Merge branch 'for-4.8/core' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:

   - the big change is the cleanup from Mike Christie, cleaning up our
     uses of command types and modified flags.  This is what will throw
     some merge conflicts

   - regression fix for the above for btrfs, from Vincent

   - following up to the above, better packing of struct request from
     Christoph

   - a 2038 fix for blktrace from Arnd

   - a few trivial/spelling fixes from Bart Van Assche

   - a front merge check fix from Damien, which could cause issues on
     SMR drives

   - Atari partition fix from Gabriel

   - convert cfq to highres timers, since jiffies isn't granular enough
     for some devices these days.  From Jan and Jeff

   - CFQ priority boost fix idle classes, from me

   - cleanup series from Ming, improving our bio/bvec iteration

   - a direct issue fix for blk-mq from Omar

   - fix for plug merging not involving the IO scheduler, like we do for
     other types of merges.  From Tahsin

   - expose DAX type internally and through sysfs.  From Toshi and Yigal

* 'for-4.8/core' of git://git.kernel.dk/linux-block: (76 commits)
  block: Fix front merge check
  block: do not merge requests without consulting with io scheduler
  block: Fix spelling in a source code comment
  block: expose QUEUE_FLAG_DAX in sysfs
  block: add QUEUE_FLAG_DAX for devices to advertise their DAX support
  Btrfs: fix comparison in __btrfs_map_block()
  block: atari: Return early for unsupported sector size
  Doc: block: Fix a typo in queue-sysfs.txt
  cfq-iosched: Charge at least 1 jiffie instead of 1 ns
  cfq-iosched: Fix regression in bonnie++ rewrite performance
  cfq-iosched: Convert slice_resid from u64 to s64
  block: Convert fifo_time from ulong to u64
  blktrace: avoid using timespec
  block/blk-cgroup.c: Declare local symbols static
  block/bio-integrity.c: Add #include "blk.h"
  block/partition-generic.c: Remove a set-but-not-used variable
  block: bio: kill BIO_MAX_SIZE
  cfq-iosched: temporarily boost queue priority for idle classes
  block: drbd: avoid to use BIO_MAX_SIZE
  block: bio: remove BIO_MAX_SECTORS
  ...

1 files changed, 47 insertions, 30 deletions

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9aef8654e90d..bedb84d168d1 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -127,12 +127,13 @@ static void trace_note_tsk(struct task_struct *tsk)
 
 static void trace_note_time(struct blk_trace *bt)
 {
-	struct timespec now;
+	struct timespec64 now;
 	unsigned long flags;
 	u32 words[2];
 
-	getnstimeofday(&now);
-	words[0] = now.tv_sec;
+	/* need to check user space to see if this breaks in y2038 or y2106 */
+	ktime_get_real_ts64(&now);
+	words[0] = (u32)now.tv_sec;
 	words[1] = now.tv_nsec;
 
 	local_irq_save(flags);
@@ -189,6 +190,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
 				 BLK_TC_ACT(BLK_TC_WRITE) };
 
 #define BLK_TC_RAHEAD		BLK_TC_AHEAD
+#define BLK_TC_PREFLUSH		BLK_TC_FLUSH
 
 /* The ilog2() calls fall out because they're constant */
 #define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
@@ -199,7 +201,8 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
  * blk_io_trace structure and places it in a per-cpu subbuffer.
  */
 static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
-		     int rw, u32 what, int error, int pdu_len, void *pdu_data)
+		     int op, int op_flags, u32 what, int error, int pdu_len,
+		     void *pdu_data)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
@@ -214,13 +217,16 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
 
