Merge branch 'for-2.6.36' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.36' of git://git.kernel.dk/linux-2.6-block: (149 commits)
  block: make sure that REQ_* types are seen even with CONFIG_BLOCK=n
  xen-blkfront: fix missing out label
  blkdev: fix blkdev_issue_zeroout return value
  block: update request stacking methods to support discards
  block: fix missing export of blk_types.h
  writeback: fix bad _bh spinlock nesting
  drbd: revert "delay probes", feature is being re-implemented differently
  drbd: Initialize all members of sync_conf to their defaults [Bugz 315]
  drbd: Disable delay probes for the upcomming release
  writeback: cleanup bdi_register
  writeback: add new tracepoints
  writeback: remove unnecessary init_timer call
  writeback: optimize periodic bdi thread wakeups
  writeback: prevent unnecessary bdi threads wakeups
  writeback: move bdi threads exiting logic to the forker thread
  writeback: restructure bdi forker loop a little
  writeback: move last_active to bdi
  writeback: do not remove bdi from bdi_list
  writeback: simplify bdi code a little
  writeback: do not lose wake-ups in bdi threads
  ...

Fixed up pretty trivial conflicts in drivers/block/virtio_blk.c and
drivers/scsi/scsi_error.c as per Jens.

13 files changed, 461 insertions, 315 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 2547daf2aef2..9d65d4d0bd9c 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -39,6 +39,7 @@ header-y += ax25.h
 header-y += b1lli.h
 header-y += baycom.h
 header-y += bfs_fs.h
+header-y += blk_types.h
 header-y += blkpg.h
 header-y += bpqether.h
 header-y += bsg.h
diff --git a/include/linux/audit.h b/include/linux/audit.h
index f391d45c8aea..e24afabc548f 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -544,7 +544,7 @@ extern int audit_signals;
 #define audit_putname(n) do { ; } while (0)
 #define __audit_inode(n,d) do { ; } while (0)
 #define __audit_inode_child(i,p) do { ; } while (0)
-#define audit_inode(n,d) do { ; } while (0)
+#define audit_inode(n,d) do { (void)(d); } while (0)
 #define audit_inode_child(i,p) do { ; } while (0)
 #define audit_core_dumps(i) do { ; } while (0)
 #define auditsc_get_stamp(c,t,s) (0)
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index e9aec0d099df..7628219e5386 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -45,22 +45,21 @@ enum bdi_stat_item {
 #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
 struct bdi_writeback {
-	struct list_head list;			/* hangs off the bdi */
-
-	struct backing_dev_info *bdi;		/* our parent bdi */
+	struct backing_dev_info *bdi;	/* our parent bdi */
 	unsigned int nr;
 
-	unsigned long last_old_flush;		/* last old data flush */
+	unsigned long last_old_flush;	/* last old data flush */
+	unsigned long last_active;	/* last time bdi thread was active */
 
-	struct task_struct	*task;		/* writeback task */
-	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 */
+	struct task_struct *task;	/* writeback thread */
+	struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */
+	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 */
 };
 
 struct backing_dev_info {
 	struct list_head bdi_list;
-	struct rcu_head rcu_head;
 	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
 	unsigned long state;	/* Always use atomic bitops on this */
 	unsigned int capabilities; /* Device capabilities */
@@ -80,8 +79,7 @@ struct backing_dev_info {
 	unsigned int max_ratio, max_prop_frac;
 
 	struct bdi_writeback wb;  /* default writeback info for this bdi */
-	spinlock_t wb_lock;	  /* protects update side of wb_list */
-	struct list_head wb_list; /* the flusher threads hanging off this bdi */
+	spinlock_t wb_lock;	  /* protects work_list */
 
 	struct list_head work_list;
 
@@ -105,9 +103,10 @@ void bdi_unregister(struct backing_dev_info *bdi);
 int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
-int bdi_writeback_task(struct bdi_writeback *wb);
+int bdi_writeback_thread(void *data);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 void bdi_arm_supers_timer(void);
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7fc5606e6ea5..5274103434ad 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -9,7 +9,7 @@
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
-
+ *
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
@@ -28,6 +28,9 @@
 
 #include <asm/io.h>
 
+/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
+#include <linux/blk_types.h>
+
 #define BIO_DEBUG
 
 #ifdef BIO_DEBUG
@@ -41,154 +44,6 @@
 #define BIO_MAX_SECTORS		(BIO_MAX_SIZE >> 9)
 
