Merge tag 'block-6.8-2024-02-10' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
     - Update a potentially stale firmware attribute (Maurizio)
     - Fixes for the recent verbose error logging (Keith, Chaitanya)
     - Protection information payload size fix for passthrough (Francis)

 - Fix for a queue freezing issue in virtblk (Yi)

 - blk-iocost underflow fix (Tejun)

 - blk-wbt task detection fix (Jan)

* tag 'block-6.8-2024-02-10' of git://git.kernel.dk/linux:
  virtio-blk: Ensure no requests in virtqueues before deleting vqs.
  blk-iocost: Fix an UBSAN shift-out-of-bounds warning
  nvme: use ns->head->pi_size instead of t10_pi_tuple structure size
  nvme-core: fix comment to reflect right functions
  nvme: move passthrough logging attribute to head
  blk-wbt: Fix detection of dirty-throttled tasks
  nvme-host: fix the updating of the firmware version

block/blk-iocost.c

@@ -1353,6 +1353,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
 
 	lockdep_assert_held(&iocg->waitq.lock);
 
+	/*
+	 * If the delay is set by another CPU, we may be in the past. No need to
+	 * change anything if so. This avoids decay calculation underflow.
+	 */
+	if (time_before64(now->now, iocg->delay_at))
+		return false;
+
 	/* calculate the current delay in effect - 1/2 every second */
 	tdelta = now->now - iocg->delay_at;
 	if (iocg->delay)

block/blk-wbt.c

@@ -163,9 +163,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb;
+	struct backing_dev_info *bdi = rwb->rqos.disk->bdi;
 
-	return time_before(jiffies, wb->dirty_sleep + HZ);
+	return time_before(jiffies, bdi->last_bdp_sleep + HZ);
 }
 
 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,

drivers/block/virtio_blk.c

@@ -1593,14 +1593,15 @@ static int virtblk_freeze(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	/* Ensure no requests in virtqueues before deleting vqs. */
+	blk_mq_freeze_queue(vblk->disk->queue);
+
 	/* Ensure we don't receive any more interrupts */
 	virtio_reset_device(vdev);
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
 
-	blk_mq_quiesce_queue(vblk->disk->queue);
-
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);
 
@@ -1618,7 +1619,7 @@ static int virtblk_restore(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	blk_mq_unquiesce_queue(vblk->disk->queue);
+	blk_mq_unfreeze_queue(vblk->disk->queue);
 	return 0;
 }
 #endif

drivers/nvme/host/core.c

@@ -713,7 +713,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
 	if (req->q->queuedata) {
 		struct nvme_ns *ns = req->q->disk->private_data;
 
-		logging_enabled = ns->passthru_err_log_enabled;
+		logging_enabled = ns->head->passthru_err_log_enabled;
 		req->timeout = NVME_IO_TIMEOUT;
 	} else { /* no queuedata implies admin queue */
 		logging_enabled = nr->ctrl->passthru_err_log_enabled;
@@ -3696,7 +3696,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
 	ns->disk = disk;
 	ns->queue = disk->queue;
-	ns->passthru_err_log_enabled = false;
 
 	if (ctrl->opts && ctrl->opts->data_digest)
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
@@ -3762,8 +3761,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
 	/*
 	 * Set ns->disk->device->driver_data to ns so we can access
-	 * ns->logging_enabled in nvme_passthru_err_log_enabled_store() and
-	 * nvme_passthru_err_log_enabled_show().
+	 * ns->head->passthru_err_log_enabled in
+	 * nvme_io_passthru_err_log_enabled_[store | show]().
 	 */
 	dev_set_drvdata(disk_to_dev(ns->disk), ns);
 
@@ -4191,6 +4190,7 @@ static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)
 static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 {
 	struct nvme_fw_slot_info_log *log;
+	u8 next_fw_slot, cur_fw_slot;
 
 	log = kmalloc(sizeof(*log), GFP_KERNEL);
 	if (!log)
@@ -4202,13 +4202,15 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 		goto out_free_log;
 	}
 
