Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

12 files changed, 95 insertions, 70 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 059467086b..96af822499 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -323,6 +323,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	blkg->q = disk->queue;
 	INIT_LIST_HEAD(&blkg->q_node);
 	blkg->blkcg = blkcg;
+	blkg->iostat.blkg = blkg;
 #ifdef CONFIG_BLK_CGROUP_PUNT_BIO
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
@@ -619,12 +620,45 @@ restart:
 	spin_unlock_irq(&q->queue_lock);
 }
 
+static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] = src->bytes[i];
+		dst->ios[i] = src->ios[i];
+	}
+}
+
+static void __blkg_clear_stat(struct blkg_iostat_set *bis)
+{
+	struct blkg_iostat cur = {0};
+	unsigned long flags;
+
+	flags = u64_stats_update_begin_irqsave(&bis->sync);
+	blkg_iostat_set(&bis->cur, &cur);
+	blkg_iostat_set(&bis->last, &cur);
+	u64_stats_update_end_irqrestore(&bis->sync, flags);
+}
+
+static void blkg_clear_stat(struct blkcg_gq *blkg)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu);
+
+		__blkg_clear_stat(s);
+	}
+	__blkg_clear_stat(&blkg->iostat);
+}
+
 static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 			     struct cftype *cftype, u64 val)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
-	int i, cpu;
+	int i;
 
 	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
@@ -635,18 +669,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	 * anyway.  If you get hit by a race, retry.
 	 */
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
-		for_each_possible_cpu(cpu) {
-			struct blkg_iostat_set *bis =
-				per_cpu_ptr(blkg->iostat_cpu, cpu);
-			memset(bis, 0, sizeof(*bis));
-
-			/* Re-initialize the cleared blkg_iostat_set */
-			u64_stats_init(&bis->sync);
-			bis->blkg = blkg;
-		}
-		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
-		u64_stats_init(&blkg->iostat.sync);
-
+		blkg_clear_stat(blkg);
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
 
@@ -949,16 +972,6 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 }
 EXPORT_SYMBOL_GPL(blkg_conf_exit);
 
-static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
-{
-	int i;
-
-	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
-		dst->bytes[i] = src->bytes[i];
-		dst->ios[i] = src->ios[i];
-	}
-}
-
 static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
 {
 	int i;
@@ -1024,7 +1037,19 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
 		struct blkg_iostat cur;
 		unsigned int seq;
 
+		/*
+		 * Order assignment of `next_bisc` from `bisc->lnode.next` in
+		 * llist_for_each_entry_safe and clearing `bisc->lqueued` for
+		 * avoiding to assign `next_bisc` with new next pointer added
+		 * in blk_cgroup_bio_start() in case of re-ordering.
+		 *
+		 * The pair barrier is implied in llist_add() in blk_cgroup_bio_start().
+		 */
+		smp_mb();
+
 		WRITE_ONCE(bisc->lqueued, false);
+		if (bisc == &blkg->iostat)
+			goto propagate_up; /* propagate up to parent only */
 
 		/* fetch the current per-cpu values */
 		do {
@@ -1034,10 +1059,24 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
 
 		blkcg_iostat_update(blkg, &cur, &bisc->last);
 
