Merge remote-tracking branch 'jens/for-4.8/core' into dm-4.8

DM's DAX support depends on block core's newly added QUEUE_FLAG_DAX.

Documentation/block/queue-sysfs.txt

@@ -53,7 +53,7 @@ disk.
 
 logical_block_size (RO)
 -----------------------
-This is the logcal block size of the device, in bytes.
+This is the logical block size of the device, in bytes.
 
 max_hw_sectors_kb (RO)
 ----------------------

block/bio-integrity.c

@@ -26,6 +26,7 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include <linux/slab.h>
+#include "blk.h"
 
 #define BIP_INLINE_VECS	4
 

block/blk-cgroup.c

@@ -905,7 +905,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 	return 0;
 }
 
-struct cftype blkcg_files[] = {
+static struct cftype blkcg_files[] = {
 	{
 		.name = "stat",
 		.flags = CFTYPE_NOT_ON_ROOT,
@@ -914,7 +914,7 @@ struct cftype blkcg_files[] = {
 	{ }	/* terminate */
 };
 
-struct cftype blkcg_legacy_files[] = {
+static struct cftype blkcg_legacy_files[] = {
 	{
 		.name = "reset_stats",
 		.write_u64 = blkcg_reset_stats,

block/blk-exec.c

@@ -62,7 +62,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	/*
 	 * don't check dying flag for MQ because the request won't
-	 * be resued after dying flag is set
+	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
 		blk_mq_insert_request(rq, at_head, true, false);

block/blk-merge.c

@@ -744,6 +744,12 @@ int attempt_front_merge(struct request_queue *q, struct request *rq)
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 			  struct request *next)
 {
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.elevator_allow_rq_merge_fn)
+		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+			return 0;
+
 	return attempt_merge(q, rq, next);
 }
 

block/blk-sysfs.c

@@ -379,6 +379,11 @@ static ssize_t queue_wc_store(struct request_queue *q, const char *page,
 	return count;
 }
 
+static ssize_t queue_dax_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_dax(q), page);
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -516,6 +521,11 @@ static struct queue_sysfs_entry queue_wc_entry = {
 	.store = queue_wc_store,
 };
 
+static struct queue_sysfs_entry queue_dax_entry = {
+	.attr = {.name = "dax", .mode = S_IRUGO },
+	.show = queue_dax_show,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -542,6 +552,7 @@ static struct attribute *default_attrs[] = {
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
+	&queue_dax_entry.attr,
 	NULL,
 };
 

block/cfq-iosched.c

@@ -132,7 +132,7 @@ struct cfq_queue {
 	/* time when first request from queue completed and slice started. */
 	u64 slice_start;
 	u64 slice_end;
-	u64 slice_resid;
+	s64 slice_resid;
 
 	/* pending priority requests */
 	int prio_pending;
@@ -1463,7 +1463,8 @@ static inline u64 cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
 		 * a single request on seeky media and cause lots of seek time
 		 * and group will never know it.
 		 */
-		slice_used = max_t(u64, (now - cfqq->dispatch_start), 1);
+		slice_used = max_t(u64, (now - cfqq->dispatch_start),
+					jiffies_to_nsecs(1));
 	} else {
 		slice_used = now - cfqq->slice_start;
 		if (slice_used > cfqq->allocated_slice) {
@@ -2543,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req,
 	struct request *__rq;
 
 	__rq = cfq_find_rq_fmerge(cfqd, bio);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_FRONT_MERGE;
 	}
@@ -2600,8 +2601,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 		cfq_del_cfqq_rr(cfqd, cfqq);
 }
 
-static int cfq_allow_merge(struct request_queue *q, struct request *rq,
-			   struct bio *bio)
+static int cfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+			       struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_io_cq *cic;
@@ -2625,6 +2626,12 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	return cfqq == RQ_CFQQ(rq);
 }
 
