Merge branch 'linus' into x86/memory-corruption-check

include/linux/Kbuild

@@ -126,6 +126,7 @@ header-y += pci_regs.h
 header-y += pfkeyv2.h
 header-y += pg.h
 header-y += phantom.h
+header-y += phonet.h
 header-y += pkt_cls.h
 header-y += pkt_sched.h
 header-y += posix_types.h
@@ -180,6 +181,7 @@ 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
@@ -232,6 +234,7 @@ unifdef-y += if_fddi.h
 unifdef-y += if_frad.h
 unifdef-y += if_ltalk.h
 unifdef-y += if_link.h
+unifdef-y += if_phonet.h
 unifdef-y += if_pppol2tp.h
 unifdef-y += if_pppox.h
 unifdef-y += if_tr.h

include/linux/ata.h

@@ -30,6 +30,7 @@
 #define __LINUX_ATA_H__
 
 #include <linux/types.h>
+#include <asm/byteorder.h>
 
 /* defines only for the constants which don't work well as enums */
 #define ATA_DMA_BOUNDARY	0xffffUL
@@ -88,6 +89,7 @@ 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,
@@ -557,6 +559,15 @@ static inline int ata_id_has_flush(const u16 *id)
 	return id[ATA_ID_COMMAND_SET_2] & (1 << 12);
 }
 
+static inline int ata_id_flush_enabled(const u16 *id)
+{
+	if (ata_id_has_flush(id) == 0)
+		return 0;
+	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
+		return 0;
+	return id[ATA_ID_CFS_ENABLE_2] & (1 << 12);
+}
+
 static inline int ata_id_has_flush_ext(const u16 *id)
 {
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
@@ -564,6 +575,19 @@ static inline int ata_id_has_flush_ext(const u16 *id)
 	return id[ATA_ID_COMMAND_SET_2] & (1 << 13);
 }
 
+static inline int ata_id_flush_ext_enabled(const u16 *id)
+{
+	if (ata_id_has_flush_ext(id) == 0)
+		return 0;
+	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
+		return 0;
+	/*
+	 * some Maxtor disks have bit 13 defined incorrectly
+	 * so check bit 10 too
+	 */
+	return (id[ATA_ID_CFS_ENABLE_2] & 0x2400) == 0x2400;
+}
+
 static inline int ata_id_has_lba48(const u16 *id)
 {
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
@@ -573,6 +597,15 @@ static inline int ata_id_has_lba48(const u16 *id)
 	return id[ATA_ID_COMMAND_SET_2] & (1 << 10);
 }
 
+static inline int ata_id_lba48_enabled(const u16 *id)
+{
+	if (ata_id_has_lba48(id) == 0)
+		return 0;
+	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
+		return 0;
+	return id[ATA_ID_CFS_ENABLE_2] & (1 << 10);
+}
+
 static inline int ata_id_hpa_enabled(const u16 *id)
 {
 	/* Yes children, word 83 valid bits cover word 82 data */
@@ -644,7 +677,15 @@ static inline unsigned int ata_id_major_version(const u16 *id)
 
 static inline int ata_id_is_sata(const u16 *id)
 {
-	return ata_id_major_version(id) >= 5 && id[ATA_ID_HW_CONFIG] == 0;
+	/*
+	 * See if word 93 is 0 AND drive is at least ATA-5 compatible
+	 * verifying that word 80 by casting it to a signed type --
+	 * this trick allows us to filter out the reserved values of
+	 * 0x0000 and 0xffff along with the earlier ATA revisions...
+	 */
+	if (id[ATA_ID_HW_CONFIG] == 0 && (short)id[ATA_ID_MAJOR_VER] >= 0x0020)
+		return 1;
+	return 0;
 }
 
 static inline int ata_id_has_tpm(const u16 *id)
@@ -667,6 +708,15 @@ static inline int ata_id_has_dword_io(const u16 *id)
 	return 0;
 }
 
+static inline int ata_id_has_unload(const u16 *id)
+{
+	if (ata_id_major_version(id) >= 7 &&
+	    (id[ATA_ID_CFSSE] & 0xC000) == 0x4000 &&
+	    id[ATA_ID_CFSSE] & (1 << 13))
+		return 1;
+	return 0;
+}
+
 static inline int ata_id_current_chs_valid(const u16 *id)
 {
 	/* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command
@@ -691,6 +741,11 @@ 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))
@@ -727,6 +782,76 @@ static inline int atapi_id_dmadir(const u16 *dev_id)
 	return ata_id_major_version(dev_id) >= 7 && (dev_id[62] & 0x8000);
 }
 
