Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

1 files changed, 38 insertions, 5 deletions

diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 02bb2e98f8a9..85e38ed62f85 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -104,7 +104,6 @@ enum {
 	PBLK_RL_LOW = 4
 };
 
-#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * NVM_MAX_VLBA)
 #define pblk_dma_ppa_size (sizeof(u64) * NVM_MAX_VLBA)
 
 /* write buffer completion context */
@@ -132,6 +131,8 @@ struct pblk_pr_ctx {
 	unsigned int bio_init_idx;
 	void *ppa_ptr;
 	dma_addr_t dma_ppa_list;
+	__le64 lba_list_mem[NVM_MAX_VLBA];
+	__le64 lba_list_media[NVM_MAX_VLBA];
 };
 
 /* Pad context */
@@ -631,7 +632,9 @@ struct pblk {
 	int state;			/* pblk line state */
 
 	int min_write_pgs; /* Minimum amount of pages required by controller */
+	int min_write_pgs_data; /* Minimum amount of payload pages */
 	int max_write_pgs; /* Maximum amount of pages supported by controller */
+	int oob_meta_size; /* Size of OOB sector metadata */
 
 	sector_t capacity; /* Device capacity when bad blocks are subtracted */
 
@@ -836,7 +839,7 @@ void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
 u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
 u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
 int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
-		   unsigned long secs_to_flush);
+		   unsigned long secs_to_flush, bool skip_meta);
 void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa,
 		  unsigned long *lun_bitmap);
 void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa);
@@ -860,6 +863,8 @@ void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
 			  u64 *lba_list, int nr_secs);
 void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
 			 sector_t blba, int nr_secs);
+void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd);
+void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd);
 
 /*
  * pblk user I/O write path
@@ -871,10 +876,10 @@ int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq);
 /*
  * pblk map
  */
-void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
+int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
 		       unsigned int sentry, unsigned long *lun_bitmap,
 		       unsigned int valid_secs, struct ppa_addr *erase_ppa);
-void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
+int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
 		 unsigned long *lun_bitmap, unsigned int valid_secs,
 		 unsigned int off);
 
@@ -905,7 +910,6 @@ int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta);
 #define PBLK_GC_MAX_READERS 8	/* Max number of outstanding GC reader jobs */
 #define PBLK_GC_RQ_QD 128	/* Queue depth for inflight GC requests */
 #define PBLK_GC_L_QD 4		/* Queue depth for inflight GC lines */
-#define PBLK_GC_RSV_LINE 1	/* Reserved lines for GC */
 
 int pblk_gc_init(struct pblk *pblk);
 void pblk_gc_exit(struct pblk *pblk, bool graceful);
@@ -1370,4 +1374,33 @@ static inline char *pblk_disk_name(struct pblk *pblk)
 
 	return disk->disk_name;
 }
+
+static inline unsigned int pblk_get_min_chks(struct pblk *pblk)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	/* In a worst-case scenario every line will have OP invalid sectors.
+	 * We will then need a minimum of 1/OP lines to free up a single line
+	 */
+
+	return DIV_ROUND_UP(100, pblk->op) * lm->blk_per_line;
+}
+
+static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk,
+							 void *meta, int index)
+{
+	return meta +
+	       max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size)
+	       * index;
+}
+
+static inline int pblk_dma_meta_size(struct pblk *pblk)
+{
+	return max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size)
+	       * NVM_MAX_VLBA;
+}
+
+static inline int pblk_is_oob_meta_supported(struct pblk *pblk)
+{
+	return pblk->oob_meta_size >= sizeof(struct pblk_sec_meta);
+}
 #endif /* PBLK_H_ */