Merge tag 'for-linus-20191212' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - stable fix for the bi_size overflow. Not a corruption issue, but a
   case wher we could merge but disallowed (Andreas)

 - NVMe pull request via Keith, with various fixes.

 - MD pull request from Song.

 - Merge window regression fix for the rq passthrough stats (Logan)

 - Remove unused blkcg_drain_queue() function (Guoqing)

* tag 'for-linus-20191212' of git://git.kernel.dk/linux-block:
  blk-cgroup: remove blkcg_drain_queue
  block: fix NULL pointer dereference in account statistics with IDE
  md: make sure desc_nr less than MD_SB_DISKS
  md: raid1: check rdev before reference in raid1_sync_request func
  raid5: need to set STRIPE_HANDLE for batch head
  block: fix "check bi_size overflow before merge"
  nvme/pci: Fix read queue count
  nvme/pci Limit write queue sizes to possible cpus
  nvme/pci: Fix write and poll queue types
  nvme/pci: Remove last_cq_head
  nvme: Namepace identification descriptor list is optional
  nvme-fc: fix double-free scenarios on hw queues
  nvme: else following return is not needed
  nvme: add error message on mismatching controller ids
  nvme_fc: add module to ops template to allow module references
  nvmet-loop: Avoid preallocating big SGL for data
  nvme-fc: Avoid preallocating big SGL for data
  nvme-rdma: Avoid preallocating big SGL for data

block/bio.c

@@ -754,10 +754,12 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return false;
 
-	if (bio->bi_vcnt > 0 && !bio_full(bio, len)) {
+	if (bio->bi_vcnt > 0) {
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
+			if (bio->bi_iter.bi_size > UINT_MAX - len)
+				return false;
 			bv->bv_len += len;
 			bio->bi_iter.bi_size += len;
 			return true;

block/blk-cgroup.c

@@ -1061,26 +1061,6 @@ int blkcg_init_queue(struct request_queue *q)
 	return PTR_ERR(blkg);
 }
 
-/**
- * blkcg_drain_queue - drain blkcg part of request_queue
- * @q: request_queue to drain
- *
- * Called from blk_drain_queue().  Responsible for draining blkcg part.
- */
-void blkcg_drain_queue(struct request_queue *q)
-{
-	lockdep_assert_held(&q->queue_lock);
-
-	/*
-	 * @q could be exiting and already have destroyed all blkgs as
-	 * indicated by NULL root_blkg.  If so, don't confuse policies.
-	 */
-	if (!q->root_blkg)
-		return;
-
-	blk_throtl_drain(q);
-}
-
 /**
  * blkcg_exit_queue - exit and release blkcg part of request_queue
  * @q: request_queue being released

block/blk-core.c

@@ -1310,7 +1310,7 @@ EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 
 void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
-	if (blk_do_io_stat(req)) {
+	if (req->part && blk_do_io_stat(req)) {
 		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 
@@ -1328,7 +1328,8 @@ void blk_account_io_done(struct request *req, u64 now)
 	 * normal IO on queueing nor completion.  Accounting the
 	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
+	if (req->part && blk_do_io_stat(req) &&
+	    !(req->rq_flags & RQF_FLUSH_SEQ)) {
 		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 

drivers/md/md.c

@@ -1159,6 +1159,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	/* not spare disk, or LEVEL_MULTIPATH */
 	if (sb->level == LEVEL_MULTIPATH ||
 		(rdev->desc_nr >= 0 &&
+		 rdev->desc_nr < MD_SB_DISKS &&
 		 sb->disks[rdev->desc_nr].state &
 		 ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))))
 		spare_disk = false;

drivers/md/raid1.c

@@ -2782,7 +2782,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 				write_targets++;
 			}
 		}
-		if (bio->bi_end_io) {
+		if (rdev && bio->bi_end_io) {
 			atomic_inc(&rdev->nr_pending);
 			bio->bi_iter.bi_sector = sector_nr + rdev->data_offset;
 			bio_set_dev(bio, rdev->bdev);

drivers/md/raid5.c

@@ -5726,7 +5726,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 				do_flush = false;
 			}
 
