From a82afdfcb8c0df09776b6458af6b68fc58b2e87b Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Jul 2009 17:48:16 +0900
Subject: block: use the same failfast bits for bio and request

bio and request use the same set of failfast bits.  This patch makes
the following changes to simplify things.

* enumify BIO_RW* bits and reorder bits such that BIOS_RW_FAILFAST_*
  bits coincide with __REQ_FAILFAST_* bits.

* The above pushes BIO_RW_AHEAD out of sync with __REQ_FAILFAST_DEV
  but the matching is useless anyway.  init_request_from_bio() is
  responsible for setting FAILFAST bits on FS requests and non-FS
  requests never use BIO_RW_AHEAD.  Drop the code and comment from
  blk_rq_bio_prep().

* Define REQ_FAILFAST_MASK which is OR of all FAILFAST bits and
  simplify FAILFAST flags handling in init_request_from_bio().

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

(limited to 'block/blk-core.c')

diff --git a/block/blk-core.c b/block/blk-core.c
index e3299a77a0d8..4daae1ee2b23 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1111,17 +1111,13 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	req->cmd_type = REQ_TYPE_FS;
 
 	/*
-	 * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
+	 * Inherit FAILFAST from bio (for read-ahead, and explicit
+	 * FAILFAST).  FAILFAST flags are identical for req and bio.
 	 */
 	if (bio_rw_ahead(bio))
-		req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-				   REQ_FAILFAST_DRIVER);
-	if (bio_failfast_dev(bio))
-		req->cmd_flags |= REQ_FAILFAST_DEV;
-	if (bio_failfast_transport(bio))
-		req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	if (bio_failfast_driver(bio))
-		req->cmd_flags |= REQ_FAILFAST_DRIVER;
+		req->cmd_flags |= REQ_FAILFAST_MASK;
+	else
+		req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
 
 	if (unlikely(bio_discard(bio))) {
 		req->cmd_flags |= REQ_DISCARD;
@@ -2239,9 +2235,8 @@ EXPORT_SYMBOL(__blk_end_request_cur);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and
-	   we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */
-	rq->cmd_flags |= (bio->bi_rw & 3);
+	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
+	rq->cmd_flags |= bio->bi_rw & REQ_RW;
 
 	if (bio_has_data(bio)) {
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
-- 
cgit v1.2.3


From 80a761fd33cf812f771e212139157bf8f58d4b3f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Jul 2009 17:48:17 +0900
Subject: block: implement mixed merge of different failfast requests

Failfast has characteristics from other attributes.  When issuing,
executing and successuflly completing requests, failfast doesn't make
any difference.  It only affects how a request is handled on failure.
Allowing requests with different failfast settings to be merged cause
normal IOs to fail prematurely while not allowing has performance
penalties as failfast is used for read aheads which are likely to be
located near in-flight or to-be-issued normal IOs.

This patch introduces the concept of 'mixed merge'.  A request is a
mixed merge if it is merge of segments which require different
handling on failure.  Currently the only mixable attributes are
failfast ones (or lack thereof).

When a bio with different failfast settings is added to an existing
request or requests of different failfast settings are merged, the
merged request is marked mixed.  Each bio carries failfast settings
and the request always tracks failfast state of the first bio.  When
the request fails, blk_rq_err_bytes() can be used to determine how
many bytes can be safely failed without crossing into an area which
requires further retrials.

This allows request merging regardless of failfast settings while
keeping the failure handling correct.

This patch only implements mixed merge but doesn't enable it.  The
next one will update SCSI to make use of mixed merge.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Niel Lambrechts <niel.lambrechts@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c       | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++
 block/blk-merge.c      | 43 ++++++++++++++++++++++
 block/blk.h            |  1 +
 include/linux/blkdev.h | 23 +++++++++---
 4 files changed, 161 insertions(+), 5 deletions(-)

(limited to 'block/blk-core.c')

diff --git a/block/blk-core.c b/block/blk-core.c
index 4daae1ee2b23..c822239bcc9d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1157,6 +1157,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
 	const int unplug = bio_unplug(bio);
+	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	int rw_flags;
 
 	if (bio_barrier(bio) && bio_has_data(bio) &&
@@ -1186,6 +1187,9 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		trace_block_bio_backmerge(q, bio);
 
+		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+			blk_rq_set_mixed_merge(req);
+
 		req->biotail->bi_next = bio;
 		req->biotail = bio;
 		req->__data_len += bytes;
@@ -1205,6 +1209,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		trace_block_bio_frontmerge(q, bio);
 
