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 22a9189f (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
  ...

Documentation/ABI/testing/sysfs-block

@@ -26,3 +26,37 @@ Description:
 		I/O statistics of partition <part>. The format is the
 		same as the above-written /sys/block/<disk>/stat
 		format.
+
+
+What:		/sys/block/<disk>/integrity/format
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Metadata format for integrity capable block device.
+		E.g. T10-DIF-TYPE1-CRC.
+
+
+What:		/sys/block/<disk>/integrity/read_verify
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Indicates whether the block layer should verify the
+		integrity of read requests serviced by devices that
+		support sending integrity metadata.
+
+
+What:		/sys/block/<disk>/integrity/tag_size
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Number of bytes of integrity tag space available per
+		512 bytes of data.
+
+
+What:		/sys/block/<disk>/integrity/write_generate
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Indicates whether the block layer should automatically
+		generate checksums for write requests bound for
+		devices that support receiving integrity metadata.

block/Kconfig

@@ -81,6 +81,18 @@ config BLK_DEV_BSG
 
 	  If unsure, say N.
 
+config BLK_DEV_INTEGRITY
+	bool "Block layer data integrity support"
+	---help---
+	Some storage devices allow extra information to be
+	stored/retrieved to help protect the data.  The block layer
+	data integrity option provides hooks which can be used by
+	filesystems to ensure better data integrity.
+
+	Say yes here if you have a storage device that provides the
+	T10/SCSI Data Integrity Field or the T13/ATA External Path
+	Protection.  If in doubt, say N.
+
 endif # BLOCK
 
 config BLOCK_COMPAT

block/Makefile

@@ -4,7 +4,8 @@
 
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
-			blk-exec.o blk-merge.o ioctl.o genhd.o scsi_ioctl.o
+			blk-exec.o blk-merge.o ioctl.o genhd.o scsi_ioctl.o \
+			cmd-filter.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
@@ -14,3 +15,4 @@ obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
 obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o

block/as-iosched.c

@@ -151,6 +151,7 @@ enum arq_state {
 
 static DEFINE_PER_CPU(unsigned long, ioc_count);
 static struct completion *ioc_gone;
+static DEFINE_SPINLOCK(ioc_gone_lock);
 
 static void as_move_to_dispatch(struct as_data *ad, struct request *rq);
 static void as_antic_stop(struct as_data *ad);
@@ -164,8 +165,19 @@ static void free_as_io_context(struct as_io_context *aic)
 {
 	kfree(aic);
 	elv_ioc_count_dec(ioc_count);
-	if (ioc_gone && !elv_ioc_count_read(ioc_count))
-		complete(ioc_gone);
+	if (ioc_gone) {
+		/*
+		 * AS scheduler is exiting, grab exit lock and check
+		 * the pending io context count. If it hits zero,
+		 * complete ioc_gone and set it back to NULL.
+		 */
+		spin_lock(&ioc_gone_lock);
+		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+			complete(ioc_gone);
+			ioc_gone = NULL;
+		}
+		spin_unlock(&ioc_gone_lock);
+	}
 }
 
 static void as_trim(struct io_context *ioc)
@@ -1493,7 +1505,7 @@ static void __exit as_exit(void)
 	/* ioc_gone's update must be visible before reading ioc_count */
 	smp_wmb();
 	if (elv_ioc_count_read(ioc_count))
-		wait_for_completion(ioc_gone);
+		wait_for_completion(&all_gone);
 	synchronize_rcu();
 }
 

block/blk-core.c

@@ -143,6 +143,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 
 		bio->bi_size -= nbytes;
 		bio->bi_sector += (nbytes >> 9);
+
+		if (bio_integrity(bio))
+			bio_integrity_advance(bio, nbytes);
+
 		if (bio->bi_size == 0)
 			bio_endio(bio, error);
 	} else {
@@ -201,8 +205,7 @@ void blk_plug_device(struct request_queue *q)
 	if (blk_queue_stopped(q))
 		return;
 
-	if (!test_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
-		__set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags);
+	if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) {
 		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
 		blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
 	}
@@ -217,10 +220,9 @@ int blk_remove_plug(struct request_queue *q)
 {
 	WARN_ON(!irqs_disabled());
 
-	if (!test_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+	if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q))
 		return 0;
 
-	queue_flag_clear(QUEUE_FLAG_PLUGGED, q);
 	del_timer(&q->unplug_timer);
 	return 1;
 }
@@ -324,8 +326,7 @@ void blk_start_queue(struct request_queue *q)
 	 * one level of recursion is ok and is much faster than kicking
 	 * the unplug handling
 	 */
-	if (!test_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
-		queue_flag_set(QUEUE_FLAG_REENTER, q);
+	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
 		q->request_fn(q);
 		queue_flag_clear(QUEUE_FLAG_REENTER, q);
 	} else {
@@ -390,8 +391,7 @@ void __blk_run_queue(struct request_queue *q)
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
 	if (!elv_queue_empty(q)) {
-		if (!test_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
-			queue_flag_set(QUEUE_FLAG_REENTER, q);
+		if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
 			q->request_fn(q);
 			queue_flag_clear(QUEUE_FLAG_REENTER, q);
 		} else {
@@ -1381,6 +1381,9 @@ static inline void __generic_make_request(struct bio *bio)
 		 */
 		blk_partition_remap(bio);
 
+		if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
+			goto end_io;
+
 		if (old_sector != -1)
 			blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
 					    old_sector);

block/blk-map.c

@@ -210,6 +210,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	if (!bio_flagged(bio, BIO_USER_MAPPED))
 		rq->cmd_flags |= REQ_COPY_USER;
 
+	blk_queue_bounce(q, &bio);
 	bio_get(bio);
 	blk_rq_bio_prep(q, rq, bio);
 	rq->buffer = rq->data = NULL;
@@ -268,6 +269,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	int reading = rq_data_dir(rq) == READ;
 	int do_copy = 0;
 	struct bio *bio;
+	unsigned long stack_mask = ~(THREAD_SIZE - 1);
 
 	if (len > (q->max_hw_sectors << 9))
 		return -EINVAL;
@@ -278,6 +280,10 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	alignment = queue_dma_alignment(q) | q->dma_pad_mask;
 	do_copy = ((kaddr & alignment) || (len & alignment));
 
+	if (!((kaddr & stack_mask) ^
+	      ((unsigned long)current->stack & stack_mask)))
+		do_copy = 1;
+
 	if (do_copy)
 		bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
 	else

block/blk-merge.c

@@ -441,6 +441,9 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	    || next->special)
 		return 0;
 
+	if (blk_integrity_rq(req) != blk_integrity_rq(next))
+		return 0;
+
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn

block/blk-settings.c

@@ -302,11 +302,10 @@ EXPORT_SYMBOL(blk_queue_stack_limits);
  * @q:     the request queue for the device
  * @mask:  pad mask
  *
- * Set pad mask.  Direct IO requests are padded to the mask specified.
+ * Set dma pad mask.
  *
- * Appending pad buffer to a request modifies ->data_len such that it
- * includes the pad buffer.  The original requested data length can be
- * obtained using blk_rq_raw_data_len().
+ * Appending pad buffer to a request modifies the last entry of a
+ * scatter list such that it includes the pad buffer.
  **/
 void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
 {
@@ -314,6 +313,23 @@ void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
 }
 EXPORT_SYMBOL(blk_queue_dma_pad);
 
+/**
+ * blk_queue_update_dma_pad - update pad mask
+ * @q:     the request queue for the device
+ * @mask:  pad mask
+ *
+ * Update dma pad mask.
+ *
+ * Appending pad buffer to a request modifies the last entry of a
+ * scatter list such that it includes the pad buffer.
+ **/
+void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
+{
+	if (mask > q->dma_pad_mask)
+		q->dma_pad_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_update_dma_pad);
+
 /**
  * blk_queue_dma_drain - Set up a drain buffer for excess dma.
  * @q:  the request queue for the device

block/blk.h

@@ -51,4 +51,12 @@ static inline int queue_congestion_off_threshold(struct request_queue *q)
 	return q->nr_congestion_off;
 }
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+#define rq_for_each_integrity_segment(bvl, _rq, _iter)		\
+	__rq_for_each_bio(_iter.bio, _rq)			\
+		bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i)
+
+#endif /* BLK_DEV_INTEGRITY */
+
 #endif

block/blktrace.c

@@ -244,6 +244,7 @@ static struct dentry *blk_create_tree(const char *blk_name)
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
 	relay_close(bt->rchan);
+	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
 	blk_remove_tree(bt->dir);
 	free_percpu(bt->sequence);
@@ -291,6 +292,44 @@ static const struct file_operations blk_dropped_fops = {
 	.read =		blk_dropped_read,
 };
 
+static int blk_msg_open(struct inode *inode, struct file *filp)
+{
+	filp->private_data = inode->i_private;
+
+	return 0;
+}
+
+static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
+				size_t count, loff_t *ppos)
+{
+	char *msg;
+	struct blk_trace *bt;
+
+	if (count > BLK_TN_MAX_MSG)
+		return -EINVAL;
+
+	msg = kmalloc(count, GFP_KERNEL);
+	if (msg == NULL)
+		return -ENOMEM;
+
+	if (copy_from_user(msg, buffer, count)) {
+		kfree(msg);
+		return -EFAULT;
+	}
+
+	bt = filp->private_data;
+	__trace_note_message(bt, "%s", msg);
+	kfree(msg);
+
+	return count;
+}
+
+static const struct file_operations blk_msg_fops = {
+	.owner =	THIS_MODULE,
+	.open =		blk_msg_open,
+	.write =	blk_msg_write,
+};
+
 /*
  * Keep track of how many times we encountered a full subbuffer, to aid
  * the user space app in telling how many lost events there were.
@@ -380,6 +419,10 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->dropped_file)
 		goto err;
 