+propagate_up:
 		/* propagate global delta to parent (unless that's root) */
-		if (parent && parent->parent)
+		if (parent && parent->parent) {
 			blkcg_iostat_update(parent, &blkg->iostat.cur,
 					    &blkg->iostat.last);
+			/*
+			 * Queue parent->iostat to its blkcg's lockless
+			 * list to propagate up to the grandparent if the
+			 * iostat hasn't been queued yet.
+			 */
+			if (!parent->iostat.lqueued) {
+				struct llist_head *plhead;
+
+				plhead = per_cpu_ptr(parent->blkcg->lhead, cpu);
+				llist_add(&parent->iostat.lnode, plhead);
+				parent->iostat.lqueued = true;
+			}
+		}
 	}
 	raw_spin_unlock_irqrestore(&blkg_stat_lock, flags);
 out:
diff --git a/block/blk-core.c b/block/blk-core.c
index b795ac1772..6fcf8ed5fc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -987,10 +987,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->bd_stamp);
-	if (unlikely(time_after(now, stamp))) {
-		if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now)))
-			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
-	}
+	if (unlikely(time_after(now, stamp)) &&
+	    likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
+	    (end || part_in_flight(part)))
+		__part_stat_add(part, io_ticks, now - stamp);
+
 	if (part->bd_partno) {
 		part = bdev_whole(part);
 		goto again;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index b0f314f4bc..9944414bf7 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -183,7 +183,7 @@ static void blk_flush_complete_seq(struct request *rq,
 		/* queue for flush */
 		if (list_empty(pending))
 			fq->flush_pending_since = jiffies;
-		list_move_tail(&rq->queuelist, pending);
+		list_add_tail(&rq->queuelist, pending);
 		break;
 
 	case REQ_FSEQ_DATA:
@@ -261,6 +261,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq,
 		unsigned int seq = blk_flush_cur_seq(rq);
 
 		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
+		list_del_init(&rq->queuelist);
 		blk_flush_complete_seq(rq, fq, seq, error);
 	}
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4e3483a16b..ae61a9c2fc 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -779,6 +779,8 @@ static void blk_account_io_merge_request(struct request *req)
 	if (blk_do_io_stat(req)) {
 		part_stat_lock();
 		part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 32afb87efb..5ac2087b05 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -997,6 +997,8 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 		update_io_ticks(req->part, jiffies, true);
 		part_stat_inc(req->part, ios[sgrp]);
 		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
+		part_stat_local_dec(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
@@ -1019,6 +1021,8 @@ static inline void blk_account_io_start(struct request *req)
 
 		part_stat_lock();
 		update_io_ticks(req->part, jiffies, false);
+		part_stat_local_inc(req->part,
+				    in_flight[op_is_write(req_op(req))]);
 		part_stat_unlock();
 	}
 }
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 9d6033e01f..15319b217b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -751,6 +751,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	unsigned int top, bottom, alignment, ret = 0;
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
+	t->max_user_sectors = min_not_zero(t->max_user_sectors,
+			b->max_user_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
 	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
diff --git a/block/blk.h b/block/blk.h
index d9f584984b..da5dbc6b13 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -357,6 +357,7 @@ static inline bool blk_do_io_stat(struct request *rq)
 }
 
 void update_io_ticks(struct block_device *part, unsigned long now, bool end);
+unsigned int part_in_flight(struct block_device *part);
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 {
diff --git a/block/fops.c b/block/fops.c
index 679d9b752f..df2c68d3f1 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -390,7 +390,7 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 
 	iomap->bdev = bdev;
 	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
-	if (iomap->offset >= isize)
+	if (offset >= isize)
 		return -EIO;
 	iomap->type = IOMAP_MAPPED;
 	iomap->addr = iomap->offset;
diff --git a/block/genhd.c b/block/genhd.c
index 52a4521df0..345d80ab97 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part,
 	}
 }
 
-static unsigned int part_in_flight(struct block_device *part)
+unsigned int part_in_flight(struct block_device *part)
 {
 	unsigned int inflight = 0;
 	int cpu;
diff --git a/block/ioctl.c b/block/ioctl.c
index f505f9c341..2639ce9df3 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -33,7 +33,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	if (op == BLKPG_DEL_PARTITION)
 		return bdev_del_partition(disk, p.pno);
 
-	if (p.start < 0 || p.length <= 0 || p.start + p.length < 0)
+	if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start)
 		return -EINVAL;
 	/* Check that the partition is aligned to the block size */
 	if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev)))
diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c
index c03bc105e5..152c85df92 100644
--- a/block/partitions/cmdline.c
+++ b/block/partitions/cmdline.c
@@ -70,8 +70,8 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef)
 	}
 
 	if (*partdef == '(') {
-		int length;
-		char *next = strchr(++partdef, ')');
+		partdef++;
+		char *next = strsep(&partdef, ")");
 
 		if (!next) {
 			pr_warn("cmdline partition format is invalid.");
@@ -79,11 +79,7 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef)
 			goto fail;
 		}
 