+		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+			blk_rq_set_mixed_merge(req);
+			req->cmd_flags &= ~REQ_FAILFAST_MASK;
+			req->cmd_flags |= ff;
+		}
+
 		bio->bi_next = req->bio;
 		req->bio = bio;
 
@@ -1649,6 +1659,50 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ *     A request could be merge of IOs which require different failure
+ *     handling.  This function determines the number of bytes which
+ *     can be failed from the beginning of the request without
+ *     crossing into area which need to be retried further.
+ *
+ * Return:
+ *     The number of bytes to fail.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	unsigned int bytes = 0;
+	struct bio *bio;
+
+	if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+		return blk_rq_bytes(rq);
+
+	/*
+	 * Currently the only 'mixing' which can happen is between
+	 * different fastfail types.  We can safely fail portions
+	 * which have all the failfast bits that the first one has -
+	 * the ones which are at least as eager to fail as the first
+	 * one.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		if ((bio->bi_rw & ff) != ff)
+			break;
+		bytes += bio->bi_size;
+	}
+
+	/* this could lead to infinite loop */
+	BUG_ON(blk_rq_bytes(rq) && !bytes);
+	return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
@@ -1995,6 +2049,12 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (blk_fs_request(req) || blk_discard_rq(req))
 		req->__sector += total_bytes >> 9;
 
+	/* mixed attributes always follow the first bio */
+	if (req->cmd_flags & REQ_MIXED_MERGE) {
+		req->cmd_flags &= ~REQ_FAILFAST_MASK;
+		req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+	}
+
 	/*
 	 * If total number of sectors is less than the first segment
 	 * size, something has gone terribly wrong.
@@ -2173,6 +2233,25 @@ bool blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(blk_end_request_cur);
 
+/**
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_err);
+
 /**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
@@ -2232,6 +2311,26 @@ bool __blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(__blk_end_request_cur);
 
+/**
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.  Must be called
+ *     with queue lock held.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
+
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
diff --git a/block/blk-merge.c b/block/blk-merge.c
index e1999679a4d5..7c9ca01baa45 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -311,6 +311,36 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+/**
+ * blk_rq_set_mixed_merge - mark a request as mixed merge
+ * @rq: request to mark as mixed merge
+ *
+ * Description:
+ *     @rq is about to be mixed merged.  Make sure the attributes
+ *     which can be mixed are set in each bio and mark @rq as mixed
+ *     merged.
+ */
+void blk_rq_set_mixed_merge(struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	struct bio *bio;
+
+	if (rq->cmd_flags & REQ_MIXED_MERGE)
+		return;
+
+	/*
+	 * @rq will no longer represent mixable attributes for all the
+	 * contained bios.  It will just track those of the first one.
+	 * Distributes the attributs to each bio.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
+			     (bio->bi_rw & REQ_FAILFAST_MASK) != ff);
+		bio->bi_rw |= ff;
+	}
+	rq->cmd_flags |= REQ_MIXED_MERGE;
+}
+
 static void blk_account_io_merge(struct request *req)
 {
 	if (blk_do_io_stat(req)) {
@@ -365,6 +395,19 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (!ll_merge_requests_fn(q, req, next))
 		return 0;
 
+	/*
+	 * If failfast settings disagree or any of the two is already
+	 * a mixed merge, mark both as mixed before proceeding.  This
+	 * makes sure that all involved bios have mixable attributes
+	 * set properly.
+	 */
+	if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE ||
+	    (req->cmd_flags & REQ_FAILFAST_MASK) !=
+	    (next->cmd_flags & REQ_FAILFAST_MASK)) {
+		blk_rq_set_mixed_merge(req);
+		blk_rq_set_mixed_merge(next);
+	}
+
 	/*
 	 * At this point we have either done a back merge
 	 * or front merge. We need the smaller start_time of
diff --git a/block/blk.h b/block/blk.h
index 3fae6add5430..5ee3d7e72feb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -104,6 +104,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 int attempt_back_merge(struct request_queue *q, struct request *rq);
 int attempt_front_merge(struct request_queue *q, struct request *rq);
 void blk_recalc_rq_segments(struct request *rq);
+void blk_rq_set_mixed_merge(struct request *rq);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c3015736d814..650b6a9cb679 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -115,6 +115,7 @@ enum rq_flag_bits {
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
 	__REQ_IO_STAT,		/* account I/O stat */
+	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -143,6 +144,7 @@ enum rq_flag_bits {
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
 #define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 #define REQ_IO_STAT	(1 << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE	(1 << __REQ_MIXED_MERGE)
 
