Merge branch 'for-2.6.28' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.28' of git://git.kernel.dk/linux-2.6-block: (132 commits)
  doc/cdrom: Trvial documentation error, file not present
  block_dev: fix kernel-doc in new functions
  block: add some comments around the bio read-write flags
  block: mark bio_split_pool static
  block: Find bio sector offset given idx and offset
  block: gendisk integrity wrapper
  block: Switch blk_integrity_compare from bdev to gendisk
  block: Fix double put in blk_integrity_unregister
  block: Introduce integrity data ownership flag
  block: revert part of d7533ad0e132f92e75c1b2eb7c26387b25a583c1
  bio.h: Remove unused conditional code
  block: remove end_{queued|dequeued}_request()
  block: change elevator to use __blk_end_request()
  gdrom: change to use __blk_end_request()
  memstick: change to use __blk_end_request()
  virtio_blk: change to use __blk_end_request()
  blktrace: use BLKTRACE_BDEV_SIZE as the name size for setup structure
  block: add lld busy state exporting interface
  block: Fix blk_start_queueing() to not kick a stopped queue
  include blktrace_api.h in headers_install
  ...

13 files changed, 412 insertions, 326 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index b68ec09..31474e8 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -180,6 +180,7 @@ unifdef-y += audit.h
 unifdef-y += auto_fs.h
 unifdef-y += auxvec.h
 unifdef-y += binfmts.h
+unifdef-y += blktrace_api.h
 unifdef-y += capability.h
 unifdef-y += capi.h
 unifdef-y += cciss_ioctl.h
diff --git a/include/linux/ata.h b/include/linux/ata.h
index a26ebd2..be00973 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -88,6 +88,7 @@ enum {
 	ATA_ID_DLF		= 128,
 	ATA_ID_CSFO		= 129,
 	ATA_ID_CFA_POWER	= 160,
+	ATA_ID_ROT_SPEED	= 217,
 	ATA_ID_PIO4		= (1 << 1),
 
 	ATA_ID_SERNO_LEN	= 20,
@@ -700,6 +701,11 @@ static inline int ata_id_is_cfa(const u16 *id)
 	return 0;
 }
 
+static inline int ata_id_is_ssd(const u16 *id)
+{
+	return id[ATA_ID_ROT_SPEED] == 0x01;
+}
+
 static inline int ata_drive_40wire(const u16 *dev_id)
 {
 	if (ata_id_is_sata(dev_id))
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 0933a14..ff5b4cf 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -26,21 +26,8 @@
 
 #ifdef CONFIG_BLOCK
 
-/* Platforms may set this to teach the BIO layer about IOMMU hardware. */
 #include <asm/io.h>
 
-#if defined(BIO_VMERGE_MAX_SIZE) && defined(BIO_VMERGE_BOUNDARY)
-#define BIOVEC_VIRT_START_SIZE(x) (bvec_to_phys(x) & (BIO_VMERGE_BOUNDARY - 1))
-#define BIOVEC_VIRT_OVERSIZE(x)	((x) > BIO_VMERGE_MAX_SIZE)
-#else
-#define BIOVEC_VIRT_START_SIZE(x)	0
-#define BIOVEC_VIRT_OVERSIZE(x)		0
-#endif
-
-#ifndef BIO_VMERGE_BOUNDARY
-#define BIO_VMERGE_BOUNDARY	0
-#endif
-
 #define BIO_DEBUG
 
 #ifdef BIO_DEBUG
@@ -88,25 +75,14 @@ struct bio {
 	/* Number of segments in this BIO after
 	 * physical address coalescing is performed.
 	 */
-	unsigned short		bi_phys_segments;
-
-	/* Number of segments after physical and DMA remapping
-	 * hardware coalescing is performed.
-	 */
-	unsigned short		bi_hw_segments;
+	unsigned int		bi_phys_segments;
 
 	unsigned int		bi_size;	/* residual I/O count */
 
-	/*
-	 * To keep track of the max hw size, we account for the
-	 * sizes of the first and last virtually mergeable segments
-	 * in this bio
-	 */
-	unsigned int		bi_hw_front_size;
-	unsigned int		bi_hw_back_size;
-
 	unsigned int		bi_max_vecs;	/* max bvl_vecs we can hold */
 
+	unsigned int		bi_comp_cpu;	/* completion CPU */
+
 	struct bio_vec		*bi_io_vec;	/* the actual vec list */
 
 	bio_end_io_t		*bi_end_io;
@@ -126,11 +102,14 @@ struct bio {
 #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	/* nr_hw_seg valid */
+#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_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
 
 /*
@@ -144,18 +123,31 @@ struct bio {
 /*
  * bio bi_rw flags
  *
- * bit 0 -- read (not set) or write (set)
+ * bit 0 -- data direction
+ *	If not set, bio is a read from device. If set, it's a write to device.
  * bit 1 -- rw-ahead when set
  * bit 2 -- barrier
+ *	Insert a serialization point in the IO queue, forcing previously
+ *	submitted IO to be completed before this oen is issued.
  * bit 3 -- fail fast, don't want low level driver retries
  * bit 4 -- synchronous I/O hint: the block layer will unplug immediately
+ *	Note that this does NOT indicate that the IO itself is sync, just
+ *	that the block layer will not postpone issue of this IO by plugging.
+ * bit 5 -- metadata request
+ *	Used for tracing to differentiate metadata and data IO. May also
+ *	get some preferential treatment in the IO scheduler
+ * bit 6 -- 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.
  */
-#define BIO_RW		0
-#define BIO_RW_AHEAD	1
+#define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
+#define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
 #define BIO_RW_BARRIER	2
 #define BIO_RW_FAILFAST	3
 #define BIO_RW_SYNC	4
 #define BIO_RW_META	5
+#define BIO_RW_DISCARD	6
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -185,14 +177,15 @@ struct bio {
 #define bio_failfast(bio)	((bio)->bi_rw & (1 << BIO_RW_FAILFAST))
 #define bio_rw_ahead(bio)	((bio)->bi_rw & (1 << BIO_RW_AHEAD))
 #define bio_rw_meta(bio)	((bio)->bi_rw & (1 << BIO_RW_META))
-#define bio_empty_barrier(bio)	(bio_barrier(bio) && !(bio)->bi_size)
+#define bio_discard(bio)	((bio)->bi_rw & (1 << BIO_RW_DISCARD))
+#define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
 
 static inline unsigned int bio_cur_sectors(struct bio *bio)
 {
 	if (bio->bi_vcnt)
 		return bio_iovec(bio)->bv_len >> 9;
-
-	return 0;
+	else /* dataless requests such as discard */
+		return bio->bi_size >> 9;
 }
 
 static inline void *bio_data(struct bio *bio)
@@ -236,8 +229,6 @@ static inline void *bio_data(struct bio *bio)
 	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
 #endif
 
