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

* 'for-linus' of git://git.kernel.dk/linux-2.6-block: (37 commits)
  splice: fix generic_file_splice_read() race with page invalidation
  ramfs: enable splice write
  drivers/block/pktcdvd.c: avoid useless memset
  cdrom: revert commit 22a9189 (cdrom: use kmalloced buffers instead of buffers on stack)
  scsi: sr avoids useless buffer allocation
  block: blk_rq_map_kern uses the bounce buffers for stack buffers
  block: add blk_queue_update_dma_pad
  DAC960: push down BKL
  pktcdvd: push BKL down into driver
  paride: push ioctl down into driver
  block: use get_unaligned_* helpers
  block: extend queue_flag bitops
  block: request_module(): use format string
  Add bvec_merge_data to handle stacked devices and ->merge_bvec()
  block: integrity flags can't use bit ops on unsigned short
  cmdfilter: extend default read filter
  sg: fix odd style (extra parenthesis) introduced by cmd filter patch
  block: add bounce support to blk_rq_map_user_iov
  cfq-iosched: get rid of enable_idle being unused warning
  allow userspace to modify scsi command filter on per device basis
  ...

5 files changed, 301 insertions, 23 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 61c15eaf3fb3..0933a14e6414 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -64,6 +64,7 @@ struct bio_vec {
 
 struct bio_set;
 struct bio;
+struct bio_integrity_payload;
 typedef void (bio_end_io_t) (struct bio *, int);
 typedef void (bio_destructor_t) (struct bio *);
 
@@ -112,6 +113,9 @@ struct bio {
 	atomic_t		bi_cnt;		/* pin count */
 
 	void			*bi_private;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	struct bio_integrity_payload *bi_integrity;  /* data integrity */
+#endif
 
 	bio_destructor_t	*bi_destructor;	/* destructor */
 };
@@ -271,6 +275,29 @@ static inline void *bio_data(struct bio *bio)
  */
 #define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+/*
+ * bio integrity payload
+ */
+struct bio_integrity_payload {
+	struct bio		*bip_bio;	/* parent bio */
+	struct bio_vec		*bip_vec;	/* integrity data vector */
+
+	sector_t		bip_sector;	/* virtual start sector */
+
+	void			*bip_buf;	/* generated integrity data */
+	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
+
+	int			bip_error;	/* saved I/O error */
+	unsigned int		bip_size;
+
+	unsigned short		bip_pool;	/* pool the ivec came from */
+	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
+	unsigned short		bip_idx;	/* current bip_vec index */
+
+	struct work_struct	bip_work;	/* I/O completion */
+};
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 /*
  * A bio_pair is used when we need to split a bio.
@@ -283,10 +310,14 @@ static inline void *bio_data(struct bio *bio)
  *   in bio2.bi_private
  */
 struct bio_pair {
-	struct bio	bio1, bio2;
-	struct bio_vec	bv1, bv2;
-	atomic_t	cnt;
-	int		error;
+	struct bio			bio1, bio2;
+	struct bio_vec			bv1, bv2;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	struct bio_integrity_payload	bip1, bip2;
+	struct bio_vec			iv1, iv2;
+#endif
+	atomic_t			cnt;
+	int				error;
 };
 extern struct bio_pair *bio_split(struct bio *bi, mempool_t *pool,
 				  int first_sectors);
@@ -333,6 +364,39 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, struct sg_iovec *,
 				     int, int);
 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);
+
+/*
+ * bio_set is used to allow other portions of the IO system to
+ * allocate their own private memory pools for bio and iovec structures.
+ * These memory pools in turn all allocate from the bio_slab
+ * and the bvec_slabs[].
+ */
+#define BIO_POOL_SIZE 2
+#define BIOVEC_NR_POOLS 6
+
+struct bio_set {
+	mempool_t *bio_pool;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	mempool_t *bio_integrity_pool;
+#endif
+	mempool_t *bvec_pools[BIOVEC_NR_POOLS];
+};
+
+struct biovec_slab {
+	int nr_vecs;
+	char *name;
+	struct kmem_cache *slab;
+};
+
+extern struct bio_set *fs_bio_set;
+
+/*
+ * a small number of entries is fine, not going to be performance critical.
+ * basically we just need to survive
+ */
+#define BIO_SPLIT_ENTRIES 2
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -381,5 +445,63 @@ 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)
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+#define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
+#define bip_vec(bip)		bip_vec_idx(bip, 0)
+
+#define __bip_for_each_vec(bvl, bip, i, start_idx)			\
+	for (bvl = bip_vec_idx((bip), (start_idx)), i = (start_idx);	\
+	     i < (bip)->bip_vcnt;					\
+	     bvl++, i++)
+
+#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
+}
+
+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);
+extern void bio_integrity_free(struct bio *, struct bio_set *);
+extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
+extern int bio_integrity_enabled(struct bio *bio);
+extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
+extern int bio_integrity_get_tag(struct bio *, void *, unsigned int);
+extern int bio_integrity_prep(struct bio *);
+extern void bio_integrity_endio(struct bio *, int);
+extern void bio_integrity_advance(struct bio *, unsigned int);
+extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
+extern void bio_integrity_split(struct bio *, struct bio_pair *, int);
+extern int bio_integrity_clone(struct bio *, struct bio *, struct bio_set *);
+extern int bioset_integrity_create(struct bio_set *, int);
+extern void bioset_integrity_free(struct bio_set *);
+extern void bio_integrity_init_slab(void);
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+
+#define bio_integrity(a)		(0)
+#define bioset_integrity_create(a, b)	(0)
+#define bio_integrity_prep(a)		(0)
+#define bio_integrity_enabled(a)	(0)
+#define bio_integrity_clone(a, b, c)	(0)
+#define bioset_integrity_free(a)	do { } while (0)
+#define bio_integrity_free(a, b)	do { } while (0)
+#define bio_integrity_endio(a, b)	do { } while (0)
+#define bio_integrity_advance(a, b)	do { } while (0)
+#define bio_integrity_trim(a, b, c)	do { } while (0)
+#define bio_integrity_split(a, b, c)	do { } while (0)
+#define bio_integrity_set_tag(a, b, c)	do { } while (0)
+#define bio_integrity_get_tag(a, b, c)	do { } while (0)
+#define bio_integrity_init_slab(a)	do { } while (0)
+
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
 #endif /* CONFIG_BLOCK */
 #endif /* __LINUX_BIO_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d2a1b71e93c3..1ffd8bfdc4c9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -23,7 +23,6 @@
 struct scsi_ioctl_command;
 