+/*
+ * ata_id_is_lba_capacity_ok() performs a sanity check on
+ * the claimed LBA capacity value for the device.
+ *
+ * Returns 1 if LBA capacity looks sensible, 0 otherwise.
+ *
+ * It is called only once for each device.
+ */
+static inline int ata_id_is_lba_capacity_ok(u16 *id)
+{
+	unsigned long lba_sects, chs_sects, head, tail;
+
+	/* No non-LBA info .. so valid! */
+	if (id[ATA_ID_CYLS] == 0)
+		return 1;
+
+	lba_sects = ata_id_u32(id, ATA_ID_LBA_CAPACITY);
+
+	/*
+	 * The ATA spec tells large drives to return
+	 * C/H/S = 16383/16/63 independent of their size.
+	 * Some drives can be jumpered to use 15 heads instead of 16.
+	 * Some drives can be jumpered to use 4092 cyls instead of 16383.
+	 */
+	if ((id[ATA_ID_CYLS] == 16383 ||
+	     (id[ATA_ID_CYLS] == 4092 && id[ATA_ID_CUR_CYLS] == 16383)) &&
+	    id[ATA_ID_SECTORS] == 63 &&
+	    (id[ATA_ID_HEADS] == 15 || id[ATA_ID_HEADS] == 16) &&
+	    (lba_sects >= 16383 * 63 * id[ATA_ID_HEADS]))
+		return 1;
+
+	chs_sects = id[ATA_ID_CYLS] * id[ATA_ID_HEADS] * id[ATA_ID_SECTORS];
+
+	/* perform a rough sanity check on lba_sects: within 10% is OK */
+	if (lba_sects - chs_sects < chs_sects/10)
+		return 1;
+
+	/* some drives have the word order reversed */
+	head = (lba_sects >> 16) & 0xffff;
+	tail = lba_sects & 0xffff;
+	lba_sects = head | (tail << 16);
+
+	if (lba_sects - chs_sects < chs_sects/10) {
+		*(__le32 *)&id[ATA_ID_LBA_CAPACITY] = __cpu_to_le32(lba_sects);
+		return 1;	/* LBA capacity is (now) good */
+	}
+
+	return 0;	/* LBA capacity value may be bad */
+}
+
+static inline void ata_id_to_hd_driveid(u16 *id)
+{
+#ifdef __BIG_ENDIAN
+	/* accessed in struct hd_driveid as 8-bit values */
+	id[ATA_ID_MAX_MULTSECT]	 = __cpu_to_le16(id[ATA_ID_MAX_MULTSECT]);
+	id[ATA_ID_CAPABILITY]	 = __cpu_to_le16(id[ATA_ID_CAPABILITY]);
+	id[ATA_ID_OLD_PIO_MODES] = __cpu_to_le16(id[ATA_ID_OLD_PIO_MODES]);
+	id[ATA_ID_OLD_DMA_MODES] = __cpu_to_le16(id[ATA_ID_OLD_DMA_MODES]);
+	id[ATA_ID_MULTSECT]	 = __cpu_to_le16(id[ATA_ID_MULTSECT]);
+
+	/* as 32-bit values */
+	*(u32 *)&id[ATA_ID_LBA_CAPACITY] = ata_id_u32(id, ATA_ID_LBA_CAPACITY);
+	*(u32 *)&id[ATA_ID_SPG]		 = ata_id_u32(id, ATA_ID_SPG);
+
+	/* as 64-bit value */
+	*(u64 *)&id[ATA_ID_LBA_CAPACITY_2] =
+		ata_id_u64(id, ATA_ID_LBA_CAPACITY_2);
+#endif
+}
+
 static inline int is_multi_taskfile(struct ata_taskfile *tf)
 {
 	return (tf->command == ATA_CMD_READ_MULTI) ||
@@ -745,7 +870,7 @@ static inline int ata_ok(u8 status)
 static inline int lba_28_ok(u64 block, u32 n_block)
 {
 	/* check the ending block number */
-	return ((block + n_block - 1) < ((u64)1 << 28)) && (n_block <= 256);
+	return ((block + n_block) < ((u64)1 << 28)) && (n_block <= 256);
 }
 
 static inline int lba_48_ok(u64 block, u32 n_block)

