for-5.4/post-2019-09-24

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl2J8xQQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpujgD/94s9GGKN8JShxCpT0YNuWyyFF5gNlaimQU
 RSGAwnv2YUgEGNSUOPpcaj5FAYhTfYzbqoHlE+jytA2U5KXTOhc5Z85QV+TY4HPs
 I03xczYuYD/uX0QuF00zU2+6eV3lETELPiBARbfEQdHfm72iwurweHzlh4dfhbxW
 P7UA/cKixXWF2CH9wg5347Ll93nD24f2pi8BUyLJi/xpdlaRrN11Ii8AzNlRmq52
 VRxURuogl98W89F6EV2VhPGFgUEYHY2Ot7II2OqqV+jmjHDQW9y5hximzINOqkxs
 bQwo5J+WrDSPoqwl8+db2k7QQjAl1XKDAHmCwz+7J/BoOgZj8/M1FMBwzita+5x+
 UqxEYe7k+2G3w2zuhBrq03BypU8pwqFep/QI0cCCPaHs4J5QnkVOScEqd6iV/C3T
 FPvMvqDf7MrElghj4Qa2IZlh/CgqmLG5NUEz8E40cXkdiP+E+eK9ZY2Uwx2XhBrm
 7Gl+SpG5DxWqqJeRNVWjFwM4p5L+01NtwDbTjZ1rsf+mCW5cNsy/L9B4UpPz4HxW
 coAs0y/Ce+ZhCopIXZ4jLDBoTG9yoVg8EcyfaHKD2Zz0mUFxa2xm+LvXKeT49qqx
 xuodpKD3fiuM7h9Xgv+cDsmn8Rr8gSeXEGV7qzpudmkxbp6IVg/yG5hC/dM921GR
 EVrRtUIwdw==
 =aAPP
 -----END PGP SIGNATURE-----

Merge tag 'for-5.4/post-2019-09-24' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "Some later additions that weren't quite done for the first pull
  request, and also a few fixes that have arrived since.

  This contains:

   - Kill silly pktcdvd warning on attempting to register a non-scsi
     passthrough device (me)

   - Use symbolic constants for the block t10 protection types, and
     switch to handling it in core rather than in the drivers (Max)

   - libahci platform missing node put fix (Nishka)

   - Small series of fixes for BFQ (Paolo)

   - Fix possible nbd crash (Xiubo)"

* tag 'for-5.4/post-2019-09-24' of git://git.kernel.dk/linux-block:
  block: drop device references in bsg_queue_rq()
  block: t10-pi: fix -Wswitch warning
  pktcdvd: remove warning on attempting to register non-passthrough dev
  ata: libahci_platform: Add of_node_put() before loop exit
  nbd: fix possible page fault for nbd disk
  nbd: rename the runtime flags as NBD_RT_ prefixed
  block, bfq: push up injection only after setting service time
  block, bfq: increase update frequency of inject limit
  block, bfq: reduce upper bound for inject limit to max_rq_in_driver+1
  block, bfq: update inject limit only after injection occurred
  block: centralize PI remapping logic to the block layer
  block: use symbolic constants for t10_pi type

block/bfq-iosched.c

@@ -2016,7 +2016,7 @@ static void bfq_add_request(struct request *rq)
 		     (bfqq->last_serv_time_ns > 0 &&
 		      bfqd->rqs_injected && bfqd->rq_in_driver > 0)) &&
 		    time_is_before_eq_jiffies(bfqq->decrease_time_jif +
-					      msecs_to_jiffies(100))) {
+					      msecs_to_jiffies(10))) {
 			bfqd->last_empty_occupied_ns = ktime_get_ns();
 			/*
 			 * Start the state machine for measuring the
@@ -2025,7 +2025,21 @@ static void bfq_add_request(struct request *rq)
 			 * be set when rq will be dispatched.
 			 */
 			bfqd->wait_dispatch = true;
-			bfqd->rqs_injected = false;
+			/*
+			 * If there is no I/O in service in the drive,
+			 * then possible injection occurred before the
+			 * arrival of rq will not affect the total
+			 * service time of rq. So the injection limit
+			 * must not be updated as a function of such
+			 * total service time, unless new injection
+			 * occurs before rq is completed. To have the
+			 * injection limit updated only in the latter
+			 * case, reset rqs_injected here (rqs_injected
+			 * will be set in case injection is performed
+			 * on bfqq before rq is completed).
+			 */
+			if (bfqd->rq_in_driver == 0)
+				bfqd->rqs_injected = false;
 		}
 	}
 
