1 files changed, 910 insertions, 576 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index bb37fb1b2d82..0a5cf2171214 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(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 +1947,7 @@ 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 +1960,18 @@ 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 +1989,22 @@ 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 +2085,6 @@ 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)
 {
@@ -2133,9 +2225,10 @@ 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.
@@ -2174,61 +2267,104 @@ 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