Merge tag 'drivers-5.10-2020-10-12' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Here are the driver updates for 5.10.

  A few SCSI updates in here too, in coordination with Martin as they
  depend on core block changes for the shared tag bitmap.

  This contains:

   - NVMe pull requests via Christoph:
      - fix keep alive timer modification (Amit Engel)
      - order the PCI ID list more sensibly (Andy Shevchenko)
      - cleanup the open by controller helper (Chaitanya Kulkarni)
      - use an xarray for the CSE log lookup (Chaitanya Kulkarni)
      - support ZNS in nvmet passthrough mode (Chaitanya Kulkarni)
      - fix nvme_ns_report_zones (Christoph Hellwig)
      - add a sanity check to nvmet-fc (James Smart)
      - fix interrupt allocation when too many polled queues are
        specified (Jeffle Xu)
      - small nvmet-tcp optimization (Mark Wunderlich)
      - fix a controller refcount leak on init failure (Chaitanya
        Kulkarni)
      - misc cleanups (Chaitanya Kulkarni)
      - major refactoring of the scanning code (Christoph Hellwig)

   - MD updates via Song:
      - Bug fixes in bitmap code, from Zhao Heming
      - Fix a work queue check, from Guoqing Jiang
      - Fix raid5 oops with reshape, from Song Liu
      - Clean up unused code, from Jason Yan
      - Discard improvements, from Xiao Ni
      - raid5/6 page offset support, from Yufen Yu

   - Shared tag bitmap for SCSI/hisi_sas/null_blk (John, Kashyap,
     Hannes)

   - null_blk open/active zone limit support (Niklas)

   - Set of bcache updates (Coly, Dongsheng, Qinglang)"

* tag 'drivers-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (78 commits)
  md/raid5: fix oops during stripe resizing
  md/bitmap: fix memory leak of temporary bitmap
  md: fix the checking of wrong work queue
  md/bitmap: md_bitmap_get_counter returns wrong blocks
  md/bitmap: md_bitmap_read_sb uses wrong bitmap blocks
  md/raid0: remove unused function is_io_in_chunk_boundary()
  nvme-core: remove extra condition for vwc
  nvme-core: remove extra variable
  nvme: remove nvme_identify_ns_list
  nvme: refactor nvme_validate_ns
  nvme: move nvme_validate_ns
  nvme: query namespace identifiers before adding the namespace
  nvme: revalidate zone bitmaps in nvme_update_ns_info
  nvme: remove nvme_update_formats
  nvme: update the known admin effects
  nvme: set the queue limits in nvme_update_ns_info
  nvme: remove the 0 lba_shift check in nvme_update_ns_info
  nvme: clean up the check for too large logic block sizes
  nvme: freeze the queue over ->lba_shift updates
  nvme: factor out a nvme_configure_metadata helper
  ...

block/scsi_ioctl.c

@@ -644,7 +644,7 @@ struct compat_cdrom_generic_command {
 	unsigned char	pad[3];
 	compat_int_t	quiet;
 	compat_int_t	timeout;
-	compat_caddr_t	reserved[1];
+	compat_caddr_t	unused;
 };
 #endif
 
@@ -666,7 +666,7 @@ static int scsi_get_cdrom_generic_arg(struct cdrom_generic_command *cgc,
 			.data_direction	= cgc32.data_direction,
 			.quiet		= cgc32.quiet,
 			.timeout	= cgc32.timeout,
-			.reserved[0]	= compat_ptr(cgc32.reserved[0]),
+			.unused		= compat_ptr(cgc32.unused),
 		};
 		memcpy(&cgc->cmd, &cgc32.cmd, CDROM_PACKET_SIZE);
 		return 0;
@@ -691,7 +691,7 @@ static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc,
 			.data_direction	= cgc->data_direction,
 			.quiet		= cgc->quiet,
 			.timeout	= cgc->timeout,
-			.reserved[0]	= (uintptr_t)(cgc->reserved[0]),
+			.unused		= (uintptr_t)(cgc->unused),
 		};
 		memcpy(&cgc32.cmd, &cgc->cmd, CDROM_PACKET_SIZE);
 

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
@@ -157,8 +179,9 @@ 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,
-	  int src_cnt, size_t len, struct async_submit_ctl *submit)
+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,
 						      &dest, 1, src_list,
@@ -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
@@ -253,9 +310,10 @@ 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,
-	      int src_cnt, size_t len, enum sum_check_flags *result,
-	      struct async_submit_ctl *submit)
+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)
 {
 	struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
@@ -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/block/null_blk.h

@@ -42,6 +42,9 @@ struct nullb_device {
 	struct badblocks badblocks;
 
 	unsigned int nr_zones;
+	unsigned int nr_zones_imp_open;
+	unsigned int nr_zones_exp_open;
+	unsigned int nr_zones_closed;
 	struct blk_zone *zones;
 	sector_t zone_size_sects;
 
@@ -51,6 +54,8 @@ struct nullb_device {
 	unsigned long zone_size; /* zone size in MB if device is zoned */
 	unsigned long zone_capacity; /* zone capacity in MB if device is zoned */
 	unsigned int zone_nr_conv; /* number of conventional zones */
+	unsigned int zone_max_open; /* max number of open zones */
+	unsigned int zone_max_active; /* max number of active zones */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int home_node; /* home node for the device */
 	unsigned int queue_mode; /* block interface */

drivers/block/null_blk_main.c

@@ -164,6 +164,10 @@ static bool shared_tags;
 module_param(shared_tags, bool, 0444);
 MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
 
+static bool g_shared_tag_bitmap;
+module_param_named(shared_tag_bitmap, g_shared_tag_bitmap, bool, 0444);
+MODULE_PARM_DESC(shared_tag_bitmap, "Use shared tag bitmap for all submission queues for blk-mq");
+
 static int g_irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -208,6 +212,14 @@ static unsigned int g_zone_nr_conv;
 module_param_named(zone_nr_conv, g_zone_nr_conv, uint, 0444);
 MODULE_PARM_DESC(zone_nr_conv, "Number of conventional zones when block device is zoned. Default: 0");
 
+static unsigned int g_zone_max_open;
+module_param_named(zone_max_open, g_zone_max_open, uint, 0444);
+MODULE_PARM_DESC(zone_max_open, "Maximum number of open zones when block device is zoned. Default: 0 (no limit)");
+
+static unsigned int g_zone_max_active;
+module_param_named(zone_max_active, g_zone_max_active, uint, 0444);
+MODULE_PARM_DESC(zone_max_active, "Maximum number of active zones when block device is zoned. Default: 0 (no limit)");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -347,6 +359,8 @@ NULLB_DEVICE_ATTR(zoned, bool, NULL);
 NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
+NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
+NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -464,6 +478,8 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_size,
 	&nullb_device_attr_zone_capacity,
 	&nullb_device_attr_zone_nr_conv,
+	&nullb_device_attr_zone_max_open,
+	&nullb_device_attr_zone_max_active,
 	NULL,
 };
 
@@ -517,7 +533,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
-			"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv\n");
+			"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv,zone_max_open,zone_max_active\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -580,6 +596,8 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_size = g_zone_size;
 	dev->zone_capacity = g_zone_capacity;
 	dev->zone_nr_conv = g_zone_nr_conv;
+	dev->zone_max_open = g_zone_max_open;
+	dev->zone_max_active = g_zone_max_active;
 	return dev;
 }
 
