Merge tag 'for-linus-20190715' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "A later pull request with some followup items. I had some vacation
  coming up to the merge window, so certain things items were delayed a
  bit. This pull request also contains fixes that came in within the
  last few days of the merge window, which I didn't want to push right
  before sending you a pull request.

  This contains:

   - NVMe pull request, mostly fixes, but also a few minor items on the
     feature side that were timing constrained (Christoph et al)

   - Report zones fixes (Damien)

   - Removal of dead code (Damien)

   - Turn on cgroup psi memstall (Josef)

   - block cgroup MAINTAINERS entry (Konstantin)

   - Flush init fix (Josef)

   - blk-throttle low iops timing fix (Konstantin)

   - nbd resize fixes (Mike)

   - nbd 0 blocksize crash fix (Xiubo)

   - block integrity error leak fix (Wenwen)

   - blk-cgroup writeback and priority inheritance fixes (Tejun)"

* tag 'for-linus-20190715' of git://git.kernel.dk/linux-block: (42 commits)
  MAINTAINERS: add entry for block io cgroup
  null_blk: fixup ->report_zones() for !CONFIG_BLK_DEV_ZONED
  block: Limit zone array allocation size
  sd_zbc: Fix report zones buffer allocation
  block: Kill gfp_t argument of blkdev_report_zones()
  block: Allow mapping of vmalloc-ed buffers
  block/bio-integrity: fix a memory leak bug
  nvme: fix NULL deref for fabrics options
  nbd: add netlink reconfigure resize support
  nbd: fix crash when the blksize is zero
  block: Disable write plugging for zoned block devices
  block: Fix elevator name declaration
  block: Remove unused definitions
  nvme: fix regression upon hot device removal and insertion
  blk-throttle: fix zero wait time for iops throttled group
  block: Fix potential overflow in blk_report_zones()
  blkcg: implement REQ_CGROUP_PUNT
  blkcg, writeback: Implement wbc_blkcg_css()
  blkcg, writeback: Add wbc->no_cgroup_owner
  blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner()
  ...

1 files changed, 39 insertions, 4 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index b2dd4e391f5c..cc09b81fc7f4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -11,6 +11,7 @@
 #include <linux/hdreg.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 #include <linux/list_sort.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -1626,6 +1627,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 {
 	sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9);
 	unsigned short bs = 1 << ns->lba_shift;
+	u32 atomic_bs, phys_bs, io_opt;
 
 	if (ns->lba_shift > PAGE_SHIFT) {
 		/* unsupported block size, set capacity to 0 later */
@@ -1634,9 +1636,37 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_freeze_queue(disk->queue);
 	blk_integrity_unregister(disk);
 
+	if (id->nabo == 0) {
+		/*
+		 * Bit 1 indicates whether NAWUPF is defined for this namespace
+		 * and whether it should be used instead of AWUPF. If NAWUPF ==
+		 * 0 then AWUPF must be used instead.
+		 */
+		if (id->nsfeat & (1 << 1) && id->nawupf)
+			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
+		else
+			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+	} else {
+		atomic_bs = bs;
+	}
+	phys_bs = bs;
+	io_opt = bs;
+	if (id->nsfeat & (1 << 4)) {
+		/* NPWG = Namespace Preferred Write Granularity */
+		phys_bs *= 1 + le16_to_cpu(id->npwg);
+		/* NOWS = Namespace Optimal Write Size */
+		io_opt *= 1 + le16_to_cpu(id->nows);
+	}
+
 	blk_queue_logical_block_size(disk->queue, bs);
-	blk_queue_physical_block_size(disk->queue, bs);
-	blk_queue_io_min(disk->queue, bs);
+	/*
+	 * Linux filesystems assume writing a single physical block is
+	 * an atomic operation. Hence limit the physical block size to the
+	 * value of the Atomic Write Unit Power Fail parameter.
+	 */
+	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
+	blk_queue_io_min(disk->queue, phys_bs);
+	blk_queue_io_opt(disk->queue, io_opt);
 
 	if (ns->ms && !ns->ext &&
 	    (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
@@ -2386,8 +2416,8 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 	lockdep_assert_held(&nvme_subsystems_lock);
 
 	list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
-		if (ctrl->state == NVME_CTRL_DELETING ||
-		    ctrl->state == NVME_CTRL_DEAD)
+		if (tmp->state == NVME_CTRL_DELETING ||
+		    tmp->state == NVME_CTRL_DEAD)
 			continue;
 
 		if (tmp->cntlid == ctrl->cntlid) {
@@ -2433,6 +2463,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
+	subsys->awupf = le16_to_cpu(id->awupf);
 #ifdef CONFIG_NVME_MULTIPATH
 	subsys->iopolicy = NVME_IOPOLICY_NUMA;
 #endif
@@ -3274,6 +3305,10 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		goto out_free_ns;
 	}
 
+	if (ctrl->opts && ctrl->opts->data_digest)
+		ns->queue->backing_dev_info->capabilities
+			|= BDI_CAP_STABLE_WRITES;
+
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
 	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
 		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);