 #define REQ_FAILFAST_MASK	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \
 				 REQ_FAILFAST_DRIVER)
@@ -832,11 +834,13 @@ static inline void blk_run_address_space(struct address_space *mapping)
 }
 
 /*
- * blk_rq_pos()		: the current sector
- * blk_rq_bytes()	: bytes left in the entire request
- * blk_rq_cur_bytes()	: bytes left in the current segment
- * blk_rq_sectors()	: sectors left in the entire request
- * blk_rq_cur_sectors()	: sectors left in the current segment
+ * blk_rq_pos()			: the current sector
+ * blk_rq_bytes()		: bytes left in the entire request
+ * blk_rq_cur_bytes()		: bytes left in the current segment
+ * blk_rq_err_bytes()		: bytes left till the next error boundary
+ * blk_rq_sectors()		: sectors left in the entire request
+ * blk_rq_cur_sectors()		: sectors left in the current segment
+ * blk_rq_err_sectors()		: sectors left till the next error boundary
  */
 static inline sector_t blk_rq_pos(const struct request *rq)
 {
@@ -853,6 +857,8 @@ static inline int blk_rq_cur_bytes(const struct request *rq)
 	return rq->bio ? bio_cur_bytes(rq->bio) : 0;
 }
 
+extern unsigned int blk_rq_err_bytes(const struct request *rq);
+
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
 	return blk_rq_bytes(rq) >> 9;
@@ -863,6 +869,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> 9;
 }
 
+static inline unsigned int blk_rq_err_sectors(const struct request *rq)
+{
+	return blk_rq_err_bytes(rq) >> 9;
+}
+
 /*
  * Request issue related functions.
  */
@@ -889,10 +900,12 @@ extern bool blk_end_request(struct request *rq, int error,
 			    unsigned int nr_bytes);
 extern void blk_end_request_all(struct request *rq, int error);
 extern bool blk_end_request_cur(struct request *rq, int error);
+extern bool blk_end_request_err(struct request *rq, int error);
 extern bool __blk_end_request(struct request *rq, int error,
 			      unsigned int nr_bytes);
 extern void __blk_end_request_all(struct request *rq, int error);
 extern bool __blk_end_request_cur(struct request *rq, int error);
+extern bool __blk_end_request_err(struct request *rq, int error);
 
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
-- 
cgit v1.2.3


From 1f98a13f623e0ef666690a18c1250335fc6d7ef1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Fri, 11 Sep 2009 14:32:04 +0200
Subject: bio: first step in sanitizing the bio->bi_rw flag testing

Get rid of any functions that test for these bits and make callers
use bio_rw_flagged() directly. Then it is at least directly apparent
what variable and flag they check.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c            | 25 +++++++++++++------------
 block/cfq-iosched.c         |  2 +-
 block/elevator.c            |  3 ++-
 drivers/block/loop.c        |  2 +-
 drivers/md/dm-raid1.c       |  2 +-
 drivers/md/dm-stripe.c      |  2 +-
 drivers/md/dm.c             | 12 ++++++------
 drivers/md/linear.c         |  2 +-
 drivers/md/multipath.c      |  4 ++--
 drivers/md/raid0.c          |  2 +-
 drivers/md/raid1.c          | 14 ++++++++------
 drivers/md/raid10.c         |  6 +++---
 drivers/md/raid5.c          |  2 +-
 drivers/staging/dst/dcore.c |  5 +++--
 fs/btrfs/volumes.c          |  4 ++--
 include/linux/bio.h         | 25 +++++++------------------
 include/linux/blkdev.h      |  2 +-
 17 files changed, 54 insertions(+), 60 deletions(-)

(limited to 'block/blk-core.c')

diff --git a/block/blk-core.c b/block/blk-core.c
index c822239bcc9d..52559715cb90 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1114,24 +1114,24 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	 * Inherit FAILFAST from bio (for read-ahead, and explicit
 	 * FAILFAST).  FAILFAST flags are identical for req and bio.
 	 */
-	if (bio_rw_ahead(bio))
+	if (bio_rw_flagged(bio, BIO_RW_AHEAD))
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 	else
 		req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
 
