Merge tag 'block-6.10-20240614' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
     - Discard double free on error conditions (Chunguang)
     - Target Fixes (Daniel)
     - Namespace detachment regression fix (Keith)

 - Fix for an issue with flush requests and queuelist reuse (Chengming)

 - nbd sparse annotation fixes (Christoph)

 - unmap and free bio mapped data via submitter (Anuj)

 - loop discard/fallocate unsupported fix (Cyril)

 - Fix for the zoned write plugging added in this release (Damien)

 - sed-opal wrong address fix (Su)

* tag 'block-6.10-20240614' of git://git.kernel.dk/linux:
  loop: Disable fallocate() zero and discard if not supported
  nvme: fix namespace removal list
  nbd: Remove __force casts
  nvmet: always initialize cqe.result
  nvmet-passthru: propagate status from id override functions
  nvme: avoid double free special payload
  block: unmap and free user mapped integrity via submitter
  block: fix request.queuelist usage in flush
  block: Optimize disk zone resource cleanup
  block: sed-opal: avoid possible wrong address reference in read_sed_opal_key()

13 files changed, 100 insertions, 53 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 2e3e8e04961e..8b528e12136f 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -144,10 +144,10 @@ void bio_integrity_free(struct bio *bio)
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
 
+	if (bip->bip_flags & BIP_INTEGRITY_USER)
+		return;
 	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
 		kfree(bvec_virt(bip->bip_vec));
-	else if (bip->bip_flags & BIP_INTEGRITY_USER)
-		bio_integrity_unmap_user(bip);
 
 	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
@@ -155,6 +155,28 @@ void bio_integrity_free(struct bio *bio)
 }
 
 /**
+ * bio_integrity_unmap_free_user - Unmap and free bio user integrity payload
+ * @bio:	bio containing bip to be unmapped and freed
+ *
+ * Description: Used to unmap and free the user mapped integrity portion of a
+ * bio. Submitter attaching the user integrity buffer is responsible for
+ * unmapping and freeing it during completion.
+ */
+void bio_integrity_unmap_free_user(struct bio *bio)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct bio_set *bs = bio->bi_pool;
+
+	if (WARN_ON_ONCE(!(bip->bip_flags & BIP_INTEGRITY_USER)))
+		return;
+	bio_integrity_unmap_user(bip);
+	__bio_integrity_free(bs, bip);
+	bio->bi_integrity = NULL;
+	bio->bi_opf &= ~REQ_INTEGRITY;
+}
+EXPORT_SYMBOL(bio_integrity_unmap_free_user);
+
+/**
  * bio_integrity_add_page - Attach integrity metadata
  * @bio:	bio to update
  * @page:	page containing integrity metadata
diff --git a/block/blk-flush.c b/block/blk-flush.c
index c17cf8ed8113..cca4f9131f79 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -185,7 +185,7 @@ static void blk_flush_complete_seq(struct request *rq,
 		/* queue for flush */
 		if (list_empty(pending))
 			fq->flush_pending_since = jiffies;
-		list_move_tail(&rq->queuelist, pending);
+		list_add_tail(&rq->queuelist, pending);
 		break;
 
 	case REQ_FSEQ_DATA:
@@ -263,6 +263,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq,
 		unsigned int seq = blk_flush_cur_seq(rq);
 
 		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
+		list_del_init(&rq->queuelist);
 		blk_flush_complete_seq(rq, fq, seq, error);
 	}
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 52abebf56027..08d7dfe8bd93 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1552,6 +1552,9 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk)
 
 void disk_free_zone_resources(struct gendisk *disk)
 {
+	if (!disk->zone_wplugs_pool)
+		return;
+
 	cancel_work_sync(&disk->zone_wplugs_work);
 
 	if (disk->zone_wplugs_wq) {
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 14fe0fef811c..598fd3e7fcc8 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen)
 			      &key_type_user, key_name, true);
 
 	if (IS_ERR(kref))
-		ret = PTR_ERR(kref);
+		return PTR_ERR(kref);
 
 	key = key_ref_to_ptr(kref);
 	down_read(&key->sem);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 93780f41646b..1153721bc7c2 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -302,6 +302,21 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq,
 	return 0;
 }
 
+static void loop_clear_limits(struct loop_device *lo, int mode)
+{
+	struct queue_limits lim = queue_limits_start_update(lo->lo_queue);
+
+	if (mode & FALLOC_FL_ZERO_RANGE)
+		lim.max_write_zeroes_sectors = 0;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		lim.max_hw_discard_sectors = 0;
+		lim.discard_granularity = 0;
+	}
+
+	queue_limits_commit_update(lo->lo_queue, &lim);
+}
+
 static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 			int mode)
 {
@@ -320,6 +335,14 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 	ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
 	if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
 		return -EIO;
+
+	/*
+	 * We initially configure the limits in a hope that fallocate is
+	 * supported and clear them here if that turns out not to be true.
+	 */
+	if (unlikely(ret == -EOPNOTSUPP))
+		loop_clear_limits(lo, mode);
+
 	return ret;
 }
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 22a79a62cc4e..b87aa80a46dd 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -589,10 +589,11 @@ static inline int was_interrupted(int result)
 }
 
