev->common.chancnt++;
+
+	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
+		irqflags = IRQF_SHARED;
+#if defined(DMTE6_IRQ)
+		if (irq >= DMTE6_IRQ)
+			irq = DMTE6_IRQ;
+		else
+#endif
+			irq = DMTE0_IRQ;
+	}
+
+	snprintf(new_sh_chan->dev_id, sizeof(new_sh_chan->dev_id),
+			"sh-dmae%d", new_sh_chan->id);
+
+	/* set up channel irq */
+	err = request_irq(irq, &sh_dmae_interrupt,
+		irqflags, new_sh_chan->dev_id, new_sh_chan);
+	if (err) {
+		dev_err(shdev->common.dev, "DMA channel %d request_irq error "
+			"with return %d\n", id, err);
+		goto err_no_irq;
+	}
+
+	/* CHCR register control function */
+	new_sh_chan->set_chcr = dmae_set_chcr;
+	/* DMARS register control function */
+	new_sh_chan->set_dmars = dmae_set_dmars;
+
+	shdev->chan[id] = new_sh_chan;
+	return 0;
+
+err_no_irq:
+	/* remove from dmaengine device node */
+	list_del(&new_sh_chan->common.device_node);
+	kfree(new_sh_chan);
+	return err;
+}
+
+static void sh_dmae_chan_remove(struct sh_dmae_device *shdev)
+{
+	int i;
+
+	for (i = shdev->common.chancnt - 1 ; i >= 0 ; i--) {
+		if (shdev->chan[i]) {
+			struct sh_dmae_chan *shchan = shdev->chan[i];
+			if (!(shdev->pdata.mode & SHDMA_MIX_IRQ))
+				free_irq(dmte_irq_map[i], shchan);
+
+			list_del(&shchan->common.device_node);
+			kfree(shchan);
+			shdev->chan[i] = NULL;
+		}
+	}
+	shdev->common.chancnt = 0;
+}
+
+static int __init sh_dmae_probe(struct platform_device *pdev)
+{
+	int err = 0, cnt, ecnt;
+	unsigned long irqflags = IRQF_DISABLED;
+#if defined(CONFIG_CPU_SH4)
+	int eirq[] = { DMAE0_IRQ,
+#if defined(DMAE1_IRQ)
+			DMAE1_IRQ
+#endif
+		};
+#endif
+	struct sh_dmae_device *shdev;
+
+	shdev = kzalloc(sizeof(struct sh_dmae_device), GFP_KERNEL);
+	if (!shdev) {
+		dev_err(&pdev->dev, "No enough memory\n");
+		err = -ENOMEM;
+		goto shdev_err;
+	}
+
+	/* get platform data */
+	if (!pdev->dev.platform_data)
+		goto shdev_err;
+
+	/* platform data */
+	memcpy(&shdev->pdata, pdev->dev.platform_data,
+			sizeof(struct sh_dmae_pdata));
+
+	/* reset dma controller */
+	err = sh_dmae_rst(0);
+	if (err)
+		goto rst_err;
+
+	/* SH7780/85/23 has DMAOR1 */
+	if (shdev->pdata.mode & SHDMA_DMAOR1) {
+		err = sh_dmae_rst(1);
+		if (err)
+			goto rst_err;
+	}
+
+	INIT_LIST_HEAD(&shdev->common.channels);
+
+	dma_cap_set(DMA_MEMCPY, shdev->common.cap_mask);
+	shdev->common.device_alloc_chan_resources
+		= sh_dmae_alloc_chan_resources;
+	shdev->common.device_free_chan_resources = sh_dmae_free_chan_resources;
+	shdev->common.device_prep_dma_memcpy = sh_dmae_prep_memcpy;
+	shdev->common.device_is_tx_complete = sh_dmae_is_complete;
+	shdev->common.device_issue_pending = sh_dmae_memcpy_issue_pending;
+	shdev->common.dev = &pdev->dev;
+
+#if defined(CONFIG_CPU_SH4)
+	/* Non Mix IRQ mode SH7722/SH7730 etc... */
+	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
+		irqflags = IRQF_SHARED;
+		eirq[0] = DMTE0_IRQ;
+#if defined(DMTE6_IRQ) && defined(DMAE1_IRQ)
+		eirq[1] = DMTE6_IRQ;
+#endif
+	}
+
+	for (ecnt = 0 ; ecnt < ARRAY_SIZE(eirq); ecnt++) {
+		err = request_irq(eirq[ecnt], sh_dmae_err,
+			irqflags, "DMAC Address Error", shdev);
+		if (err) {
+			dev_err(&pdev->dev, "DMA device request_irq"
+				"error (irq %d) with return %d\n",
+				eirq[ecnt], err);
+			goto eirq_err;
+		}
+	}
+#endif /* CONFIG_CPU_SH4 */
+
+	/* Create DMA Channel */
+	for (cnt = 0 ; cnt < MAX_DMA_CHANNELS ; cnt++) {
+		err = sh_dmae_chan_probe(shdev, cnt);
+		if (err)
+			goto chan_probe_err;
+	}
+
+	platform_set_drvdata(pdev, shdev);
+	dma_async_device_register(&shdev->common);
+
+	return err;
+
+chan_probe_err:
+	sh_dmae_chan_remove(shdev);
+
+eirq_err:
+	for (ecnt-- ; ecnt >= 0; ecnt--)
+		free_irq(eirq[ecnt], shdev);
+
+rst_err:
+	kfree(shdev);
+
+shdev_err:
+	return err;
+}
+
+static int __exit sh_dmae_remove(struct platform_device *pdev)
+{
+	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&shdev->common);
+
+	if (shdev->pdata.mode & SHDMA_MIX_IRQ) {
+		free_irq(DMTE0_IRQ, shdev);
+#if defined(DMTE6_IRQ)
+		free_irq(DMTE6_IRQ, shdev);
+#endif
+	}
+
+	/* channel data remove */
+	sh_dmae_chan_remove(shdev);
+
+	if (!(shdev->pdata.mode & SHDMA_MIX_IRQ)) {
+		free_irq(DMAE0_IRQ, shdev);
+#if defined(DMAE1_IRQ)
+		free_irq(DMAE1_IRQ, shdev);
+#endif
+	}
+	kfree(shdev);
+
+	return 0;
+}
+
+static void sh_dmae_shutdown(struct platform_device *pdev)
+{
+	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
+	sh_dmae_ctl_stop(0);
+	if (shdev->pdata.mode & SHDMA_DMAOR1)
+		sh_dmae_ctl_stop(1);
+}
+
+static struct platform_driver sh_dmae_driver = {
+	.remove		= __exit_p(sh_dmae_remove),
+	.shutdown	= sh_dmae_shutdown,
+	.driver = {
+		.name	= "sh-dma-engine",
+	},
+};
+
+static int __init sh_dmae_init(void)
+{
+	return platform_driver_probe(&sh_dmae_driver, sh_dmae_probe);
+}
+module_init(sh_dmae_init);
+
+static void __exit sh_dmae_exit(void)
+{
+	platform_driver_unregister(&sh_dmae_driver);
+}
+module_exit(sh_dmae_exit);
+
+MODULE_AUTHOR("Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>");
+MODULE_DESCRIPTION("Renesas SH DMA Engine driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h
new file mode 100644
index 00000000000..2b4bc15a2c0
--- /dev/null
+++ b/drivers/dma/shdma.h
@@ -0,0 +1,64 @@
+/*
+ * Renesas SuperH DMA Engine support
+ *
+ * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+#ifndef __DMA_SHDMA_H
+#define __DMA_SHDMA_H
+
+#include <linux/device.h>
+#include <linux/dmapool.h>
+#include <linux/dmaengine.h>
+
+#define SH_DMA_TCR_MAX 0x00FFFFFF	/* 16MB */
+
+struct sh_dmae_regs {
+	u32 sar; /* SAR / source address */
+	u32 dar; /* DAR / destination address */
+	u32 tcr; /* TCR / transfer count */
+};
+
+struct sh_desc {
+	struct list_head tx_list;
+	struct sh_dmae_regs hw;
+	struct list_head node;
+	struct dma_async_tx_descriptor async_tx;
+	int mark;
+};
+
+struct sh_dmae_chan {
+	dma_cookie_t completed_cookie;	/* The maximum cookie completed */
+	spinlock_t desc_lock;			/* Descriptor operation lock */
+	struct list_head ld_queue;		/* Link descriptors queue */
+	struct list_head ld_free;		/* Link descriptors free */
+	struct dma_chan common;			/* DMA common channel */
+	struct device *dev;				/* Channel device */
+	struct tasklet_struct tasklet;	/* Tasklet */
+	int descs_allocated;			/* desc count */
+	int id;				/* Raw id of this channel */
+	char dev_id[16];	/* unique name per DMAC of channel */
+
+	/* Set chcr */
+	int (*set_chcr)(struct sh_dmae_chan *sh_chan, u32 regs);
+	/* Set DMA resource */
+	int (*set_dmars)(struct sh_dmae_chan *sh_chan, u16 res);
+};
+
+struct sh_dmae_device {
+	struct dma_device common;
+	struct sh_dmae_chan *chan[MAX_DMA_CHANNELS];
+	struct sh_dmae_pdata pdata;
+};
+
+#define to_sh_chan(chan) container_of(chan, struct sh_dmae_chan, common)
+#define to_sh_desc(lh) container_of(lh, struct sh_desc, node)
+#define tx_to_sh_desc(tx) container_of(tx, struct sh_desc, async_tx)
+
+#endif	/* __DMA_SHDMA_H */
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 7837930146a..fb6bb64e886 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -180,9 +180,8 @@ static struct txx9dmac_desc *txx9dmac_first_queued(struct txx9dmac_chan *dc)
 
 static struct txx9dmac_desc *txx9dmac_last_child(struct txx9dmac_desc *desc)
 {
-	if (!list_empty(&desc->txd.tx_list))
-		desc = list_entry(desc->txd.tx_list.prev,
-				  struct txx9dmac_desc, desc_node);
+	if (!list_empty(&desc->tx_list))
+		desc = list_entry(desc->tx_list.prev, typeof(*desc), desc_node);
 	return desc;
 }
 
@@ -197,6 +196,7 @@ static struct txx9dmac_desc *txx9dmac_desc_alloc(struct txx9dmac_chan *dc,
 	desc = kzalloc(sizeof(*desc), flags);
 	if (!desc)
 		return NULL;
+	INIT_LIST_HEAD(&desc->tx_list);
 	dma_async_tx_descriptor_init(&desc->txd, &dc->chan);
 	desc->txd.tx_submit = txx9dmac_tx_submit;
 	/* txd.flags will be overwritten in prep funcs */
@@ -245,7 +245,7 @@ static void txx9dmac_sync_desc_for_cpu(struct txx9dmac_chan *dc,
 	struct txx9dmac_dev *ddev = dc->ddev;
 	struct txx9dmac_desc *child;
 
-	list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &desc->tx_list, desc_node)
 		dma_sync_single_for_cpu(chan2parent(&dc->chan),
 				child->txd.phys, ddev->descsize,
 				DMA_TO_DEVICE);
@@ -267,11 +267,11 @@ static void txx9dmac_desc_put(struct txx9dmac_chan *dc,
 		txx9dmac_sync_desc_for_cpu(dc, desc);
 
 		spin_lock_bh(&dc->lock);
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&dc->chan),
 				 "moving child desc %p to freelist\n",
 				 child);
-		list_splice_init(&desc->txd.tx_list, &dc->free_list);
+		list_splice_init(&desc->tx_list, &dc->free_list);
 		dev_vdbg(chan2dev(&dc->chan), "moving desc %p to freelist\n",
 			 desc);
 		list_add(&desc->desc_node, &dc->free_list);
@@ -429,7 +429,7 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc,
 	param = txd->callback_param;
 
 	txx9dmac_sync_desc_for_cpu(dc, desc);
-	list_splice_init(&txd->tx_list, &dc->free_list);
+	list_splice_init(&desc->tx_list, &dc->free_list);
 	list_move(&desc->desc_node, &dc->free_list);
 
 	if (!ds) {
@@ -571,7 +571,7 @@ static void txx9dmac_handle_error(struct txx9dmac_chan *dc, u32 csr)
 		 "Bad descriptor submitted for DMA! (cookie: %d)\n",
 		 bad_desc->txd.cookie);
 	txx9dmac_dump_desc(dc, &bad_desc->hwdesc);
-	list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		txx9dmac_dump_desc(dc, &child->hwdesc);
 	/* Pretend the descriptor completed successfully */
 	txx9dmac_descriptor_complete(dc, bad_desc);
@@ -613,7 +613,7 @@ static void txx9dmac_scan_descriptors(struct txx9dmac_chan *dc)
 			return;
 		}
 
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			if (desc_read_CHAR(dc, child) == chain) {
 				/* Currently in progress */
 				if (csr & TXX9_DMA_CSR_ABCHC)
@@ -823,8 +823,7 @@ txx9dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			dma_sync_single_for_device(chan2parent(&dc->chan),
 					prev->txd.phys, ddev->descsize,
 					DMA_TO_DEVICE);
-			list_add_tail(&desc->desc_node,
-					&first->txd.tx_list);
+			list_add_tail(&desc->desc_node, &first->tx_list);
 		}
 		prev = desc;
 	}
@@ -919,8 +918,7 @@ txx9dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 					prev->txd.phys,
 					ddev->descsize,
 					DMA_TO_DEVICE);
-			list_add_tail(&desc->desc_node,
-					&first->txd.tx_list);
+			list_add_tail(&desc->desc_node, &first->tx_list);
 		}
 		prev = desc;
 	}
diff --git a/drivers/dma/txx9dmac.h b/drivers/dma/txx9dmac.h
index c907ff01d27..365d42366b9 100644
--- a/drivers/dma/txx9dmac.h
+++ b/drivers/dma/txx9dmac.h
@@ -231,6 +231,7 @@ struct txx9dmac_desc {
 