-#define BIOVEC_VIRT_MERGEABLE(vec1, vec2)	\
-	((((bvec_to_phys((vec1)) + (vec1)->bv_len) | bvec_to_phys((vec2))) & (BIO_VMERGE_BOUNDARY - 1)) == 0)
 #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
 	(((addr1) | (mask)) == (((addr2) - 1) | (mask)))
 #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
@@ -319,15 +310,14 @@ struct bio_pair {
 	atomic_t			cnt;
 	int				error;
 };
-extern struct bio_pair *bio_split(struct bio *bi, mempool_t *pool,
-				  int first_sectors);
-extern mempool_t *bio_split_pool;
+extern struct bio_pair *bio_split(struct bio *bi, int first_sectors);
 extern void bio_pair_release(struct bio_pair *dbio);
 
 extern struct bio_set *bioset_create(int, int);
 extern void bioset_free(struct bio_set *);
 
 extern struct bio *bio_alloc(gfp_t, int);
+extern struct bio *bio_kmalloc(gfp_t, int);
 extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
 extern void bio_put(struct bio *);
 extern void bio_free(struct bio *, struct bio_set *);
@@ -335,7 +325,6 @@ extern void bio_free(struct bio *, struct bio_set *);
 extern void bio_endio(struct bio *, int);
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
-extern int bio_hw_segments(struct request_queue *, struct bio *);
 
 extern void __bio_clone(struct bio *, struct bio *);
 extern struct bio *bio_clone(struct bio *, gfp_t);
@@ -346,12 +335,14 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 extern int bio_get_nr_vecs(struct block_device *);
+extern sector_t bio_sector_offset(struct bio *, unsigned short, unsigned int);
 extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
-				unsigned long, unsigned int, int);
+				unsigned long, unsigned int, int, gfp_t);
 struct sg_iovec;
+struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
 				    struct block_device *,
-				    struct sg_iovec *, int, int);
+				    struct sg_iovec *, int, int, gfp_t);
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
@@ -359,15 +350,25 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
 				 gfp_t, int);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
-extern struct bio *bio_copy_user(struct request_queue *, unsigned long, unsigned int, int);
-extern struct bio *bio_copy_user_iov(struct request_queue *, struct sg_iovec *,
-				     int, int);
+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 *,
+				     struct rq_map_data *, struct sg_iovec *,
+				     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 unsigned int bvec_nr_vecs(unsigned short idx);
 
 /*
+ * Allow queuer to specify a completion CPU for this bio
+ */
+static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu)
+{
+	bio->bi_comp_cpu = cpu;
+}
+
+/*
  * 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
@@ -445,6 +446,14 @@ static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
 	__bio_kmap_irq((bio), (bio)->bi_idx, (flags))
 #define bio_kunmap_irq(buf,flags)	__bio_kunmap_irq(buf, flags)
 
+/*
+ * Check whether this bio carries any data or not. A NULL bio is allowed.
+ */
+static inline int bio_has_data(struct bio *bio)
+{
+	return bio && bio->bi_io_vec != NULL;
+}
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
 #define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
@@ -458,14 +467,7 @@ static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
 #define bip_for_each_vec(bvl, bip, i)					\
 	__bip_for_each_vec(bvl, bip, i, (bip)->bip_idx)
 
-static inline int bio_integrity(struct bio *bio)
-{
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-	return bio->bi_integrity != NULL;
-#else
-	return 0;
-#endif
-}
+#define bio_integrity(bio) (bio->bi_integrity != NULL)
 
 extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *);
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 53ea933..a92d9e4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -16,7 +16,9 @@
 #include <linux/bio.h>
 #include <linux/module.h>
 #include <linux/stringify.h>
+#include <linux/gfp.h>
 #include <linux/bsg.h>
+#include <linux/smp.h>
 
 #include <asm/scatterlist.h>
 
@@ -54,7 +56,6 @@ enum rq_cmd_type_bits {
 	REQ_TYPE_PM_SUSPEND,		/* suspend request */
 	REQ_TYPE_PM_RESUME,		/* resume request */
 	REQ_TYPE_PM_SHUTDOWN,		/* shutdown request */
-	REQ_TYPE_FLUSH,			/* flush request */
 	REQ_TYPE_SPECIAL,		/* driver defined type */
 	REQ_TYPE_LINUX_BLOCK,		/* generic block layer message */
 	/*
@@ -76,19 +77,18 @@ enum rq_cmd_type_bits {
  *
  */
 enum {
-	/*
-	 * just examples for now
-	 */
 	REQ_LB_OP_EJECT	= 0x40,		/* eject request */
-	REQ_LB_OP_FLUSH = 0x41,		/* flush device */
+	REQ_LB_OP_FLUSH = 0x41,		/* flush request */
+	REQ_LB_OP_DISCARD = 0x42,	/* discard sectors */
 };
 
 /*
- * request type modified bits. first three bits match BIO_RW* bits, important
+ * request type modified bits. first two bits match BIO_RW* bits, important
  */
 enum rq_flag_bits {
 	__REQ_RW,		/* not set, read. set, write */
 	__REQ_FAILFAST,		/* no low level driver retries */
+	__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 */
@@ -111,6 +111,7 @@ enum rq_flag_bits {
 };
 
 #define REQ_RW		(1 << __REQ_RW)
+#define REQ_DISCARD	(1 << __REQ_DISCARD)
 #define REQ_FAILFAST	(1 << __REQ_FAILFAST)
 #define REQ_SORTED	(1 << __REQ_SORTED)
 #define REQ_SOFTBARRIER	(1 << __REQ_SOFTBARRIER)
@@ -140,12 +141,14 @@ enum rq_flag_bits {
  */
 struct request {
 	struct list_head queuelist;
-	struct list_head donelist;
+	struct call_single_data csd;
+	int cpu;
 
 	struct request_queue *q;
 
 	unsigned int cmd_flags;
 	enum rq_cmd_type_bits cmd_type;
+	unsigned long atomic_flags;
 
 	/* Maintain bio traversal state for part by part I/O submission.
 	 * hard_* are block layer internals, no driver should touch them!
@@ -190,13 +193,6 @@ struct request {
 	 */
 	unsigned short nr_phys_segments;
 