@@ -1692,6 +1710,8 @@ static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
 	set->flags = BLK_MQ_F_SHOULD_MERGE;
 	if (g_no_sched)
 		set->flags |= BLK_MQ_F_NO_SCHED;
+	if (g_shared_tag_bitmap)
+		set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
 	set->driver_data = NULL;
 
 	if ((nullb && nullb->dev->blocking) || g_blocking)

drivers/block/rsxx/core.c

@@ -439,7 +439,7 @@ static void card_state_change(struct rsxx_cardinfo *card,
 	case CARD_STATE_FAULT:
 		dev_crit(CARD_TO_DEV(card),
 			"Hardware Fault reported!\n");
-		/* Fall through. */
+		fallthrough;
 
 	/* Everything else, detach DMA interface if it's attached. */
 	case CARD_STATE_SHUTDOWN:

drivers/md/bcache/alloc.c

@@ -49,7 +49,7 @@
  *
  * bch_bucket_alloc() allocates a single bucket from a specific cache.
  *
- * bch_bucket_alloc_set() allocates one or more buckets from different caches
+ * bch_bucket_alloc_set() allocates one  bucket from different caches
  * out of a cache set.
  *
  * free_some_buckets() drives all the processes described above. It's called
@@ -87,8 +87,7 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
 {
 	struct cache *ca;
 	struct bucket *b;
-	unsigned long next = c->nbuckets * c->sb.bucket_size / 1024;
-	unsigned int i;
+	unsigned long next = c->nbuckets * c->cache->sb.bucket_size / 1024;
 	int r;
 
 	atomic_sub(sectors, &c->rescale);
@@ -104,14 +103,14 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
 
 	c->min_prio = USHRT_MAX;
 
-	for_each_cache(ca, c, i)
-		for_each_bucket(b, ca)
-			if (b->prio &&
-			    b->prio != BTREE_PRIO &&
-			    !atomic_read(&b->pin)) {
-				b->prio--;
-				c->min_prio = min(c->min_prio, b->prio);
-			}
+	ca = c->cache;
+	for_each_bucket(b, ca)
+		if (b->prio &&
+		    b->prio != BTREE_PRIO &&
+		    !atomic_read(&b->pin)) {
+			b->prio--;
+			c->min_prio = min(c->min_prio, b->prio);
+		}
 
 	mutex_unlock(&c->bucket_lock);
 }
@@ -362,7 +361,7 @@ static int bch_allocator_thread(void *arg)
 		 * new stuff to them:
 		 */
 		allocator_wait(ca, !atomic_read(&ca->set->prio_blocked));
-		if (CACHE_SYNC(&ca->set->sb)) {
+		if (CACHE_SYNC(&ca->sb)) {
 			/*
 			 * This could deadlock if an allocation with a btree
 			 * node locked ever blocked - having the btree node
@@ -488,34 +487,29 @@ void bch_bucket_free(struct cache_set *c, struct bkey *k)
 }
 
 int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
-			   struct bkey *k, int n, bool wait)
+			   struct bkey *k, bool wait)
 {
-	int i;
+	struct cache *ca;
+	long b;
 
 	/* No allocation if CACHE_SET_IO_DISABLE bit is set */
 	if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
 		return -1;
 
 	lockdep_assert_held(&c->bucket_lock);
-	BUG_ON(!n || n > c->caches_loaded || n > MAX_CACHES_PER_SET);
 
 	bkey_init(k);
 
-	/* sort by free space/prio of oldest data in caches */
-
-	for (i = 0; i < n; i++) {
-		struct cache *ca = c->cache_by_alloc[i];
-		long b = bch_bucket_alloc(ca, reserve, wait);
+	ca = c->cache;
+	b = bch_bucket_alloc(ca, reserve, wait);
+	if (b == -1)
+		goto err;
 
-		if (b == -1)
-			goto err;
+	k->ptr[0] = MAKE_PTR(ca->buckets[b].gen,
+			     bucket_to_sector(c, b),
+			     ca->sb.nr_this_dev);
 
-		k->ptr[i] = MAKE_PTR(ca->buckets[b].gen,
-				bucket_to_sector(c, b),
-				ca->sb.nr_this_dev);
-
-		SET_KEY_PTRS(k, i + 1);
-	}
+	SET_KEY_PTRS(k, 1);
 
 	return 0;
 err:
@@ -525,12 +519,12 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
 }
 
 int bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
-			 struct bkey *k, int n, bool wait)
+			 struct bkey *k, bool wait)
 {
 	int ret;
 
 	mutex_lock(&c->bucket_lock);
-	ret = __bch_bucket_alloc_set(c, reserve, k, n, wait);
+	ret = __bch_bucket_alloc_set(c, reserve, k, wait);
 	mutex_unlock(&c->bucket_lock);
 	return ret;
 }
@@ -589,7 +583,7 @@ static struct open_bucket *pick_data_bucket(struct cache_set *c,
 					   struct open_bucket, list);
 found:
 	if (!ret->sectors_free && KEY_PTRS(alloc)) {
-		ret->sectors_free = c->sb.bucket_size;
+		ret->sectors_free = c->cache->sb.bucket_size;
 		bkey_copy(&ret->key, alloc);
 		bkey_init(alloc);
 	}
@@ -638,7 +632,7 @@ bool bch_alloc_sectors(struct cache_set *c,
 
 		spin_unlock(&c->data_bucket_lock);
 
-		if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, wait))
+		if (bch_bucket_alloc_set(c, watermark, &alloc.key, wait))
 			return false;
 
 		spin_lock(&c->data_bucket_lock);
@@ -683,7 +677,7 @@ bool bch_alloc_sectors(struct cache_set *c,
 				&PTR_CACHE(c, &b->key, i)->sectors_written);
 	}
 
-	if (b->sectors_free < c->sb.block_size)
+	if (b->sectors_free < c->cache->sb.block_size)
 		b->sectors_free = 0;
 
 	/*

drivers/md/bcache/bcache.h

@@ -517,11 +517,7 @@ struct cache_set {
 	atomic_t		idle_counter;
 	atomic_t		at_max_writeback_rate;
 
-	struct cache_sb		sb;
-
-	struct cache		*cache[MAX_CACHES_PER_SET];
-	struct cache		*cache_by_alloc[MAX_CACHES_PER_SET];
-	int			caches_loaded;
+	struct cache		*cache;
 
 	struct bcache_device	**devices;
 	unsigned int		devices_max_used;
@@ -670,6 +666,7 @@ struct cache_set {
 	struct mutex		verify_lock;
 #endif
 
+	uint8_t			set_uuid[16];
 	unsigned int		nr_uuids;
 	struct uuid_entry	*uuids;
 	BKEY_PADDED(uuid_bucket);
@@ -758,9 +755,8 @@ struct bbio {
 #define btree_default_blocks(c)						\
 	((unsigned int) ((PAGE_SECTORS * (c)->btree_pages) >> (c)->block_bits))
 
