Merge tag 'block-6.7-2023-12-01' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
     - Invalid namespace identification error handling (Marizio Ewan,
       Keith)
     - Fabrics keep-alive tuning (Mark)

 - Fix for a bad error check regression in bcache (Markus)

 - Fix for a performance regression with O_DIRECT (Ming)

 - Fix for a flush related deadlock (Ming)

 - Make the read-only warn on per-partition (Yu)

* tag 'block-6.7-2023-12-01' of git://git.kernel.dk/linux:
  nvme-core: check for too small lba shift
  blk-mq: don't count completed flush data request as inflight in case of quiesce
  block: Document the role of the two attribute groups
  block: warn once for each partition in bio_check_ro()
  block: move .bd_inode into 1st cacheline of block_device
  nvme: check for valid nvme_identify_ns() before using it
  nvme-core: fix a memory leak in nvme_ns_info_from_identify()
  nvme: fine-tune sending of first keep-alive
  bcache: revert replacing IS_ERR_OR_NULL with IS_ERR

2 files changed, 29 insertions, 7 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 1b0892fe7ddb..196cdacce38f 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1522,7 +1522,7 @@ out_nocoalesce:
 	bch_keylist_free(&keylist);
 
 	for (i = 0; i < nodes; i++)
-		if (!IS_ERR(new_nodes[i])) {
+		if (!IS_ERR_OR_NULL(new_nodes[i])) {
 			btree_node_free(new_nodes[i]);
 			rw_unlock(true, new_nodes[i]);
 		}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 46a4c9c5ea96..1be1ce522896 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1192,8 +1192,16 @@ static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl)
 
 static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 {
-	queue_delayed_work(nvme_wq, &ctrl->ka_work,
-			   nvme_keep_alive_work_period(ctrl));
+	unsigned long now = jiffies;
+	unsigned long delay = nvme_keep_alive_work_period(ctrl);
+	unsigned long ka_next_check_tm = ctrl->ka_last_check_time + delay;
+
+	if (time_after(now, ka_next_check_tm))
+		delay = 0;
+	else
+		delay = ka_next_check_tm - now;
+
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
 static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
@@ -1479,7 +1487,8 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 	if (id->ncap == 0) {
 		/* namespace not allocated or attached */
 		info->is_removed = true;
-		return -ENODEV;
+		ret = -ENODEV;
+		goto error;
 	}
 
 	info->anagrpid = id->anagrpid;
@@ -1497,8 +1506,10 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 		    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
 			memcpy(ids->nguid, id->nguid, sizeof(ids->nguid));
 	}
+
+error:
 	kfree(id);
-	return 0;
+	return ret;
 }
 
 static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
@@ -1890,9 +1901,10 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
-	 * yet, so catch this early and don't allow block I/O.
+	 * or smaller than a sector size yet, so catch this early and don't
+	 * allow block I/O.
 	 */
-	if (ns->lba_shift > PAGE_SHIFT) {
+	if (ns->lba_shift > PAGE_SHIFT || ns->lba_shift < SECTOR_SHIFT) {
 		capacity = 0;
 		bs = (1 << 9);
 	}
@@ -2029,6 +2041,13 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (ret)
 		return ret;
 
+	if (id->ncap == 0) {
+		/* namespace not allocated or attached */
+		info->is_removed = true;
+		ret = -ENODEV;
+		goto error;
+	}
+
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
 	ns->lba_shift = id->lbaf[lbaf].ds;
@@ -2090,6 +2109,8 @@ out:
 		set_bit(NVME_NS_READY, &ns->flags);
 		ret = 0;
 	}
+
+error:
 	kfree(id);
 	return ret;
 }
@@ -4471,6 +4492,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+	ctrl->ka_last_check_time = jiffies;
 
 	BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) >
 			PAGE_SIZE);