@@ -5784,14 +5798,14 @@ static void bfq_update_inject_limit(struct bfq_data *bfqd,
 	u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
 	unsigned int old_limit = bfqq->inject_limit;
 
-	if (bfqq->last_serv_time_ns > 0) {
+	if (bfqq->last_serv_time_ns > 0 && bfqd->rqs_injected) {
 		u64 threshold = (bfqq->last_serv_time_ns * 3)>>1;
 
 		if (tot_time_ns >= threshold && old_limit > 0) {
 			bfqq->inject_limit--;
 			bfqq->decrease_time_jif = jiffies;
 		} else if (tot_time_ns < threshold &&
-			   old_limit < bfqd->max_rq_in_driver<<1)
+			   old_limit <= bfqd->max_rq_in_driver)
 			bfqq->inject_limit++;
 	}
 
@@ -5809,12 +5823,14 @@ static void bfq_update_inject_limit(struct bfq_data *bfqd,
 	 */
 	if ((bfqq->last_serv_time_ns == 0 && bfqd->rq_in_driver == 1) ||
 	    tot_time_ns < bfqq->last_serv_time_ns) {
+		if (bfqq->last_serv_time_ns == 0) {
+			/*
+			 * Now we certainly have a base value: make sure we
+			 * start trying injection.
+			 */
+			bfqq->inject_limit = max_t(unsigned int, 1, old_limit);
+		}
 		bfqq->last_serv_time_ns = tot_time_ns;
-		/*
-		 * Now we certainly have a base value: make sure we
-		 * start trying injection.
-		 */
-		bfqq->inject_limit = max_t(unsigned int, 1, old_limit);
 	} else if (!bfqd->rqs_injected && bfqd->rq_in_driver == 1)
 		/*
 		 * No I/O injected and no request still in service in
@@ -5830,6 +5846,7 @@ static void bfq_update_inject_limit(struct bfq_data *bfqd,
 
 	/* update complete, not waiting for any request completion any longer */
 	bfqd->waited_rq = NULL;
+	bfqd->rqs_injected = false;
 }
 
 /*

block/blk-core.c

@@ -34,6 +34,7 @@
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
 #include <linux/blk-cgroup.h>
+#include <linux/t10-pi.h>
 #include <linux/debugfs.h>
 #include <linux/bpf.h>
 #include <linux/psi.h>
@@ -1436,6 +1437,12 @@ bool blk_update_request(struct request *req, blk_status_t error,
 	if (!req->bio)
 		return false;
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
+	    error == BLK_STS_OK)
+		req->q->integrity.profile->complete_fn(req, nr_bytes);
+#endif
+
 	if (unlikely(error && !blk_rq_is_passthrough(req) &&
 		     !(req->rq_flags & RQF_QUIET)))
 		print_req_error(req, error, __func__);

block/blk-integrity.c

@@ -368,10 +368,21 @@ static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
 	return BLK_STS_OK;
 }
 
+static void blk_integrity_nop_prepare(struct request *rq)
+{
+}
+
+static void blk_integrity_nop_complete(struct request *rq,
+		unsigned int nr_bytes)
+{
+}
+
 static const struct blk_integrity_profile nop_profile = {
 	.name = "nop",
 	.generate_fn = blk_integrity_nop_fn,
 	.verify_fn = blk_integrity_nop_fn,
+	.prepare_fn = blk_integrity_nop_prepare,
+	.complete_fn = blk_integrity_nop_complete,
 };
 
 /**

block/blk-mq.c

@@ -30,6 +30,7 @@
 #include <trace/events/block.h>
 
 #include <linux/blk-mq.h>
+#include <linux/t10-pi.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
@@ -700,6 +701,11 @@ void blk_mq_start_request(struct request *rq)
 		 */
 		rq->nr_phys_segments++;
 	}
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
+		q->integrity.profile->prepare_fn(rq);
+#endif
 }
 EXPORT_SYMBOL(blk_mq_start_request);
 

block/bsg-lib.c

@@ -266,6 +266,7 @@ static blk_status_t bsg_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct bsg_set *bset =
 		container_of(q->tag_set, struct bsg_set, tag_set);
+	int sts = BLK_STS_IOERR;
 	int ret;
 
 	blk_mq_start_request(req);
@@ -274,14 +275,15 @@ static blk_status_t bsg_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return BLK_STS_IOERR;
 
 	if (!bsg_prepare_job(dev, req))
-		return BLK_STS_IOERR;
+		goto out;
 
 	ret = bset->job_fn(blk_mq_rq_to_pdu(req));
-	if (ret)
+	if (!ret)
-		return BLK_STS_IOERR;
+		sts = BLK_STS_OK;
 