-#define bucket_pages(c)		((c)->sb.bucket_size / PAGE_SECTORS)
-#define bucket_bytes(c)		((c)->sb.bucket_size << 9)
-#define block_bytes(c)		((c)->sb.block_size << 9)
+#define bucket_bytes(ca)	((ca)->sb.bucket_size << 9)
+#define block_bytes(ca)		((ca)->sb.block_size << 9)
 
 static inline unsigned int meta_bucket_pages(struct cache_sb *sb)
 {
@@ -801,14 +797,14 @@ static inline sector_t bucket_to_sector(struct cache_set *c, size_t b)
 
 static inline sector_t bucket_remainder(struct cache_set *c, sector_t s)
 {
-	return s & (c->sb.bucket_size - 1);
+	return s & (c->cache->sb.bucket_size - 1);
 }
 
 static inline struct cache *PTR_CACHE(struct cache_set *c,
 				      const struct bkey *k,
 				      unsigned int ptr)
 {
-	return c->cache[PTR_DEV(k, ptr)];
+	return c->cache;
 }
 
 static inline size_t PTR_BUCKET_NR(struct cache_set *c,
@@ -889,9 +885,6 @@ do {									\
 
 /* Looping macros */
 
-#define for_each_cache(ca, cs, iter)					\
-	for (iter = 0; ca = cs->cache[iter], iter < (cs)->sb.nr_in_set; iter++)
-
 #define for_each_bucket(b, ca)						\
 	for (b = (ca)->buckets + (ca)->sb.first_bucket;			\
 	     b < (ca)->buckets + (ca)->sb.nbuckets; b++)
@@ -933,11 +926,9 @@ static inline uint8_t bucket_gc_gen(struct bucket *b)
 
 static inline void wake_up_allocators(struct cache_set *c)
 {
-	struct cache *ca;
-	unsigned int i;
+	struct cache *ca = c->cache;
 
-	for_each_cache(ca, c, i)
-		wake_up_process(ca->alloc_thread);
+	wake_up_process(ca->alloc_thread);
 }
 
 static inline void closure_bio_submit(struct cache_set *c,
@@ -994,9 +985,9 @@ void bch_bucket_free(struct cache_set *c, struct bkey *k);
 
 long bch_bucket_alloc(struct cache *ca, unsigned int reserve, bool wait);
 int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
-			   struct bkey *k, int n, bool wait);
+			   struct bkey *k, bool wait);
 int bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
-			 struct bkey *k, int n, bool wait);
+			 struct bkey *k, bool wait);
 bool bch_alloc_sectors(struct cache_set *c, struct bkey *k,
 		       unsigned int sectors, unsigned int write_point,
 		       unsigned int write_prio, bool wait);

drivers/md/bcache/btree.h

@@ -194,7 +194,7 @@ static inline unsigned int bset_block_offset(struct btree *b, struct bset *i)
 
 static inline void set_gc_sectors(struct cache_set *c)
 {
-	atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 16);
+	atomic_set(&c->sectors_to_gc, c->cache->sb.bucket_size * c->nbuckets / 16);
 }
 
 void bkey_put(struct cache_set *c, struct bkey *k);

drivers/md/bcache/closure.c

@@ -159,7 +159,7 @@ void closure_debug_destroy(struct closure *cl)
 
 static struct dentry *closure_debug;
 
-static int debug_seq_show(struct seq_file *f, void *data)
+static int debug_show(struct seq_file *f, void *data)
 {
 	struct closure *cl;
 
@@ -188,17 +188,7 @@ static int debug_seq_show(struct seq_file *f, void *data)
 	return 0;
 }
 
-static int debug_seq_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, debug_seq_show, NULL);
-}
-
-static const struct file_operations debug_ops = {
-	.owner		= THIS_MODULE,
-	.open		= debug_seq_open,
-	.read		= seq_read,
-	.release	= single_release
-};
+DEFINE_SHOW_ATTRIBUTE(debug);
 
 void  __init closure_debug_init(void)
 {
@@ -209,7 +199,7 @@ void  __init closure_debug_init(void)
 		 * about this.
 		 */
 		closure_debug = debugfs_create_file(
-			"closures", 0400, bcache_debug, NULL, &debug_ops);
+			"closures", 0400, bcache_debug, NULL, &debug_fops);
 }
 #endif
 

drivers/md/bcache/debug.c

@@ -25,8 +25,8 @@ struct dentry *bcache_debug;
 	for (i = (start);						\
 	     (void *) i < (void *) (start) + (KEY_SIZE(&b->key) << 9) &&\
 	     i->seq == (start)->seq;					\
-	     i = (void *) i + set_blocks(i, block_bytes(b->c)) *	\
-		 block_bytes(b->c))
+	     i = (void *) i + set_blocks(i, block_bytes(b->c->cache)) *	\
+		 block_bytes(b->c->cache))
 
 void bch_btree_verify(struct btree *b)
 {
@@ -82,14 +82,14 @@ void bch_btree_verify(struct btree *b)
 
 		for_each_written_bset(b, ondisk, i) {
 			unsigned int block = ((void *) i - (void *) ondisk) /
-				block_bytes(b->c);
+				block_bytes(b->c->cache);
 
 			pr_err("*** on disk block %u:\n", block);
 			bch_dump_bset(&b->keys, i, block);
 		}
 
 		pr_err("*** block %zu not written\n",
-		       ((void *) i - (void *) ondisk) / block_bytes(b->c));
+		       ((void *) i - (void *) ondisk) / block_bytes(b->c->cache));
 
 		for (j = 0; j < inmemory->keys; j++)
 			if (inmemory->d[j] != sorted->d[j])
@@ -238,7 +238,7 @@ void bch_debug_init_cache_set(struct cache_set *c)
 	if (!IS_ERR_OR_NULL(bcache_debug)) {
 		char name[50];
 
-		snprintf(name, 50, "bcache-%pU", c->sb.set_uuid);
+		snprintf(name, 50, "bcache-%pU", c->set_uuid);
 		c->debug = debugfs_create_file(name, 0400, bcache_debug, c,
 					       &cache_set_debug_ops);
 	}

drivers/md/bcache/extents.c

@@ -54,7 +54,7 @@ static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
 			size_t bucket = PTR_BUCKET_NR(c, k, i);
 			size_t r = bucket_remainder(c, PTR_OFFSET(k, i));
 
-			if (KEY_SIZE(k) + r > c->sb.bucket_size ||
+			if (KEY_SIZE(k) + r > c->cache->sb.bucket_size ||
 			    bucket <  ca->sb.first_bucket ||
 			    bucket >= ca->sb.nbuckets)
 				return true;
@@ -75,7 +75,7 @@ static const char *bch_ptr_status(struct cache_set *c, const struct bkey *k)
 			size_t bucket = PTR_BUCKET_NR(c, k, i);
 			size_t r = bucket_remainder(c, PTR_OFFSET(k, i));
 
