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

Conflicts:
	include/linux/dmaengine.h

7 files changed, 1021 insertions, 640 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 3b3c01b6f1e..912a51b5cbd 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -4,7 +4,7 @@
 
 menuconfig DMADEVICES
 	bool "DMA Engine support"
-	depends on !HIGHMEM64G && HAS_DMA
+	depends on HAS_DMA
 	help
 	  DMA engines can do asynchronous data transfers without
 	  involving the host CPU.  Currently, this framework can be
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 5a87384ea4f..96598479eec 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -644,8 +644,12 @@ int dma_async_device_register(struct dma_device *device)
 		!device->device_prep_dma_memcpy);
 	BUG_ON(dma_has_cap(DMA_XOR, device->cap_mask) &&
 		!device->device_prep_dma_xor);
-	BUG_ON(dma_has_cap(DMA_ZERO_SUM, device->cap_mask) &&
-		!device->device_prep_dma_zero_sum);
+	BUG_ON(dma_has_cap(DMA_XOR_VAL, device->cap_mask) &&
+		!device->device_prep_dma_xor_val);
+	BUG_ON(dma_has_cap(DMA_PQ, device->cap_mask) &&
+		!device->device_prep_dma_pq);
+	BUG_ON(dma_has_cap(DMA_PQ_VAL, device->cap_mask) &&
+		!device->device_prep_dma_pq_val);
 	BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) &&
 		!device->device_prep_dma_memset);
 	BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) &&
@@ -939,49 +943,24 @@ EXPORT_SYMBOL(dma_async_tx_descriptor_init);
 
 /* dma_wait_for_async_tx - spin wait for a transaction to complete
  * @tx: in-flight transaction to wait on
- *
- * This routine assumes that tx was obtained from a call to async_memcpy,
- * async_xor, async_memset, etc which ensures that tx is "in-flight" (prepped
- * and submitted).  Walking the parent chain is only meant to cover for DMA
- * drivers that do not implement the DMA_INTERRUPT capability and may race with
- * the driver's descriptor cleanup routine.
  */
 enum dma_status
 dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 {
-	enum dma_status status;
-	struct dma_async_tx_descriptor *iter;
-	struct dma_async_tx_descriptor *parent;
+	unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);
 
 	if (!tx)
 		return DMA_SUCCESS;
 
-	WARN_ONCE(tx->parent, "%s: speculatively walking dependency chain for"
-		  " %s\n", __func__, dma_chan_name(tx->chan));
-
-	/* poll through the dependency chain, return when tx is complete */
-	do {
-		iter = tx;
-
-		/* find the root of the unsubmitted dependency chain */
-		do {
-			parent = iter->parent;
-			if (!parent)
-				break;
-			else
-				iter = parent;
-		} while (parent);
-
-		/* there is a small window for ->parent == NULL and
-		 * ->cookie == -EBUSY
-		 */
-		while (iter->cookie == -EBUSY)
-			cpu_relax();
-
-		status = dma_sync_wait(iter->chan, iter->cookie);
-	} while (status == DMA_IN_PROGRESS || (iter != tx));
-
-	return status;
+	while (tx->cookie == -EBUSY) {
+		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
+			pr_err("%s timeout waiting for descriptor submission\n",
+				__func__);
+			return DMA_ERROR;
+		}
+		cpu_relax();
+	}
+	return dma_sync_wait(tx->chan, tx->cookie);
 }
 EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index fb7da5141e9..58e49e41c7a 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -43,6 +43,11 @@ module_param(xor_sources, uint, S_IRUGO);
 MODULE_PARM_DESC(xor_sources,
 		"Number of xor source buffers (default: 3)");
 