-	if (unlikely(bio_discard(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) {
 		req->cmd_flags |= REQ_DISCARD;
-		if (bio_barrier(bio))
+		if (bio_rw_flagged(bio, BIO_RW_BARRIER))
 			req->cmd_flags |= REQ_SOFTBARRIER;
 		req->q->prepare_discard_fn(req->q, req);
-	} else if (unlikely(bio_barrier(bio)))
+	} else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
 		req->cmd_flags |= REQ_HARDBARRIER;
 
-	if (bio_sync(bio))
+	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		req->cmd_flags |= REQ_RW_SYNC;
-	if (bio_rw_meta(bio))
+	if (bio_rw_flagged(bio, BIO_RW_META))
 		req->cmd_flags |= REQ_RW_META;
-	if (bio_noidle(bio))
+	if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
 		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
@@ -1155,12 +1155,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret;
 	unsigned int bytes = bio->bi_size;
 	const unsigned short prio = bio_prio(bio);
-	const int sync = bio_sync(bio);
-	const int unplug = bio_unplug(bio);
+	const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+	const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG);
 	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	int rw_flags;
 
-	if (bio_barrier(bio) && bio_has_data(bio) &&
+	if (bio_rw_flagged(bio, BIO_RW_BARRIER) && bio_has_data(bio) &&
 	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
@@ -1174,7 +1174,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely(bio_barrier(bio)) || elv_queue_empty(q))
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1470,7 +1470,8 @@ static inline void __generic_make_request(struct bio *bio)
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
-		if (bio_discard(bio) && !q->prepare_discard_fn) {
+		if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+		    !q->prepare_discard_fn) {
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ca0d7e71324b..9e6d0af6c990 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -257,7 +257,7 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic,
  */
 static inline int cfq_bio_sync(struct bio *bio)
 {
-	if (bio_data_dir(bio) == READ || bio_sync(bio))
+	if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		return 1;
 
 	return 0;
diff --git a/block/elevator.c b/block/elevator.c
index ca861927ba41..1975b619c86d 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -79,7 +79,8 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	/*
 	 * Don't merge file system requests and discard requests
 	 */
-	if (bio_discard(bio) != bio_discard(rq->bio))
+	if (bio_rw_flagged(bio, BIO_RW_DISCARD) !=
+	    bio_rw_flagged(rq->bio, BIO_RW_DISCARD))
 		return 0;
 
 	/*
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 5757188cd1fb..bbb79441d895 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -475,7 +475,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
 
 	if (bio_rw(bio) == WRITE) {
-		int barrier = bio_barrier(bio);
+		bool barrier = bio_rw_flagged(bio, BIO_RW_BARRIER);
 		struct file *file = lo->lo_backing_file;
 
 		if (barrier) {
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 33f179e66bf5..cc9dc79b0784 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1129,7 +1129,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	if (error == -EOPNOTSUPP)
 		goto out;
 
-	if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+	if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
 		goto out;
 
 	if (unlikely(error)) {
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 3e563d251733..fde658ccbcec 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -285,7 +285,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio,
 	if (!error)
 		return 0; /* I/O complete */
 
-	if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+	if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
 		return error;
 
 	if (error == -EOPNOTSUPP)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b4845b14740d..ec012f030240 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -586,7 +586,7 @@ static void dec_pending(struct dm_io *io, int error)
 			 */
 			spin_lock_irqsave(&md->deferred_lock, flags);
 			if (__noflush_suspending(md)) {
-				if (!bio_barrier(io->bio))
+				if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER))
 					bio_list_add_head(&md->deferred,
 							  io->bio);
 			} else
@@ -598,7 +598,7 @@ static void dec_pending(struct dm_io *io, int error)
 		io_error = io->error;
 		bio = io->bio;
 
-		if (bio_barrier(bio)) {
+		if (bio_rw_flagged(bio, BIO_RW_BARRIER)) {
 			/*
 			 * There can be just one barrier request so we use
 			 * a per-device variable for error reporting.
@@ -1209,7 +1209,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
 
 	ci.map = dm_get_table(md);
 	if (unlikely(!ci.map)) {
-		if (!bio_barrier(bio))
+		if (!bio_rw_flagged(bio, BIO_RW_BARRIER))
 			bio_io_error(bio);
 		else
 			if (!md->barrier_error)
@@ -1321,7 +1321,7 @@ static int _dm_request(struct request_queue *q, struct bio *bio)
 	 * we have to queue this io for later.
 	 */
 	if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) ||
-	    unlikely(bio_barrier(bio))) {
+	    unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		up_read(&md->io_lock);
 
