Merge branch 'for-4.16/block' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block IO related changes for the
  4.16 kernel. Nothing major in this pull request, but a good amount of
  improvements and fixes all over the map. This contains:

   - BFQ improvements, fixes, and cleanups from Angelo, Chiara, and
     Paolo.

   - Support for SMR zones for deadline and mq-deadline from Damien and
     Christoph.

   - Set of fixes for bcache by way of Michael Lyle, including fixes
     from himself, Kent, Rui, Tang, and Coly.

   - Series from Matias for lightnvm with fixes from Hans Holmberg,
     Javier, and Matias. Mostly centered around pblk, and the removing
     rrpc 1.2 in preparation for supporting 2.0.

   - A couple of NVMe pull requests from Christoph. Nothing major in
     here, just fixes and cleanups, and support for command tracing from
     Johannes.

   - Support for blk-throttle for tracking reads and writes separately.
     From Joseph Qi. A few cleanups/fixes also for blk-throttle from
     Weiping.

   - Series from Mike Snitzer that enables dm to register its queue more
     logically, something that's alwways been problematic on dm since
     it's a stacked device.

   - Series from Ming cleaning up some of the bio accessor use, in
     preparation for supporting multipage bvecs.

   - Various fixes from Ming closing up holes around queue mapping and
     quiescing.

   - BSD partition fix from Richard Narron, fixing a problem where we
     can't mount newer (10/11) FreeBSD partitions.

   - Series from Tejun reworking blk-mq timeout handling. The previous
     scheme relied on atomic bits, but it had races where we would think
     a request had timed out if it to reused at the wrong time.

   - null_blk now supports faking timeouts, to enable us to better
     exercise and test that functionality separately. From me.

   - Kill the separate atomic poll bit in the request struct. After
     this, we don't use the atomic bits on blk-mq anymore at all. From
     me.

   - sgl_alloc/free helpers from Bart.

   - Heavily contended tag case scalability improvement from me.

   - Various little fixes and cleanups from Arnd, Bart, Corentin,
     Douglas, Eryu, Goldwyn, and myself"

* 'for-4.16/block' of git://git.kernel.dk/linux-block: (186 commits)
  block: remove smart1,2.h
  nvme: add tracepoint for nvme_complete_rq
  nvme: add tracepoint for nvme_setup_cmd
  nvme-pci: introduce RECONNECTING state to mark initializing procedure
  nvme-rdma: remove redundant boolean for inline_data
  nvme: don't free uuid pointer before printing it
  nvme-pci: Suspend queues after deleting them
  bsg: use pr_debug instead of hand crafted macros
  blk-mq-debugfs: don't allow write on attributes with seq_operations set
  nvme-pci: Fix queue double allocations
  block: Set BIO_TRACE_COMPLETION on new bio during split
  blk-throttle: use queue_is_rq_based
  block: Remove kblockd_schedule_delayed_work{,_on}()
  blk-mq: Avoid that blk_mq_delay_run_hw_queue() introduces unintended delays
  blk-mq: Rename blk_mq_request_direct_issue() into blk_mq_request_issue_directly()
  lib/scatterlist: Fix chaining support in sgl_alloc_order()
  blk-throttle: track read and write request individually
  block: add bdev_read_only() checks to common helpers
  block: fail op_is_write() requests to read-only partitions
  blk-throttle: export io_serviced_recursive, io_service_bytes_recursive
  ...

1 files changed, 37 insertions, 17 deletions

diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
index dacc71922260..0d457b162f23 100644
--- a/drivers/lightnvm/pblk-rl.c
+++ b/drivers/lightnvm/pblk-rl.c
@@ -89,17 +89,15 @@ unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl)
 	return atomic_read(&rl->free_blocks);
 }
 
-/*
- * We check for (i) the number of free blocks in the current LUN and (ii) the
- * total number of free blocks in the pblk instance. This is to even out the
- * number of free blocks on each LUN when GC kicks in.
- *
- * Only the total number of free blocks is used to configure the rate limiter.
- */
-void pblk_rl_update_rates(struct pblk_rl *rl)
+unsigned long pblk_rl_nr_user_free_blks(struct pblk_rl *rl)
+{
+	return atomic_read(&rl->free_user_blocks);
+}
+
+static void __pblk_rl_update_rates(struct pblk_rl *rl,
+				   unsigned long free_blocks)
 {
 	struct pblk *pblk = container_of(rl, struct pblk, rl);
-	unsigned long free_blocks = pblk_rl_nr_free_blks(rl);
 	int max = rl->rb_budget;
 
 	if (free_blocks >= rl->high) {
@@ -132,20 +130,37 @@ void pblk_rl_update_rates(struct pblk_rl *rl)
 		pblk_gc_should_stop(pblk);
 }
 
+void pblk_rl_update_rates(struct pblk_rl *rl)
+{
+	__pblk_rl_update_rates(rl, pblk_rl_nr_user_free_blks(rl));
+}
+
 void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line)
 {
 	int blk_in_line = atomic_read(&line->blk_in_line);
+	int free_blocks;
 
 	atomic_add(blk_in_line, &rl->free_blocks);
-	pblk_rl_update_rates(rl);
+	free_blocks = atomic_add_return(blk_in_line, &rl->free_user_blocks);
+
+	__pblk_rl_update_rates(rl, free_blocks);
 }
 
-void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line)
+void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line,
+			    bool used)
 {
 	int blk_in_line = atomic_read(&line->blk_in_line);
+	int free_blocks;
 
 	atomic_sub(blk_in_line, &rl->free_blocks);
-	pblk_rl_update_rates(rl);
+
+	if (used)
+		free_blocks = atomic_sub_return(blk_in_line,
+							&rl->free_user_blocks);
+	else
+		free_blocks = atomic_read(&rl->free_user_blocks);
+
+	__pblk_rl_update_rates(rl, free_blocks);
 }
 
 int pblk_rl_high_thrs(struct pblk_rl *rl)
@@ -174,16 +189,21 @@ void pblk_rl_free(struct pblk_rl *rl)
 void pblk_rl_init(struct pblk_rl *rl, int budget)
 {
 	struct pblk *pblk = container_of(rl, struct pblk, rl);
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line_meta *lm = &pblk->lm;
 	int min_blocks = lm->blk_per_line * PBLK_GC_RSV_LINE;
+	int sec_meta, blk_meta;
+
 	unsigned int rb_windows;
 
-	rl->high = rl->total_blocks / PBLK_USER_HIGH_THRS;
-	rl->high_pw = get_count_order(rl->high);
+	/* Consider sectors used for metadata */
+	sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines;
+	blk_meta = DIV_ROUND_UP(sec_meta, geo->sec_per_chk);
 
-	rl->low = rl->total_blocks / PBLK_USER_LOW_THRS;
-	if (rl->low < min_blocks)
-		rl->low = min_blocks;
+	rl->high = pblk->op_blks - blk_meta - lm->blk_per_line;
+	rl->high_pw = get_count_order(rl->high);
 
 	rl->rsv_blocks = min_blocks;