Merge branch 'for-3.10/core' of git://git.kernel.dk/linux-block

Pull block core updates from Jens Axboe:

 - Major bit is Kents prep work for immutable bio vecs.

 - Stable candidate fix for a scheduling-while-atomic in the queue
   bypass operation.

 - Fix for the hang on exceeded rq->datalen 32-bit unsigned when merging
   discard bios.

 - Tejuns changes to convert the writeback thread pool to the generic
   workqueue mechanism.

 - Runtime PM framework, SCSI patches exists on top of these in James'
   tree.

 - A few random fixes.

* 'for-3.10/core' of git://git.kernel.dk/linux-block: (40 commits)
  relay: move remove_buf_file inside relay_close_buf
  partitions/efi.c: replace useless kzalloc's by kmalloc's
  fs/block_dev.c: fix iov_shorten() criteria in blkdev_aio_read()
  block: fix max discard sectors limit
  blkcg: fix "scheduling while atomic" in blk_queue_bypass_start
  Documentation: cfq-iosched: update documentation help for cfq tunables
  writeback: expose the bdi_wq workqueue
  writeback: replace custom worker pool implementation with unbound workqueue
  writeback: remove unused bdi_pending_list
  aoe: Fix unitialized var usage
  bio-integrity: Add explicit field for owner of bip_buf
  block: Add an explicit bio flag for bios that own their bvec
  block: Add bio_alloc_pages()
  block: Convert some code to bio_for_each_segment_all()
  block: Add bio_for_each_segment_all()
  bounce: Refactor __blk_queue_bounce to not use bi_io_vec
  raid1: use bio_copy_data()
  pktcdvd: Use bio_reset() in disabled code to kill bi_idx usage
  pktcdvd: use bio_copy_data()
  block: Add bio_copy_data()
  ...

6 files changed, 115 insertions, 67 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 350459910fe1..c3881553f7d1 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -18,6 +18,7 @@
 #include <linux/writeback.h>
 #include <linux/atomic.h>
 #include <linux/sysctl.h>
+#include <linux/workqueue.h>
 
 struct page;
 struct device;
@@ -27,7 +28,6 @@ struct dentry;
  * Bits in backing_dev_info.state
  */
 enum bdi_state {
-	BDI_pending,		/* On its way to being activated */
 	BDI_wb_alloc,		/* Default embedded wb allocated */
 	BDI_async_congested,	/* The async (write) queue is getting full */
 	BDI_sync_congested,	/* The sync queue is getting full */
@@ -53,10 +53,8 @@ struct bdi_writeback {
 	unsigned int nr;
 
 	unsigned long last_old_flush;	/* last old data flush */
-	unsigned long last_active;	/* last time bdi thread was active */
 
-	struct task_struct *task;	/* writeback thread */
-	struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */
+	struct delayed_work dwork;	/* work item used for writeback */
 	struct list_head b_dirty;	/* dirty inodes */
 	struct list_head b_io;		/* parked for writeback */
 	struct list_head b_more_io;	/* parked for more writeback */
@@ -123,14 +121,15 @@ int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 			enum wb_reason reason);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
-int bdi_writeback_thread(void *data);
+void bdi_writeback_workfn(struct work_struct *work);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
 void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
-extern struct list_head bdi_pending_list;
+
+extern struct workqueue_struct *bdi_wq;
 
 static inline int wb_has_dirty_io(struct bdi_writeback *wb)
 {
@@ -336,11 +335,6 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
 	return bdi->capabilities & BDI_CAP_SWAP_BACKED;
 }
 
-static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi)
-{
-	return bdi == &default_backing_dev_info;
-}
-
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 820e7aaad4fd..ef24466d8f82 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -67,6 +67,7 @@
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
 #define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
+#define bio_end_sector(bio)	((bio)->bi_sector + bio_sectors((bio)))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
@@ -84,11 +85,6 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
-static inline int bio_has_allocated_vec(struct bio *bio)
-{
-	return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs;
-}
-
 /*
  * will die
  */
@@ -136,16 +132,27 @@ static inline int bio_has_allocated_vec(struct bio *bio)
 #define bio_io_error(bio) bio_endio((bio), -EIO)
 
 /*
- * drivers should not use the __ version unless they _really_ want to
- * run through the entire bio and not just pending pieces
+ * drivers should not use the __ version unless they _really_ know what
+ * they're doing
  */
 #define __bio_for_each_segment(bvl, bio, i, start_idx)			\
 	for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx);	\
 	     i < (bio)->bi_vcnt;					\
 	     bvl++, i++)
 
