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
  ...

16 files changed, 959 insertions, 157 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 3e97f2bc446f..1ab7c15c8d7a 100644
--- a/block/Kconfig
+++ b/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
diff --git a/block/Makefile b/block/Makefile
index 5a43c7d79594..208000b0750d 100644
--- a/block/Makefile
+++ b/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
diff --git a/block/as-iosched.c b/block/as-iosched.c
index 743f33a01a07..9735acb5b4f5 100644
--- a/block/as-iosched.c
+++ b/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();
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 1905aaba49fb..dbc7f42b5d2b 100644
--- a/block/blk-core.c
+++ b/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 @@ end_io:
 		 */
 		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);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
new file mode 100644
index 000000000000..3f1a8478cc38
--- /dev/null
+++ b/block/blk-integrity.c
@@ -0,0 +1,381 @@
+/*
+ * blk-integrity.c - Block layer data integrity extensions
+ *
+ * Copyright (C) 2007, 2008 Oracle Corporation
+ * Written by: Martin K. Petersen <martin.petersen@oracle.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 License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
+ * USA.
+ *
+ */
+
+#include <linux/blkdev.h>
+#include <linux/mempool.h>
+#include <linux/bio.h>
+#include <linux/scatterlist.h>
+
+#include "blk.h"
+
+static struct kmem_cache *integrity_cachep;
+
+/**
+ * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
+ * @rq:		request with integrity metadata attached
+ *
+ * Description: Returns the number of elements required in a
+ * scatterlist corresponding to the integrity metadata in a request.
+ */
+int blk_rq_count_integrity_sg(struct request *rq)
+{
+	struct bio_vec *iv, *ivprv;
+	struct req_iterator iter;
+	unsigned int segments;
+
+	ivprv = NULL;
+	segments = 0;
+
+	rq_for_each_integrity_segment(iv, rq, iter) {
+
+		if (!ivprv || !BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+			segments++;
+
+		ivprv = iv;
+	}
+
+	return segments;
+}
+EXPORT_SYMBOL(blk_rq_count_integrity_sg);
+
+/**
+ * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
+ * @rq:		request with integrity metadata attached
+ * @sglist:	target scatterlist
+ *
+ * Description: Map the integrity vectors in request into a
+ * scatterlist.  The scatterlist must be big enough to hold all
+ * elements.  I.e. sized using blk_rq_count_integrity_sg().
+ */
+int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist)
+{
+	struct bio_vec *iv, *ivprv;
+	struct req_iterator iter;
+	struct scatterlist *sg;
+	unsigned int segments;
+
+	ivprv = NULL;
+	sg = NULL;
+	segments = 0;
+
+	rq_for_each_integrity_segment(iv, rq, iter) {
+
+		if (ivprv) {
+			if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+				goto new_segment;
+
+			sg->length += iv->bv_len;
+		} else {
+new_segment:
+			if (!sg)
+				sg = sglist;
+			else {
+				sg->page_link &= ~0x02;
+				sg = sg_next(sg);
+			}
+
+			sg_set_page(sg, iv->bv_page, iv->bv_len, iv->bv_offset);
+			segments++;
+		}
+
+		ivprv = iv;
+	}
+
+	if (sg)
+		sg_mark_end(sg);
+
+	return segments;
+}
+EXPORT_SYMBOL(blk_rq_map_integrity_sg);
+
+/**
+ * blk_integrity_compare - Compare integrity profile of two block devices
+ * @b1:		Device to compare
+ * @b2:		Device to compare
+ *
+ * Description: Meta-devices like DM and MD need to verify that all
+ * sub-devices use the same integrity format before advertising to
+ * upper layers that they can send/receive integrity metadata.  This
+ * function can be used to check whether two block devices have
+ * compatible integrity formats.