+static int cfq_allow_rq_merge(struct request_queue *q, struct request *rq,
+			      struct request *next)
+{
+	return RQ_CFQQ(rq) == RQ_CFQQ(next);
+}
+
 static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	hrtimer_try_to_cancel(&cfqd->idle_slice_timer);
@@ -2689,7 +2696,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
 		else
 			cfqq->slice_resid = cfqq->slice_end - ktime_get_ns();
-		cfq_log_cfqq(cfqd, cfqq, "resid=%llu", cfqq->slice_resid);
+		cfq_log_cfqq(cfqd, cfqq, "resid=%lld", cfqq->slice_resid);
 	}
 
 	cfq_group_served(cfqd, cfqq->cfqg, cfqq);
@@ -4243,7 +4250,16 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 					cfqq_type(cfqq));
 
 		st->ttime.last_end_request = now;
-		if (!(rq->start_time + cfqd->cfq_fifo_expire[1] > now))
+		/*
+		 * We have to do this check in jiffies since start_time is in
+		 * jiffies and it is not trivial to convert to ns. If
+		 * cfq_fifo_expire[1] ever comes close to 1 jiffie, this test
+		 * will become problematic but so far we are fine (the default
+		 * is 128 ms).
+		 */
+		if (!time_after(rq->start_time +
+				  nsecs_to_jiffies(cfqd->cfq_fifo_expire[1]),
+				jiffies))
 			cfqd->last_delayed_sync = now;
 	}
 
@@ -4811,7 +4827,8 @@ static struct elevator_type iosched_cfq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
-		.elevator_allow_merge_fn =	cfq_allow_merge,
+		.elevator_allow_bio_merge_fn =	cfq_allow_bio_merge,
+		.elevator_allow_rq_merge_fn =	cfq_allow_rq_merge,
 		.elevator_bio_merged_fn =	cfq_bio_merged,
 		.elevator_dispatch_fn =		cfq_dispatch_requests,
 		.elevator_add_req_fn =		cfq_insert_request,

block/deadline-iosched.c

@@ -137,7 +137,7 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		if (__rq) {
 			BUG_ON(sector != blk_rq_pos(__rq));
 
-			if (elv_rq_merge_ok(__rq, bio)) {
+			if (elv_bio_merge_ok(__rq, bio)) {
 				ret = ELEVATOR_FRONT_MERGE;
 				goto out;
 			}
@@ -173,7 +173,8 @@ deadline_merged_requests(struct request_queue *q, struct request *req,
 	 * and move into next position (next will be deleted) in fifo
 	 */
 	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
-		if (time_before(next->fifo_time, req->fifo_time)) {
+		if (time_before((unsigned long)next->fifo_time,
+				(unsigned long)req->fifo_time)) {
 			list_move(&req->queuelist, &next->queuelist);
 			req->fifo_time = next->fifo_time;
 		}
@@ -227,7 +228,7 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	/*
 	 * rq is expired!
 	 */
-	if (time_after_eq(jiffies, rq->fifo_time))
+	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
 		return 1;
 
 	return 0;

block/elevator.c

@@ -53,13 +53,13 @@ static LIST_HEAD(elv_list);
  * Query io scheduler to see if the current process issuing bio may be
  * merged with rq.
  */
-static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
+static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 {
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_merge_fn)
-		return e->type->ops.elevator_allow_merge_fn(q, rq, bio);
+	if (e->type->ops.elevator_allow_bio_merge_fn)
+		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
 }
@@ -67,17 +67,17 @@ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
 /*
  * can we safely merge with this request?
  */
-bool elv_rq_merge_ok(struct request *rq, struct bio *bio)
+bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
 {
 	if (!blk_rq_merge_ok(rq, bio))
-		return 0;
+		return false;
 
-	if (!elv_iosched_allow_merge(rq, bio))
-		return 0;
+	if (!elv_iosched_allow_bio_merge(rq, bio))
+		return false;
 
-	return 1;
+	return true;
 }
-EXPORT_SYMBOL(elv_rq_merge_ok);
+EXPORT_SYMBOL(elv_bio_merge_ok);
 
 static struct elevator_type *elevator_find(const char *name)
 {
@@ -425,7 +425,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	/*
 	 * First try one-hit cache.
 	 */
-	if (q->last_merge && elv_rq_merge_ok(q->last_merge, bio)) {
+	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
 		ret = blk_try_merge(q->last_merge, bio);
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
@@ -440,7 +440,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * See if our hash lookup can find a potential backmerge.
 	 */
 	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_BACK_MERGE;
 	}

block/partition-generic.c

@@ -495,7 +495,6 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 	/* add partitions */
 	for (p = 1; p < state->limit; p++) {
 		sector_t size, from;
-		struct partition_meta_info *info = NULL;
 
 		size = state->parts[p].size;
 		if (!size)
@@ -530,8 +529,6 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 			}
 		}
 
-		if (state->parts[p].has_info)
-			info = &state->parts[p].info;
 		part = add_partition(disk, p, from, size,
 				     state->parts[p].flags,
 				     &state->parts[p].info);

block/partitions/atari.c

@@ -42,6 +42,13 @@ int atari_partition(struct parsed_partitions *state)
 	int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */
 #endif
 