 /*
- * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns
- * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed.
+ * Returns BLK_STS_RESOURCE if the caller should retry after a delay.
+ * Returns BLK_STS_IOERR if sending failed.
  */
-static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
+static blk_status_t nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd,
+				 int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 	struct nbd_config *config = nbd->config;
@@ -614,13 +615,13 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 
 	type = req_to_nbd_cmd_type(req);
 	if (type == U32_MAX)
-		return -EIO;
+		return BLK_STS_IOERR;
 
 	if (rq_data_dir(req) == WRITE &&
 	    (config->flags & NBD_FLAG_READ_ONLY)) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Write on read-only\n");
-		return -EIO;
+		return BLK_STS_IOERR;
 	}
 
 	if (req->cmd_flags & REQ_FUA)
@@ -674,11 +675,11 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				nsock->sent = sent;
 			}
 			set_bit(NBD_CMD_REQUEUED, &cmd->flags);
-			return (__force int)BLK_STS_RESOURCE;
+			return BLK_STS_RESOURCE;
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
-		return -EAGAIN;
+		goto requeue;
 	}
 send_pages:
 	if (type != NBD_CMD_WRITE)
@@ -715,12 +716,12 @@ send_pages:
 					nsock->pending = req;
 					nsock->sent = sent;
 					set_bit(NBD_CMD_REQUEUED, &cmd->flags);
-					return (__force int)BLK_STS_RESOURCE;
+					return BLK_STS_RESOURCE;
 				}
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
 					result);
-				return -EAGAIN;
+				goto requeue;
 			}
 			/*
 			 * The completion might already have come in,
@@ -737,7 +738,16 @@ out:
 	trace_nbd_payload_sent(req, handle);
 	nsock->pending = NULL;
 	nsock->sent = 0;
-	return 0;
+	__set_bit(NBD_CMD_INFLIGHT, &cmd->flags);
+	return BLK_STS_OK;
+
+requeue:
+	/* retry on a different socket */
+	dev_err_ratelimited(disk_to_dev(nbd->disk),
+			    "Request send failed, requeueing\n");
+	nbd_mark_nsock_dead(nbd, nsock, 1);
+	nbd_requeue_cmd(cmd);
+	return BLK_STS_OK;
 }
 
 static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock,
@@ -1018,7 +1028,7 @@ static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 	struct nbd_device *nbd = cmd->nbd;
 	struct nbd_config *config;
 	struct nbd_sock *nsock;
-	int ret;
+	blk_status_t ret;
 
 	lockdep_assert_held(&cmd->lock);
 
@@ -1072,28 +1082,11 @@ again:
 		ret = BLK_STS_OK;
 		goto out;
 	}
-	/*
-	 * Some failures are related to the link going down, so anything that
-	 * returns EAGAIN can be retried on a different socket.
-	 */
 	ret = nbd_send_cmd(nbd, cmd, index);
-	/*
-	 * Access to this flag is protected by cmd->lock, thus it's safe to set
-	 * the flag after nbd_send_cmd() succeed to send request to server.
-	 */
-	if (!ret)
-		__set_bit(NBD_CMD_INFLIGHT, &cmd->flags);
-	else if (ret == -EAGAIN) {
-		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Request send failed, requeueing\n");
-		nbd_mark_nsock_dead(nbd, nsock, 1);
-		nbd_requeue_cmd(cmd);
-		ret = BLK_STS_OK;
-	}
 out:
 	mutex_unlock(&nsock->tx_lock);
 	nbd_config_put(nbd);
-	return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret;
+	return ret;
 }
 
 static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f5d150c62955..782090ce0bc1 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -998,6 +998,7 @@ void nvme_cleanup_cmd(struct request *req)
 			clear_bit_unlock(0, &ctrl->discard_page_busy);
 		else
 			kfree(bvec_virt(&req->special_vec));
+		req->rq_flags &= ~RQF_SPECIAL_PAYLOAD;
 	}
 }
 EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
@@ -3959,12 +3960,13 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 
 	mutex_lock(&ctrl->namespaces_lock);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid)
-			list_splice_init_rcu(&ns->list, &rm_list,
-					     synchronize_rcu);
+		if (ns->head->ns_id > nsid) {
+			list_del_rcu(&ns->list);
+			synchronize_srcu(&ctrl->srcu);
+			list_add_tail_rcu(&ns->list, &rm_list);
+		}
 	}
 	mutex_unlock(&ctrl->namespaces_lock);
-	synchronize_srcu(&ctrl->srcu);
 
 	list_for_each_entry_safe(ns, next, &rm_list, list)
 		nvme_ns_remove(ns);
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 9d9d2a127c4e..8b69427a4476 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -111,6 +111,13 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 	return req;
 }
 