 struct request_queue;
-typedef struct request_queue request_queue_t __deprecated;
 struct elevator_queue;
 typedef struct elevator_queue elevator_t;
 struct request_pm_state;
@@ -34,12 +33,6 @@ struct sg_io_hdr;
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
 
-int put_io_context(struct io_context *ioc);
-void exit_io_context(void);
-struct io_context *get_io_context(gfp_t gfp_flags, int node);
-struct io_context *alloc_io_context(gfp_t gfp_flags, int node);
-void copy_io_context(struct io_context **pdst, struct io_context **psrc);
-
 struct request;
 typedef void (rq_end_io_fn)(struct request *, int);
 
@@ -113,6 +106,7 @@ enum rq_flag_bits {
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_RW_META,		/* metadata io request */
 	__REQ_COPY_USER,	/* contains copies of user pages */
+	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -135,6 +129,7 @@ enum rq_flag_bits {
 #define REQ_ALLOCED	(1 << __REQ_ALLOCED)
 #define REQ_RW_META	(1 << __REQ_RW_META)
 #define REQ_COPY_USER	(1 << __REQ_COPY_USER)
+#define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
 
 #define BLK_MAX_CDB	16
 
@@ -259,7 +254,14 @@ typedef int (prep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unplug_fn) (struct request_queue *);
 
 struct bio_vec;
-typedef int (merge_bvec_fn) (struct request_queue *, struct bio *, struct bio_vec *);
+struct bvec_merge_data {
+	struct block_device *bi_bdev;
+	sector_t bi_sector;
+	unsigned bi_size;
+	unsigned long bi_rw;
+};
+typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
+			     struct bio_vec *);
 typedef void (prepare_flush_fn) (struct request_queue *, struct request *);
 typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);
@@ -426,6 +428,32 @@ static inline void queue_flag_set_unlocked(unsigned int flag,
 	__set_bit(flag, &q->queue_flags);
 }
 
+static inline int queue_flag_test_and_clear(unsigned int flag,
+					    struct request_queue *q)
+{
+	WARN_ON_ONCE(!queue_is_locked(q));
+
+	if (test_bit(flag, &q->queue_flags)) {
+		__clear_bit(flag, &q->queue_flags);
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline int queue_flag_test_and_set(unsigned int flag,
+					  struct request_queue *q)
+{
+	WARN_ON_ONCE(!queue_is_locked(q));
+
+	if (!test_bit(flag, &q->queue_flags)) {
+		__set_bit(flag, &q->queue_flags);
+		return 0;
+	}
+
+	return 1;
+}
+
 static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
 {
 	WARN_ON_ONCE(!queue_is_locked(q));
@@ -676,7 +704,6 @@ extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 				  struct request *, int, rq_end_io_fn *);
-extern int blk_verify_command(unsigned char *, int);
 extern void blk_unplug(struct request_queue *q);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
@@ -749,6 +776,7 @@ extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_hardsect_size(struct request_queue *, unsigned short);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
+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);
@@ -802,6 +830,15 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 
 extern int blkdev_issue_flush(struct block_device *, sector_t *);
 