 	/* THEN values for driver housekeeping */
 	struct list_head		desc_node ____cacheline_aligned;
+	struct list_head		tx_list;
 	struct dma_async_tx_descriptor	txd;
 	size_t				len;
 };
diff --git a/drivers/idle/i7300_idle.c b/drivers/idle/i7300_idle.c
index 949c97ff57e..1f20a042a4f 100644
--- a/drivers/idle/i7300_idle.c
+++ b/drivers/idle/i7300_idle.c
@@ -29,8 +29,8 @@
 
 #include <asm/idle.h>
 
-#include "../dma/ioatdma_hw.h"
-#include "../dma/ioatdma_registers.h"
+#include "../dma/ioat/hw.h"
+#include "../dma/ioat/registers.h"
 
 #define I7300_IDLE_DRIVER_VERSION	"1.55"
 #define I7300_PRINT			"i7300_idle:"
@@ -126,9 +126,9 @@ static void i7300_idle_ioat_stop(void)
 		udelay(10);
 
 		sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
-			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+			IOAT_CHANSTS_STATUS;
 
-		if (sts != IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE)
+		if (sts != IOAT_CHANSTS_ACTIVE)
 			break;
 
 	}
@@ -160,9 +160,9 @@ static int __init i7300_idle_ioat_selftest(u8 *ctl,
 	udelay(1000);
 
 	chan_sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
-			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+			IOAT_CHANSTS_STATUS;
 
-	if (chan_sts != IOAT_CHANSTS_DMA_TRANSFER_STATUS_DONE) {
+	if (chan_sts != IOAT_CHANSTS_DONE) {
 		/* Not complete, reset the channel */
 		writeb(IOAT_CHANCMD_RESET,
 		       ioat_chanbase + IOAT1_CHANCMD_OFFSET);
@@ -288,9 +288,9 @@ static void __exit i7300_idle_ioat_exit(void)
 		       ioat_chanbase + IOAT1_CHANCMD_OFFSET);
 
 		chan_sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
-			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+			IOAT_CHANSTS_STATUS;
 
-		if (chan_sts != IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE) {
+		if (chan_sts != IOAT_CHANSTS_ACTIVE) {
 			writew(0, ioat_chanbase + IOAT_CHANCTRL_OFFSET);
 			break;
 		}
@@ -298,14 +298,14 @@ static void __exit i7300_idle_ioat_exit(void)
 	}
 
 	chan_sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
-			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+			IOAT_CHANSTS_STATUS;
 
 	/*
 	 * We tried to reset multiple times. If IO A/T channel is still active
 	 * flag an error and return without cleanup. Memory leak is better
 	 * than random corruption in that extreme error situation.
 	 */
-	if (chan_sts == IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE) {
+	if (chan_sts == IOAT_CHANSTS_ACTIVE) {
 		printk(KERN_ERR I7300_PRINT "Unable to stop IO A/T channels."
 			" Not freeing resources\n");
 		return;
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 020f9573fd8..2158377a135 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -124,6 +124,8 @@ config MD_RAID456
 	select MD_RAID6_PQ
 	select ASYNC_MEMCPY
 	select ASYNC_XOR
+	select ASYNC_PQ
+	select ASYNC_RAID6_RECOV
 	---help---
 	  A RAID-5 set of N drives with a capacity of C MB per drive provides
 	  the capacity of C * (N - 1) MB, and protects against a failure
@@ -152,9 +154,33 @@ config MD_RAID456
 
 	  If unsure, say Y.
 
+config MULTICORE_RAID456
+	bool "RAID-4/RAID-5/RAID-6 Multicore processing (EXPERIMENTAL)"
+	depends on MD_RAID456
+	depends on SMP
+	depends on EXPERIMENTAL
+	---help---
+	  Enable the raid456 module to dispatch per-stripe raid operations to a
+	  thread pool.
+
+	  If unsure, say N.
+
 config MD_RAID6_PQ
 	tristate
 
+config ASYNC_RAID6_TEST
+	tristate "Self test for hardware accelerated raid6 recovery"
+	depends on MD_RAID6_PQ
+	select ASYNC_RAID6_RECOV
+	---help---
+	  This is a one-shot self test that permutes through the
+	  recovery of all the possible two disk failure scenarios for a
+	  N-disk array.  Recovery is performed with the asynchronous
+	  raid6 recovery routines, and will optionally use an offload
+	  engine if one is available.
+
+	  If unsure, say N.
+
 config MD_MULTIPATH
 	tristate "Multipath I/O support"
 	depends on BLK_DEV_MD
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9db84c98a41..94829804ab7 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -47,7 +47,9 @@
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
+#include <linux/async.h>
 #include <linux/seq_file.h>
+#include <linux/cpu.h>
 #include "md.h"
 #include "raid5.h"
 #include "bitmap.h"
@@ -499,11 +501,18 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 	struct page *bio_page;
 	int i;
 	int page_offset;
+	struct async_submit_ctl submit;
+	enum async_tx_flags flags = 0;
 
 	if (bio->bi_sector >= sector)
 		page_offset = (signed)(bio->bi_sector - sector) * 512;
 	else
 		page_offset = (signed)(sector - bio->bi_sector) * -512;
+
+	if (frombio)
+		flags |= ASYNC_TX_FENCE;
+	init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
+
 	bio_for_each_segment(bvl, bio, i) {
 		int len = bio_iovec_idx(bio, i)->bv_len;
 		int clen;
@@ -525,15 +534,14 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 			bio_page = bio_iovec_idx(bio, i)->bv_page;
 			if (frombio)
 				tx = async_memcpy(page, bio_page, page_offset,
-					b_offset, clen,
-					ASYNC_TX_DEP_ACK,
-					tx, NULL, NULL);
+						  b_offset, clen, &submit);
 			else
 				tx = async_memcpy(bio_page, page, b_offset,
-					page_offset, clen,
-					ASYNC_TX_DEP_ACK,
-					tx, NULL, NULL);
+						  page_offset, clen, &submit);
 		}
+		/* chain the operations */
+		submit.depend_tx = tx;
+
 		if (clen < len) /* hit end of page */
 			break;
 		page_offset +=  len;
@@ -592,6 +600,7 @@ static void ops_run_biofill(struct stripe_head *sh)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	raid5_conf_t *conf = sh->raid_conf;
+	struct async_submit_ctl submit;
 	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
@@ -615,22 +624,34 @@ static void ops_run_biofill(struct stripe_head *sh)
 	}
 
 	atomic_inc(&sh->count);
-	async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
-		ops_complete_biofill, sh);
+	init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_biofill, sh, NULL);
+	async_trigger_callback(&submit);
 }
 
-static void ops_complete_compute5(void *stripe_head_ref)
+static void mark_target_uptodate(struct stripe_head *sh, int target)
 {
-	struct stripe_head *sh = stripe_head_ref;
-	int target = sh->ops.target;
-	struct r5dev *tgt = &sh->dev[target];
+	struct r5dev *tgt;
 
-	pr_debug("%s: stripe %llu\n", __func__,
-		(unsigned long long)sh->sector);
+	if (target < 0)
+		return;
 
+	tgt = &sh->dev[target];
 	set_bit(R5_UPTODATE, &tgt->flags);
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 	clear_bit(R5_Wantcompute, &tgt->flags);
+}
+
+static void ops_complete_compute(void *stripe_head_ref)
+{
+	struct stripe_head *sh = stripe_head_ref;
+
+	pr_debug("%s: stripe %llu\n", __func__,
+		(unsigned long long)sh->sector);
+
+	/* mark the computed target(s) as uptodate */
+	mark_target_uptodate(sh, sh->ops.target);
+	mark_target_uptodate(sh, sh->ops.target2);
+
 	clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
 	if (sh->check_state == check_state_compute_run)
 		sh->check_state = check_state_compute_result;
@@ -638,16 +659,24 @@ static void ops_complete_compute5(void *stripe_head_ref)
 	release_stripe(sh);
 }
 
-static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh)
+/* return a pointer to the address conversion region of the scribble buffer */
+static addr_conv_t *to_addr_conv(struct stripe_head *sh,
+				 struct raid5_percpu *percpu)
+{
+	return percpu->scribble + sizeof(struct page *) * (sh->disks + 2);
+}
+
+static struct dma_async_tx_descriptor *
+ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
 {
-	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
-	struct page *xor_srcs[disks];
+	struct page **xor_srcs = percpu->scribble;
 	int target = sh->ops.target;
 	struct r5dev *tgt = &sh->dev[target];
 	struct page *xor_dest = tgt->page;
 	int count = 0;
 	struct dma_async_tx_descriptor *tx;
+	struct async_submit_ctl submit;
 	int i;
 
 	pr_debug("%s: stripe %llu block: %d\n",
@@ -660,17 +689,215 @@ static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh)
 
 	atomic_inc(&sh->count);
 
+	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
+			  ops_complete_compute, sh, to_addr_conv(sh, percpu));
 	if (unlikely(count == 1))
-		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
-			0, NULL, ops_complete_compute5, sh);
+		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
 	else
-		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
-			ASYNC_TX_XOR_ZERO_DST, NULL,
-			ops_complete_compute5, sh);
+		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
 
 	return tx;
 }
 
+/* set_syndrome_sources - populate source buffers for gen_syndrome
+ * @srcs - (struct page *) array of size sh->disks
+ * @sh - stripe_head to parse
+ *
+ * Populates srcs in proper layout order for the stripe and returns the
+ * 'count' of sources to be used in a call to async_gen_syndrome.  The P
+ * destination buffer is recorded in srcs[count] and the Q destination
+ * is recorded in srcs[count+1]].
+ */
+static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh)
+{
+	int disks = sh->disks;
+	int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
+	int d0_idx = raid6_d0(sh);
+	int count;
+	int i;
+
+	for (i = 0; i < disks; i++)
+		srcs[i] = (void *)raid6_empty_zero_page;
+
+	count = 0;
+	i = d0_idx;
+	do {
+		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+
+		srcs[slot] = sh->dev[i].page;
+		i = raid6_next_disk(i, disks);
+	} while (i != d0_idx);
+	BUG_ON(count != syndrome_disks);
+
+	return count;
+}
+
+static struct dma_async_tx_descriptor *
+ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
+{
+	int disks = sh->disks;
+	struct page **blocks = percpu->scribble;
+	int target;
+	int qd_idx = sh->qd_idx;
+	struct dma_async_tx_descriptor *tx;
+	struct async_submit_ctl submit;
+	struct r5dev *tgt;
+	struct page *dest;
+	int i;
+	int count;
+
+	if (sh->ops.target < 0)
+		target = sh->ops.target2;
+	else if (sh->ops.target2 < 0)
+		target = sh->ops.target;
+	else
+		/* we should only have one valid target */
+		BUG();
+	BUG_ON(target < 0);
+	pr_debug("%s: stripe %llu block: %d\n",
+		__func__, (unsigned long long)sh->sector, target);
+
+	tgt = &sh->dev[target];
+	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
+	dest = tgt->page;
+
+	atomic_inc(&sh->count);
+
+	if (target == qd_idx) {
+		count = set_syndrome_sources(blocks, sh);
+		blocks[count] = NULL; /* regenerating p is not necessary */
+		BUG_ON(blocks[count+1] != dest); /* q should already be set */
+		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+				  ops_complete_compute, sh,
+				  to_addr_conv(sh, percpu));
+		tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
+	} else {
+		/* Compute any data- or p-drive using XOR */
+		count = 0;
+		for (i = disks; i-- ; ) {
+			if (i == target || i == qd_idx)
+				continue;
+			blocks[count++] = sh->dev[i].page;
+		}
+
+		init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
+				  NULL, ops_complete_compute, sh,
+				  to_addr_conv(sh, percpu));
+		tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit);
+	}
+
+	return tx;
+}
+
+static struct dma_async_tx_descriptor *
+ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
+{
+	int i, count, disks = sh->disks;
+	int syndrome_disks = sh->ddf_layout ? disks : disks-2;
+	int d0_idx = raid6_d0(sh);
+	int faila = -1, failb = -1;
+	int target = sh->ops.target;
+	int target2 = sh->ops.target2;
+	struct r5dev *tgt = &sh->dev[target];
+	struct r5dev *tgt2 = &sh->dev[target2];
+	struct dma_async_tx_descriptor *tx;
+	struct page **blocks = percpu->scribble;
+	struct async_submit_ctl submit;
+
+	pr_debug("%s: stripe %llu block1: %d block2: %d\n",
+		 __func__, (unsigned long long)sh->sector, target, target2);
+	BUG_ON(target < 0 || target2 < 0);
+	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
+	BUG_ON(!test_bit(R5_Wantcompute, &tgt2->flags));
+
+	/* we need to open-code set_syndrome_sources to handle the
+	 * slot number conversion for 'faila' and 'failb'
+	 */
+	for (i = 0; i < disks ; i++)
+		blocks[i] = (void *)raid6_empty_zero_page;
+	count = 0;
+	i = d0_idx;
+	do {
+		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+
+		blocks[slot] = sh->dev[i].page;
+
+		if (i == target)
+			faila = slot;
+		if (i == target2)
+			failb = slot;
+		i = raid6_next_disk(i, disks);
+	} while (i != d0_idx);
+	BUG_ON(count != syndrome_disks);
+
+	BUG_ON(faila == failb);
+	if (failb < faila)
+		swap(faila, failb);
+	pr_debug("%s: stripe: %llu faila: %d failb: %d\n",
+		 __func__, (unsigned long long)sh->sector, faila, failb);
+
+	atomic_inc(&sh->count);
+
+	if (failb == syndrome_disks+1) {
+		/* Q disk is one of the missing disks */
+		if (faila == syndrome_disks) {
+			/* Missing P+Q, just recompute */
+			init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+					  ops_complete_compute, sh,
+					  to_addr_conv(sh, percpu));
+			return async_gen_syndrome(blocks, 0, count+2,
+						  STRIPE_SIZE, &submit);
+		} else {
+			struct page *dest;
+			int data_target;
+			int qd_idx = sh->qd_idx;
+
+			/* Missing D+Q: recompute D from P, then recompute Q */
+			if (target == qd_idx)
+				data_target = target2;
+			else
+				data_target = target;
+
+			count = 0;
+			for (i = disks; i-- ; ) {
+				if (i == data_target || i == qd_idx)
+					continue;
+				blocks[count++] = sh->dev[i].page;
+			}
+			dest = sh->dev[data_target].page;
+			init_async_submit(&submit,
+					  ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
+					  NULL, NULL, NULL,
+					  to_addr_conv(sh, percpu));
+			tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE,
+				       &submit);
+
+			count = set_syndrome_sources(blocks, sh);
+			init_async_submit(&submit, ASYNC_TX_FENCE, tx,
+					  ops_complete_compute, sh,
+					  to_addr_conv(sh, percpu));
+			return async_gen_syndrome(blocks, 0, count+2,
+						  STRIPE_SIZE, &submit);
+		}
+	} else {
+		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+				  ops_complete_compute, sh,
+				  to_addr_conv(sh, percpu));
+		if (failb == syndrome_disks) {
+			/* We're missing D+P. */
+			return async_raid6_datap_recov(syndrome_disks+2,
+						       STRIPE_SIZE, faila,
+						       blocks, &submit);
+		} else {
+			/* We're missing D+D. */
+			return async_raid6_2data_recov(syndrome_disks+2,
+						       STRIPE_SIZE, faila, failb,
+						       blocks, &submit);
+		}
+	}
+}
+
+
 static void ops_complete_prexor(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
@@ -680,12 +907,13 @@ static void ops_complete_prexor(void *stripe_head_ref)
 }
 
