Merge branch 'for-4.8/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "This branch also contains core changes.  I've come to the conclusion
  that from 4.9 and forward, I'll be doing just a single branch.  We
  often have dependencies between core and drivers, and it's hard to
  always split them up appropriately without pulling core into drivers
  when that happens.

  That said, this contains:

   - separate secure erase type for the core block layer, from
     Christoph.

   - set of discard fixes, from Christoph.

   - bio shrinking fixes from Christoph, as a followup up to the
     op/flags change in the core branch.

   - map and append request fixes from Christoph.

   - NVMeF (NVMe over Fabrics) code from Christoph.  This is pretty
     exciting!

   - nvme-loop fixes from Arnd.

   - removal of ->driverfs_dev from Dan, after providing a
     device_add_disk() helper.

   - bcache fixes from Bhaktipriya and Yijing.

   - cdrom subchannel read fix from Vchannaiah.

   - set of lightnvm updates from Wenwei, Matias, Johannes, and Javier.

   - set of drbd updates and fixes from Fabian, Lars, and Philipp.

   - mg_disk error path fix from Bart.

   - user notification for failed device add for loop, from Minfei.

   - NVMe in general:
        + NVMe delay quirk from Guilherme.
        + SR-IOV support and command retry limits from Keith.
        + fix for memory-less NUMA node from Masayoshi.
        + use UINT_MAX for discard sectors, from Minfei.
        + cancel IO fixes from Ming.
        + don't allocate unused major, from Neil.
        + error code fixup from Dan.
        + use constants for PSDT/FUSE from James.
        + variable init fix from Jay.
        + fabrics fixes from Ming, Sagi, and Wei.
        + various fixes"

* 'for-4.8/drivers' of git://git.kernel.dk/linux-block: (115 commits)
  nvme/pci: Provide SR-IOV support
  nvme: initialize variable before logical OR'ing it
  block: unexport various bio mapping helpers
  scsi/osd: open code blk_make_request
  target: stop using blk_make_request
  block: simplify and export blk_rq_append_bio
  block: ensure bios return from blk_get_request are properly initialized
  virtio_blk: use blk_rq_map_kern
  memstick: don't allow REQ_TYPE_BLOCK_PC requests
  block: shrink bio size again
  block: simplify and cleanup bvec pool handling
  block: get rid of bio_rw and READA
  block: don't ignore -EOPNOTSUPP blkdev_issue_write_same
  block: introduce BLKDEV_DISCARD_ZERO to fix zeroout
  NVMe: don't allocate unused nvme_major
  nvme: avoid crashes when node 0 is memoryless node.
  nvme: Limit command retries
  loop: Make user notify for adding loop device failed
  nvme-loop: fix nvme-loop Kconfig dependencies
  nvmet: fix return value check in nvmet_subsys_alloc()
  ...

1 files changed, 75 insertions, 74 deletions

diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index de86d72dcdf0..37fcaadbf80c 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -48,7 +48,7 @@ static void rrpc_page_invalidate(struct rrpc *rrpc, struct rrpc_addr *a)
 }
 
 static void rrpc_invalidate_range(struct rrpc *rrpc, sector_t slba,
-								unsigned len)
+							unsigned int len)
 {
 	sector_t i;
 
@@ -96,10 +96,13 @@ static void rrpc_discard(struct rrpc *rrpc, struct bio *bio)
 	sector_t len = bio->bi_iter.bi_size / RRPC_EXPOSED_PAGE_SIZE;
 	struct nvm_rq *rqd;
 
-	do {
+	while (1) {
 		rqd = rrpc_inflight_laddr_acquire(rrpc, slba, len);
+		if (rqd)
+			break;
+
 		schedule();
-	} while (!rqd);
+	}
 
 	if (IS_ERR(rqd)) {
 		pr_err("rrpc: unable to acquire inflight IO\n");
@@ -172,39 +175,32 @@ static struct ppa_addr rrpc_ppa_to_gaddr(struct nvm_dev *dev, u64 addr)
 }
 
 /* requires lun->lock taken */
-static void rrpc_set_lun_cur(struct rrpc_lun *rlun, struct rrpc_block *rblk)
+static void rrpc_set_lun_cur(struct rrpc_lun *rlun, struct rrpc_block *new_rblk,
+						struct rrpc_block **cur_rblk)
 {
 	struct rrpc *rrpc = rlun->rrpc;
 
