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>

1 files changed, 18 insertions, 5 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c3015736..650b6a9 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 *);