 static struct dma_async_tx_descriptor *
-ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu,
+	       struct dma_async_tx_descriptor *tx)
 {
-	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
-	struct page *xor_srcs[disks];
+	struct page **xor_srcs = percpu->scribble;
 	int count = 0, pd_idx = sh->pd_idx, i;
+	struct async_submit_ctl submit;
 
 	/* existing parity data subtracted */
 	struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
@@ -700,9 +928,9 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 			xor_srcs[count++] = dev->page;
 	}
 
-	tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
-		ASYNC_TX_DEP_ACK | ASYNC_TX_XOR_DROP_DST, tx,
-		ops_complete_prexor, sh);
+	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
+			  ops_complete_prexor, sh, to_addr_conv(sh, percpu));
+	tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
 
 	return tx;
 }
@@ -742,17 +970,21 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 	return tx;
 }
 
-static void ops_complete_postxor(void *stripe_head_ref)
+static void ops_complete_reconstruct(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-	int disks = sh->disks, i, pd_idx = sh->pd_idx;
+	int disks = sh->disks;
+	int pd_idx = sh->pd_idx;
+	int qd_idx = sh->qd_idx;
+	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
-		if (dev->written || i == pd_idx)
+
+		if (dev->written || i == pd_idx || i == qd_idx)
 			set_bit(R5_UPTODATE, &dev->flags);
 	}
 
@@ -770,12 +1002,12 @@ static void ops_complete_postxor(void *stripe_head_ref)
 }
 
 static void
-ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
+		     struct dma_async_tx_descriptor *tx)
 {
-	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
-	struct page *xor_srcs[disks];
-
+	struct page **xor_srcs = percpu->scribble;
+	struct async_submit_ctl submit;
 	int count = 0, pd_idx = sh->pd_idx, i;
 	struct page *xor_dest;
 	int prexor = 0;
@@ -809,18 +1041,36 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 	 * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
 	 * for the synchronous xor case
 	 */
-	flags = ASYNC_TX_DEP_ACK | ASYNC_TX_ACK |
+	flags = ASYNC_TX_ACK |
 		(prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);
 
 	atomic_inc(&sh->count);
 
-	if (unlikely(count == 1)) {
-		flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
-		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
-			flags, tx, ops_complete_postxor, sh);
-	} else
-		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
-			flags, tx, ops_complete_postxor, sh);
+	init_async_submit(&submit, flags, tx, ops_complete_reconstruct, sh,
+			  to_addr_conv(sh, percpu));
+	if (unlikely(count == 1))
+		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
+	else
+		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
+}
+
+static void
+ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
+		     struct dma_async_tx_descriptor *tx)
+{
+	struct async_submit_ctl submit;
+	struct page **blocks = percpu->scribble;
+	int count;
+
+	pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
+
+	count = set_syndrome_sources(blocks, sh);
+
+	atomic_inc(&sh->count);
+
+	init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_reconstruct,
+			  sh, to_addr_conv(sh, percpu));
+	async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE,  &submit);
 }
 
 static void ops_complete_check(void *stripe_head_ref)
@@ -835,63 +1085,115 @@ static void ops_complete_check(void *stripe_head_ref)
 	release_stripe(sh);
 }
 
-static void ops_run_check(struct stripe_head *sh)
+static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
 {
-	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
-	struct page *xor_srcs[disks];
+	int pd_idx = sh->pd_idx;
+	int qd_idx = sh->qd_idx;
+	struct page *xor_dest;
+	struct page **xor_srcs = percpu->scribble;
 	struct dma_async_tx_descriptor *tx;
-
-	int count = 0, pd_idx = sh->pd_idx, i;
-	struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
+	struct async_submit_ctl submit;
+	int count;
+	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
+	count = 0;
+	xor_dest = sh->dev[pd_idx].page;
+	xor_srcs[count++] = xor_dest;
 	for (i = disks; i--; ) {
-		struct r5dev *dev = &sh->dev[i];
-		if (i != pd_idx)
-			xor_srcs[count++] = dev->page;
+		if (i == pd_idx || i == qd_idx)
+			continue;
+		xor_srcs[count++] = sh->dev[i].page;
 	}
 
-	tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
-		&sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
+	init_async_submit(&submit, 0, NULL, NULL, NULL,
+			  to_addr_conv(sh, percpu));
+	tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
+			   &sh->ops.zero_sum_result, &submit);
+
+	atomic_inc(&sh->count);
+	init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL);
+	tx = async_trigger_callback(&submit);
+}
+
+static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
+{
+	struct page **srcs = percpu->scribble;
+	struct async_submit_ctl submit;
+	int count;
+
+	pr_debug("%s: stripe %llu checkp: %d\n", __func__,
+		(unsigned long long)sh->sector, checkp);
+
+	count = set_syndrome_sources(srcs, sh);
+	if (!checkp)
+		srcs[count] = NULL;
 
 	atomic_inc(&sh->count);
-	tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
-		ops_complete_check, sh);
+	init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
+			  sh, to_addr_conv(sh, percpu));
+	async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE,
+			   &sh->ops.zero_sum_result, percpu->spare_page, &submit);
 }
 
-static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request)
+static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 {
 	int overlap_clear = 0, i, disks = sh->disks;
 	struct dma_async_tx_descriptor *tx = NULL;
+	raid5_conf_t *conf = sh->raid_conf;
+	int level = conf->level;
+	struct raid5_percpu *percpu;
+	unsigned long cpu;
 
+	cpu = get_cpu();
+	percpu = per_cpu_ptr(conf->percpu, cpu);
 	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
 	}
 
 	if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) {
-		tx = ops_run_compute5(sh);
-		/* terminate the chain if postxor is not set to be run */
-		if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
+		if (level < 6)
+			tx = ops_run_compute5(sh, percpu);
+		else {
+			if (sh->ops.target2 < 0 || sh->ops.target < 0)
+				tx = ops_run_compute6_1(sh, percpu);
+			else
+				tx = ops_run_compute6_2(sh, percpu);
+		}
+		/* terminate the chain if reconstruct is not set to be run */
+		if (tx && !test_bit(STRIPE_OP_RECONSTRUCT, &ops_request))
 			async_tx_ack(tx);
 	}
 
 	if (test_bit(STRIPE_OP_PREXOR, &ops_request))
-		tx = ops_run_prexor(sh, tx);
+		tx = ops_run_prexor(sh, percpu, tx);
 
 	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
 		tx = ops_run_biodrain(sh, tx);
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
-		ops_run_postxor(sh, tx);
+	if (test_bit(STRIPE_OP_RECONSTRUCT, &ops_request)) {
+		if (level < 6)
+			ops_run_reconstruct5(sh, percpu, tx);
+		else
+			ops_run_reconstruct6(sh, percpu, tx);
+	}
 
-	if (test_bit(STRIPE_OP_CHECK, &ops_request))
-		ops_run_check(sh);
+	if (test_bit(STRIPE_OP_CHECK, &ops_request)) {
+		if (sh->check_state == check_state_run)
+			ops_run_check_p(sh, percpu);
+		else if (sh->check_state == check_state_run_q)
+			ops_run_check_pq(sh, percpu, 0);
+		else if (sh->check_state == check_state_run_pq)
+			ops_run_check_pq(sh, percpu, 1);
+		else
+			BUG();
+	}
 
 	if (overlap_clear)
 		for (i = disks; i--; ) {
@@ -899,6 +1201,7 @@ static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request)
 			if (test_and_clear_bit(R5_Overlap, &dev->flags))
 				wake_up(&sh->raid_conf->wait_for_overlap);
 		}
+	put_cpu();
 }
 
 static int grow_one_stripe(raid5_conf_t *conf)
@@ -948,6 +1251,28 @@ static int grow_stripes(raid5_conf_t *conf, int num)
 	return 0;
 }
 
+/**
+ * scribble_len - return the required size of the scribble region
+ * @num - total number of disks in the array
+ *
+ * The size must be enough to contain:
+ * 1/ a struct page pointer for each device in the array +2
+ * 2/ room to convert each entry in (1) to its corresponding dma
+ *    (dma_map_page()) or page (page_address()) address.
+ *
+ * Note: the +2 is for the destination buffers of the ddf/raid6 case where we
+ * calculate over all devices (not just the data blocks), using zeros in place
+ * of the P and Q blocks.
+ */
+static size_t scribble_len(int num)
+{
+	size_t len;
+
+	len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2);
+
+	return len;
+}
+
 static int resize_stripes(raid5_conf_t *conf, int newsize)
 {
 	/* Make all the stripes able to hold 'newsize' devices.
@@ -976,6 +1301,7 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 	struct stripe_head *osh, *nsh;
 	LIST_HEAD(newstripes);
 	struct disk_info *ndisks;
+	unsigned long cpu;
 	int err;
 	struct kmem_cache *sc;
 	int i;
@@ -1041,7 +1367,7 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 	/* Step 3.
 	 * At this point, we are holding all the stripes so the array
 	 * is completely stalled, so now is a good time to resize
-	 * conf->disks.
+	 * conf->disks and the scribble region
 	 */
 	ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO);
 	if (ndisks) {
@@ -1052,10 +1378,30 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 	} else
 		err = -ENOMEM;
 
+	get_online_cpus();
+	conf->scribble_len = scribble_len(newsize);
+	for_each_present_cpu(cpu) {
+		struct raid5_percpu *percpu;
+		void *scribble;
+
+		percpu = per_cpu_ptr(conf->percpu, cpu);
+		scribble = kmalloc(conf->scribble_len, GFP_NOIO);
+
+		if (scribble) {
+			kfree(percpu->scribble);
+			percpu->scribble = scribble;
+		} else {
+			err = -ENOMEM;
+			break;
+		}
+	}
+	put_online_cpus();
+
 	/* Step 4, return new stripes to service */
 	while(!list_empty(&newstripes)) {
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
 		list_del_init(&nsh->lru);
+
 		for (i=conf->raid_disks; i < newsize; i++)
 			if (nsh->dev[i].page == NULL) {
 				struct page *p = alloc_page(GFP_NOIO);
@@ -1594,258 +1940,13 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 }
 