+/*
+ * drivers should _never_ use the all version - the bio may have been split
+ * before it got to the driver and the driver won't own all of it
+ */
+#define bio_for_each_segment_all(bvl, bio, i)				\
+	for (i = 0;							\
+	     bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt;	\
+	     i++)
+
 #define bio_for_each_segment(bvl, bio, i)				\
-	__bio_for_each_segment(bvl, bio, i, (bio)->bi_idx)
+	for (i = (bio)->bi_idx;						\
+	     bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt;	\
+	     i++)
 
 /*
  * get a reference to a bio, so it won't disappear. the intended use is
@@ -180,9 +187,12 @@ struct bio_integrity_payload {
 	unsigned short		bip_slab;	/* slab the bip came from */
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_idx;	/* current bip_vec index */
+	unsigned		bip_owns_buf:1;	/* should free bip_buf */
 
 	struct work_struct	bip_work;	/* I/O completion */
-	struct bio_vec		bip_vec[0];	/* embedded bvec array */
+
+	struct bio_vec		*bip_vec;
+	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
 };
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
@@ -211,6 +221,7 @@ extern void bio_pair_release(struct bio_pair *dbio);
 
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
+extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries);
 
 extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
 extern void bio_put(struct bio *);
@@ -245,6 +256,9 @@ extern void bio_endio(struct bio *, int);
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
 
+extern int submit_bio_wait(int rw, struct bio *bio);
+extern void bio_advance(struct bio *, unsigned);
+
 extern void bio_init(struct bio *);
 extern void bio_reset(struct bio *);
 
@@ -279,6 +293,9 @@ static inline void bio_flush_dcache_pages(struct bio *bi)
 }
 #endif
 
+extern void bio_copy_data(struct bio *dst, struct bio *src);
+extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
+
 extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
 				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
@@ -286,8 +303,8 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
 				     int, int, gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
-extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *);
-extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int);
+extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
+extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 #ifdef CONFIG_BLK_CGROUP
@@ -298,39 +315,6 @@ static inline int bio_associate_current(struct bio *bio) { return -ENOENT; }
 static inline void bio_disassociate_task(struct bio *bio) { }
 #endif	/* CONFIG_BLK_CGROUP */
 
-/*
- * bio_set is used to allow other portions of the IO system to
- * allocate their own private memory pools for bio and iovec structures.
- * These memory pools in turn all allocate from the bio_slab
- * and the bvec_slabs[].
- */
-#define BIO_POOL_SIZE 2
-#define BIOVEC_NR_POOLS 6
-#define BIOVEC_MAX_IDX	(BIOVEC_NR_POOLS - 1)
-
-struct bio_set {
-	struct kmem_cache *bio_slab;
-	unsigned int front_pad;
-
-	mempool_t *bio_pool;
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-	mempool_t *bio_integrity_pool;
-#endif
-	mempool_t *bvec_pool;
-};
-
-struct biovec_slab {
-	int nr_vecs;
-	char *name;
-	struct kmem_cache *slab;
-};
-
-/*
- * a small number of entries is fine, not going to be performance critical.
- * basically we just need to survive
- */
-#define BIO_SPLIT_ENTRIES 2
-
 #ifdef CONFIG_HIGHMEM
 /*
  * remember never ever reenable interrupts between a bvec_kmap_irq and
@@ -527,6 +511,49 @@ static inline struct bio *bio_list_get(struct bio_list *bl)
 	return bio;
 }
 
+/*
+ * bio_set is used to allow other portions of the IO system to
+ * allocate their own private memory pools for bio and iovec structures.
+ * These memory pools in turn all allocate from the bio_slab
+ * and the bvec_slabs[].
+ */
+#define BIO_POOL_SIZE 2
+#define BIOVEC_NR_POOLS 6
+#define BIOVEC_MAX_IDX	(BIOVEC_NR_POOLS - 1)
+
+struct bio_set {
+	struct kmem_cache *bio_slab;
+	unsigned int front_pad;
+
+	mempool_t *bio_pool;
+	mempool_t *bvec_pool;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	mempool_t *bio_integrity_pool;
+	mempool_t *bvec_integrity_pool;
+#endif
+
+	/*
+	 * Deadlock avoidance for stacking block drivers: see comments in
+	 * bio_alloc_bioset() for details
+	 */
+	spinlock_t		rescue_lock;
+	struct bio_list		rescue_list;
+	struct work_struct	rescue_work;
+	struct workqueue_struct	*rescue_workqueue;
+};
+
+struct biovec_slab {
+	int nr_vecs;
+	char *name;
+	struct kmem_cache *slab;
+};
+
+/*
+ * a small number of entries is fine, not going to be performance critical.
+ * basically we just need to survive
+ */
+#define BIO_SPLIT_ENTRIES 2
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
 #define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 22990cf4439d..fa1abeb45b76 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -118,6 +118,7 @@ struct bio {
  * BIO_POOL_IDX()
  */
 #define BIO_RESET_BITS	13
+#define BIO_OWNS_VEC	13	/* bio_free() should free bvec */
 