 /*
- * was unsigned short, but we might as well be ready for > 64kB I/O pages
- */
-struct bio_vec {
-	struct page	*bv_page;
-	unsigned int	bv_len;
-	unsigned int	bv_offset;
-};
-
-struct bio_set;
-struct bio;
-struct bio_integrity_payload;
-typedef void (bio_end_io_t) (struct bio *, int);
-typedef void (bio_destructor_t) (struct bio *);
-
-/*
- * main unit of I/O for the block layer and lower layers (ie drivers and
- * stacking drivers)
- */
-struct bio {
-	sector_t		bi_sector;	/* device address in 512 byte
-						   sectors */
-	struct bio		*bi_next;	/* request queue link */
-	struct block_device	*bi_bdev;
-	unsigned long		bi_flags;	/* status, command, etc */
-	unsigned long		bi_rw;		/* bottom bits READ/WRITE,
-						 * top bits priority
-						 */
-
-	unsigned short		bi_vcnt;	/* how many bio_vec's */
-	unsigned short		bi_idx;		/* current index into bvl_vec */
-
-	/* Number of segments in this BIO after
-	 * physical address coalescing is performed.
-	 */
-	unsigned int		bi_phys_segments;
-
-	unsigned int		bi_size;	/* residual I/O count */
-
-	/*
-	 * To keep track of the max segment size, we account for the
-	 * sizes of the first and last mergeable segments in this bio.
-	 */
-	unsigned int		bi_seg_front_size;
-	unsigned int		bi_seg_back_size;
-
-	unsigned int		bi_max_vecs;	/* max bvl_vecs we can hold */
-
-	unsigned int		bi_comp_cpu;	/* completion CPU */
-
-	atomic_t		bi_cnt;		/* pin count */
-
-	struct bio_vec		*bi_io_vec;	/* the actual vec list */
-
-	bio_end_io_t		*bi_end_io;
-
-	void			*bi_private;
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-	struct bio_integrity_payload *bi_integrity;  /* data integrity */
-#endif
-
-	bio_destructor_t	*bi_destructor;	/* destructor */
-
-	/*
-	 * We can inline a number of vecs at the end of the bio, to avoid
-	 * double allocations for a small number of bio_vecs. This member
-	 * MUST obviously be kept at the very end of the bio.
-	 */
-	struct bio_vec		bi_inline_vecs[0];
-};
-
-/*
- * 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_CPU_AFFINE	8	/* complete bio on same CPU as submitted */
-#define BIO_NULL_MAPPED 9	/* contains invalid user pages */
-#define BIO_FS_INTEGRITY 10	/* fs owns integrity data, not block layer */
-#define BIO_QUIET	11	/* Make BIO Quiet */
-#define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
-
-/*
- * top 4 bits of bio flags indicate the pool this bio came from
- */
-#define BIO_POOL_BITS		(4)
-#define BIO_POOL_NONE		((1UL << BIO_POOL_BITS) - 1)
-#define BIO_POOL_OFFSET		(BITS_PER_LONG - BIO_POOL_BITS)
-#define BIO_POOL_MASK		(1UL << BIO_POOL_OFFSET)
-#define BIO_POOL_IDX(bio)	((bio)->bi_flags >> BIO_POOL_OFFSET)	
-
-/*
- * bio bi_rw flags
- *
- * bit 0 -- data direction
- *	If not set, bio is a read from device. If set, it's a write to device.
- * bit 1 -- fail fast device errors
- * bit 2 -- fail fast transport errors
- * bit 3 -- fail fast driver errors
- * bit 4 -- rw-ahead when set
- * bit 5 -- barrier
- *	Insert a serialization point in the IO queue, forcing previously
- *	submitted IO to be completed before this one is issued.
- * bit 6 -- synchronous I/O hint.
- * bit 7 -- Unplug the device immediately after submitting this bio.
- * bit 8 -- metadata request
- *	Used for tracing to differentiate metadata and data IO. May also
- *	get some preferential treatment in the IO scheduler
- * bit 9 -- discard sectors
- *	Informs the lower level device that this range of sectors is no longer
- *	used by the file system and may thus be freed by the device. Used
- *	for flash based storage.
- *	Don't want driver retries for any fast fail whatever the reason.
- * bit 10 -- Tell the IO scheduler not to wait for more requests after this
-	one has been submitted, even if it is a SYNC request.
- */
-enum bio_rw_flags {
-	BIO_RW,
-	BIO_RW_FAILFAST_DEV,
-	BIO_RW_FAILFAST_TRANSPORT,
-	BIO_RW_FAILFAST_DRIVER,
-	/* above flags must match REQ_* */
-	BIO_RW_AHEAD,
-	BIO_RW_BARRIER,
-	BIO_RW_SYNCIO,
-	BIO_RW_UNPLUG,
-	BIO_RW_META,
-	BIO_RW_DISCARD,
-	BIO_RW_NOIDLE,
-};
-
-/*
- * First four bits must match between bio->bi_rw and rq->cmd_flags, make
- * that explicit here.
- */
-#define BIO_RW_RQ_MASK		0xf
-
-static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
-{
-	return (bio->bi_rw & (1 << flag)) != 0;
-}
-
-/*
  * upper 16 bits of bi_rw define the io priority of this bio
  */
 #define BIO_PRIO_SHIFT	(8 * sizeof(unsigned long) - IOPRIO_BITS)
@@ -211,7 +66,10 @@ static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
 #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_empty_barrier(bio)	(bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD))
+#define bio_empty_barrier(bio) \
+	((bio->bi_rw & REQ_HARDBARRIER) && \
+	 !bio_has_data(bio) && \
+	 !(bio->bi_rw & REQ_DISCARD))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
new file mode 100644
index 000000000000..53691774d34e
--- /dev/null
+++ b/include/linux/blk_types.h
@@ -0,0 +1,194 @@
+/*
+ * Block data types and constants.  Directly include this file only to
+ * break include dependency loop.
+ */
+#ifndef __LINUX_BLK_TYPES_H
+#define __LINUX_BLK_TYPES_H
+
+#ifdef CONFIG_BLOCK
+
+#include <linux/types.h>
+
+struct bio_set;
+struct bio;
+struct bio_integrity_payload;
+struct page;
+struct block_device;
+typedef void (bio_end_io_t) (struct bio *, int);
+typedef void (bio_destructor_t) (struct bio *);
+
+/*
+ * was unsigned short, but we might as well be ready for > 64kB I/O pages
+ */
+struct bio_vec {
+	struct page	*bv_page;
+	unsigned int	bv_len;
+	unsigned int	bv_offset;
+};
+
+/*
+ * main unit of I/O for the block layer and lower layers (ie drivers and
+ * stacking drivers)
+ */
+struct bio {
+	sector_t		bi_sector;	/* device address in 512 byte
+						   sectors */
+	struct bio		*bi_next;	/* request queue link */
+	struct block_device	*bi_bdev;
+	unsigned long		bi_flags;	/* status, command, etc */