 		if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) &&
@@ -1344,7 +1344,7 @@ static int dm_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct mapped_device *md = q->queuedata;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
@@ -2164,7 +2164,7 @@ static void dm_wq_work(struct work_struct *work)
 		if (dm_request_based(md))
 			generic_make_request(c);
 		else {
-			if (bio_barrier(c))
+			if (bio_rw_flagged(c, BIO_RW_BARRIER))
 				process_barrier(md, c);
 			else
 				__split_and_process_bio(md, c);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 5fe39c2a3d2b..ea4842905444 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -288,7 +288,7 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
 	sector_t start_sector;
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 7140909f6662..89e76819f61f 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -90,7 +90,7 @@ static void multipath_end_request(struct bio *bio, int error)
 
 	if (uptodate)
 		multipath_end_bh_io(mp_bh, 0);
-	else if (!bio_rw_ahead(bio)) {
+	else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) {
 		/*
 		 * oops, IO error:
 		 */
@@ -144,7 +144,7 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	const int rw = bio_data_dir(bio);
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 898e2bdfee47..f845ed98fec9 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -448,7 +448,7 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio)
 	const int rw = bio_data_dir(bio);
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8726fd7ebce5..ff7ed3335995 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -782,8 +782,9 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	struct bio_list bl;
 	struct page **behind_pages = NULL;
 	const int rw = bio_data_dir(bio);
-	const int do_sync = bio_sync(bio);
-	int cpu, do_barriers;
+	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+	int cpu;
+	bool do_barriers;
 	mdk_rdev_t *blocked_rdev;
 
 	/*
@@ -797,7 +798,8 @@ static int make_request(struct request_queue *q, struct bio * bio)
 
 	md_write_start(mddev, bio); /* wait on superblock update early */
 
-	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+	if (unlikely(!mddev->barriers_work &&
+		     bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		if (rw == WRITE)
 			md_write_end(mddev);
 		bio_endio(bio, -EOPNOTSUPP);
@@ -925,7 +927,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	atomic_set(&r1_bio->remaining, 0);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
-	do_barriers = bio_barrier(bio);
+	do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER);
 	if (do_barriers)
 		set_bit(R1BIO_Barrier, &r1_bio->state);
 
@@ -1600,7 +1602,7 @@ static void raid1d(mddev_t *mddev)
 			 * We already have a nr_pending reference on these rdevs.
 			 */
 			int i;
-			const int do_sync = bio_sync(r1_bio->master_bio);
+			const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
 			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
 			clear_bit(R1BIO_Barrier, &r1_bio->state);
 			for (i=0; i < conf->raid_disks; i++)
@@ -1654,7 +1656,7 @@ static void raid1d(mddev_t *mddev)
 				       (unsigned long long)r1_bio->sector);
 				raid_end_bio_io(r1_bio);
 			} else {
-				const int do_sync = bio_sync(r1_bio->master_bio);
+				const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
 				r1_bio->bios[r1_bio->read_disk] =
 					mddev->ro ? IO_BLOCKED : NULL;
 				r1_bio->read_disk = disk;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3d9020cf6f6e..d0a2152e064f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -796,12 +796,12 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	int i;
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
-	const int do_sync = bio_sync(bio);
+	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
 	struct bio_list bl;
 	unsigned long flags;
 	mdk_rdev_t *blocked_rdev;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
@@ -1610,7 +1610,7 @@ static void raid10d(mddev_t *mddev)
 				raid_end_bio_io(r10_bio);
 				bio_put(bio);
 			} else {
-				const int do_sync = bio_sync(r10_bio->master_bio);
+				const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO);
 				bio_put(bio);
 				rdev = conf->mirrors[mirror].rdev;
 				if (printk_ratelimit())
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b8a2c5dc67ba..826eb3467357 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3606,7 +3606,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 	const int rw = bio_data_dir(bi);
 	int cpu, remaining;
 
-	if (unlikely(bio_barrier(bi))) {
+	if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
 		bio_endio(bi, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c
index fad25b753042..b1c258ca2102 100644
--- a/drivers/staging/dst/dcore.c
+++ b/drivers/staging/dst/dcore.c
@@ -112,8 +112,9 @@ static int dst_request(struct request_queue *q, struct bio *bio)
 		 * I worked with.
 		 *
 		 * Empty barriers are not allowed anyway, see 51fd77bd9f512
-		 * for example, although later it was changed to bio_discard()
-		 * only, which does not work in this case.
+		 * for example, although later it was changed to
+		 * bio_rw_flagged(bio, BIO_RW_DISCARD) only, which does not
+		 * work in this case.
 		 */
 		//err = -EOPNOTSUPP;
 		err = 0;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5dbefd11b4af..5cf405b0828d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -260,7 +260,7 @@ loop_lock:
 		num_run++;
 		batch_run++;
 
