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_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.h

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

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_ */