-			if (KEY_SIZE(k) + r > c->sb.bucket_size)
+			if (KEY_SIZE(k) + r > c->cache->sb.bucket_size)
 				return "bad, length too big";
 			if (bucket <  ca->sb.first_bucket)
 				return "bad, short offset";
@@ -136,7 +136,7 @@ static void bch_bkey_dump(struct btree_keys *keys, const struct bkey *k)
 		size_t n = PTR_BUCKET_NR(b->c, k, j);
 
 		pr_cont(" bucket %zu", n);
-		if (n >= b->c->sb.first_bucket && n < b->c->sb.nbuckets)
+		if (n >= b->c->cache->sb.first_bucket && n < b->c->cache->sb.nbuckets)
 			pr_cont(" prio %i",
 				PTR_BUCKET(b->c, k, j)->prio);
 	}

drivers/md/bcache/features.c

@@ -30,7 +30,7 @@ static struct feature feature_list[] = {
 	for (f = &feature_list[0]; f->compat != 0; f++) {		\
 		if (f->compat != BCH_FEATURE_ ## type)			\
 			continue;					\
-		if (BCH_HAS_ ## type ## _FEATURE(&c->sb, f->mask)) {	\
+		if (BCH_HAS_ ## type ## _FEATURE(&c->cache->sb, f->mask)) {	\
 			if (first) {					\
 				out += snprintf(out, buf + size - out,	\
 						"[");	\
@@ -44,7 +44,7 @@ static struct feature feature_list[] = {
 									\
 		out += snprintf(out, buf + size - out, "%s", f->string);\
 									\
-		if (BCH_HAS_ ## type ## _FEATURE(&c->sb, f->mask))	\
+		if (BCH_HAS_ ## type ## _FEATURE(&c->cache->sb, f->mask))	\
 			out += snprintf(out, buf + size - out, "]");	\
 									\
 		first = false;						\

drivers/md/bcache/io.c

@@ -26,7 +26,7 @@ struct bio *bch_bbio_alloc(struct cache_set *c)
 	struct bbio *b = mempool_alloc(&c->bio_meta, GFP_NOIO);
 	struct bio *bio = &b->bio;
 
-	bio_init(bio, bio->bi_inline_vecs, meta_bucket_pages(&c->sb));
+	bio_init(bio, bio->bi_inline_vecs, meta_bucket_pages(&c->cache->sb));
 
 	return bio;
 }

drivers/md/bcache/journal.c

@@ -98,7 +98,7 @@ reread:		left = ca->sb.bucket_size - offset;
 				return ret;
 			}
 
-			blocks = set_blocks(j, block_bytes(ca->set));
+			blocks = set_blocks(j, block_bytes(ca));
 
 			/*
 			 * Nodes in 'list' are in linear increasing order of
@@ -179,112 +179,109 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
 		ret;							\
 	})
 
-	struct cache *ca;
-	unsigned int iter;
+	struct cache *ca = c->cache;
 	int ret = 0;
+	struct journal_device *ja = &ca->journal;
+	DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
+	unsigned int i, l, r, m;
+	uint64_t seq;
 
-	for_each_cache(ca, c, iter) {
-		struct journal_device *ja = &ca->journal;
-		DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
-		unsigned int i, l, r, m;
-		uint64_t seq;
-
-		bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
-		pr_debug("%u journal buckets\n", ca->sb.njournal_buckets);
+	bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
+	pr_debug("%u journal buckets\n", ca->sb.njournal_buckets);
 
+	/*
+	 * Read journal buckets ordered by golden ratio hash to quickly
+	 * find a sequence of buckets with valid journal entries
+	 */
+	for (i = 0; i < ca->sb.njournal_buckets; i++) {
 		/*
-		 * Read journal buckets ordered by golden ratio hash to quickly
-		 * find a sequence of buckets with valid journal entries
+		 * We must try the index l with ZERO first for
+		 * correctness due to the scenario that the journal
+		 * bucket is circular buffer which might have wrapped
 		 */
-		for (i = 0; i < ca->sb.njournal_buckets; i++) {
-			/*
-			 * We must try the index l with ZERO first for
-			 * correctness due to the scenario that the journal
-			 * bucket is circular buffer which might have wrapped
-			 */
-			l = (i * 2654435769U) % ca->sb.njournal_buckets;
+		l = (i * 2654435769U) % ca->sb.njournal_buckets;
 
-			if (test_bit(l, bitmap))
-				break;
+		if (test_bit(l, bitmap))
+			break;
 
-			if (read_bucket(l))
-				goto bsearch;
-		}
+		if (read_bucket(l))
+			goto bsearch;
+	}
 
-		/*
-		 * If that fails, check all the buckets we haven't checked
-		 * already
-		 */
-		pr_debug("falling back to linear search\n");
+	/*
+	 * If that fails, check all the buckets we haven't checked
+	 * already
+	 */
+	pr_debug("falling back to linear search\n");
 
-		for_each_clear_bit(l, bitmap, ca->sb.njournal_buckets)
-			if (read_bucket(l))
-				goto bsearch;
+	for_each_clear_bit(l, bitmap, ca->sb.njournal_buckets)
+		if (read_bucket(l))
+			goto bsearch;
 
-		/* no journal entries on this device? */
-		if (l == ca->sb.njournal_buckets)
-			continue;
+	/* no journal entries on this device? */
+	if (l == ca->sb.njournal_buckets)
+		goto out;
 bsearch:
-		BUG_ON(list_empty(list));
+	BUG_ON(list_empty(list));
 
-		/* Binary search */
-		m = l;
-		r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
-		pr_debug("starting binary search, l %u r %u\n", l, r);
+	/* Binary search */
+	m = l;
+	r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
+	pr_debug("starting binary search, l %u r %u\n", l, r);
 
-		while (l + 1 < r) {
-			seq = list_entry(list->prev, struct journal_replay,
-					 list)->j.seq;
+	while (l + 1 < r) {
+		seq = list_entry(list->prev, struct journal_replay,
+				 list)->j.seq;
 
-			m = (l + r) >> 1;
-			read_bucket(m);
+		m = (l + r) >> 1;
+		read_bucket(m);
 
-			if (seq != list_entry(list->prev, struct journal_replay,
-					      list)->j.seq)
-				l = m;
-			else
-				r = m;
-		}
+		if (seq != list_entry(list->prev, struct journal_replay,
+				      list)->j.seq)
+			l = m;
+		else
+			r = m;
+	}
 
-		/*
-		 * Read buckets in reverse order until we stop finding more
-		 * journal entries
-		 */
-		pr_debug("finishing up: m %u njournal_buckets %u\n",
-			 m, ca->sb.njournal_buckets);
-		l = m;
+	/*
+	 * Read buckets in reverse order until we stop finding more
+	 * journal entries
+	 */
+	pr_debug("finishing up: m %u njournal_buckets %u\n",
+		 m, ca->sb.njournal_buckets);
+	l = m;
 
-		while (1) {
-			if (!l--)
-				l = ca->sb.njournal_buckets - 1;
+	while (1) {
+		if (!l--)
+			l = ca->sb.njournal_buckets - 1;
 
-			if (l == m)
-				break;
+		if (l == m)
+			break;
 
-			if (test_bit(l, bitmap))
-				continue;
+		if (test_bit(l, bitmap))
+			continue;
 
-			if (!read_bucket(l))
-				break;
-		}
+		if (!read_bucket(l))
+			break;
+	}
 
-		seq = 0;
+	seq = 0;
 
-		for (i = 0; i < ca->sb.njournal_buckets; i++)
-			if (ja->seq[i] > seq) {
-				seq = ja->seq[i];
-				/*
-				 * When journal_reclaim() goes to allocate for
-				 * the first time, it'll use the bucket after
-				 * ja->cur_idx
-				 */
-				ja->cur_idx = i;
-				ja->last_idx = ja->discard_idx = (i + 1) %
-					ca->sb.njournal_buckets;
+	for (i = 0; i < ca->sb.njournal_buckets; i++)
+		if (ja->seq[i] > seq) {
+			seq = ja->seq[i];
+			/*
+			 * When journal_reclaim() goes to allocate for
+			 * the first time, it'll use the bucket after
+			 * ja->cur_idx
+			 */
+			ja->cur_idx = i;
+			ja->last_idx = ja->discard_idx = (i + 1) %
+				ca->sb.njournal_buckets;
 