-		if (bio_sync(cur))
+		if (bio_rw_flagged(cur, BIO_RW_SYNCIO))
 			num_sync_run++;
 
 		if (need_resched()) {
@@ -2903,7 +2903,7 @@ static noinline int schedule_bio(struct btrfs_root *root,
 	bio->bi_rw |= rw;
 
 	spin_lock(&device->io_lock);
-	if (bio_sync(bio))
+	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		pending_bios = &device->pending_sync_bios;
 	else
 		pending_bios = &device->pending_bios;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 4f8fd0221cd2..5be93f18d842 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -177,28 +177,17 @@ enum bio_rw_flags {
 	BIO_RW_NOIDLE,
 };
 
+/*
+ * First four bits must match between bio->bi_rw and rq->cmd_flags, make
+ * that explicit here.
+ */
+#define BIO_RW_RQ_MASK		0xf
+
 static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
 {
 	return (bio->bi_rw & (1 << flag)) != 0;
 }
 
-/*
- * Old defines, these should eventually be replaced by direct usage of
- * bio_rw_flagged()
- */
-#define bio_barrier(bio)	bio_rw_flagged(bio, BIO_RW_BARRIER)
-#define bio_sync(bio)		bio_rw_flagged(bio, BIO_RW_SYNCIO)
-#define bio_unplug(bio)		bio_rw_flagged(bio, BIO_RW_UNPLUG)
-#define bio_failfast_dev(bio)	bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV)
-#define bio_failfast_transport(bio)	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT)
-#define bio_failfast_driver(bio) 	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER)
-#define bio_rw_ahead(bio)	bio_rw_flagged(bio, BIO_RW_AHEAD)
-#define bio_rw_meta(bio)	bio_rw_flagged(bio, BIO_RW_META)
-#define bio_discard(bio)	bio_rw_flagged(bio, BIO_RW_DISCARD)
-#define bio_noidle(bio)		bio_rw_flagged(bio, BIO_RW_NOIDLE)
-
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
  */
@@ -222,7 +211,7 @@ static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
 #define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
-#define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
+#define bio_empty_barrier(bio)	(bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 650b6a9cb679..88edb62def82 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -86,7 +86,7 @@ enum {
 };
 
 /*
- * request type modified bits. first two bits match BIO_RW* bits, important
+ * request type modified bits. first four bits match BIO_RW* bits, important
  */
 enum rq_flag_bits {
 	__REQ_RW,		/* not set, read. set, write */
-- 
cgit v1.2.3


From fb1e75389bd06fd5987e9cda1b4e0305c782f854 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Thu, 30 Jul 2009 08:18:24 +0200
Subject: block: improve queue_should_plug() by looking at IO depths

Instead of just checking whether this device uses block layer
tagging, we can improve the detection by looking at the maximum
queue depth it has reached. If that crosses 4, then deem it a
queuing device.

This is important on high IOPS devices, since plugging hurts
the performance there (it can be as much as 10-15% of the sys
time).

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c       | 11 +++++++++--
 include/linux/blkdev.h |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'block/blk-core.c')

diff --git a/block/blk-core.c b/block/blk-core.c
index 52559715cb90..93051d151635 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1146,7 +1146,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
  */
 static inline bool queue_should_plug(struct request_queue *q)
 {
-	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+	return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
 }
 
 static int __make_request(struct request_queue *q, struct bio *bio)
@@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
 	 * and to it is freed is accounted as io that is in progress at
 	 * the driver side.
 	 */
-	if (blk_account_rq(rq))
+	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]++;
+		/*
+		 * Mark this device as supporting hardware queuing, if
+		 * we have more IOs in flight than 4.
+		 */
+		if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
+			set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
+	}
 }
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 88edb62def82..98b45633a27e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -459,6 +459,7 @@ struct request_queue
 #define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
+#define QUEUE_FLAG_CQ	       16	/* hardware does queuing */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
@@ -581,6 +582,7 @@ enum {
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
+#define blk_queue_queuing(q)	test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
-- 
cgit v1.2.3


From 01edede41e352e4879a89cdc5468f72ffc89b713 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan.kim@gmail.com>
Date: Tue, 8 Sep 2009 21:56:38 +0200
Subject: block: trace bio queueing trial only when it occurs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If BIO is discarded or cross over end of device,
BIO queueing trial doesn't occur.