-	/* Number of scatter-gather addr+len pairs after
-	 * physical and DMA remapping hardware coalescing is performed.
-	 * This is the number of scatter-gather entries the driver
-	 * will actually have to deal with after DMA mapping is done.
-	 */
-	unsigned short nr_hw_segments;
-
 	unsigned short ioprio;
 
 	void *special;
@@ -220,6 +216,8 @@ struct request {
 	void *data;
 	void *sense;
 
+	unsigned long deadline;
+	struct list_head timeout_list;
 	unsigned int timeout;
 	int retries;
 
@@ -233,6 +231,11 @@ struct request {
 	struct request *next_rq;
 };
 
+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.
@@ -252,6 +255,7 @@ 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 (unplug_fn) (struct request_queue *);
+typedef int (prepare_discard_fn) (struct request_queue *, struct request *);
 
 struct bio_vec;
 struct bvec_merge_data {
@@ -265,6 +269,15 @@ typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
 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);
+
+enum blk_eh_timer_return {
+	BLK_EH_NOT_HANDLED,
+	BLK_EH_HANDLED,
+	BLK_EH_RESET_TIMER,
+};
+
+typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *);
 
 enum blk_queue_state {
 	Queue_down,
@@ -307,10 +320,13 @@ struct request_queue
 	make_request_fn		*make_request_fn;
 	prep_rq_fn		*prep_rq_fn;
 	unplug_fn		*unplug_fn;
+	prepare_discard_fn	*prepare_discard_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;
+	lld_busy_fn		*lld_busy_fn;
 
 	/*
 	 * Dispatch queue sorting
@@ -385,6 +401,10 @@ struct request_queue
 	unsigned int		nr_sorted;
 	unsigned int		in_flight;
 
+	unsigned int		rq_timeout;
+	struct timer_list	timeout;
+	struct list_head	timeout_list;
+
 	/*
 	 * sg stuff
 	 */
@@ -421,6 +441,10 @@ struct request_queue
 #define QUEUE_FLAG_ELVSWITCH	8	/* don't use elevator, just do FIFO */
 #define QUEUE_FLAG_BIDI		9	/* queue supports bidi requests */
 #define QUEUE_FLAG_NOMERGES    10	/* disable merge attempts */
+#define QUEUE_FLAG_SAME_COMP   11	/* force complete on same CPU */
+#define QUEUE_FLAG_FAIL_IO     12	/* fake timeout */
+#define QUEUE_FLAG_STACKABLE   13	/* supports request stacking */
+#define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
 
 static inline int queue_is_locked(struct request_queue *q)
 {
@@ -526,7 +550,10 @@ enum {
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
+#define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(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_fs_request(rq)	((rq)->cmd_type == REQ_TYPE_FS)
 #define blk_pc_request(rq)	((rq)->cmd_type == REQ_TYPE_BLOCK_PC)
@@ -536,16 +563,18 @@ enum {
 #define blk_noretry_request(rq)	((rq)->cmd_flags & REQ_FAILFAST)
 #define blk_rq_started(rq)	((rq)->cmd_flags & REQ_STARTED)
 
-#define blk_account_rq(rq)	(blk_rq_started(rq) && blk_fs_request(rq))
+#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_pm_request(rq)	\
 	(blk_pm_suspend_request(rq) || blk_pm_resume_request(rq))
 
+#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)
 #define blk_empty_barrier(rq)	(blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
 /* rq->queuelist of dequeued request must be list_empty() */
@@ -592,7 +621,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int rw)
 #define RQ_NOMERGE_FLAGS	\
 	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
 #define rq_mergeable(rq)	\
-	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq)))
+	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
+	 (blk_discard_rq(rq) || blk_fs_request((rq))))
 
 /*
  * q->prep_rq_fn return values
@@ -637,6 +667,12 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
 }
 #endif /* CONFIG_MMU */
 
+struct rq_map_data {
+	struct page **pages;
+	int page_order;
+	int nr_entries;
+};
+
 struct req_iterator {
 	int i;
 	struct bio *bio;
@@ -664,6 +700,10 @@ extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, 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 int blk_rq_check_limits(struct request_queue *q, struct request *rq);
+extern int blk_lld_busy(struct request_queue *q);
+extern int blk_insert_cloned_request(struct request_queue *q,
+				     struct request *rq);
 extern void blk_plug_device(struct request_queue *);
 extern void blk_plug_device_unlocked(struct request_queue *);
 extern int blk_remove_plug(struct request_queue *);
@@ -705,11 +745,14 @@ extern void __blk_stop_queue(struct request_queue *q);
 extern void __blk_run_queue(struct request_queue *);
 extern void blk_run_queue(struct request_queue *);
 extern void blk_start_queueing(struct request_queue *);
-extern int blk_rq_map_user(struct request_queue *, struct request *, void __user *, unsigned long);
+extern int blk_rq_map_user(struct request_queue *, struct request *,
+			   struct rq_map_data *, void __user *, unsigned long,
+			   gfp_t);
 extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct sg_iovec *, int, unsigned int);
+			       struct rq_map_data *, struct sg_iovec *, int,
+			       unsigned int, gfp_t);
 extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
@@ -750,12 +793,15 @@ extern int __blk_end_request(struct request *rq, int error,
 extern int blk_end_bidi_request(struct request *rq, int error,
 				unsigned int nr_bytes, unsigned int bidi_bytes);
 extern void end_request(struct request *, int);
-extern void end_queued_request(struct request *, int);
-extern void end_dequeued_request(struct request *, int);
 extern int blk_end_request_callback(struct request *rq, int error,
 				unsigned int nr_bytes,
 				int (drv_callback)(struct request *));
 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_update_request(struct request *rq, int error,
+			       unsigned int nr_bytes);
 
 /*
  * blk_end_request() takes bytes instead of sectors as a complete size.
@@ -790,12 +836,16 @@ extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
 			       void *buf, unsigned int size);
+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_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);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
+extern void blk_queue_set_discard(struct request_queue *, prepare_discard_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_do_ordered(struct request_queue *, struct request **);
@@ -837,6 +887,16 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 }
 
 extern int blkdev_issue_flush(struct block_device *, sector_t *);
+extern int blkdev_issue_discard(struct block_device *,
+				sector_t sector, sector_t nr_sects, gfp_t);
+
+static inline int sb_issue_discard(struct super_block *sb,
+				   sector_t block, sector_t nr_blocks)
+{
+	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);
+}
 
 /*
 * command filter functions
@@ -874,6 +934,13 @@ static inline int queue_dma_alignment(struct request_queue *q)
 	return q ? q->dma_alignment : 511;
 }
 
