Merge branch 'for-3.6/core' of git://git.kernel.dk/linux-block

Pull core block IO bits from Jens Axboe:
 "The most complicated part if this is the request allocation rework by
  Tejun, which has been queued up for a long time and has been in
  for-next ditto as well.

  There are a few commits from yesterday and today, mostly trivial and
  obvious fixes.  So I'm pretty confident that it is sound.  It's also
  smaller than usual."

* 'for-3.6/core' of git://git.kernel.dk/linux-block:
  block: remove dead func declaration
  block: add partition resize function to blkpg ioctl
  block: uninitialized ioc->nr_tasks triggers WARN_ON
  block: do not artificially constrain max_sectors for stacking drivers
  blkcg: implement per-blkg request allocation
  block: prepare for multiple request_lists
  block: add q->nr_rqs[] and move q->rq.elvpriv to q->nr_rqs_elvpriv
  blkcg: inline bio_blkcg() and friends
  block: allocate io_context upfront
  block: refactor get_request[_wait]()
  block: drop custom queue draining used by scsi_transport_{iscsi|fc}
  mempool: add @gfp_mask to mempool_create_node()
  blkcg: make root blkcg allocation use %GFP_KERNEL
  blkcg: __blkg_lookup_create() doesn't need radix preload

5 files changed, 92 insertions, 23 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 07954b05b86..3816ce8a08f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -46,16 +46,23 @@ struct blkcg_gq;
 struct request;
 typedef void (rq_end_io_fn)(struct request *, int);
 
+#define BLK_RL_SYNCFULL		(1U << 0)
+#define BLK_RL_ASYNCFULL	(1U << 1)
+
 struct request_list {
+	struct request_queue	*q;	/* the queue this rl belongs to */
+#ifdef CONFIG_BLK_CGROUP
+	struct blkcg_gq		*blkg;	/* blkg this request pool belongs to */
+#endif
 	/*
 	 * count[], starved[], and wait[] are indexed by
 	 * BLK_RW_SYNC/BLK_RW_ASYNC
 	 */
-	int count[2];
-	int starved[2];
-	int elvpriv;
-	mempool_t *rq_pool;
-	wait_queue_head_t wait[2];
+	int			count[2];
+	int			starved[2];
+	mempool_t		*rq_pool;
+	wait_queue_head_t	wait[2];
+	unsigned int		flags;
 };
 
 /*
@@ -138,6 +145,7 @@ struct request {
 	struct hd_struct *part;
 	unsigned long start_time;
 #ifdef CONFIG_BLK_CGROUP
+	struct request_list *rl;		/* rl this rq is alloced from */
 	unsigned long long start_time_ns;
 	unsigned long long io_start_time_ns;    /* when passed to hardware */
 #endif
@@ -282,11 +290,16 @@ struct request_queue {
 	struct list_head	queue_head;
 	struct request		*last_merge;
 	struct elevator_queue	*elevator;
+	int			nr_rqs[2];	/* # allocated [a]sync rqs */
+	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
 	/*
-	 * the queue request freelist, one for reads and one for writes
+	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
+	 * is used, root blkg allocates from @q->root_rl and all other
+	 * blkgs from their own blkg->rl.  Which one to use should be
+	 * determined using bio_request_list().
 	 */
-	struct request_list	rq;
+	struct request_list	root_rl;
 
 	request_fn_proc		*request_fn;
 	make_request_fn		*make_request_fn;
@@ -561,27 +574,25 @@ static inline bool rq_is_sync(struct request *rq)
 	return rw_is_sync(rq->cmd_flags);
 }
 
-static inline int blk_queue_full(struct request_queue *q, int sync)
+static inline bool blk_rl_full(struct request_list *rl, bool sync)
 {
-	if (sync)
-		return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags);
-	return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags);
+	unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
+
+	return rl->flags & flag;
 }
 
-static inline void blk_set_queue_full(struct request_queue *q, int sync)
+static inline void blk_set_rl_full(struct request_list *rl, bool sync)
 {
-	if (sync)
-		queue_flag_set(QUEUE_FLAG_SYNCFULL, q);
-	else
-		queue_flag_set(QUEUE_FLAG_ASYNCFULL, q);
+	unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
+
+	rl->flags |= flag;
 }
 