+out:
 	put_device(dev);
-	return BLK_STS_OK;
+	return sts;
 }
 
 /* called right after the request is allocated for the request_queue */

block/t10-pi.c

@@ -27,7 +27,7 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len)
  * tag.
  */
 static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
-		csum_fn *fn, unsigned int type)
+		csum_fn *fn, enum t10_dif_type type)
 {
 	unsigned int i;
 
@@ -37,7 +37,7 @@ static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 		pi->guard_tag = fn(iter->data_buf, iter->interval);
 		pi->app_tag = 0;
 
-		if (type == 1)
+		if (type == T10_PI_TYPE1_PROTECTION)
 			pi->ref_tag = cpu_to_be32(lower_32_bits(iter->seed));
 		else
 			pi->ref_tag = 0;
@@ -51,17 +51,18 @@ static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 }
 
 static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
-		csum_fn *fn, unsigned int type)
+		csum_fn *fn, enum t10_dif_type type)
 {
 	unsigned int i;
 
+	BUG_ON(type == T10_PI_TYPE0_PROTECTION);
+
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
 		struct t10_pi_tuple *pi = iter->prot_buf;
 		__be16 csum;
 
-		switch (type) {
+		if (type == T10_PI_TYPE1_PROTECTION ||
-		case 1:
+		    type == T10_PI_TYPE2_PROTECTION) {
-		case 2:
 			if (pi->app_tag == T10_PI_APP_ESCAPE)
 				goto next;
 
@@ -73,12 +74,10 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 				       iter->seed, be32_to_cpu(pi->ref_tag));
 				return BLK_STS_PROTECTION;
 			}
-			break;
+		} else if (type == T10_PI_TYPE3_PROTECTION) {
-		case 3:
 			if (pi->app_tag == T10_PI_APP_ESCAPE &&
 			    pi->ref_tag == T10_PI_REF_ESCAPE)
 				goto next;
-			break;
 		}
 
 		csum = fn(iter->data_buf, iter->interval);
@@ -102,94 +101,40 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 
 static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
 {
-	return t10_pi_generate(iter, t10_pi_crc_fn, 1);
+	return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION);
 }
 
 static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
 {
-	return t10_pi_generate(iter, t10_pi_ip_fn, 1);
+	return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION);
 }
 
 static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
 {
-	return t10_pi_verify(iter, t10_pi_crc_fn, 1);
+	return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION);
 }
 
 static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
 {
-	return t10_pi_verify(iter, t10_pi_ip_fn, 1);
+	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION);
 }
 
-static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_crc_fn, 3);
-}
-
-static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_ip_fn, 3);
-}
-
-static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_crc_fn, 3);
-}
-
-static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_ip_fn, 3);
-}
-
-const struct blk_integrity_profile t10_pi_type1_crc = {
-	.name			= "T10-DIF-TYPE1-CRC",
-	.generate_fn		= t10_pi_type1_generate_crc,
-	.verify_fn		= t10_pi_type1_verify_crc,
-};
-EXPORT_SYMBOL(t10_pi_type1_crc);
-
-const struct blk_integrity_profile t10_pi_type1_ip = {
-	.name			= "T10-DIF-TYPE1-IP",
-	.generate_fn		= t10_pi_type1_generate_ip,
-	.verify_fn		= t10_pi_type1_verify_ip,
-};
-EXPORT_SYMBOL(t10_pi_type1_ip);
-
-const struct blk_integrity_profile t10_pi_type3_crc = {
-	.name			= "T10-DIF-TYPE3-CRC",
-	.generate_fn		= t10_pi_type3_generate_crc,
-	.verify_fn		= t10_pi_type3_verify_crc,
-};
-EXPORT_SYMBOL(t10_pi_type3_crc);
-
-const struct blk_integrity_profile t10_pi_type3_ip = {
-	.name			= "T10-DIF-TYPE3-IP",
-	.generate_fn		= t10_pi_type3_generate_ip,
-	.verify_fn		= t10_pi_type3_verify_ip,
-};
-EXPORT_SYMBOL(t10_pi_type3_ip);
-
 /**
- * t10_pi_prepare - prepare PI prior submitting request to device
+ * t10_pi_type1_prepare - prepare PI prior submitting request to device
  * @rq:              request with PI that should be prepared
- * @protection_type: PI type (Type 1/Type 2/Type 3)
  *
  * For Type 1/Type 2, the virtual start sector is the one that was
  * originally submitted by the block layer for the ref_tag usage. Due to
  * partitioning, MD/DM cloning, etc. the actual physical start sector is
  * likely to be different. Remap protection information to match the
  * physical LBA.
- *
- * Type 3 does not have a reference tag so no remapping is required.
  */
-void t10_pi_prepare(struct request *rq, u8 protection_type)
+static void t10_pi_type1_prepare(struct request *rq)
 {
 	const int tuple_sz = rq->q->integrity.tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	struct bio *bio;
 
