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

Pull block fixes from Jens Axboe:
 "A few fixes for the current series. This contains:

   - Two fixes for NVMe:

     One fixes a reset race that can be triggered by repeated
     insert/removal of the module.

     The other fixes an issue on some platforms, where we get probe
     timeouts since legacy interrupts isn't working.  This used not to
     be a problem since we had the worker thread poll for completions,
     but since that was killed off, it means those poor souls can't
     successfully probe their NVMe device.  Use a proper IRQ check and
     probe (msi-x -> msi ->legacy), like most other drivers to work
     around this.  Both from Keith.

   - A loop corruption issue with offset in iters, from Ming Lei.

   - A fix for not having the partition stat per cpu ref count
     initialized before sending out the KOBJ_ADD, which could cause user
     space to access the counter prior to initialization.  Also from
     Ming Lei.

   - A fix for using the wrong congestion state, from Kaixu Xia"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: loop: fix filesystem corruption in case of aio/dio
  NVMe: Always use MSI/MSI-x interrupts
  NVMe: Fix reset/remove race
  writeback: fix the wrong congested state variable definition
  block: partition: initialize percpuref before sending out KOBJ_ADD

block/partition-generic.c

@@ -361,15 +361,20 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 			goto out_del;
 	}
 
+	err = hd_ref_init(p);
+	if (err) {
+		if (flags & ADDPART_FLAG_WHOLEDISK)
+			goto out_remove_file;
+		goto out_del;
+	}
+
 	/* everything is up and running, commence */
 	rcu_assign_pointer(ptbl->part[partno], p);
 
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
-
-	if (!hd_ref_init(p))
-		return p;
+	return p;
 
 out_free_info:
 	free_part_info(p);
@@ -378,6 +383,8 @@ out_free_stats:
 out_free:
 	kfree(p);
 	return ERR_PTR(err);
+out_remove_file:
+	device_remove_file(pdev, &dev_attr_whole_disk);
 out_del:
 	kobject_put(p->holder_dir);
 	device_del(pdev);

drivers/block/loop.c

@@ -488,6 +488,12 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
 	iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
 		      bio_segments(bio), blk_rq_bytes(cmd->rq));
+	/*
+	 * This bio may be started from the middle of the 'bvec'
+	 * because of bio splitting, so offset from the bvec must
+	 * be passed to iov iterator
+	 */
+	iter.iov_offset = bio->bi_iter.bi_bvec_done;
 
 	cmd->iocb.ki_pos = pos;
 	cmd->iocb.ki_filp = file;

drivers/nvme/host/pci.c

@@ -1478,8 +1478,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (result > 0) {
 		dev_err(dev->ctrl.device,
 			"Could not set queue count (%d)\n", result);
-		nr_io_queues = 0;
-		result = 0;
+		return 0;
 	}
 
 	if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
@@ -1513,7 +1512,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	 * If we enable msix early due to not intx, disable it again before
 	 * setting up the full range we need.
 	 */
-	if (!pdev->irq)
+	if (pdev->msi_enabled)
+		pci_disable_msi(pdev);
+	else if (pdev->msix_enabled)
 		pci_disable_msix(pdev);
 
 	for (i = 0; i < nr_io_queues; i++)
@@ -1696,7 +1697,6 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	if (pci_enable_device_mem(pdev))
 		return result;
 
-	dev->entry[0].vector = pdev->irq;
 	pci_set_master(pdev);
 
 	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
@@ -1709,13 +1709,18 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	}
 
 	/*
-	 * Some devices don't advertse INTx interrupts, pre-enable a single
-	 * MSIX vec for setup. We'll adjust this later.
+	 * Some devices and/or platforms don't advertise or work with INTx
+	 * interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
+	 * adjust this later.
 	 */
-	if (!pdev->irq) {
-		result = pci_enable_msix(pdev, dev->entry, 1);
-		if (result < 0)
-			goto disable;
+	if (pci_enable_msix(pdev, dev->entry, 1)) {
+		pci_enable_msi(pdev);
+		dev->entry[0].vector = pdev->irq;
+	}
+
+	if (!dev->entry[0].vector) {
+		result = -ENODEV;
+		goto disable;
 	}
 
 	cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
@@ -1859,6 +1864,9 @@ static void nvme_reset_work(struct work_struct *work)
 	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
 
+	if (test_bit(NVME_CTRL_REMOVING, &dev->flags))
+		goto out;
+
 	set_bit(NVME_CTRL_RESETTING, &dev->flags);
 
 	result = nvme_pci_enable(dev);
@@ -2078,11 +2086,10 @@ static void nvme_remove(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
 
-	del_timer_sync(&dev->watchdog_timer);
-
 	set_bit(NVME_CTRL_REMOVING, &dev->flags);
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->async_work);
+	flush_work(&dev->reset_work);
 	flush_work(&dev->scan_work);
 	nvme_remove_namespaces(&dev->ctrl);
 	nvme_uninit_ctrl(&dev->ctrl);

mm/backing-dev.c

@@ -898,7 +898,7 @@ static atomic_t nr_wb_congested[2];
 void clear_wb_congested(struct bdi_writeback_congested *congested, int sync)
 {
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
-	enum wb_state bit;
+	enum wb_congested_state bit;
 
 	bit = sync ? WB_sync_congested : WB_async_congested;
 	if (test_and_clear_bit(bit, &congested->state))
@@ -911,7 +911,7 @@ EXPORT_SYMBOL(clear_wb_congested);
 
 void set_wb_congested(struct bdi_writeback_congested *congested, int sync)
 {
-	enum wb_state bit;
+	enum wb_congested_state bit;
 
 	bit = sync ? WB_sync_congested : WB_async_congested;
 	if (!test_and_set_bit(bit, &congested->state))