+/*
+* command filter functions
+*/
+extern int blk_verify_command(struct file *file, unsigned char *cmd);
+extern int blk_cmd_filter_verify_command(struct blk_scsi_cmd_filter *filter,
+					 unsigned char *cmd, mode_t *f_mode);
+extern int blk_register_filter(struct gendisk *disk);
+extern void blk_unregister_filter(struct gendisk *disk);
+
 #define MAX_PHYS_SEGMENTS 128
 #define MAX_HW_SEGMENTS 128
 #define SAFE_MAX_SECTORS 255
@@ -865,28 +902,116 @@ void kblockd_flush_work(struct work_struct *work);
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-*")
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
 
-#else /* CONFIG_BLOCK */
-/*
- * stubs for when the block layer is configured out
- */
-#define buffer_heads_over_limit 0
+#define INTEGRITY_FLAG_READ	2	/* verify data integrity on read */
+#define INTEGRITY_FLAG_WRITE	4	/* generate data integrity on write */
 
-static inline long nr_blockdev_pages(void)
+struct blk_integrity_exchg {
+	void			*prot_buf;
+	void			*data_buf;
+	sector_t		sector;
+	unsigned int		data_size;
+	unsigned short		sector_size;
+	const char		*disk_name;
+};
+
+typedef void (integrity_gen_fn) (struct blk_integrity_exchg *);
+typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *);
+typedef void (integrity_set_tag_fn) (void *, void *, unsigned int);
+typedef void (integrity_get_tag_fn) (void *, void *, unsigned int);
+
+struct blk_integrity {
+	integrity_gen_fn	*generate_fn;
+	integrity_vrfy_fn	*verify_fn;
+	integrity_set_tag_fn	*set_tag_fn;
+	integrity_get_tag_fn	*get_tag_fn;
+
+	unsigned short		flags;
+	unsigned short		tuple_size;
+	unsigned short		sector_size;
+	unsigned short		tag_size;
+
+	const char		*name;
+
+	struct kobject		kobj;
+};
+
+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_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 void exit_io_context(void)
+static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
 {
+	return bdev->bd_disk->integrity;
 }
 
-struct io_context;
-static inline int put_io_context(struct io_context *ioc)
+static inline unsigned int bdev_get_tag_size(struct block_device *bdev)
 {
-	return 1;
+	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;
 }
 
+static inline int blk_integrity_rq(struct request *rq)
+{
+	return bio_integrity(rq->bio);
+}
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+
+#define blk_integrity_rq(rq)			(0)
+#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_integrity_compare(a, b)		(0)
+#define blk_integrity_register(a, b)		(0)
+#define blk_integrity_unregister(a)		do { } while (0);
+
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
+#else /* CONFIG_BLOCK */
+/*
+ * stubs for when the block layer is configured out
+ */
+#define buffer_heads_over_limit 0
+
+static inline long nr_blockdev_pages(void)
+{
+	return 0;
+}
 
 #endif /* CONFIG_BLOCK */
 
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index e3ef903aae88..d084b8d227a5 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -129,6 +129,7 @@ struct blk_trace {
 	u32 dev;
 	struct dentry *dir;
 	struct dentry *dropped_file;
+	struct dentry *msg_file;
 	atomic_t dropped;
 };
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index ae7aec3cabee..e8787417f65a 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -110,6 +110,14 @@ struct hd_struct {
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	32
 #define GENHD_FL_FAIL				64
 
+#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 gendisk {
 	int major;			/* major number of driver */
@@ -120,6 +128,7 @@ struct gendisk {
 	struct hd_struct **part;	/* [indexed by minor] */
 	struct block_device_operations *fops;
 	struct request_queue *queue;
+	struct blk_scsi_cmd_filter cmd_filter;
 	void *private_data;
 	sector_t capacity;
 
@@ -141,6 +150,9 @@ struct gendisk {
 	struct disk_stats dkstats;
 #endif
 	struct work_struct async_notify;
+#ifdef  CONFIG_BLK_DEV_INTEGRITY
+	struct blk_integrity *integrity;
+#endif
 };
 
 /* 
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 2b7a1187cb29..08b987bccf89 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -99,4 +99,22 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc)
 	return NULL;
 }
 
+#ifdef CONFIG_BLOCK
+int put_io_context(struct io_context *ioc);
+void exit_io_context(void);
+struct io_context *get_io_context(gfp_t gfp_flags, int node);
+struct io_context *alloc_io_context(gfp_t gfp_flags, int node);
+void copy_io_context(struct io_context **pdst, struct io_context **psrc);
+#else
+static inline void exit_io_context(void)
+{
+}
+
+struct io_context;
+static inline int put_io_context(struct io_context *ioc)
+{
+	return 1;
+}
+#endif
+
 #endif