Merge branch 'md-next' of...

Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.10/drivers

Pull MD updates from Song.

* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/raid10: improve discard request for far layout
  md/raid10: improve raid10 discard request
  md/raid10: pull codes that wait for blocked dev into one function
  md/raid10: extend r10bio devs to raid disks
  md: add md_submit_discard_bio() for submitting discard bio
  md: Simplify code with existing definition RESYNC_SECTORS in raid10.c
  md/raid5: reallocate page array after setting new stripe_size
  md/raid5: resize stripe_head when reshape array
  md/raid5: let multiple devices of stripe_head share page
  md/raid6: let async recovery function support different page offset
  md/raid6: let syndrome computor support different page offset
  md/raid5: convert to new xor compution interface
  md/raid5: add new xor function to support different page offset
  md/raid5: make async_copy_data() to support different page offset
  md/raid5: add a new member of offset into r5dev
  md: only calculate blocksize once and use i_blocksize()

crypto/async_tx/async_pq.c

@@ -104,7 +104,7 @@ do_async_gen_syndrome(struct dma_chan *chan,
  * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
  */
 static void
-do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+do_sync_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 		     size_t len, struct async_submit_ctl *submit)
 {
 	void **srcs;
@@ -121,7 +121,8 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 			BUG_ON(i > disks - 3); /* P or Q can't be zero */
 			srcs[i] = (void*)raid6_empty_zero_page;
 		} else {
-			srcs[i] = page_address(blocks[i]) + offset;
+			srcs[i] = page_address(blocks[i]) + offsets[i];
+
 			if (i < disks - 2) {
 				stop = i;
 				if (start == -1)
@@ -138,10 +139,23 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	async_tx_sync_epilog(submit);
 }
 
+static inline bool
+is_dma_pq_aligned_offs(struct dma_device *dev, unsigned int *offs,
+				     int src_cnt, size_t len)
+{
+	int i;
+
+	for (i = 0; i < src_cnt; i++) {
+		if (!is_dma_pq_aligned(dev, offs[i], 0, len))
+			return false;
+	}
+	return true;
+}
+
 /**
  * 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
+ * @offsets: offset array 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
@@ -160,7 +174,7 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
  * path.
  */
 struct dma_async_tx_descriptor *
-async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 		   size_t len, struct async_submit_ctl *submit)
 {
 	int src_cnt = disks - 2;
@@ -179,7 +193,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
 	    (src_cnt <= dma_maxpq(device, 0) ||
 	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
-	    is_dma_pq_aligned(device, offset, 0, len)) {
+	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = 0;
 		unsigned char coefs[MAX_DISKS];
@@ -196,8 +210,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		for (i = 0, j = 0; i < src_cnt; i++) {
 			if (blocks[i] == NULL)
 				continue;
-			unmap->addr[j] = dma_map_page(device->dev, blocks[i], offset,
-						      len, DMA_TO_DEVICE);
+			unmap->addr[j] = dma_map_page(device->dev, blocks[i],
+						offsets[i], len, DMA_TO_DEVICE);
 			coefs[j] = raid6_gfexp[i];
 			unmap->to_cnt++;
 			j++;
@@ -210,7 +224,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		unmap->bidi_cnt++;
 		if (P(blocks, disks))
 			unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
-							offset, len, DMA_BIDIRECTIONAL);
+							P(offsets, disks),
+							len, DMA_BIDIRECTIONAL);
 		else {
 			unmap->addr[j++] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
@@ -219,7 +234,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		unmap->bidi_cnt++;
 		if (Q(blocks, disks))
 			unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
-						       offset, len, DMA_BIDIRECTIONAL);
+							Q(offsets, disks),
+							len, DMA_BIDIRECTIONAL);
 		else {
 			unmap->addr[j++] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
@@ -240,13 +256,13 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 
 	if (!P(blocks, disks)) {
 		P(blocks, disks) = pq_scribble_page;
-		BUG_ON(len + offset > PAGE_SIZE);
+		P(offsets, disks) = 0;
 	}
 	if (!Q(blocks, disks)) {
 		Q(blocks, disks) = pq_scribble_page;
-		BUG_ON(len + offset > PAGE_SIZE);
+		Q(offsets, disks) = 0;
 	}
-	do_sync_gen_syndrome(blocks, offset, disks, len, submit);
+	do_sync_gen_syndrome(blocks, offsets, disks, len, submit);
 
 	return NULL;
 }
@@ -270,6 +286,7 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
  * @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
+ * @s_off: spare buffer page offset
  * @submit: submission / completion modifiers
  *
  * The same notes from async_gen_syndrome apply to the 'blocks',
@@ -278,9 +295,9 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
  * specified.
  */
 struct dma_async_tx_descriptor *
-async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int disks,
 		   size_t len, enum sum_check_flags *pqres, struct page *spare,
-		   struct async_submit_ctl *submit)
+		   unsigned int s_off, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
 	struct dma_device *device = chan ? chan->device : NULL;
@@ -295,7 +312,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
 
 	if (unmap && disks <= dma_maxpq(device, 0) &&
-	    is_dma_pq_aligned(device, offset, 0, len)) {
+	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct device *dev = device->dev;
 		dma_addr_t pq[2];
 		int i, j = 0, src_cnt = 0;
@@ -307,7 +324,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		for (i = 0; i < disks-2; i++)
 			if (likely(blocks[i])) {
 				unmap->addr[j] = dma_map_page(dev, blocks[i],
-							      offset, len,
+							      offsets[i], len,
 							      DMA_TO_DEVICE);
 				coefs[j] = raid6_gfexp[i];
 				unmap->to_cnt++;
@@ -320,7 +337,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
 		} else {
 			pq[0] = dma_map_page(dev, P(blocks, disks),
-					     offset, len,
+					     P(offsets, disks), len,
 					     DMA_TO_DEVICE);
 			unmap->addr[j++] = pq[0];
 			unmap->to_cnt++;
@@ -330,7 +347,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
 		} else {
 			pq[1] = dma_map_page(dev, Q(blocks, disks),
-					     offset, len,
+					     Q(offsets, disks), len,
 					     DMA_TO_DEVICE);
 			unmap->addr[j++] = pq[1];
 			unmap->to_cnt++;
@@ -355,7 +372,9 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		async_tx_submit(chan, tx, submit);
 	} else {
 		struct page *p_src = P(blocks, disks);
+		unsigned int p_off = P(offsets, disks);
 		struct page *q_src = Q(blocks, disks);
+		unsigned int q_off = Q(offsets, disks);
 		enum async_tx_flags flags_orig = submit->flags;
 		dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 		void *scribble = submit->scribble;
@@ -381,27 +400,32 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		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);
+			tx = async_xor_offs(spare, s_off,
+					blocks, offsets, disks-2, len, submit);
 			async_tx_quiesce(&tx);
-			p = page_address(p_src) + offset;
-			s = page_address(spare) + offset;
+			p = page_address(p_src) + p_off;
+			s = page_address(spare) + s_off;
 			*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
 		}
 
 		if (q_src) {
 			P(blocks, disks) = NULL;
 			Q(blocks, disks) = spare;
+			Q(offsets, disks) = s_off;
 			init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
-			tx = async_gen_syndrome(blocks, offset, disks, len, submit);
+			tx = async_gen_syndrome(blocks, offsets, disks,
+					len, submit);
 			async_tx_quiesce(&tx);
-			q = page_address(q_src) + offset;
-			s = page_address(spare) + offset;
+			q = page_address(q_src) + q_off;
+			s = page_address(spare) + s_off;
 			*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
 		}
 
 		/* restore P, Q and submit */
 		P(blocks, disks) = p_src;
+		P(offsets, disks) = p_off;
 		Q(blocks, disks) = q_src;
+		Q(offsets, disks) = q_off;
 
 		submit->cb_fn = cb_fn_orig;
 		submit->cb_param = cb_param_orig;

crypto/async_tx/async_raid6_recov.c

@@ -15,7 +15,8 @@
 #include <linux/dmaengine.h>
 
 static struct dma_async_tx_descriptor *
-async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
+async_sum_product(struct page *dest, unsigned int d_off,
+		struct page **srcs, unsigned int *src_offs, unsigned char *coef,
 		size_t len, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
@@ -37,11 +38,14 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		unmap->addr[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
-		unmap->addr[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
+		unmap->addr[0] = dma_map_page(dev, srcs[0], src_offs[0],
+						len, DMA_TO_DEVICE);
+		unmap->addr[1] = dma_map_page(dev, srcs[1], src_offs[1],
+						len, DMA_TO_DEVICE);
 		unmap->to_cnt = 2;
 