+	bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
+	if (!bt->msg_file)
+		goto err;
+
 	bt->rchan = relay_open("trace", dir, buts->buf_size,
 				buts->buf_nr, &blk_relay_callbacks, bt);
 	if (!bt->rchan)
@@ -409,6 +452,8 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (dir)
 		blk_remove_tree(dir);
 	if (bt) {
+		if (bt->msg_file)
+			debugfs_remove(bt->msg_file);
 		if (bt->dropped_file)
 			debugfs_remove(bt->dropped_file);
 		free_percpu(bt->sequence);

block/bsg.c

@@ -44,11 +44,12 @@ struct bsg_device {
 	char name[BUS_ID_SIZE];
 	int max_queue;
 	unsigned long flags;
+	struct blk_scsi_cmd_filter *cmd_filter;
+	mode_t *f_mode;
 };
 
 enum {
 	BSG_F_BLOCK		= 1,
-	BSG_F_WRITE_PERM	= 2,
 };
 
 #define BSG_DEFAULT_CMDS	64
@@ -172,7 +173,7 @@ static int bsg_io_schedule(struct bsg_device *bd)
 }
 
 static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
-				struct sg_io_v4 *hdr, int has_write_perm)
+				struct sg_io_v4 *hdr, struct bsg_device *bd)
 {
 	if (hdr->request_len > BLK_MAX_CDB) {
 		rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
@@ -185,7 +186,8 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 		return -EFAULT;
 
 	if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
-		if (blk_verify_command(rq->cmd, has_write_perm))
+		if (blk_cmd_filter_verify_command(bd->cmd_filter, rq->cmd,
+						 bd->f_mode))
 			return -EPERM;
 	} else if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
@@ -263,8 +265,7 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr)
 	rq = blk_get_request(q, rw, GFP_KERNEL);
 	if (!rq)
 		return ERR_PTR(-ENOMEM);
-	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, test_bit(BSG_F_WRITE_PERM,
-						       &bd->flags));
+	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd);
 	if (ret)
 		goto out;
 
@@ -566,12 +567,23 @@ static inline void bsg_set_block(struct bsg_device *bd, struct file *file)
 		set_bit(BSG_F_BLOCK, &bd->flags);
 }
 
-static inline void bsg_set_write_perm(struct bsg_device *bd, struct file *file)
+static void bsg_set_cmd_filter(struct bsg_device *bd,
+			   struct file *file)
 {
-	if (file->f_mode & FMODE_WRITE)
-		set_bit(BSG_F_WRITE_PERM, &bd->flags);
-	else
-		clear_bit(BSG_F_WRITE_PERM, &bd->flags);
+	struct inode *inode;
+	struct gendisk *disk;
+
+	if (!file)
+		return;
+
+	inode = file->f_dentry->d_inode;
+	if (!inode)
+		return;
+
+	disk = inode->i_bdev->bd_disk;
+
+	bd->cmd_filter = &disk->cmd_filter;
+	bd->f_mode = &file->f_mode;
 }
 
 /*
@@ -595,6 +607,8 @@ bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	dprintk("%s: read %Zd bytes\n", bd->name, count);
 
 	bsg_set_block(bd, file);
+	bsg_set_cmd_filter(bd, file);
+
 	bytes_read = 0;
 	ret = __bsg_read(buf, count, bd, NULL, &bytes_read);
 	*ppos = bytes_read;
@@ -668,7 +682,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	dprintk("%s: write %Zd bytes\n", bd->name, count);
 
 	bsg_set_block(bd, file);
-	bsg_set_write_perm(bd, file);
+	bsg_set_cmd_filter(bd, file);
 
 	bytes_written = 0;
 	ret = __bsg_write(bd, buf, count, &bytes_written);
@@ -772,7 +786,9 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	}
 
 	bd->queue = rq;
+
 	bsg_set_block(bd, file);
+	bsg_set_cmd_filter(bd, file);
 
 	atomic_set(&bd->ref_count, 1);
 	mutex_lock(&bsg_mutex);

block/cfq-iosched.c

@@ -11,6 +11,7 @@
 #include <linux/elevator.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
+#include <linux/blktrace_api.h>
 
 /*
  * tunables
@@ -41,13 +42,14 @@ static int cfq_slice_idle = HZ / 125;
 
 #define RQ_CIC(rq)		\
 	((struct cfq_io_context *) (rq)->elevator_private)
-#define RQ_CFQQ(rq)		((rq)->elevator_private2)
+#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)
 
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
 
 static DEFINE_PER_CPU(unsigned long, ioc_count);
 static struct completion *ioc_gone;
+static DEFINE_SPINLOCK(ioc_gone_lock);
 
 #define CFQ_PRIO_LISTS		IOPRIO_BE_NR
 #define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
@@ -155,6 +157,7 @@ struct cfq_queue {
 	unsigned short ioprio, org_ioprio;
 	unsigned short ioprio_class, org_ioprio_class;
 
+	pid_t pid;
 };
 
 enum cfqq_state_flags {
@@ -198,6 +201,11 @@ CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 #undef CFQ_CFQQ_FNS
 
+#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
+	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log(cfqd, fmt, args...)	\
+	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
+
 static void cfq_dispatch_insert(struct request_queue *, struct request *);
 static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
 				       struct io_context *, gfp_t);
@@ -234,8 +242,10 @@ static inline int cfq_bio_sync(struct bio *bio)
  */
 static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
 {
-	if (cfqd->busy_queues)
+	if (cfqd->busy_queues) {
+		cfq_log(cfqd, "schedule dispatch");
 		kblockd_schedule_work(&cfqd->unplug_work);
+	}
 }
 
 static int cfq_queue_empty(struct request_queue *q)
@@ -270,6 +280,7 @@ static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
 }
 
 /*
@@ -539,6 +550,7 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  */
 static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	cfq_log_cfqq(cfqd, cfqq, "add_to_rr");
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
@@ -552,6 +564,7 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  */
 static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	cfq_clear_cfqq_on_rr(cfqq);
 
@@ -638,6 +651,8 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
 	cfqd->rq_in_driver++;
+	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
+						cfqd->rq_in_driver);
 
 	/*
 	 * If the depth is larger 1, it really could be queueing. But lets
@@ -657,6 +672,8 @@ static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
 
 	WARN_ON(!cfqd->rq_in_driver);
 	cfqd->rq_in_driver--;
+	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
+						cfqd->rq_in_driver);
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -746,6 +763,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				   struct cfq_queue *cfqq)
 {
 	if (cfqq) {
+		cfq_log_cfqq(cfqd, cfqq, "set_active");
 		cfqq->slice_end = 0;
 		cfq_clear_cfqq_must_alloc_slice(cfqq);
 		cfq_clear_cfqq_fifo_expire(cfqq);
@@ -763,6 +781,8 @@ static void
 __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		    int timed_out)
 {
+	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
+
 	if (cfq_cfqq_wait_request(cfqq))
 		del_timer(&cfqd->idle_slice_timer);
 
@@ -772,8 +792,10 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	/*
 	 * store what was left of this slice, if the queue idled/timed out
 	 */
-	if (timed_out && !cfq_cfqq_slice_new(cfqq))
+	if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
 		cfqq->slice_resid = cfqq->slice_end - jiffies;
+		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+	}
 
 	cfq_resort_rr_list(cfqd, cfqq);
 
@@ -865,6 +887,12 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	if (!cfqd->cfq_slice_idle || !cfq_cfqq_idle_window(cfqq))
 		return;
 
+	/*
+	 * still requests with the driver, don't idle
+	 */
+	if (cfqd->rq_in_driver)
+		return;
+
 	/*
 	 * task has exited, don't wait
 	 */
@@ -892,6 +920,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 		sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
 
 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	cfq_log(cfqd, "arm_idle: %lu", sl);
 }
 
 /*
@@ -902,6 +931,8 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 
+	cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
+
 	cfq_remove_request(rq);
 	cfqq->dispatched++;
 	elv_dispatch_sort(q, rq);
@@ -931,8 +962,9 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 	rq = rq_entry_fifo(cfqq->fifo.next);
 
 	if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
-		return NULL;
+		rq = NULL;
 
+	cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq);
 	return rq;
 }
 
@@ -1072,6 +1104,7 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 
 	BUG_ON(cfqd->busy_queues);
 
+	cfq_log(cfqd, "forced_dispatch=%d\n", dispatched);
 	return dispatched;
 }
 
@@ -1112,6 +1145,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 		dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
 	}
 
+	cfq_log(cfqd, "dispatched=%d", dispatched);
 	return dispatched;
 }
 
@@ -1130,6 +1164,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	if (!atomic_dec_and_test(&cfqq->ref))
 		return;
 
+	cfq_log_cfqq(cfqd, cfqq, "put_queue");
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
@@ -1177,8 +1212,19 @@ static void cfq_cic_free_rcu(struct rcu_head *head)
 	kmem_cache_free(cfq_ioc_pool, cic);
 	elv_ioc_count_dec(ioc_count);
 
