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

Conflicts:
	include/linux/dmaengine.h

2 files changed, 199 insertions, 43 deletions

diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 5fc2ef8..866e61c 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -58,25 +58,57 @@ 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.
  */
 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),
+};
+
+/**
+ * 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 +116,16 @@ 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 +137,70 @@ 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/dmaengine.h b/include/linux/dmaengine.h
index ffefba8..1012f1a 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -52,11 +52,11 @@ enum dma_status {
 enum dma_transaction_type {
 	DMA_MEMCPY,
 	DMA_XOR,
-	DMA_PQ_XOR,
+	DMA_PQ,
 	DMA_DUAL_XOR,
 	DMA_PQ_UPDATE,
-	DMA_ZERO_SUM,
-	DMA_PQ_ZERO_SUM,
+	DMA_XOR_VAL,
+	DMA_PQ_VAL,
 	DMA_MEMSET,
 	DMA_MEMCPY_CRC32C,
 	DMA_INTERRUPT,
@@ -70,18 +70,23 @@ 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
  */
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),
@@ -90,9 +95,31 @@ 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),
 };
 
 /**
+ * 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
  */
@@ -213,6 +240,7 @@ 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
  * @dev_id: unique device ID
  * @dev: struct device reference for dma mapping api
  * @device_alloc_chan_resources: allocate resources and return the
@@ -220,7 +248,9 @@ 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 +265,9 @@ 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;
+	#define DMA_HAS_PQ_CONTINUE (1 << 15)
 
 	int dev_id;
 	struct device *dev;
@@ -249,9 +281,17 @@ 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 +310,60 @@ struct dma_device {
 	void (*device_issue_pending)(struct dma_chan *chan);
 };
 
+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