Actually the trace was called just before make_request at first:
[PATCH] Block queue IO tracing support (blktrace) as of 2006-03-23
      2056a782f8e7e65fd4bfd027506b4ce1c5e9ccd4

And then 2 patches added some checks between them:
[PATCH] md: check bio address after mapping through partitions
        5ddfe9691c91a244e8d1be597b6428fcefd58103,
[BLOCK] Don't allow empty barriers to be passed down to
queues that don't grok them
        51fd77bd9f512ab6cc9df0733ba1caaab89eb957

It breaks original goal.
Let's trace it only when it happens.

Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'block/blk-core.c')

diff --git a/block/blk-core.c b/block/blk-core.c
index 93051d151635..982d634e67f9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1462,8 +1462,6 @@ static inline void __generic_make_request(struct bio *bio)
 		if (old_sector != -1)
 			trace_block_remap(q, bio, old_dev, old_sector);
 
-		trace_block_bio_queue(q, bio);
-
 		old_sector = bio->bi_sector;
 		old_dev = bio->bi_bdev->bd_dev;
 
@@ -1476,6 +1474,8 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
+		trace_block_bio_queue(q, bio);
+
 		ret = q->make_request_fn(q, bio);
 	} while (ret);
 
-- 
cgit v1.2.3


From a9327cac440be4d8333bba975cbbf76045096275 Mon Sep 17 00:00:00 2001
From: Nikanth Karthikesan <knikanth@suse.de>
Date: Fri, 11 Sep 2009 09:18:54 +0200
Subject: Seperate read and write statistics of in_flight requests

Currently, there is a single in_flight counter measuring the number of
requests in the request_queue. But some monitoring tools would like to
know how many read requests and write requests are in progress. Split the
current in_flight counter into two seperate counters for read and write.

This information is exported as a sysfs attribute, as changing the
currently available stat files would break the existing tools.

Signed-off-by: Nikanth Karthikesan <knikanth@suse.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c      |  6 +++---
 block/blk-merge.c     |  2 +-
 block/genhd.c         |  4 +++-
 drivers/md/dm.c       | 16 ++++++++++------
 fs/partitions/check.c | 12 +++++++++++-
 include/linux/genhd.h | 21 ++++++++++++++-------
 6 files changed, 42 insertions(+), 19 deletions(-)

(limited to 'block/blk-core.c')

diff --git a/block/blk-core.c b/block/blk-core.c
index 982d634e67f9..182ebe3eb9e0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -69,7 +69,7 @@ static void drive_stat_acct(struct request *rq, int new_io)
 		part_stat_inc(cpu, part, merges[rw]);
 	else {
 		part_round_stats(cpu, part);
-		part_inc_in_flight(part);
+		part_inc_in_flight(part, rw);
 	}
 
 	part_stat_unlock();
@@ -1030,7 +1030,7 @@ static void part_round_stats_single(int cpu, struct hd_struct *part,
 
 	if (part->in_flight) {
 		__part_stat_add(cpu, part, time_in_queue,
-				part->in_flight * (now - part->stamp));
+				part_in_flight(part) * (now - part->stamp));
 		__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
 	}
 	part->stamp = now;
@@ -1737,7 +1737,7 @@ static void blk_account_io_done(struct request *req)
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
 		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
+		part_dec_in_flight(part, rw);
 
 		part_stat_unlock();
 	}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b0de8574fdc8..99cb5cf1f447 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req)
 		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 
 		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
+		part_dec_in_flight(part, rq_data_dir(req));
 
 		part_stat_unlock();
 	}
diff --git a/block/genhd.c b/block/genhd.c
index b89328eceee2..5b76bf55d05c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -869,6 +869,7 @@ static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -888,6 +889,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_alignment_offset.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
+	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
@@ -1053,7 +1055,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   part_stat_read(hd, merges[1]),
 			   (unsigned long long)part_stat_read(hd, sectors[1]),
 			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
-			   hd->in_flight,
+			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
 			);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ec012f030240..eee28fac210c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -130,7 +130,7 @@ struct mapped_device {
 	/*
 	 * A list of ios that arrived while we were suspended.
 	 */
-	atomic_t pending;
+	atomic_t pending[2];
 	wait_queue_head_t wait;
 	struct work_struct work;
 	struct bio_list deferred;
@@ -453,13 +453,14 @@ static void start_io_acct(struct dm_io *io)
 {
 	struct mapped_device *md = io->md;
 	int cpu;
+	int rw = bio_data_dir(io->bio);
 