-static inline void blk_clear_queue_full(struct request_queue *q, int sync)
+static inline void blk_clear_rl_full(struct request_list *rl, bool sync)
 {
-	if (sync)
-		queue_flag_clear(QUEUE_FLAG_SYNCFULL, q);
-	else
-		queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q);
+	unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
+
+	rl->flags &= ~flag;
 }
 
 
diff --git a/include/linux/blkpg.h b/include/linux/blkpg.h
index faf8a45af21..a8519446c11 100644
--- a/include/linux/blkpg.h
+++ b/include/linux/blkpg.h
@@ -40,6 +40,7 @@ struct blkpg_ioctl_arg {
 /* The subfunctions (for the op field) */
 #define BLKPG_ADD_PARTITION	1
 #define BLKPG_DEL_PARTITION	2
+#define BLKPG_RESIZE_PARTITION	3
 
 /* Sizes of name fields. Unused at present. */
 #define BLKPG_DEVNAMELTH	64
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index f55ab8cdc10..4d0fb3df2f4 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -67,7 +67,6 @@ void bsg_job_done(struct bsg_job *job, int result,
 int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name,
 		    bsg_job_fn *job_fn, int dd_job_size);
 void bsg_request_fn(struct request_queue *q);
-void bsg_remove_queue(struct request_queue *q);
 void bsg_goose_queue(struct request_queue *q);
 
 #endif
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index ae0aaa9d42f..4f440b3e89f 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -97,7 +97,13 @@ struct partition_meta_info {
 
 struct hd_struct {
 	sector_t start_sect;
+	/*
+	 * nr_sects is protected by sequence counter. One might extend a
+	 * partition while IO is happening to it and update of nr_sects
+	 * can be non-atomic on 32bit machines with 64bit sector_t.
+	 */
 	sector_t nr_sects;
+	seqcount_t nr_sects_seq;
 	sector_t alignment_offset;
 	unsigned int discard_alignment;
 	struct device __dev;
@@ -647,6 +653,57 @@ static inline void hd_struct_put(struct hd_struct *part)
 		__delete_partition(part);
 }
 
+/*
+ * Any access of part->nr_sects which is not protected by partition
+ * bd_mutex or gendisk bdev bd_mutex, should be done using this
+ * accessor function.
+ *
+ * Code written along the lines of i_size_read() and i_size_write().
+ * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption
+ * on.
+ */
+static inline sector_t part_nr_sects_read(struct hd_struct *part)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
+	sector_t nr_sects;
+	unsigned seq;
+	do {
+		seq = read_seqcount_begin(&part->nr_sects_seq);
+		nr_sects = part->nr_sects;
+	} while (read_seqcount_retry(&part->nr_sects_seq, seq));
+	return nr_sects;
+#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
+	sector_t nr_sects;
+
+	preempt_disable();
+	nr_sects = part->nr_sects;
+	preempt_enable();
+	return nr_sects;
+#else
+	return part->nr_sects;
+#endif
+}
+
+/*
+ * Should be called with mutex lock held (typically bd_mutex) of partition
+ * to provide mutual exlusion among writers otherwise seqcount might be
+ * left in wrong state leaving the readers spinning infinitely.
+ */
+static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
+	write_seqcount_begin(&part->nr_sects_seq);
+	part->nr_sects = size;
+	write_seqcount_end(&part->nr_sects_seq);
+#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
+	preempt_disable();
+	part->nr_sects = size;
+	preempt_enable();
+#else
+	part->nr_sects = size;
+#endif
+}
+
 #else /* CONFIG_BLOCK */
 
 static inline void printk_all_partitions(void) { }
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index 7c08052e332..39ed62ab5b8 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -26,7 +26,8 @@ typedef struct mempool_s {
 extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
 			mempool_free_t *free_fn, void *pool_data);
 extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
-			mempool_free_t *free_fn, void *pool_data, int nid);
+			mempool_free_t *free_fn, void *pool_data,
+			gfp_t gfp_mask, int nid);
 
 extern int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask);
 extern void mempool_destroy(mempool_t *pool);