 #define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
 
@@ -176,6 +177,7 @@ enum rq_flag_bits {
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
+	__REQ_PM,		/* runtime pm request */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -198,6 +200,8 @@ enum rq_flag_bits {
 	 REQ_SECURE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
+#define BIO_NO_ADVANCE_ITER_MASK	(REQ_DISCARD|REQ_WRITE_SAME)
+
 /* This mask is used for both bio and request merge checking */
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA)
@@ -224,5 +228,6 @@ enum rq_flag_bits {
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
 #define REQ_KERNEL		(1 << __REQ_KERNEL)
+#define REQ_PM			(1 << __REQ_PM)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e38cfe77f7f0..2fdb4a451b49 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -361,6 +361,12 @@ struct request_queue {
 	 */
 	struct kobject kobj;
 
+#ifdef CONFIG_PM_RUNTIME
+	struct device		*dev;
+	int			rpm_status;
+	unsigned int		nr_pending;
+#endif
+
 	/*
 	 * queue settings
 	 */
@@ -838,7 +844,7 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     unsigned int cmd_flags)
 {
 	if (unlikely(cmd_flags & REQ_DISCARD))
-		return q->limits.max_discard_sectors;
+		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
 
 	if (unlikely(cmd_flags & REQ_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
@@ -961,6 +967,27 @@ struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
 
 /*
+ * block layer runtime pm functions
+ */
+#ifdef CONFIG_PM_RUNTIME
+extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
+extern int blk_pre_runtime_suspend(struct request_queue *q);
+extern void blk_post_runtime_suspend(struct request_queue *q, int err);
+extern void blk_pre_runtime_resume(struct request_queue *q);
+extern void blk_post_runtime_resume(struct request_queue *q, int err);
+#else
+static inline void blk_pm_runtime_init(struct request_queue *q,
+	struct device *dev) {}
+static inline int blk_pre_runtime_suspend(struct request_queue *q)
+{
+	return -ENOSYS;
+}
+static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {}
+static inline void blk_pre_runtime_resume(struct request_queue *q) {}
+static inline void blk_post_runtime_resume(struct request_queue *q, int err) {}
+#endif
+
+/*
  * blk_plug permits building a queue of related requests by holding the I/O
  * fragments for a short period. This allows merging of sequential requests
  * into single larger request. As the requests are moved from a per-task list to
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 9c1467357b03..60ae7c3db912 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -244,7 +244,7 @@ TRACE_EVENT(block_bio_bounce,
 		__entry->dev		= bio->bi_bdev ?
 					  bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
@@ -281,7 +281,7 @@ TRACE_EVENT(block_bio_complete,
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		__entry->error		= error;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 	),
@@ -309,7 +309,7 @@ DECLARE_EVENT_CLASS(block_bio_merge,
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
@@ -376,7 +376,7 @@ TRACE_EVENT(block_bio_queue,
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
@@ -404,7 +404,7 @@ DECLARE_EVENT_CLASS(block_get_rq,
 	TP_fast_assign(
 		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio ? bio->bi_sector : 0;
-		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		__entry->nr_sector	= bio ? bio_sectors(bio) : 0;
 		blk_fill_rwbs(__entry->rwbs,
 			      bio ? bio->bi_rw : 0, __entry->nr_sector);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
@@ -580,7 +580,7 @@ TRACE_EVENT(block_bio_remap,
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		__entry->old_dev	= dev;
 		__entry->old_sector	= from;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 6a16fd2e70ed..464ea82e10db 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -183,7 +183,6 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 DEFINE_EVENT(writeback_work_class, name, \
 	TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \
 	TP_ARGS(bdi, work))
-DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_queue);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_exec);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_start);
@@ -222,12 +221,8 @@ DEFINE_EVENT(writeback_class, name, \
 
 DEFINE_WRITEBACK_EVENT(writeback_nowork);
 DEFINE_WRITEBACK_EVENT(writeback_wake_background);
-DEFINE_WRITEBACK_EVENT(writeback_wake_thread);
-DEFINE_WRITEBACK_EVENT(writeback_wake_forker_thread);
 DEFINE_WRITEBACK_EVENT(writeback_bdi_register);
 DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
-DEFINE_WRITEBACK_EVENT(writeback_thread_start);
-DEFINE_WRITEBACK_EVENT(writeback_thread_stop);
 
 DECLARE_EVENT_CLASS(wbc_class,
 	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi),