Merge tag 'block-5.7-2020-04-10' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Here's a set of fixes that should go into this merge window. This
  contains:

   - NVMe pull request from Christoph with various fixes

   - Better discard support for loop (Evan)

   - Only call ->commit_rqs() if we have queued IO (Keith)

   - blkcg offlining fixes (Tejun)

   - fix (and fix the fix) for busy partitions"

* tag 'block-5.7-2020-04-10' of git://git.kernel.dk/linux-block:
  block: fix busy device checking in blk_drop_partitions again
  block: fix busy device checking in blk_drop_partitions
  nvmet-rdma: fix double free of rdma queue
  blk-mq: don't commit_rqs() if none were queued
  nvme-fc: Revert "add module to ops template to allow module references"
  nvme: fix deadlock caused by ANA update wrong locking
  nvmet-rdma: fix bonding failover possible NULL deref
  loop: Better discard support for block devices
  loop: Report EOPNOTSUPP properly
  nvmet: fix NULL dereference when removing a referral
  nvme: inherit stable pages constraint in the mpath stack device
  blkcg: don't offline parent blkcg first
  blkcg: rename blkcg->cgwb_refcnt to ->online_pin and always use it
  nvme-tcp: fix possible crash in recv error flow
  nvme-tcp: don't poll a non-live queue
  nvme-tcp: fix possible crash in write_zeroes processing
  nvmet-fc: fix typo in comment
  nvme-rdma: Replace comma with a semicolon
  nvme-fcloop: fix deallocation of working context
  nvme: fix compat address handling in several ioctls

Author: torvalds

block/blk-cgroup.c

@@ -883,8 +883,8 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css)
 	/* this prevents anyone from attaching or migrating to this blkcg */
 	wb_blkcg_offline(blkcg);
 
-	/* put the base cgwb reference allowing step 2 to be triggered */
-	blkcg_cgwb_put(blkcg);
+	/* put the base online pin allowing step 2 to be triggered */
+	blkcg_unpin_online(blkcg);
 }
 
 /**
@@ -983,11 +983,11 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	}
 
 	spin_lock_init(&blkcg->lock);
+	refcount_set(&blkcg->online_pin, 1);
 	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN);
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&blkcg->cgwb_list);
-	refcount_set(&blkcg->cgwb_refcnt, 1);
 #endif
 	list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
 
@@ -1006,6 +1006,21 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	return ret;
 }
 
+static int blkcg_css_online(struct cgroup_subsys_state *css)
+{
+	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg *parent = blkcg_parent(blkcg);
+
+	/*
+	 * blkcg_pin_online() is used to delay blkcg offline so that blkgs
+	 * don't go offline while cgwbs are still active on them.  Pin the
+	 * parent so that offline always happens towards the root.
+	 */
+	if (parent)
+		blkcg_pin_online(parent);
+	return 0;
+}
+
 /**
  * blkcg_init_queue - initialize blkcg part of request queue
  * @q: request_queue to initialize
@@ -1199,6 +1214,7 @@ static void blkcg_exit(struct task_struct *tsk)
 
 struct cgroup_subsys io_cgrp_subsys = {
 	.css_alloc = blkcg_css_alloc,
+	.css_online = blkcg_css_online,
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,

block/blk-mq.c

@@ -1289,7 +1289,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		 * the driver there was more coming, but that turned out to
 		 * be a lie.
 		 */
-		if (q->mq_ops->commit_rqs)
+		if (q->mq_ops->commit_rqs && queued)
 			q->mq_ops->commit_rqs(hctx);
 
 		spin_lock(&hctx->lock);
@@ -1911,6 +1911,8 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
+	int queued = 0;
+
 	while (!list_empty(list)) {
 		blk_status_t ret;
 		struct request *rq = list_first_entry(list, struct request,
@@ -1926,15 +1928,16 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				break;
 			}
 			blk_mq_end_request(rq, ret);
-		}
+		} else
+			queued++;
 	}
 
 	/*
 	 * If we didn't flush the entire list, we could have told
 	 * the driver there was more coming, but that turned out to
 	 * be a lie.
 	 */
-	if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs)
+	if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs && queued)
 		hctx->queue->mq_ops->commit_rqs(hctx);
 }
 

block/partitions/core.c

@@ -496,7 +496,7 @@ int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev)
 
 	if (!disk_part_scan_enabled(disk))
 		return 0;
-	if (bdev->bd_part_count || bdev->bd_super)
+	if (bdev->bd_part_count || bdev->bd_openers > 1)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
 	if (res)

drivers/block/loop.c

@@ -429,11 +429,12 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 	 * information.
 	 */
 	struct file *file = lo->lo_backing_file;
+	struct request_queue *q = lo->lo_queue;
 	int ret;
 
 	mode |= FALLOC_FL_KEEP_SIZE;
 
-	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
+	if (!blk_queue_discard(q)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -463,7 +464,7 @@ static void lo_complete_rq(struct request *rq)
 	if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
 	    req_op(rq) != REQ_OP_READ) {
 		if (cmd->ret < 0)
-			ret = BLK_STS_IOERR;
+			ret = errno_to_blk_status(cmd->ret);
 		goto end_io;
 	}
 
@@ -867,28 +868,47 @@ static void loop_config_discard(struct loop_device *lo)
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
 