 
-
-/*
- * Copy data between a page in the stripe cache, and one or more bion
- * The page could align with the middle of the bio, or there could be
- * several bion, each with several bio_vecs, which cover part of the page
- * Multiple bion are linked together on bi_next.  There may be extras
- * at the end of this list.  We ignore them.
- */
-static void copy_data(int frombio, struct bio *bio,
-		     struct page *page,
-		     sector_t sector)
-{
-	char *pa = page_address(page);
-	struct bio_vec *bvl;
-	int i;
-	int page_offset;
-
-	if (bio->bi_sector >= sector)
-		page_offset = (signed)(bio->bi_sector - sector) * 512;
-	else
-		page_offset = (signed)(sector - bio->bi_sector) * -512;
-	bio_for_each_segment(bvl, bio, i) {
-		int len = bio_iovec_idx(bio,i)->bv_len;
-		int clen;
-		int b_offset = 0;
-
-		if (page_offset < 0) {
-			b_offset = -page_offset;
-			page_offset += b_offset;
-			len -= b_offset;
-		}
-
-		if (len > 0 && page_offset + len > STRIPE_SIZE)
-			clen = STRIPE_SIZE - page_offset;
-		else clen = len;
-
-		if (clen > 0) {
-			char *ba = __bio_kmap_atomic(bio, i, KM_USER0);
-			if (frombio)
-				memcpy(pa+page_offset, ba+b_offset, clen);
-			else
-				memcpy(ba+b_offset, pa+page_offset, clen);
-			__bio_kunmap_atomic(ba, KM_USER0);
-		}
-		if (clen < len) /* hit end of page */
-			break;
-		page_offset +=  len;
-	}
-}
-
-#define check_xor()	do {						  \
-				if (count == MAX_XOR_BLOCKS) {		  \
-				xor_blocks(count, STRIPE_SIZE, dest, ptr);\
-				count = 0;				  \
-			   }						  \
-			} while(0)
-
-static void compute_parity6(struct stripe_head *sh, int method)
-{
-	raid5_conf_t *conf = sh->raid_conf;
-	int i, pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
-	int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
-	struct bio *chosen;
-	/**** FIX THIS: This could be very bad if disks is close to 256 ****/
-	void *ptrs[syndrome_disks+2];
-
-	pd_idx = sh->pd_idx;
-	qd_idx = sh->qd_idx;
-	d0_idx = raid6_d0(sh);
-
-	pr_debug("compute_parity, stripe %llu, method %d\n",
-		(unsigned long long)sh->sector, method);
-
-	switch(method) {
-	case READ_MODIFY_WRITE:
-		BUG();		/* READ_MODIFY_WRITE N/A for RAID-6 */
-	case RECONSTRUCT_WRITE:
-		for (i= disks; i-- ;)
-			if ( i != pd_idx && i != qd_idx && sh->dev[i].towrite ) {
-				chosen = sh->dev[i].towrite;
-				sh->dev[i].towrite = NULL;
-
-				if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
-					wake_up(&conf->wait_for_overlap);
-
-				BUG_ON(sh->dev[i].written);
-				sh->dev[i].written = chosen;
-			}
-		break;
-	case CHECK_PARITY:
-		BUG();		/* Not implemented yet */
-	}
-
-	for (i = disks; i--;)
-		if (sh->dev[i].written) {
-			sector_t sector = sh->dev[i].sector;
-			struct bio *wbi = sh->dev[i].written;
-			while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
-				copy_data(1, wbi, sh->dev[i].page, sector);
-				wbi = r5_next_bio(wbi, sector);
-			}
-
-			set_bit(R5_LOCKED, &sh->dev[i].flags);
-			set_bit(R5_UPTODATE, &sh->dev[i].flags);
-		}
-
-	/* Note that unlike RAID-5, the ordering of the disks matters greatly.*/
-
-	for (i = 0; i < disks; i++)
-		ptrs[i] = (void *)raid6_empty_zero_page;
-
-	count = 0;
-	i = d0_idx;
-	do {
-		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
-
-		ptrs[slot] = page_address(sh->dev[i].page);
-		if (slot < syndrome_disks &&
-		    !test_bit(R5_UPTODATE, &sh->dev[i].flags)) {
-			printk(KERN_ERR "block %d/%d not uptodate "
-			       "on parity calc\n", i, count);
-			BUG();
-		}
-
-		i = raid6_next_disk(i, disks);
-	} while (i != d0_idx);
-	BUG_ON(count != syndrome_disks);
-
-	raid6_call.gen_syndrome(syndrome_disks+2, STRIPE_SIZE, ptrs);
-
-	switch(method) {
-	case RECONSTRUCT_WRITE:
-		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-		set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
-		set_bit(R5_LOCKED,   &sh->dev[pd_idx].flags);
-		set_bit(R5_LOCKED,   &sh->dev[qd_idx].flags);
-		break;
-	case UPDATE_PARITY:
-		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-		set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
-		break;
-	}
-}
-
-
-/* Compute one missing block */
-static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
-{
-	int i, count, disks = sh->disks;
-	void *ptr[MAX_XOR_BLOCKS], *dest, *p;
-	int qd_idx = sh->qd_idx;
-
-	pr_debug("compute_block_1, stripe %llu, idx %d\n",
-		(unsigned long long)sh->sector, dd_idx);
-
-	if ( dd_idx == qd_idx ) {
-		/* We're actually computing the Q drive */
-		compute_parity6(sh, UPDATE_PARITY);
-	} else {
-		dest = page_address(sh->dev[dd_idx].page);
-		if (!nozero) memset(dest, 0, STRIPE_SIZE);
-		count = 0;
-		for (i = disks ; i--; ) {
-			if (i == dd_idx || i == qd_idx)
-				continue;
-			p = page_address(sh->dev[i].page);
-			if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
-				ptr[count++] = p;
-			else
-				printk("compute_block() %d, stripe %llu, %d"
-				       " not present\n", dd_idx,
-				       (unsigned long long)sh->sector, i);
-
-			check_xor();
-		}
-		if (count)
-			xor_blocks(count, STRIPE_SIZE, dest, ptr);
-		if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
-		else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
-	}
-}
-
-/* Compute two missing blocks */
-static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
-{
-	int i, count, disks = sh->disks;
-	int syndrome_disks = sh->ddf_layout ? disks : disks-2;
-	int d0_idx = raid6_d0(sh);
-	int faila = -1, failb = -1;
-	/**** FIX THIS: This could be very bad if disks is close to 256 ****/
-	void *ptrs[syndrome_disks+2];
-
-	for (i = 0; i < disks ; i++)
-		ptrs[i] = (void *)raid6_empty_zero_page;
-	count = 0;
-	i = d0_idx;
-	do {
-		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
-
-		ptrs[slot] = page_address(sh->dev[i].page);
-
-		if (i == dd_idx1)
-			faila = slot;
-		if (i == dd_idx2)
-			failb = slot;
-		i = raid6_next_disk(i, disks);
-	} while (i != d0_idx);
-	BUG_ON(count != syndrome_disks);
-
-	BUG_ON(faila == failb);
-	if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }
-
-	pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
-		 (unsigned long long)sh->sector, dd_idx1, dd_idx2,
-		 faila, failb);
-
-	if (failb == syndrome_disks+1) {
-		/* Q disk is one of the missing disks */
-		if (faila == syndrome_disks) {
-			/* Missing P+Q, just recompute */
-			compute_parity6(sh, UPDATE_PARITY);
-			return;
-		} else {
-			/* We're missing D+Q; recompute D from P */
-			compute_block_1(sh, ((dd_idx1 == sh->qd_idx) ?
-					     dd_idx2 : dd_idx1),
-					0);
-			compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
-			return;
-		}
-	}
-
-	/* We're missing D+P or D+D; */
-	if (failb == syndrome_disks) {
-		/* We're missing D+P. */
-		raid6_datap_recov(syndrome_disks+2, STRIPE_SIZE, faila, ptrs);
-	} else {
-		/* We're missing D+D. */
-		raid6_2data_recov(syndrome_disks+2, STRIPE_SIZE, faila, failb,
-				  ptrs);
-	}
-
-	/* Both the above update both missing blocks */
-	set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
-	set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
-}
-
 static void
-schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
+schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 			 int rcw, int expand)
 {
 	int i, pd_idx = sh->pd_idx, disks = sh->disks;
+	raid5_conf_t *conf = sh->raid_conf;
+	int level = conf->level;
 
 	if (rcw) {
 		/* if we are not expanding this is a proper write request, and
@@ -1858,7 +1959,7 @@ schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
 		} else
 			sh->reconstruct_state = reconstruct_state_run;
 
-		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
@@ -1871,17 +1972,18 @@ schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
 				s->locked++;
 			}
 		}
-		if (s->locked + 1 == disks)
+		if (s->locked + conf->max_degraded == disks)
 			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
-				atomic_inc(&sh->raid_conf->pending_full_writes);
+				atomic_inc(&conf->pending_full_writes);
 	} else {
+		BUG_ON(level == 6);
 		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
 			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
 
 		sh->reconstruct_state = reconstruct_state_prexor_drain_run;
 		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
 		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
-		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
@@ -1899,13 +2001,22 @@ schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
 		}
 	}
 
-	/* keep the parity disk locked while asynchronous operations
+	/* keep the parity disk(s) locked while asynchronous operations
 	 * are in flight
 	 */
 	set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
 	clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
 	s->locked++;
 
+	if (level == 6) {
+		int qd_idx = sh->qd_idx;
+		struct r5dev *dev = &sh->dev[qd_idx];
+
+		set_bit(R5_LOCKED, &dev->flags);
+		clear_bit(R5_UPTODATE, &dev->flags);
+		s->locked++;
+	}
+
 	pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
 		__func__, (unsigned long long)sh->sector,
 		s->locked, s->ops_request);
@@ -1986,13 +2097,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 
 static void end_reshape(raid5_conf_t *conf);
 
-static int page_is_zero(struct page *p)
-{
-	char *a = page_address(p);
-	return ((*(u32*)a) == 0 &&
-		memcmp(a, a+4, STRIPE_SIZE-4)==0);
-}
-
 static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
 			    struct stripe_head *sh)
 {
@@ -2132,9 +2236,10 @@ static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s,
 			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
 			set_bit(R5_Wantcompute, &dev->flags);
 			sh->ops.target = disk_idx;
+			sh->ops.target2 = -1;
 			s->req_compute = 1;
 			/* Careful: from this point on 'uptodate' is in the eye
-			 * of raid5_run_ops which services 'compute' operations
+			 * of raid_run_ops which services 'compute' operations
 			 * before writes. R5_Wantcompute flags a block that will
 			 * be R5_UPTODATE by the time it is needed for a
 			 * subsequent operation.
@@ -2173,61 +2278,104 @@ static void handle_stripe_fill5(struct stripe_head *sh,
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
 
-static void handle_stripe_fill6(struct stripe_head *sh,
-			struct stripe_head_state *s, struct r6_state *r6s,
-			int disks)
+/* fetch_block6 - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill6 to continue
+ */
+static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
+			 struct r6_state *r6s, int disk_idx, int disks)
 {
-	int i;
-	for (i = disks; i--; ) {
-		struct r5dev *dev = &sh->dev[i];
-		if (!test_bit(R5_LOCKED, &dev->flags) &&
-		    !test_bit(R5_UPTODATE, &dev->flags) &&
-		    (dev->toread || (dev->towrite &&
-		     !test_bit(R5_OVERWRITE, &dev->flags)) ||
-		     s->syncing || s->expanding ||
-		     (s->failed >= 1 &&
-		      (sh->dev[r6s->failed_num[0]].toread ||
-		       s->to_write)) ||
-		     (s->failed >= 2 &&
-		      (sh->dev[r6s->failed_num[1]].toread ||
-		       s->to_write)))) {
-			/* we would like to get this block, possibly
-			 * by computing it, but we might not be able to
+	struct r5dev *dev = &sh->dev[disk_idx];
+	struct r5dev *fdev[2] = { &sh->dev[r6s->failed_num[0]],
+				  &sh->dev[r6s->failed_num[1]] };
+
+	if (!test_bit(R5_LOCKED, &dev->flags) &&
+	    !test_bit(R5_UPTODATE, &dev->flags) &&
+	    (dev->toread ||
+	     (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
+	     s->syncing || s->expanding ||
+	     (s->failed >= 1 &&
+	      (fdev[0]->toread || s->to_write)) ||
+	     (s->failed >= 2 &&
+	      (fdev[1]->toread || s->to_write)))) {
+		/* we would like to get this block, possibly by computing it,
+		 * otherwise read it if the backing disk is insync
+		 */
+		BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
+		BUG_ON(test_bit(R5_Wantread, &dev->flags));
+		if ((s->uptodate == disks - 1) &&
+		    (s->failed && (disk_idx == r6s->failed_num[0] ||
+				   disk_idx == r6s->failed_num[1]))) {
+			/* have disk failed, and we're requested to fetch it;
+			 * do compute it
 			 */
-			if ((s->uptodate == disks - 1) &&
-			    (s->failed && (i == r6s->failed_num[0] ||
-					   i == r6s->failed_num[1]))) {
-				pr_debug("Computing stripe %llu block %d\n",
-				       (unsigned long long)sh->sector, i);
-				compute_block_1(sh, i, 0);
-				s->uptodate++;
-			} else if ( s->uptodate == disks-2 && s->failed >= 2 ) {
-				/* Computing 2-failure is *very* expensive; only
-				 * do it if failed >= 2
-				 */
-				int other;
-				for (other = disks; other--; ) {
-					if (other == i)
-						continue;
-					if (!test_bit(R5_UPTODATE,
-					      &sh->dev[other].flags))
-						break;
-				}
-				BUG_ON(other < 0);
-				pr_debug("Computing stripe %llu blocks %d,%d\n",
-				       (unsigned long long)sh->sector,
-				       i, other);
-				compute_block_2(sh, i, other);
-				s->uptodate += 2;
-			} else if (test_bit(R5_Insync, &dev->flags)) {
-				set_bit(R5_LOCKED, &dev->flags);
-				set_bit(R5_Wantread, &dev->flags);
-				s->locked++;
-				pr_debug("Reading block %d (sync=%d)\n",
-					i, s->syncing);
+			pr_debug("Computing stripe %llu block %d\n",
+			       (unsigned long long)sh->sector, disk_idx);
+			set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+			set_bit(R5_Wantcompute, &dev->flags);
+			sh->ops.target = disk_idx;
+			sh->ops.target2 = -1; /* no 2nd target */
+			s->req_compute = 1;
+			s->uptodate++;
+			return 1;
+		} else if (s->uptodate == disks-2 && s->failed >= 2) {
+			/* Computing 2-failure is *very* expensive; only
+			 * do it if failed >= 2
+			 */
+			int other;
+			for (other = disks; other--; ) {
+				if (other == disk_idx)
+					continue;
+				if (!test_bit(R5_UPTODATE,
+				      &sh->dev[other].flags))
+					break;
 			}
+			BUG_ON(other < 0);
+			pr_debug("Computing stripe %llu blocks %d,%d\n",
+			       (unsigned long long)sh->sector,
+			       disk_idx, other);
+			set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+			set_bit(R5_Wantcompute, &sh->dev[disk_idx].flags);
+			set_bit(R5_Wantcompute, &sh->dev[other].flags);
+			sh->ops.target = disk_idx;
+			sh->ops.target2 = other;
+			s->uptodate += 2;
+			s->req_compute = 1;
+			return 1;
+		} else if (test_bit(R5_Insync, &dev->flags)) {
+			set_bit(R5_LOCKED, &dev->flags);
+			set_bit(R5_Wantread, &dev->flags);
+			s->locked++;
+			pr_debug("Reading block %d (sync=%d)\n",
+				disk_idx, s->syncing);
 		}
 	}
+
+	return 0;
+}
+
+/**
+ * handle_stripe_fill6 - read or compute data to satisfy pending requests.
+ */
+static void handle_stripe_fill6(struct stripe_head *sh,
+			struct stripe_head_state *s, struct r6_state *r6s,
+			int disks)
+{
+	int i;
+
+	/* look for blocks to read/compute, skip this if a compute
+	 * is already in flight, or if the stripe contents are in the
+	 * midst of changing due to a write
+	 */
+	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
+	    !sh->reconstruct_state)
+		for (i = disks; i--; )
+			if (fetch_block6(sh, s, r6s, i, disks))
+				break;
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
 