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);
@@ -359,14 +350,24 @@ 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.
@@ -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);

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 **);
@@ -837,14 +887,22 @@ 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
 */
 extern int blk_verify_command(struct blk_cmd_filter *filter,
 			      unsigned char *cmd, int has_write_perm);
-extern int blk_register_filter(struct gendisk *disk);
-extern void blk_unregister_filter(struct gendisk *disk);
 extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define MAX_PHYS_SEGMENTS 128
@@ -876,6 +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)
 {
@@ -902,7 +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) \
@@ -947,49 +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)
@@ -1006,7 +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);

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);

include/linux/cnt32_to_63.h

@@ -0,0 +1,80 @@
+/*
+ *  Extend a 32-bit counter to 63 bits
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	December 3, 2006
+ *  Copyright:	MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_CNT32_TO_63_H__
+#define __LINUX_CNT32_TO_63_H__
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* this is used only to give gcc a clue about good code generation */
+union cnt32_to_63 {
+	struct {
+#if defined(__LITTLE_ENDIAN)
+		u32 lo, hi;
+#elif defined(__BIG_ENDIAN)
+		u32 hi, lo;
+#endif
+	};
+	u64 val;
+};
+
+
+/**
+ * cnt32_to_63 - Expand a 32-bit counter to a 63-bit counter
+ * @cnt_lo: The low part of the counter
+ *
+ * Many hardware clock counters are only 32 bits wide and therefore have
+ * a relatively short period making wrap-arounds rather frequent.  This
+ * is a problem when implementing sched_clock() for example, where a 64-bit
+ * non-wrapping monotonic value is expected to be returned.
+ *
+ * To overcome that limitation, let's extend a 32-bit counter to 63 bits
+ * in a completely lock free fashion. Bits 0 to 31 of the clock are provided
+ * by the hardware while bits 32 to 62 are stored in memory.  The top bit in
+ * memory is used to synchronize with the hardware clock half-period.  When
+ * the top bit of both counters (hardware and in memory) differ then the
+ * memory is updated with a new value, incrementing it when the hardware
+ * counter wraps around.
+ *
+ * Because a word store in memory is atomic then the incremented value will
+ * always be in synch with the top bit indicating to any potential concurrent
+ * reader if the value in memory is up to date or not with regards to the
+ * needed increment.  And any race in updating the value in memory is harmless
+ * as the same value would simply be stored more than once.
+ *
+ * The only restriction for the algorithm to work properly is that this
+ * code must be executed at least once per each half period of the 32-bit
+ * counter to properly update the state bit in memory. This is usually not a
+ * problem in practice, but if it is then a kernel timer could be scheduled
+ * to manage for this code to be executed often enough.
+ *
+ * Note that the top bit (bit 63) in the returned value should be considered
+ * as garbage.  It is not cleared here because callers are likely to use a
+ * multiplier on the returned value which can get rid of the top bit
+ * implicitly by making the multiplier even, therefore saving on a runtime
+ * clear-bit instruction. Otherwise caller must remember to clear the top
+ * bit explicitly.
+ */
+#define cnt32_to_63(cnt_lo) \
+({ \
+	static volatile u32 __m_cnt_hi; \
+	union cnt32_to_63 __x; \
+	__x.hi = __m_cnt_hi; \
+	__x.lo = (cnt_lo); \
+	if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \
+		__m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \
+	__x.val; \
+})
+
+#endif

include/linux/compiler.h

@@ -190,7 +190,9 @@ extern void __chk_io_ptr(const volatile void __iomem *);
  * ACCESS_ONCE() in different C statements.
  *
  * This macro does absolutely -nothing- to prevent the CPU from reordering,
- * merging, or refetching absolutely anything at any time.
+ * merging, or refetching absolutely anything at any time.  Its main intended
+ * use is to mediate communication between process-level code and irq/NMI
+ * handlers, all running on the same CPU.
  */
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 