-			}
-	}
+		}
 
+out:
 	if (!list_empty(list))
 		c->journal.seq = list_entry(list->prev,
 					    struct journal_replay,
@@ -342,12 +339,10 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list)
 
 static bool is_discard_enabled(struct cache_set *s)
 {
-	struct cache *ca;
-	unsigned int i;
+	struct cache *ca = s->cache;
 
-	for_each_cache(ca, s, i)
-		if (ca->discard)
-			return true;
+	if (ca->discard)
+		return true;
 
 	return false;
 }
@@ -633,9 +628,10 @@ static void do_journal_discard(struct cache *ca)
 static void journal_reclaim(struct cache_set *c)
 {
 	struct bkey *k = &c->journal.key;
-	struct cache *ca;
+	struct cache *ca = c->cache;
 	uint64_t last_seq;
-	unsigned int iter, n = 0;
+	unsigned int next;
+	struct journal_device *ja = &ca->journal;
 	atomic_t p __maybe_unused;
 
 	atomic_long_inc(&c->reclaim);
@@ -647,46 +643,31 @@ static void journal_reclaim(struct cache_set *c)
 
 	/* Update last_idx */
 
-	for_each_cache(ca, c, iter) {
-		struct journal_device *ja = &ca->journal;
-
-		while (ja->last_idx != ja->cur_idx &&
-		       ja->seq[ja->last_idx] < last_seq)
-			ja->last_idx = (ja->last_idx + 1) %
-				ca->sb.njournal_buckets;
-	}
+	while (ja->last_idx != ja->cur_idx &&
+	       ja->seq[ja->last_idx] < last_seq)
+		ja->last_idx = (ja->last_idx + 1) %
+			ca->sb.njournal_buckets;
 
-	for_each_cache(ca, c, iter)
-		do_journal_discard(ca);
+	do_journal_discard(ca);
 
 	if (c->journal.blocks_free)
 		goto out;
 
-	/*
-	 * Allocate:
-	 * XXX: Sort by free journal space
-	 */
-
-	for_each_cache(ca, c, iter) {
-		struct journal_device *ja = &ca->journal;
-		unsigned int next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
+	next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
+	/* No space available on this device */
+	if (next == ja->discard_idx)
+		goto out;
 
-		/* No space available on this device */
-		if (next == ja->discard_idx)
-			continue;
+	ja->cur_idx = next;
+	k->ptr[0] = MAKE_PTR(0,
+			     bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
+			     ca->sb.nr_this_dev);
+	atomic_long_inc(&c->reclaimed_journal_buckets);
 
-		ja->cur_idx = next;
-		k->ptr[n++] = MAKE_PTR(0,
-				  bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
-				  ca->sb.nr_this_dev);
-		atomic_long_inc(&c->reclaimed_journal_buckets);
-	}
+	bkey_init(k);
+	SET_KEY_PTRS(k, 1);
+	c->journal.blocks_free = ca->sb.bucket_size >> c->block_bits;
 
-	if (n) {
-		bkey_init(k);
-		SET_KEY_PTRS(k, n);
-		c->journal.blocks_free = c->sb.bucket_size >> c->block_bits;
-	}
 out:
 	if (!journal_full(&c->journal))
 		__closure_wake_up(&c->journal.wait);
@@ -750,11 +731,11 @@ static void journal_write_unlocked(struct closure *cl)
 	__releases(c->journal.lock)
 {
 	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
-	struct cache *ca;
+	struct cache *ca = c->cache;
 	struct journal_write *w = c->journal.cur;
 	struct bkey *k = &c->journal.key;
-	unsigned int i, sectors = set_blocks(w->data, block_bytes(c)) *
-		c->sb.block_size;
+	unsigned int i, sectors = set_blocks(w->data, block_bytes(ca)) *
+		ca->sb.block_size;
 
 	struct bio *bio;
 	struct bio_list list;
@@ -773,17 +754,15 @@ static void journal_write_unlocked(struct closure *cl)
 		return;
 	}
 
-	c->journal.blocks_free -= set_blocks(w->data, block_bytes(c));
+	c->journal.blocks_free -= set_blocks(w->data, block_bytes(ca));
 
 	w->data->btree_level = c->root->level;
 
 	bkey_copy(&w->data->btree_root, &c->root->key);
 	bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);
 
-	for_each_cache(ca, c, i)
-		w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
-
-	w->data->magic		= jset_magic(&c->sb);
+	w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
+	w->data->magic		= jset_magic(&ca->sb);
 	w->data->version	= BCACHE_JSET_VERSION;
 	w->data->last_seq	= last_seq(&c->journal);
 	w->data->csum		= csum_set(w->data);
@@ -859,6 +838,7 @@ static struct journal_write *journal_wait_for_write(struct cache_set *c,
 	size_t sectors;
 	struct closure cl;
 	bool wait = false;
+	struct cache *ca = c->cache;
 
 	closure_init_stack(&cl);
 
@@ -868,10 +848,10 @@ static struct journal_write *journal_wait_for_write(struct cache_set *c,
 		struct journal_write *w = c->journal.cur;
 
 		sectors = __set_blocks(w->data, w->data->keys + nkeys,
-				       block_bytes(c)) * c->sb.block_size;
+				       block_bytes(ca)) * ca->sb.block_size;
 
 		if (sectors <= min_t(size_t,
-				     c->journal.blocks_free * c->sb.block_size,
+				     c->journal.blocks_free * ca->sb.block_size,
 				     PAGE_SECTORS << JSET_BITS))
 			return w;
 
@@ -936,7 +916,7 @@ atomic_t *bch_journal(struct cache_set *c,
 	if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
 		return NULL;
 
-	if (!CACHE_SYNC(&c->sb))
+	if (!CACHE_SYNC(&c->cache->sb))
 		return NULL;
 
 	w = journal_wait_for_write(c, bch_keylist_nkeys(keys));

drivers/md/bcache/movinggc.c

@@ -196,50 +196,48 @@ static unsigned int bucket_heap_top(struct cache *ca)
 
 void bch_moving_gc(struct cache_set *c)
 {
-	struct cache *ca;
+	struct cache *ca = c->cache;
 	struct bucket *b;
-	unsigned int i;
+	unsigned long sectors_to_move, reserve_sectors;
 
 	if (!c->copy_gc_enabled)
 		return;
 
 	mutex_lock(&c->bucket_lock);
 
-	for_each_cache(ca, c, i) {
-		unsigned long sectors_to_move = 0;
-		unsigned long reserve_sectors = ca->sb.bucket_size *
+	sectors_to_move = 0;
+	reserve_sectors = ca->sb.bucket_size *
 			     fifo_used(&ca->free[RESERVE_MOVINGGC]);
 
-		ca->heap.used = 0;
-
-		for_each_bucket(b, ca) {
-			if (GC_MARK(b) == GC_MARK_METADATA ||
-			    !GC_SECTORS_USED(b) ||
-			    GC_SECTORS_USED(b) == ca->sb.bucket_size ||
-			    atomic_read(&b->pin))
-				continue;
-
-			if (!heap_full(&ca->heap)) {
-				sectors_to_move += GC_SECTORS_USED(b);
-				heap_add(&ca->heap, b, bucket_cmp);
-			} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
-				sectors_to_move -= bucket_heap_top(ca);
-				sectors_to_move += GC_SECTORS_USED(b);
-
-				ca->heap.data[0] = b;
-				heap_sift(&ca->heap, 0, bucket_cmp);
-			}
-		}
+	ca->heap.used = 0;
+
+	for_each_bucket(b, ca) {
+		if (GC_MARK(b) == GC_MARK_METADATA ||
+		    !GC_SECTORS_USED(b) ||
+		    GC_SECTORS_USED(b) == ca->sb.bucket_size ||
+		    atomic_read(&b->pin))
+			continue;
 