+	/*
+	 * If the backing device is a block device, mirror its zeroing
+	 * capability. Set the discard sectors to the block device's zeroing
+	 * capabilities because loop discards result in blkdev_issue_zeroout(),
+	 * not blkdev_issue_discard(). This maintains consistent behavior with
+	 * file-backed loop devices: discarded regions read back as zero.
+	 */
+	if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
+		struct request_queue *backingq;
+
+		backingq = bdev_get_queue(inode->i_bdev);
+		blk_queue_max_discard_sectors(q,
+			backingq->limits.max_write_zeroes_sectors);
+
+		blk_queue_max_write_zeroes_sectors(q,
+			backingq->limits.max_write_zeroes_sectors);
+
 	/*
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard. However we do not support discard if
 	 * encryption is enabled, because it may give an attacker
 	 * useful information.
 	 */
-	if ((!file->f_op->fallocate) ||
-	    lo->lo_encrypt_key_size) {
+	} else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
 		q->limits.discard_granularity = 0;
 		q->limits.discard_alignment = 0;
 		blk_queue_max_discard_sectors(q, 0);
 		blk_queue_max_write_zeroes_sectors(q, 0);
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
-		return;
-	}
 
-	q->limits.discard_granularity = inode->i_sb->s_blocksize;
-	q->limits.discard_alignment = 0;
+	} else {
+		q->limits.discard_granularity = inode->i_sb->s_blocksize;
+		q->limits.discard_alignment = 0;
+
+		blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
+		blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+	}
 
-	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	if (q->limits.max_write_zeroes_sectors)
+		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)
@@ -1955,7 +1975,10 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
  failed:
 	/* complete non-aio request */
 	if (!cmd->use_aio || ret) {
-		cmd->ret = ret ? -EIO : 0;
+		if (ret == -EOPNOTSUPP)
+			cmd->ret = ret;
+		else
+			cmd->ret = ret ? -EIO : 0;
 		blk_mq_complete_request(rq);
 	}
 }

drivers/nvme/host/core.c

@@ -6,6 +6,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/compat.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/hdreg.h>
@@ -1252,6 +1253,18 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 	queue_work(nvme_wq, &ctrl->async_event_work);
 }
 
+/*
+ * Convert integer values from ioctl structures to user pointers, silently
+ * ignoring the upper bits in the compat case to match behaviour of 32-bit
+ * kernels.
+ */
+static void __user *nvme_to_user_ptr(uintptr_t ptrval)
+{
+	if (in_compat_syscall())
+		ptrval = (compat_uptr_t)ptrval;
+	return (void __user *)ptrval;
+}
+
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 {
 	struct nvme_user_io io;
@@ -1275,7 +1288,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 
 	length = (io.nblocks + 1) << ns->lba_shift;
 	meta_len = (io.nblocks + 1) * ns->ms;
-	metadata = (void __user *)(uintptr_t)io.metadata;
+	metadata = nvme_to_user_ptr(io.metadata);
 
 	if (ns->ext) {
 		length += meta_len;
@@ -1298,7 +1311,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.appmask = cpu_to_le16(io.appmask);
 
 	return nvme_submit_user_cmd(ns->queue, &c,
-			(void __user *)(uintptr_t)io.addr, length,
+			nvme_to_user_ptr(io.addr), length,
 			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
 }
 
@@ -1418,9 +1431,9 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata,
-			cmd.metadata_len, 0, &result, timeout);
+			nvme_to_user_ptr(cmd.addr), cmd.data_len,
+			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
+			0, &result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
 	if (status >= 0) {
@@ -1465,8 +1478,8 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
+			nvme_to_user_ptr(cmd.addr), cmd.data_len,
+			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
 			0, &cmd.result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
@@ -1884,6 +1897,13 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
+		if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
+			struct backing_dev_info *info =
+				ns->head->disk->queue->backing_dev_info;
+
+                        info->capabilities |= BDI_CAP_STABLE_WRITES;
+		}
+
 		revalidate_disk(ns->head->disk);
 	}
 #endif

drivers/nvme/host/fc.c

@@ -342,8 +342,7 @@ 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->module) {
+	    !template->max_dif_sgl_segments || !template->dma_boundary) {
 		ret = -EINVAL;
 		goto out_reghost_failed;
 	}
@@ -2016,7 +2015,6 @@ 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) {
@@ -2043,7 +2041,6 @@ 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
@@ -3074,15 +3071,10 @@ 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_mod_put;
+		goto out_free_ctrl;
 	}
 
 	ctrl->ctrl.opts = opts;
@@ -3232,8 +3224,6 @@ 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/multipath.c

@@ -510,7 +510,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	if (!nr_nsids)
 		return 0;
 
-	down_write(&ctrl->namespaces_rwsem);
+	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
 		unsigned nsid = le32_to_cpu(desc->nsids[n]);
 
@@ -521,7 +521,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 		if (++n == nr_nsids)
 			break;
 	}
-	up_write(&ctrl->namespaces_rwsem);
+	up_read(&ctrl->namespaces_rwsem);
 	return 0;
 }
 

drivers/nvme/host/rdma.c

@@ -1342,7 +1342,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 	int ret;
 
 	sge->addr   = qe->dma;
-	sge->length = sizeof(struct nvme_command),
+	sge->length = sizeof(struct nvme_command);
 	sge->lkey   = queue->device->pd->local_dma_lkey;
 
 	wr.next       = NULL;