-		unmap->addr[2] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->addr[2] = dma_map_page(dev, dest, d_off,
+						len, DMA_BIDIRECTIONAL);
 		unmap->bidi_cnt = 1;
 		/* engine only looks at Q, but expects it to follow P */
 		pq[1] = unmap->addr[2];
@@ -66,9 +70,9 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 	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);
+	a = page_address(srcs[0]) + src_offs[0];
+	b = page_address(srcs[1]) + src_offs[1];
+	c = page_address(dest) + d_off;
 
 	while (len--) {
 		ax    = amul[*a++];
@@ -80,7 +84,8 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 }
 
 static struct dma_async_tx_descriptor *
-async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
+async_mult(struct page *dest, unsigned int d_off, struct page *src,
+		unsigned int s_off, u8 coef, size_t len,
 		struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
@@ -101,9 +106,11 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		unmap->addr[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
+		unmap->addr[0] = dma_map_page(dev, src, s_off,
+						len, DMA_TO_DEVICE);
 		unmap->to_cnt++;
-		unmap->addr[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->addr[1] = dma_map_page(dev, dest, d_off,
+						len, DMA_BIDIRECTIONAL);
 		dma_dest[1] = unmap->addr[1];
 		unmap->bidi_cnt++;
 		unmap->len = len;
@@ -133,8 +140,8 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 	 */
 	async_tx_quiesce(&submit->depend_tx);
 	qmul  = raid6_gfmul[coef];
-	d = page_address(dest);
-	s = page_address(src);
+	d = page_address(dest) + d_off;
+	s = page_address(src) + s_off;
 
 	while (len--)
 		*d++ = qmul[*s++];
@@ -144,11 +151,14 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 
 static struct dma_async_tx_descriptor *
 __2data_recov_4(int disks, size_t bytes, int faila, int failb,
-		struct page **blocks, struct async_submit_ctl *submit)
+		struct page **blocks, unsigned int *offs,
+		struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *a, *b;
+	unsigned int p_off, q_off, a_off, b_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -156,26 +166,34 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
 	void *scribble = submit->scribble;
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 
 	a = blocks[faila];
+	a_off = offs[faila];
 	b = blocks[failb];
+	b_off = offs[failb];
 
 	/* in the 4 disk case P + Pxy == P and Q + Qxy == Q */
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	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);
+	tx = async_sum_product(b, b_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = b;
+	src_offs[1] = b_off;
 	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);
+	tx = async_xor_offs(a, a_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 
@@ -183,11 +201,14 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
 
 static struct dma_async_tx_descriptor *
 __2data_recov_5(int disks, size_t bytes, int faila, int failb,
-		struct page **blocks, struct async_submit_ctl *submit)
+		struct page **blocks, unsigned int *offs,
+		struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *g, *dp, *dq;
+	unsigned int p_off, q_off, g_off, dp_off, dq_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -208,60 +229,77 @@ __2data_recov_5(int disks, size_t bytes, int faila, int failb,
 	BUG_ON(good_srcs > 1);
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 	g = blocks[good];
+	g_off = offs[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];
+	dp_off = offs[faila];
 	dq = blocks[failb];
+	dq_off = offs[failb];
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_memcpy(dp, g, 0, 0, bytes, submit);
+	tx = async_memcpy(dp, g, dp_off, g_off, bytes, submit);
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+	tx = async_mult(dq, dq_off, g, g_off,
+			raid6_gfexp[good], bytes, submit);
 
 	/* compute P + Pxy */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = p;
+	src_offs[1] = p_off;
 	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);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	/* compute Q + Qxy */
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	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);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	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);
+	tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	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);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 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 page **blocks, unsigned int *offs,
+		  struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *dp, *dq;
+	unsigned int p_off, q_off, dp_off, dq_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -269,56 +307,74 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
 	void *scribble = submit->scribble;
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[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];
+	dp_off = offs[faila];
 	blocks[faila] = NULL;
 	blocks[disks-2] = dp;
+	offs[disks-2] = dp_off;
 	dq = blocks[failb];
+	dq_off = offs[failb];
 	blocks[failb] = NULL;
 	blocks[disks-1] = dq;
+	offs[disks-1] = dq_off;
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+	tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
 
 	/* Restore pointer table */
 	blocks[faila]   = dp;
+	offs[faila] = dp_off;
 	blocks[failb]   = dq;
+	offs[failb] = dq_off;
 	blocks[disks-2] = p;
+	offs[disks-2] = p_off;
 	blocks[disks-1] = q;
+	offs[disks-1] = q_off;
 
 	/* compute P + Pxy */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = p;
+	src_offs[1] = p_off;
 	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);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	/* compute Q + Qxy */
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	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);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	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);
+	tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	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);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }
@@ -330,11 +386,13 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
  * @faila: first failed drive index
  * @failb: second failed drive index
  * @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
  * @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)
+			struct page **blocks, unsigned int *offs,
+			struct async_submit_ctl *submit)
 {
 	void *scribble = submit->scribble;
 	int non_zero_srcs, i;
@@ -358,7 +416,7 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 			if (blocks[i] == NULL)
 				ptrs[i] = (void *) raid6_empty_zero_page;
 			else
-				ptrs[i] = page_address(blocks[i]);
+				ptrs[i] = page_address(blocks[i]) + offs[i];
 
 		raid6_2data_recov(disks, bytes, faila, failb, ptrs);
 
@@ -383,16 +441,19 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 		 * explicitly handle the special case of a 4 disk array with
 		 * both data disks missing.
 		 */
-		return __2data_recov_4(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_4(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	case 3:
 		/* dma devices do not uniformly understand a single
 		 * source pq operation (in contrast to the synchronous
 		 * case), so explicitly handle the special case of a 5 disk
 		 * array with 2 of 3 data disks missing.
 		 */
-		return __2data_recov_5(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_5(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	default:
-		return __2data_recov_n(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_n(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	}
 }
 EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
@@ -403,14 +464,17 @@ EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
  * @bytes: block size
  * @faila: failed drive index
  * @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
  * @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 page **blocks, unsigned int *offs,
+			struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *dq;
+	unsigned int p_off, q_off, dq_off;
 	u8 coef;
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -418,6 +482,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 	void *scribble = submit->scribble;
 	int good_srcs, good, i;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 
 	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
 
@@ -434,7 +499,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 			if (blocks[i] == NULL)
 				ptrs[i] = (void*)raid6_empty_zero_page;
 			else
-				ptrs[i] = page_address(blocks[i]);
+				ptrs[i] = page_address(blocks[i]) + offs[i];
 
 		raid6_datap_recov(disks, bytes, faila, ptrs);
 
@@ -458,55 +523,67 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 	BUG_ON(good_srcs == 0);
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[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];
+	dq_off = offs[faila];
 	blocks[faila] = NULL;
 	blocks[disks-1] = dq;
+	offs[disks-1] = dq_off;
 
 	/* in the 4-disk case we only need to perform a single source
 	 * multiplication with the one good data block.
 	 */
 	if (good_srcs == 1) {
 		struct page *g = blocks[good];
+		unsigned int g_off = offs[good];
 
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_memcpy(p, g, 0, 0, bytes, submit);
+		tx = async_memcpy(p, g, p_off, g_off, bytes, submit);
 
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+		tx = async_mult(dq, dq_off, g, g_off,
+				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);
+		tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
 	}
 
 	/* Restore pointer table */
 	blocks[faila]   = dq;
+	offs[faila] = dq_off;
 	blocks[disks-1] = q;
+	offs[disks-1] = q_off;
 
 	/* calculate g^{-faila} */
 	coef = raid6_gfinv[raid6_gfexp[faila]];
 
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	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);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_mult(dq, dq, coef, bytes, submit);
+	tx = async_mult(dq, dq_off, dq, dq_off, coef, bytes, submit);
 
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	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);
+	tx = async_xor_offs(p, p_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }

crypto/async_tx/async_xor.c

@@ -97,7 +97,8 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 }
 
 static void
-do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
+do_sync_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
 	    int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
 	int i;
@@ -114,7 +115,8 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	/* convert to buffer pointers */
 	for (i = 0; i < src_cnt; i++)
 		if (src_list[i])
-			srcs[xor_src_cnt++] = page_address(src_list[i]) + offset;
+			srcs[xor_src_cnt++] = page_address(src_list[i]) +
+				(src_offs ? src_offs[i] : offset);
 	src_cnt = xor_src_cnt;
 	/* set destination address */
 	dest_buf = page_address(dest) + offset;
@@ -135,11 +137,31 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	async_tx_sync_epilog(submit);
 }
 
+static inline bool
+dma_xor_aligned_offsets(struct dma_device *device, unsigned int offset,
+		unsigned int *src_offs, int src_cnt, int len)
+{
+	int i;
+
+	if (!is_dma_xor_aligned(device, offset, 0, len))
+		return false;
+
+	if (!src_offs)
+		return true;
+
+	for (i = 0; i < src_cnt; i++) {
+		if (!is_dma_xor_aligned(device, src_offs[i], 0, len))
+			return false;
+	}
+	return true;
+}
+
 /**
- * async_xor - attempt to xor a set of blocks with a dma engine.
+ * async_xor_offs - attempt to xor a set of blocks with a dma engine.
  * @dest: destination page
+ * @offset: dst offset to start transaction
  * @src_list: array of source pages
- * @offset: common src/dst offset to start transaction
+ * @src_offs: array of source pages offset, NULL means common src/dst offset
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @submit: submission / completion modifiers
@@ -157,7 +179,8 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
  * is not specified.
  */
 struct dma_async_tx_descriptor *
-async_xor(struct page *dest, struct page **src_list, unsigned int offset,
+async_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
 		int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
@@ -171,7 +194,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	if (device)
 		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT);
 
-	if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
+	if (unmap && dma_xor_aligned_offsets(device, offset,
+				src_offs, src_cnt, len)) {
 		struct dma_async_tx_descriptor *tx;
 		int i, j;
 