@@ -2361,114 +2509,61 @@ static void handle_stripe_dirtying5(raid5_conf_t *conf,
 	 */
 	/* since handle_stripe can be called at any time we need to handle the
 	 * case where a compute block operation has been submitted and then a
-	 * subsequent call wants to start a write request.  raid5_run_ops only
-	 * handles the case where compute block and postxor are requested
+	 * subsequent call wants to start a write request.  raid_run_ops only
+	 * handles the case where compute block and reconstruct are requested
 	 * simultaneously.  If this is not the case then new writes need to be
 	 * held off until the compute completes.
 	 */
 	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
 	    (s->locked == 0 && (rcw == 0 || rmw == 0) &&
 	    !test_bit(STRIPE_BIT_DELAY, &sh->state)))
-		schedule_reconstruction5(sh, s, rcw == 0, 0);
+		schedule_reconstruction(sh, s, rcw == 0, 0);
 }
 
 static void handle_stripe_dirtying6(raid5_conf_t *conf,
 		struct stripe_head *sh,	struct stripe_head_state *s,
 		struct r6_state *r6s, int disks)
 {
-	int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i;
+	int rcw = 0, pd_idx = sh->pd_idx, i;
 	int qd_idx = sh->qd_idx;
+
+	set_bit(STRIPE_HANDLE, &sh->state);
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
-		/* Would I have to read this buffer for reconstruct_write */
-		if (!test_bit(R5_OVERWRITE, &dev->flags)
-		    && i != pd_idx && i != qd_idx
-		    && (!test_bit(R5_LOCKED, &dev->flags)
-			    ) &&
-		    !test_bit(R5_UPTODATE, &dev->flags)) {
-			if (test_bit(R5_Insync, &dev->flags)) rcw++;
-			else {
-				pr_debug("raid6: must_compute: "
-					"disk %d flags=%#lx\n", i, dev->flags);
-				must_compute++;
+		/* check if we haven't enough data */
+		if (!test_bit(R5_OVERWRITE, &dev->flags) &&
+		    i != pd_idx && i != qd_idx &&
+		    !test_bit(R5_LOCKED, &dev->flags) &&
+		    !(test_bit(R5_UPTODATE, &dev->flags) ||
+		      test_bit(R5_Wantcompute, &dev->flags))) {
+			rcw++;
+			if (!test_bit(R5_Insync, &dev->flags))
+				continue; /* it's a failed drive */
+
+			if (
+			  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+				pr_debug("Read_old stripe %llu "
+					"block %d for Reconstruct\n",
+				     (unsigned long long)sh->sector, i);
+				set_bit(R5_LOCKED, &dev->flags);
+				set_bit(R5_Wantread, &dev->flags);
+				s->locked++;
+			} else {
+				pr_debug("Request delayed stripe %llu "
+					"block %d for Reconstruct\n",
+				     (unsigned long long)sh->sector, i);
+				set_bit(STRIPE_DELAYED, &sh->state);
+				set_bit(STRIPE_HANDLE, &sh->state);
 			}
 		}
 	}
-	pr_debug("for sector %llu, rcw=%d, must_compute=%d\n",
-	       (unsigned long long)sh->sector, rcw, must_compute);
-	set_bit(STRIPE_HANDLE, &sh->state);
-
-	if (rcw > 0)
-		/* want reconstruct write, but need to get some data */
-		for (i = disks; i--; ) {
-			struct r5dev *dev = &sh->dev[i];
-			if (!test_bit(R5_OVERWRITE, &dev->flags)
-			    && !(s->failed == 0 && (i == pd_idx || i == qd_idx))
-			    && !test_bit(R5_LOCKED, &dev->flags) &&
-			    !test_bit(R5_UPTODATE, &dev->flags) &&
-			    test_bit(R5_Insync, &dev->flags)) {
-				if (
-				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-					pr_debug("Read_old stripe %llu "
-						"block %d for Reconstruct\n",
-					     (unsigned long long)sh->sector, i);
-					set_bit(R5_LOCKED, &dev->flags);
-					set_bit(R5_Wantread, &dev->flags);
-					s->locked++;
-				} else {
-					pr_debug("Request delayed stripe %llu "
-						"block %d for Reconstruct\n",
-					     (unsigned long long)sh->sector, i);
-					set_bit(STRIPE_DELAYED, &sh->state);
-					set_bit(STRIPE_HANDLE, &sh->state);
-				}
-			}
-		}
 	/* now if nothing is locked, and if we have enough data, we can start a
 	 * write request
 	 */
-	if (s->locked == 0 && rcw == 0 &&
+	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
+	    s->locked == 0 && rcw == 0 &&
 	    !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
-		if (must_compute > 0) {
-			/* We have failed blocks and need to compute them */
-			switch (s->failed) {
-			case 0:
-				BUG();
-			case 1:
-				compute_block_1(sh, r6s->failed_num[0], 0);
-				break;
-			case 2:
-				compute_block_2(sh, r6s->failed_num[0],
-						r6s->failed_num[1]);
-				break;
-			default: /* This request should have been failed? */
-				BUG();
-			}
-		}
-
-		pr_debug("Computing parity for stripe %llu\n",
-			(unsigned long long)sh->sector);
-		compute_parity6(sh, RECONSTRUCT_WRITE);
-		/* now every locked buffer is ready to be written */
-		for (i = disks; i--; )
-			if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
-				pr_debug("Writing stripe %llu block %d\n",
-				       (unsigned long long)sh->sector, i);
-				s->locked++;
-				set_bit(R5_Wantwrite, &sh->dev[i].flags);
-			}
-		if (s->locked == disks)
-			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
-				atomic_inc(&conf->pending_full_writes);
-		/* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
-		set_bit(STRIPE_INSYNC, &sh->state);
-
-		if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-			atomic_dec(&conf->preread_active_stripes);
-			if (atomic_read(&conf->preread_active_stripes) <
-			    IO_THRESHOLD)
-				md_wakeup_thread(conf->mddev->thread);
-		}
+		schedule_reconstruction(sh, s, 1, 0);
 	}
 }
 
@@ -2527,7 +2622,7 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 		 * we are done.  Otherwise update the mismatch count and repair
 		 * parity if !MD_RECOVERY_CHECK
 		 */
-		if (sh->ops.zero_sum_result == 0)
+		if ((sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) == 0)
 			/* parity is correct (on disc,
 			 * not in buffer any more)
 			 */
@@ -2544,6 +2639,7 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 				set_bit(R5_Wantcompute,
 					&sh->dev[sh->pd_idx].flags);
 				sh->ops.target = sh->pd_idx;
+				sh->ops.target2 = -1;
 				s->uptodate++;
 			}
 		}
@@ -2560,67 +2656,74 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 
 
 static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
-				struct stripe_head_state *s,
-				struct r6_state *r6s, struct page *tmp_page,
-				int disks)
+				  struct stripe_head_state *s,
+				  struct r6_state *r6s, int disks)
 {
-	int update_p = 0, update_q = 0;
-	struct r5dev *dev;
 	int pd_idx = sh->pd_idx;
 	int qd_idx = sh->qd_idx;
+	struct r5dev *dev;
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 
 	BUG_ON(s->failed > 2);
-	BUG_ON(s->uptodate < disks);
+
 	/* Want to check and possibly repair P and Q.
 	 * However there could be one 'failed' device, in which
 	 * case we can only check one of them, possibly using the
 	 * other to generate missing data
 	 */
 
-	/* If !tmp_page, we cannot do the calculations,
-	 * but as we have set STRIPE_HANDLE, we will soon be called
-	 * by stripe_handle with a tmp_page - just wait until then.
-	 */
-	if (tmp_page) {
+	switch (sh->check_state) {
+	case check_state_idle:
+		/* start a new check operation if there are < 2 failures */
 		if (s->failed == r6s->q_failed) {
-			/* The only possible failed device holds 'Q', so it
+			/* The only possible failed device holds Q, so it
 			 * makes sense to check P (If anything else were failed,
 			 * we would have used P to recreate it).
 			 */
-			compute_block_1(sh, pd_idx, 1);
-			if (!page_is_zero(sh->dev[pd_idx].page)) {
-				compute_block_1(sh, pd_idx, 0);
-				update_p = 1;
-			}
+			sh->check_state = check_state_run;
 		}
 		if (!r6s->q_failed && s->failed < 2) {
-			/* q is not failed, and we didn't use it to generate
+			/* Q is not failed, and we didn't use it to generate
 			 * anything, so it makes sense to check it
 			 */
-			memcpy(page_address(tmp_page),
-			       page_address(sh->dev[qd_idx].page),
-			       STRIPE_SIZE);
-			compute_parity6(sh, UPDATE_PARITY);
-			if (memcmp(page_address(tmp_page),
-				   page_address(sh->dev[qd_idx].page),
-				   STRIPE_SIZE) != 0) {
-				clear_bit(STRIPE_INSYNC, &sh->state);
-				update_q = 1;
-			}
+			if (sh->check_state == check_state_run)
+				sh->check_state = check_state_run_pq;
+			else
+				sh->check_state = check_state_run_q;
 		}
-		if (update_p || update_q) {
-			conf->mddev->resync_mismatches += STRIPE_SECTORS;
-			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
-				/* don't try to repair!! */
-				update_p = update_q = 0;
+
+		/* discard potentially stale zero_sum_result */
+		sh->ops.zero_sum_result = 0;
+
+		if (sh->check_state == check_state_run) {
+			/* async_xor_zero_sum destroys the contents of P */
+			clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
+			s->uptodate--;
+		}
+		if (sh->check_state >= check_state_run &&
+		    sh->check_state <= check_state_run_pq) {
+			/* async_syndrome_zero_sum preserves P and Q, so
+			 * no need to mark them !uptodate here
+			 */
+			set_bit(STRIPE_OP_CHECK, &s->ops_request);
+			break;
 		}
 
+		/* we have 2-disk failure */
+		BUG_ON(s->failed != 2);
+		/* fall through */
+	case check_state_compute_result:
+		sh->check_state = check_state_idle;
+
+		/* check that a write has not made the stripe insync */
+		if (test_bit(STRIPE_INSYNC, &sh->state))
+			break;
+
 		/* now write out any block on a failed drive,
-		 * or P or Q if they need it
+		 * or P or Q if they were recomputed
 		 */
-
+		BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
 		if (s->failed == 2) {
 			dev = &sh->dev[r6s->failed_num[1]];
 			s->locked++;
@@ -2633,14 +2736,13 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantwrite, &dev->flags);
 		}
-
-		if (update_p) {
+		if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) {
 			dev = &sh->dev[pd_idx];
 			s->locked++;
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantwrite, &dev->flags);
 		}
-		if (update_q) {
+		if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) {
 			dev = &sh->dev[qd_idx];
 			s->locked++;
 			set_bit(R5_LOCKED, &dev->flags);
@@ -2649,6 +2751,70 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
 		clear_bit(STRIPE_DEGRADED, &sh->state);
 
 		set_bit(STRIPE_INSYNC, &sh->state);
+		break;
+	case check_state_run:
+	case check_state_run_q:
+	case check_state_run_pq:
+		break; /* we will be called again upon completion */
+	case check_state_check_result:
+		sh->check_state = check_state_idle;
+
+		/* handle a successful check operation, if parity is correct
+		 * we are done.  Otherwise update the mismatch count and repair
+		 * parity if !MD_RECOVERY_CHECK
+		 */
+		if (sh->ops.zero_sum_result == 0) {
+			/* both parities are correct */
+			if (!s->failed)
+				set_bit(STRIPE_INSYNC, &sh->state);
+			else {
+				/* in contrast to the raid5 case we can validate
+				 * parity, but still have a failure to write
+				 * back
+				 */
+				sh->check_state = check_state_compute_result;
+				/* Returning at this point means that we may go
+				 * off and bring p and/or q uptodate again so
+				 * we make sure to check zero_sum_result again
+				 * to verify if p or q need writeback
+				 */
+			}
+		} else {
+			conf->mddev->resync_mismatches += STRIPE_SECTORS;
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+				/* don't try to repair!! */
+				set_bit(STRIPE_INSYNC, &sh->state);
+			else {
+				int *target = &sh->ops.target;
+
+				sh->ops.target = -1;
+				sh->ops.target2 = -1;
+				sh->check_state = check_state_compute_run;
+				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+				if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) {
+					set_bit(R5_Wantcompute,
+						&sh->dev[pd_idx].flags);
+					*target = pd_idx;
+					target = &sh->ops.target2;
+					s->uptodate++;
+				}
+				if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) {
+					set_bit(R5_Wantcompute,
+						&sh->dev[qd_idx].flags);
+					*target = qd_idx;
+					s->uptodate++;
+				}
+			}
+		}
+		break;
+	case check_state_compute_run:
+		break;
+	default:
+		printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
+		       __func__, sh->check_state,
+		       (unsigned long long) sh->sector);
+		BUG();
 	}
 }
 