-	if (ioc_gone && !elv_ioc_count_read(ioc_count))
-		complete(ioc_gone);
+	if (ioc_gone) {
+		/*
+		 * CFQ scheduler is exiting, grab exit lock and check
+		 * the pending io context count. If it hits zero,
+		 * complete ioc_gone and set it back to NULL
+		 */
+		spin_lock(&ioc_gone_lock);
+		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+			complete(ioc_gone);
+			ioc_gone = NULL;
+		}
+		spin_unlock(&ioc_gone_lock);
+	}
 }
 
 static void cfq_cic_free(struct cfq_io_context *cic)
@@ -1427,6 +1473,8 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
 				cfq_mark_cfqq_idle_window(cfqq);
 			cfq_mark_cfqq_sync(cfqq);
 		}
+		cfqq->pid = current->pid;
+		cfq_log_cfqq(cfqd, cfqq, "alloced");
 	}
 
 	if (new_cfqq)
@@ -1675,7 +1723,7 @@ static void
 cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct cfq_io_context *cic)
 {
-	int enable_idle;
+	int old_idle, enable_idle;
 
 	/*
 	 * Don't idle for async or idle io prio class
@@ -1683,7 +1731,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq))
 		return;
 
-	enable_idle = cfq_cfqq_idle_window(cfqq);
+	enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
 
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
 	    (cfqd->hw_tag && CIC_SEEKY(cic)))
@@ -1695,10 +1743,13 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			enable_idle = 1;
 	}
 
-	if (enable_idle)
-		cfq_mark_cfqq_idle_window(cfqq);
-	else
-		cfq_clear_cfqq_idle_window(cfqq);
+	if (old_idle != enable_idle) {
+		cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle);
+		if (enable_idle)
+			cfq_mark_cfqq_idle_window(cfqq);
+		else
+			cfq_clear_cfqq_idle_window(cfqq);
+	}
 }
 
 /*
@@ -1757,6 +1808,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
  */
 static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	cfq_log_cfqq(cfqd, cfqq, "preempt");
 	cfq_slice_expired(cfqd, 1);
 
 	/*
@@ -1818,6 +1870,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 
+	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);
 
 	cfq_add_rq_rb(rq);
@@ -1835,6 +1888,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	unsigned long now;
 
 	now = jiffies;
+	cfq_log_cfqq(cfqd, cfqq, "complete");
 
 	WARN_ON(!cfqd->rq_in_driver);
 	WARN_ON(!cfqq->dispatched);
@@ -2004,6 +2058,7 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 
 	cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(q->queue_lock, flags);
+	cfq_log(cfqd, "set_request fail");
 	return 1;
 }
 
@@ -2029,6 +2084,8 @@ static void cfq_idle_slice_timer(unsigned long data)
 	unsigned long flags;
 	int timed_out = 1;
 
+	cfq_log(cfqd, "idle timer fired");
+
 	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
 
 	cfqq = cfqd->active_queue;
@@ -2317,7 +2374,7 @@ static void __exit cfq_exit(void)
 	 * pending RCU callbacks
 	 */
 	if (elv_ioc_count_read(ioc_count))
-		wait_for_completion(ioc_gone);
+		wait_for_completion(&all_gone);
 	cfq_slab_kill();
 }
 