@@ -184,7 +208,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 				continue;
 			unmap->to_cnt++;
 			unmap->addr[j++] = dma_map_page(device->dev, src_list[i],
-							offset, len, DMA_TO_DEVICE);
+					src_offs ? src_offs[i] : offset,
+					len, DMA_TO_DEVICE);
 		}
 
 		/* map it bidirectional as it may be re-used as a source */
@@ -213,11 +238,42 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 		/* wait for any prerequisite operations */
 		async_tx_quiesce(&submit->depend_tx);
 
-		do_sync_xor(dest, src_list, offset, src_cnt, len, submit);
+		do_sync_xor_offs(dest, offset, src_list, src_offs,
+				src_cnt, len, submit);
 
 		return NULL;
 	}
 }
+EXPORT_SYMBOL_GPL(async_xor_offs);
+
+/**
+ * async_xor - attempt to xor a set of blocks with a dma engine.
+ * @dest: destination page
+ * @src_list: array of source pages
+ * @offset: common src/dst offset to start transaction
+ * @src_cnt: number of source pages
+ * @len: length in bytes
+ * @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, struct async_submit_ctl *submit)
+{
+	return async_xor_offs(dest, offset, src_list, NULL,
+			src_cnt, len, submit);
+}
 EXPORT_SYMBOL_GPL(async_xor);
 
 static int page_is_zero(struct page *p, unsigned int offset, size_t len)
@@ -237,10 +293,11 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
 }
 
 /**
- * async_xor_val - attempt a xor parity check with a dma engine.
+ * async_xor_val_offs - attempt a xor parity check with a dma engine.
  * @dest: destination page used if the xor is performed synchronously
+ * @offset: des offset in pages to start transaction
  * @src_list: array of source pages
- * @offset: offset in pages to start transaction
+ * @src_offs: array of source pages offset, NULL means common src/det offset
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @result: 0 if sum == 0 else non-zero
@@ -253,7 +310,8 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
  * is not specified.
  */
 struct dma_async_tx_descriptor *
-async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
+async_xor_val_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
 		int src_cnt, size_t len, enum sum_check_flags *result,
 		struct async_submit_ctl *submit)
 {
@@ -268,7 +326,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT);
 
 	if (unmap && src_cnt <= device->max_xor &&
-	    is_dma_xor_aligned(device, offset, 0, len)) {
+	    dma_xor_aligned_offsets(device, offset, src_offs, src_cnt, len)) {
 		unsigned long dma_prep_flags = 0;
 		int i;
 
@@ -281,7 +339,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 
 		for (i = 0; i < src_cnt; i++) {
 			unmap->addr[i] = dma_map_page(device->dev, src_list[i],
-						      offset, len, DMA_TO_DEVICE);
+					src_offs ? src_offs[i] : offset,
+					len, DMA_TO_DEVICE);
 			unmap->to_cnt++;
 		}
 		unmap->len = len;
@@ -312,7 +371,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 		submit->flags |= ASYNC_TX_XOR_DROP_DST;
 		submit->flags &= ~ASYNC_TX_ACK;
 
-		tx = async_xor(dest, src_list, offset, src_cnt, len, submit);
+		tx = async_xor_offs(dest, offset, src_list, src_offs,
+				src_cnt, len, submit);
 
 		async_tx_quiesce(&tx);
 
@@ -325,6 +385,32 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 
 	return tx;
 }
+EXPORT_SYMBOL_GPL(async_xor_val_offs);
+
+/**
+ * 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
+ * @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
+ * @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_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)
+{
+	return async_xor_val_offs(dest, offset, src_list, NULL, src_cnt,
+			len, result, submit);
+}
 EXPORT_SYMBOL_GPL(async_xor_val);
 
 MODULE_AUTHOR("Intel Corporation");

crypto/async_tx/raid6test.c

@@ -18,6 +18,7 @@
 #define NDISKS 64 /* Including P and Q */
 
 static struct page *dataptrs[NDISKS];
+unsigned int dataoffs[NDISKS];
 static addr_conv_t addr_conv[NDISKS];
 static struct page *data[NDISKS+3];
 static struct page *spare;
@@ -38,6 +39,7 @@ static void makedata(int disks)
 	for (i = 0; i < disks; i++) {
 		prandom_bytes(page_address(data[i]), PAGE_SIZE);
 		dataptrs[i] = data[i];
+		dataoffs[i] = 0;
 	}
 }
 
@@ -52,7 +54,8 @@ static char disk_type(int d, int disks)
 }
 
 /* Recover two failed blocks. */
-static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, struct page **ptrs)
+static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
+		struct page **ptrs, unsigned int *offs)
 {
 	struct async_submit_ctl submit;
 	struct completion cmp;
@@ -66,7 +69,8 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 		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);
+			tx = async_gen_syndrome(ptrs, offs,
+					disks, bytes, &submit);
 		} else {
 			struct page *blocks[NDISKS];
 			struct page *dest;
@@ -89,22 +93,26 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 			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);
+			tx = async_gen_syndrome(ptrs, offs,
+					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);
+			tx = async_raid6_datap_recov(disks, bytes,
+					faila, ptrs, offs, &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);
+			tx = async_raid6_2data_recov(disks, bytes,
+					faila, failb, ptrs, offs, &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);
+	tx = async_syndrome_val(ptrs, offs,
+			disks, bytes, &result, spare, 0, &submit);
 	async_tx_issue_pending(tx);
 
 	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0)
@@ -126,7 +134,7 @@ static int test_disks(int i, int j, int disks)
 	dataptrs[i] = recovi;
 	dataptrs[j] = recovj;
 
-	raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs);
+	raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs, dataoffs);
 
 	erra = memcmp(page_address(data[i]), page_address(recovi), PAGE_SIZE);
 	errb = memcmp(page_address(data[j]), page_address(recovj), PAGE_SIZE);
@@ -162,7 +170,7 @@ static int test(int disks, int *tests)
 	/* 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);
+	tx = async_gen_syndrome(dataptrs, dataoffs, disks, PAGE_SIZE, &submit);
 	async_tx_issue_pending(tx);
 
 	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0) {

drivers/md/md-bitmap.c

@@ -357,11 +357,12 @@ static int read_page(struct file *file, unsigned long index,
 	struct inode *inode = file_inode(file);
 	struct buffer_head *bh;
 	sector_t block, blk_cur;
+	unsigned long blocksize = i_blocksize(inode);
 
 	pr_debug("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE,
 		 (unsigned long long)index << PAGE_SHIFT);
 
-	bh = alloc_page_buffers(page, 1<<inode->i_blkbits, false);
+	bh = alloc_page_buffers(page, blocksize, false);
 	if (!bh) {
 		ret = -ENOMEM;
 		goto out;
@@ -383,10 +384,10 @@ static int read_page(struct file *file, unsigned long index,
 
 			bh->b_blocknr = block;
 			bh->b_bdev = inode->i_sb->s_bdev;
-			if (count < (1<<inode->i_blkbits))
+			if (count < blocksize)
 				count = 0;
 			else
-				count -= (1<<inode->i_blkbits);
+				count -= blocksize;
 
 			bh->b_end_io = end_bitmap_write;
 			bh->b_private = bitmap;

drivers/md/md.c

@@ -8583,6 +8583,26 @@ void md_write_end(struct mddev *mddev)
 
 EXPORT_SYMBOL(md_write_end);
 
+/* This is used by raid0 and raid10 */
+void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
+			struct bio *bio, sector_t start, sector_t size)
+{
+	struct bio *discard_bio = NULL;
+
+	if (__blkdev_issue_discard(rdev->bdev, start, size,
+		GFP_NOIO, 0, &discard_bio) || !discard_bio)
+		return;
+
+	bio_chain(discard_bio, bio);
+	bio_clone_blkg_association(discard_bio, bio);
+	if (mddev->gendisk)
+		trace_block_bio_remap(bdev_get_queue(rdev->bdev),
+			discard_bio, disk_devt(mddev->gendisk),
+			bio->bi_iter.bi_sector);
+	submit_bio_noacct(discard_bio);
+}
+EXPORT_SYMBOL(md_submit_discard_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before

drivers/md/md.h

@@ -713,6 +713,8 @@ extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
+extern void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
+			struct bio *bio, sector_t start, sector_t size);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,

drivers/md/raid0.c

@@ -494,7 +494,6 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 	for (disk = 0; disk < zone->nb_dev; disk++) {
 		sector_t dev_start, dev_end;
-		struct bio *discard_bio = NULL;
 		struct md_rdev *rdev;
 
 		if (disk < start_disk_index)
@@ -517,18 +516,9 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 		rdev = conf->devlist[(zone - conf->strip_zone) *
 			conf->strip_zone[0].nb_dev + disk];
-		if (__blkdev_issue_discard(rdev->bdev,
+		md_submit_discard_bio(mddev, rdev, bio,
 			dev_start + zone->dev_start + rdev->data_offset,
-			dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
-		    !discard_bio)
-			continue;
-		bio_chain(discard_bio, bio);
-		bio_clone_blkg_association(discard_bio, bio);
-		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
-				discard_bio, disk_devt(mddev->gendisk),
-				bio->bi_iter.bi_sector);
-		submit_bio_noacct(discard_bio);
+			dev_end - dev_start);
 	}
 	bio_endio(bio);
 }

drivers/md/raid10.c

@@ -91,7 +91,7 @@ static inline struct r10bio *get_resync_r10bio(struct bio *bio)
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct r10conf *conf = data;
-	int size = offsetof(struct r10bio, devs[conf->copies]);
+	int size = offsetof(struct r10bio, devs[conf->geo.raid_disks]);
 