+static inline int blk_rq_aligned(struct request_queue *q, void *addr,
+				 unsigned int len)
+{
+	unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
+	return !((unsigned long)addr & alignment) && !(len & alignment);
+}
+
 /* assumes size > 256 */
 static inline unsigned int blksize_bits(unsigned int size)
 {
@@ -900,7 +967,7 @@ static inline void put_dev_sector(Sector p)
 }
 
 struct work_struct;
-int kblockd_schedule_work(struct work_struct *work);
+int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
 void kblockd_flush_work(struct work_struct *work);
 
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
@@ -945,49 +1012,19 @@ struct blk_integrity {
 
 extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
 extern void blk_integrity_unregister(struct gendisk *);
-extern int blk_integrity_compare(struct block_device *, struct block_device *);
+extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request *);
 
-static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
-{
-	if (bi)
-		return bi->tuple_size;
-
-	return 0;
-}
-
-static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
+static inline
+struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
 {
 	return bdev->bd_disk->integrity;
 }
 
-static inline unsigned int bdev_get_tag_size(struct block_device *bdev)
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
-	struct blk_integrity *bi = bdev_get_integrity(bdev);
-
-	if (bi)
-		return bi->tag_size;
-
-	return 0;
-}
-
-static inline int bdev_integrity_enabled(struct block_device *bdev, int rw)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bdev);
-
-	if (bi == NULL)
-		return 0;
-
-	if (rw == READ && bi->verify_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_READ))
-		return 1;
-
-	if (rw == WRITE && bi->generate_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_WRITE))
-		return 1;
-
-	return 0;
+	return disk->integrity;
 }
 
 static inline int blk_integrity_rq(struct request *rq)
@@ -1004,7 +1041,7 @@ static inline int blk_integrity_rq(struct request *rq)
 #define blk_rq_count_integrity_sg(a)		(0)
 #define blk_rq_map_integrity_sg(a, b)		(0)
 #define bdev_get_integrity(a)			(0)
-#define bdev_get_tag_size(a)			(0)
+#define blk_get_integrity(a)			(0)
 #define blk_integrity_compare(a, b)		(0)
 #define blk_integrity_register(a, b)		(0)
 #define blk_integrity_unregister(a)		do { } while (0);
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index d084b8d..3a31eb5 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -1,8 +1,10 @@
 #ifndef BLKTRACE_H
 #define BLKTRACE_H
 
+#ifdef __KERNEL__
 #include <linux/blkdev.h>
 #include <linux/relay.h>
+#endif
 
 /*
  * Trace categories
@@ -21,6 +23,7 @@ enum blktrace_cat {
 	BLK_TC_NOTIFY	= 1 << 10,	/* special message */
 	BLK_TC_AHEAD	= 1 << 11,	/* readahead */
 	BLK_TC_META	= 1 << 12,	/* metadata */
+	BLK_TC_DISCARD	= 1 << 13,	/* discard requests */
 
 	BLK_TC_END	= 1 << 15,	/* only 16-bits, reminder */
 };
@@ -47,6 +50,7 @@ enum blktrace_act {
 	__BLK_TA_SPLIT,			/* bio was split */
 	__BLK_TA_BOUNCE,		/* bio was bounced */
 	__BLK_TA_REMAP,			/* bio was remapped */
+	__BLK_TA_ABORT,			/* request aborted */
 };
 
 /*
@@ -77,6 +81,7 @@ enum blktrace_notify {
 #define BLK_TA_SPLIT		(__BLK_TA_SPLIT)
 #define BLK_TA_BOUNCE		(__BLK_TA_BOUNCE)
 #define BLK_TA_REMAP		(__BLK_TA_REMAP | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_ABORT		(__BLK_TA_ABORT | BLK_TC_ACT(BLK_TC_QUEUE))
 
 #define BLK_TN_PROCESS		(__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY))
 #define BLK_TN_TIMESTAMP	(__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY))
@@ -89,17 +94,17 @@ enum blktrace_notify {
  * The trace itself
  */
 struct blk_io_trace {
-	u32 magic;		/* MAGIC << 8 | version */
-	u32 sequence;		/* event number */
-	u64 time;		/* in microseconds */
-	u64 sector;		/* disk offset */
-	u32 bytes;		/* transfer length */
-	u32 action;		/* what happened */
-	u32 pid;		/* who did it */
-	u32 device;		/* device number */
-	u32 cpu;		/* on what cpu did it happen */
-	u16 error;		/* completion error */
-	u16 pdu_len;		/* length of data after this trace */
+	__u32 magic;		/* MAGIC << 8 | version */
+	__u32 sequence;		/* event number */
+	__u64 time;		/* in microseconds */
+	__u64 sector;		/* disk offset */
+	__u32 bytes;		/* transfer length */
+	__u32 action;		/* what happened */
+	__u32 pid;		/* who did it */
+	__u32 device;		/* device number */
+	__u32 cpu;		/* on what cpu did it happen */
+	__u16 error;		/* completion error */
+	__u16 pdu_len;		/* length of data after this trace */
 };
 
 /*
@@ -117,6 +122,23 @@ enum {
 	Blktrace_stopped,
 };
 
+#define BLKTRACE_BDEV_SIZE	32
+
+/*
+ * User setup structure passed with BLKTRACESTART
+ */
+struct blk_user_trace_setup {
+	char name[BLKTRACE_BDEV_SIZE];	/* output */
+	__u16 act_mask;			/* input */
+	__u32 buf_size;			/* input */
+	__u32 buf_nr;			/* input */
+	__u64 start_lba;
+	__u64 end_lba;
+	__u32 pid;
+};
+
+#ifdef __KERNEL__
+#if defined(CONFIG_BLK_DEV_IO_TRACE)
 struct blk_trace {
 	int trace_state;
 	struct rchan *rchan;
@@ -133,21 +155,6 @@ struct blk_trace {
 	atomic_t dropped;
 };
 
-/*
- * User setup structure passed with BLKTRACESTART
- */
-struct blk_user_trace_setup {
-	char name[BDEVNAME_SIZE];	/* output */
-	u16 act_mask;			/* input */
-	u32 buf_size;			/* input */
-	u32 buf_nr;			/* input */
-	u64 start_lba;
-	u64 end_lba;
-	u32 pid;
-};
-
-#ifdef __KERNEL__
-#if defined(CONFIG_BLK_DEV_IO_TRACE)
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
 extern void __blk_add_trace(struct blk_trace *, sector_t, int, int, u32, int, int, void *);
@@ -195,6 +202,9 @@ static inline void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 	if (likely(!bt))
 		return;
 