block/cmd-filter.c

+/*
+ * Copyright 2004 Peter M. Jones <pjones@redhat.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ *
+ */
+
+#include <linux/list.h>
+#include <linux/genhd.h>
+#include <linux/spinlock.h>
+#include <linux/parser.h>
+#include <linux/capability.h>
+#include <linux/bitops.h>
+
+#include <scsi/scsi.h>
+#include <linux/cdrom.h>
+
+int blk_cmd_filter_verify_command(struct blk_scsi_cmd_filter *filter,
+				  unsigned char *cmd, mode_t *f_mode)
+{
+	/* root can do any command. */
+	if (capable(CAP_SYS_RAWIO))
+		return 0;
+
+	/* if there's no filter set, assume we're filtering everything out */
+	if (!filter)
+		return -EPERM;
+
+	/* Anybody who can open the device can do a read-safe command */
+	if (test_bit(cmd[0], filter->read_ok))
+		return 0;
+
+	/* Write-safe commands require a writable open */
+	if (test_bit(cmd[0], filter->write_ok) && (*f_mode & FMODE_WRITE))
+		return 0;
+
+	return -EPERM;
+}
+EXPORT_SYMBOL(blk_cmd_filter_verify_command);
+
+int blk_verify_command(struct file *file, unsigned char *cmd)
+{
+	struct gendisk *disk;
+	struct inode *inode;
+
+	if (!file)
+		return -EINVAL;
+
+	inode = file->f_dentry->d_inode;
+	if (!inode)
+		return -EINVAL;
+
+	disk = inode->i_bdev->bd_disk;
+
+	return blk_cmd_filter_verify_command(&disk->cmd_filter,
+						 cmd, &file->f_mode);
+}
+EXPORT_SYMBOL(blk_verify_command);
+
+/* and now, the sysfs stuff */
+static ssize_t rcf_cmds_show(struct blk_scsi_cmd_filter *filter, char *page,
+			     int rw)
+{
+	char *npage = page;
+	unsigned long *okbits;
+	int i;
+
+	if (rw == READ)
+		okbits = filter->read_ok;
+	else
+		okbits = filter->write_ok;
+
+	for (i = 0; i < BLK_SCSI_MAX_CMDS; i++) {
+		if (test_bit(i, okbits)) {
+			sprintf(npage, "%02x", i);
+			npage += 2;
+			if (i < BLK_SCSI_MAX_CMDS - 1)
+				sprintf(npage++, " ");
+		}
+	}
+
+	if (npage != page)
+		npage += sprintf(npage, "\n");
+
+	return npage - page;
+}
+
+static ssize_t rcf_readcmds_show(struct blk_scsi_cmd_filter *filter, char *page)
+{
+	return rcf_cmds_show(filter, page, READ);
+}
+
+static ssize_t rcf_writecmds_show(struct blk_scsi_cmd_filter *filter,
+				 char *page)
+{
+	return rcf_cmds_show(filter, page, WRITE);
+}
+
+static ssize_t rcf_cmds_store(struct blk_scsi_cmd_filter *filter,
+			      const char *page, size_t count, int rw)
+{
+	ssize_t ret = 0;
+	unsigned long okbits[BLK_SCSI_CMD_PER_LONG], *target_okbits;
+	int cmd, status, len;
+	substring_t ss;
+
+	memset(&okbits, 0, sizeof(okbits));
+
+	for (len = strlen(page); len > 0; len -= 3) {
+		if (len < 2)
+			break;
+		ss.from = (char *) page + ret;
+		ss.to = (char *) page + ret + 2;
+		ret += 3;
+		status = match_hex(&ss, &cmd);
+		/* either of these cases means invalid input, so do nothing. */
+		if (status || cmd >= BLK_SCSI_MAX_CMDS)
+			return -EINVAL;
+
+		__set_bit(cmd, okbits);
+	}
+
+	if (rw == READ)
+		target_okbits = filter->read_ok;
+	else
+		target_okbits = filter->write_ok;
+
+	memmove(target_okbits, okbits, sizeof(okbits));
+	return count;
+}
+
+static ssize_t rcf_readcmds_store(struct blk_scsi_cmd_filter *filter,
+				  const char *page, size_t count)
+{
+	return rcf_cmds_store(filter, page, count, READ);
+}
+
+static ssize_t rcf_writecmds_store(struct blk_scsi_cmd_filter *filter,
+				   const char *page, size_t count)
+{
+	return rcf_cmds_store(filter, page, count, WRITE);
+}
+
+struct rcf_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct blk_scsi_cmd_filter *, char *);
+	ssize_t (*store)(struct blk_scsi_cmd_filter *, const char *, size_t);
+};
+
+static struct rcf_sysfs_entry rcf_readcmds_entry = {
+	.attr = { .name = "read_table", .mode = S_IRUGO | S_IWUSR },
+	.show = rcf_readcmds_show,
+	.store = rcf_readcmds_store,
+};
+
+static struct rcf_sysfs_entry rcf_writecmds_entry = {
+	.attr = {.name = "write_table", .mode = S_IRUGO | S_IWUSR },
+	.show = rcf_writecmds_show,
+	.store = rcf_writecmds_store,
+};
+
+static struct attribute *default_attrs[] = {
+	&rcf_readcmds_entry.attr,
+	&rcf_writecmds_entry.attr,
+	NULL,
+};
+
+#define to_rcf(atr) container_of((atr), struct rcf_sysfs_entry, attr)
+
+static ssize_t
+rcf_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct rcf_sysfs_entry *entry = to_rcf(attr);
+	struct blk_scsi_cmd_filter *filter;
+
+	filter = container_of(kobj, struct blk_scsi_cmd_filter, kobj);
+	if (entry->show)
+		return entry->show(filter, page);
+
+	return 0;
+}
+
+static ssize_t
+rcf_attr_store(struct kobject *kobj, struct attribute *attr,
+			const char *page, size_t length)
+{
+	struct rcf_sysfs_entry *entry = to_rcf(attr);
+	struct blk_scsi_cmd_filter *filter;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	if (!entry->store)
+		return -EINVAL;
+
+	filter = container_of(kobj, struct blk_scsi_cmd_filter, kobj);
+	return entry->store(filter, page, length);
+}
+
+static struct sysfs_ops rcf_sysfs_ops = {
+	.show = rcf_attr_show,
+	.store = rcf_attr_store,
+};
+
+static struct kobj_type rcf_ktype = {
+	.sysfs_ops = &rcf_sysfs_ops,
+	.default_attrs = default_attrs,
+};
+
+#ifndef MAINTENANCE_IN_CMD
+#define MAINTENANCE_IN_CMD 0xa3
+#endif
+
+static void rcf_set_defaults(struct blk_scsi_cmd_filter *filter)
+{
+	/* Basic read-only commands */
+	__set_bit(TEST_UNIT_READY, filter->read_ok);
+	__set_bit(REQUEST_SENSE, filter->read_ok);
+	__set_bit(READ_6, filter->read_ok);
+	__set_bit(READ_10, filter->read_ok);
+	__set_bit(READ_12, filter->read_ok);
+	__set_bit(READ_16, filter->read_ok);
+	__set_bit(READ_BUFFER, filter->read_ok);
+	__set_bit(READ_DEFECT_DATA, filter->read_ok);
+	__set_bit(READ_CAPACITY, filter->read_ok);
+	__set_bit(READ_LONG, filter->read_ok);
+	__set_bit(INQUIRY, filter->read_ok);
+	__set_bit(MODE_SENSE, filter->read_ok);
+	__set_bit(MODE_SENSE_10, filter->read_ok);
+	__set_bit(LOG_SENSE, filter->read_ok);
+	__set_bit(START_STOP, filter->read_ok);
+	__set_bit(GPCMD_VERIFY_10, filter->read_ok);
+	__set_bit(VERIFY_16, filter->read_ok);
+	__set_bit(REPORT_LUNS, filter->read_ok);
+	__set_bit(SERVICE_ACTION_IN, filter->read_ok);
+	__set_bit(RECEIVE_DIAGNOSTIC, filter->read_ok);
+	__set_bit(MAINTENANCE_IN_CMD, filter->read_ok);
+	__set_bit(GPCMD_READ_BUFFER_CAPACITY, filter->read_ok);
+
+	/* Audio CD commands */
+	__set_bit(GPCMD_PLAY_CD, filter->read_ok);
+	__set_bit(GPCMD_PLAY_AUDIO_10, filter->read_ok);
+	__set_bit(GPCMD_PLAY_AUDIO_MSF, filter->read_ok);
+	__set_bit(GPCMD_PLAY_AUDIO_TI, filter->read_ok);
+	__set_bit(GPCMD_PAUSE_RESUME, filter->read_ok);
+
+	/* CD/DVD data reading */
+	__set_bit(GPCMD_READ_CD, filter->read_ok);
+	__set_bit(GPCMD_READ_CD_MSF, filter->read_ok);
+	__set_bit(GPCMD_READ_DISC_INFO, filter->read_ok);
+	__set_bit(GPCMD_READ_CDVD_CAPACITY, filter->read_ok);
+	__set_bit(GPCMD_READ_DVD_STRUCTURE, filter->read_ok);
+	__set_bit(GPCMD_READ_HEADER, filter->read_ok);
+	__set_bit(GPCMD_READ_TRACK_RZONE_INFO, filter->read_ok);
+	__set_bit(GPCMD_READ_SUBCHANNEL, filter->read_ok);
+	__set_bit(GPCMD_READ_TOC_PMA_ATIP, filter->read_ok);
+	__set_bit(GPCMD_REPORT_KEY, filter->read_ok);
+	__set_bit(GPCMD_SCAN, filter->read_ok);
+	__set_bit(GPCMD_GET_CONFIGURATION, filter->read_ok);
+	__set_bit(GPCMD_READ_FORMAT_CAPACITIES, filter->read_ok);
+	__set_bit(GPCMD_GET_EVENT_STATUS_NOTIFICATION, filter->read_ok);
+	__set_bit(GPCMD_GET_PERFORMANCE, filter->read_ok);
+	__set_bit(GPCMD_SEEK, filter->read_ok);
+	__set_bit(GPCMD_STOP_PLAY_SCAN, filter->read_ok);
+
+	/* Basic writing commands */
+	__set_bit(WRITE_6, filter->write_ok);
+	__set_bit(WRITE_10, filter->write_ok);
+	__set_bit(WRITE_VERIFY, filter->write_ok);
+	__set_bit(WRITE_12, filter->write_ok);
+	__set_bit(WRITE_VERIFY_12, filter->write_ok);
+	__set_bit(WRITE_16, filter->write_ok);
+	__set_bit(WRITE_LONG, filter->write_ok);
+	__set_bit(WRITE_LONG_2, filter->write_ok);
+	__set_bit(ERASE, filter->write_ok);
+	__set_bit(GPCMD_MODE_SELECT_10, filter->write_ok);
+	__set_bit(MODE_SELECT, filter->write_ok);
+	__set_bit(LOG_SELECT, filter->write_ok);
+	__set_bit(GPCMD_BLANK, filter->write_ok);
+	__set_bit(GPCMD_CLOSE_TRACK, filter->write_ok);
+	__set_bit(GPCMD_FLUSH_CACHE, filter->write_ok);
+	__set_bit(GPCMD_FORMAT_UNIT, filter->write_ok);
+	__set_bit(GPCMD_REPAIR_RZONE_TRACK, filter->write_ok);
+	__set_bit(GPCMD_RESERVE_RZONE_TRACK, filter->write_ok);
+	__set_bit(GPCMD_SEND_DVD_STRUCTURE, filter->write_ok);
+	__set_bit(GPCMD_SEND_EVENT, filter->write_ok);
+	__set_bit(GPCMD_SEND_KEY, filter->write_ok);
+	__set_bit(GPCMD_SEND_OPC, filter->write_ok);
+	__set_bit(GPCMD_SEND_CUE_SHEET, filter->write_ok);
+	__set_bit(GPCMD_SET_SPEED, filter->write_ok);
+	__set_bit(GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL, filter->write_ok);
+	__set_bit(GPCMD_LOAD_UNLOAD, filter->write_ok);
+	__set_bit(GPCMD_SET_STREAMING, filter->write_ok);
+}
+
+int blk_register_filter(struct gendisk *disk)
+{
+	int ret;
+	struct blk_scsi_cmd_filter *filter = &disk->cmd_filter;
+	struct kobject *parent = kobject_get(disk->holder_dir->parent);
+
+	if (!parent)
+		return -ENODEV;
+
+	ret = kobject_init_and_add(&filter->kobj, &rcf_ktype, parent,
+				 "%s", "cmd_filter");
+
+	if (ret < 0)
+		return ret;
+
+	rcf_set_defaults(filter);
+	return 0;
+}
+
+void blk_unregister_filter(struct gendisk *disk)
+{
+	struct blk_scsi_cmd_filter *filter = &disk->cmd_filter;
+
+	kobject_put(&filter->kobj);
+	kobject_put(disk->holder_dir->parent);
+}
+

block/elevator.c

@@ -86,6 +86,12 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
 		return 0;
 
+	/*
+	 * only merge integrity protected bio into ditto rq
+	 */
+	if (bio_integrity(bio) != blk_integrity_rq(rq))
+		return 0;
+
 	if (!elv_iosched_allow_merge(rq, bio))
 		return 0;
 
@@ -144,7 +150,7 @@ static struct elevator_type *elevator_get(const char *name)
 		else
 			sprintf(elv, "%s-iosched", name);
 
-		request_module(elv);
+		request_module("%s", elv);
 		spin_lock(&elv_list_lock);
 		e = elevator_find(name);
 	}

block/genhd.c

@@ -189,6 +189,7 @@ void add_disk(struct gendisk *disk)
 			    disk->minors, NULL, exact_match, exact_lock, disk);
 	register_disk(disk);
 	blk_register_queue(disk);
+	blk_register_filter(disk);
 
 	bdi = &disk->queue->backing_dev_info;
 	bdi_register_dev(bdi, MKDEV(disk->major, disk->first_minor));
@@ -200,6 +201,7 @@ EXPORT_SYMBOL(del_gendisk);	/* in partitions/check.c */
 
 void unlink_gendisk(struct gendisk *disk)
 {
+	blk_unregister_filter(disk);
 	sysfs_remove_link(&disk->dev.kobj, "bdi");
 	bdi_unregister(&disk->queue->backing_dev_info);
 	blk_unregister_queue(disk);
@@ -400,6 +402,14 @@ static ssize_t disk_removable_show(struct device *dev,
 		       (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
 }
 
+static ssize_t disk_ro_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", disk->policy ? 1 : 0);
+}
+
 static ssize_t disk_size_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
@@ -472,6 +482,7 @@ static ssize_t disk_fail_store(struct device *dev,
 
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
+static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, disk_size_show, NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, disk_stat_show, NULL);
@@ -483,6 +494,7 @@ static struct device_attribute dev_attr_fail =
 static struct attribute *disk_attrs[] = {
 	&dev_attr_range.attr,
 	&dev_attr_removable.attr,
+	&dev_attr_ro.attr,
 	&dev_attr_size.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,

block/scsi_ioctl.c

@@ -105,120 +105,12 @@ static int sg_emulated_host(struct request_queue *q, int __user *p)
 	return put_user(1, p);
 }
 