@@ -2666,6 +2832,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 		if (i != sh->pd_idx && i != sh->qd_idx) {
 			int dd_idx, j;
 			struct stripe_head *sh2;
+			struct async_submit_ctl submit;
 
 			sector_t bn = compute_blocknr(sh, i, 1);
 			sector_t s = raid5_compute_sector(conf, bn, 0,
@@ -2685,9 +2852,10 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 			}
 
 			/* place all the copies on one channel */
+			init_async_submit(&submit, 0, tx, NULL, NULL, NULL);
 			tx = async_memcpy(sh2->dev[dd_idx].page,
-				sh->dev[i].page, 0, 0, STRIPE_SIZE,
-				ASYNC_TX_DEP_ACK, tx, NULL, NULL);
+					  sh->dev[i].page, 0, 0, STRIPE_SIZE,
+					  &submit);
 
 			set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
 			set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
@@ -2974,7 +3142,7 @@ static bool handle_stripe5(struct stripe_head *sh)
 		/* Need to write out all blocks after computing parity */
 		sh->disks = conf->raid_disks;
 		stripe_set_idx(sh->sector, conf, 0, sh);
-		schedule_reconstruction5(sh, &s, 1, 1);
+		schedule_reconstruction(sh, &s, 1, 1);
 	} else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
 		atomic_dec(&conf->reshape_stripes);
@@ -2994,7 +3162,7 @@ static bool handle_stripe5(struct stripe_head *sh)
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
 	if (s.ops_request)
-		raid5_run_ops(sh, s.ops_request);
+		raid_run_ops(sh, s.ops_request);
 
 	ops_run_io(sh, &s);
 
@@ -3003,7 +3171,7 @@ static bool handle_stripe5(struct stripe_head *sh)
 	return blocked_rdev == NULL;
 }
 
-static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
+static bool handle_stripe6(struct stripe_head *sh)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int disks = sh->disks;
@@ -3015,9 +3183,10 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	mdk_rdev_t *blocked_rdev = NULL;
 
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
-		"pd_idx=%d, qd_idx=%d\n",
+		"pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
 	       (unsigned long long)sh->sector, sh->state,
-	       atomic_read(&sh->count), pd_idx, qd_idx);
+	       atomic_read(&sh->count), pd_idx, qd_idx,
+	       sh->check_state, sh->reconstruct_state);
 	memset(&s, 0, sizeof(s));
 
 	spin_lock(&sh->lock);
@@ -3037,35 +3206,26 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 
 		pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
 			i, dev->flags, dev->toread, dev->towrite, dev->written);
-		/* maybe we can reply to a read */
-		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
-			struct bio *rbi, *rbi2;
-			pr_debug("Return read for disc %d\n", i);
-			spin_lock_irq(&conf->device_lock);
-			rbi = dev->toread;
-			dev->toread = NULL;
-			if (test_and_clear_bit(R5_Overlap, &dev->flags))
-				wake_up(&conf->wait_for_overlap);
-			spin_unlock_irq(&conf->device_lock);
-			while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
-				copy_data(0, rbi, dev->page, dev->sector);
-				rbi2 = r5_next_bio(rbi, dev->sector);
-				spin_lock_irq(&conf->device_lock);
-				if (!raid5_dec_bi_phys_segments(rbi)) {
-					rbi->bi_next = return_bi;
-					return_bi = rbi;
-				}
-				spin_unlock_irq(&conf->device_lock);
-				rbi = rbi2;
-			}
-		}
+		/* maybe we can reply to a read
+		 *
+		 * new wantfill requests are only permitted while
+		 * ops_complete_biofill is guaranteed to be inactive
+		 */
+		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
+		    !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
+			set_bit(R5_Wantfill, &dev->flags);
 
 		/* now count some things */
 		if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
 		if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
+		if (test_bit(R5_Wantcompute, &dev->flags)) {
+			s.compute++;
+			BUG_ON(s.compute > 2);
+		}
 
-
-		if (dev->toread)
+		if (test_bit(R5_Wantfill, &dev->flags)) {
+			s.to_fill++;
+		} else if (dev->toread)
 			s.to_read++;
 		if (dev->towrite) {
 			s.to_write++;
@@ -3106,6 +3266,11 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 		blocked_rdev = NULL;
 	}
 
+	if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+		set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+		set_bit(STRIPE_BIOFILL_RUN, &sh->state);
+	}
+
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
@@ -3146,19 +3311,62 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	 * or to load a block that is being partially written.
 	 */
 	if (s.to_read || s.non_overwrite || (s.to_write && s.failed) ||
-	    (s.syncing && (s.uptodate < disks)) || s.expanding)
+	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
 		handle_stripe_fill6(sh, &s, &r6s, disks);
 
-	/* now to consider writing and what else, if anything should be read */
-	if (s.to_write)
+	/* Now we check to see if any write operations have recently
+	 * completed
+	 */
+	if (sh->reconstruct_state == reconstruct_state_drain_result) {
+		int qd_idx = sh->qd_idx;
+
+		sh->reconstruct_state = reconstruct_state_idle;
+		/* All the 'written' buffers and the parity blocks are ready to
+		 * be written back to disk
+		 */
+		BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
+		BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[qd_idx].flags));
+		for (i = disks; i--; ) {
+			dev = &sh->dev[i];
+			if (test_bit(R5_LOCKED, &dev->flags) &&
+			    (i == sh->pd_idx || i == qd_idx ||
+			     dev->written)) {
+				pr_debug("Writing block %d\n", i);
+				BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
+				set_bit(R5_Wantwrite, &dev->flags);
+				if (!test_bit(R5_Insync, &dev->flags) ||
+				    ((i == sh->pd_idx || i == qd_idx) &&
+				      s.failed == 0))
+					set_bit(STRIPE_INSYNC, &sh->state);
+			}
+		}
+		if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+			atomic_dec(&conf->preread_active_stripes);
+			if (atomic_read(&conf->preread_active_stripes) <
+				IO_THRESHOLD)
+				md_wakeup_thread(conf->mddev->thread);
+		}
+	}
+
+	/* Now to consider new write requests and what else, if anything
+	 * should be read.  We do not handle new writes when:
+	 * 1/ A 'write' operation (copy+gen_syndrome) is already in flight.
+	 * 2/ A 'check' operation is in flight, as it may clobber the parity
+	 *    block.
+	 */
+	if (s.to_write && !sh->reconstruct_state && !sh->check_state)
 		handle_stripe_dirtying6(conf, sh, &s, &r6s, disks);
 
 	/* maybe we need to check and possibly fix the parity for this stripe
 	 * Any reads will already have been scheduled, so we just see if enough
-	 * data is available
+	 * data is available.  The parity check is held off while parity
+	 * dependent operations are in flight.
 	 */
-	if (s.syncing && s.locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state))
-		handle_parity_checks6(conf, sh, &s, &r6s, tmp_page, disks);
+	if (sh->check_state ||
+	    (s.syncing && s.locked == 0 &&
+	     !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
+	     !test_bit(STRIPE_INSYNC, &sh->state)))
+		handle_parity_checks6(conf, sh, &s, &r6s, disks);
 
 	if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,1);
@@ -3179,15 +3387,29 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 					set_bit(R5_Wantwrite, &dev->flags);
 					set_bit(R5_ReWrite, &dev->flags);
 					set_bit(R5_LOCKED, &dev->flags);
+					s.locked++;
 				} else {
 					/* let's read it back */
 					set_bit(R5_Wantread, &dev->flags);
 					set_bit(R5_LOCKED, &dev->flags);
+					s.locked++;
 				}
 			}
 		}
 
-	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
+	/* Finish reconstruct operations initiated by the expansion process */
+	if (sh->reconstruct_state == reconstruct_state_result) {
+		sh->reconstruct_state = reconstruct_state_idle;
+		clear_bit(STRIPE_EXPANDING, &sh->state);
+		for (i = conf->raid_disks; i--; ) {
+			set_bit(R5_Wantwrite, &sh->dev[i].flags);
+			set_bit(R5_LOCKED, &sh->dev[i].flags);
+			s.locked++;
+		}
+	}
+
+	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
+	    !sh->reconstruct_state) {
 		struct stripe_head *sh2
 			= get_active_stripe(conf, sh->sector, 1, 1, 1);
 		if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
@@ -3208,14 +3430,8 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 		/* Need to write out all blocks after computing P&Q */
 		sh->disks = conf->raid_disks;
 		stripe_set_idx(sh->sector, conf, 0, sh);
-		compute_parity6(sh, RECONSTRUCT_WRITE);
-		for (i = conf->raid_disks ; i-- ;  ) {
-			set_bit(R5_LOCKED, &sh->dev[i].flags);
-			s.locked++;
-			set_bit(R5_Wantwrite, &sh->dev[i].flags);
-		}
-		clear_bit(STRIPE_EXPANDING, &sh->state);
-	} else if (s.expanded) {
+		schedule_reconstruction(sh, &s, 1, 1);
+	} else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
 		atomic_dec(&conf->reshape_stripes);
 		wake_up(&conf->wait_for_overlap);
@@ -3233,6 +3449,9 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	if (unlikely(blocked_rdev))
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
+	if (s.ops_request)
+		raid_run_ops(sh, s.ops_request);
+
 	ops_run_io(sh, &s);
 
 	return_io(return_bi);
@@ -3241,16 +3460,14 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 }
 
 /* returns true if the stripe was handled */
-static bool handle_stripe(struct stripe_head *sh, struct page *tmp_page)
+static bool handle_stripe(struct stripe_head *sh)
 {
 	if (sh->raid_conf->level == 6)
-		return handle_stripe6(sh, tmp_page);
+		return handle_stripe6(sh);
 	else
 		return handle_stripe5(sh);
 }
 
-
-
 static void raid5_activate_delayed(raid5_conf_t *conf)
 {
 	if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
@@ -4061,7 +4278,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 	spin_unlock(&sh->lock);
 
 	/* wait for any blocked device to be handled */
-	while(unlikely(!handle_stripe(sh, NULL)))
+	while (unlikely(!handle_stripe(sh)))
 		;
 	release_stripe(sh);
 
@@ -4118,7 +4335,7 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
 			return handled;
 		}
 
-		handle_stripe(sh, NULL);
+		handle_stripe(sh);
 		release_stripe(sh);
 		handled++;
 	}
@@ -4132,6 +4349,36 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
 	return handled;
 }
 
+#ifdef CONFIG_MULTICORE_RAID456
+static void __process_stripe(void *param, async_cookie_t cookie)
+{
+	struct stripe_head *sh = param;
+
+	handle_stripe(sh);
+	release_stripe(sh);
+}
+
+static void process_stripe(struct stripe_head *sh, struct list_head *domain)
+{
+	async_schedule_domain(__process_stripe, sh, domain);
+}
+
+static void synchronize_stripe_processing(struct list_head *domain)
+{
+	async_synchronize_full_domain(domain);
+}
+#else
+static void process_stripe(struct stripe_head *sh, struct list_head *domain)
+{
+	handle_stripe(sh);
+	release_stripe(sh);
+	cond_resched();
+}
+
+static void synchronize_stripe_processing(struct list_head *domain)
+{
+}
+#endif
 
 
 /*
@@ -4146,6 +4393,7 @@ static void raid5d(mddev_t *mddev)
 	struct stripe_head *sh;
 	raid5_conf_t *conf = mddev->private;
 	int handled;
+	LIST_HEAD(raid_domain);
 
 	pr_debug("+++ raid5d active\n");
 
@@ -4182,8 +4430,7 @@ static void raid5d(mddev_t *mddev)
 		spin_unlock_irq(&conf->device_lock);
 		
 		handled++;
-		handle_stripe(sh, conf->spare_page);
-		release_stripe(sh);
+		process_stripe(sh, &raid_domain);
 
 		spin_lock_irq(&conf->device_lock);
 	}
@@ -4191,6 +4438,7 @@ static void raid5d(mddev_t *mddev)
 
 	spin_unlock_irq(&conf->device_lock);
 
+	synchronize_stripe_processing(&raid_domain);
 	async_tx_issue_pending_all();
 	unplug_slaves(mddev);
 
@@ -4323,15 +4571,118 @@ raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks)
 	return sectors * (raid_disks - conf->max_degraded);
 }
 