+	unsigned long		bi_rw;		/* bottom bits READ/WRITE,
+						 * top bits priority
+						 */
+
+	unsigned short		bi_vcnt;	/* how many bio_vec's */
+	unsigned short		bi_idx;		/* current index into bvl_vec */
+
+	/* Number of segments in this BIO after
+	 * physical address coalescing is performed.
+	 */
+	unsigned int		bi_phys_segments;
+
+	unsigned int		bi_size;	/* residual I/O count */
+
+	/*
+	 * To keep track of the max segment size, we account for the
+	 * sizes of the first and last mergeable segments in this bio.
+	 */
+	unsigned int		bi_seg_front_size;
+	unsigned int		bi_seg_back_size;
+
+	unsigned int		bi_max_vecs;	/* max bvl_vecs we can hold */
+
+	unsigned int		bi_comp_cpu;	/* completion CPU */
+
+	atomic_t		bi_cnt;		/* pin count */
+
+	struct bio_vec		*bi_io_vec;	/* the actual vec list */
+
+	bio_end_io_t		*bi_end_io;
+
+	void			*bi_private;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	struct bio_integrity_payload *bi_integrity;  /* data integrity */
+#endif
+
+	bio_destructor_t	*bi_destructor;	/* destructor */
+
+	/*
+	 * We can inline a number of vecs at the end of the bio, to avoid
+	 * double allocations for a small number of bio_vecs. This member
+	 * MUST obviously be kept at the very end of the bio.
+	 */
+	struct bio_vec		bi_inline_vecs[0];
+};
+
+/*
+ * 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_CPU_AFFINE	8	/* complete bio on same CPU as submitted */
+#define BIO_NULL_MAPPED 9	/* contains invalid user pages */
+#define BIO_FS_INTEGRITY 10	/* fs owns integrity data, not block layer */
+#define BIO_QUIET	11	/* Make BIO Quiet */
+#define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
+
+/*
+ * top 4 bits of bio flags indicate the pool this bio came from
+ */
+#define BIO_POOL_BITS		(4)
+#define BIO_POOL_NONE		((1UL << BIO_POOL_BITS) - 1)
+#define BIO_POOL_OFFSET		(BITS_PER_LONG - BIO_POOL_BITS)
+#define BIO_POOL_MASK		(1UL << BIO_POOL_OFFSET)
+#define BIO_POOL_IDX(bio)	((bio)->bi_flags >> BIO_POOL_OFFSET)
+
+#endif /* CONFIG_BLOCK */
+
+/*
+ * Request flags.  For use in the cmd_flags field of struct request, and in
+ * bi_rw of struct bio.  Note that some flags are only valid in either one.
+ */
+enum rq_flag_bits {
+	/* common flags */
+	__REQ_WRITE,		/* not set, read. set, write */
+	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
+	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
+	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
+
+	__REQ_HARDBARRIER,	/* may not be passed by drive either */
+	__REQ_SYNC,		/* request is sync (sync write or read) */
+	__REQ_META,		/* metadata io request */
+	__REQ_DISCARD,		/* request to discard sectors */
+	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
+
+	/* bio only flags */
+	__REQ_UNPLUG,		/* unplug the immediately after submission */
+	__REQ_RAHEAD,		/* read ahead, can fail anytime */
+
+	/* request only flags */
+	__REQ_SORTED,		/* elevator knows about this request */
+	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
+	__REQ_FUA,		/* forced unit access */
+	__REQ_NOMERGE,		/* don't touch this for merging */
+	__REQ_STARTED,		/* drive already may have started this one */
+	__REQ_DONTPREP,		/* don't call prep for this one */
+	__REQ_QUEUED,		/* uses queueing */
+	__REQ_ELVPRIV,		/* elevator private data attached */
+	__REQ_FAILED,		/* set if the request failed */
+	__REQ_QUIET,		/* don't worry about errors */
+	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
+	__REQ_ORDERED_COLOR,	/* is before or after barrier */
+	__REQ_ALLOCED,		/* request came from our alloc pool */
+	__REQ_COPY_USER,	/* contains copies of user pages */
+	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
+	__REQ_FLUSH,		/* request for cache flush */
+	__REQ_IO_STAT,		/* account I/O stat */
+	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
+	__REQ_NR_BITS,		/* stops here */
+};
+
+#define REQ_WRITE		(1 << __REQ_WRITE)
+#define REQ_FAILFAST_DEV	(1 << __REQ_FAILFAST_DEV)
+#define REQ_FAILFAST_TRANSPORT	(1 << __REQ_FAILFAST_TRANSPORT)
+#define REQ_FAILFAST_DRIVER	(1 << __REQ_FAILFAST_DRIVER)
+#define REQ_HARDBARRIER		(1 << __REQ_HARDBARRIER)
+#define REQ_SYNC		(1 << __REQ_SYNC)
+#define REQ_META		(1 << __REQ_META)
+#define REQ_DISCARD		(1 << __REQ_DISCARD)
+#define REQ_NOIDLE		(1 << __REQ_NOIDLE)
+
+#define REQ_FAILFAST_MASK \
+	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
+#define REQ_COMMON_MASK \
+	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \
+	 REQ_META| REQ_DISCARD | REQ_NOIDLE)
+
+#define REQ_UNPLUG		(1 << __REQ_UNPLUG)
+#define REQ_RAHEAD		(1 << __REQ_RAHEAD)
+
+#define REQ_SORTED		(1 << __REQ_SORTED)
+#define REQ_SOFTBARRIER		(1 << __REQ_SOFTBARRIER)
+#define REQ_FUA			(1 << __REQ_FUA)
+#define REQ_NOMERGE		(1 << __REQ_NOMERGE)
+#define REQ_STARTED		(1 << __REQ_STARTED)
+#define REQ_DONTPREP		(1 << __REQ_DONTPREP)
+#define REQ_QUEUED		(1 << __REQ_QUEUED)
+#define REQ_ELVPRIV		(1 << __REQ_ELVPRIV)
+#define REQ_FAILED		(1 << __REQ_FAILED)
+#define REQ_QUIET		(1 << __REQ_QUIET)
+#define REQ_PREEMPT		(1 << __REQ_PREEMPT)
+#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
+#define REQ_ALLOCED		(1 << __REQ_ALLOCED)
+#define REQ_COPY_USER		(1 << __REQ_COPY_USER)
+#define REQ_INTEGRITY		(1 << __REQ_INTEGRITY)
+#define REQ_FLUSH		(1 << __REQ_FLUSH)
+#define REQ_IO_STAT		(1 << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
+
+#endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 09a840264d6f..89c855c5655c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -60,7 +60,6 @@ enum rq_cmd_type_bits {
 	REQ_TYPE_PM_RESUME,		/* resume request */
 	REQ_TYPE_PM_SHUTDOWN,		/* shutdown request */
 	REQ_TYPE_SPECIAL,		/* driver defined type */
-	REQ_TYPE_LINUX_BLOCK,		/* generic block layer message */
 	/*
 	 * 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
@@ -70,84 +69,6 @@ enum rq_cmd_type_bits {
 	REQ_TYPE_ATA_PC,
 };
 