 	/* allocate a r10bio with room for raid_disks entries in the
 	 * bios array */
@@ -238,7 +238,7 @@ static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio)
 {
 	int i;
 
-	for (i = 0; i < conf->copies; i++) {
+	for (i = 0; i < conf->geo.raid_disks; i++) {
 		struct bio **bio = & r10_bio->devs[i].bio;
 		if (!BIO_SPECIAL(*bio))
 			bio_put(*bio);
@@ -327,7 +327,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 	int slot;
 	int repl = 0;
 
-	for (slot = 0; slot < conf->copies; slot++) {
+	for (slot = 0; slot < conf->geo.raid_disks; slot++) {
 		if (r10_bio->devs[slot].bio == bio)
 			break;
 		if (r10_bio->devs[slot].repl_bio == bio) {
@@ -336,7 +336,6 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 		}
 	}
 
-	BUG_ON(slot == conf->copies);
 	update_head_pos(slot, r10_bio);
 
 	if (slotp)
@@ -1276,12 +1275,75 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	}
 }
 
+static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
+{
+	int i;
+	struct r10conf *conf = mddev->private;
+	struct md_rdev *blocked_rdev;
+
+retry_wait:
+	blocked_rdev = NULL;
+	rcu_read_lock();
+	for (i = 0; i < conf->copies; i++) {
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[i].replacement);
+		if (rdev == rrdev)
+			rrdev = NULL;
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			atomic_inc(&rdev->nr_pending);
+			blocked_rdev = rdev;
+			break;
+		}
+		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
+			atomic_inc(&rrdev->nr_pending);
+			blocked_rdev = rrdev;
+			break;
+		}
+
+		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
+			sector_t first_bad;
+			sector_t dev_sector = r10_bio->devs[i].addr;
+			int bad_sectors;
+			int is_bad;
+
+			/* Discard request doesn't care the write result
+			 * so it doesn't need to wait blocked disk here.
+			 */
+			if (!r10_bio->sectors)
+				continue;
+
+			is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
+					     &first_bad, &bad_sectors);
+			if (is_bad < 0) {
+				/* Mustn't write here until the bad block
+				 * is acknowledged
+				 */
+				atomic_inc(&rdev->nr_pending);
+				set_bit(BlockedBadBlocks, &rdev->flags);
+				blocked_rdev = rdev;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	if (unlikely(blocked_rdev)) {
+		/* Have to wait for this device to get unblocked, then retry */
+		allow_barrier(conf);
+		raid10_log(conf->mddev, "%s wait rdev %d blocked",
+				__func__, blocked_rdev->raid_disk);
+		md_wait_for_blocked_rdev(blocked_rdev, mddev);
+		wait_barrier(conf);
+		goto retry_wait;
+	}
+}
+
 static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 				 struct r10bio *r10_bio)
 {
 	struct r10conf *conf = mddev->private;
 	int i;
-	struct md_rdev *blocked_rdev;
 	sector_t sectors;
 	int max_sectors;
 
@@ -1339,8 +1401,9 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 
 	r10_bio->read_slot = -1; /* make sure repl_bio gets freed */
 	raid10_find_phys(conf, r10_bio);
-retry_write:
-	blocked_rdev = NULL;
+
+	wait_blocked_dev(mddev, r10_bio);
+
 	rcu_read_lock();
 	max_sectors = r10_bio->sectors;
 
@@ -1351,16 +1414,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			conf->mirrors[d].replacement);
 		if (rdev == rrdev)
 			rrdev = NULL;
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
-		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
-			atomic_inc(&rrdev->nr_pending);
-			blocked_rdev = rrdev;
-			break;
-		}
 		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
 		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
@@ -1381,15 +1434,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 
 			is_bad = is_badblock(rdev, dev_sector, max_sectors,
 					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
-				/* Mustn't write here until the bad block
-				 * is acknowledged
-				 */
-				atomic_inc(&rdev->nr_pending);
-				set_bit(BlockedBadBlocks, &rdev->flags);
-				blocked_rdev = rdev;
-				break;
-			}
 			if (is_bad && first_bad <= dev_sector) {
 				/* Cannot write here at all */
 				bad_sectors -= (dev_sector - first_bad);
@@ -1425,35 +1469,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	}
 	rcu_read_unlock();
 
-	if (unlikely(blocked_rdev)) {
-		/* Have to wait for this device to get unblocked, then retry */
-		int j;
-		int d;
-
-		for (j = 0; j < i; j++) {
-			if (r10_bio->devs[j].bio) {
-				d = r10_bio->devs[j].devnum;
-				rdev_dec_pending(conf->mirrors[d].rdev, mddev);
-			}
-			if (r10_bio->devs[j].repl_bio) {
-				struct md_rdev *rdev;
-				d = r10_bio->devs[j].devnum;
-				rdev = conf->mirrors[d].replacement;
-				if (!rdev) {
-					/* Race with remove_disk */
-					smp_mb();
-					rdev = conf->mirrors[d].rdev;
-				}
-				rdev_dec_pending(rdev, mddev);
-			}
-		}
-		allow_barrier(conf);
-		raid10_log(conf->mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
-		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		wait_barrier(conf);
-		goto retry_write;
-	}
-
 	if (max_sectors < r10_bio->sectors)
 		r10_bio->sectors = max_sectors;
 
@@ -1493,7 +1508,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 	r10_bio->mddev = mddev;
 	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
-	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies);
+	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->geo.raid_disks);
 
 	if (bio_data_dir(bio) == READ)
 		raid10_read_request(mddev, bio, r10_bio);
@@ -1501,6 +1516,296 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 		raid10_write_request(mddev, bio, r10_bio);
 }
 