include/linux/completion.h

@@ -10,6 +10,18 @@
 
 #include <linux/wait.h>
 
+/**
+ * struct completion - structure used to maintain state for a "completion"
+ *
+ * This is the opaque structure used to maintain the state for a "completion".
+ * Completions currently use a FIFO to queue threads that have to wait for
+ * the "completion" event.
+ *
+ * See also:  complete(), wait_for_completion() (and friends _timeout,
+ * _interruptible, _interruptible_timeout, and _killable), init_completion(),
+ * and macros DECLARE_COMPLETION(), DECLARE_COMPLETION_ONSTACK(), and
+ * INIT_COMPLETION().
+ */
 struct completion {
 	unsigned int done;
 	wait_queue_head_t wait;
@@ -21,6 +33,14 @@ struct completion {
 #define COMPLETION_INITIALIZER_ONSTACK(work) \
 	({ init_completion(&work); work; })
 
+/**
+ * DECLARE_COMPLETION: - declare and initialize a completion structure
+ * @work:  identifier for the completion structure
+ *
+ * This macro declares and initializes a completion structure. Generally used
+ * for static declarations. You should use the _ONSTACK variant for automatic
+ * variables.
+ */
 #define DECLARE_COMPLETION(work) \
 	struct completion work = COMPLETION_INITIALIZER(work)
 
@@ -29,6 +49,13 @@ struct completion {
  * completions - so we use the _ONSTACK() variant for those that
  * are on the kernel stack:
  */
+/**
+ * DECLARE_COMPLETION_ONSTACK: - declare and initialize a completion structure
+ * @work:  identifier for the completion structure
+ *
+ * This macro declares and initializes a completion structure on the kernel
+ * stack.
+ */
 #ifdef CONFIG_LOCKDEP
 # define DECLARE_COMPLETION_ONSTACK(work) \
 	struct completion work = COMPLETION_INITIALIZER_ONSTACK(work)
@@ -36,6 +63,13 @@ struct completion {
 # define DECLARE_COMPLETION_ONSTACK(work) DECLARE_COMPLETION(work)
 #endif
 
+/**
+ * init_completion: - Initialize a dynamically allocated completion
+ * @x:  completion structure that is to be initialized
+ *
+ * This inline function will initialize a dynamically created completion
+ * structure.
+ */
 static inline void init_completion(struct completion *x)
 {
 	x->done = 0;
@@ -55,6 +89,13 @@ extern bool completion_done(struct completion *x);
 extern void complete(struct completion *);
 extern void complete_all(struct completion *);
 
+/**
+ * INIT_COMPLETION: - reinitialize a completion structure
+ * @x:  completion structure to be reinitialized
+ *
+ * This macro should be used to reinitialize a completion structure so it can
+ * be reused. This is especially important after complete_all() is used.
+ */
 #define INIT_COMPLETION(x)	((x).done = 0)
 
 

include/linux/cpu.h

@@ -69,6 +69,7 @@ static inline void unregister_cpu_notifier(struct notifier_block *nb)
 #endif
 
 int cpu_up(unsigned int cpu);
+void notify_cpu_starting(unsigned int cpu);
 extern void cpu_hotplug_init(void);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);

include/linux/cpufreq.h

@@ -187,7 +187,8 @@ extern int __cpufreq_driver_target(struct cpufreq_policy *policy,
 				   unsigned int relation);
 
 
-extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy);
+extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy,
+				   unsigned int cpu);
 
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
@@ -226,7 +227,9 @@ struct cpufreq_driver {
 	unsigned int	(*get)	(unsigned int cpu);
 
 	/* optional */
-	unsigned int (*getavg)	(unsigned int cpu);
+	unsigned int (*getavg)	(struct cpufreq_policy *policy,
+				 unsigned int cpu);
+
 	int	(*exit)		(struct cpufreq_policy *policy);
 	int	(*suspend)	(struct cpufreq_policy *policy, pm_message_t pmsg);
 	int	(*resume)	(struct cpufreq_policy *policy);

include/linux/crypto.h

@@ -38,6 +38,7 @@
 #define CRYPTO_ALG_TYPE_DIGEST		0x00000008
 #define CRYPTO_ALG_TYPE_HASH		0x00000009
 #define CRYPTO_ALG_TYPE_AHASH		0x0000000a
+#define CRYPTO_ALG_TYPE_RNG		0x0000000c
 