-		while (sectors_to_move > reserve_sectors) {
-			heap_pop(&ca->heap, b, bucket_cmp);
-			sectors_to_move -= GC_SECTORS_USED(b);
+		if (!heap_full(&ca->heap)) {
+			sectors_to_move += GC_SECTORS_USED(b);
+			heap_add(&ca->heap, b, bucket_cmp);
+		} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
+			sectors_to_move -= bucket_heap_top(ca);
+			sectors_to_move += GC_SECTORS_USED(b);
+
+			ca->heap.data[0] = b;
+			heap_sift(&ca->heap, 0, bucket_cmp);
 		}
+	}
 
-		while (heap_pop(&ca->heap, b, bucket_cmp))
-			SET_GC_MOVE(b, 1);
+	while (sectors_to_move > reserve_sectors) {
+		heap_pop(&ca->heap, b, bucket_cmp);
+		sectors_to_move -= GC_SECTORS_USED(b);
 	}
 
+	while (heap_pop(&ca->heap, b, bucket_cmp))
+		SET_GC_MOVE(b, 1);
+
 	mutex_unlock(&c->bucket_lock);
 
 	c->moving_gc_keys.last_scanned = ZERO_KEY;

drivers/md/bcache/request.c

@@ -99,7 +99,7 @@ static int bch_keylist_realloc(struct keylist *l, unsigned int u64s,
 	 * bch_data_insert_keys() will insert the keys created so far
 	 * and finish the rest when the keylist is empty.
 	 */
-	if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
+	if (newsize * sizeof(uint64_t) > block_bytes(c->cache) - sizeof(struct jset))
 		return -ENOMEM;
 
 	return __bch_keylist_realloc(l, u64s);
@@ -394,8 +394,8 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 			goto skip;
 	}
 
-	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
-	    bio_sectors(bio) & (c->sb.block_size - 1)) {
+	if (bio->bi_iter.bi_sector & (c->cache->sb.block_size - 1) ||
+	    bio_sectors(bio) & (c->cache->sb.block_size - 1)) {
 		pr_debug("skipping unaligned io\n");
 		goto skip;
 	}

drivers/md/bcache/sysfs.c

@@ -711,10 +711,10 @@ SHOW(__bch_cache_set)
 {
 	struct cache_set *c = container_of(kobj, struct cache_set, kobj);
 
-	sysfs_print(synchronous,		CACHE_SYNC(&c->sb));
+	sysfs_print(synchronous,		CACHE_SYNC(&c->cache->sb));
 	sysfs_print(journal_delay_ms,		c->journal_delay_ms);
-	sysfs_hprint(bucket_size,		bucket_bytes(c));
-	sysfs_hprint(block_size,		block_bytes(c));
+	sysfs_hprint(bucket_size,		bucket_bytes(c->cache));
+	sysfs_hprint(block_size,		block_bytes(c->cache));
 	sysfs_print(tree_depth,			c->root->level);
 	sysfs_print(root_usage_percent,		bch_root_usage(c));
 
@@ -812,8 +812,8 @@ STORE(__bch_cache_set)
 	if (attr == &sysfs_synchronous) {
 		bool sync = strtoul_or_return(buf);
 
-		if (sync != CACHE_SYNC(&c->sb)) {
-			SET_CACHE_SYNC(&c->sb, sync);
+		if (sync != CACHE_SYNC(&c->cache->sb)) {
+			SET_CACHE_SYNC(&c->cache->sb, sync);
 			bcache_write_super(c);
 		}
 	}

drivers/md/bcache/writeback.c

@@ -35,7 +35,7 @@ static uint64_t __calc_target_rate(struct cached_dev *dc)
 	 * This is the size of the cache, minus the amount used for
 	 * flash-only devices
 	 */
-	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
+	uint64_t cache_sectors = c->nbuckets * c->cache->sb.bucket_size -
 				atomic_long_read(&c->flash_dev_dirty_sectors);
 
 	/*

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;
@@ -605,8 +606,8 @@ static int md_bitmap_read_sb(struct bitmap *bitmap)
 	if (bitmap->cluster_slot >= 0) {
 		sector_t bm_blocks = bitmap->mddev->resync_max_sectors;
 
-		sector_div(bm_blocks,
-			   bitmap->mddev->bitmap_info.chunksize >> 9);
+		bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks,
+			   (bitmap->mddev->bitmap_info.chunksize >> 9));
 		/* bits to bytes */
 		bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t);
 		/* to 4k blocks */
@@ -1367,7 +1368,7 @@ __acquires(bitmap->lock)
 	if (bitmap->bp[page].hijacked ||
 	    bitmap->bp[page].map == NULL)
 		csize = ((sector_t)1) << (bitmap->chunkshift +
-					  PAGE_COUNTER_SHIFT - 1);
+					  PAGE_COUNTER_SHIFT);
 	else
 		csize = ((sector_t)1) << bitmap->chunkshift;
 	*blocks = csize - (offset & (csize - 1));
@@ -1949,6 +1950,7 @@ int md_bitmap_load(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(md_bitmap_load);
 
+/* caller need to free returned bitmap with md_bitmap_free() */
 struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot)
 {
 	int rv = 0;
@@ -2012,6 +2014,7 @@ int md_bitmap_copy_from_slot(struct mddev *mddev, int slot,
 	md_bitmap_unplug(mddev->bitmap);
 	*low = lo;
 	*high = hi;
+	md_bitmap_free(bitmap);
 
 	return rv;
 }
@@ -2615,4 +2618,3 @@ struct attribute_group md_bitmap_group = {
 	.name = "bitmap",
 	.attrs = md_bitmap_attrs,
 };
-

drivers/md/md-cluster.c

@@ -1166,6 +1166,7 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz
 			 * can't resize bitmap
 			 */
 			goto out;
+		md_bitmap_free(bitmap);
 	}
 
 	return 0;

drivers/md/md.c

@@ -8582,6 +8582,26 @@ 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
@@ -9544,7 +9564,7 @@ static int __init md_init(void)
 		goto err_misc_wq;
 
 	md_rdev_misc_wq = alloc_workqueue("md_rdev_misc", 0, 0);
-	if (!md_misc_wq)
+	if (!md_rdev_misc_wq)
 		goto err_rdev_misc_wq;
 
 	if ((ret = register_blkdev(MD_MAJOR, "md")) < 0)

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

@@ -426,23 +426,6 @@ static void raid0_free(struct mddev *mddev, void *priv)
 	kfree(conf);
 }
 