+static struct bio *raid10_split_bio(struct r10conf *conf,
+			struct bio *bio, sector_t sectors, bool want_first)
+{
+	struct bio *split;
+
+	split = bio_split(bio, sectors,	GFP_NOIO, &conf->bio_split);
+	bio_chain(split, bio);
+	allow_barrier(conf);
+	if (want_first) {
+		submit_bio_noacct(bio);
+		bio = split;
+	} else
+		submit_bio_noacct(split);
+	wait_barrier(conf);
+
+	return bio;
+}
+
+static void raid_end_discard_bio(struct r10bio *r10bio)
+{
+	struct r10conf *conf = r10bio->mddev->private;
+	struct r10bio *first_r10bio;
+
+	while (atomic_dec_and_test(&r10bio->remaining)) {
+
+		allow_barrier(conf);
+
+		if (!test_bit(R10BIO_Discard, &r10bio->state)) {
+			first_r10bio = (struct r10bio *)r10bio->master_bio;
+			free_r10bio(r10bio);
+			r10bio = first_r10bio;
+		} else {
+			md_write_end(r10bio->mddev);
+			bio_endio(r10bio->master_bio);
+			free_r10bio(r10bio);
+			break;
+		}
+	}
+}
+
+static void raid10_end_discard_request(struct bio *bio)
+{
+	struct r10bio *r10_bio = bio->bi_private;
+	struct r10conf *conf = r10_bio->mddev->private;
+	struct md_rdev *rdev = NULL;
+	int dev;
+	int slot, repl;
+
+	/*
+	 * We don't care the return value of discard bio
+	 */
+	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
+		set_bit(R10BIO_Uptodate, &r10_bio->state);
+
+	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
+	if (repl)
+		rdev = conf->mirrors[dev].replacement;
+	if (!rdev) {
+		/* raid10_remove_disk uses smp_mb to make sure rdev is set to
+		 * replacement before setting replacement to NULL. It can read
+		 * rdev first without barrier protect even replacment is NULL
+		 */
+		smp_rmb();
+		rdev = conf->mirrors[dev].rdev;
+	}
+
+	raid_end_discard_bio(r10_bio);
+	rdev_dec_pending(rdev, conf->mddev);
+}
+
+/* There are some limitations to handle discard bio
+ * 1st, the discard size is bigger than stripe_size*2.
+ * 2st, if the discard bio spans reshape progress, we use the old way to
+ * handle discard bio
+ */
+static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
+{
+	struct r10conf *conf = mddev->private;
+	struct geom *geo = &conf->geo;
+	struct r10bio *r10_bio, *first_r10bio;
+	int far_copies = geo->far_copies;
+	bool first_copy = true;
+
+	int disk;
+	sector_t chunk;
+	unsigned int stripe_size;
+	sector_t split_size;
+
+	sector_t bio_start, bio_end;
+	sector_t first_stripe_index, last_stripe_index;
+	sector_t start_disk_offset;
+	unsigned int start_disk_index;
+	sector_t end_disk_offset;
+	unsigned int end_disk_index;
+	unsigned int remainder;
+
+	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+		return -EAGAIN;
+
+	wait_barrier(conf);
+
+	/* Check reshape again to avoid reshape happens after checking
+	 * MD_RECOVERY_RESHAPE and before wait_barrier
+	 */
+	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+		goto out;
+
+	stripe_size = geo->raid_disks << geo->chunk_shift;
+	bio_start = bio->bi_iter.bi_sector;
+	bio_end = bio_end_sector(bio);
+
+	/* Maybe one discard bio is smaller than strip size or across one stripe
+	 * and discard region is larger than one stripe size. For far offset layout,
+	 * if the discard region is not aligned with stripe size, there is hole
+	 * when we submit discard bio to member disk. For simplicity, we only
+	 * handle discard bio which discard region is bigger than stripe_size*2
+	 */
+	if (bio_sectors(bio) < stripe_size*2)
+		goto out;
+
+	/* For far and far offset layout, if bio is not aligned with stripe size,
+	 * it splits the part that is not aligned with strip size.
+	 */
+	div_u64_rem(bio_start, stripe_size, &remainder);
+	if ((far_copies > 1) && remainder) {
+		split_size = stripe_size - remainder;
+		bio = raid10_split_bio(conf, bio, split_size, false);
+	}
+	div_u64_rem(bio_end, stripe_size, &remainder);
+	if ((far_copies > 1) && remainder) {
+		split_size = bio_sectors(bio) - remainder;
+		bio = raid10_split_bio(conf, bio, split_size, true);
+	}
+
+	bio_start = bio->bi_iter.bi_sector;
+	bio_end = bio_end_sector(bio);
+
+	/* raid10 uses chunk as the unit to store data. It's similar like raid0.
+	 * One stripe contains the chunks from all member disk (one chunk from
+	 * one disk at the same HBA address). For layout detail, see 'man md 4'
+	 */
+	chunk = bio_start >> geo->chunk_shift;
+	chunk *= geo->near_copies;
+	first_stripe_index = chunk;
+	start_disk_index = sector_div(first_stripe_index, geo->raid_disks);
+	if (geo->far_offset)
+		first_stripe_index *= geo->far_copies;
+	start_disk_offset = (bio_start & geo->chunk_mask) +
+				(first_stripe_index << geo->chunk_shift);
+
+	chunk = bio_end >> geo->chunk_shift;
+	chunk *= geo->near_copies;
+	last_stripe_index = chunk;
+	end_disk_index = sector_div(last_stripe_index, geo->raid_disks);
+	if (geo->far_offset)
+		last_stripe_index *= geo->far_copies;
+	end_disk_offset = (bio_end & geo->chunk_mask) +
+				(last_stripe_index << geo->chunk_shift);
+
+retry_discard:
+	r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
+	r10_bio->mddev = mddev;
+	r10_bio->state = 0;
+	r10_bio->sectors = 0;
+	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks);
+	wait_blocked_dev(mddev, r10_bio);
+
+	/* For far layout it needs more than one r10bio to cover all regions.
+	 * Inspired by raid10_sync_request, we can use the first r10bio->master_bio
+	 * to record the discard bio. Other r10bio->master_bio record the first
+	 * r10bio. The first r10bio only release after all other r10bios finish.
+	 * The discard bio returns only first r10bio finishes
+	 */
+	if (first_copy) {
+		r10_bio->master_bio = bio;
+		set_bit(R10BIO_Discard, &r10_bio->state);
+		first_copy = false;
+		first_r10bio = r10_bio;
+	} else
+		r10_bio->master_bio = (struct bio *)first_r10bio;
+
+	rcu_read_lock();
+	for (disk = 0; disk < geo->raid_disks; disk++) {
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[disk].replacement);
+
+		r10_bio->devs[disk].bio = NULL;
+		r10_bio->devs[disk].repl_bio = NULL;
+
+		if (rdev && (test_bit(Faulty, &rdev->flags)))
+			rdev = NULL;
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
+			rrdev = NULL;
+		if (!rdev && !rrdev)
+			continue;
+
+		if (rdev) {
+			r10_bio->devs[disk].bio = bio;
+			atomic_inc(&rdev->nr_pending);
+		}
+		if (rrdev) {
+			r10_bio->devs[disk].repl_bio = bio;
+			atomic_inc(&rrdev->nr_pending);
+		}
+	}
+	rcu_read_unlock();
+
+	atomic_set(&r10_bio->remaining, 1);
+	for (disk = 0; disk < geo->raid_disks; disk++) {
+		sector_t dev_start, dev_end;
+		struct bio *mbio, *rbio = NULL;
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[disk].replacement);
+
+		/*
+		 * Now start to calculate the start and end address for each disk.
+		 * The space between dev_start and dev_end is the discard region.
+		 *
+		 * For dev_start, it needs to consider three conditions:
+		 * 1st, the disk is before start_disk, you can imagine the disk in
+		 * the next stripe. So the dev_start is the start address of next
+		 * stripe.
+		 * 2st, the disk is after start_disk, it means the disk is at the
+		 * same stripe of first disk
+		 * 3st, the first disk itself, we can use start_disk_offset directly
+		 */
+		if (disk < start_disk_index)
+			dev_start = (first_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > start_disk_index)
+			dev_start = first_stripe_index * mddev->chunk_sectors;
+		else
+			dev_start = start_disk_offset;
+
+		if (disk < end_disk_index)
+			dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > end_disk_index)
+			dev_end = last_stripe_index * mddev->chunk_sectors;
+		else
+			dev_end = end_disk_offset;
+
+		/* It only handles discard bio which size is >= stripe size, so
+		 * dev_end > dev_start all the time
+		 */
+		if (r10_bio->devs[disk].bio) {
+			mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
+			mbio->bi_end_io = raid10_end_discard_request;
+			mbio->bi_private = r10_bio;
+			r10_bio->devs[disk].bio = mbio;
+			r10_bio->devs[disk].devnum = disk;
+			atomic_inc(&r10_bio->remaining);
+			md_submit_discard_bio(mddev, rdev, mbio,
+					dev_start + choose_data_offset(r10_bio, rdev),
+					dev_end - dev_start);
+			bio_endio(mbio);
+		}
+		if (r10_bio->devs[disk].repl_bio) {
+			rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
+			rbio->bi_end_io = raid10_end_discard_request;
+			rbio->bi_private = r10_bio;
+			r10_bio->devs[disk].repl_bio = rbio;
+			r10_bio->devs[disk].devnum = disk;
+			atomic_inc(&r10_bio->remaining);
+			md_submit_discard_bio(mddev, rrdev, rbio,
+					dev_start + choose_data_offset(r10_bio, rrdev),
+					dev_end - dev_start);
+			bio_endio(rbio);
+		}
+	}
+
+	if (!geo->far_offset && --far_copies) {
+		first_stripe_index += geo->stride >> geo->chunk_shift;
+		start_disk_offset += geo->stride;
+		last_stripe_index += geo->stride >> geo->chunk_shift;
+		end_disk_offset += geo->stride;
+		atomic_inc(&first_r10bio->remaining);
+		raid_end_discard_bio(r10_bio);
+		wait_barrier(conf);
+		goto retry_discard;
+	}
+
+	raid_end_discard_bio(r10_bio);
+
+	return 0;
+out:
+	allow_barrier(conf);
+	return -EAGAIN;
+}
+
 static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct r10conf *conf = mddev->private;
@@ -1515,6 +1820,10 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	if (!md_write_start(mddev, bio))
 		return false;
 
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
+		if (!raid10_handle_discard(mddev, bio))
+			return true;
+
 	/*
 	 * If this request crosses a chunk boundary, we need to split
 	 * it.
@@ -3754,7 +4063,7 @@ static int raid10_run(struct mddev *mddev)
 
 	if (mddev->queue) {
 		blk_queue_max_discard_sectors(mddev->queue,
-					      mddev->chunk_sectors);
+					      UINT_MAX);
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
@@ -4458,8 +4767,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 		last = conf->reshape_progress - 1;
 		sector_nr = last & ~(sector_t)(conf->geo.chunk_mask
 					       & conf->prev.chunk_mask);
-		if (sector_nr + RESYNC_BLOCK_SIZE/512 < last)
-			sector_nr = last + 1 - RESYNC_BLOCK_SIZE/512;
+		if (sector_nr + RESYNC_SECTORS < last)
+			sector_nr = last + 1 - RESYNC_SECTORS;
 	} else {
 		/* 'next' is after the last device address that we
 		 * might write to for this chunk in the new layout
@@ -4481,8 +4790,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 		last  = sector_nr | (conf->geo.chunk_mask
 				     & conf->prev.chunk_mask);
 
-		if (sector_nr + RESYNC_BLOCK_SIZE/512 <= last)
-			last = sector_nr + RESYNC_BLOCK_SIZE/512 - 1;
+		if (sector_nr + RESYNC_SECTORS <= last)
+			last = sector_nr + RESYNC_SECTORS - 1;
 	}
 
 	if (need_flush ||

drivers/md/raid10.h

@@ -179,5 +179,6 @@ enum r10bio_state {
 	R10BIO_Previous,
 /* failfast devices did receive failfast requests. */
 	R10BIO_FailFast,
+	R10BIO_Discard,
 };
 #endif

drivers/md/raid5.c

@@ -448,13 +448,74 @@ static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash)
 	return sh;
 }
 