-		length = min_t(int, next - partdef,
-			       sizeof(new_subpart->name) - 1);
-		strscpy(new_subpart->name, partdef, length);
-
-		partdef = ++next;
+		strscpy(new_subpart->name, next, sizeof(new_subpart->name));
 	} else
 		new_subpart->name[0] = '\0';
 
@@ -117,14 +113,12 @@ static void free_subpart(struct cmdline_parts *parts)
 	}
 }
 
-static int parse_parts(struct cmdline_parts **parts, const char *bdevdef)
+static int parse_parts(struct cmdline_parts **parts, char *bdevdef)
 {
 	int ret = -EINVAL;
 	char *next;
-	int length;
 	struct cmdline_subpart **next_subpart;
 	struct cmdline_parts *newparts;
-	char buf[BDEVNAME_SIZE + 32 + 4];
 
 	*parts = NULL;
 
@@ -132,28 +126,19 @@ static int parse_parts(struct cmdline_parts **parts, const char *bdevdef)
 	if (!newparts)
 		return -ENOMEM;
 
-	next = strchr(bdevdef, ':');
+	next = strsep(&bdevdef, ":");
 	if (!next) {
 		pr_warn("cmdline partition has no block device.");
 		goto fail;
 	}
 
-	length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1);
-	strscpy(newparts->name, bdevdef, length);
+	strscpy(newparts->name, next, sizeof(newparts->name));
 	newparts->nr_subparts = 0;
 
 	next_subpart = &newparts->subpart;
 
-	while (next && *(++next)) {
-		bdevdef = next;
-		next = strchr(bdevdef, ',');
-
-		length = (!next) ? (sizeof(buf) - 1) :
-			min_t(int, next - bdevdef, sizeof(buf) - 1);
-
-		strscpy(buf, bdevdef, length);
-
-		ret = parse_subpart(next_subpart, buf);
+	while ((next = strsep(&bdevdef, ","))) {
+		ret = parse_subpart(next_subpart, next);
 		if (ret)
 			goto fail;
 
@@ -199,24 +184,17 @@ static int cmdline_parts_parse(struct cmdline_parts **parts,
 
 	*parts = NULL;
 
-	next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL);
+	pbuf = buf = kstrdup(cmdline, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	next_parts = parts;
 
-	while (next && *pbuf) {
-		next = strchr(pbuf, ';');
-		if (next)
-			*next = '\0';
-
-		ret = parse_parts(next_parts, pbuf);
+	while ((next = strsep(&pbuf, ";"))) {
+		ret = parse_parts(next_parts, next);
 		if (ret)
 			goto fail;
 
-		if (next)
-			pbuf = ++next;
-
 		next_parts = &(*next_parts)->next_parts;
 	}
 
@@ -250,7 +228,6 @@ static struct cmdline_parts *bdev_parts;
 static int add_part(int slot, struct cmdline_subpart *subpart,
 		struct parsed_partitions *state)
 {
-	int label_min;
 	struct partition_meta_info *info;
 	char tmp[sizeof(info->volname) + 4];
 
@@ -262,9 +239,7 @@ static int add_part(int slot, struct cmdline_subpart *subpart,
 
 	info = &state->parts[slot].info;
 
-	label_min = min_t(int, sizeof(info->volname) - 1,
-			  sizeof(subpart->name));
-	strscpy(info->volname, subpart->name, label_min);
+	strscpy(info->volname, subpart->name, sizeof(info->volname));
 
 	snprintf(tmp, sizeof(tmp), "(%s)", info->volname);
 	strlcat(state->pp_buf, tmp, PAGE_SIZE);
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 14fe0fef81..598fd3e7fc 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen)
 			      &key_type_user, key_name, true);
 
 	if (IS_ERR(kref))
-		ret = PTR_ERR(kref);
+		return PTR_ERR(kref);
 
 	key = key_ref_to_ptr(kref);
 	down_read(&key->sem);