-/*
- * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being
- * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a
- * SCSI cdb.
- *
- * 0x00 -> 0x3f are driver private, to be used for whatever purpose they need,
- * typically to differentiate REQ_TYPE_SPECIAL requests.
- *
- */
-enum {
-	REQ_LB_OP_EJECT	= 0x40,		/* eject request */
-	REQ_LB_OP_FLUSH = 0x41,		/* flush request */
-};
-
-/*
- * request type modified bits. first four bits match BIO_RW* bits, important
- */
-enum rq_flag_bits {
-	__REQ_RW,		/* not set, read. set, write */
-	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
-	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
-	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
-	/* above flags must match BIO_RW_* */
-	__REQ_DISCARD,		/* request to discard sectors */
-	__REQ_SORTED,		/* elevator knows about this request */
-	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
-	__REQ_HARDBARRIER,	/* may not be passed by drive either */
-	__REQ_FUA,		/* forced unit access */
-	__REQ_NOMERGE,		/* don't touch this for merging */
-	__REQ_STARTED,		/* drive already may have started this one */
-	__REQ_DONTPREP,		/* don't call prep for this one */
-	__REQ_QUEUED,		/* uses queueing */
-	__REQ_ELVPRIV,		/* elevator private data attached */
-	__REQ_FAILED,		/* set if the request failed */
-	__REQ_QUIET,		/* don't worry about errors */
-	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
-	__REQ_ORDERED_COLOR,	/* is before or after barrier */
-	__REQ_RW_SYNC,		/* request is sync (sync write or read) */
-	__REQ_ALLOCED,		/* request came from our alloc pool */
-	__REQ_RW_META,		/* metadata io request */
-	__REQ_COPY_USER,	/* contains copies of user pages */
-	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
-	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
-	__REQ_IO_STAT,		/* account I/O stat */
-	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
-	__REQ_NR_BITS,		/* stops here */
-};
-
-#define REQ_RW		(1 << __REQ_RW)
-#define REQ_FAILFAST_DEV	(1 << __REQ_FAILFAST_DEV)
-#define REQ_FAILFAST_TRANSPORT	(1 << __REQ_FAILFAST_TRANSPORT)
-#define REQ_FAILFAST_DRIVER	(1 << __REQ_FAILFAST_DRIVER)
-#define REQ_DISCARD	(1 << __REQ_DISCARD)
-#define REQ_SORTED	(1 << __REQ_SORTED)
-#define REQ_SOFTBARRIER	(1 << __REQ_SOFTBARRIER)
-#define REQ_HARDBARRIER	(1 << __REQ_HARDBARRIER)
-#define REQ_FUA		(1 << __REQ_FUA)
-#define REQ_NOMERGE	(1 << __REQ_NOMERGE)
-#define REQ_STARTED	(1 << __REQ_STARTED)
-#define REQ_DONTPREP	(1 << __REQ_DONTPREP)
-#define REQ_QUEUED	(1 << __REQ_QUEUED)
-#define REQ_ELVPRIV	(1 << __REQ_ELVPRIV)
-#define REQ_FAILED	(1 << __REQ_FAILED)
-#define REQ_QUIET	(1 << __REQ_QUIET)
-#define REQ_PREEMPT	(1 << __REQ_PREEMPT)
-#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
-#define REQ_RW_SYNC	(1 << __REQ_RW_SYNC)
-#define REQ_ALLOCED	(1 << __REQ_ALLOCED)
-#define REQ_RW_META	(1 << __REQ_RW_META)
-#define REQ_COPY_USER	(1 << __REQ_COPY_USER)
-#define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
-#define REQ_NOIDLE	(1 << __REQ_NOIDLE)
-#define REQ_IO_STAT	(1 << __REQ_IO_STAT)
-#define REQ_MIXED_MERGE	(1 << __REQ_MIXED_MERGE)
-
-#define REQ_FAILFAST_MASK	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \
-				 REQ_FAILFAST_DRIVER)
-
 #define BLK_MAX_CDB	16
 