-static void shrink_buffers(struct stripe_head *sh)
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+static void free_stripe_pages(struct stripe_head *sh)
+{
+	int i;
+	struct page *p;
+
+	/* Have not allocate page pool */
+	if (!sh->pages)
+		return;
+
+	for (i = 0; i < sh->nr_pages; i++) {
+		p = sh->pages[i];
+		if (p)
+			put_page(p);
+		sh->pages[i] = NULL;
+	}
+}
+
+static int alloc_stripe_pages(struct stripe_head *sh, gfp_t gfp)
 {
+	int i;
 	struct page *p;
+
+	for (i = 0; i < sh->nr_pages; i++) {
+		/* The page have allocated. */
+		if (sh->pages[i])
+			continue;
+
+		p = alloc_page(gfp);
+		if (!p) {
+			free_stripe_pages(sh);
+			return -ENOMEM;
+		}
+		sh->pages[i] = p;
+	}
+	return 0;
+}
+
+static int
+init_stripe_shared_pages(struct stripe_head *sh, struct r5conf *conf, int disks)
+{
+	int nr_pages, cnt;
+
+	if (sh->pages)
+		return 0;
+
+	/* Each of the sh->dev[i] need one conf->stripe_size */
+	cnt = PAGE_SIZE / conf->stripe_size;
+	nr_pages = (disks + cnt - 1) / cnt;
+
+	sh->pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!sh->pages)
+		return -ENOMEM;
+	sh->nr_pages = nr_pages;
+	sh->stripes_per_page = cnt;
+	return 0;
+}
+#endif
+
+static void shrink_buffers(struct stripe_head *sh)
+{
 	int i;
 	int num = sh->raid_conf->pool_size;
 
+#if PAGE_SIZE == DEFAULT_STRIPE_SIZE
 	for (i = 0; i < num ; i++) {
+		struct page *p;
+
 		WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
 		p = sh->dev[i].page;
 		if (!p)
@@ -462,6 +523,11 @@ static void shrink_buffers(struct stripe_head *sh)
 		sh->dev[i].page = NULL;
 		put_page(p);
 	}
+#else
+	for (i = 0; i < num; i++)
+		sh->dev[i].page = NULL;
+	free_stripe_pages(sh); /* Free pages */
+#endif
 }
 
 static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
@@ -469,6 +535,7 @@ static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
 	int i;
 	int num = sh->raid_conf->pool_size;
 
+#if PAGE_SIZE == DEFAULT_STRIPE_SIZE
 	for (i = 0; i < num; i++) {
 		struct page *page;
 
@@ -477,8 +544,18 @@ static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
 		}
 		sh->dev[i].page = page;
 		sh->dev[i].orig_page = page;
+		sh->dev[i].offset = 0;
 	}
+#else
+	if (alloc_stripe_pages(sh, gfp))
+		return -ENOMEM;
 
+	for (i = 0; i < num; i++) {
+		sh->dev[i].page = raid5_get_dev_page(sh, i);
+		sh->dev[i].orig_page = sh->dev[i].page;
+		sh->dev[i].offset = raid5_get_page_offset(sh, i);
+	}
+#endif
 	return 0;
 }
 
@@ -1130,7 +1207,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 				sh->dev[i].vec.bv_page = sh->dev[i].page;
 			bi->bi_vcnt = 1;
 			bi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf);
-			bi->bi_io_vec[0].bv_offset = 0;
+			bi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
 			bi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf);
 			bi->bi_write_hint = sh->dev[i].write_hint;
 			if (!rrdev)
@@ -1184,7 +1261,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			sh->dev[i].rvec.bv_page = sh->dev[i].page;
 			rbi->bi_vcnt = 1;
 			rbi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf);
-			rbi->bi_io_vec[0].bv_offset = 0;
+			rbi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
 			rbi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf);
 			rbi->bi_write_hint = sh->dev[i].write_hint;
 			sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
@@ -1226,7 +1303,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 
 static struct dma_async_tx_descriptor *
 async_copy_data(int frombio, struct bio *bio, struct page **page,
-	sector_t sector, struct dma_async_tx_descriptor *tx,
+	unsigned int poff, sector_t sector, struct dma_async_tx_descriptor *tx,
 	struct stripe_head *sh, int no_skipcopy)
 {
 	struct bio_vec bvl;
@@ -1272,11 +1349,11 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
 				    !no_skipcopy)
 					*page = bio_page;
 				else
-					tx = async_memcpy(*page, bio_page, page_offset,
+					tx = async_memcpy(*page, bio_page, page_offset + poff,
 						  b_offset, clen, &submit);
 			} else
 				tx = async_memcpy(bio_page, *page, b_offset,
-						  page_offset, clen, &submit);
+						  page_offset + poff, clen, &submit);
 		}
 		/* chain the operations */
 		submit.depend_tx = tx;
@@ -1349,6 +1426,7 @@ static void ops_run_biofill(struct stripe_head *sh)
 			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + RAID5_STRIPE_SECTORS(conf)) {
 				tx = async_copy_data(0, rbi, &dev->page,
+						     dev->offset,
 						     dev->sector, tx, sh, 0);
 				rbi = r5_next_bio(conf, rbi, dev->sector);
 			}
@@ -1404,14 +1482,25 @@ static addr_conv_t *to_addr_conv(struct stripe_head *sh,
 	return (void *) (to_addr_page(percpu, i) + sh->disks + 2);
 }
 
+/*
+ * Return a pointer to record offset address.
+ */
+static unsigned int *
+to_addr_offs(struct stripe_head *sh, struct raid5_percpu *percpu)
+{
+	return (unsigned int *) (to_addr_conv(sh, percpu, 0) + sh->disks + 2);
+}
+
 static struct dma_async_tx_descriptor *
 ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
 {
 	int disks = sh->disks;
 	struct page **xor_srcs = to_addr_page(percpu, 0);
+	unsigned int *off_srcs = to_addr_offs(sh, percpu);
 	int target = sh->ops.target;
 	struct r5dev *tgt = &sh->dev[target];
 	struct page *xor_dest = tgt->page;
+	unsigned int off_dest = tgt->offset;
 	int count = 0;
 	struct dma_async_tx_descriptor *tx;
 	struct async_submit_ctl submit;
@@ -1423,19 +1512,22 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
 		__func__, (unsigned long long)sh->sector, target);
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 
-	for (i = disks; i--; )
-		if (i != target)
+	for (i = disks; i--; ) {
+		if (i != target) {
+			off_srcs[count] = sh->dev[i].offset;
 			xor_srcs[count++] = sh->dev[i].page;
+		}
+	}
 
 	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, 0));
 	if (unlikely(count == 1))
-		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0,
+		tx = async_memcpy(xor_dest, xor_srcs[0], off_dest, off_srcs[0],
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 	else
-		tx = async_xor(xor_dest, xor_srcs, 0, count,
+		tx = async_xor_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 
 	return tx;
@@ -1443,6 +1535,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
 
 /* set_syndrome_sources - populate source buffers for gen_syndrome
  * @srcs - (struct page *) array of size sh->disks
+ * @offs - (unsigned int) array of offset for each page
  * @sh - stripe_head to parse
  *
  * Populates srcs in proper layout order for the stripe and returns the
@@ -1451,6 +1544,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
  * is recorded in srcs[count+1]].
  */
 static int set_syndrome_sources(struct page **srcs,
+				unsigned int *offs,
 				struct stripe_head *sh,
 				int srctype)
 {
@@ -1481,6 +1575,12 @@ static int set_syndrome_sources(struct page **srcs,
 				srcs[slot] = sh->dev[i].orig_page;
 			else
 				srcs[slot] = sh->dev[i].page;
+			/*
+			 * For R5_InJournal, PAGE_SIZE must be 4KB and will
+			 * not shared page. In that case, dev[i].offset
+			 * is 0.
+			 */
+			offs[slot] = sh->dev[i].offset;
 		}
 		i = raid6_next_disk(i, disks);
 	} while (i != d0_idx);
@@ -1493,12 +1593,14 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
 {
 	int disks = sh->disks;
 	struct page **blocks = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	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;
+	unsigned int dest_off;
 	int i;
 	int count;
 
@@ -1517,17 +1619,18 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
 	tgt = &sh->dev[target];
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 	dest = tgt->page;
+	dest_off = tgt->offset;
 
 	atomic_inc(&sh->count);
 
 	if (target == qd_idx) {
-		count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+		count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
 		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, 0));
-		tx = async_gen_syndrome(blocks, 0, count+2,
+		tx = async_gen_syndrome(blocks, offs, count+2,
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 	} else {
 		/* Compute any data- or p-drive using XOR */
@@ -1535,13 +1638,14 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
 		for (i = disks; i-- ; ) {
 			if (i == target || i == qd_idx)
 				continue;
+			offs[count] = sh->dev[i].offset;
 			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, 0));
-		tx = async_xor(dest, blocks, 0, count,
+		tx = async_xor_offs(dest, dest_off, blocks, offs, count,
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 	}
 
@@ -1561,6 +1665,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 	struct r5dev *tgt2 = &sh->dev[target2];
 	struct dma_async_tx_descriptor *tx;
 	struct page **blocks = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	struct async_submit_ctl submit;
 