+	if (blk_discard_rq(rq))
+		rw |= (1 << BIO_RW_DISCARD);
+
 	if (blk_pc_request(rq)) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
 		__blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors, sizeof(rq->cmd), rq->cmd);
diff --git a/include/linux/device.h b/include/linux/device.h
index 4d8372d..246937c 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -199,6 +199,11 @@ struct class {
 	struct class_private *p;
 };
 
+struct class_dev_iter {
+	struct klist_iter		ki;
+	const struct device_type	*type;
+};
+
 extern struct kobject *sysfs_dev_block_kobj;
 extern struct kobject *sysfs_dev_char_kobj;
 extern int __must_check __class_register(struct class *class,
@@ -213,6 +218,13 @@ extern void class_unregister(struct class *class);
 	__class_register(class, &__key);	\
 })
 
+extern void class_dev_iter_init(struct class_dev_iter *iter,
+				struct class *class,
+				struct device *start,
+				const struct device_type *type);
+extern struct device *class_dev_iter_next(struct class_dev_iter *iter);
+extern void class_dev_iter_exit(struct class_dev_iter *iter);
+
 extern int class_for_each_device(struct class *class, struct device *start,
 				 void *data,
 				 int (*fn)(struct device *dev, void *data));
@@ -396,7 +408,7 @@ struct device {
 	spinlock_t		devres_lock;
 	struct list_head	devres_head;
 
-	struct list_head	node;
+	struct klist_node	knode_class;
 	struct class		*class;
 	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
 	struct attribute_group	**groups;	/* optional groups */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 639624b..92f6f63 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -112,6 +112,7 @@ extern struct request *elv_latter_request(struct request_queue *, struct request
 extern int elv_register_queue(struct request_queue *q);
 extern void elv_unregister_queue(struct request_queue *q);
 extern int elv_may_queue(struct request_queue *, int);
+extern void elv_abort_queue(struct request_queue *);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *, struct request *, gfp_t);
 extern void elv_put_request(struct request_queue *, struct request *);
@@ -173,15 +174,15 @@ enum {
 #define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
 
 /*
- * Hack to reuse the donelist list_head as the fifo time holder while
+ * Hack to reuse the csd.list list_head as the fifo time holder while
  * the request is in the io scheduler. Saves an unsigned long in rq.
  */
-#define rq_fifo_time(rq)	((unsigned long) (rq)->donelist.next)
-#define rq_set_fifo_time(rq,exp)	((rq)->donelist.next = (void *) (exp))
+#define rq_fifo_time(rq)	((unsigned long) (rq)->csd.list.next)
+#define rq_set_fifo_time(rq,exp)	((rq)->csd.list.next = (void *) (exp))
 #define rq_entry_fifo(ptr)	list_entry((ptr), struct request, queuelist)
 #define rq_fifo_clear(rq)	do {		\
 	list_del_init(&(rq)->queuelist);	\
-	INIT_LIST_HEAD(&(rq)->donelist);	\
+	INIT_LIST_HEAD(&(rq)->csd.list);	\
 	} while (0)
 
 /*
diff --git a/include/linux/fd.h b/include/linux/fd.h
index b6bd41d..f5d194a 100644
--- a/include/linux/fd.h
+++ b/include/linux/fd.h
@@ -15,10 +15,16 @@ struct floppy_struct {
 			sect,		/* sectors per track */
 			head,		/* nr of heads */
 			track,		/* nr of tracks */
-			stretch;	/* !=0 means double track steps */
+			stretch;	/* bit 0 !=0 means double track steps */
+					/* bit 1 != 0 means swap sides */
+					/* bits 2..9 give the first sector */
+					/*  number (the LSB is flipped) */
 #define FD_STRETCH 1
 #define FD_SWAPSIDES 2
 #define FD_ZEROBASED 4
+#define FD_SECTBASEMASK 0x3FC
+#define FD_MKSECTBASE(s) (((s) ^ 1) << 2)
+#define FD_SECTBASE(floppy) ((((floppy)->stretch & FD_SECTBASEMASK) >> 2) ^ 1)
 
 	unsigned char	gap,		/* gap1 size */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 580b513..32477e8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -86,7 +86,9 @@ extern int dir_notify_enable;
 #define READ_META	(READ | (1 << BIO_RW_META))
 #define WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNC))
 #define SWRITE_SYNC	(SWRITE | (1 << BIO_RW_SYNC))
-#define WRITE_BARRIER	((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
+#define WRITE_BARRIER	(WRITE | (1 << BIO_RW_BARRIER))
+#define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD)
+#define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER))
 
 #define SEL_IN		1
 #define SEL_OUT		2
@@ -222,6 +224,7 @@ extern int dir_notify_enable;
 #define BLKTRACESTART _IO(0x12,116)
 #define BLKTRACESTOP _IO(0x12,117)
 #define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
@@ -1682,6 +1685,7 @@ extern void chrdev_show(struct seq_file *,off_t);
 
 /* fs/block_dev.c */
 #define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
+#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
 
 #ifdef CONFIG_BLOCK
 #define BLKDEV_MAJOR_HASH_SIZE	255
@@ -1718,6 +1722,9 @@ extern int fs_may_remount_ro(struct super_block *);
  */
 #define bio_data_dir(bio)	((bio)->bi_rw & 1)
 
+extern void check_disk_size_change(struct gendisk *disk,
+				   struct block_device *bdev);
+extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
 extern int __invalidate_device(struct block_device *);
 extern int invalidate_partition(struct gendisk *, int);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index be4f5e5..206cdf9 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -11,12 +11,15 @@
 
 #include <linux/types.h>
 #include <linux/kdev_t.h>
+#include <linux/rcupdate.h>
 
 #ifdef CONFIG_BLOCK
 
-#define kobj_to_dev(k) container_of(k, struct device, kobj)
-#define dev_to_disk(device) container_of(device, struct gendisk, dev)
-#define dev_to_part(device) container_of(device, struct hd_struct, dev)
+#define kobj_to_dev(k)		container_of((k), struct device, kobj)
+#define dev_to_disk(device)	container_of((device), struct gendisk, part0.__dev)
+#define dev_to_part(device)	container_of((device), struct hd_struct, __dev)
+#define disk_to_dev(disk)	(&(disk)->part0.__dev)
+#define part_to_dev(part)	(&((part)->__dev))
 
 extern struct device_type part_type;
 extern struct kobject *block_depr;
@@ -55,6 +58,9 @@ enum {
 	UNIXWARE_PARTITION = 0x63,	/* Same as GNU_HURD and SCO Unix */
 };
 