 #define CRYPTO_ALG_TYPE_HASH_MASK	0x0000000e
 #define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000c
@@ -60,6 +61,14 @@
  */
 #define CRYPTO_ALG_GENIV		0x00000200
 
+/*
+ * Set if the algorithm has passed automated run-time testing.  Note that
+ * if there is no run-time testing for a given algorithm it is considered
+ * to have passed.
+ */
+
+#define CRYPTO_ALG_TESTED		0x00000400
+
 /*
  * Transform masks and values (for crt_flags).
  */
@@ -105,6 +114,7 @@ struct crypto_aead;
 struct crypto_blkcipher;
 struct crypto_hash;
 struct crypto_ahash;
+struct crypto_rng;
 struct crypto_tfm;
 struct crypto_type;
 struct aead_givcrypt_request;
@@ -290,6 +300,15 @@ struct compress_alg {
 			      unsigned int slen, u8 *dst, unsigned int *dlen);
 };
 
+struct rng_alg {
+	int (*rng_make_random)(struct crypto_rng *tfm, u8 *rdata,
+			       unsigned int dlen);
+	int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen);
+
+	unsigned int seedsize;
+};
+
+
 #define cra_ablkcipher	cra_u.ablkcipher
 #define cra_aead	cra_u.aead
 #define cra_blkcipher	cra_u.blkcipher
@@ -298,6 +317,7 @@ struct compress_alg {
 #define cra_hash	cra_u.hash
 #define cra_ahash	cra_u.ahash
 #define cra_compress	cra_u.compress
+#define cra_rng		cra_u.rng
 
 struct crypto_alg {
 	struct list_head cra_list;
@@ -325,6 +345,7 @@ struct crypto_alg {
 		struct hash_alg hash;
 		struct ahash_alg ahash;
 		struct compress_alg compress;
+		struct rng_alg rng;
 	} cra_u;
 
 	int (*cra_init)(struct crypto_tfm *tfm);
@@ -430,6 +451,12 @@ struct compress_tfm {
 	                      u8 *dst, unsigned int *dlen);
 };
 
+struct rng_tfm {
+	int (*rng_gen_random)(struct crypto_rng *tfm, u8 *rdata,
+			      unsigned int dlen);
+	int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen);
+};
+
 #define crt_ablkcipher	crt_u.ablkcipher
 #define crt_aead	crt_u.aead
 #define crt_blkcipher	crt_u.blkcipher
@@ -437,6 +464,7 @@ struct compress_tfm {
 #define crt_hash	crt_u.hash
 #define crt_ahash	crt_u.ahash
 #define crt_compress	crt_u.compress
+#define crt_rng		crt_u.rng
 
 struct crypto_tfm {
 
@@ -450,6 +478,7 @@ struct crypto_tfm {
 		struct hash_tfm hash;
 		struct ahash_tfm ahash;
 		struct compress_tfm compress;
+		struct rng_tfm rng;
 	} crt_u;
 	
 	struct crypto_alg *__crt_alg;
@@ -481,6 +510,10 @@ struct crypto_hash {
 	struct crypto_tfm base;
 };
 
+struct crypto_rng {
+	struct crypto_tfm base;
+};
+
 enum {
 	CRYPTOA_UNSPEC,
 	CRYPTOA_ALG,
@@ -515,6 +548,8 @@ struct crypto_tfm *crypto_alloc_tfm(const char *alg_name, u32 tfm_flags);
 struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask);
 void crypto_free_tfm(struct crypto_tfm *tfm);
 
+int alg_test(const char *driver, const char *alg, u32 type, u32 mask);
+
 /*
  * Transform helpers which query the underlying algorithm.
  */

include/linux/device-mapper.h

@@ -13,7 +13,6 @@
 
 struct dm_target;
 struct dm_table;
-struct dm_dev;
 struct mapped_device;
 struct bio_vec;
 
@@ -84,6 +83,12 @@ void dm_error(const char *message);
  */
 void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev);
 