 	BUG_ON(sh->batch_head);
@@ -1573,13 +1678,16 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 	/* we need to open-code set_syndrome_sources to handle the
 	 * slot number conversion for 'faila' and 'failb'
 	 */
-	for (i = 0; i < disks ; i++)
+	for (i = 0; i < disks ; i++) {
+		offs[i] = 0;
 		blocks[i] = NULL;
+	}
 	count = 0;
 	i = d0_idx;
 	do {
 		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
 
+		offs[slot] = sh->dev[i].offset;
 		blocks[slot] = sh->dev[i].page;
 
 		if (i == target)
@@ -1604,11 +1712,12 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
 					  ops_complete_compute, sh,
 					  to_addr_conv(sh, percpu, 0));
-			return async_gen_syndrome(blocks, 0, syndrome_disks+2,
+			return async_gen_syndrome(blocks, offs, syndrome_disks+2,
 						  RAID5_STRIPE_SIZE(sh->raid_conf),
 						  &submit);
 		} else {
 			struct page *dest;
+			unsigned int dest_off;
 			int data_target;
 			int qd_idx = sh->qd_idx;
 
@@ -1622,22 +1731,24 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			for (i = disks; i-- ; ) {
 				if (i == data_target || i == qd_idx)
 					continue;
+				offs[count] = sh->dev[i].offset;
 				blocks[count++] = sh->dev[i].page;
 			}
 			dest = sh->dev[data_target].page;
+			dest_off = sh->dev[data_target].offset;
 			init_async_submit(&submit,
 					  ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
 					  NULL, NULL, NULL,
 					  to_addr_conv(sh, percpu, 0));
-			tx = async_xor(dest, blocks, 0, count,
+			tx = async_xor_offs(dest, dest_off, blocks, offs, count,
 				       RAID5_STRIPE_SIZE(sh->raid_conf),
 				       &submit);
 
-			count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+			count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
 			init_async_submit(&submit, ASYNC_TX_FENCE, tx,
 					  ops_complete_compute, sh,
 					  to_addr_conv(sh, percpu, 0));
-			return async_gen_syndrome(blocks, 0, count+2,
+			return async_gen_syndrome(blocks, offs, count+2,
 						  RAID5_STRIPE_SIZE(sh->raid_conf),
 						  &submit);
 		}
@@ -1650,13 +1761,13 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			return async_raid6_datap_recov(syndrome_disks+2,
 						RAID5_STRIPE_SIZE(sh->raid_conf),
 						faila,
-						blocks, &submit);
+						blocks, offs, &submit);
 		} else {
 			/* We're missing D+D. */
 			return async_raid6_2data_recov(syndrome_disks+2,
 						RAID5_STRIPE_SIZE(sh->raid_conf),
 						faila, failb,
-						blocks, &submit);
+						blocks, offs, &submit);
 		}
 	}
 }
@@ -1682,10 +1793,12 @@ ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
 {
 	int disks = sh->disks;
 	struct page **xor_srcs = to_addr_page(percpu, 0);
+	unsigned int *off_srcs = to_addr_offs(sh, percpu);
 	int count = 0, pd_idx = sh->pd_idx, i;
 	struct async_submit_ctl submit;
 
 	/* existing parity data subtracted */
+	unsigned int off_dest = off_srcs[count] = sh->dev[pd_idx].offset;
 	struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
 
 	BUG_ON(sh->batch_head);
@@ -1695,15 +1808,22 @@ ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		/* Only process blocks that are known to be uptodate */
-		if (test_bit(R5_InJournal, &dev->flags))
+		if (test_bit(R5_InJournal, &dev->flags)) {
+			/*
+			 * For this case, PAGE_SIZE must be equal to 4KB and
+			 * page offset is zero.
+			 */
+			off_srcs[count] = dev->offset;
 			xor_srcs[count++] = dev->orig_page;
-		else if (test_bit(R5_Wantdrain, &dev->flags))
+		} else if (test_bit(R5_Wantdrain, &dev->flags)) {
+			off_srcs[count] = dev->offset;
 			xor_srcs[count++] = dev->page;
 		}
+	}
 
 	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
-	tx = async_xor(xor_dest, xor_srcs, 0, count,
+	tx = async_xor_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
 			RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 
 	return tx;
@@ -1714,17 +1834,18 @@ ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
 		struct dma_async_tx_descriptor *tx)
 {
 	struct page **blocks = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	int count;
 	struct async_submit_ctl submit;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_WANT_DRAIN);
+	count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_WANT_DRAIN);
 
 	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx,
 			  ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
-	tx = async_gen_syndrome(blocks, 0, count+2,
+	tx = async_gen_syndrome(blocks, offs, count+2,
 			RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 
 	return tx;
@@ -1775,6 +1896,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 					set_bit(R5_Discard, &dev->flags);
 				else {
 					tx = async_copy_data(1, wbi, &dev->page,
+							     dev->offset,
 							     dev->sector, tx, sh,
 							     r5c_is_writeback(conf->log));
 					if (dev->page != dev->orig_page &&
@@ -1854,9 +1976,11 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
 {
 	int disks = sh->disks;
 	struct page **xor_srcs;
+	unsigned int *off_srcs;
 	struct async_submit_ctl submit;
 	int count, pd_idx = sh->pd_idx, i;
 	struct page *xor_dest;
+	unsigned int off_dest;
 	int prexor = 0;
 	unsigned long flags;
 	int j = 0;
@@ -1881,26 +2005,33 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
 again:
 	count = 0;
 	xor_srcs = to_addr_page(percpu, j);
+	off_srcs = to_addr_offs(sh, percpu);
 	/* check if prexor is active which means only process blocks
 	 * that are part of a read-modify-write (written)
 	 */
 	if (head_sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
 		prexor = 1;
+		off_dest = off_srcs[count] = sh->dev[pd_idx].offset;
 		xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (head_sh->dev[i].written ||
-			    test_bit(R5_InJournal, &head_sh->dev[i].flags))
+			    test_bit(R5_InJournal, &head_sh->dev[i].flags)) {
+				off_srcs[count] = dev->offset;
 				xor_srcs[count++] = dev->page;
 			}
+		}
 	} else {
 		xor_dest = sh->dev[pd_idx].page;
+		off_dest = sh->dev[pd_idx].offset;
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
-			if (i != pd_idx)
+			if (i != pd_idx) {
+				off_srcs[count] = dev->offset;
 				xor_srcs[count++] = dev->page;
 			}
 		}
+	}
 
 	/* 1/ if we prexor'd then the dest is reused as a source
 	 * 2/ if we did not prexor then we are redoing the parity
@@ -1924,10 +2055,10 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
 	}
 
 	if (unlikely(count == 1))
-		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0,
+		tx = async_memcpy(xor_dest, xor_srcs[0], off_dest, off_srcs[0],
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 	else
-		tx = async_xor(xor_dest, xor_srcs, 0, count,
+		tx = async_xor_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 	if (!last_stripe) {
 		j++;
@@ -1943,6 +2074,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 {
 	struct async_submit_ctl submit;
 	struct page **blocks;
+	unsigned int *offs;
 	int count, i, j = 0;
 	struct stripe_head *head_sh = sh;
 	int last_stripe;
@@ -1967,6 +2099,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 
 again:
 	blocks = to_addr_page(percpu, j);
+	offs = to_addr_offs(sh, percpu);
 
 	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
 		synflags = SYNDROME_SRC_WRITTEN;
@@ -1976,7 +2109,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 		txflags = ASYNC_TX_ACK;
 	}
 
-	count = set_syndrome_sources(blocks, sh, synflags);
+	count = set_syndrome_sources(blocks, offs, sh, synflags);
 	last_stripe = !head_sh->batch_head ||
 		list_first_entry(&sh->batch_list,
 				 struct stripe_head, batch_list) == head_sh;
@@ -1988,7 +2121,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 	} else
 		init_async_submit(&submit, 0, tx, NULL, NULL,
 				  to_addr_conv(sh, percpu, j));
-	tx = async_gen_syndrome(blocks, 0, count+2,
+	tx = async_gen_syndrome(blocks, offs, count+2,
 			RAID5_STRIPE_SIZE(sh->raid_conf),  &submit);
 	if (!last_stripe) {
 		j++;
@@ -2016,7 +2149,9 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
 	int pd_idx = sh->pd_idx;
 	int qd_idx = sh->qd_idx;
 	struct page *xor_dest;
+	unsigned int off_dest;
 	struct page **xor_srcs = to_addr_page(percpu, 0);
+	unsigned int *off_srcs = to_addr_offs(sh, percpu);
 	struct dma_async_tx_descriptor *tx;
 	struct async_submit_ctl submit;
 	int count;
@@ -2028,16 +2163,19 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
 	BUG_ON(sh->batch_head);
 	count = 0;
 	xor_dest = sh->dev[pd_idx].page;
+	off_dest = sh->dev[pd_idx].offset;
+	off_srcs[count] = off_dest;
 	xor_srcs[count++] = xor_dest;
 	for (i = disks; i--; ) {
 		if (i == pd_idx || i == qd_idx)
 			continue;
+		off_srcs[count] = sh->dev[i].offset;
 		xor_srcs[count++] = sh->dev[i].page;
 	}
 
 	init_async_submit(&submit, 0, NULL, NULL, NULL,
 			  to_addr_conv(sh, percpu, 0));
-	tx = async_xor_val(xor_dest, xor_srcs, 0, count,
+	tx = async_xor_val_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
 			   RAID5_STRIPE_SIZE(sh->raid_conf),
 			   &sh->ops.zero_sum_result, &submit);
 