+ */
+int blk_integrity_compare(struct block_device *bd1, struct block_device *bd2)
+{
+	struct blk_integrity *b1 = bd1->bd_disk->integrity;
+	struct blk_integrity *b2 = bd2->bd_disk->integrity;
+
+	BUG_ON(bd1->bd_disk == NULL);
+	BUG_ON(bd2->bd_disk == NULL);
+
+	if (!b1 || !b2)
+		return 0;
+
+	if (b1->sector_size != b2->sector_size) {
+		printk(KERN_ERR "%s: %s/%s sector sz %u != %u\n", __func__,
+		       bd1->bd_disk->disk_name, bd2->bd_disk->disk_name,
+		       b1->sector_size, b2->sector_size);
+		return -1;
+	}
+
+	if (b1->tuple_size != b2->tuple_size) {
+		printk(KERN_ERR "%s: %s/%s tuple sz %u != %u\n", __func__,
+		       bd1->bd_disk->disk_name, bd2->bd_disk->disk_name,
+		       b1->tuple_size, b2->tuple_size);
+		return -1;
+	}
+
+	if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) {
+		printk(KERN_ERR "%s: %s/%s tag sz %u != %u\n", __func__,
+		       bd1->bd_disk->disk_name, bd2->bd_disk->disk_name,
+		       b1->tag_size, b2->tag_size);
+		return -1;
+	}
+
+	if (strcmp(b1->name, b2->name)) {
+		printk(KERN_ERR "%s: %s/%s type %s != %s\n", __func__,
+		       bd1->bd_disk->disk_name, bd2->bd_disk->disk_name,
+		       b1->name, b2->name);
+		return -1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(blk_integrity_compare);
+
+struct integrity_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct blk_integrity *, char *);
+	ssize_t (*store)(struct blk_integrity *, const char *, size_t);
+};
+
+static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr,
+				   char *page)
+{
+	struct blk_integrity *bi =
+		container_of(kobj, struct blk_integrity, kobj);
+	struct integrity_sysfs_entry *entry =
+		container_of(attr, struct integrity_sysfs_entry, attr);
+
+	return entry->show(bi, page);
+}
+
+static ssize_t integrity_attr_store(struct kobject *kobj,
+				    struct attribute *attr, const char *page,
+				    size_t count)
+{
+	struct blk_integrity *bi =
+		container_of(kobj, struct blk_integrity, kobj);
+	struct integrity_sysfs_entry *entry =
+		container_of(attr, struct integrity_sysfs_entry, attr);
+	ssize_t ret = 0;
+
+	if (entry->store)
+		ret = entry->store(bi, page, count);
+
+	return ret;
+}
+
+static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
+{
+	if (bi != NULL && bi->name != NULL)
+		return sprintf(page, "%s\n", bi->name);
+	else
+		return sprintf(page, "none\n");
+}
+
+static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
+{
+	if (bi != NULL)
+		return sprintf(page, "%u\n", bi->tag_size);
+	else
+		return sprintf(page, "0\n");
+}
+
+static ssize_t integrity_read_store(struct blk_integrity *bi,
+				    const char *page, size_t count)
+{
+	char *p = (char *) page;
+	unsigned long val = simple_strtoul(p, &p, 10);
+
+	if (val)
+		bi->flags |= INTEGRITY_FLAG_READ;
+	else
+		bi->flags &= ~INTEGRITY_FLAG_READ;
+
+	return count;
+}
+
+static ssize_t integrity_read_show(struct blk_integrity *bi, char *page)
+{
+	return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_READ) != 0);
+}
+
+static ssize_t integrity_write_store(struct blk_integrity *bi,
+				     const char *page, size_t count)
+{
+	char *p = (char *) page;
+	unsigned long val = simple_strtoul(p, &p, 10);
+
+	if (val)
+		bi->flags |= INTEGRITY_FLAG_WRITE;
+	else
+		bi->flags &= ~INTEGRITY_FLAG_WRITE;
+
+	return count;
+}
+
+static ssize_t integrity_write_show(struct blk_integrity *bi, char *page)
+{
+	return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_WRITE) != 0);
+}
+
+static struct integrity_sysfs_entry integrity_format_entry = {
+	.attr = { .name = "format", .mode = S_IRUGO },
+	.show = integrity_format_show,
+};
+
+static struct integrity_sysfs_entry integrity_tag_size_entry = {
+	.attr = { .name = "tag_size", .mode = S_IRUGO },
+	.show = integrity_tag_size_show,
+};
+
+static struct integrity_sysfs_entry integrity_read_entry = {
+	.attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
+	.show = integrity_read_show,
+	.store = integrity_read_store,
+};
+
+static struct integrity_sysfs_entry integrity_write_entry = {
+	.attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR },
+	.show = integrity_write_show,
+	.store = integrity_write_store,
+};
+
+static struct attribute *integrity_attrs[] = {
+	&integrity_format_entry.attr,
+	&integrity_tag_size_entry.attr,
+	&integrity_read_entry.attr,
+	&integrity_write_entry.attr,
+	NULL,
+};
+
+static struct sysfs_ops integrity_ops = {
+	.show	= &integrity_attr_show,
+	.store	= &integrity_attr_store,
+};
+
+static int __init blk_dev_integrity_init(void)
+{
+	integrity_cachep = kmem_cache_create("blkdev_integrity",
+					     sizeof(struct blk_integrity),
+					     0, SLAB_PANIC, NULL);
+	return 0;
+}
+subsys_initcall(blk_dev_integrity_init);
+
+static void blk_integrity_release(struct kobject *kobj)
+{
+	struct blk_integrity *bi =
+		container_of(kobj, struct blk_integrity, kobj);
+
+	kmem_cache_free(integrity_cachep, bi);
+}
+
+static struct kobj_type integrity_ktype = {
+	.default_attrs	= integrity_attrs,
+	.sysfs_ops	= &integrity_ops,
+	.release	= blk_integrity_release,
+};
+
+/**
+ * blk_integrity_register - Register a gendisk as being integrity-capable
+ * @disk:	struct gendisk pointer to make integrity-aware
+ * @template:	integrity profile
+ *
+ * Description: When a device needs to advertise itself as being able
+ * to send/receive integrity metadata it must use this function to
+ * register the capability with the block layer.  The template is a
+ * blk_integrity struct with values appropriate for the underlying
+ * hardware.  See Documentation/block/data-integrity.txt.