-	BUG_ON(!rblk);
-
-	if (rlun->cur) {
-		spin_lock(&rlun->cur->lock);
-		WARN_ON(!block_is_full(rrpc, rlun->cur));
-		spin_unlock(&rlun->cur->lock);
+	if (*cur_rblk) {
+		spin_lock(&(*cur_rblk)->lock);
+		WARN_ON(!block_is_full(rrpc, *cur_rblk));
+		spin_unlock(&(*cur_rblk)->lock);
 	}
-	rlun->cur = rblk;
+	*cur_rblk = new_rblk;
 }
 
 static struct rrpc_block *rrpc_get_blk(struct rrpc *rrpc, struct rrpc_lun *rlun,
 							unsigned long flags)
 {
-	struct nvm_lun *lun = rlun->parent;
 	struct nvm_block *blk;
 	struct rrpc_block *rblk;
 
-	spin_lock(&lun->lock);
-	blk = nvm_get_blk_unlocked(rrpc->dev, rlun->parent, flags);
+	blk = nvm_get_blk(rrpc->dev, rlun->parent, flags);
 	if (!blk) {
 		pr_err("nvm: rrpc: cannot get new block from media manager\n");
-		spin_unlock(&lun->lock);
 		return NULL;
 	}
 
 	rblk = rrpc_get_rblk(rlun, blk->id);
-	list_add_tail(&rblk->list, &rlun->open_list);
-	spin_unlock(&lun->lock);
-
 	blk->priv = rblk;
 	bitmap_zero(rblk->invalid_pages, rrpc->dev->sec_per_blk);
 	rblk->next_page = 0;
@@ -216,13 +212,7 @@ static struct rrpc_block *rrpc_get_blk(struct rrpc *rrpc, struct rrpc_lun *rlun,
 
 static void rrpc_put_blk(struct rrpc *rrpc, struct rrpc_block *rblk)
 {
-	struct rrpc_lun *rlun = rblk->rlun;
-	struct nvm_lun *lun = rlun->parent;
-
-	spin_lock(&lun->lock);
-	nvm_put_blk_unlocked(rrpc->dev, rblk->parent);
-	list_del(&rblk->list);
-	spin_unlock(&lun->lock);
+	nvm_put_blk(rrpc->dev, rblk->parent);
 }
 
 static void rrpc_put_blks(struct rrpc *rrpc)
@@ -508,21 +498,11 @@ static void rrpc_gc_queue(struct work_struct *work)
 	struct rrpc *rrpc = gcb->rrpc;
 	struct rrpc_block *rblk = gcb->rblk;
 	struct rrpc_lun *rlun = rblk->rlun;
-	struct nvm_lun *lun = rblk->parent->lun;
-	struct nvm_block *blk = rblk->parent;
 
 	spin_lock(&rlun->lock);
 	list_add_tail(&rblk->prio, &rlun->prio_list);
 	spin_unlock(&rlun->lock);
 
-	spin_lock(&lun->lock);
-	lun->nr_open_blocks--;
-	lun->nr_closed_blocks++;
-	blk->state &= ~NVM_BLK_ST_OPEN;
-	blk->state |= NVM_BLK_ST_CLOSED;
-	list_move_tail(&rblk->list, &rlun->closed_list);
-	spin_unlock(&lun->lock);
-
 	mempool_free(gcb, rrpc->gcb_pool);
 	pr_debug("nvm: block '%lu' is full, allow GC (sched)\n",
 							rblk->parent->id);
@@ -596,21 +576,20 @@ out:
 	return addr;
 }
 
-/* Simple round-robin Logical to physical address translation.
- *
- * Retrieve the mapping using the active append point. Then update the ap for
- * the next write to the disk.
+/* Map logical address to a physical page. The mapping implements a round robin
+ * approach and allocates a page from the next lun available.
  *
- * Returns rrpc_addr with the physical address and block. Remember to return to
- * rrpc->addr_cache when request is finished.
+ * Returns rrpc_addr with the physical address and block. Returns NULL if no
+ * blocks in the next rlun are available.
  */
 static struct rrpc_addr *rrpc_map_page(struct rrpc *rrpc, sector_t laddr,
 								int is_gc)
 {
 	struct rrpc_lun *rlun;
-	struct rrpc_block *rblk;
+	struct rrpc_block *rblk, **cur_rblk;
 	struct nvm_lun *lun;
 	u64 paddr;
+	int gc_force = 0;
 
 	rlun = rrpc_get_lun_rr(rrpc, is_gc);
 	lun = rlun->parent;
@@ -618,41 +597,65 @@ static struct rrpc_addr *rrpc_map_page(struct rrpc *rrpc, sector_t laddr,
 	if (!is_gc && lun->nr_free_blocks < rrpc->nr_luns * 4)
 		return NULL;
 
-	spin_lock(&rlun->lock);
+	/*
+	 * page allocation steps:
+	 * 1. Try to allocate new page from current rblk
+	 * 2a. If succeed, proceed to map it in and return
+	 * 2b. If fail, first try to allocate a new block from media manger,
+	 *     and then retry step 1. Retry until the normal block pool is
+	 *     exhausted.
+	 * 3. If exhausted, and garbage collector is requesting the block,
+	 *    go to the reserved block and retry step 1.
+	 *    In the case that this fails as well, or it is not GC
+	 *    requesting, report not able to retrieve a block and let the
+	 *    caller handle further processing.
+	 */
 