+struct dm_dev {
+	struct block_device *bdev;
+	int mode;
+	char name[16];
+};
+
 /*
  * Constructors should call these functions to ensure destination devices
  * are opened/closed correctly.
@@ -202,6 +207,7 @@ int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid);
 struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct mapped_device *md);
 int dm_noflush_suspending(struct dm_target *ti);
+union map_info *dm_get_mapinfo(struct bio *bio);
 
 /*
  * Geometry functions.
@@ -231,6 +237,11 @@ int dm_table_add_target(struct dm_table *t, const char *type,
  */
 int dm_table_complete(struct dm_table *t);
 
+/*
+ * Unplug all devices in a table.
+ */
+void dm_table_unplug_all(struct dm_table *t);
+
 /*
  * Table reference counting.
  */
@@ -256,6 +267,11 @@ void dm_table_event(struct dm_table *t);
  */
 int dm_swap_table(struct mapped_device *md, struct dm_table *t);
 
+/*
+ * A wrapper around vmalloc.
+ */
+void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
+
 /*-----------------------------------------------------------------
  * Macros.
  *---------------------------------------------------------------*/

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 */

include/linux/dlm.h

@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -65,9 +65,12 @@ struct dlm_lksb {
 	char *	 sb_lvbptr;
 };
 
+/* dlm_new_lockspace() flags */
+
 #define DLM_LSFL_NODIR		0x00000001
 #define DLM_LSFL_TIMEWARN	0x00000002
 #define DLM_LSFL_FS     	0x00000004
+#define DLM_LSFL_NEWEXCL     	0x00000008
 
 #ifdef __KERNEL__
 

include/linux/dlm_device.h

@@ -26,7 +26,7 @@
 /* Version of the device interface */
 #define DLM_DEVICE_VERSION_MAJOR 6
 #define DLM_DEVICE_VERSION_MINOR 0
-#define DLM_DEVICE_VERSION_PATCH 0
+#define DLM_DEVICE_VERSION_PATCH 1
 
 /* struct passed to the lock write */
 struct dlm_lock_params {

include/linux/dma-mapping.h

@@ -48,6 +48,11 @@ static inline int is_device_dma_capable(struct device *dev)
 	return dev->dma_mask != NULL && *dev->dma_mask != DMA_MASK_NONE;
 }
 
+static inline int is_buffer_dma_capable(u64 mask, dma_addr_t addr, size_t size)
+{
+	return addr + size <= mask;
+}
+
 #ifdef CONFIG_HAS_DMA
 #include <asm/dma-mapping.h>
 #else
@@ -58,6 +63,13 @@ static inline int is_device_dma_capable(struct device *dev)
 #define dma_sync_single		dma_sync_single_for_cpu
 #define dma_sync_sg		dma_sync_sg_for_cpu
 
+static inline u64 dma_get_mask(struct device *dev)
+{
+	if (dev && dev->dma_mask && *dev->dma_mask)
+		return *dev->dma_mask;
+	return DMA_32BIT_MASK;
+}
+
 extern u64 dma_get_required_mask(struct device *dev);
 
 static inline unsigned int dma_get_max_seg_size(struct device *dev)

include/linux/dmar.h

@@ -25,9 +25,99 @@
 #include <linux/types.h>
 #include <linux/msi.h>
 
-#ifdef CONFIG_DMAR
+#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
 struct intel_iommu;
 