+static void nvme_unmap_bio(struct bio *bio)
+{
+	if (bio_integrity(bio))
+		bio_integrity_unmap_free_user(bio);
+	blk_rq_unmap_user(bio);
+}
+
 static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
 		u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
@@ -157,7 +164,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 
 out_unmap:
 	if (bio)
-		blk_rq_unmap_user(bio);
+		nvme_unmap_bio(bio);
 out:
 	blk_mq_free_request(req);
 	return ret;
@@ -195,7 +202,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
 	if (bio)
-		blk_rq_unmap_user(bio);
+		nvme_unmap_bio(bio);
 	blk_mq_free_request(req);
 
 	if (effects)
@@ -406,7 +413,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
 	if (pdu->bio)
-		blk_rq_unmap_user(pdu->bio);
+		nvme_unmap_bio(pdu->bio);
 	io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags);
 }
 
@@ -432,7 +439,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	 */
 	if (blk_rq_is_poll(req)) {
 		if (pdu->bio)
-			blk_rq_unmap_user(pdu->bio);
+			nvme_unmap_bio(pdu->bio);
 		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
 	} else {
 		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 06f0c587f343..4ff460ba2826 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -957,6 +957,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	req->metadata_sg_cnt = 0;
 	req->transfer_len = 0;
 	req->metadata_len = 0;
+	req->cqe->result.u64 = 0;
 	req->cqe->status = 0;
 	req->cqe->sq_head = 0;
 	req->ns = NULL;
diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c
index d61b8c6ff3b2..cb34d644ed08 100644
--- a/drivers/nvme/target/fabrics-cmd-auth.c
+++ b/drivers/nvme/target/fabrics-cmd-auth.c
@@ -333,7 +333,6 @@ done:
 		pr_debug("%s: ctrl %d qid %d nvme status %x error loc %d\n",
 			 __func__, ctrl->cntlid, req->sq->qid,
 			 status, req->error_loc);
-	req->cqe->result.u64 = 0;
 	if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 &&
 	    req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) {
 		unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120;
@@ -516,8 +515,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req)
 	status = nvmet_copy_to_sgl(req, 0, d, al);
 	kfree(d);
 done:
-	req->cqe->result.u64 = 0;
-
 	if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2)
 		nvmet_auth_sq_free(req->sq);
 	else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) {
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 042b379cbb36..69d77d34bec1 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -226,9 +226,6 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	if (status)
 		goto out;
 
-	/* zero out initial completion result, assign values as needed */
-	req->cqe->result.u32 = 0;
-
 	if (c->recfmt != 0) {
 		pr_warn("invalid connect version (%d).\n",
 			le16_to_cpu(c->recfmt));
@@ -305,9 +302,6 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	if (status)
 		goto out;
 
-	/* zero out initial completion result, assign values as needed */
-	req->cqe->result.u32 = 0;
-
 	if (c->recfmt != 0) {
 		pr_warn("invalid connect version (%d).\n",
 			le16_to_cpu(c->recfmt));
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index bb4a69d538fd..f003782d4ecf 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -226,13 +226,13 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
 	    req->cmd->common.opcode == nvme_admin_identify) {
 		switch (req->cmd->identify.cns) {
 		case NVME_ID_CNS_CTRL:
-			nvmet_passthru_override_id_ctrl(req);
+			status = nvmet_passthru_override_id_ctrl(req);
 			break;
 		case NVME_ID_CNS_NS:
-			nvmet_passthru_override_id_ns(req);
+			status = nvmet_passthru_override_id_ns(req);
 			break;
 		case NVME_ID_CNS_NS_DESC_LIST:
-			nvmet_passthru_override_id_descs(req);
+			status = nvmet_passthru_override_id_descs(req);
 			break;
 		}
 	} else if (status < 0)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index d5379548d684..818e93612947 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -731,6 +731,7 @@ static inline bool bioset_initialized(struct bio_set *bs)
 		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
 
 int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed);
+void bio_integrity_unmap_free_user(struct bio *bio);
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
 extern bool bio_integrity_prep(struct bio *);
@@ -807,6 +808,9 @@ static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf,
 {
 	return -EINVAL;
 }
+static inline void bio_integrity_unmap_free_user(struct bio *bio)
+{
+}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */