Merge tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - drbd patches, bringing us closer to unifying the out-of-tree version
   and the in tree one (Andreas, Christoph)

 - support for auto-quiesce for the s390 dasd driver (Stefan)

 - MD pull request via Song:
      - md/bitmap: Optimal last page size (Jon Derrick)
      - Various raid10 fixes (Yu Kuai, Li Nan)
      - md: add error_handlers for raid0 and linear (Mariusz Tkaczyk)

 - NVMe pull request via Christoph:
      - Drop redundant pci_enable_pcie_error_reporting (Bjorn Helgaas)
      - Validate nvmet module parameters (Chaitanya Kulkarni)
      - Fence TCP socket on receive error (Chris Leech)
      - Fix async event trace event (Keith Busch)
      - Minor cleanups (Chaitanya Kulkarni, zhenwei pi)
      - Fix and cleanup nvmet Identify handling (Damien Le Moal,
        Christoph Hellwig)
      - Fix double blk_mq_complete_request race in the timeout handler
        (Lei Yin)
      - Fix irq locking in nvme-fcloop (Ming Lei)
      - Remove queue mapping helper for rdma devices (Sagi Grimberg)

 - use structured request attribute checks for nbd (Jakub)

 - fix blk-crypto race conditions between keyslot management (Eric)

 - add sed-opal support for reading read locking range attributes
   (Ondrej)

 - make fault injection configurable for null_blk (Akinobu)

 - clean up the request insertion API (Christoph)

 - clean up the queue running API (Christoph)

 - blkg config helper cleanups (Tejun)

 - lazy init support for blk-iolatency (Tejun)

 - various fixes and tweaks to ublk (Ming)

 - remove hybrid polling. It hasn't really been useful since we got
   async polled IO support, and these days we don't support sync polled
   IO at all (Keith)

 - misc fixes, cleanups, improvements (Zhong, Ondrej, Colin, Chengming,
   Chaitanya, me)

* tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux: (118 commits)
  nbd: fix incomplete validation of ioctl arg
  ublk: don't return 0 in case of any failure
  sed-opal: geometry feature reporting command
  null_blk: Always check queue mode setting from configfs
  block: ublk: switch to ioctl command encoding
  blk-mq: fix the blk_mq_add_to_requeue_list call in blk_kick_flush
  block, bfq: Fix division by zero error on zero wsum
  fault-inject: fix build error when FAULT_INJECTION_CONFIGFS=y and CONFIGFS_FS=m
  block: store bdev->bd_disk->fops->submit_bio state in bdev
  block: re-arrange the struct block_device fields for better layout
  md/raid5: remove unused working_disks variable
  md/raid10: don't call bio_start_io_acct twice for bio which experienced read error
  md/raid10: fix memleak of md thread
  md/raid10: fix memleak for 'conf->bio_split'
  md/raid10: fix leak of 'r10bio->remaining' for recovery
  md/raid10: don't BUG_ON() in raise_barrier()
  md: fix soft lockup in status_resync
  md: add error_handlers for raid0 and linear
  md: Use optimal I/O size for last bitmap page
  md: Fix types in sb writer
  ...

1 files changed, 88 insertions, 47 deletions

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 9e6b032c8ecc..b195b8b9fe32 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -250,7 +250,7 @@ static void null_free_device_storage(struct nullb_device *dev, bool is_cache);
 
 static inline struct nullb_device *to_nullb_device(struct config_item *item)
 {
-	return item ? container_of(item, struct nullb_device, item) : NULL;
+	return item ? container_of(to_config_group(item), struct nullb_device, group) : NULL;
 }
 
 static inline ssize_t nullb_device_uint_attr_show(unsigned int val, char *page)
@@ -593,8 +593,29 @@ static const struct config_item_type nullb_device_type = {
 	.ct_owner	= THIS_MODULE,
 };
 
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+
+static void nullb_add_fault_config(struct nullb_device *dev)
+{
+	fault_config_init(&dev->timeout_config, "timeout_inject");
+	fault_config_init(&dev->requeue_config, "requeue_inject");
+	fault_config_init(&dev->init_hctx_fault_config, "init_hctx_fault_inject");
+
+	configfs_add_default_group(&dev->timeout_config.group, &dev->group);
+	configfs_add_default_group(&dev->requeue_config.group, &dev->group);
+	configfs_add_default_group(&dev->init_hctx_fault_config.group, &dev->group);
+}
+
+#else
+
+static void nullb_add_fault_config(struct nullb_device *dev)
+{
+}
+
+#endif
+
 static struct
-config_item *nullb_group_make_item(struct config_group *group, const char *name)
+config_group *nullb_group_make_group(struct config_group *group, const char *name)
 {
 	struct nullb_device *dev;
 