-#define CMD_READ_SAFE	0x01
-#define CMD_WRITE_SAFE	0x02
-#define CMD_WARNED	0x04
-#define safe_for_read(cmd)	[cmd] = CMD_READ_SAFE
-#define safe_for_write(cmd)	[cmd] = CMD_WRITE_SAFE
-
-int blk_verify_command(unsigned char *cmd, int has_write_perm)
-{
-	static unsigned char cmd_type[256] = {
-
-		/* Basic read-only commands */
-		safe_for_read(TEST_UNIT_READY),
-		safe_for_read(REQUEST_SENSE),
-		safe_for_read(READ_6),
-		safe_for_read(READ_10),
-		safe_for_read(READ_12),
-		safe_for_read(READ_16),
-		safe_for_read(READ_BUFFER),
-		safe_for_read(READ_DEFECT_DATA),
-		safe_for_read(READ_LONG),
-		safe_for_read(INQUIRY),
-		safe_for_read(MODE_SENSE),
-		safe_for_read(MODE_SENSE_10),
-		safe_for_read(LOG_SENSE),
-		safe_for_read(START_STOP),
-		safe_for_read(GPCMD_VERIFY_10),
-		safe_for_read(VERIFY_16),
-
-		/* Audio CD commands */
-		safe_for_read(GPCMD_PLAY_CD),
-		safe_for_read(GPCMD_PLAY_AUDIO_10),
-		safe_for_read(GPCMD_PLAY_AUDIO_MSF),
-		safe_for_read(GPCMD_PLAY_AUDIO_TI),
-		safe_for_read(GPCMD_PAUSE_RESUME),
-
-		/* CD/DVD data reading */
-		safe_for_read(GPCMD_READ_BUFFER_CAPACITY),
-		safe_for_read(GPCMD_READ_CD),
-		safe_for_read(GPCMD_READ_CD_MSF),
-		safe_for_read(GPCMD_READ_DISC_INFO),
-		safe_for_read(GPCMD_READ_CDVD_CAPACITY),
-		safe_for_read(GPCMD_READ_DVD_STRUCTURE),
-		safe_for_read(GPCMD_READ_HEADER),
-		safe_for_read(GPCMD_READ_TRACK_RZONE_INFO),
-		safe_for_read(GPCMD_READ_SUBCHANNEL),
-		safe_for_read(GPCMD_READ_TOC_PMA_ATIP),
-		safe_for_read(GPCMD_REPORT_KEY),
-		safe_for_read(GPCMD_SCAN),
-		safe_for_read(GPCMD_GET_CONFIGURATION),
-		safe_for_read(GPCMD_READ_FORMAT_CAPACITIES),
-		safe_for_read(GPCMD_GET_EVENT_STATUS_NOTIFICATION),
-		safe_for_read(GPCMD_GET_PERFORMANCE),
-		safe_for_read(GPCMD_SEEK),
-		safe_for_read(GPCMD_STOP_PLAY_SCAN),
-
-		/* Basic writing commands */
-		safe_for_write(WRITE_6),
-		safe_for_write(WRITE_10),
-		safe_for_write(WRITE_VERIFY),
-		safe_for_write(WRITE_12),
-		safe_for_write(WRITE_VERIFY_12),
-		safe_for_write(WRITE_16),
-		safe_for_write(WRITE_LONG),
-		safe_for_write(WRITE_LONG_2),
-		safe_for_write(ERASE),
-		safe_for_write(GPCMD_MODE_SELECT_10),
-		safe_for_write(MODE_SELECT),
-		safe_for_write(LOG_SELECT),
-		safe_for_write(GPCMD_BLANK),
-		safe_for_write(GPCMD_CLOSE_TRACK),
-		safe_for_write(GPCMD_FLUSH_CACHE),
-		safe_for_write(GPCMD_FORMAT_UNIT),
-		safe_for_write(GPCMD_REPAIR_RZONE_TRACK),
-		safe_for_write(GPCMD_RESERVE_RZONE_TRACK),
-		safe_for_write(GPCMD_SEND_DVD_STRUCTURE),
-		safe_for_write(GPCMD_SEND_EVENT),
-		safe_for_write(GPCMD_SEND_KEY),
-		safe_for_write(GPCMD_SEND_OPC),
-		safe_for_write(GPCMD_SEND_CUE_SHEET),
-		safe_for_write(GPCMD_SET_SPEED),
-		safe_for_write(GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL),
-		safe_for_write(GPCMD_LOAD_UNLOAD),
-		safe_for_write(GPCMD_SET_STREAMING),
-	};
-	unsigned char type = cmd_type[cmd[0]];
-
-	/* Anybody who can open the device can do a read-safe command */
-	if (type & CMD_READ_SAFE)
-		return 0;
-
-	/* Write-safe commands just require a writable open.. */
-	if ((type & CMD_WRITE_SAFE) && has_write_perm)
-		return 0;
-
-	/* And root can do any command.. */
-	if (capable(CAP_SYS_RAWIO))
-		return 0;
-
-	if (!type) {
-		cmd_type[cmd[0]] = CMD_WARNED;
-		printk(KERN_WARNING "scsi: unknown opcode 0x%02x\n", cmd[0]);
-	}
-
-	/* Otherwise fail it with an "Operation not permitted" */
-	return -EPERM;
-}
-EXPORT_SYMBOL_GPL(blk_verify_command);
-
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
-			     struct sg_io_hdr *hdr, int has_write_perm)
+			     struct sg_io_hdr *hdr, struct file *file)
 {
 	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
-	if (blk_verify_command(rq->cmd, has_write_perm))
+	if (blk_verify_command(file, rq->cmd))
 		return -EPERM;
 
 	/*
@@ -287,7 +179,7 @@ static int sg_io(struct file *file, struct request_queue *q,
 		struct gendisk *bd_disk, struct sg_io_hdr *hdr)
 {
 	unsigned long start_time;
-	int writing = 0, ret = 0, has_write_perm = 0;
+	int writing = 0, ret = 0;
 	struct request *rq;
 	char sense[SCSI_SENSE_BUFFERSIZE];
 	struct bio *bio;
@@ -316,10 +208,7 @@ static int sg_io(struct file *file, struct request_queue *q,
 	if (!rq)
 		return -ENOMEM;
 
-	if (file)
-		has_write_perm = file->f_mode & FMODE_WRITE;
-
-	if (blk_fill_sghdr_rq(q, rq, hdr, has_write_perm)) {
+	if (blk_fill_sghdr_rq(q, rq, hdr, file)) {
 		blk_put_request(rq);
 		return -EFAULT;
 	}
@@ -451,7 +340,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	err = blk_verify_command(rq->cmd, file->f_mode & FMODE_WRITE);
+	err = blk_verify_command(file, rq->cmd);
 	if (err)
 		goto error;
 

drivers/ata/libata-scsi.c

@@ -885,7 +885,8 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 		/* set the min alignment and padding */
 		blk_queue_update_dma_alignment(sdev->request_queue,
 					       ATA_DMA_PAD_SZ - 1);
-		blk_queue_dma_pad(sdev->request_queue, ATA_DMA_PAD_SZ - 1);
+		blk_queue_update_dma_pad(sdev->request_queue,
+					 ATA_DMA_PAD_SZ - 1);
 
 		/* configure draining */
 		buf = kmalloc(ATAPI_MAX_DRAIN, q->bounce_gfp | GFP_KERNEL);

drivers/block/aoe/aoecmd.c

@@ -1003,7 +1003,7 @@ aoecmd_cfg_rsp(struct sk_buff *skb)
 	 * Enough people have their dip switches set backwards to
 	 * warrant a loud message for this special case.
 	 */
-	aoemajor = be16_to_cpu(get_unaligned(&h->major));
+	aoemajor = get_unaligned_be16(&h->major);
 	if (aoemajor == 0xfff) {
 		printk(KERN_ERR "aoe: Warning: shelf address is all ones.  "
 			"Check shelf dip switches.\n");

drivers/block/paride/pt.c

@@ -146,6 +146,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3};
 #include <linux/mtio.h>
 #include <linux/device.h>
 #include <linux/sched.h>	/* current, TASK_*, schedule_timeout() */
+#include <linux/smp_lock.h>
 
 #include <asm/uaccess.h>
 
@@ -189,8 +190,7 @@ module_param_array(drive3, int, NULL, 0);
 #define ATAPI_LOG_SENSE		0x4d
 
 static int pt_open(struct inode *inode, struct file *file);
-static int pt_ioctl(struct inode *inode, struct file *file,
-		    unsigned int cmd, unsigned long arg);
+static long pt_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 static int pt_release(struct inode *inode, struct file *file);
 static ssize_t pt_read(struct file *filp, char __user *buf,
 		       size_t count, loff_t * ppos);
@@ -236,7 +236,7 @@ static const struct file_operations pt_fops = {
 	.owner = THIS_MODULE,
 	.read = pt_read,
 	.write = pt_write,
-	.ioctl = pt_ioctl,
+	.unlocked_ioctl = pt_ioctl,
 	.open = pt_open,
 	.release = pt_release,
 };
@@ -685,8 +685,7 @@ static int pt_open(struct inode *inode, struct file *file)
 	return err;
 }
 