-			if (!sh->batch_head)
+			if (!sh->batch_head || sh == sh->batch_head)
 				set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((!sh->batch_head || sh == sh->batch_head) &&

drivers/nvme/host/core.c

@@ -1735,6 +1735,8 @@ static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
 		if (ret)
 			dev_warn(ctrl->device,
 				 "Identify Descriptors failed (%d)\n", ret);
+		if (ret > 0)
+			ret = 0;
 	}
 	return ret;
 }
@@ -2852,6 +2854,10 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		 * admin connect
 		 */
 		if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
+			dev_err(ctrl->device,
+				"Mismatching cntlid: Connect %u vs Identify "
+				"%u, rejecting\n",
+				ctrl->cntlid, le16_to_cpu(id->cntlid));
 			ret = -EINVAL;
 			goto out_free;
 		}

drivers/nvme/host/fc.c

@@ -95,7 +95,7 @@ struct nvme_fc_fcp_op {
 
 struct nvme_fcp_op_w_sgl {
 	struct nvme_fc_fcp_op	op;
-	struct scatterlist	sgl[SG_CHUNK_SIZE];
+	struct scatterlist	sgl[NVME_INLINE_SG_CNT];
 	uint8_t			priv[0];
 };
 
@@ -342,7 +342,8 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo,
 	    !template->ls_req || !template->fcp_io ||
 	    !template->ls_abort || !template->fcp_abort ||
 	    !template->max_hw_queues || !template->max_sgl_segments ||
-	    !template->max_dif_sgl_segments || !template->dma_boundary) {
+	    !template->max_dif_sgl_segments || !template->dma_boundary ||
+	    !template->module) {
 		ret = -EINVAL;
 		goto out_reghost_failed;
 	}
@@ -2015,6 +2016,7 @@ nvme_fc_ctrl_free(struct kref *ref)
 {
 	struct nvme_fc_ctrl *ctrl =
 		container_of(ref, struct nvme_fc_ctrl, ref);
+	struct nvme_fc_lport *lport = ctrl->lport;
 	unsigned long flags;
 
 	if (ctrl->ctrl.tagset) {
@@ -2041,6 +2043,7 @@ nvme_fc_ctrl_free(struct kref *ref)
 	if (ctrl->ctrl.opts)
 		nvmf_free_options(ctrl->ctrl.opts);
 	kfree(ctrl);
+	module_put(lport->ops->module);
 }
 
 static void
@@ -2141,7 +2144,7 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 	freq->sg_table.sgl = freq->first_sgl;
 	ret = sg_alloc_table_chained(&freq->sg_table,
 			blk_rq_nr_phys_segments(rq), freq->sg_table.sgl,
-			SG_CHUNK_SIZE);
+			NVME_INLINE_SG_CNT);
 	if (ret)
 		return -ENOMEM;
 
@@ -2150,7 +2153,7 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 	freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl,
 				op->nents, rq_dma_dir(rq));
 	if (unlikely(freq->sg_cnt <= 0)) {
-		sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE);
+		sg_free_table_chained(&freq->sg_table, NVME_INLINE_SG_CNT);
 		freq->sg_cnt = 0;
 		return -EFAULT;
 	}
@@ -2173,7 +2176,7 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 	fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents,
 			rq_dma_dir(rq));
 
-	sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE);
+	sg_free_table_chained(&freq->sg_table, NVME_INLINE_SG_CNT);
 
 	freq->sg_cnt = 0;
 }
@@ -2910,10 +2913,22 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 static void
 __nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl)
 {
-	nvme_stop_keep_alive(&ctrl->ctrl);
+	/*
+	 * if state is connecting - the error occurred as part of a
+	 * reconnect attempt. The create_association error paths will
+	 * clean up any outstanding io.
+	 *
+	 * if it's a different state - ensure all pending io is
+	 * terminated. Given this can delay while waiting for the
+	 * aborted io to return, we recheck adapter state below
+	 * before changing state.
+	 */
+	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) {
+		nvme_stop_keep_alive(&ctrl->ctrl);
 