-	what |= ddir_act[rw & WRITE];
-	what |= MASK_TC_BIT(rw, SYNC);
-	what |= MASK_TC_BIT(rw, RAHEAD);
-	what |= MASK_TC_BIT(rw, META);
-	what |= MASK_TC_BIT(rw, DISCARD);
-	what |= MASK_TC_BIT(rw, FLUSH);
-	what |= MASK_TC_BIT(rw, FUA);
+	what |= ddir_act[op_is_write(op) ? WRITE : READ];
+	what |= MASK_TC_BIT(op_flags, SYNC);
+	what |= MASK_TC_BIT(op_flags, RAHEAD);
+	what |= MASK_TC_BIT(op_flags, META);
+	what |= MASK_TC_BIT(op_flags, PREFLUSH);
+	what |= MASK_TC_BIT(op_flags, FUA);
+	if (op == REQ_OP_DISCARD)
+		what |= BLK_TC_ACT(BLK_TC_DISCARD);
+	if (op == REQ_OP_FLUSH)
+		what |= BLK_TC_ACT(BLK_TC_FLUSH);
 
 	pid = tsk->pid;
 	if (act_log_check(bt, what, sector, pid))
@@ -708,11 +714,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
+		__blk_add_trace(bt, 0, nr_bytes, req_op(rq), rq->cmd_flags,
 				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
+		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, req_op(rq),
 				rq->cmd_flags, what, rq->errors, 0, NULL);
 	}
 }
@@ -770,7 +776,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 		return;
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio->bi_rw, what, error, 0, NULL);
+			bio_op(bio), bio->bi_rw, what, error, 0, NULL);
 }
 
 static void blk_add_trace_bio_bounce(void *ignore,
@@ -818,7 +824,8 @@ static void blk_add_trace_getrq(void *ignore,
 		struct blk_trace *bt = q->blk_trace;
 
 		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0, NULL);
+			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
+					NULL);
 	}
 }
 
@@ -833,7 +840,7 @@ static void blk_add_trace_sleeprq(void *ignore,
 		struct blk_trace *bt = q->blk_trace;
 
 		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ,
+			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
 					0, 0, NULL);
 	}
 }
@@ -843,7 +850,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 	struct blk_trace *bt = q->blk_trace;
 
 	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
+		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
 }
 
 static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
@@ -860,7 +867,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 		else
 			what = BLK_TA_UNPLUG_TIMER;
 
-		__blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
+		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
 	}
 }
 
@@ -874,8 +881,9 @@ static void blk_add_trace_split(void *ignore,
 		__be64 rpdu = cpu_to_be64(pdu);
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
-				bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT,
-				bio->bi_error, sizeof(rpdu), &rpdu);
+				bio->bi_iter.bi_size, bio_op(bio), bio->bi_rw,
+				BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu),
+				&rpdu);
 	}
 }
 
@@ -907,7 +915,7 @@ static void blk_add_trace_bio_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio->bi_rw, BLK_TA_REMAP, bio->bi_error,
+			bio_op(bio), bio->bi_rw, BLK_TA_REMAP, bio->bi_error,
 			sizeof(r), &r);
 }
 
@@ -940,7 +948,7 @@ static void blk_add_trace_rq_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-			rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
+			rq_data_dir(rq), 0, BLK_TA_REMAP, !!rq->errors,
 			sizeof(r), &r);
 }
 
@@ -965,10 +973,10 @@ void blk_add_driver_data(struct request_queue *q,
 		return;
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), 0,
+		__blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, rq->errors, len, data);
 	else
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0,
+		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, rq->errors, len, data);
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
@@ -1769,21 +1777,30 @@ void blk_dump_cmd(char *buf, struct request *rq)
 	}
 }
 
-void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
+void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes)
 {
 	int i = 0;
 
-	if (rw & REQ_FLUSH)
+	if (rw & REQ_PREFLUSH)
 		rwbs[i++] = 'F';
 
-	if (rw & WRITE)
+	switch (op) {
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_SAME:
 		rwbs[i++] = 'W';
-	else if (rw & REQ_DISCARD)
+		break;
+	case REQ_OP_DISCARD:
 		rwbs[i++] = 'D';
-	else if (bytes)
+		break;
+	case REQ_OP_FLUSH:
+		rwbs[i++] = 'F';
+		break;
+	case REQ_OP_READ:
 		rwbs[i++] = 'R';
-	else
+		break;
+	default:
 		rwbs[i++] = 'N';
+	}
 
 	if (rw & REQ_FUA)
 		rwbs[i++] = 'F';