Merge branch 'for-4.2/core' of git://git.kernel.dk/linux-block

Pull core block IO update from Jens Axboe:
 "Nothing really major in here, mostly a collection of smaller
  optimizations and cleanups, mixed with various fixes.  In more detail,
  this contains:

   - Addition of policy specific data to blkcg for block cgroups.  From
     Arianna Avanzini.

   - Various cleanups around command types from Christoph.

   - Cleanup of the suspend block I/O path from Christoph.

   - Plugging updates from Shaohua and Jeff Moyer, for blk-mq.

   - Eliminating atomic inc/dec of both remaining IO count and reference
     count in a bio.  From me.

   - Fixes for SG gap and chunk size support for data-less (discards)
     IO, so we can merge these better.  From me.

   - Small restructuring of blk-mq shared tag support, freeing drivers
     from iterating hardware queues.  From Keith Busch.

   - A few cfq-iosched tweaks, from Tahsin Erdogan and me.  Makes the
     IOPS mode the default for non-rotational storage"

* 'for-4.2/core' of git://git.kernel.dk/linux-block: (35 commits)
  cfq-iosched: fix other locations where blkcg_to_cfqgd() can return NULL
  cfq-iosched: fix sysfs oops when attempting to read unconfigured weights
  cfq-iosched: move group scheduling functions under ifdef
  cfq-iosched: fix the setting of IOPS mode on SSDs
  blktrace: Add blktrace.c to BLOCK LAYER in MAINTAINERS file
  block, cgroup: implement policy-specific per-blkcg data
  block: Make CFQ default to IOPS mode on SSDs
  block: add blk_set_queue_dying() to blkdev.h
  blk-mq: Shared tag enhancements
  block: don't honor chunk sizes for data-less IO
  block: only honor SG gap prevention for merges that contain data
  block: fix returnvar.cocci warnings
  block, dm: don't copy bios for request clones
  block: remove management of bi_remaining when restoring original bi_end_io
  block: replace trylock with mutex_lock in blkdev_reread_part()
  block: export blkdev_reread_part() and __blkdev_reread_part()
  suspend: simplify block I/O handling
  block: collapse bio bit space
  block: remove unused BIO_RW_BLOCK and BIO_EOF flags
  block: remove BIO_EOPNOTSUPP
  ...

8 files changed, 71 insertions, 53 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index da3a127c9958..f0291cf64cc5 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -290,7 +290,21 @@ static inline unsigned bio_segments(struct bio *bio)
  * returns. and then bio would be freed memory when if (bio->bi_flags ...)
  * runs
  */
-#define bio_get(bio)    atomic_inc(&(bio)->bi_cnt)
+static inline void bio_get(struct bio *bio)
+{
+        bio->bi_flags |= (1 << BIO_REFFED);
+        smp_mb__before_atomic();
+        atomic_inc(&bio->__bi_cnt);
+}
+
+static inline void bio_cnt_set(struct bio *bio, unsigned int count)
+{
+        if (count != 1) {
+                bio->bi_flags |= (1 << BIO_REFFED);
+                smp_mb__before_atomic();
+        }
+        atomic_set(&bio->__bi_cnt, count);
+}
 
 enum bip_flags {
         BIP_BLOCK_INTEGRITY     = 1 << 0, /* block layer owns integrity data */
@@ -413,7 +427,6 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
 }
 
 extern void bio_endio(struct bio *, int);
-extern void bio_endio_nodec(struct bio *, int);
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2056a99b92f8..37d1602c4f7a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -96,6 +96,7 @@ typedef void (exit_request_fn)(void *, struct request *, unsigned int,
 
 typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
                 bool);
+typedef void (busy_tag_iter_fn)(struct request *, void *, bool);
 
 struct blk_mq_ops {
         /*
@@ -182,6 +183,7 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
                 gfp_t gfp, bool reserved);
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
+struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags);
 
 enum {
         BLK_MQ_UNIQUE_TAG_BITS = 16,
@@ -224,6 +226,8 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
                 void *priv);
+void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
+                void *priv);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index b7299febc4b4..6ab9d12d1f17 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -65,7 +65,7 @@ struct bio {
         unsigned int            bi_seg_front_size;
         unsigned int            bi_seg_back_size;
 
-        atomic_t                bi_remaining;
+        atomic_t                __bi_remaining;
 
         bio_end_io_t            *bi_end_io;
 