-/*
- * Is io distribute over 1 or more chunks ?
-*/
-static inline int is_io_in_chunk_boundary(struct mddev *mddev,
-			unsigned int chunk_sects, struct bio *bio)
-{
-	if (likely(is_power_of_2(chunk_sects))) {
-		return chunk_sects >=
-			((bio->bi_iter.bi_sector & (chunk_sects-1))
-					+ bio_sectors(bio));
-	} else{
-		sector_t sector = bio->bi_iter.bi_sector;
-		return chunk_sects >= (sector_div(sector, chunk_sects)
-						+ bio_sectors(bio));
-	}
-}
-
 static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 {
 	struct r0conf *conf = mddev->private;
@@ -494,7 +477,6 @@ 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 +499,9 @@ 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);

drivers/nvme/host/nvme.h

@@ -300,7 +300,7 @@ struct nvme_ctrl {
 	unsigned long quirks;
 	struct nvme_id_power_state psd[32];
 	struct nvme_effects_log *effects;
-	struct list_head cels;
+	struct xarray cels;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
@@ -758,10 +758,9 @@ static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+int nvme_revalidate_zones(struct nvme_ns *ns);
 #ifdef CONFIG_BLK_DEV_ZONED
-int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
-			  unsigned lbaf);
-
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
 int nvme_report_zones(struct gendisk *disk, sector_t sector,
 		      unsigned int nr_zones, report_zones_cb cb, void *data);
 
@@ -778,9 +777,7 @@ static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
 	return BLK_STS_NOTSUPP;
 }
 
-static inline int nvme_update_zone_info(struct gendisk *disk,
-					struct nvme_ns *ns,
-					unsigned lbaf)
+static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 {
 	dev_warn(ns->ctrl->device,
 		 "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
@@ -825,7 +822,7 @@ static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			 u8 opcode);
 void nvme_execute_passthru_rq(struct request *rq);
-struct nvme_ctrl *nvme_ctrl_get_by_path(const char *path);
+struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
 void nvme_put_ns(struct nvme_ns *ns);
 

drivers/nvme/host/pci.c

@@ -2038,32 +2038,30 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.calc_sets	= nvme_calc_irq_sets,
 		.priv		= dev,
 	};
-	unsigned int irq_queues, this_p_queues;
+	unsigned int irq_queues, poll_queues;
 
 	/*
-	 * Poll queues don't need interrupts, but we need at least one IO
-	 * queue left over for non-polled IO.
+	 * Poll queues don't need interrupts, but we need at least one I/O queue
+	 * left over for non-polled I/O.
 	 */
-	this_p_queues = dev->nr_poll_queues;
-	if (this_p_queues >= nr_io_queues) {
-		this_p_queues = nr_io_queues - 1;
-		irq_queues = 1;
-	} else {
-		irq_queues = nr_io_queues - this_p_queues + 1;
-	}
-	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
+	poll_queues = min(dev->nr_poll_queues, nr_io_queues - 1);
+	dev->io_queues[HCTX_TYPE_POLL] = poll_queues;
 
-	/* Initialize for the single interrupt case */
+	/*
+	 * Initialize for the single interrupt case, will be updated in
+	 * nvme_calc_irq_sets().
+	 */
 	dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
 	dev->io_queues[HCTX_TYPE_READ] = 0;
 
 	/*
-	 * Some Apple controllers require all queues to use the
-	 * first vector.
+	 * We need interrupts for the admin queue and each non-polled I/O queue,
+	 * but some Apple controllers require all queues to use the first
+	 * vector.
 	 */
-	if (dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR)
-		irq_queues = 1;
-
+	irq_queues = 1;
+	if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR))
+		irq_queues += (nr_io_queues - poll_queues);
 	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
 			      PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
 }
@@ -3187,7 +3185,6 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
-	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
@@ -3195,6 +3192,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR |
 				NVME_QUIRK_128_BYTES_SQES |
 				NVME_QUIRK_SHARED_TAGS },
+
+	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, nvme_id_table);

drivers/nvme/host/zns.c

@@ -7,6 +7,17 @@
 #include <linux/vmalloc.h>
 #include "nvme.h"
 
+int nvme_revalidate_zones(struct nvme_ns *ns)
+{
+	struct request_queue *q = ns->queue;
+	int ret;
+
+	ret = blk_revalidate_disk_zones(ns->disk, NULL);
+	if (!ret)
+		blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
+	return ret;
+}
+
 static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 {
 	struct nvme_command c = { };
@@ -35,11 +46,10 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 	return 0;
 }
 
-int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
-			  unsigned lbaf)
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 {
 	struct nvme_effects_log *log = ns->head->effects;
-	struct request_queue *q = disk->queue;
+	struct request_queue *q = ns->queue;
 	struct nvme_command c = { };
 	struct nvme_id_ns_zns *id;
 	int status;
@@ -133,28 +143,6 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 	return NULL;
 }
 
-static int __nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
-				  struct nvme_zone_report *report,
-				  size_t buflen)
-{
-	struct nvme_command c = { };
-	int ret;
-
-	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
-	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
-	c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
-	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
-	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
-	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
-	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
-
-	ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
-	if (ret)
-		return ret;
-
-	return le64_to_cpu(report->nr_zones);
-}
-
 static int nvme_zone_parse_entry(struct nvme_ns *ns,
 				 struct nvme_zone_descriptor *entry,
 				 unsigned int idx, report_zones_cb cb,
@@ -182,6 +170,7 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nvme_zone_report *report;
+	struct nvme_command c = { };
 	int ret, zone_idx = 0;
 	unsigned int nz, i;
 	size_t buflen;
@@ -190,14 +179,26 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	if (!report)
 		return -ENOMEM;
 
+	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
+	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
+	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
+	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
+	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
+	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
+
 	sector &= ~(ns->zsze - 1);
 	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
 		memset(report, 0, buflen);
-		ret = __nvme_ns_report_zones(ns, sector, report, buflen);
-		if (ret < 0)
+
+		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+		ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
+		if (ret) {
+			if (ret > 0)
+				ret = -EIO;
 			goto out_free;
+		}
 
-		nz = min_t(unsigned int, ret, nr_zones);
+		nz = min((unsigned int)le64_to_cpu(report->nr_zones), nr_zones);
 		if (!nz)
 			break;
 

drivers/nvme/target/admin-cmd.c

@@ -727,7 +727,9 @@ u16 nvmet_set_feat_kato(struct nvmet_req *req)
 {
 	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);
 
+	nvmet_stop_keep_alive_timer(req->sq->ctrl);
 	req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
+	nvmet_start_keep_alive_timer(req->sq->ctrl);
 
 	nvmet_set_result(req, req->sq->ctrl->kato);
 

drivers/nvme/target/core.c

@@ -395,7 +395,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 	nvmet_ctrl_fatal_error(ctrl);
 }
 