@@ -2049,6 +2187,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
 static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
 {
 	struct page **srcs = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	struct async_submit_ctl submit;
 	int count;
 
@@ -2056,16 +2195,16 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
 		(unsigned long long)sh->sector, checkp);
 
 	BUG_ON(sh->batch_head);
-	count = set_syndrome_sources(srcs, sh, SYNDROME_SRC_ALL);
+	count = set_syndrome_sources(srcs, offs, sh, SYNDROME_SRC_ALL);
 	if (!checkp)
 		srcs[count] = NULL;
 
 	atomic_inc(&sh->count);
 	init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
 			  sh, to_addr_conv(sh, percpu, 0));
-	async_syndrome_val(srcs, 0, count+2,
+	async_syndrome_val(srcs, offs, count+2,
 			   RAID5_STRIPE_SIZE(sh->raid_conf),
-			   &sh->ops.zero_sum_result, percpu->spare_page, &submit);
+			   &sh->ops.zero_sum_result, percpu->spare_page, 0, &submit);
 }
 
 static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
@@ -2142,6 +2281,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 
 static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
 {
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+	kfree(sh->pages);
+#endif
 	if (sh->ppl_page)
 		__free_page(sh->ppl_page);
 	kmem_cache_free(sc, sh);
@@ -2175,9 +2317,15 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
 			sh->ppl_page = alloc_page(gfp);
 			if (!sh->ppl_page) {
 				free_stripe(sc, sh);
-				sh = NULL;
+				return NULL;
 			}
 		}
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+		if (init_stripe_shared_pages(sh, conf, disks)) {
+			free_stripe(sc, sh);
+			return NULL;
+		}
+#endif
 	}
 	return sh;
 }
@@ -2253,8 +2401,9 @@ static int scribble_alloc(struct raid5_percpu *percpu,
 			  int num, int cnt)
 {
 	size_t obj_size =
-		sizeof(struct page *) * (num+2) +
-		sizeof(addr_conv_t) * (num+2);
+		sizeof(struct page *) * (num + 2) +
+		sizeof(addr_conv_t) * (num + 2) +
+		sizeof(unsigned int) * (num + 2);
 	void *scribble;
 
 	/*
@@ -2386,9 +2535,16 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		osh = get_free_stripe(conf, hash);
 		unlock_device_hash_lock(conf, hash);
 
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+	for (i = 0; i < osh->nr_pages; i++) {
+		nsh->pages[i] = osh->pages[i];
+		osh->pages[i] = NULL;
+	}
+#endif
 		for(i=0; i<conf->pool_size; i++) {
 			nsh->dev[i].page = osh->dev[i].page;
 			nsh->dev[i].orig_page = osh->dev[i].page;
+			nsh->dev[i].offset = osh->dev[i].offset;
 		}
 		nsh->hash_lock_index = hash;
 		free_stripe(conf->slab_cache, osh);
@@ -2439,14 +2595,33 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
 		list_del_init(&nsh->lru);
 
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+		for (i = 0; i < nsh->nr_pages; i++) {
+			if (nsh->pages[i])
+				continue;
+			nsh->pages[i] = alloc_page(GFP_NOIO);
+			if (!nsh->pages[i])
+				err = -ENOMEM;
+		}
+
+		for (i = conf->raid_disks; i < newsize; i++) {
+			if (nsh->dev[i].page)
+				continue;
+			nsh->dev[i].page = raid5_get_dev_page(nsh, i);
+			nsh->dev[i].orig_page = nsh->dev[i].page;
+			nsh->dev[i].offset = raid5_get_page_offset(nsh, i);
+		}
+#else
 		for (i=conf->raid_disks; i < newsize; i++)
 			if (nsh->dev[i].page == NULL) {
 				struct page *p = alloc_page(GFP_NOIO);
 				nsh->dev[i].page = p;
 				nsh->dev[i].orig_page = p;
+				nsh->dev[i].offset = 0;
 				if (!p)
 					err = -ENOMEM;
 			}
+#endif
 		raid5_release_stripe(nsh);
 	}
 	/* critical section pass, GFP_NOIO no longer needed */
@@ -4369,7 +4544,8 @@ static void handle_stripe_expansion(struct r5conf *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, RAID5_STRIPE_SIZE(conf),
+					  sh->dev[i].page, sh2->dev[dd_idx].offset,
+					  sh->dev[i].offset, RAID5_STRIPE_SIZE(conf),
 					  &submit);
 
 			set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
@@ -6506,6 +6682,7 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 	struct r5conf *conf;
 	unsigned long new;
 	int err;
+	int size;
 
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
@@ -6538,10 +6715,29 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 	pr_debug("md/raid: change stripe_size from %lu to %lu\n",
 			conf->stripe_size, new);
 
+	if (mddev->sync_thread ||
+		test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+		mddev->reshape_position != MaxSector ||
+		mddev->sysfs_active) {
+		err = -EBUSY;
+		goto out_unlock;
+	}
+
 	mddev_suspend(mddev);
+	mutex_lock(&conf->cache_size_mutex);
+	size = conf->max_nr_stripes;
+
+	shrink_stripes(conf);
+
 	conf->stripe_size = new;
 	conf->stripe_shift = ilog2(new) - 9;
 	conf->stripe_sectors = new >> 9;
+	if (grow_stripes(conf, size)) {
+		pr_warn("md/raid:%s: couldn't allocate buffers\n",
+				mdname(mddev));
+		err = -ENOMEM;
+	}
+	mutex_unlock(&conf->cache_size_mutex);
 	mddev_resume(mddev);
 
 out_unlock:

drivers/md/raid5.h

@@ -195,6 +195,7 @@ enum reconstruct_states {
 	reconstruct_state_result,
 };
 
+#define DEFAULT_STRIPE_SIZE	4096
 struct stripe_head {
 	struct hlist_node	hash;
 	struct list_head	lru;	      /* inactive_list or handle_list */
@@ -246,6 +247,13 @@ struct stripe_head {
 		int 		     target, target2;
 		enum sum_check_flags zero_sum_result;
 	} ops;
+
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+	/* These pages will be used by bios in dev[i] */
+	struct page	**pages;
+	int	nr_pages;	/* page array size */
+	int	stripes_per_page;
+#endif
 	struct r5dev {
 		/* rreq and rvec are used for the replacement device when
 		 * writing data to both devices.
@@ -253,6 +261,7 @@ struct stripe_head {
 		struct bio	req, rreq;
 		struct bio_vec	vec, rvec;
 		struct page	*page, *orig_page;
+		unsigned int    offset;     /* offset of the page */
 		struct bio	*toread, *read, *towrite, *written;
 		sector_t	sector;			/* sector of this page */
 		unsigned long	flags;
@@ -472,7 +481,6 @@ struct disk_info {
  */
 
 #define NR_STRIPES		256
-#define DEFAULT_STRIPE_SIZE	4096
 
 #if PAGE_SIZE == DEFAULT_STRIPE_SIZE
 #define STRIPE_SIZE		PAGE_SIZE
@@ -771,6 +779,25 @@ static inline int algorithm_is_DDF(int layout)
 	return layout >= 8 && layout <= 10;
 }
 
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+/*
+ * Return offset of the corresponding page for r5dev.
+ */
+static inline int raid5_get_page_offset(struct stripe_head *sh, int disk_idx)
+{
+	return (disk_idx % sh->stripes_per_page) * RAID5_STRIPE_SIZE(sh->raid_conf);
+}
+
+/*
+ * Return corresponding page address for r5dev.
+ */
+static inline struct page *
+raid5_get_dev_page(struct stripe_head *sh, int disk_idx)
+{
+	return sh->pages[disk_idx / sh->stripes_per_page];
+}
+#endif
+
 extern void md_raid5_kick_device(struct r5conf *conf);
 extern int raid5_set_cache_size(struct mddev *mddev, int size);
 extern sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous);

include/linux/async_tx.h

@@ -162,11 +162,22 @@ struct dma_async_tx_descriptor *
 async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	  int src_cnt, size_t len, struct async_submit_ctl *submit);
 
+struct dma_async_tx_descriptor *
+async_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offset,
+		int src_cnt, size_t len, struct async_submit_ctl *submit);
+
 struct dma_async_tx_descriptor *
 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_xor_val_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_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,
@@ -175,21 +186,23 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 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,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, 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,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt,
 		   size_t len, enum sum_check_flags *pqres, struct page *spare,
-		   struct async_submit_ctl *submit);
+		   unsigned int s_off, 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 page **ptrs, unsigned int *offs,
+			struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_raid6_datap_recov(int src_num, size_t bytes, int faila,
-			struct page **ptrs, struct async_submit_ctl *submit);
+			struct page **ptrs, unsigned int *offs,
+			struct async_submit_ctl *submit);
 
 void async_tx_quiesce(struct dma_async_tx_descriptor **tx);
 #endif /* _ASYNC_TX_H_ */