+ */
+int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
+{
+	struct blk_integrity *bi;
+
+	BUG_ON(disk == NULL);
+	BUG_ON(template == NULL);
+
+	if (disk->integrity == NULL) {
+		bi = kmem_cache_alloc(integrity_cachep,
+						GFP_KERNEL | __GFP_ZERO);
+		if (!bi)
+			return -1;
+
+		if (kobject_init_and_add(&bi->kobj, &integrity_ktype,
+					 &disk->dev.kobj, "%s", "integrity")) {
+			kmem_cache_free(integrity_cachep, bi);
+			return -1;
+		}
+
+		kobject_uevent(&bi->kobj, KOBJ_ADD);
+
+		bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
+		bi->sector_size = disk->queue->hardsect_size;
+		disk->integrity = bi;
+	} else
+		bi = disk->integrity;
+
+	/* Use the provided profile as template */
+	bi->name = template->name;
+	bi->generate_fn = template->generate_fn;
+	bi->verify_fn = template->verify_fn;
+	bi->tuple_size = template->tuple_size;
+	bi->set_tag_fn = template->set_tag_fn;
+	bi->get_tag_fn = template->get_tag_fn;
+	bi->tag_size = template->tag_size;
+
+	return 0;
+}
+EXPORT_SYMBOL(blk_integrity_register);
+
+/**
+ * blk_integrity_unregister - Remove block integrity profile
+ * @disk:	disk whose integrity profile to deallocate
+ *
+ * Description: This function frees all memory used by the block
+ * integrity profile.  To be called at device teardown.
+ */
+void blk_integrity_unregister(struct gendisk *disk)
+{
+	struct blk_integrity *bi;
+
+	if (!disk || !disk->integrity)
+		return;
+
+	bi = disk->integrity;
+
+	kobject_uevent(&bi->kobj, KOBJ_REMOVE);
+	kobject_del(&bi->kobj);
+	kobject_put(&disk->dev.kobj);
+	kmem_cache_free(integrity_cachep, bi);
+}
+EXPORT_SYMBOL(blk_integrity_unregister);
diff --git a/block/blk-map.c b/block/blk-map.c
index 0b1af5a3537c..ddd96fb11a7d 100644
--- a/block/blk-map.c
+++ b/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
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 651136aae76e..5efc9e7a68b7 100644
--- a/block/blk-merge.c
+++ b/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
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 8dd86418f35d..dfc77012843f 100644
--- a/block/blk-settings.c
+++ b/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)
 {
@@ -315,6 +314,23 @@ 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
  * @dma_drain_needed: fn which returns non-zero if drain is necessary
diff --git a/block/blk.h b/block/blk.h
index 59776ab4742a..c79f30e1df52 100644
--- a/block/blk.h
+++ b/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
diff --git a/block/blktrace.c b/block/blktrace.c
index 8d3a27780260..eb9651ccb241 100644
--- a/block/blktrace.c
+++ b/block/blktrace.c
@@ -244,6 +244,7 @@ err:
 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 @@ err:
 	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);
diff --git a/block/bsg.c b/block/bsg.c
index 54d617f7df3e..93e757d7174b 100644
--- a/block/bsg.c
+++ b/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 @@ unlock:
 }
 
 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);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index d01b411c72f0..1e2aff812ee2 100644
--- a/block/cfq-iosched.c
+++ b/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);
 
@@ -866,6 +888,12 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 		return;
 
 	/*
+	 * still requests with the driver, don't idle
+	 */
+	if (cfqd->rq_in_driver)
+		return;
+
+	/*
 	 * task has exited, don't wait
 	 */
 	cic = cfqd->activ