-	if (protection_type == T10_PI_TYPE3_PROTECTION)
-		return;
-
 	__rq_for_each_bio(bio, rq) {
 		struct bio_integrity_payload *bip = bio_integrity(bio);
 		u32 virt = bip_get_seed(bip) & 0xffffffff;
@@ -222,13 +167,11 @@ void t10_pi_prepare(struct request *rq, u8 protection_type)
 		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
 	}
 }
-EXPORT_SYMBOL(t10_pi_prepare);
 
 /**
- * t10_pi_complete - prepare PI prior returning request to the block layer
+ * t10_pi_type1_complete - prepare PI prior returning request to the blk layer
  * @rq:              request with PI that should be prepared
- * @protection_type: PI type (Type 1/Type 2/Type 3)
+ * @nr_bytes:        total bytes to prepare
- * @intervals:       total elements to prepare
  *
  * For Type 1/Type 2, the virtual start sector is the one that was
  * originally submitted by the block layer for the ref_tag usage. Due to
@@ -236,19 +179,14 @@ EXPORT_SYMBOL(t10_pi_prepare);
  * likely to be different. Since the physical start sector was submitted
  * to the device, we should remap it back to virtual values expected by the
  * block layer.
- *
- * Type 3 does not have a reference tag so no remapping is required.
  */
-void t10_pi_complete(struct request *rq, u8 protection_type,
+static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
-		     unsigned int intervals)
 {
+	unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
 	const int tuple_sz = rq->q->integrity.tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	struct bio *bio;
 
-	if (protection_type == T10_PI_TYPE3_PROTECTION)
-		return;
-
 	__rq_for_each_bio(bio, rq) {
 		struct bio_integrity_payload *bip = bio_integrity(bio);
 		u32 virt = bip_get_seed(bip) & 0xffffffff;
@@ -276,4 +214,73 @@ void t10_pi_complete(struct request *rq, u8 protection_type,
 		}
 	}
 }
-EXPORT_SYMBOL(t10_pi_complete);
+
+static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION);
+}
+
+static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
+}
+
+static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION);
+}
+
+static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
+}
+
+/**
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+static void t10_pi_type3_prepare(struct request *rq)
+{
+}
+
+/**
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes)
+{
+}
+
+const struct blk_integrity_profile t10_pi_type1_crc = {
+	.name			= "T10-DIF-TYPE1-CRC",
+	.generate_fn		= t10_pi_type1_generate_crc,
+	.verify_fn		= t10_pi_type1_verify_crc,
+	.prepare_fn		= t10_pi_type1_prepare,
+	.complete_fn		= t10_pi_type1_complete,
+};
+EXPORT_SYMBOL(t10_pi_type1_crc);
+
+const struct blk_integrity_profile t10_pi_type1_ip = {
+	.name			= "T10-DIF-TYPE1-IP",
+	.generate_fn		= t10_pi_type1_generate_ip,
+	.verify_fn		= t10_pi_type1_verify_ip,
+	.prepare_fn		= t10_pi_type1_prepare,
+	.complete_fn		= t10_pi_type1_complete,
+};
+EXPORT_SYMBOL(t10_pi_type1_ip);
+
+const struct blk_integrity_profile t10_pi_type3_crc = {
+	.name			= "T10-DIF-TYPE3-CRC",
+	.generate_fn		= t10_pi_type3_generate_crc,
+	.verify_fn		= t10_pi_type3_verify_crc,
+	.prepare_fn		= t10_pi_type3_prepare,
+	.complete_fn		= t10_pi_type3_complete,
+};
+EXPORT_SYMBOL(t10_pi_type3_crc);
+
+const struct blk_integrity_profile t10_pi_type3_ip = {
+	.name			= "T10-DIF-TYPE3-IP",
+	.generate_fn		= t10_pi_type3_generate_ip,
+	.verify_fn		= t10_pi_type3_verify_ip,
+	.prepare_fn		= t10_pi_type3_prepare,
+	.complete_fn		= t10_pi_type3_complete,
+};
+EXPORT_SYMBOL(t10_pi_type3_ip);