-static int pt_ioctl(struct inode *inode, struct file *file,
-	 unsigned int cmd, unsigned long arg)
+static long pt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct pt_unit *tape = file->private_data;
 	struct mtop __user *p = (void __user *)arg;
@@ -700,23 +699,26 @@ static int pt_ioctl(struct inode *inode, struct file *file,
 		switch (mtop.mt_op) {
 
 		case MTREW:
+			lock_kernel();
 			pt_rewind(tape);
+			unlock_kernel();
 			return 0;
 
 		case MTWEOF:
+			lock_kernel();
 			pt_write_fm(tape);
+			unlock_kernel();
 			return 0;
 
 		default:
-			printk("%s: Unimplemented mt_op %d\n", tape->name,
+			/* FIXME: rate limit ?? */
+			printk(KERN_DEBUG "%s: Unimplemented mt_op %d\n", tape->name,
 			       mtop.mt_op);
 			return -EINVAL;
 		}
 
 	default:
-		printk("%s: Unimplemented ioctl 0x%x\n", tape->name, cmd);
-		return -EINVAL;
-
+		return -ENOTTY;
 	}
 }
 

drivers/block/pktcdvd.c

@@ -49,6 +49,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
+#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/spinlock.h>
 #include <linux/file.h>
@@ -2079,7 +2080,6 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 	unsigned char buf[64];
 	int ret;
 
-	memset(buf, 0, sizeof(buf));
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
 	cgc.sense = &sense;
 	cgc.buflen = pd->mode_offset + 12;
@@ -2126,7 +2126,6 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
 	unsigned char *cap_buf;
 	int ret, offset;
 
-	memset(buf, 0, sizeof(buf));
 	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
 	cgc.sense = &sense;
@@ -2633,11 +2632,12 @@ static int pkt_make_request(struct request_queue *q, struct bio *bio)
 
 
 
-static int pkt_merge_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *bvec)
+static int pkt_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
+			  struct bio_vec *bvec)
 {
 	struct pktcdvd_device *pd = q->queuedata;
-	sector_t zone = ZONE(bio->bi_sector, pd);
-	int used = ((bio->bi_sector - zone) << 9) + bio->bi_size;
+	sector_t zone = ZONE(bmd->bi_sector, pd);
+	int used = ((bmd->bi_sector - zone) << 9) + bmd->bi_size;
 	int remaining = (pd->settings.size << 9) - used;
 	int remaining2;
 
@@ -2645,7 +2645,7 @@ static int pkt_merge_bvec(struct request_queue *q, struct bio *bio, struct bio_v
 	 * A bio <= PAGE_SIZE must be allowed. If it crosses a packet
 	 * boundary, pkt_make_request() will split the bio.
 	 */
-	remaining2 = PAGE_SIZE - bio->bi_size;
+	remaining2 = PAGE_SIZE - bmd->bi_size;
 	remaining = max(remaining, remaining2);
 
 	BUG_ON(remaining < 0);
@@ -2796,9 +2796,14 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	return ret;
 }
 
-static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg)
+static long pkt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct pktcdvd_device *pd = inode->i_bdev->bd_disk->private_data;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct pktcdvd_device *pd;
+	long ret;
+
+	lock_kernel();
+	pd = inode->i_bdev->bd_disk->private_data;
 
 	VPRINTK("pkt_ioctl: cmd %x, dev %d:%d\n", cmd, imajor(inode), iminor(inode));
 
@@ -2811,7 +2816,8 @@ static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, u
 	case CDROM_LAST_WRITTEN:
 	case CDROM_SEND_PACKET:
 	case SCSI_IOCTL_SEND_COMMAND:
-		return blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		ret = blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		break;
 
 	case CDROMEJECT:
 		/*
@@ -2820,14 +2826,15 @@ static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, u
 		 */
 		if (pd->refcnt == 1)
 			pkt_lock_door(pd, 0);
-		return blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		ret = blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		break;
 
 	default:
 		VPRINTK(DRIVER_NAME": Unknown ioctl for %s (%x)\n", pd->name, cmd);
-		return -ENOTTY;
+		ret = -ENOTTY;
 	}
-
-	return 0;
+	unlock_kernel();
+	return ret;
 }
 
 static int pkt_media_changed(struct gendisk *disk)
@@ -2849,7 +2856,7 @@ static struct block_device_operations pktcdvd_ops = {
 	.owner =		THIS_MODULE,
 	.open =			pkt_open,
 	.release =		pkt_close,
-	.ioctl =		pkt_ioctl,
+	.unlocked_ioctl =	pkt_ioctl,
 	.media_changed =	pkt_media_changed,
 };
 
@@ -3014,7 +3021,8 @@ static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
 	mutex_unlock(&ctl_mutex);
 }
 
-static int pkt_ctl_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg)
+static long pkt_ctl_ioctl(struct file *file, unsigned int cmd,
+						unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct pkt_ctrl_command ctrl_cmd;
@@ -3031,16 +3039,22 @@ static int pkt_ctl_ioctl(struct inode *inode, struct file *file, unsigned int cm
 	case PKT_CTRL_CMD_SETUP:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
+		lock_kernel();
 		ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
 		ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
+		unlock_kernel();
 		break;
 	case PKT_CTRL_CMD_TEARDOWN:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
+		lock_kernel();
 		ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
+		unlock_kernel();
 		break;
 	case PKT_CTRL_CMD_STATUS:
+		lock_kernel();
 		pkt_get_status(&ctrl_cmd);
+		unlock_kernel();
 		break;
 	default:
 		return -ENOTTY;
@@ -3053,7 +3067,7 @@ static int pkt_ctl_ioctl(struct inode *inode, struct file *file, unsigned int cm
 
 
 static const struct file_operations pkt_ctl_fops = {
-	.ioctl	 = pkt_ctl_ioctl,
+	.unlocked_ioctl	 = pkt_ctl_ioctl,
 	.owner	 = THIS_MODULE,
 };
 

drivers/block/xen-blkfront.c

@@ -38,6 +38,7 @@
 #include <linux/interrupt.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
+#include <linux/cdrom.h>
 #include <linux/module.h>
 
 #include <xen/xenbus.h>
@@ -153,6 +154,40 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
 	return 0;
 }
 
+int blkif_ioctl(struct inode *inode, struct file *filep,
+		unsigned command, unsigned long argument)
+{
+	struct blkfront_info *info =
+		inode->i_bdev->bd_disk->private_data;
+	int i;
+
+	dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n",
+		command, (long)argument);
+
+	switch (command) {
+	case CDROMMULTISESSION:
+		dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n");
+		for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+			if (put_user(0, (char __user *)(argument + i)))
+				return -EFAULT;
+		return 0;
+
+	case CDROM_GET_CAPABILITY: {
+		struct gendisk *gd = info->gd;
+		if (gd->flags & GENHD_FL_CD)
+			return 0;
+		return -EINVAL;
+	}
+
+	default:
+		/*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n",
+		  command);*/
+		return -EINVAL; /* same return as native Linux */
+	}
+
+	return 0;
+}
+
 /*
  * blkif_queue_request
  *
@@ -324,6 +359,9 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 	/* Make sure buffer addresses are sector-aligned. */
 	blk_queue_dma_alignment(rq, 511);
 
+	/* Make sure we don't use bounce buffers. */
+	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
+
 	gd->queue = rq;
 
 	return 0;
@@ -546,7 +584,7 @@ static int setup_blkring(struct xenbus_device *dev,
 
 	info->ring_ref = GRANT_INVALID_REF;
 
-	sring = (struct blkif_sring *)__get_free_page(GFP_KERNEL);
+	sring = (struct blkif_sring *)__get_free_page(GFP_NOIO | __GFP_HIGH);
 	if (!sring) {
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
 		return -ENOMEM;
@@ -703,7 +741,8 @@ static int blkif_recover(struct blkfront_info *info)
 	int j;
 
 	/* Stage 1: Make a safe copy of the shadow state. */
-	copy = kmalloc(sizeof(info->shadow), GFP_KERNEL);
+	copy = kmalloc(sizeof(info->shadow),
+		       GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
 	if (!copy)
 		return -ENOMEM;
 	memcpy(copy, info->shadow, sizeof(info->shadow));
@@ -959,7 +998,7 @@ static int blkif_release(struct inode *inode, struct file *filep)
 		struct xenbus_device *dev = info->xbdev;
 		enum xenbus_state state = xenbus_read_driver_state(dev->otherend);
 
-		if (state == XenbusStateClosing)
+		if (state == XenbusStateClosing && info->is_ready)
 			blkfront_closing(dev);
 	}
 	return 0;
@@ -971,6 +1010,7 @@ static struct block_device_operations xlvbd_block_fops =
 	.open = blkif_open,
 	.release = blkif_release,
 	.getgeo = blkif_getgeo,
+	.ioctl = blkif_ioctl,
 };
 
 
@@ -1006,7 +1046,7 @@ static int __init xlblk_init(void)
 module_init(xlblk_init);
 