-	/* will block will waiting for io to terminate */
-	nvme_fc_delete_association(ctrl);
+		/* will block will waiting for io to terminate */
+		nvme_fc_delete_association(ctrl);
+	}
 
 	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING &&
 	    !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
@@ -3059,10 +3074,15 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		goto out_fail;
 	}
 
+	if (!try_module_get(lport->ops->module)) {
+		ret = -EUNATCH;
+		goto out_free_ctrl;
+	}
+
 	idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL);
 	if (idx < 0) {
 		ret = -ENOSPC;
-		goto out_free_ctrl;
+		goto out_mod_put;
 	}
 
 	ctrl->ctrl.opts = opts;
@@ -3215,6 +3235,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 out_free_ida:
 	put_device(ctrl->dev);
 	ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
+out_mod_put:
+	module_put(lport->ops->module);
 out_free_ctrl:
 	kfree(ctrl);
 out_fail:

drivers/nvme/host/nvme.h

@@ -28,6 +28,12 @@ extern unsigned int admin_timeout;
 #define NVME_DEFAULT_KATO	5
 #define NVME_KATO_GRACE		10
 
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
+#define  NVME_INLINE_SG_CNT  0
+#else
+#define  NVME_INLINE_SG_CNT  2
+#endif
+
 extern struct workqueue_struct *nvme_wq;
 extern struct workqueue_struct *nvme_reset_wq;
 extern struct workqueue_struct *nvme_delete_wq;

drivers/nvme/host/pci.c

@@ -68,14 +68,14 @@ static int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
 
-static int write_queues;
-module_param(write_queues, int, 0644);
+static unsigned int write_queues;
+module_param(write_queues, uint, 0644);
 MODULE_PARM_DESC(write_queues,
 	"Number of queues to use for writes. If not set, reads and writes "
 	"will share a queue set.");
 
-static int poll_queues;
-module_param(poll_queues, int, 0644);
+static unsigned int poll_queues;
+module_param(poll_queues, uint, 0644);
 MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO.");
 
 struct nvme_dev;
@@ -176,7 +176,6 @@ struct nvme_queue {
 	u16 sq_tail;
 	u16 last_sq_tail;
 	u16 cq_head;
-	u16 last_cq_head;
 	u16 qid;
 	u8 cq_phase;
 	u8 sqes;
@@ -1026,10 +1025,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
 	 * the irq handler, even if that was on another CPU.
 	 */
 	rmb();
-	if (nvmeq->cq_head != nvmeq->last_cq_head)
-		ret = IRQ_HANDLED;
 	nvme_process_cq(nvmeq, &start, &end, -1);
-	nvmeq->last_cq_head = nvmeq->cq_head;
 	wmb();
 
 	if (start != end) {
@@ -1549,7 +1545,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
 		return result;
-	else if (result)
+	if (result)
 		goto release_cq;
 
 	nvmeq->cq_vector = vector;
@@ -2058,7 +2054,6 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.priv		= dev,
 	};
 	unsigned int irq_queues, this_p_queues;
-	unsigned int nr_cpus = num_possible_cpus();
 
 	/*
 	 * Poll queues don't need interrupts, but we need at least one IO
@@ -2069,10 +2064,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		this_p_queues = nr_io_queues - 1;
 		irq_queues = 1;
 	} else {
-		if (nr_cpus < nr_io_queues - this_p_queues)
-			irq_queues = nr_cpus + 1;
-		else
-			irq_queues = nr_io_queues - this_p_queues + 1;
+		irq_queues = nr_io_queues - this_p_queues + 1;
 	}
 	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
 