 /*
@@ -264,6 +185,7 @@ struct request_pm_state
 typedef void (request_fn_proc) (struct request_queue *q);
 typedef int (make_request_fn) (struct request_queue *q, struct bio *bio);
 typedef int (prep_rq_fn) (struct request_queue *, struct request *);
+typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unplug_fn) (struct request_queue *);
 
 struct bio_vec;
@@ -275,7 +197,6 @@ struct bvec_merge_data {
 };
 typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
 			     struct bio_vec *);
-typedef void (prepare_flush_fn) (struct request_queue *, struct request *);
 typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);
 typedef int (lld_busy_fn) (struct request_queue *q);
@@ -346,9 +267,9 @@ struct request_queue
 	request_fn_proc		*request_fn;
 	make_request_fn		*make_request_fn;
 	prep_rq_fn		*prep_rq_fn;
+	unprep_rq_fn		*unprep_rq_fn;
 	unplug_fn		*unplug_fn;
 	merge_bvec_fn		*merge_bvec_fn;
-	prepare_flush_fn	*prepare_flush_fn;
 	softirq_done_fn		*softirq_done_fn;
 	rq_timed_out_fn		*rq_timed_out_fn;
 	dma_drain_needed_fn	*dma_drain_needed;
@@ -467,11 +388,13 @@ struct request_queue
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
 #define QUEUE_FLAG_DISCARD     16	/* supports DISCARD */
 #define QUEUE_FLAG_NOXMERGES   17	/* No extended merges */
+#define QUEUE_FLAG_ADD_RANDOM  18	/* Contributes to random pool */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
-				 (1 << QUEUE_FLAG_SAME_COMP))
+				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
+				 (1 << QUEUE_FLAG_ADD_RANDOM))
 
 static inline int queue_is_locked(struct request_queue *q)
 {
@@ -596,38 +519,26 @@ enum {
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
+#define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
 #define blk_queue_flushing(q)	((q)->ordseq)
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
 
-#define blk_fs_request(rq)	((rq)->cmd_type == REQ_TYPE_FS)
-#define blk_pc_request(rq)	((rq)->cmd_type == REQ_TYPE_BLOCK_PC)
-#define blk_special_request(rq)	((rq)->cmd_type == REQ_TYPE_SPECIAL)
-#define blk_sense_request(rq)	((rq)->cmd_type == REQ_TYPE_SENSE)
-
-#define blk_failfast_dev(rq)	((rq)->cmd_flags & REQ_FAILFAST_DEV)
-#define blk_failfast_transport(rq) ((rq)->cmd_flags & REQ_FAILFAST_TRANSPORT)
-#define blk_failfast_driver(rq)	((rq)->cmd_flags & REQ_FAILFAST_DRIVER)
-#define blk_noretry_request(rq)	(blk_failfast_dev(rq) ||	\
-				 blk_failfast_transport(rq) ||	\
-				 blk_failfast_driver(rq))
-#define blk_rq_started(rq)	((rq)->cmd_flags & REQ_STARTED)
-#define blk_rq_io_stat(rq)	((rq)->cmd_flags & REQ_IO_STAT)
-#define blk_rq_quiet(rq)	((rq)->cmd_flags & REQ_QUIET)
-
-#define blk_account_rq(rq)	(blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) 
-
-#define blk_pm_suspend_request(rq)	((rq)->cmd_type == REQ_TYPE_PM_SUSPEND)
-#define blk_pm_resume_request(rq)	((rq)->cmd_type == REQ_TYPE_PM_RESUME)
+#define blk_noretry_request(rq) \
+	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
+			     REQ_FAILFAST_DRIVER))
+
+#define blk_account_rq(rq) \
+	(((rq)->cmd_flags & REQ_STARTED) && \
+	 ((rq)->cmd_type == REQ_TYPE_FS || \
+	  ((rq)->cmd_flags & REQ_DISCARD)))
+
 #define blk_pm_request(rq)	\
-	(blk_pm_suspend_request(rq) || blk_pm_resume_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_sorted_rq(rq)	((rq)->cmd_flags & REQ_SORTED)
-#define blk_barrier_rq(rq)	((rq)->cmd_flags & REQ_HARDBARRIER)
-#define blk_fua_rq(rq)		((rq)->cmd_flags & REQ_FUA)
-#define blk_discard_rq(rq)	((rq)->cmd_flags & REQ_DISCARD)
 #define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
 /* rq->queuelist of dequeued request must be list_empty() */
 #define blk_queued_rq(rq)	(!list_empty(&(rq)->queuelist))
@@ -641,7 +552,7 @@ enum {
  */
 static inline bool rw_is_sync(unsigned int rw_flags)
 {
-	return !(rw_flags & REQ_RW) || (rw_flags & REQ_RW_SYNC);
+	return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC);
 }
 
 static inline bool rq_is_sync(struct request *rq)
@@ -649,9 +560,6 @@ static inline bool rq_is_sync(struct request *rq)
 	return rw_is_sync(rq->cmd_flags);
 }
 