drivers/ata/libahci_platform.c

@@ -497,6 +497,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 
 			if (of_property_read_u32(child, "reg", &port)) {
 				rc = -EINVAL;
+				of_node_put(child);
 				goto err_out;
 			}
 
@@ -514,14 +515,18 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 			if (port_dev) {
 				rc = ahci_platform_get_regulator(hpriv, port,
 								&port_dev->dev);
-				if (rc == -EPROBE_DEFER)
+				if (rc == -EPROBE_DEFER) {
+					of_node_put(child);
 					goto err_out;
+				}
 			}
 #endif
 
 			rc = ahci_platform_get_phy(hpriv, port, dev, child);
-			if (rc)
+			if (rc) {
+				of_node_put(child);
 				goto err_out;
+			}
 
 			enabled_ports++;
 		}

drivers/block/nbd.c

@@ -26,6 +26,7 @@
 #include <linux/ioctl.h>
 #include <linux/mutex.h>
 #include <linux/compiler.h>
+#include <linux/completion.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -71,14 +72,17 @@ struct link_dead_args {
 	int index;
 };
 
-#define NBD_TIMEDOUT			0
+#define NBD_RT_TIMEDOUT			0
+#define NBD_RT_DISCONNECT_REQUESTED	1
+#define NBD_RT_DISCONNECTED		2
+#define NBD_RT_HAS_PID_FILE		3
+#define NBD_RT_HAS_CONFIG_REF		4
+#define NBD_RT_BOUND			5
+#define NBD_RT_DESTROY_ON_DISCONNECT	6
+#define NBD_RT_DISCONNECT_ON_CLOSE	7
+
+#define NBD_DESTROY_ON_DISCONNECT	0
 #define NBD_DISCONNECT_REQUESTED	1
-#define NBD_DISCONNECTED		2
-#define NBD_HAS_PID_FILE		3
-#define NBD_HAS_CONFIG_REF		4
-#define NBD_BOUND			5
-#define NBD_DESTROY_ON_DISCONNECT	6
-#define NBD_DISCONNECT_ON_CLOSE 	7
 
 struct nbd_config {
 	u32 flags;
@@ -113,6 +117,9 @@ struct nbd_device {
 	struct list_head list;
 	struct task_struct *task_recv;
 	struct task_struct *task_setup;
+
+	struct completion *destroy_complete;
+	unsigned long flags;
 };
 
 #define NBD_CMD_REQUEUED	1
@@ -223,6 +230,16 @@ static void nbd_dev_remove(struct nbd_device *nbd)
 		disk->private_data = NULL;
 		put_disk(disk);
 	}
+
+	/*
+	 * Place this in the last just before the nbd is freed to
+	 * make sure that the disk and the related kobject are also
+	 * totally removed to avoid duplicate creation of the same
+	 * one.
+	 */
+	if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) && nbd->destroy_complete)
+		complete(nbd->destroy_complete);
+
 	kfree(nbd);
 }
 
@@ -238,8 +255,8 @@ static void nbd_put(struct nbd_device *nbd)
 
 static int nbd_disconnected(struct nbd_config *config)
 {
-	return test_bit(NBD_DISCONNECTED, &config->runtime_flags) ||
+	return test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags) ||
-		test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags);
+		test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags);
 }
 
 static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
@@ -257,9 +274,9 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
 	if (!nsock->dead) {
 		kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
 		if (atomic_dec_return(&nbd->config->live_connections) == 0) {
-			if (test_and_clear_bit(NBD_DISCONNECT_REQUESTED,
+			if (test_and_clear_bit(NBD_RT_DISCONNECT_REQUESTED,
 					       &nbd->config->runtime_flags)) {
-				set_bit(NBD_DISCONNECTED,
+				set_bit(NBD_RT_DISCONNECTED,
 					&nbd->config->runtime_flags);
 				dev_info(nbd_to_dev(nbd),
 					"Disconnected due to user request.\n");
@@ -333,7 +350,7 @@ static void sock_shutdown(struct nbd_device *nbd)
 