+#define DISK_MAX_PARTS			256
+#define DISK_NAME_LEN			32
+
 #include <linux/major.h>
 #include <linux/device.h>
 #include <linux/smp.h>
@@ -87,7 +93,7 @@ struct disk_stats {
 struct hd_struct {
 	sector_t start_sect;
 	sector_t nr_sects;
-	struct device dev;
+	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -100,6 +106,7 @@ struct hd_struct {
 #else
 	struct disk_stats dkstats;
 #endif
+	struct rcu_head rcu_head;
 };
 
 #define GENHD_FL_REMOVABLE			1
@@ -108,100 +115,148 @@ struct hd_struct {
 #define GENHD_FL_CD				8
 #define GENHD_FL_UP				16
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	32
-#define GENHD_FL_FAIL				64
+#define GENHD_FL_EXT_DEVT			64 /* allow extended devt */
+
+#define BLK_SCSI_MAX_CMDS	(256)
+#define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
+
+struct blk_scsi_cmd_filter {
+	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
+	unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
+	struct kobject kobj;
+};
+
+struct disk_part_tbl {
+	struct rcu_head rcu_head;
+	int len;
+	struct hd_struct *part[];
+};
 
 struct gendisk {
+	/* major, first_minor and minors are input parameters only,
+	 * don't use directly.  Use disk_devt() and disk_max_parts().
+	 */
 	int major;			/* major number of driver */
 	int first_minor;
 	int minors;                     /* maximum number of minors, =1 for
                                          * disks that can't be partitioned. */
-	char disk_name[32];		/* name of major driver */
-	struct hd_struct **part;	/* [indexed by minor] */
+
+	char disk_name[DISK_NAME_LEN];	/* name of major driver */
+
+	/* Array of pointers to partitions indexed by partno.
+	 * Protected with matching bdev lock but stat and other
+	 * non-critical accesses use RCU.  Always access through
+	 * helpers.
+	 */
+	struct disk_part_tbl *part_tbl;
+	struct hd_struct part0;
+
 	struct block_device_operations *fops;
 	struct request_queue *queue;
 	void *private_data;
-	sector_t capacity;
 
 	int flags;
 	struct device *driverfs_dev;  // FIXME: remove
-	struct device dev;
-	struct kobject *holder_dir;
 	struct kobject *slave_dir;
 
 	struct timer_rand_state *random;
-	int policy;
 
 	atomic_t sync_io;		/* RAID */
-	unsigned long stamp;
-	int in_flight;
-#ifdef	CONFIG_SMP
-	struct disk_stats *dkstats;
-#else
-	struct disk_stats dkstats;
-#endif
 	struct work_struct async_notify;
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct blk_integrity *integrity;
 #endif
+	int node_id;
 };
 
-/* 
- * Macros to operate on percpu disk statistics:
- *
- * The __ variants should only be called in critical sections. The full
- * variants disable/enable preemption.
- */
-static inline struct hd_struct *get_part(struct gendisk *gendiskp,
-					 sector_t sector)
+static inline struct gendisk *part_to_disk(struct hd_struct *part)
 {
-	struct hd_struct *part;
-	int i;
-	for (i = 0; i < gendiskp->minors - 1; i++) {
-		part = gendiskp->part[i];
-		if (part && part->start_sect <= sector
-		    && sector < part->start_sect + part->nr_sects)
-			return part;
+	if (likely(part)) {
+		if (part->partno)
+			return dev_to_disk(part_to_dev(part)->parent);
+		else
+			return dev_to_disk(part_to_dev(part));
 	}
 	return NULL;
 }
 
-#ifdef	CONFIG_SMP
-#define __disk_stat_add(gendiskp, field, addnd) 	\
-	(per_cpu_ptr(gendiskp->dkstats, smp_processor_id())->field += addnd)
+static inline int disk_max_parts(struct gendisk *disk)
+{
+	if (disk->flags & GENHD_FL_EXT_DEVT)
+		return DISK_MAX_PARTS;
+	return disk->minors;
+}
 
-#define disk_stat_read(gendiskp, field)					\
-({									\
-	typeof(gendiskp->dkstats->field) res = 0;			\
-	int i;								\
-	for_each_possible_cpu(i)					\
-		res += per_cpu_ptr(gendiskp->dkstats, i)->field;	\
-	res;								\
-})
+static inline bool disk_partitionable(struct gendisk *disk)
+{
+	return disk_max_parts(disk) > 1;
+}
 
-static inline void disk_stat_set_all(struct gendisk *gendiskp, int value)	{
-	int i;
+static inline dev_t disk_devt(struct gendisk *disk)
+{
+	return disk_to_dev(disk)->devt;
+}
 
-	for_each_possible_cpu(i)
-		memset(per_cpu_ptr(gendiskp->dkstats, i), value,
-				sizeof(struct disk_stats));
-}		
+static inline dev_t part_devt(struct hd_struct *part)
+{
+	return part_to_dev(part)->devt;
+}
 
-#define __part_stat_add(part, field, addnd)				\
-	(per_cpu_ptr(part->dkstats, smp_processor_id())->field += addnd)
+extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno);
 
-#define __all_stat_add(gendiskp, part, field, addnd, sector)	\
-({								\
-	if (part)						\
-		__part_stat_add(part, field, addnd);		\
-	__disk_stat_add(gendiskp, field, addnd);		\
-})
+static inline void disk_put_part(struct hd_struct *part)
+{
+	if (likely(part))
+		put_device(part_to_dev(part));
+}
+
+/*
+ * Smarter partition iterator without context limits.
+ */
+#define DISK_PITER_REVERSE	(1 << 0) /* iterate in the reverse direction */
+#define DISK_PITER_INCL_EMPTY	(1 << 1) /* include 0-sized parts */
+#define DISK_PITER_INCL_PART0	(1 << 2) /* include partition 0 */
+
+struct disk_part_iter {
+	struct gendisk		*disk;
+	struct hd_struct	*part;
+	int			idx;
+	unsigned int		flags;
+};
+
+extern void disk_part_iter_init(struct disk_part_iter *piter,
+				 struct gendisk *disk, unsigned int flags);
+extern struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter);
+extern void disk_part_iter_exit(struct disk_part_iter *piter);
+
+extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk,
+					     sector_t sector);
+
+/*
+ * Macros to operate on percpu disk statistics:
+ *
+ * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters
+ * and should be called between disk_stat_lock() and
+ * disk_stat_unlock().
+ *
+ * part_stat_read() can be called at any time.
+ *
+ * part_stat_{add|set_all}() and {init|free}_part_stats are for
+ * internal use only.
+ */
+#ifdef	CONFIG_SMP
+#define part_stat_lock()	({ rcu_read_lock(); get_cpu(); })
+#define part_stat_unlock()	do { put_cpu(); rcu_read_unlock(); } while (0)
+
+#define __part_stat_add(cpu, part, field, addnd)			\
+	(per_cpu_ptr((part)->dkstats, (cpu))->field += (addnd))
 