@@ -92,7 +92,7 @@ struct bio {
 
         unsigned short          bi_max_vecs;    /* max bvl_vecs we can hold */
 
-        atomic_t                bi_cnt;         /* pin count */
+        atomic_t                __bi_cnt;       /* pin count */
 
         struct bio_vec          *bi_io_vec;     /* the actual vec list */
 
@@ -112,16 +112,15 @@ struct bio {
  * bio flags
  */
 #define BIO_UPTODATE    0       /* ok after I/O completion */
-#define BIO_RW_BLOCK    1       /* RW_AHEAD set, and read/write would block */
-#define BIO_EOF         2       /* out-out-bounds error */
-#define BIO_SEG_VALID   3       /* bi_phys_segments valid */
-#define BIO_CLONED      4       /* doesn't own data */
-#define BIO_BOUNCED     5       /* bio is a bounce bio */
-#define BIO_USER_MAPPED 6       /* contains user pages */
-#define BIO_EOPNOTSUPP  7       /* not supported */
-#define BIO_NULL_MAPPED 8       /* contains invalid user pages */
-#define BIO_QUIET       9       /* Make BIO Quiet */
-#define BIO_SNAP_STABLE 10      /* bio data must be snapshotted during write */
+#define BIO_SEG_VALID   1       /* bi_phys_segments valid */
+#define BIO_CLONED      2       /* doesn't own data */
+#define BIO_BOUNCED     3       /* bio is a bounce bio */
+#define BIO_USER_MAPPED 4       /* contains user pages */
+#define BIO_NULL_MAPPED 5       /* contains invalid user pages */
+#define BIO_QUIET       6       /* Make BIO Quiet */
+#define BIO_SNAP_STABLE 7       /* bio data must be snapshotted during write */
+#define BIO_CHAIN       8       /* chained bio, ->bi_remaining in effect */
+#define BIO_REFFED      9       /* bio has elevated ->bi_cnt */
 
 /*
  * Flags starting here get preserved by bio_reset() - this includes
@@ -193,6 +192,7 @@ enum rq_flag_bits {
         __REQ_HASHED,           /* on IO scheduler merge hash */
         __REQ_MQ_INFLIGHT,      /* track inflight for MQ */
         __REQ_NO_TIMEOUT,       /* requests may never expire */
+        __REQ_CLONE,            /* cloned bios */
         __REQ_NR_BITS,          /* stops here */
 };
 
@@ -247,5 +247,6 @@ enum rq_flag_bits {
 #define REQ_HASHED              (1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT         (1ULL << __REQ_MQ_INFLIGHT)
 #define REQ_NO_TIMEOUT          (1ULL << __REQ_NO_TIMEOUT)
+#define REQ_CLONE               (1ULL << __REQ_CLONE)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5d93a6645e88..a6ae5f9bee49 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -30,7 +30,6 @@ struct scsi_ioctl_command;
 
 struct request_queue;
 struct elevator_queue;
-struct request_pm_state;
 struct blk_trace;
 struct request;
 struct sg_io_hdr;
@@ -75,18 +74,7 @@ struct request_list {
 enum rq_cmd_type_bits {
         REQ_TYPE_FS             = 1,    /* fs request */
         REQ_TYPE_BLOCK_PC,              /* scsi command */
-        REQ_TYPE_SENSE,                 /* sense request */
-        REQ_TYPE_PM_SUSPEND,            /* suspend request */
-        REQ_TYPE_PM_RESUME,             /* resume request */
-        REQ_TYPE_PM_SHUTDOWN,           /* shutdown request */
-        REQ_TYPE_SPECIAL,               /* driver defined type */
-        /*
-         * for ATA/ATAPI devices. this really doesn't belong here, ide should
-         * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver
-         * private REQ_LB opcodes to differentiate what type of request this is
-         */
-        REQ_TYPE_ATA_TASKFILE,
-        REQ_TYPE_ATA_PC,
+        REQ_TYPE_DRV_PRIV,              /* driver defined types from here */
 };
 
 #define BLK_MAX_CDB     16
@@ -108,7 +96,7 @@ struct request {
         struct blk_mq_ctx *mq_ctx;
 
         u64 cmd_flags;
-        enum rq_cmd_type_bits cmd_type;
+        unsigned cmd_type;
         unsigned long atomic_flags;
 
         int cpu;
@@ -216,19 +204,6 @@ static inline unsigned short req_get_ioprio(struct request *req)
         return req->ioprio;
 }
 
-/*
- * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
- * requests. Some step values could eventually be made generic.
- */
-struct request_pm_state
-{
-        /* PM state machine step value, currently driver specific */
-        int     pm_step;
-        /* requested PM state value (S1, S2, S3, S4, ...) */
-        u32     pm_state;
-        void*   data;           /* for driver use */
-};
-
 #include <linux/elevator.h>
 
 struct blk_queue_ctx;
@@ -469,7 +444,7 @@ struct request_queue {
         struct mutex            sysfs_lock;
 
         int                     bypass_depth;
-        int                     mq_freeze_depth;
+        atomic_t                mq_freeze_depth;
 
 #if defined(CONFIG_BLK_DEV_BSG)
         bsg_job_fn              *bsg_job_fn;
@@ -610,10 +585,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
         (((rq)->cmd_flags & REQ_STARTED) && \
          ((rq)->cmd_type == REQ_TYPE_FS))
 