 	if (config->num_connections == 0)
 		return;
-	if (test_and_set_bit(NBD_DISCONNECTED, &config->runtime_flags))
+	if (test_and_set_bit(NBD_RT_DISCONNECTED, &config->runtime_flags))
 		return;
 
 	for (i = 0; i < config->num_connections; i++) {
@@ -427,7 +444,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	}
 
 	dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out\n");
-	set_bit(NBD_TIMEDOUT, &config->runtime_flags);
+	set_bit(NBD_RT_TIMEDOUT, &config->runtime_flags);
 	cmd->status = BLK_STS_IOERR;
 	mutex_unlock(&cmd->lock);
 	sock_shutdown(nbd);
@@ -795,7 +812,7 @@ static int find_fallback(struct nbd_device *nbd, int index)
 	struct nbd_sock *nsock = config->socks[index];
 	int fallback = nsock->fallback_index;
 
-	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+	if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags))
 		return new_index;
 
 	if (config->num_connections <= 1) {
@@ -836,7 +853,7 @@ static int wait_for_reconnect(struct nbd_device *nbd)
 	struct nbd_config *config = nbd->config;
 	if (!config->dead_conn_timeout)
 		return 0;
-	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+	if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags))
 		return 0;
 	return wait_event_timeout(config->conn_wait,
 				  atomic_read(&config->live_connections) > 0,
@@ -969,12 +986,12 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 		return err;
 
 	if (!netlink && !nbd->task_setup &&
-	    !test_bit(NBD_BOUND, &config->runtime_flags))
+	    !test_bit(NBD_RT_BOUND, &config->runtime_flags))
 		nbd->task_setup = current;
 
 	if (!netlink &&
 	    (nbd->task_setup != current ||
-	     test_bit(NBD_BOUND, &config->runtime_flags))) {
+	     test_bit(NBD_RT_BOUND, &config->runtime_flags))) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Device being setup by another task");
 		sockfd_put(sock);
@@ -1053,7 +1070,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 		mutex_unlock(&nsock->tx_lock);
 		sockfd_put(old);
 
-		clear_bit(NBD_DISCONNECTED, &config->runtime_flags);
+		clear_bit(NBD_RT_DISCONNECTED, &config->runtime_flags);
 
 		/* We take the tx_mutex in an error path in the recv_work, so we
 		 * need to queue_work outside of the tx_mutex.
@@ -1124,7 +1141,8 @@ static int nbd_disconnect(struct nbd_device *nbd)
 	struct nbd_config *config = nbd->config;
 
 	dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
-	set_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags);
+	set_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags);
+	set_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags);
 	send_disconnects(nbd);
 	return 0;
 }
@@ -1143,7 +1161,7 @@ static void nbd_config_put(struct nbd_device *nbd)
 		struct nbd_config *config = nbd->config;
 		nbd_dev_dbg_close(nbd);
 		nbd_size_clear(nbd);
-		if (test_and_clear_bit(NBD_HAS_PID_FILE,
+		if (test_and_clear_bit(NBD_RT_HAS_PID_FILE,
 				       &config->runtime_flags))
 			device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
 		nbd->task_recv = NULL;
@@ -1209,7 +1227,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 		dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
 		return error;
 	}
-	set_bit(NBD_HAS_PID_FILE, &config->runtime_flags);
+	set_bit(NBD_RT_HAS_PID_FILE, &config->runtime_flags);
 