-	if (log->afi & 0x70 || !(log->afi & 0x7)) {
+	cur_fw_slot = log->afi & 0x7;
+	next_fw_slot = (log->afi & 0x70) >> 4;
+	if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) {
 		dev_info(ctrl->device,
 			 "Firmware is activated after next Controller Level Reset\n");
 		goto out_free_log;
 	}
 
-	memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1],
+	memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1],
 		sizeof(ctrl->subsys->firmware_rev));
 
 out_free_log:

drivers/nvme/host/ioctl.c

@@ -228,7 +228,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->head->ms == sizeof(struct t10_pi_tuple)) {
+	    (ns->head->ms == ns->head->pi_size)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.

drivers/nvme/host/nvme.h

@@ -455,6 +455,7 @@ struct nvme_ns_head {
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
+	bool			passthru_err_log_enabled;
 	int			instance;
 	struct nvme_effects_log *effects;
 	u64			nuse;
@@ -523,7 +524,6 @@ struct nvme_ns {
 	struct device		cdev_device;
 
 	struct nvme_fault_inject fault_inject;
-	bool			passthru_err_log_enabled;
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */

drivers/nvme/host/sysfs.c

@@ -48,8 +48,8 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
-	int err;
 	bool passthru_err_log_enabled;
+	int err;
 
 	err = kstrtobool(buf, &passthru_err_log_enabled);
 	if (err)
@@ -60,25 +60,34 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
 	return count;
 }
 
+static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (nvme_disk_is_ns_head(disk))
+		return disk->private_data;
+	return nvme_get_ns_from_dev(dev)->head;
+}
+
 static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct nvme_ns *n = dev_get_drvdata(dev);
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
 
-	return sysfs_emit(buf, n->passthru_err_log_enabled ? "on\n" : "off\n");
+	return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n");
 }
 
 static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
-	struct nvme_ns *ns = dev_get_drvdata(dev);
-	int err;
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
 	bool passthru_err_log_enabled;
+	int err;
 
 	err = kstrtobool(buf, &passthru_err_log_enabled);
 	if (err)
 		return -EINVAL;
-	ns->passthru_err_log_enabled = passthru_err_log_enabled;
+	head->passthru_err_log_enabled = passthru_err_log_enabled;
 
 	return count;
 }
@@ -91,15 +100,6 @@ static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
 	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
 	nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
 
-static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
-{
-	struct gendisk *disk = dev_to_disk(dev);
-
-	if (nvme_disk_is_ns_head(disk))
-		return disk->private_data;
-	return nvme_get_ns_from_dev(dev)->head;
-}
-
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {

include/linux/backing-dev-defs.h

@@ -141,8 +141,6 @@ struct bdi_writeback {
 	struct delayed_work dwork;	/* work item used for writeback */
 	struct delayed_work bw_dwork;	/* work item used for bandwidth estimate */
 
-	unsigned long dirty_sleep;	/* last wait */
-
 	struct list_head bdi_node;	/* anchored at bdi->wb_list */
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -179,6 +177,11 @@ struct backing_dev_info {
 	 * any dirty wbs, which is depended upon by bdi_has_dirty().
 	 */
 	atomic_long_t tot_write_bandwidth;
+	/*
+	 * Jiffies when last process was dirty throttled on this bdi. Used by
+	 * blk-wbt.
+	 */
+	unsigned long last_bdp_sleep;
 
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
 	struct list_head wb_list; /* list of all wbs */

mm/backing-dev.c

@@ -436,7 +436,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_LIST_HEAD(&wb->work_list);
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 	INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
-	wb->dirty_sleep = jiffies;
 
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
@@ -921,6 +920,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
 	init_waitqueue_head(&bdi->wb_waitq);
+	bdi->last_bdp_sleep = jiffies;
 
 	return cgwb_bdi_init(bdi);
 }

mm/page-writeback.c

@@ -1921,7 +1921,7 @@ static int balance_dirty_pages(struct bdi_writeback *wb,
 			break;
 		}
 		__set_current_state(TASK_KILLABLE);
-		wb->dirty_sleep = now;
+		bdi->last_bdp_sleep = jiffies;
 		io_schedule_timeout(pause);
 
 		current->dirty_paused_when = now + pause;