 
-static void xlblk_exit(void)
+static void __exit xlblk_exit(void)
 {
 	return xenbus_unregister_driver(&blkfront);
 }

drivers/md/linear.c

@@ -50,17 +50,19 @@ static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
 /**
  *	linear_mergeable_bvec -- tell bio layer if two requests can be merged
  *	@q: request queue
- *	@bio: the buffer head that's been built up so far
+ *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can take at this offset
  */
-static int linear_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+static int linear_mergeable_bvec(struct request_queue *q,
+				 struct bvec_merge_data *bvm,
+				 struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
 	dev_info_t *dev0;
-	unsigned long maxsectors, bio_sectors = bio->bi_size >> 9;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 
 	dev0 = which_dev(mddev, sector);
 	maxsectors = (dev0->size << 1) - (sector - (dev0->offset<<1));

drivers/md/raid0.c

@@ -241,18 +241,20 @@ static int create_strip_zones (mddev_t *mddev)
 /**
  *	raid0_mergeable_bvec -- tell bio layer if a two requests can be merged
  *	@q: request queue
- *	@bio: the buffer head that's been built up so far
+ *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
  */
-static int raid0_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+static int raid0_mergeable_bvec(struct request_queue *q,
+				struct bvec_merge_data *bvm,
+				struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bvm->bi_size >> 9;
 
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
 	if (max < 0) max = 0; /* bio_add cannot handle a negative return */

drivers/md/raid10.c

@@ -439,26 +439,27 @@ static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev)
 /**
  *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
  *	@q: request queue
- *	@bio: the buffer head that's been built up so far
+ *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
  *      If near_copies == raid_disk, there are no striping issues,
  *      but in that case, the function isn't called at all.
  */
-static int raid10_mergeable_bvec(struct request_queue *q, struct bio *bio,
-				struct bio_vec *bio_vec)
+static int raid10_mergeable_bvec(struct request_queue *q,
+				 struct bvec_merge_data *bvm,
+				 struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bvm->bi_size >> 9;
 
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
 	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
-	if (max <= bio_vec->bv_len && bio_sectors == 0)
-		return bio_vec->bv_len;
+	if (max <= biovec->bv_len && bio_sectors == 0)
+		return biovec->bv_len;
 	else
 		return max;
 }

drivers/md/raid5.c

@@ -3314,15 +3314,17 @@ static int raid5_congested(void *data, int bits)
 /* We want read requests to align with chunks where possible,
  * but write requests don't need to.
  */
-static int raid5_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+static int raid5_mergeable_bvec(struct request_queue *q,
+				struct bvec_merge_data *bvm,
+				struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bvm->bi_size >> 9;
 
-	if (bio_data_dir(bio) == WRITE)
+	if ((bvm->bi_rw & 1) == WRITE)
 		return biovec->bv_len; /* always allow writes to be mergeable */
 
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;

drivers/net/xen-netfront.c

@@ -1324,7 +1324,7 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
 		goto fail;
 	}
 
-	txs = (struct xen_netif_tx_sring *)get_zeroed_page(GFP_KERNEL);
+	txs = (struct xen_netif_tx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH);
 	if (!txs) {
 		err = -ENOMEM;
 		xenbus_dev_fatal(dev, err, "allocating tx ring page");
@@ -1340,7 +1340,7 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
 	}
 
 	info->tx_ring_ref = err;
-	rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_KERNEL);
+	rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH);
 	if (!rxs) {
 		err = -ENOMEM;
 		xenbus_dev_fatal(dev, err, "allocating rx ring page");

drivers/scsi/sg.c

@@ -182,8 +182,9 @@ static int sg_build_sgat(Sg_scatter_hold * schp, const Sg_fd * sfp,
 			 int tablesize);
 static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count,
 			   Sg_request * srp);
-static ssize_t sg_new_write(Sg_fd * sfp, const char __user *buf, size_t count,
-			    int blocking, int read_only, Sg_request ** o_srp);
+static ssize_t sg_new_write(Sg_fd *sfp, struct file *file,
+			const char __user *buf, size_t count, int blocking,
+			int read_only, Sg_request **o_srp);
 static int sg_common_write(Sg_fd * sfp, Sg_request * srp,
 			   unsigned char *cmnd, int timeout, int blocking);
 static int sg_u_iovec(sg_io_hdr_t * hp, int sg_num, int ind,
@@ -204,7 +205,6 @@ static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id);
 static Sg_request *sg_add_request(Sg_fd * sfp);
 static int sg_remove_request(Sg_fd * sfp, Sg_request * srp);
 static int sg_res_in_use(Sg_fd * sfp);
-static int sg_allow_access(unsigned char opcode, char dev_type);
 static int sg_build_direct(Sg_request * srp, Sg_fd * sfp, int dxfer_len);
 static Sg_device *sg_get_dev(int dev);
 #ifdef CONFIG_SCSI_PROC_FS
@@ -544,7 +544,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 		return -EFAULT;
 	blocking = !(filp->f_flags & O_NONBLOCK);
 	if (old_hdr.reply_len < 0)
-		return sg_new_write(sfp, buf, count, blocking, 0, NULL);
+		return sg_new_write(sfp, filp, buf, count, blocking, 0, NULL);
 	if (count < (SZ_SG_HEADER + 6))
 		return -EIO;	/* The minimum scsi command length is 6 bytes. */
 
@@ -621,8 +621,9 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 }
 
 static ssize_t
-sg_new_write(Sg_fd * sfp, const char __user *buf, size_t count,
-	     int blocking, int read_only, Sg_request ** o_srp)
+sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
+		 size_t count, int blocking, int read_only,
+		 Sg_request **o_srp)
 {
 	int k;
 	Sg_request *srp;
@@ -678,8 +679,7 @@ sg_new_write(Sg_fd * sfp, const char __user *buf, size_t count,
 		sg_remove_request(sfp, srp);
 		return -EFAULT;
 	}
-	if (read_only &&
-	    (!sg_allow_access(cmnd[0], sfp->parentdp->device->type))) {
+	if (read_only && !blk_verify_command(file, cmnd)) {
 		sg_remove_request(sfp, srp);
 		return -EPERM;
 	}
@@ -799,7 +799,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
 			if (!access_ok(VERIFY_WRITE, p, SZ_SG_IO_HDR))
 				return -EFAULT;
 			result =
-			    sg_new_write(sfp, p, SZ_SG_IO_HDR,
+			    sg_new_write(sfp, filp, p, SZ_SG_IO_HDR,
 					 blocking, read_only, &srp);
 			if (result < 0)
 				return result;
@@ -1048,7 +1048,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
 
 			if (copy_from_user(&opcode, siocp->data, 1))
 				return -EFAULT;
-			if (!sg_allow_access(opcode, sdp->device->type))
+			if (!blk_verify_command(filp, &opcode))
 				return -EPERM;
 		}
 		return sg_scsi_ioctl(filp, sdp->device->request_queue, NULL, p);
@@ -2502,30 +2502,6 @@ sg_page_free(struct page *page, int size)
 	__free_pages(page, order);
 }
 
-#ifndef MAINTENANCE_IN_CMD
-#define MAINTENANCE_IN_CMD 0xa3
-#endif
-
-static unsigned char allow_ops[] = { TEST_UNIT_READY, REQUEST_SENSE,
-	INQUIRY, READ_CAPACITY, READ_BUFFER, READ_6, READ_10, READ_12,
-	READ_16, MODE_SENSE, MODE_SENSE_10, LOG_SENSE, REPORT_LUNS,
-	SERVICE_ACTION_IN, RECEIVE_DIAGNOSTIC, READ_LONG, MAINTENANCE_IN_CMD
-};
-
-static int
-sg_allow_access(unsigned char opcode, char dev_type)
-{
-	int k;
-
-	if (TYPE_SCANNER == dev_type)	/* TYPE_ROM maybe burner */
-		return 1;
-	for (k = 0; k < sizeof (allow_ops); ++k) {
-		if (opcode == allow_ops[k])
-			return 1;
-	}
-	return 0;
-}
-
 #ifdef CONFIG_SCSI_PROC_FS
 static int
 sg_idr_max_id(int id, void *p, void *data)

drivers/scsi/sr.c

@@ -673,24 +673,20 @@ static int sr_probe(struct device *dev)
 static void get_sectorsize(struct scsi_cd *cd)
 {
 	unsigned char cmd[10];
-	unsigned char *buffer;
+	unsigned char buffer[8];
 	int the_result, retries = 3;
 	int sector_size;
 	struct request_queue *queue;
 
-	buffer = kmalloc(512, GFP_KERNEL | GFP_DMA);
-	if (!buffer)
-		goto Enomem;
-
 	do {
 		cmd[0] = READ_CAPACITY;
 		memset((void *) &cmd[1], 0, 9);
-		memset(buffer, 0, 8);
+		memset(buffer, 0, sizeof(buffer));
 
 		/* Do the command and wait.. */
 		the_result = scsi_execute_req(cd->device, cmd, DMA_FROM_DEVICE,
-					      buffer, 8, NULL, SR_TIMEOUT,
-					      MAX_RETRIES);
+					      buffer, sizeof(buffer), NULL,
+					      SR_TIMEOUT, MAX_RETRIES);
 
 		retries--;
 
@@ -745,14 +741,8 @@ static void get_sectorsize(struct scsi_cd *cd)
 
 	queue = cd->device->request_queue;
 	blk_queue_hardsect_size(queue, sector_size);
-out:
-	kfree(buffer);
-	return;
 