-#define rq_is_meta(rq)		((rq)->cmd_flags & REQ_RW_META)
-#define rq_noidle(rq)		((rq)->cmd_flags & REQ_NOIDLE)
-
 static inline int blk_queue_full(struct request_queue *q, int sync)
 {
 	if (sync)
@@ -684,7 +592,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync)
 	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
-	 (blk_discard_rq(rq) || blk_fs_request((rq))))
+	 (((rq)->cmd_flags & REQ_DISCARD) || \
+	  (rq)->cmd_type == REQ_TYPE_FS))
 
 /*
  * q->prep_rq_fn return values
@@ -709,7 +618,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn;
 #define BLK_BOUNCE_HIGH		-1ULL
 #endif
 #define BLK_BOUNCE_ANY		(-1ULL)
-#define BLK_BOUNCE_ISA		(ISA_DMA_THRESHOLD)
+#define BLK_BOUNCE_ISA		(DMA_BIT_MASK(24))
 
 /*
  * default timeout for SG_IO if none specified
@@ -781,6 +690,8 @@ extern struct request *blk_make_request(struct request_queue *, struct bio *,
 					gfp_t);
 extern void blk_insert_request(struct request_queue *, struct request *, int, void *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
+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,
@@ -915,6 +826,7 @@ extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
 extern void blk_abort_queue(struct request_queue *);
+extern void blk_unprep_request(struct request *);
 
 /*
  * Access functions for manipulating queue properties
@@ -959,6 +871,7 @@ extern int blk_queue_dma_drain(struct request_queue *q,
 extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn);
+extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn);
 extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *);
 extern void blk_queue_dma_alignment(struct request_queue *, int);
 extern void blk_queue_update_dma_alignment(struct request_queue *, int);
@@ -966,7 +879,7 @@ extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
-extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *);
+extern int blk_queue_ordered(struct request_queue *, unsigned);
 extern bool blk_do_ordered(struct request_queue *, struct request **);
 extern unsigned blk_ordered_cur_seq(struct request_queue *);
 extern unsigned blk_ordered_req_seq(struct request *);
@@ -1020,7 +933,7 @@ static inline int sb_issue_discard(struct super_block *sb,
 {
 	block <<= (sb->s_blocksize_bits - 9);
 	nr_blocks <<= (sb->s_blocksize_bits - 9);
-	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
+	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS,
 				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 }
 
@@ -1333,7 +1246,6 @@ static inline int blk_integrity_rq(struct request *rq)
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	int (*release) (struct gendisk *, fmode_t);
-	int (*locked_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*direct_access) (struct block_device *, sector_t,
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 416bf62d6d46..3395cf7130f5 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -5,6 +5,7 @@
 #ifdef __KERNEL__
 #include <linux/blkdev.h>
 #include <linux/relay.h>
+#include <linux/compat.h>
 #endif
 
 /*
@@ -220,11 +221,26 @@ static inline int blk_trace_init_sysfs(struct device *dev)
 
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
+#ifdef CONFIG_COMPAT
+
+struct compat_blk_user_trace_setup {
+	char name[32];
+	u16 act_mask;
+	u32 buf_size;
+	u32 buf_nr;
+	compat_u64 start_lba;
+	compat_u64 end_lba;
+	u32 pid;
+};
+#define BLKTRACESETUP32 _IOWR(0x12, 115, struct compat_blk_user_trace_setup)
+
+#endif
+
 #if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
 
 static inline int blk_cmd_buf_len(struct request *rq)
 {
-	return blk_pc_request(rq) ? rq->cmd_len * 3 : 1;
+	return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1;
 }
 
 extern void blk_dump_cmd(char *buf, struct request *rq);
diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h
index 8859e2ede9fe..284b520934a0 100644
--- a/include/linux/coda_psdev.h
+++ b/include/linux/coda_psdev.h
@@ -86,9 +86,9 @@ struct upc_req {
 	wait_queue_head_t   uc_sleep;   /* process' wait queue */
 };
 
-#define REQ_ASYNC  0x1
-#define REQ_READ   0x2
-#define REQ_WRITE  0x4
-#define REQ_ABORT  0x8
+#define CODA_REQ_ASYNC  0x1
+#define CODA_REQ_READ   0x2
+#define CODA_REQ_WRITE  0x4
+#define CODA_REQ_ABORT  0x8
 
 #endif
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index b8d2516668aa..479ee3a1d901 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -53,7 +53,7 @@
 