+struct dmar_drhd_unit {
+	struct list_head list;		/* list of drhd units	*/
+	struct  acpi_dmar_header *hdr;	/* ACPI header		*/
+	u64	reg_base_addr;		/* register base address*/
+	struct	pci_dev **devices; 	/* target device array	*/
+	int	devices_cnt;		/* target device count	*/
+	u8	ignored:1; 		/* ignore drhd		*/
+	u8	include_all:1;
+	struct intel_iommu *iommu;
+};
+
+extern struct list_head dmar_drhd_units;
+
+#define for_each_drhd_unit(drhd) \
+	list_for_each_entry(drhd, &dmar_drhd_units, list)
+
+extern int dmar_table_init(void);
+extern int early_dmar_detect(void);
+extern int dmar_dev_scope_init(void);
+
+/* Intel IOMMU detection */
+extern void detect_intel_iommu(void);
+
+
+extern int parse_ioapics_under_ir(void);
+extern int alloc_iommu(struct dmar_drhd_unit *);
+#else
+static inline void detect_intel_iommu(void)
+{
+	return;
+}
+
+static inline int dmar_table_init(void)
+{
+	return -ENODEV;
+}
+#endif /* !CONFIG_DMAR && !CONFIG_INTR_REMAP */
+
+#ifdef CONFIG_INTR_REMAP
+extern int intr_remapping_enabled;
+extern int enable_intr_remapping(int);
+
+struct irte {
+	union {
+		struct {
+			__u64	present 	: 1,
+				fpd		: 1,
+				dst_mode	: 1,
+				redir_hint	: 1,
+				trigger_mode	: 1,
+				dlvry_mode	: 3,
+				avail		: 4,
+				__reserved_1	: 4,
+				vector		: 8,
+				__reserved_2	: 8,
+				dest_id		: 32;
+		};
+		__u64 low;
+	};
+
+	union {
+		struct {
+			__u64	sid		: 16,
+				sq		: 2,
+				svt		: 2,
+				__reserved_3	: 44;
+		};
+		__u64 high;
+	};
+};
+extern int get_irte(int irq, struct irte *entry);
+extern int modify_irte(int irq, struct irte *irte_modified);
+extern int alloc_irte(struct intel_iommu *iommu, int irq, u16 count);
+extern int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index,
+   			u16 sub_handle);
+extern int map_irq_to_irte_handle(int irq, u16 *sub_handle);
+extern int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index);
+extern int flush_irte(int irq);
+extern int free_irte(int irq);
+
+extern int irq_remapped(int irq);
+extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev);
+extern struct intel_iommu *map_ioapic_to_ir(int apic);
+#else
+#define irq_remapped(irq)		(0)
+#define enable_intr_remapping(mode)	(-1)
+#define intr_remapping_enabled		(0)
+#endif
+
+#ifdef CONFIG_DMAR
 extern const char *dmar_get_fault_reason(u8 fault_reason);
 
 /* Can't use the common MSI interrupt functions
@@ -40,47 +130,30 @@ extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
 extern int arch_setup_dmar_msi(unsigned int irq);
 
-/* Intel IOMMU detection and initialization functions */
-extern void detect_intel_iommu(void);
-extern int intel_iommu_init(void);
-
-extern int dmar_table_init(void);
-extern int early_dmar_detect(void);
-
-extern struct list_head dmar_drhd_units;
+extern int iommu_detected, no_iommu;
 extern struct list_head dmar_rmrr_units;
-
-struct dmar_drhd_unit {
-	struct list_head list;		/* list of drhd units	*/
-	u64	reg_base_addr;		/* register base address*/
-	struct	pci_dev **devices; 	/* target device array	*/
-	int	devices_cnt;		/* target device count	*/
-	u8	ignored:1; 		/* ignore drhd		*/
-	u8	include_all:1;
-	struct intel_iommu *iommu;
-};
-
 struct dmar_rmrr_unit {
 	struct list_head list;		/* list of rmrr units	*/
+	struct acpi_dmar_header *hdr;	/* ACPI header		*/
 	u64	base_address;		/* reserved base address*/
 	u64	end_address;		/* reserved end address */
 	struct pci_dev **devices;	/* target devices */
 	int	devices_cnt;		/* target device count */
 };
 
-#define for_each_drhd_unit(drhd) \
-	list_for_each_entry(drhd, &dmar_drhd_units, list)
 #define for_each_rmrr_units(rmrr) \
 	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
+/* Intel DMAR  initialization functions */
+extern int intel_iommu_init(void);
+extern int dmar_disabled;
 #else
-static inline void detect_intel_iommu(void)
-{
-	return;
-}
 static inline int intel_iommu_init(void)
 {
+#ifdef CONFIG_INTR_REMAP
+	return dmar_dev_scope_init();
+#else
 	return -ENODEV;
+#endif
 }
-
 #endif /* !CONFIG_DMAR */
 #endif /* __DMAR_H__ */

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)
 
 /*

include/linux/ext3_fs.h

@@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *);
 extern void ext3_set_inode_flags(struct inode *);
 extern void ext3_get_inode_flags(struct ext3_inode_info *);
 extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		       u64 start, u64 len);
 
 /* ioctl.c */
 extern int ext3_ioctl (struct inode *, struct file *, unsigned int,

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 */