@@ -3142,6 +3134,9 @@ static int __init nvme_init(void)
 	BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
 	BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2);
+
+	write_queues = min(write_queues, num_possible_cpus());
+	poll_queues = min(poll_queues, num_possible_cpus());
 	return pci_register_driver(&nvme_driver);
 }
 

drivers/nvme/host/rdma.c

@@ -731,7 +731,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 		set->reserved_tags = 2; /* connect + keep-alive */
 		set->numa_node = nctrl->numa_node;
 		set->cmd_size = sizeof(struct nvme_rdma_request) +
-			SG_CHUNK_SIZE * sizeof(struct scatterlist);
+			NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
 		set->driver_data = ctrl;
 		set->nr_hw_queues = 1;
 		set->timeout = ADMIN_TIMEOUT;
@@ -745,7 +745,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 		set->numa_node = nctrl->numa_node;
 		set->flags = BLK_MQ_F_SHOULD_MERGE;
 		set->cmd_size = sizeof(struct nvme_rdma_request) +
-			SG_CHUNK_SIZE * sizeof(struct scatterlist);
+			NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
 		set->driver_data = ctrl;
 		set->nr_hw_queues = nctrl->queue_count - 1;
 		set->timeout = NVME_IO_TIMEOUT;
@@ -1160,7 +1160,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 	}
 
 	ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq));
-	sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE);
+	sg_free_table_chained(&req->sg_table, NVME_INLINE_SG_CNT);
 }
 
 static int nvme_rdma_set_sg_null(struct nvme_command *c)
@@ -1276,7 +1276,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 	req->sg_table.sgl = req->first_sgl;
 	ret = sg_alloc_table_chained(&req->sg_table,
 			blk_rq_nr_phys_segments(rq), req->sg_table.sgl,
-			SG_CHUNK_SIZE);
+			NVME_INLINE_SG_CNT);
 	if (ret)
 		return -ENOMEM;
 
@@ -1314,7 +1314,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 out_unmap_sg:
 	ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq));
 out_free_table:
-	sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE);
+	sg_free_table_chained(&req->sg_table, NVME_INLINE_SG_CNT);
 	return ret;
 }
 

drivers/nvme/target/fcloop.c

@@ -850,6 +850,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport)
 #define FCLOOP_DMABOUND_4G		0xFFFFFFFF
 
 static struct nvme_fc_port_template fctemplate = {
+	.module			= THIS_MODULE,
 	.localport_delete	= fcloop_localport_delete,
 	.remoteport_delete	= fcloop_remoteport_delete,
 	.create_queue		= fcloop_create_queue,

drivers/nvme/target/loop.c

@@ -76,7 +76,7 @@ static void nvme_loop_complete_rq(struct request *req)
 {
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
 
-	sg_free_table_chained(&iod->sg_table, SG_CHUNK_SIZE);
+	sg_free_table_chained(&iod->sg_table, NVME_INLINE_SG_CNT);
 	nvme_complete_rq(req);
 }
 
@@ -156,7 +156,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		iod->sg_table.sgl = iod->first_sgl;
 		if (sg_alloc_table_chained(&iod->sg_table,
 				blk_rq_nr_phys_segments(req),
-				iod->sg_table.sgl, SG_CHUNK_SIZE)) {
+				iod->sg_table.sgl, NVME_INLINE_SG_CNT)) {
 			nvme_cleanup_cmd(req);
 			return BLK_STS_RESOURCE;
 		}
@@ -342,7 +342,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
 	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
 	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
-		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+		NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
 	ctrl->admin_tag_set.driver_data = ctrl;
 	ctrl->admin_tag_set.nr_hw_queues = 1;
 	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
@@ -516,7 +516,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 	ctrl->tag_set.numa_node = NUMA_NO_NODE;
 	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
-		SG_CHUNK_SIZE * sizeof(struct scatterlist);
+		NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
 	ctrl->tag_set.driver_data = ctrl;
 	ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1;
 	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;