+static void raid5_free_percpu(raid5_conf_t *conf)
+{
+	struct raid5_percpu *percpu;
+	unsigned long cpu;
+
+	if (!conf->percpu)
+		return;
+
+	get_online_cpus();
+	for_each_possible_cpu(cpu) {
+		percpu = per_cpu_ptr(conf->percpu, cpu);
+		safe_put_page(percpu->spare_page);
+		kfree(percpu->scribble);
+	}
+#ifdef CONFIG_HOTPLUG_CPU
+	unregister_cpu_notifier(&conf->cpu_notify);
+#endif
+	put_online_cpus();
+
+	free_percpu(conf->percpu);
+}
+
 static void free_conf(raid5_conf_t *conf)
 {
 	shrink_stripes(conf);
-	safe_put_page(conf->spare_page);
+	raid5_free_percpu(conf);
 	kfree(conf->disks);
 	kfree(conf->stripe_hashtbl);
 	kfree(conf);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
+			      void *hcpu)
+{
+	raid5_conf_t *conf = container_of(nfb, raid5_conf_t, cpu_notify);
+	long cpu = (long)hcpu;
+	struct raid5_percpu *percpu = per_cpu_ptr(conf->percpu, cpu);
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		if (conf->level == 6 && !percpu->spare_page)
+			percpu->spare_page = alloc_page(GFP_KERNEL);
+		if (!percpu->scribble)
+			percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+		if (!percpu->scribble ||
+		    (conf->level == 6 && !percpu->spare_page)) {
+			safe_put_page(percpu->spare_page);
+			kfree(percpu->scribble);
+			pr_err("%s: failed memory allocation for cpu%ld\n",
+			       __func__, cpu);
+			return NOTIFY_BAD;
+		}
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		safe_put_page(percpu->spare_page);
+		kfree(percpu->scribble);
+		percpu->spare_page = NULL;
+		percpu->scribble = NULL;
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+#endif
+
+static int raid5_alloc_percpu(raid5_conf_t *conf)
+{
+	unsigned long cpu;
+	struct page *spare_page;
+	struct raid5_percpu *allcpus;
+	void *scribble;
+	int err;
+
+	allcpus = alloc_percpu(struct raid5_percpu);
+	if (!allcpus)
+		return -ENOMEM;
+	conf->percpu = allcpus;
+
+	get_online_cpus();
+	err = 0;
+	for_each_present_cpu(cpu) {
+		if (conf->level == 6) {
+			spare_page = alloc_page(GFP_KERNEL);
+			if (!spare_page) {
+				err = -ENOMEM;
+				break;
+			}
+			per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
+		}
+		scribble = kmalloc(scribble_len(conf->raid_disks), GFP_KERNEL);
+		if (!scribble) {
+			err = -ENOMEM;
+			break;
+		}
+		per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
+	}
+#ifdef CONFIG_HOTPLUG_CPU
+	conf->cpu_notify.notifier_call = raid456_cpu_notify;
+	conf->cpu_notify.priority = 0;
+	if (err == 0)
+		err = register_cpu_notifier(&conf->cpu_notify);
+#endif
+	put_online_cpus();
+
+	return err;
+}
+
 static raid5_conf_t *setup_conf(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
@@ -4373,6 +4724,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 		goto abort;
 
 	conf->raid_disks = mddev->raid_disks;
+	conf->scribble_len = scribble_len(conf->raid_disks);
 	if (mddev->reshape_position == MaxSector)
 		conf->previous_raid_disks = mddev->raid_disks;
 	else
@@ -4388,11 +4740,10 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 	if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
 		goto abort;
 
-	if (mddev->new_level == 6) {
-		conf->spare_page = alloc_page(GFP_KERNEL);
-		if (!conf->spare_page)
-			goto abort;
-	}
+	conf->level = mddev->new_level;
+	if (raid5_alloc_percpu(conf) != 0)
+		goto abort;
+
 	spin_lock_init(&conf->device_lock);
 	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 9459689c4ea..2390e0e83da 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -2,6 +2,7 @@
 #define _RAID5_H
 
 #include <linux/raid/xor.h>
+#include <linux/dmaengine.h>
 
 /*
  *
@@ -175,7 +176,9 @@
  */
 enum check_states {
 	check_state_idle = 0,
-	check_state_run, /* parity check */
+	check_state_run, /* xor parity check */
+	check_state_run_q, /* q-parity check */
+	check_state_run_pq, /* pq dual parity check */
 	check_state_check_result,
 	check_state_compute_run, /* parity repair */
 	check_state_compute_result,
@@ -215,8 +218,8 @@ struct stripe_head {
 	 * @target - STRIPE_OP_COMPUTE_BLK target
 	 */
 	struct stripe_operations {
-		int		   target;
-		u32		   zero_sum_result;
+		int 		     target, target2;
+		enum sum_check_flags zero_sum_result;
 	} ops;
 	struct r5dev {
 		struct bio	req;
@@ -298,7 +301,7 @@ struct r6_state {
 #define STRIPE_OP_COMPUTE_BLK	1
 #define STRIPE_OP_PREXOR	2
 #define STRIPE_OP_BIODRAIN	3
-#define STRIPE_OP_POSTXOR	4
+#define STRIPE_OP_RECONSTRUCT	4
 #define STRIPE_OP_CHECK	5
 
 /*
@@ -385,8 +388,21 @@ struct raid5_private_data {
 					    * (fresh device added).
 					    * Cleared when a sync completes.
 					    */
-
-	struct page 		*spare_page; /* Used when checking P/Q in raid6 */
+	/* per cpu variables */
+	struct raid5_percpu {
+		struct page	*spare_page; /* Used when checking P/Q in raid6 */
+		void		*scribble;   /* space for constructing buffer
+					      * lists and performing address
+					      * conversions
+					      */
+	} *percpu;
+	size_t			scribble_len; /* size of scribble region must be
+					       * associated with conf to handle
+					       * cpu hotplug while reshaping
+					       */
+#ifdef CONFIG_HOTPLUG_CPU
+	struct notifier_block	cpu_notify;
+#endif
 
 	/*
 	 * Free stripes pool
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 7b603e4b41d..5e10d3663ab 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -576,6 +576,7 @@ atmci_submit_data_dma(struct atmel_mci *host, struct mmc_data *data)
 	struct scatterlist		*sg;
 	unsigned int			i;
 	enum dma_data_direction		direction;
+	unsigned int			sglen;
 
 	/*
 	 * We don't do DMA on "complex" transfers, i.e. with
@@ -605,11 +606,14 @@ atmci_submit_data_dma(struct atmel_mci *host, struct mmc_data *data)
 	else
 		direction = DMA_TO_DEVICE;
 
+	sglen = dma_map_sg(&host->pdev->dev, data->sg, data->sg_len, direction);
+	if (sglen != data->sg_len)
+		goto unmap_exit;
 	desc = chan->device->device_prep_slave_sg(chan,
 			data->sg, data->sg_len, direction,
 			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
-		return -ENOMEM;
+		goto unmap_exit;
 
 	host->dma.data_desc = desc;
 	desc->callback = atmci_dma_complete;
@@ -620,6 +624,9 @@ atmci_submit_data_dma(struct atmel_mci *host, struct mmc_data *data)
 	chan->device->device_issue_pending(chan);
 
 	return 0;
+unmap_exit:
+	dma_unmap_sg(&host->pdev->dev, data->sg, sglen, direction);
+	return -ENOMEM;
 }
 
 #else /* CONFIG_MMC_ATMELMCI_DMA */
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 5fc2ef8d97f..a1c486a88e8 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -58,25 +58,60 @@ struct dma_chan_ref {
  * array.
  * @ASYNC_TX_ACK: immediately ack the descriptor, precludes setting up a
  * dependency chain
- * @ASYNC_TX_DEP_ACK: ack the dependency descriptor.  Useful for chaining.
+ * @ASYNC_TX_FENCE: specify that the next operation in the dependency
+ * chain uses this operation's result as an input
  */
 enum async_tx_flags {
 	ASYNC_TX_XOR_ZERO_DST	 = (1 << 0),
 	ASYNC_TX_XOR_DROP_DST	 = (1 << 1),
-	ASYNC_TX_ACK		 = (1 << 3),
-	ASYNC_TX_DEP_ACK	 = (1 << 4),
+	ASYNC_TX_ACK		 = (1 << 2),
+	ASYNC_TX_FENCE		 = (1 << 3),
+};
+
+/**
+ * struct async_submit_ctl - async_tx submission/completion modifiers
+ * @flags: submission modifiers
+ * @depend_tx: parent dependency of the current operation being submitted
+ * @cb_fn: callback routine to run at operation completion
+ * @cb_param: parameter for the callback routine
+ * @scribble: caller provided space for dma/page address conversions
+ */
+struct async_submit_ctl {
+	enum async_tx_flags flags;
+	struct dma_async_tx_descriptor *depend_tx;
+	dma_async_tx_callback cb_fn;
+	void *cb_param;
+	void *scribble;
 };
 
 #ifdef CONFIG_DMA_ENGINE
 #define async_tx_issue_pending_all dma_issue_pending_all
+
+/**
+ * async_tx_issue_pending - send pending descriptor to the hardware channel
+ * @tx: descriptor handle to retrieve hardware context
+ *
+ * Note: any dependent operations will have already been issued by
+ * async_tx_channel_switch, or (in the case of no channel switch) will
+ * be already pending on this channel.
+ */
+static inline void async_tx_issue_pending(struct dma_async_tx_descriptor *tx)
+{
+	if (likely(tx)) {
+		struct dma_chan *chan = tx->chan;
+		struct dma_device *dma = chan->device;
+
+		dma->device_issue_pending(chan);
+	}
+}
 #ifdef CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL
 #include <asm/async_tx.h>
 #else
 #define async_tx_find_channel(dep, type, dst, dst_count, src, src_count, len) \
 	 __async_tx_find_channel(dep, type)
 struct dma_chan *
-__async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
-	enum dma_transaction_type tx_type);
+__async_tx_find_channel(struct async_submit_ctl *submit,
+			enum dma_transaction_type tx_type);
 #endif /* CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL */
 #else
 static inline void async_tx_issue_pending_all(void)
@@ -84,10 +119,16 @@ static inline void async_tx_issue_pending_all(void)
 	do { } while (0);
 }
 
+static inline void async_tx_issue_pending(struct dma_async_tx_descriptor *tx)
+{
+	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,
-	struct page **src, int src_count, size_t len)
+async_tx_find_channel(struct async_submit_ctl *submit,
+		      enum dma_transaction_type tx_type, struct page **dst,
+		      int dst_count, struct page **src, int src_count,
+		      size_t len)
 {
 	return NULL;
 }
@@ -99,46 +140,70 @@ async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
  * @cb_fn_param: parameter to pass to the callback routine
  */
 static inline void
-async_tx_sync_epilog(dma_async_tx_callback cb_fn, void *cb_fn_param)
+async_tx_sync_epilog(struct async_submit_ctl *submit)
 {
-	if (cb_fn)
-		cb_fn(cb_fn_param);
+	if (submit->cb_fn)
+		submit->cb_fn(submit->cb_param);
 }
 
-void
-async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx,
-	enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_fn_param);
+typedef union {
+	unsigned long addr;
+	struct page *page;
+	dma_addr_t dma;
+} addr_conv_t;
+
+static inline void
+init_async_submit(struct async_submit_ctl *args, enum async_tx_flags flags,
+		  struct dma_async_tx_descriptor *tx,
+		  dma_async_tx_callback cb_fn, void *cb_param,
+		  addr_conv_t *scribble)
+{
+	args->flags = flags;
+	args->depend_tx = tx;
+	args->cb_fn = cb_fn;
+	args->cb_param = cb_param;
+	args->scribble = scribble;
+}
+
+void async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx,
+		     struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_xor(struct page *dest, struct page **src_list, unsigned int offset,
-	int src_cnt, size_t len, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_fn_param);
+	  int src_cnt, size_t len, struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
-async_xor_zero_sum(struct page *dest, struct page **src_list,
-	unsigned int offset, int src_cnt, size_t len,
-	u32 *result, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_fn_param);
+async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
+	      int src_cnt, size_t len, enum sum_check_flags *result,
+	      struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
-	unsigned int src_offset, size_t len, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_fn_param);
+	     unsigned int src_offset, size_t len,
+	     struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_memset(struct page *dest, int val, unsigned int offset,
-	size_t len, enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_fn_param);
+	     size_t len, struct async_submit_ctl *submit);
+
+struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit);
+
+struct dma_async_tx_descriptor *
+async_gen_syndrome(struct page **blocks, unsigned int offset, int src_cnt,
+		   size_t len, struct async_submit_ctl *submit);
+
+struct dma_async_tx_descriptor *
+async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt,
+		   size_t len, enum sum_check_flags *pqres, struct page *spare,
+		   struct async_submit_ctl *submit);
+
+struct dma_async_tx_descriptor *
+async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb,
+			struct page **ptrs, struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
-async_trigger_callback(enum async_tx_flags flags,
-	struct dma_async_tx_descriptor *depend_tx,
-	dma_async_tx_callback cb_fn, void *cb_fn_param);
+async_raid6_datap_recov(int src_num, size_t bytes, int faila,
+			struct page **ptrs, struct async_submit_ctl *submit);
 
 void async_tx_quiesce(struct dma_async_tx_descriptor **tx);
 #endif /* _ASYNC_TX_H_ */
diff --git a/include/linux/dca.h b/include/linux/dca.h
index 9c20c7e87d0..d27a7a05718 100644
--- a/include/linux/dca.h
+++ b/include/linux/dca.h
@@ -20,6 +20,9 @@
  */
 #ifndef DCA_H
 #define DCA_H
+
+#include <linux/pci.h>
+
 /* DCA Provider API */
 