 	io->start_time = jiffies;
 
 	cpu = part_stat_lock();
 	part_round_stats(cpu, &dm_disk(md)->part0);
 	part_stat_unlock();
-	dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending);
+	dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]);
 }
 
 static void end_io_acct(struct dm_io *io)
@@ -479,8 +480,9 @@ static void end_io_acct(struct dm_io *io)
 	 * After this is decremented the bio must not be touched if it is
 	 * a barrier.
 	 */
-	dm_disk(md)->part0.in_flight = pending =
-		atomic_dec_return(&md->pending);
+	dm_disk(md)->part0.in_flight[rw] = pending =
+		atomic_dec_return(&md->pending[rw]);
+	pending += atomic_read(&md->pending[rw^0x1]);
 
 	/* nudge anyone waiting on suspend queue */
 	if (!pending)
@@ -1785,7 +1787,8 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->disk)
 		goto bad_disk;
 
-	atomic_set(&md->pending, 0);
+	atomic_set(&md->pending[0], 0);
+	atomic_set(&md->pending[1], 0);
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
@@ -2088,7 +2091,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
 				break;
 			}
 			spin_unlock_irqrestore(q->queue_lock, flags);
-		} else if (!atomic_read(&md->pending))
+		} else if (!atomic_read(&md->pending[0]) &&
+					!atomic_read(&md->pending[1]))
 			break;
 
 		if (interruptible == TASK_INTERRUPTIBLE &&
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index ea4e6cb29e13..619ba99dfe39 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -248,11 +248,19 @@ ssize_t part_stat_show(struct device *dev,
 		part_stat_read(p, merges[WRITE]),
 		(unsigned long long)part_stat_read(p, sectors[WRITE]),
 		jiffies_to_msecs(part_stat_read(p, ticks[WRITE])),
-		p->in_flight,
+		part_in_flight(p),
 		jiffies_to_msecs(part_stat_read(p, io_ticks)),
 		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
 }
 
+ssize_t part_inflight_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+
+	return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]);
+}
+
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 ssize_t part_fail_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
@@ -281,6 +289,7 @@ static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -292,6 +301,7 @@ static struct attribute *part_attrs[] = {
 	&dev_attr_size.attr,
 	&dev_attr_alignment_offset.attr,
 	&dev_attr_stat.attr,
+	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 45fc320a53c6..44263cb27121 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -98,7 +98,7 @@ struct hd_struct {
 	int make_it_fail;
 #endif
 	unsigned long stamp;
-	int in_flight;
+	int in_flight[2];
 #ifdef	CONFIG_SMP
 	struct disk_stats *dkstats;
 #else
@@ -322,18 +322,23 @@ static inline void free_part_stats(struct hd_struct *part)
 #define part_stat_sub(cpu, gendiskp, field, subnd)			\
 	part_stat_add(cpu, gendiskp, field, -subnd)
 
-static inline void part_inc_in_flight(struct hd_struct *part)
+static inline void part_inc_in_flight(struct hd_struct *part, int rw)
 {
-	part->in_flight++;
+	part->in_flight[rw]++;
 	if (part->partno)
-		part_to_disk(part)->part0.in_flight++;
+		part_to_disk(part)->part0.in_flight[rw]++;
 }
 
-static inline void part_dec_in_flight(struct hd_struct *part)
+static inline void part_dec_in_flight(struct hd_struct *part, int rw)
 {
-	part->in_flight--;
+	part->in_flight[rw]--;
 	if (part->partno)
-		part_to_disk(part)->part0.in_flight--;
+		part_to_disk(part)->part0.in_flight[rw]--;
+}
+
+static inline int part_in_flight(struct hd_struct *part)
+{
+	return part->in_flight[0] + part->in_flight[1];
 }
 
 /* block/blk-core.c */
@@ -546,6 +551,8 @@ extern ssize_t part_size_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
 extern ssize_t part_stat_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
+extern ssize_t part_inflight_show(struct device *dev,
+			      struct device_attribute *attr, char *buf);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 extern ssize_t part_fail_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
-- 
cgit v1.2.3