 #define part_stat_read(part, field)					\
 ({									\
-	typeof(part->dkstats->field) res = 0;				\
+	typeof((part)->dkstats->field) res = 0;				\
 	int i;								\
 	for_each_possible_cpu(i)					\
-		res += per_cpu_ptr(part->dkstats, i)->field;		\
+		res += per_cpu_ptr((part)->dkstats, i)->field;		\
 	res;								\
 })
 
@@ -213,171 +268,107 @@ static inline void part_stat_set_all(struct hd_struct *part, int value)
 		memset(per_cpu_ptr(part->dkstats, i), value,
 				sizeof(struct disk_stats));
 }
-				
-#else /* !CONFIG_SMP */
-#define __disk_stat_add(gendiskp, field, addnd) \
-				(gendiskp->dkstats.field += addnd)
-#define disk_stat_read(gendiskp, field)	(gendiskp->dkstats.field)
 
-static inline void disk_stat_set_all(struct gendisk *gendiskp, int value)
+static inline int init_part_stats(struct hd_struct *part)
 {
-	memset(&gendiskp->dkstats, value, sizeof (struct disk_stats));
+	part->dkstats = alloc_percpu(struct disk_stats);
+	if (!part->dkstats)
+		return 0;
+	return 1;
 }
 
-#define __part_stat_add(part, field, addnd) \
-	(part->dkstats.field += addnd)
-
-#define __all_stat_add(gendiskp, part, field, addnd, sector)	\
-({								\
-	if (part)						\
-		part->dkstats.field += addnd;			\
-	__disk_stat_add(gendiskp, field, addnd);		\
-})
-
-#define part_stat_read(part, field)	(part->dkstats.field)
-
-static inline void part_stat_set_all(struct hd_struct *part, int value)
+static inline void free_part_stats(struct hd_struct *part)
 {
-	memset(&part->dkstats, value, sizeof(struct disk_stats));
+	free_percpu(part->dkstats);
 }
 
-#endif /* CONFIG_SMP */
+#else /* !CONFIG_SMP */
+#define part_stat_lock()	({ rcu_read_lock(); 0; })
+#define part_stat_unlock()	rcu_read_unlock()
 
-#define disk_stat_add(gendiskp, field, addnd)			\
-	do {							\
-		preempt_disable();				\
-		__disk_stat_add(gendiskp, field, addnd);	\
-		preempt_enable();				\
-	} while (0)
-
-#define __disk_stat_dec(gendiskp, field) __disk_stat_add(gendiskp, field, -1)
-#define disk_stat_dec(gendiskp, field) disk_stat_add(gendiskp, field, -1)
-
-#define __disk_stat_inc(gendiskp, field) __disk_stat_add(gendiskp, field, 1)
-#define disk_stat_inc(gendiskp, field) disk_stat_add(gendiskp, field, 1)
-
-#define __disk_stat_sub(gendiskp, field, subnd) \
-		__disk_stat_add(gendiskp, field, -subnd)
-#define disk_stat_sub(gendiskp, field, subnd) \
-		disk_stat_add(gendiskp, field, -subnd)
-
-#define part_stat_add(gendiskp, field, addnd)		\
-	do {						\
-		preempt_disable();			\
-		__part_stat_add(gendiskp, field, addnd);\
-		preempt_enable();			\
-	} while (0)
-
-#define __part_stat_dec(gendiskp, field) __part_stat_add(gendiskp, field, -1)
-#define part_stat_dec(gendiskp, field) part_stat_add(gendiskp, field, -1)
-
-#define __part_stat_inc(gendiskp, field) __part_stat_add(gendiskp, field, 1)
-#define part_stat_inc(gendiskp, field) part_stat_add(gendiskp, field, 1)
-
-#define __part_stat_sub(gendiskp, field, subnd) \
-		__part_stat_add(gendiskp, field, -subnd)
-#define part_stat_sub(gendiskp, field, subnd) \
-		part_stat_add(gendiskp, field, -subnd)
-
-#define all_stat_add(gendiskp, part, field, addnd, sector)	\
-	do {							\
-		preempt_disable();				\
-		__all_stat_add(gendiskp, part, field, addnd, sector);	\
-		preempt_enable();				\
-	} while (0)
-
-#define __all_stat_dec(gendiskp, field, sector) \
-		__all_stat_add(gendiskp, field, -1, sector)
-#define all_stat_dec(gendiskp, field, sector) \
-		all_stat_add(gendiskp, field, -1, sector)
-
-#define __all_stat_inc(gendiskp, part, field, sector) \
-		__all_stat_add(gendiskp, part, field, 1, sector)
-#define all_stat_inc(gendiskp, part, field, sector) \
-		all_stat_add(gendiskp, part, field, 1, sector)
-
-#define __all_stat_sub(gendiskp, part, field, subnd, sector) \
-		__all_stat_add(gendiskp, part, field, -subnd, sector)
-#define all_stat_sub(gendiskp, part, field, subnd, sector) \
-		all_stat_add(gendiskp, part, field, -subnd, sector)
-
-/* Inlines to alloc and free disk stats in struct gendisk */
-#ifdef  CONFIG_SMP
-static inline int init_disk_stats(struct gendisk *disk)
-{
-	disk->dkstats = alloc_percpu(struct disk_stats);
-	if (!disk->dkstats)
-		return 0;
-	return 1;
-}
+#define __part_stat_add(cpu, part, field, addnd)				\
+	((part)->dkstats.field += addnd)
+
+#define part_stat_read(part, field)	((part)->dkstats.field)
 
-static inline void free_disk_stats(struct gendisk *disk)
+static inline void part_stat_set_all(struct hd_struct *part, int value)
 {
-	free_percpu(disk->dkstats);
+	memset(&part->dkstats, value, sizeof(struct disk_stats));
 }
 
 static inline int init_part_stats(struct hd_struct *part)
 {
-	part->dkstats = alloc_percpu(struct disk_stats);
-	if (!part->dkstats)
-		return 0;
 	return 1;
 }
 
 static inline void free_part_stats(struct hd_struct *part)
 {
-	free_percpu(part->dkstats);
-}
-
-#else	/* CONFIG_SMP */
-static inline int init_disk_stats(struct gendisk *disk)
-{
-	return 1;
 }
 