-#define blk_pm_request(rq)      \
-        ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \
-         (rq)->cmd_type == REQ_TYPE_PM_RESUME)
-
 #define blk_rq_cpu_valid(rq)    ((rq)->cpu != -1)
 #define blk_bidi_rq(rq)         ((rq)->next_rq != NULL)
 /* rq->queuelist of dequeued request must be list_empty() */
@@ -804,11 +775,7 @@ extern void blk_add_request_payload(struct request *rq, struct page *page,
                 unsigned int len);
 extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
-extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
-                             struct bio_set *bs, gfp_t gfp_mask,
-                             int (*bio_ctr)(struct bio *, struct bio *, void *),
-                             void *data);
-extern void blk_rq_unprep_clone(struct request *rq);
+extern void blk_rq_prep_clone(struct request *rq, struct request *rq_src);
 extern int blk_insert_cloned_request(struct request_queue *q,
                                      struct request *rq);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
@@ -845,6 +812,7 @@ extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
 extern void __blk_run_queue(struct request_queue *q);
+extern void __blk_run_queue_uncond(struct request_queue *q);
 extern void blk_run_queue(struct request_queue *);
 extern void blk_run_queue_async(struct request_queue *q);
 extern int blk_rq_map_user(struct request_queue *, struct request *,
@@ -933,7 +901,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
         if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
                 return q->limits.max_hw_sectors;
 
-        if (!q->limits.chunk_sectors)
+        if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
                 return blk_queue_get_max_sectors(q, rq->cmd_flags);
 
         return min(blk_max_size_offset(q, blk_rq_pos(rq)),
@@ -1054,6 +1022,7 @@ bool __must_check blk_get_queue(struct request_queue *);
 struct request_queue *blk_alloc_queue(gfp_t);
 struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
+extern void blk_set_queue_dying(struct request_queue *);
 
 /*
  * block layer runtime pm functions
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 45a91474487d..638b324f0291 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -39,6 +39,7 @@ typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct reques
 typedef int (elevator_init_fn) (struct request_queue *,
                                 struct elevator_type *e);
 typedef void (elevator_exit_fn) (struct elevator_queue *);
+typedef void (elevator_registered_fn) (struct request_queue *);
 
 struct elevator_ops
 {
@@ -68,6 +69,7 @@ struct elevator_ops
 
         elevator_init_fn *elevator_init_fn;
         elevator_exit_fn *elevator_exit_fn;
+        elevator_registered_fn *elevator_registered_fn;
 };
 
 #define ELV_NAME_MAX    (16)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b577e801b4af..5db7b1379d17 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2280,6 +2280,9 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
                                               void *holder);
 extern void blkdev_put(struct block_device *bdev, fmode_t mode);
+extern int __blkdev_reread_part(struct block_device *bdev);
+extern int blkdev_reread_part(struct block_device *bdev);
+
 #ifdef CONFIG_SYSFS
 extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
 extern void bd_unlink_disk_holder(struct block_device *bdev,
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 93b5ca754b5b..a633898f36ac 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -39,6 +39,19 @@
 
 struct device;
 
+/* IDE-specific values for req->cmd_type */
+enum ata_cmd_type_bits {
+        REQ_TYPE_ATA_TASKFILE = REQ_TYPE_DRV_PRIV + 1,
+        REQ_TYPE_ATA_PC,
+        REQ_TYPE_ATA_SENSE,     /* sense request */
+        REQ_TYPE_ATA_PM_SUSPEND,/* suspend request */
+        REQ_TYPE_ATA_PM_RESUME, /* resume request */
+};
+
+#define ata_pm_request(rq)      \
+        ((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \
+         (rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME)
+
 /* Error codes returned in rq->errors to the higher part of the driver. */
 enum {
         IDE_DRV_ERROR_GENERAL   = 101,
@@ -1314,6 +1327,19 @@ struct ide_port_info {
         u8                      udma_mask;
 };
 
+/*
+ * State information carried for REQ_TYPE_ATA_PM_SUSPEND and REQ_TYPE_ATA_PM_RESUME
+ * requests.
+ */
+struct ide_pm_state {
+        /* PM state machine step value, currently driver specific */
+        int     pm_step;
+        /* requested PM state value (S1, S2, S3, S4, ...) */
+        u32     pm_state;
+        void*   data;           /* for driver use */
+};
+
+
 int ide_pci_init_one(struct pci_dev *, const struct ide_port_info *, void *);
 int ide_pci_init_two(struct pci_dev *, struct pci_dev *,
                      const struct ide_port_info *, void *);
@@ -1551,4 +1577,5 @@ static inline void ide_set_drivedata(ide_drive_t *drive, void *data)
 #define ide_host_for_each_port(i, port, host) \
         for ((i) = 0; ((port) = (host)->ports[i]) || (i) < MAX_HOST_PORTS; (i)++)
 
+
 #endif /* _IDE_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index cee108cbe2d5..38874729dc5f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -377,7 +377,6 @@ extern void end_swap_bio_write(struct bio *bio, int err);
 extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
         void (*end_write_func)(struct bio *, int));
 extern int swap_set_page_dirty(struct page *page);
-extern void end_swap_bio_read(struct bio *bio, int err);
 
 int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
                 unsigned long nr_pages, sector_t start_block);