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.8"
+#define REL_VERSION "8.3.8.1"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 94
diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h
index ce77a746fc9d..5f042810a56c 100644
--- a/include/linux/drbd_nl.h
+++ b/include/linux/drbd_nl.h
@@ -78,10 +78,11 @@ NL_PACKET(syncer_conf, 8,
 	NL_INTEGER(	30,	T_MAY_IGNORE,	rate)
 	NL_INTEGER(	31,	T_MAY_IGNORE,	after)
 	NL_INTEGER(	32,	T_MAY_IGNORE,	al_extents)
-	NL_INTEGER(     71,	T_MAY_IGNORE,	dp_volume)
-	NL_INTEGER(     72,	T_MAY_IGNORE,	dp_interval)
-	NL_INTEGER(     73,	T_MAY_IGNORE,	throttle_th)
-	NL_INTEGER(     74,	T_MAY_IGNORE,	hold_off_th)
+/*	NL_INTEGER(     71,	T_MAY_IGNORE,	dp_volume)
+ *	NL_INTEGER(     72,	T_MAY_IGNORE,	dp_interval)
+ *	NL_INTEGER(     73,	T_MAY_IGNORE,	throttle_th)
+ *	NL_INTEGER(     74,	T_MAY_IGNORE,	hold_off_th)
+ * feature will be reimplemented differently with 8.3.9 */
 	NL_STRING(      52,     T_MAY_IGNORE,   verify_alg,     SHARED_SECRET_MAX)
 	NL_STRING(      51,     T_MAY_IGNORE,   cpu_mask,       32)
 	NL_STRING(	64,	T_MAY_IGNORE,	csums_alg,	SHARED_SECRET_MAX)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a8ccf85b8691..1542e0e52b2e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -8,6 +8,7 @@
 
 #include <linux/limits.h>
 #include <linux/ioctl.h>
+#include <linux/blk_types.h>
 
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
@@ -121,7 +122,7 @@ struct inodes_stat_t {
  *			immediately wait on this read without caring about
  *			unplugging.
  * READA		Used for read-ahead operations. Lower priority, and the
- *			 block layer could (in theory) choose to ignore this
+ *			block layer could (in theory) choose to ignore this
  *			request if it runs into resource problems.
  * WRITE		A normal async write. Device will be plugged.
  * SWRITE		Like WRITE, but a special case for ll_rw_block() that
@@ -140,7 +141,7 @@ struct inodes_stat_t {
  * SWRITE_SYNC
  * SWRITE_SYNC_PLUG	Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
  *			See SWRITE.
- * WRITE_BARRIER	Like WRITE, but tells the block layer that all
+ * WRITE_BARRIER	Like WRITE_SYNC, but tells the block layer that all
  *			previously submitted writes must be safely on storage
  *			before this one is started. Also guarantees that when
  *			this write is complete, it itself is also safely on
@@ -148,29 +149,31 @@ struct inodes_stat_t {
  *			of this IO.
  *
  */
-#define RW_MASK		1
-#define RWA_MASK	2
-#define READ 0
-#define WRITE 1
-#define READA 2		/* read-ahead  - don't block if no resources */
-#define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
-#define READ_SYNC	(READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
-#define READ_META	(READ | (1 << BIO_RW_META))
-#define WRITE_SYNC_PLUG	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
-#define WRITE_SYNC	(WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
-#define WRITE_ODIRECT_PLUG	(WRITE | (1 << BIO_RW_SYNCIO))
-#define WRITE_META	(WRITE | (1 << BIO_RW_META))
-#define SWRITE_SYNC_PLUG	\
-			(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
-#define SWRITE_SYNC	(SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
-#define WRITE_BARRIER	(WRITE | (1 << BIO_RW_BARRIER))
+#define RW_MASK			REQ_WRITE
+#define RWA_MASK		REQ_RAHEAD
+
+#define READ			0
+#define WRITE			RW_MASK
+#define READA			RWA_MASK
+#define SWRITE			(WRITE | READA)
+
+#define READ_SYNC		(READ | REQ_SYNC | REQ_UNPLUG)
+#define READ_META		(READ | REQ_META)
+#define WRITE_SYNC_PLUG		(WRITE | REQ_SYNC | REQ_NOIDLE)
+#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
+#define WRITE_ODIRECT_PLUG	(WRITE | REQ_SYNC)
+#define WRITE_META		(WRITE | REQ_META)
+#define WRITE_BARRIER		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_HARDBARRIER)
+#define SWRITE_SYNC_PLUG	(SWRITE | REQ_SYNC | REQ_NOIDLE)
+#define SWRITE_SYNC		(SWRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
 
 /*
  * These aren't really reads or writes, they pass down information about
  * parts of device that are now unused by the file system.
  */
-#define DISCARD_NOBARRIER (WRITE | (1 << BIO_RW_DISCARD))
-#define DISCARD_BARRIER (DISCARD_NOBARRIER | (1 << BIO_RW_BARRIER))
+#define DISCARD_NOBARRIER	(WRITE | REQ_DISCARD)
+#define DISCARD_BARRIER		(WRITE | REQ_DISCARD | REQ_HARDBARRIER)
 
 #define SEL_IN		1
 #define SEL_OUT		2
@@ -2196,7 +2199,6 @@ static inline void insert_inode_hash(struct inode *inode) {
 extern void file_move(struct file *f, struct list_head *list);
 extern void file_kill(struct file *f);
 #ifdef CONFIG_BLOCK
-struct bio;
 extern void submit_bio(int, struct bio *);
 extern int bdev_read_only(struct block_device *);
 #endif
@@ -2263,7 +2265,6 @@ static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
 #endif
 
 #ifdef CONFIG_BLOCK
-struct bio;
 typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
 			    loff_t file_offset);
 