 	nbd_dev_dbg_init(nbd);
 	for (i = 0; i < num_connections; i++) {
@@ -1256,9 +1274,9 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 	mutex_lock(&nbd->config_lock);
 	nbd_bdev_reset(bdev);
 	/* user requested, ignore socket errors */
-	if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags))
+	if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags))
 		ret = 0;
-	if (test_bit(NBD_TIMEDOUT, &config->runtime_flags))
+	if (test_bit(NBD_RT_TIMEDOUT, &config->runtime_flags))
 		ret = -ETIMEDOUT;
 	return ret;
 }
@@ -1269,7 +1287,7 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
 	sock_shutdown(nbd);
 	__invalidate_device(bdev, true);
 	nbd_bdev_reset(bdev);
-	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+	if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF,
 			       &nbd->config->runtime_flags))
 		nbd_config_put(nbd);
 }
@@ -1364,7 +1382,7 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 	/* Don't allow ioctl operations on a nbd device that was created with
 	 * netlink, unless it's DISCONNECT or CLEAR_SOCK, which are fine.
 	 */
-	if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+	if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) ||
 	    (cmd == NBD_DISCONNECT || cmd == NBD_CLEAR_SOCK))
 		error = __nbd_ioctl(bdev, nbd, cmd, arg);
 	else
@@ -1435,7 +1453,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode)
 	struct nbd_device *nbd = disk->private_data;
 	struct block_device *bdev = bdget_disk(disk, 0);
 
-	if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
+	if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
 			bdev->bd_openers == 0)
 		nbd_disconnect_and_put(nbd);
 
@@ -1636,6 +1654,7 @@ static int nbd_dev_add(int index)
 	nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE |
 		BLK_MQ_F_BLOCKING;
 	nbd->tag_set.driver_data = nbd;
+	nbd->destroy_complete = NULL;
 
 	err = blk_mq_alloc_tag_set(&nbd->tag_set);
 	if (err)
@@ -1750,6 +1769,7 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd)
 
 static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 {
+	DECLARE_COMPLETION_ONSTACK(destroy_complete);
 	struct nbd_device *nbd = NULL;
 	struct nbd_config *config;
 	int index = -1;
@@ -1801,6 +1821,17 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 		mutex_unlock(&nbd_index_mutex);
 		return -EINVAL;
 	}
+
+	if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) &&
+	    test_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags)) {
+		nbd->destroy_complete = &destroy_complete;
+		mutex_unlock(&nbd_index_mutex);
+
+		/* Wait untill the the nbd stuff is totally destroyed */
+		wait_for_completion(&destroy_complete);
+		goto again;
+	}
+
 	if (!refcount_inc_not_zero(&nbd->refs)) {
 		mutex_unlock(&nbd_index_mutex);
 		if (index == -1)
@@ -1833,7 +1864,7 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	}
 	refcount_set(&nbd->config_refs, 1);
-	set_bit(NBD_BOUND, &config->runtime_flags);
+	set_bit(NBD_RT_BOUND, &config->runtime_flags);
 
 	ret = nbd_genl_size_set(info, nbd);
 	if (ret)
@@ -1853,12 +1884,15 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
 		u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
 		if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
-			set_bit(NBD_DESTROY_ON_DISCONNECT,
+			set_bit(NBD_RT_DESTROY_ON_DISCONNECT,
 				&config->runtime_flags);
+			set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags);
 			put_dev = true;
+		} else {
+			clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags);
 		}
 		if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
-			set_bit(NBD_DISCONNECT_ON_CLOSE,
+			set_bit(NBD_RT_DISCONNECT_ON_CLOSE,
 				&config->runtime_flags);
 		}
 	}
@@ -1897,7 +1931,7 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 out:
 	mutex_unlock(&nbd->config_lock);
 	if (!ret) {
-		set_bit(NBD_HAS_CONFIG_REF, &config->runtime_flags);
+		set_bit(NBD_RT_HAS_CONFIG_REF, &config->runtime_flags);
 		refcount_inc(&nbd->config_refs);
 		nbd_connect_reply(info, nbd->index);
 	}
@@ -1919,7 +1953,7 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd)
 	 * queue.
 	 */
 	flush_workqueue(nbd->recv_workq);
-	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+	if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF,
 			       &nbd->config->runtime_flags))
 		nbd_config_put(nbd);
 }
@@ -2003,7 +2037,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 
 	mutex_lock(&nbd->config_lock);
 	config = nbd->config;
-	if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+	if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) ||
 	    !nbd->task_recv) {
 		dev_err(nbd_to_dev(nbd),
 			"not configured, cannot reconfigure\n");
@@ -2026,20 +2060,22 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
 		u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
 		if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
-			if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT,
+			if (!test_and_set_bit(NBD_RT_DESTROY_ON_DISCONNECT,
 					      &config->runtime_flags))
 				put_dev = true;
+			set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags);
 		} else {
-			if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT,
+			if (test_and_clear_bit(NBD_RT_DESTROY_ON_DISCONNECT,
 					       &config->runtime_flags))
 				refcount_inc(&nbd->refs);
+			clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags);
 		}
 