+static unsigned int pq_sources = 3;
+module_param(pq_sources, uint, S_IRUGO);
+MODULE_PARM_DESC(pq_sources,
+		"Number of p+q source buffers (default: 3)");
+
 /*
  * Initialization patterns. All bytes in the source buffer has bit 7
  * set, all bytes in the destination buffer has bit 7 cleared.
@@ -227,6 +232,7 @@ static int dmatest_func(void *data)
 	dma_cookie_t		cookie;
 	enum dma_status		status;
 	enum dma_ctrl_flags 	flags;
+	u8			pq_coefs[pq_sources];
 	int			ret;
 	int			src_cnt;
 	int			dst_cnt;
@@ -243,6 +249,11 @@ static int dmatest_func(void *data)
 	else if (thread->type == DMA_XOR) {
 		src_cnt = xor_sources | 1; /* force odd to ensure dst = src */
 		dst_cnt = 1;
+	} else if (thread->type == DMA_PQ) {
+		src_cnt = pq_sources | 1; /* force odd to ensure dst = src */
+		dst_cnt = 2;
+		for (i = 0; i < pq_sources; i++)
+			pq_coefs[i] = 1;
 	} else
 		goto err_srcs;
 
@@ -310,6 +321,15 @@ static int dmatest_func(void *data)
 						      dma_dsts[0] + dst_off,
 						      dma_srcs, xor_sources,
 						      len, flags);
+		else if (thread->type == DMA_PQ) {
+			dma_addr_t dma_pq[dst_cnt];
+
+			for (i = 0; i < dst_cnt; i++)
+				dma_pq[i] = dma_dsts[i] + dst_off;
+			tx = dev->device_prep_dma_pq(chan, dma_pq, dma_srcs,
+						     pq_sources, pq_coefs,
+						     len, flags);
+		}
 
 		if (!tx) {
 			for (i = 0; i < src_cnt; i++)
@@ -446,6 +466,8 @@ static int dmatest_add_threads(struct dmatest_chan *dtc, enum dma_transaction_ty
 		op = "copy";
 	else if (type == DMA_XOR)
 		op = "xor";
+	else if (type == DMA_PQ)
+		op = "pq";
 	else
 		return -EINVAL;
 
@@ -501,6 +523,10 @@ static int dmatest_add_channel(struct dma_chan *chan)
 		cnt = dmatest_add_threads(dtc, DMA_XOR);
 		thread_count += cnt > 0 ?: 0;
 	}
+	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
+		cnt = dmatest_add_threads(dtc, DMA_PQ);
+		thread_count += cnt > 0 ?: 0;
+	}
 
 	pr_info("dmatest: Started %u threads using %s\n",
 		thread_count, dma_chan_name(chan));
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 2f052265122..4496bc60666 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -660,9 +660,9 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 }
 
 static struct dma_async_tx_descriptor *
-iop_adma_prep_dma_zero_sum(struct dma_chan *chan, dma_addr_t *dma_src,
-			   unsigned int src_cnt, size_t len, u32 *result,
-			   unsigned long flags)
+iop_adma_prep_dma_xor_val(struct dma_chan *chan, dma_addr_t *dma_src,
+			  unsigned int src_cnt, size_t len, u32 *result,
+			  unsigned long flags)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
 	struct iop_adma_desc_slot *sw_desc, *grp_start;
@@ -906,7 +906,7 @@ out:
 
 #define IOP_ADMA_NUM_SRC_TEST 4 /* must be <= 15 */
 static int __devinit
-iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
+iop_adma_xor_val_self_test(struct iop_adma_device *device)
 {
 	int i, src_idx;
 	struct page *dest;
@@ -1002,7 +1002,7 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		PAGE_SIZE, DMA_TO_DEVICE);
 
 	/* skip zero sum if the capability is not present */
-	if (!dma_has_cap(DMA_ZERO_SUM, dma_chan->device->cap_mask))
+	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
 		goto free_resources;
 