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index d870a918559c..d8ce278515c3 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -25,8 +25,10 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 
 	TP_fast_assign(
 		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
-		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
-		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+		__entry->sector    = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_pos(rq);
+		__entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_sectors(rq);
 		__entry->errors    = rq->errors;
 
 		blk_fill_rwbs_rq(__entry->rwbs, rq);
@@ -109,9 +111,12 @@ DECLARE_EVENT_CLASS(block_rq,
 
 	TP_fast_assign(
 		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
-		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
-		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
-		__entry->bytes     = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0;
+		__entry->sector    = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_pos(rq);
+		__entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_sectors(rq);
+		__entry->bytes     = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					blk_rq_bytes(rq) : 0;
 
 		blk_fill_rwbs_rq(__entry->rwbs, rq);
 		blk_dump_cmd(__get_str(cmd), rq);
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
new file mode 100644
index 000000000000..f345f66ae9d1
--- /dev/null
+++ b/include/trace/events/writeback.h
@@ -0,0 +1,159 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM writeback
+
+#if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WRITEBACK_H
+
+#include <linux/backing-dev.h>
+#include <linux/device.h>
+#include <linux/writeback.h>
+
+struct wb_writeback_work;
+
+DECLARE_EVENT_CLASS(writeback_work_class,
+	TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work),
+	TP_ARGS(bdi, work),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(long, nr_pages)
+		__field(dev_t, sb_dev)
+		__field(int, sync_mode)
+		__field(int, for_kupdate)
+		__field(int, range_cyclic)
+		__field(int, for_background)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->nr_pages = work->nr_pages;
+		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
+		__entry->sync_mode = work->sync_mode;
+		__entry->for_kupdate = work->for_kupdate;
+		__entry->range_cyclic = work->range_cyclic;
+		__entry->for_background	= work->for_background;
+	),
+	TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
+		  "kupdate=%d range_cyclic=%d background=%d",
+		  __entry->name,
+		  MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
+		  __entry->nr_pages,
+		  __entry->sync_mode,
+		  __entry->for_kupdate,
+		  __entry->range_cyclic,
+		  __entry->for_background
+	)
+);
+#define DEFINE_WRITEBACK_WORK_EVENT(name) \
+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);
+
+TRACE_EVENT(writeback_pages_written,
+	TP_PROTO(long pages_written),
+	TP_ARGS(pages_written),
+	TP_STRUCT__entry(
+		__field(long,		pages)
+	),
+	TP_fast_assign(
+		__entry->pages		= pages_written;
+	),
+	TP_printk("%ld", __entry->pages)
+);
+
+DECLARE_EVENT_CLASS(writeback_class,
+	TP_PROTO(struct backing_dev_info *bdi),
+	TP_ARGS(bdi),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+	),
+	TP_printk("bdi %s",
+		  __entry->name
+	)
+);
+#define DEFINE_WRITEBACK_EVENT(name) \
+DEFINE_EVENT(writeback_class, name, \
+	TP_PROTO(struct backing_dev_info *bdi), \
+	TP_ARGS(bdi))
+
+DEFINE_WRITEBACK_EVENT(writeback_nowork);
+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),
+	TP_ARGS(wbc, bdi),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(long, nr_to_write)
+		__field(long, pages_skipped)
+		__field(int, sync_mode)
+		__field(int, nonblocking)
+		__field(int, encountered_congestion)
+		__field(int, for_kupdate)
+		__field(int, for_background)
+		__field(int, for_reclaim)
+		__field(int, range_cyclic)
+		__field(int, more_io)
+		__field(unsigned long, older_than_this)
+		__field(long, range_start)
+		__field(long, range_end)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->nr_to_write	= wbc->nr_to_write;
+		__entry->pages_skipped	= wbc->pages_skipped;
+		__entry->sync_mode	= wbc->sync_mode;
+		__entry->for_kupdate	= wbc->for_kupdate;
+		__entry->for_background	= wbc->for_background;
+		__entry->for_reclaim	= wbc->for_reclaim;
+		__entry->range_cyclic	= wbc->range_cyclic;
+		__entry->more_io	= wbc->more_io;
+		__entry->older_than_this = wbc->older_than_this ?
+						*wbc->older_than_this : 0;
+		__entry->range_start	= (long)wbc->range_start;
+		__entry->range_end	= (long)wbc->range_end;
+	),
+
+	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
+		"bgrd=%d reclm=%d cyclic=%d more=%d older=0x%lx "
+		"start=0x%lx end=0x%lx",
+		__entry->name,
+		__entry->nr_to_write,
+		__entry->pages_skipped,
+		__entry->sync_mode,
+		__entry->for_kupdate,
+		__entry->for_background,
+		__entry->for_reclaim,
+		__entry->range_cyclic,
+		__entry->more_io,
+		__entry->older_than_this,
+		__entry->range_start,
+		__entry->range_end)
+)
+
+#define DEFINE_WBC_EVENT(name) \
+DEFINE_EVENT(wbc_class, name, \
+	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \
+	TP_ARGS(wbc, bdi))
+DEFINE_WBC_EVENT(wbc_writeback_start);
+DEFINE_WBC_EVENT(wbc_writeback_written);
+DEFINE_WBC_EVENT(wbc_writeback_wait);
+DEFINE_WBC_EVENT(wbc_balance_dirty_start);
+DEFINE_WBC_EVENT(wbc_balance_dirty_written);
+DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
+DEFINE_WBC_EVENT(wbc_writepage);
+
+#endif /* _TRACE_WRITEBACK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>