-Enomem:
-	cd->capacity = 0x1fffff;
-	cd->device->sector_size = 2048;	/* A guess, just in case */
-	goto out;
+	return;
 }
 
 static void get_capabilities(struct scsi_cd *cd)

drivers/xen/xenbus/xenbus_client.c

@@ -117,7 +117,7 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev,
 	char *path;
 
 	va_start(ap, pathfmt);
-	path = kvasprintf(GFP_KERNEL, pathfmt, ap);
+	path = kvasprintf(GFP_NOIO | __GFP_HIGH, pathfmt, ap);
 	va_end(ap);
 
 	if (!path) {

drivers/xen/xenbus/xenbus_xs.c

@@ -283,9 +283,9 @@ static char *join(const char *dir, const char *name)
 	char *buffer;
 
 	if (strlen(name) == 0)
-		buffer = kasprintf(GFP_KERNEL, "%s", dir);
+		buffer = kasprintf(GFP_NOIO | __GFP_HIGH, "%s", dir);
 	else
-		buffer = kasprintf(GFP_KERNEL, "%s/%s", dir, name);
+		buffer = kasprintf(GFP_NOIO | __GFP_HIGH, "%s/%s", dir, name);
 	return (!buffer) ? ERR_PTR(-ENOMEM) : buffer;
 }
 
@@ -297,7 +297,7 @@ static char **split(char *strings, unsigned int len, unsigned int *num)
 	*num = count_strings(strings, len);
 
 	/* Transfer to one big alloc for easy freeing. */
-	ret = kmalloc(*num * sizeof(char *) + len, GFP_KERNEL);
+	ret = kmalloc(*num * sizeof(char *) + len, GFP_NOIO | __GFP_HIGH);
 	if (!ret) {
 		kfree(strings);
 		return ERR_PTR(-ENOMEM);
@@ -751,7 +751,7 @@ static int process_msg(void)
 	}
 
 
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
+	msg = kmalloc(sizeof(*msg), GFP_NOIO | __GFP_HIGH);
 	if (msg == NULL) {
 		err = -ENOMEM;
 		goto out;
@@ -763,7 +763,7 @@ static int process_msg(void)
 		goto out;
 	}
 
-	body = kmalloc(msg->hdr.len + 1, GFP_KERNEL);
+	body = kmalloc(msg->hdr.len + 1, GFP_NOIO | __GFP_HIGH);
 	if (body == NULL) {
 		kfree(msg);
 		err = -ENOMEM;

fs/Makefile

@@ -19,6 +19,7 @@ else
 obj-y +=	no-block.o
 endif
 
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
 obj-$(CONFIG_INOTIFY)		+= inotify.o
 obj-$(CONFIG_INOTIFY_USER)	+= inotify_user.o
 obj-$(CONFIG_EPOLL)		+= eventpoll.o

fs/bio.c

@@ -28,25 +28,10 @@
 #include <linux/blktrace_api.h>
 #include <scsi/sg.h>		/* for struct sg_iovec */
 
-#define BIO_POOL_SIZE 2
-
 static struct kmem_cache *bio_slab __read_mostly;
 
-#define BIOVEC_NR_POOLS 6
-
-/*
- * a small number of entries is fine, not going to be performance critical.
- * basically we just need to survive
- */
-#define BIO_SPLIT_ENTRIES 2
 mempool_t *bio_split_pool __read_mostly;
 
-struct biovec_slab {
-	int nr_vecs;
-	char *name; 
-	struct kmem_cache *slab;
-};
-
 /*
  * if you change this list, also change bvec_alloc or things will
  * break badly! cannot be bigger than what you can fit into an
@@ -59,24 +44,18 @@ static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
 };
 #undef BV
 
-/*
- * 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[].
- */
-struct bio_set {
-	mempool_t *bio_pool;
-	mempool_t *bvec_pools[BIOVEC_NR_POOLS];
-};
-
 /*
  * fs_bio_set is the bio_set containing bio and iovec memory pools used by
  * IO code that does not need private memory pools.
  */
-static struct bio_set *fs_bio_set;
+struct bio_set *fs_bio_set;
+
+unsigned int bvec_nr_vecs(unsigned short idx)
+{
+	return bvec_slabs[idx].nr_vecs;
+}
 
-static inline struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
+struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
 {
 	struct bio_vec *bvl;
 
@@ -117,6 +96,9 @@ void bio_free(struct bio *bio, struct bio_set *bio_set)
 		mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]);
 	}
 
+	if (bio_integrity(bio))
+		bio_integrity_free(bio, bio_set);
+
 	mempool_free(bio, bio_set->bio_pool);
 }
 
@@ -275,9 +257,19 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
 {
 	struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
 
-	if (b) {
-		b->bi_destructor = bio_fs_destructor;
-		__bio_clone(b, bio);
+	if (!b)
+		return NULL;
+
+	b->bi_destructor = bio_fs_destructor;
+	__bio_clone(b, bio);
+
+	if (bio_integrity(bio)) {
+		int ret;
+
+		ret = bio_integrity_clone(b, bio, fs_bio_set);
+
+		if (ret < 0)
+			return NULL;
 	}
 
 	return b;
@@ -333,10 +325,19 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		if (page == prev->bv_page &&
 		    offset == prev->bv_offset + prev->bv_len) {
 			prev->bv_len += len;
-			if (q->merge_bvec_fn &&
-			    q->merge_bvec_fn(q, bio, prev) < len) {
-				prev->bv_len -= len;
-				return 0;
+
+			if (q->merge_bvec_fn) {
+				struct bvec_merge_data bvm = {
+					.bi_bdev = bio->bi_bdev,
+					.bi_sector = bio->bi_sector,
+					.bi_size = bio->bi_size,
+					.bi_rw = bio->bi_rw,
+				};
+
+				if (q->merge_bvec_fn(q, &bvm, prev) < len) {
+					prev->bv_len -= len;
+					return 0;
+				}
 			}
 
 			goto done;
@@ -377,11 +378,18 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	 * queue to get further control
 	 */
 	if (q->merge_bvec_fn) {
+		struct bvec_merge_data bvm = {
+			.bi_bdev = bio->bi_bdev,
+			.bi_sector = bio->bi_sector,
+			.bi_size = bio->bi_size,
+			.bi_rw = bio->bi_rw,
+		};
+
 		/*
 		 * merge_bvec_fn() returns number of bytes it can accept
 		 * at this offset
 		 */
-		if (q->merge_bvec_fn(q, bio, bvec) < len) {
+		if (q->merge_bvec_fn(q, &bvm, bvec) < len) {
 			bvec->bv_page = NULL;
 			bvec->bv_len = 0;
 			bvec->bv_offset = 0;
@@ -1249,6 +1257,9 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
 	bp->bio1.bi_private = bi;
 	bp->bio2.bi_private = pool;
 
+	if (bio_integrity(bi))
+		bio_integrity_split(bi, bp, first_sectors);
+
 	return bp;
 }
 
@@ -1290,6 +1301,7 @@ void bioset_free(struct bio_set *bs)
 	if (bs->bio_pool)
 		mempool_destroy(bs->bio_pool);
 
+	bioset_integrity_free(bs);
 	biovec_free_pools(bs);
 
 	kfree(bs);
@@ -1306,6 +1318,9 @@ struct bio_set *bioset_create(int bio_pool_size, int bvec_pool_size)
 	if (!bs->bio_pool)
 		goto bad;
 
+	if (bioset_integrity_create(bs, bio_pool_size))
+		goto bad;
+
 	if (!biovec_create_pools(bs, bvec_pool_size))
 		return bs;
 
@@ -1332,6 +1347,7 @@ static int __init init_bio(void)
 {
 	bio_slab = KMEM_CACHE(bio, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
+	bio_integrity_init_slab();
 	biovec_init_slabs();
 
 	fs_bio_set = bioset_create(BIO_POOL_SIZE, 2);

fs/ramfs/file-mmu.c

@@ -45,6 +45,7 @@ const struct file_operations ramfs_file_operations = {
 	.mmap		= generic_file_mmap,
 	.fsync		= simple_sync_file,
 	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
 	.llseek		= generic_file_llseek,
 };
 

fs/ramfs/file-nommu.c

@@ -43,6 +43,7 @@ const struct file_operations ramfs_file_operations = {
 	.aio_write		= generic_file_aio_write,
 	.fsync			= simple_sync_file,
 	.splice_read		= generic_file_splice_read,
+	.splice_write		= generic_file_splice_write,
 	.llseek			= generic_file_llseek,
 };
 

fs/splice.c

@@ -379,13 +379,22 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 				lock_page(page);
 
 			/*
-			 * page was truncated, stop here. if this isn't the
-			 * first page, we'll just complete what we already
-			 * added
+			 * Page was truncated, or invalidated by the
+			 * filesystem.  Redo the find/create, but this time the
+			 * page is kept locked, so there's no chance of another
+			 * race with truncate/invalidate.
 			 */
 			if (!page->mapping) {
 				unlock_page(page);
-				break;
+				page = find_or_create_page(mapping, index,
+						mapping_gfp_mask(mapping));
+
+				if (!page) {
+					error = -ENOMEM;
+					break;
+				}
+				page_cache_release(pages[page_nr]);
+				pages[page_nr] = page;
 			}
 			/*
 			 * page was already under io and is now done, great

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 */

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 */
 

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;
 };
 

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
 };
 
 /* 

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

kernel/exit.c

@@ -13,6 +13,7 @@
 #include <linux/personality.h>
 #include <linux/tty.h>
 #include <linux/mnt_namespace.h>
+#include <linux/iocontext.h>
 #include <linux/key.h>
 #include <linux/security.h>
 #include <linux/cpu.h>

kernel/fork.c

@@ -23,6 +23,7 @@
 #include <linux/sem.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/iocontext.h>
 #include <linux/key.h>
 #include <linux/binfmts.h>
 #include <linux/mman.h>