+	/*
+	 * ATARI partition scheme supports 512 lba only.  If this is not
+	 * the case, bail early to avoid miscalculating hd_size.
+	 */
+	if (bdev_logical_block_size(state->bdev) != 512)
+		return 0;
+
 	rs = read_part_sector(state, 0, &sect);
 	if (!rs)
 		return -1;

drivers/block/brd.c

@@ -509,7 +509,9 @@ static struct brd_device *brd_alloc(int i)
 	blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
-
+#ifdef CONFIG_BLK_DEV_RAM_DAX
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
+#endif
 	disk = brd->brd_disk = alloc_disk(max_part);
 	if (!disk)
 		goto out_free_queue;

drivers/nvdimm/pmem.c

@@ -283,6 +283,7 @@ static int pmem_attach_disk(struct device *dev,
 	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, q);
 	q->queuedata = pmem;
 
 	disk = alloc_disk_node(0, nid);

drivers/s390/block/dcssblk.c

@@ -618,6 +618,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->gd->driverfs_dev = &dev_info->dev;
 	blk_queue_make_request(dev_info->dcssblk_queue, dcssblk_make_request);
 	blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, dev_info->dcssblk_queue);
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
 	set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors

fs/block_dev.c

@@ -493,7 +493,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
 
 	if (size < 0)
 		return size;
-	if (!ops->direct_access)
+	if (!blk_queue_dax(bdev_get_queue(bdev)) || !ops->direct_access)
 		return -EOPNOTSUPP;
 	if ((sector + DIV_ROUND_UP(size, 512)) >
 					part_nr_sects_read(bdev->bd_part))
@@ -1287,7 +1287,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) &&
+		    blk_queue_dax(disk->queue))
 			bdev->bd_inode->i_flags = S_DAX;
 		else
 			bdev->bd_inode->i_flags = 0;

fs/btrfs/volumes.c

@@ -5494,7 +5494,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		}
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
-		if (op == REQ_OP_WRITE || REQ_OP_DISCARD ||
+		if (op == REQ_OP_WRITE || op == REQ_OP_DISCARD ||
 		    op == REQ_GET_READ_MIRRORS) {
 			num_stripes = map->num_stripes;
 		} else if (mirror_num) {

include/linux/blkdev.h

@@ -90,7 +90,7 @@ struct request {
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
-		unsigned long fifo_time;
+		u64 fifo_time;
 	};
 
 	struct request_queue *q;
@@ -505,6 +505,7 @@ struct request_queue {
 #define QUEUE_FLAG_WC	       23	/* Write back caching */
 #define QUEUE_FLAG_FUA	       24	/* device supports FUA writes */
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
+#define QUEUE_FLAG_DAX         26	/* device supports DAX */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -594,6 +595,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
 #define blk_queue_secdiscard(q)	(blk_queue_discard(q) && \
 	test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags))
+#define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
 
 #define blk_noretry_request(rq) \
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \

include/linux/elevator.h

@@ -16,7 +16,11 @@ typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *,
 
 typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int);
 
-typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *);
+typedef int (elevator_allow_bio_merge_fn) (struct request_queue *,
+					   struct request *, struct bio *);
+
+typedef int (elevator_allow_rq_merge_fn) (struct request_queue *,
+					  struct request *, struct request *);
 
 typedef void (elevator_bio_merged_fn) (struct request_queue *,
 						struct request *, struct bio *);
@@ -46,7 +50,8 @@ struct elevator_ops
 	elevator_merge_fn *elevator_merge_fn;
 	elevator_merged_fn *elevator_merged_fn;
 	elevator_merge_req_fn *elevator_merge_req_fn;
-	elevator_allow_merge_fn *elevator_allow_merge_fn;
+	elevator_allow_bio_merge_fn *elevator_allow_bio_merge_fn;
+	elevator_allow_rq_merge_fn *elevator_allow_rq_merge_fn;
 	elevator_bio_merged_fn *elevator_bio_merged_fn;
 
 	elevator_dispatch_fn *elevator_dispatch_fn;
@@ -157,7 +162,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 extern int elevator_init(struct request_queue *, char *);
 extern void elevator_exit(struct elevator_queue *);
 extern int elevator_change(struct request_queue *, const char *);
-extern bool elv_rq_merge_ok(struct request *, struct bio *);
+extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,
 					struct elevator_type *);
 

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);