+	spin_lock(&rlun->lock);
+	cur_rblk = &rlun->cur;
 	rblk = rlun->cur;
 retry:
 	paddr = rrpc_alloc_addr(rrpc, rblk);
 
-	if (paddr == ADDR_EMPTY) {
-		rblk = rrpc_get_blk(rrpc, rlun, 0);
-		if (rblk) {
-			rrpc_set_lun_cur(rlun, rblk);
-			goto retry;
-		}
+	if (paddr != ADDR_EMPTY)
+		goto done;
 
-		if (is_gc) {
-			/* retry from emergency gc block */
-			paddr = rrpc_alloc_addr(rrpc, rlun->gc_cur);
-			if (paddr == ADDR_EMPTY) {
-				rblk = rrpc_get_blk(rrpc, rlun, 1);
-				if (!rblk) {
-					pr_err("rrpc: no more blocks");
-					goto err;
-				}
-
-				rlun->gc_cur = rblk;
-				paddr = rrpc_alloc_addr(rrpc, rlun->gc_cur);
-			}
-			rblk = rlun->gc_cur;
-		}
+	if (!list_empty(&rlun->wblk_list)) {
+new_blk:
+		rblk = list_first_entry(&rlun->wblk_list, struct rrpc_block,
+									prio);
+		rrpc_set_lun_cur(rlun, rblk, cur_rblk);
+		list_del(&rblk->prio);
+		goto retry;
+	}
+	spin_unlock(&rlun->lock);
+
+	rblk = rrpc_get_blk(rrpc, rlun, gc_force);
+	if (rblk) {
+		spin_lock(&rlun->lock);
+		list_add_tail(&rblk->prio, &rlun->wblk_list);
+		/*
+		 * another thread might already have added a new block,
+		 * Therefore, make sure that one is used, instead of the
+		 * one just added.
+		 */
+		goto new_blk;
 	}
 
+	if (unlikely(is_gc) && !gc_force) {
+		/* retry from emergency gc block */
+		cur_rblk = &rlun->gc_cur;
+		rblk = rlun->gc_cur;
+		gc_force = 1;
+		spin_lock(&rlun->lock);
+		goto retry;
+	}
+
+	pr_err("rrpc: failed to allocate new block\n");
+	return NULL;
+done:
 	spin_unlock(&rlun->lock);
 	return rrpc_update_map(rrpc, laddr, rblk, paddr);
-err:
-	spin_unlock(&rlun->lock);
-	return NULL;
 }
 
 static void rrpc_run_gc(struct rrpc *rrpc, struct rrpc_block *rblk)
@@ -850,14 +853,14 @@ static int rrpc_setup_rq(struct rrpc *rrpc, struct bio *bio,
 			return NVM_IO_ERR;
 		}
 
-		if (bio_rw(bio) == WRITE)
+		if (bio_op(bio) == REQ_OP_WRITE)
 			return rrpc_write_ppalist_rq(rrpc, bio, rqd, flags,
 									npages);
 
 		return rrpc_read_ppalist_rq(rrpc, bio, rqd, flags, npages);
 	}
 
-	if (bio_rw(bio) == WRITE)
+	if (bio_op(bio) == REQ_OP_WRITE)
 		return rrpc_write_rq(rrpc, bio, rqd, flags);
 
 	return rrpc_read_rq(rrpc, bio, rqd, flags);
@@ -1196,8 +1199,7 @@ static int rrpc_luns_init(struct rrpc *rrpc, int lun_begin, int lun_end)
 
 		rlun->rrpc = rrpc;
 		INIT_LIST_HEAD(&rlun->prio_list);
-		INIT_LIST_HEAD(&rlun->open_list);
-		INIT_LIST_HEAD(&rlun->closed_list);
+		INIT_LIST_HEAD(&rlun->wblk_list);
 
 		INIT_WORK(&rlun->ws_gc, rrpc_lun_gc);
 		spin_lock_init(&rlun->lock);
@@ -1338,14 +1340,13 @@ static int rrpc_luns_configure(struct rrpc *rrpc)
 		rblk = rrpc_get_blk(rrpc, rlun, 0);
 		if (!rblk)
 			goto err;
-
-		rrpc_set_lun_cur(rlun, rblk);
+		rrpc_set_lun_cur(rlun, rblk, &rlun->cur);
 
 		/* Emergency gc block */
 		rblk = rrpc_get_blk(rrpc, rlun, 1);
 		if (!rblk)
 			goto err;
-		rlun->gc_cur = rblk;
+		rrpc_set_lun_cur(rlun, rblk, &rlun->gc_cur);
 	}
 
 	return 0;