@@ -605,9 +626,10 @@ config_item *nullb_group_make_item(struct config_group *group, const char *name)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	config_item_init_type_name(&dev->item, name, &nullb_device_type);
+	config_group_init_type_name(&dev->group, name, &nullb_device_type);
+	nullb_add_fault_config(dev);
 
-	return &dev->item;
+	return &dev->group;
 }
 
 static void
@@ -645,7 +667,7 @@ static struct configfs_attribute *nullb_group_attrs[] = {
 };
 
 static struct configfs_group_operations nullb_group_ops = {
-	.make_item	= nullb_group_make_item,
+	.make_group	= nullb_group_make_group,
 	.drop_item	= nullb_group_drop_item,
 };
 
@@ -676,6 +698,13 @@ static struct nullb_device *null_alloc_dev(void)
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return NULL;
+
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+	dev->timeout_config.attr = null_timeout_attr;
+	dev->requeue_config.attr = null_requeue_attr;
+	dev->init_hctx_fault_config.attr = null_init_hctx_attr;
+#endif
+
 	INIT_RADIX_TREE(&dev->data, GFP_ATOMIC);
 	INIT_RADIX_TREE(&dev->cache, GFP_ATOMIC);
 	if (badblocks_init(&dev->badblocks, 0)) {
@@ -1030,8 +1059,8 @@ static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page)
 	if (!t_page)
 		return -ENOMEM;
 
-	src = kmap_atomic(c_page->page);
-	dst = kmap_atomic(t_page->page);
+	src = kmap_local_page(c_page->page);
+	dst = kmap_local_page(t_page->page);
 
 	for (i = 0; i < PAGE_SECTORS;
 			i += (nullb->dev->blocksize >> SECTOR_SHIFT)) {
@@ -1043,8 +1072,8 @@ static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page)
 		}
 	}
 
-	kunmap_atomic(dst);
-	kunmap_atomic(src);
+	kunmap_local(dst);
+	kunmap_local(src);
 
 	ret = radix_tree_delete_item(&nullb->dev->cache, idx, c_page);
 	null_free_page(ret);
@@ -1112,7 +1141,6 @@ static int copy_to_nullb(struct nullb *nullb, struct page *source,
 	size_t temp, count = 0;
 	unsigned int offset;
 	struct nullb_page *t_page;
-	void *dst, *src;
 
 	while (count < n) {
 		temp = min_t(size_t, nullb->dev->blocksize, n - count);
@@ -1126,11 +1154,7 @@ static int copy_to_nullb(struct nullb *nullb, struct page *source,
 		if (!t_page)
 			return -ENOSPC;
 
-		src = kmap_atomic(source);
-		dst = kmap_atomic(t_page->page);
-		memcpy(dst + offset, src + off + count, temp);
-		kunmap_atomic(dst);
-		kunmap_atomic(src);
+		memcpy_page(t_page->page, offset, source, off + count, temp);
 
 		__set_bit(sector & SECTOR_MASK, t_page->bitmap);
 
@@ -1149,7 +1173,6 @@ static int copy_from_nullb(struct nullb *nullb, struct page *dest,
 	size_t temp, count = 0;
 	unsigned int offset;
 	struct nullb_page *t_page;
-	void *dst, *src;
 
 	while (count < n) {
 		temp = min_t(size_t, nullb->dev->blocksize, n - count);
@@ -1158,16 +1181,11 @@ static int copy_from_nullb(struct nullb *nullb, struct page *dest,
 		t_page = null_lookup_page(nullb, sector, false,
 			!null_cache_active(nullb));
 