-static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
+void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
 	if (unlikely(ctrl->kato == 0))
 		return;
@@ -407,7 +407,7 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
-static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
+void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
 	if (unlikely(ctrl->kato == 0))
 		return;

drivers/nvme/target/fc.c

@@ -1019,7 +1019,7 @@ static void
 nvmet_fc_free_hostport(struct nvmet_fc_hostport *hostport)
 {
 	/* if LLDD not implemented, leave as NULL */
-	if (!hostport->hosthandle)
+	if (!hostport || !hostport->hosthandle)
 		return;
 
 	nvmet_fc_hostport_put(hostport);

drivers/nvme/target/loop.c

@@ -579,7 +579,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops,
 				0 /* no quirks, we're perfect! */);
 	if (ret)
-		goto out_put_ctrl;
+		goto out;
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
 		WARN_ON_ONCE(1);
@@ -635,8 +635,8 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	kfree(ctrl->queues);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
-out_put_ctrl:
 	nvme_put_ctrl(&ctrl->ctrl);
+out:
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);

drivers/nvme/target/nvmet.h

@@ -395,6 +395,8 @@ void nvmet_get_feat_async_event(struct nvmet_req *req);
 u16 nvmet_set_feat_kato(struct nvmet_req *req);
 u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask);
 void nvmet_execute_async_event(struct nvmet_req *req);
+void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl);
+void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl);
 
 u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
 void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id);

drivers/nvme/target/passthru.c

@@ -456,10 +456,26 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 			req->execute = nvmet_passthru_execute_cmd;
 			req->p.use_workqueue = true;
 			return NVME_SC_SUCCESS;
+		case NVME_ID_CNS_CS_CTRL:
+			switch (req->cmd->identify.csi) {
+			case NVME_CSI_ZNS:
+				req->execute = nvmet_passthru_execute_cmd;
+				req->p.use_workqueue = true;
+				return NVME_SC_SUCCESS;
+			}
+			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		case NVME_ID_CNS_NS:
 			req->execute = nvmet_passthru_execute_cmd;
 			req->p.use_workqueue = true;
 			return NVME_SC_SUCCESS;
+		case NVME_ID_CNS_CS_NS:
+			switch (req->cmd->identify.csi) {
+			case NVME_CSI_ZNS:
+				req->execute = nvmet_passthru_execute_cmd;
+				req->p.use_workqueue = true;
+				return NVME_SC_SUCCESS;
+			}
+			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		default:
 			return nvmet_setup_passthru_command(req);
 		}
@@ -474,6 +490,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 {
 	struct nvme_ctrl *ctrl;
+	struct file *file;
 	int ret = -EINVAL;
 	void *old;
 
@@ -488,24 +505,29 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 		goto out_unlock;
 	}
 
-	ctrl = nvme_ctrl_get_by_path(subsys->passthru_ctrl_path);
-	if (IS_ERR(ctrl)) {
-		ret = PTR_ERR(ctrl);
+	file = filp_open(subsys->passthru_ctrl_path, O_RDWR, 0);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto out_unlock;
+	}
+
+	ctrl = nvme_ctrl_from_file(file);
+	if (!ctrl) {
 		pr_err("failed to open nvme controller %s\n",
 		       subsys->passthru_ctrl_path);
 
-		goto out_unlock;
+		goto out_put_file;
 	}
 
 	old = xa_cmpxchg(&passthru_subsystems, ctrl->cntlid, NULL,
 			 subsys, GFP_KERNEL);
 	if (xa_is_err(old)) {
 		ret = xa_err(old);
-		goto out_put_ctrl;
+		goto out_put_file;
 	}
 
 	if (old)
-		goto out_put_ctrl;
+		goto out_put_file;
 
 	subsys->passthru_ctrl = ctrl;
 	subsys->ver = ctrl->vs;
@@ -516,13 +538,12 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 			NVME_TERTIARY(subsys->ver));
 		subsys->ver = NVME_VS(1, 2, 1);
 	}
-
+	nvme_get_ctrl(ctrl);
 	__module_get(subsys->passthru_ctrl->ops->module);
-	mutex_unlock(&subsys->lock);
-	return 0;
+	ret = 0;
 
-out_put_ctrl:
-	nvme_put_ctrl(ctrl);
+out_put_file:
+	filp_close(file, NULL);
 out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;

drivers/nvme/target/tcp.c

@@ -94,7 +94,6 @@ struct nvmet_tcp_queue {
 	struct socket		*sock;
 	struct nvmet_tcp_port	*port;
 	struct work_struct	io_work;
-	int			cpu;
 	struct nvmet_cq		nvme_cq;
 	struct nvmet_sq		nvme_sq;
 
@@ -144,7 +143,6 @@ struct nvmet_tcp_port {
 	struct work_struct	accept_work;
 	struct nvmet_port	*nport;
 	struct sockaddr_storage addr;
-	int			last_cpu;
 	void (*data_ready)(struct sock *);
 };
 
@@ -219,6 +217,11 @@ static inline void nvmet_tcp_put_cmd(struct nvmet_tcp_cmd *cmd)
 	list_add_tail(&cmd->entry, &cmd->queue->free_list);
 }
 
+static inline int queue_cpu(struct nvmet_tcp_queue *queue)
+{
+	return queue->sock->sk->sk_incoming_cpu;
+}
+
 static inline u8 nvmet_tcp_hdgst_len(struct nvmet_tcp_queue *queue)
 {
 	return queue->hdr_digest ? NVME_TCP_DIGEST_LENGTH : 0;
@@ -506,7 +509,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 	struct nvmet_tcp_queue	*queue = cmd->queue;
 
 	llist_add(&cmd->lentry, &queue->resp_list);
-	queue_work_on(cmd->queue->cpu, nvmet_tcp_wq, &cmd->queue->io_work);
+	queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &cmd->queue->io_work);
 }
 
 static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
@@ -1223,7 +1226,7 @@ static void nvmet_tcp_io_work(struct work_struct *w)
 	 * We exahusted our budget, requeue our selves
 	 */
 	if (pending)
-		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 }
 
 static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
@@ -1383,7 +1386,7 @@ static void nvmet_tcp_data_ready(struct sock *sk)
 	read_lock_bh(&sk->sk_callback_lock);
 	queue = sk->sk_user_data;
 	if (likely(queue))
-		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
@@ -1403,7 +1406,7 @@ static void nvmet_tcp_write_space(struct sock *sk)
 
 	if (sk_stream_is_writeable(sk)) {
 		clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 	}
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -1512,9 +1515,6 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	if (ret)
 		goto out_free_connect;
 
-	port->last_cpu = cpumask_next_wrap(port->last_cpu,
-				cpu_online_mask, -1, false);
-	queue->cpu = port->last_cpu;
 	nvmet_prepare_receive_pdu(queue);
 
 	mutex_lock(&nvmet_tcp_queue_mutex);
@@ -1525,7 +1525,7 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	if (ret)
 		goto out_destroy_sq;
 
-	queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+	queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 
 	return 0;
 out_destroy_sq:
@@ -1612,7 +1612,6 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 	}
 
 	port->nport = nport;
-	port->last_cpu = -1;
 	INIT_WORK(&port->accept_work, nvmet_tcp_accept_work);
 	if (port->nport->inline_data_size < 0)
 		port->nport->inline_data_size = NVMET_TCP_DEF_INLINE_DATA_SIZE;

drivers/scsi/hisi_sas/hisi_sas.h

@@ -8,6 +8,8 @@
 #define _HISI_SAS_H_
 
 #include <linux/acpi.h>
+#include <linux/blk-mq.h>
+#include <linux/blk-mq-pci.h>
 #include <linux/clk.h>
 #include <linux/debugfs.h>
 #include <linux/dmapool.h>
@@ -431,7 +433,6 @@ struct hisi_hba {
 	u32 intr_coal_count;	/* Interrupt count to coalesce */
 
 	int cq_nvecs;
-	unsigned int *reply_map;
 
 	/* bist */
 	enum sas_linkrate debugfs_bist_linkrate;

drivers/scsi/hosts.c

@@ -421,6 +421,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	shost->cmd_per_lun = sht->cmd_per_lun;
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->no_write_same = sht->no_write_same;
+	shost->host_tagset = sht->host_tagset;
 
 	if (shost_eh_deadline == -1 || !sht->eh_host_reset_handler)
 		shost->eh_deadline = -1;