-static inline void free_disk_stats(struct gendisk *disk)
-{
-}
+#endif /* CONFIG_SMP */
 
-static inline int init_part_stats(struct hd_struct *part)
+#define part_stat_add(cpu, part, field, addnd)	do {			\
+	__part_stat_add((cpu), (part), field, addnd);			\
+	if ((part)->partno)						\
+		__part_stat_add((cpu), &part_to_disk((part))->part0,	\
+				field, addnd);				\
+} while (0)
+
+#define part_stat_dec(cpu, gendiskp, field)				\
+	part_stat_add(cpu, gendiskp, field, -1)
+#define part_stat_inc(cpu, gendiskp, field)				\
+	part_stat_add(cpu, gendiskp, field, 1)
+#define part_stat_sub(cpu, gendiskp, field, subnd)			\
+	part_stat_add(cpu, gendiskp, field, -subnd)
+
+static inline void part_inc_in_flight(struct hd_struct *part)
 {
-	return 1;
+	part->in_flight++;
+	if (part->partno)
+		part_to_disk(part)->part0.in_flight++;
 }
 
-static inline void free_part_stats(struct hd_struct *part)
+static inline void part_dec_in_flight(struct hd_struct *part)
 {
+	part->in_flight--;
+	if (part->partno)
+		part_to_disk(part)->part0.in_flight--;
 }
-#endif	/* CONFIG_SMP */
 
 /* drivers/block/ll_rw_blk.c */
-extern void disk_round_stats(struct gendisk *disk);
-extern void part_round_stats(struct hd_struct *part);
+extern void part_round_stats(int cpu, struct hd_struct *part);
 
 /* drivers/block/genhd.c */
 extern int get_blkdev_list(char *, int);
 extern void add_disk(struct gendisk *disk);
 extern void del_gendisk(struct gendisk *gp);
 extern void unlink_gendisk(struct gendisk *gp);
-extern struct gendisk *get_gendisk(dev_t dev, int *part);
+extern struct gendisk *get_gendisk(dev_t dev, int *partno);
+extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
 
 extern void set_device_ro(struct block_device *bdev, int flag);
 extern void set_disk_ro(struct gendisk *disk, int flag);
 
+static inline int get_disk_ro(struct gendisk *disk)
+{
+	return disk->part0.policy;
+}
+
 /* drivers/char/random.c */
 extern void add_disk_randomness(struct gendisk *disk);
 extern void rand_initialize_disk(struct gendisk *disk);
 
 static inline sector_t get_start_sect(struct block_device *bdev)
 {
-	return bdev->bd_contains == bdev ? 0 : bdev->bd_part->start_sect;
+	return bdev->bd_part->start_sect;
 }
 static inline sector_t get_capacity(struct gendisk *disk)
 {
-	return disk->capacity;
+	return disk->part0.nr_sects;
 }
 static inline void set_capacity(struct gendisk *disk, sector_t size)
 {
-	disk->capacity = size;
+	disk->part0.nr_sects = size;
 }
 
 #ifdef CONFIG_SOLARIS_X86_PARTITION
@@ -527,9 +518,12 @@ struct unixware_disklabel {
 #define ADDPART_FLAG_RAID	1
 #define ADDPART_FLAG_WHOLEDISK	2
 
-extern dev_t blk_lookup_devt(const char *name, int part);
-extern char *disk_name (struct gendisk *hd, int part, char *buf);
+extern int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
+extern void blk_free_devt(dev_t devt);
+extern dev_t blk_lookup_devt(const char *name, int partno);
+extern char *disk_name (struct gendisk *hd, int partno, char *buf);
 
+extern int disk_expand_part_tbl(struct gendisk *disk, int target);
 extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev);
 extern int __must_check add_partition(struct gendisk *, int, sector_t, sector_t, int);
 extern void delete_partition(struct gendisk *, int);
@@ -546,16 +540,23 @@ extern void blk_register_region(dev_t devt, unsigned long range,
 			void *data);
 extern void blk_unregister_region(dev_t devt, unsigned long range);
 
-static inline struct block_device *bdget_disk(struct gendisk *disk, int index)
-{
-	return bdget(MKDEV(disk->major, disk->first_minor) + index);
-}
+extern ssize_t part_size_show(struct device *dev,
+			      struct device_attribute *attr, char *buf);
+extern ssize_t part_stat_show(struct device *dev,
+			      struct device_attribute *attr, char *buf);
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+extern ssize_t part_fail_show(struct device *dev,
+			      struct device_attribute *attr, char *buf);
+extern ssize_t part_fail_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count);
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
 
 #else /* CONFIG_BLOCK */
 
 static inline void printk_all_partitions(void) { }
 
-static inline dev_t blk_lookup_devt(const char *name, int part)
+static inline dev_t blk_lookup_devt(const char *name, int partno)
 {
 	dev_t devt = MKDEV(0, 0);
 	return devt;
diff --git a/include/linux/klist.h b/include/linux/klist.h
index 06c338e..8ea98db 100644
--- a/include/linux/klist.h
+++ b/include/linux/klist.h
@@ -38,7 +38,7 @@ extern void klist_init(struct klist *k, void (*get)(struct klist_node *),
 		       void (*put)(struct klist_node *));
 
 struct klist_node {
-	struct klist		*n_klist;
+	void			*n_klist;	/* never access directly */
 	struct list_head	n_node;
 	struct kref		n_ref;
 	struct completion	n_removed;
@@ -57,7 +57,6 @@ extern int klist_node_attached(struct klist_node *n);
 
 struct klist_iter {
 	struct klist		*i_klist;
-	struct list_head	*i_head;
 	struct klist_node	*i_cur;
 };
 
diff --git a/include/linux/major.h b/include/linux/major.h
index 53d5faf..8824945 100644
--- a/include/linux/major.h
+++ b/include/linux/major.h
@@ -170,4 +170,6 @@
 
 #define VIOTAPE_MAJOR		230
 
+#define BLOCK_EXT_MAJOR		259
+
 #endif
diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h
index 310e616..8b4aa05 100644
--- a/include/linux/mtd/blktrans.h
+++ b/include/linux/mtd/blktrans.h
@@ -41,6 +41,8 @@ struct mtd_blktrans_ops {
 		    unsigned long block, char *buffer);
 	int (*writesect)(struct mtd_blktrans_dev *dev,
 		     unsigned long block, char *buffer);
+	int (*discard)(struct mtd_blktrans_dev *dev,
+		       unsigned long block, unsigned nr_blocks);
 
 	/* Block layer ioctls */
 	int (*getgeo)(struct mtd_blktrans_dev *dev, struct hd_geometry *geo);