-		dst = kmap_atomic(dest);
-		if (!t_page) {
-			memset(dst + off + count, 0, temp);
-			goto next;
-		}
-		src = kmap_atomic(t_page->page);
-		memcpy(dst + off + count, src + offset, temp);
-		kunmap_atomic(src);
-next:
-		kunmap_atomic(dst);
+		if (t_page)
+			memcpy_page(dest, off + count, t_page->page, offset,
+				    temp);
+		else
+			zero_user(dest, off + count, temp);
 
 		count += temp;
 		sector += temp >> SECTOR_SHIFT;
@@ -1178,11 +1196,7 @@ next:
 static void nullb_fill_pattern(struct nullb *nullb, struct page *page,
 			       unsigned int len, unsigned int off)
 {
-	void *dst;
-
-	dst = kmap_atomic(page);
-	memset(dst + off, 0xFF, len);
-	kunmap_atomic(dst);
+	memset_page(page, off, 0xff, len);
 }
 
 blk_status_t null_handle_discard(struct nullb_device *dev,
@@ -1529,24 +1543,48 @@ static void null_submit_bio(struct bio *bio)
 	null_handle_cmd(alloc_cmd(nq, bio), sector, nr_sectors, bio_op(bio));
 }
 
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+
+static bool should_timeout_request(struct request *rq)
+{
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	struct nullb_device *dev = cmd->nq->dev;
+
+	return should_fail(&dev->timeout_config.attr, 1);
+}
+
+static bool should_requeue_request(struct request *rq)
+{
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	struct nullb_device *dev = cmd->nq->dev;
+
+	return should_fail(&dev->requeue_config.attr, 1);
+}
+
+static bool should_init_hctx_fail(struct nullb_device *dev)
+{
+	return should_fail(&dev->init_hctx_fault_config.attr, 1);
+}
+
+#else
+
 static bool should_timeout_request(struct request *rq)
 {
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-	if (g_timeout_str[0])
-		return should_fail(&null_timeout_attr, 1);
-#endif
 	return false;
 }
 
 static bool should_requeue_request(struct request *rq)
 {
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-	if (g_requeue_str[0])
-		return should_fail(&null_requeue_attr, 1);
-#endif
 	return false;
 }
 
+static bool should_init_hctx_fail(struct nullb_device *dev)
+{
+	return false;
+}
+
+#endif
+
 static void null_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nullb *nullb = set->driver_data;
@@ -1743,10 +1781,8 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
 	struct nullb *nullb = hctx->queue->queuedata;
 	struct nullb_queue *nq;
 
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-	if (g_init_hctx_str[0] && should_fail(&null_init_hctx_attr, 1))
+	if (should_init_hctx_fail(nullb->dev))
 		return -EFAULT;
-#endif
 
 	nq = &nullb->queues[hctx_idx];
 	hctx->driver_data = nq;
@@ -1964,6 +2000,11 @@ static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
 
 static int null_validate_conf(struct nullb_device *dev)
 {
+	if (dev->queue_mode == NULL_Q_RQ) {
+		pr_err("legacy IO path is no longer available\n");
+		return -EINVAL;
+	}
+
 	dev->blocksize = round_down(dev->blocksize, 512);
 	dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096);
 
@@ -2066,9 +2107,6 @@ static int null_add_dev(struct nullb_device *dev)
 		if (rv)
 			goto out_cleanup_queues;
 
-		if (!null_setup_fault())
-			goto out_cleanup_tags;
-
 		nullb->tag_set->timeout = 5 * HZ;
 		nullb->disk = blk_mq_alloc_disk(nullb->tag_set, nullb);
 		if (IS_ERR(nullb->disk)) {
@@ -2130,10 +2168,10 @@ static int null_add_dev(struct nullb_device *dev)
 
 	null_config_discard(nullb);
 
-	if (config_item_name(&dev->item)) {
+	if (config_item_name(&dev->group.cg_item)) {
 		/* Use configfs dir name as the device name */
 		snprintf(nullb->disk_name, sizeof(nullb->disk_name),
-			 "%s", config_item_name(&dev->item));
+			 "%s", config_item_name(&dev->group.cg_item));
 	} else {
 		sprintf(nullb->disk_name, "nullb%d", nullb->index);
 	}
@@ -2233,6 +2271,9 @@ static int __init null_init(void)
 		g_home_node = NUMA_NO_NODE;
 	}
 
+	if (!null_setup_fault())
+		return -EINVAL;
+
 	if (g_queue_mode == NULL_Q_RQ) {
 		pr_err("legacy IO path is no longer available\n");
 		return -EINVAL;