 		if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
-			set_bit(NBD_DISCONNECT_ON_CLOSE,
+			set_bit(NBD_RT_DISCONNECT_ON_CLOSE,
 					&config->runtime_flags);
 		} else {
-			clear_bit(NBD_DISCONNECT_ON_CLOSE,
+			clear_bit(NBD_RT_DISCONNECT_ON_CLOSE,
 					&config->runtime_flags);
 		}
 	}

drivers/block/pktcdvd.c

@@ -2594,7 +2594,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	if (ret)
 		return ret;
 	if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) {
-		WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
 		blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
 		return -EINVAL;
 	}

drivers/md/dm-integrity.c

@@ -345,6 +345,14 @@ static void __DEBUG_bytes(__u8 *bytes, size_t len, const char *msg, ...)
 #define DEBUG_bytes(bytes, len, msg, ...)	do { } while (0)
 #endif
 
+static void dm_integrity_prepare(struct request *rq)
+{
+}
+
+static void dm_integrity_complete(struct request *rq, unsigned int nr_bytes)
+{
+}
+
 /*
  * DM Integrity profile, protection is performed layer above (dm-crypt)
  */
@@ -352,6 +360,8 @@ static const struct blk_integrity_profile dm_integrity_profile = {
 	.name			= "DM-DIF-EXT-TAG",
 	.generate_fn		= NULL,
 	.verify_fn		= NULL,
+	.prepare_fn		= dm_integrity_prepare,
+	.complete_fn		= dm_integrity_complete,
 };
 
 static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map);

drivers/nvme/host/core.c

@@ -666,8 +666,6 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
-		} else if (req_op(req) == REQ_OP_WRITE) {
-			t10_pi_prepare(req, ns->pi_type);
 		}
 
 		switch (ns->pi_type) {
@@ -690,13 +688,6 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 
 void nvme_cleanup_cmd(struct request *req)
 {
-	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
-	    nvme_req(req)->status == 0) {
-		struct nvme_ns *ns = req->rq_disk->private_data;
-
-		t10_pi_complete(req, ns->pi_type,
-				blk_rq_bytes(req) >> ns->lba_shift);
-	}
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
 		struct nvme_ns *ns = req->rq_disk->private_data;
 		struct page *page = req->special_vec.bv_page;

drivers/scsi/sd.c

@@ -1211,9 +1211,6 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 	dix = scsi_prot_sg_count(cmd);
 	dif = scsi_host_dif_capable(cmd->device->host, sdkp->protection_type);
 
-	if (write && dix)
-		t10_pi_prepare(cmd->request, sdkp->protection_type);
-
 	if (dif || dix)
 		protect = sd_setup_protect_cmnd(cmd, dix, dif);
 	else
@@ -2055,11 +2052,6 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 					   "sd_done: completed %d of %d bytes\n",
 					   good_bytes, scsi_bufflen(SCpnt)));
 
-	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt) &&
-	    good_bytes)
-		t10_pi_complete(SCpnt->request, sdkp->protection_type,
-				good_bytes / scsi_prot_interval(SCpnt));
-
 	return good_bytes;
 }
 

include/linux/blkdev.h

@@ -1524,10 +1524,14 @@ struct blk_integrity_iter {
 };
 
 typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
+typedef void (integrity_prepare_fn) (struct request *);
+typedef void (integrity_complete_fn) (struct request *, unsigned int);
 
 struct blk_integrity_profile {
 	integrity_processing_fn		*generate_fn;
 	integrity_processing_fn		*verify_fn;
+	integrity_prepare_fn		*prepare_fn;
+	integrity_complete_fn		*complete_fn;
 	const char			*name;
 };
 

include/linux/t10-pi.h

@@ -53,18 +53,4 @@ extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
 extern const struct blk_integrity_profile t10_pi_type3_ip;
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-extern void t10_pi_prepare(struct request *rq, u8 protection_type);
-extern void t10_pi_complete(struct request *rq, u8 protection_type,
-			    unsigned int intervals);
-#else
-static inline void t10_pi_complete(struct request *rq, u8 protection_type,
-				   unsigned int intervals)
-{
-}
-static inline void t10_pi_prepare(struct request *rq, u8 protection_type)
-{
-}
-#endif
-
 #endif