 	/* zero sum the sources with the destintation page */
@@ -1016,10 +1016,10 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		dma_srcs[i] = dma_map_page(dma_chan->device->dev,
 					   zero_sum_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-	tx = iop_adma_prep_dma_zero_sum(dma_chan, dma_srcs,
-					IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
-					&zero_sum_result,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	tx = iop_adma_prep_dma_xor_val(dma_chan, dma_srcs,
+				       IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
+				       &zero_sum_result,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
 	cookie = iop_adma_tx_submit(tx);
 	iop_adma_issue_pending(dma_chan);
@@ -1072,10 +1072,10 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		dma_srcs[i] = dma_map_page(dma_chan->device->dev,
 					   zero_sum_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-	tx = iop_adma_prep_dma_zero_sum(dma_chan, dma_srcs,
-					IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
-					&zero_sum_result,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	tx = iop_adma_prep_dma_xor_val(dma_chan, dma_srcs,
+				       IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
+				       &zero_sum_result,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
 	cookie = iop_adma_tx_submit(tx);
 	iop_adma_issue_pending(dma_chan);
@@ -1192,9 +1192,9 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 		dma_dev->max_xor = iop_adma_get_max_xor();
 		dma_dev->device_prep_dma_xor = iop_adma_prep_dma_xor;
 	}
-	if (dma_has_cap(DMA_ZERO_SUM, dma_dev->cap_mask))
-		dma_dev->device_prep_dma_zero_sum =
-			iop_adma_prep_dma_zero_sum;
+	if (dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask))
+		dma_dev->device_prep_dma_xor_val =
+			iop_adma_prep_dma_xor_val;
 	if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask))
 		dma_dev->device_prep_dma_interrupt =
 			iop_adma_prep_dma_interrupt;
@@ -1249,7 +1249,7 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask) ||
 		dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)) {
-		ret = iop_adma_xor_zero_sum_self_test(adev);
+		ret = iop_adma_xor_val_self_test(adev);
 		dev_dbg(&pdev->dev, "xor self test returned %d\n", ret);
 		if (ret)
 			goto err_free_iop_chan;
@@ -1257,12 +1257,12 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 
 	dev_printk(KERN_INFO, &pdev->dev, "Intel(R) IOP: "
 	  "( %s%s%s%s%s%s%s%s%s%s)\n",
-	  dma_has_cap(DMA_PQ_XOR, dma_dev->cap_mask) ? "pq_xor " : "",
+	  dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "",
 	  dma_has_cap(DMA_PQ_UPDATE, dma_dev->cap_mask) ? "pq_update " : "",
-	  dma_has_cap(DMA_PQ_ZERO_SUM, dma_dev->cap_mask) ? "pq_zero_sum " : "",
+	  dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "",
 	  dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
 	  dma_has_cap(DMA_DUAL_XOR, dma_dev->cap_mask) ? "dual_xor " : "",
-	  dma_has_cap(DMA_ZERO_SUM, dma_dev->cap_mask) ? "xor_zero_sum " : "",
+	  dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask) ? "xor_val " : "",
 	  dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
 	  dma_has_cap(DMA_MEMCPY_CRC32C, dma_dev->cap_mask) ? "cpy+crc " : "",
 	  dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 36e0675be9f..09c0c6e49ab 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 bb37fb1b2d8..0a5cf217121 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 +501,14 @@ 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;
 
 	if (bio->bi_sector >= sector)
 		page_offset = (signed)(bio->bi_sector - sector) * 512;
 	else
 		page_offset = (signed)(sector - bio->bi_sector) * -512;
+
+	init_async_submit(&submit, 0, tx, NULL, NULL, NULL);
 	bio_for_each_segment(bvl, bio, i) {
 		int len = bio_iovec_idx(bio, i)->bv_len;
 		int clen;
@@ -525,15 +530,14 @@ 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 +596,7 @@ 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 +620,34 @@ 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 +655,24 @@ 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 +685,207 @@ static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh)
 
 	atomic_inc(&sh->count);
 
+	init_async_submit(&submit, 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, 0, 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_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 to 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, 0, 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_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, 0, tx, ops_complete_compute,
+					  sh, to_addr_conv(sh, percpu));
+			return async_gen_syndrome(blocks, 0, count+2,
+						  STRIPE_SIZE, &submit);
+		}
+	}
+
+	init_async_submit(&submit, 0, 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 +895,13 @@ 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 +916,9 @@ 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_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 +958,21 @@ 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 +990,12 @@ 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 +1029,36 @@ 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 +1073,115 @@ 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 +1189,7 @@ 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 +1239,28 @@ 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 +1289,7 @@ 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 +1355,7 @@ 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 +1366,30 @@ 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 +1928,13 @@ static sector_t compute_blocknr(stru