 /* DCA Notifier Interface */
@@ -36,6 +39,12 @@ struct dca_provider {
 	int			 id;
 };
 
+struct dca_domain {
+	struct list_head	node;
+	struct list_head	dca_providers;
+	struct pci_bus		*pci_rc;
+};
+
 struct dca_ops {
 	int	(*add_requester)    (struct dca_provider *, struct device *);
 	int	(*remove_requester) (struct dca_provider *, struct device *);
@@ -47,7 +56,7 @@ struct dca_ops {
 struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size);
 void free_dca_provider(struct dca_provider *dca);
 int register_dca_provider(struct dca_provider *dca, struct device *dev);
-void unregister_dca_provider(struct dca_provider *dca);
+void unregister_dca_provider(struct dca_provider *dca, struct device *dev);
 
 static inline void *dca_priv(struct dca_provider *dca)
 {
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index ffefba81c81..2b9f2ac7ed6 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -48,19 +48,20 @@ enum dma_status {
 
 /**
  * enum dma_transaction_type - DMA transaction types/indexes
+ *
+ * Note: The DMA_ASYNC_TX capability is not to be set by drivers.  It is
+ * automatically set as dma devices are registered.
  */
 enum dma_transaction_type {
 	DMA_MEMCPY,
 	DMA_XOR,
-	DMA_PQ_XOR,
-	DMA_DUAL_XOR,
-	DMA_PQ_UPDATE,
-	DMA_ZERO_SUM,
-	DMA_PQ_ZERO_SUM,
+	DMA_PQ,
+	DMA_XOR_VAL,
+	DMA_PQ_VAL,
 	DMA_MEMSET,
-	DMA_MEMCPY_CRC32C,
 	DMA_INTERRUPT,
 	DMA_PRIVATE,
+	DMA_ASYNC_TX,
 	DMA_SLAVE,
 };
 
@@ -70,18 +71,25 @@ enum dma_transaction_type {
 
 /**
  * enum dma_ctrl_flags - DMA flags to augment operation preparation,
- * 	control completion, and communicate status.
+ *  control completion, and communicate status.
  * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of
- * 	this transaction
+ *  this transaction
  * @DMA_CTRL_ACK - the descriptor cannot be reused until the client
- * 	acknowledges receipt, i.e. has has a chance to establish any
- * 	dependency chains
+ *  acknowledges receipt, i.e. has has a chance to establish any dependency
+ *  chains
  * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s)
  * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s)
  * @DMA_COMPL_SRC_UNMAP_SINGLE - set to do the source dma-unmapping as single
  * 	(if not set, do the source dma-unmapping as page)
  * @DMA_COMPL_DEST_UNMAP_SINGLE - set to do the destination dma-unmapping as single
  * 	(if not set, do the destination dma-unmapping as page)
+ * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q
+ * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P
+ * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as
+ *  sources that were the result of a previous operation, in the case of a PQ
+ *  operation it continues the calculation with new sources
+ * @DMA_PREP_FENCE - tell the driver that subsequent operations depend
+ *  on the result of this operation
  */
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),
@@ -90,9 +98,32 @@ enum dma_ctrl_flags {
 	DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3),
 	DMA_COMPL_SRC_UNMAP_SINGLE = (1 << 4),
 	DMA_COMPL_DEST_UNMAP_SINGLE = (1 << 5),
+	DMA_PREP_PQ_DISABLE_P = (1 << 6),
+	DMA_PREP_PQ_DISABLE_Q = (1 << 7),
+	DMA_PREP_CONTINUE = (1 << 8),
+	DMA_PREP_FENCE = (1 << 9),
 };
 
 /**
+ * enum sum_check_bits - bit position of pq_check_flags
+ */
+enum sum_check_bits {
+	SUM_CHECK_P = 0,
+	SUM_CHECK_Q = 1,
+};
+
+/**
+ * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations
+ * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise
+ * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise
+ */
+enum sum_check_flags {
+	SUM_CHECK_P_RESULT = (1 << SUM_CHECK_P),
+	SUM_CHECK_Q_RESULT = (1 << SUM_CHECK_Q),
+};
+
+
+/**
  * dma_cap_mask_t - capabilities bitmap modeled after cpumask_t.
  * See linux/cpumask.h
  */
@@ -180,8 +211,6 @@ typedef void (*dma_async_tx_callback)(void *dma_async_param);
  * @flags: flags to augment operation preparation, control completion, and
  * 	communicate status
  * @phys: physical address of the descriptor
- * @tx_list: driver common field for operations that require multiple
- *	descriptors
  * @chan: target channel for this operation
  * @tx_submit: set the prepared descriptor(s) to be executed by the engine
  * @callback: routine to call after this operation is complete
@@ -195,7 +224,6 @@ struct dma_async_tx_descriptor {
 	dma_cookie_t cookie;
 	enum dma_ctrl_flags flags; /* not a 'long' to pack with cookie */
 	dma_addr_t phys;
-	struct list_head tx_list;
 	struct dma_chan *chan;
 	dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx);
 	dma_async_tx_callback callback;
@@ -213,6 +241,11 @@ struct dma_async_tx_descriptor {
  * @global_node: list_head for global dma_device_list
  * @cap_mask: one or more dma_capability flags
  * @max_xor: maximum number of xor sources, 0 if no capability
+ * @max_pq: maximum number of PQ sources and PQ-continue capability
+ * @copy_align: alignment shift for memcpy operations
+ * @xor_align: alignment shift for xor operations
+ * @pq_align: alignment shift for pq operations
+ * @fill_align: alignment shift for memset operations
  * @dev_id: unique device ID
  * @dev: struct device reference for dma mapping api
  * @device_alloc_chan_resources: allocate resources and return the
@@ -220,7 +253,9 @@ struct dma_async_tx_descriptor {
  * @device_free_chan_resources: release DMA channel's resources
  * @device_prep_dma_memcpy: prepares a memcpy operation
  * @device_prep_dma_xor: prepares a xor operation
- * @device_prep_dma_zero_sum: prepares a zero_sum operation
+ * @device_prep_dma_xor_val: prepares a xor validation operation
+ * @device_prep_dma_pq: prepares a pq operation
+ * @device_prep_dma_pq_val: prepares a pqzero_sum operation
  * @device_prep_dma_memset: prepares a memset operation
  * @device_prep_dma_interrupt: prepares an end of chain interrupt operation
  * @device_prep_slave_sg: prepares a slave dma operation
@@ -235,7 +270,13 @@ struct dma_device {
 	struct list_head channels;
 	struct list_head global_node;
 	dma_cap_mask_t  cap_mask;
-	int max_xor;
+	unsigned short max_xor;
+	unsigned short max_pq;
+	u8 copy_align;
+	u8 xor_align;
+	u8 pq_align;
+	u8 fill_align;
+	#define DMA_HAS_PQ_CONTINUE (1 << 15)
 
 	int dev_id;
 	struct device *dev;
@@ -249,9 +290,17 @@ struct dma_device {
 	struct dma_async_tx_descriptor *(*device_prep_dma_xor)(
 		struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		unsigned int src_cnt, size_t len, unsigned long flags);
-	struct dma_async_tx_descriptor *(*device_prep_dma_zero_sum)(
+	struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)(
 		struct dma_chan *chan, dma_addr_t *src,	unsigned int src_cnt,
-		size_t len, u32 *result, unsigned long flags);
+		size_t len, enum sum_check_flags *result, unsigned long flags);
+	struct dma_async_tx_descriptor *(*device_prep_dma_pq)(
+		struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
+		unsigned int src_cnt, const unsigned char *scf,
+		size_t len, unsigned long flags);
+	struct dma_async_tx_descriptor *(*device_prep_dma_pq_val)(
+		struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
+		unsigned int src_cnt, const unsigned char *scf, size_t len,
+		enum sum_check_flags *pqres, unsigned long flags);
 	struct dma_async_tx_descriptor *(*device_prep_dma_memset)(
 		struct dma_chan *chan, dma_addr_t dest, int value, size_t len,
 		unsigned long flags);
@@ -270,6 +319,96 @@ struct dma_device {
 	void (*device_issue_pending)(struct dma_chan *chan);
 };
 
+static inline bool dmaengine_check_align(u8 align, size_t off1, size_t off2, size_t len)
+{
+	size_t mask;
+
+	if (!align)
+		return true;
+	mask = (1 << align) - 1;
+	if (mask & (off1 | off2 | len))
+		return false;
+	return true;
+}
+
+static inline bool is_dma_copy_aligned(struct dma_device *dev, size_t off1,
+				       size_t off2, size_t len)
+{
+	return dmaengine_check_align(dev->copy_align, off1, off2, len);
+}
+
+static inline bool is_dma_xor_aligned(struct dma_device *dev, size_t off1,
+				      size_t off2, size_t len)
+{
+	return dmaengine_check_align(dev->xor_align, off1, off2, len);
+}
+
+static inline bool is_dma_pq_aligned(struct dma_device *dev, size_t off1,
+				     size_t off2, size_t len)
+{
+	return dmaengine_check_align(dev->pq_align, off1, off2, len);
+}
+
+static inline bool is_dma_fill_aligned(struct dma_device *dev, size_t off1,
+				       size_t off2, size_t len)
+{
+	return dmaengine_check_align(dev->fill_align, off1, off2, len);
+}
+
+static inline void
+dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue)
+{
+	dma->max_pq = maxpq;
+	if (has_pq_continue)
+		dma->max_pq |= DMA_HAS_PQ_CONTINUE;
+}
+
+static inline bool dmaf_continue(enum dma_ctrl_flags flags)
+{
+	return (flags & DMA_PREP_CONTINUE) == DMA_PREP_CONTINUE;
+}
+
+static inline bool dmaf_p_disabled_continue(enum dma_ctrl_flags flags)
+{
+	enum dma_ctrl_flags mask = DMA_PREP_CONTINUE | DMA_PREP_PQ_DISABLE_P;
+
+	return (flags & mask) == mask;
+}
+
+static inline bool dma_dev_has_pq_continue(struct dma_device *dma)
+{
+	return (dma->max_pq & DMA_HAS_PQ_CONTINUE) == DMA_HAS_PQ_CONTINUE;
+}
+
+static unsigned short dma_dev_to_maxpq(struct dma_device *dma)
+{
+	return dma->max_pq & ~DMA_HAS_PQ_CONTINUE;
+}
+
+/* dma_maxpq - reduce maxpq in the face of continued operations
+ * @dma - dma device with PQ capability
+ * @flags - to check if DMA_PREP_CONTINUE and DMA_PREP_PQ_DISABLE_P are set
+ *
+ * When an engine does not support native continuation we need 3 extra
+ * source slots to reuse P and Q with the following coefficients:
+ * 1/ {00} * P : remove P from Q', but use it as a source for P'
+ * 2/ {01} * Q : use Q to continue Q' calculation
+ * 3/ {00} * Q : subtract Q from P' to cancel (2)
+ *
+ * In the case where P is disabled we only need 1 extra source:
+ * 1/ {01} * Q : use Q to continue Q' calculation
+ */
+static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags)
+{
+	if (dma_dev_has_pq_continue(dma) || !dmaf_continue(flags))
+		return dma_dev_to_maxpq(dma);
+	else if (dmaf_p_disabled_continue(flags))
+		return dma_dev_to_maxpq(dma) - 1;
+	else if (dmaf_continue(flags))
+		return dma_dev_to_maxpq(dma) - 3;
+	BUG();
+}
+
 /* --- public DMA engine API --- */
 
 #ifdef CONFIG_DMA_ENGINE
@@ -299,7 +438,11 @@ static inline void net_dmaengine_put(void)
 #ifdef CONFIG_ASYNC_TX_DMA
 #define async_dmaengine_get()	dmaengine_get()
 #define async_dmaengine_put()	dmaengine_put()
+#ifdef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH
+#define async_dma_find_channel(type) dma_find_channel(DMA_ASYNC_TX)
+#else
 #define async_dma_find_channel(type) dma_find_channel(type)
+#endif /* CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH */
 #else
 static inline void async_dmaengine_get(void)
 {
@@ -312,7 +455,7 @@ async_dma_find_channel(enum dma_transaction_type type)
 {
 	return NULL;
 }
-#endif
+#endif /* CONFIG_ASYNC_TX_DMA */
 
 dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan,
 	void *dest, void *src, size_t len);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 3b6b788fe2b..6f9623710f2 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2526,6 +2526,16 @@
 #define PCI_DEVICE_ID_INTEL_E7525_MCH	0x359e
 #define PCI_DEVICE_ID_INTEL_IOAT_CNB	0x360b
 #define PCI_DEVICE_ID_INTEL_FBD_CNB	0x360c
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF0	0x3710
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF1	0x3711
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF2	0x3712
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF3	0x3713
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF4	0x3714
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF5	0x3715
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF6	0x3716
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF7	0x3717
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF8	0x3718
+#define PCI_DEVICE_ID_INTEL_IOAT_JSF9	0x3719
 #define PCI_DEVICE_ID_INTEL_ICH10_0	0x3a14
 #define PCI_DEVICE_ID_INTEL_ICH10_1	0x3a16
 #define PCI_DEVICE_ID_INTEL_ICH10_2	0x3a18