Merging upstream version 6.1.82.

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

5 files changed, 51 insertions, 7 deletions

diff --git a/block/bio.c b/block/bio.c
index 6c22dd7b6..74c2818c7 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -927,7 +927,7 @@ static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
 
 	if ((addr1 | mask) != (addr2 | mask))
 		return false;
-	if (bv->bv_len + len > queue_max_segment_size(q))
+	if (len > queue_max_segment_size(q) - bv->bv_len)
 		return false;
 	return __bio_try_merge_page(bio, page, len, offset, same_page);
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index 6eaf2b0ad..aefdf07bd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -864,7 +864,16 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	 */
 	blk_flush_plug(current->plug, false);
 
-	if (bio_queue_enter(bio))
+	/*
+	 * We need to be able to enter a frozen queue, similar to how
+	 * timeouts also need to do that. If that is blocked, then we can
+	 * have pending IO when a queue freeze is started, and then the
+	 * wait for the freeze to finish will wait for polled requests to
+	 * timeout as the poller is preventer from entering the queue and
+	 * completing them. As long as we prevent new IO from being queued,
+	 * that should be all that matters.
+	 */
+	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return 0;
 	if (queue_is_mq(q)) {
 		ret = blk_mq_poll(q, cookie, iob, flags);
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 7dd6a33e1..e6557024e 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1337,6 +1337,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
 
 	lockdep_assert_held(&iocg->waitq.lock);
 
+	/*
+	 * If the delay is set by another CPU, we may be in the past. No need to
+	 * change anything if so. This avoids decay calculation underflow.
+	 */
+	if (time_before64(now->now, iocg->delay_at))
+		return false;
+
 	/* calculate the current delay in effect - 1/2 every second */
 	tdelta = now->now - iocg->delay_at;
 	if (iocg->delay)
diff --git a/block/blk-map.c b/block/blk-map.c
index 66da9e2b1..b337ae347 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -203,12 +203,19 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 	/*
 	 * success
 	 */
-	if ((iov_iter_rw(iter) == WRITE &&
-	     (!map_data || !map_data->null_mapped)) ||
-	    (map_data && map_data->from_user)) {
+	if (iov_iter_rw(iter) == WRITE &&
+	     (!map_data || !map_data->null_mapped)) {
 		ret = bio_copy_from_iter(bio, iter);
 		if (ret)
 			goto cleanup;
+	} else if (map_data && map_data->from_user) {
+		struct iov_iter iter2 = *iter;
+
+		/* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */
+		iter2.data_source = ITER_SOURCE;
+		ret = bio_copy_from_iter(bio, &iter2);
+		if (ret)
+			goto cleanup;
 	} else {
 		if (bmd->is_our_pages)
 			zero_fill_bio(bio);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b3f99dda4..7ed6b9469 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -747,11 +747,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		/*
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
+		 * For such case, force the completed nbytes to be equal to
+		 * the BIO size so that bio_advance() sets the BIO remaining
+		 * size to 0 and we end up calling bio_endio() before returning.
 		 */
-		if (bio->bi_iter.bi_size != nbytes)
+		if (bio->bi_iter.bi_size != nbytes) {
 			bio->bi_status = BLK_STS_IOERR;
-		else
+			nbytes = bio->bi_iter.bi_size;
+		} else {
 			bio->bi_iter.bi_sector = rq->__sector;
+		}
 	}
 
 	bio_advance(bio, nbytes);
@@ -1860,6 +1865,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	__add_wait_queue(wq, wait);
 
 	/*
+	 * Add one explicit barrier since blk_mq_get_driver_tag() may
+	 * not imply barrier in case of failure.
+	 *
+	 * Order adding us to wait queue and allocating driver tag.
+	 *
+	 * The pair is the one implied in sbitmap_queue_wake_up() which
+	 * orders clearing sbitmap tag bits and waitqueue_active() in
+	 * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
+	 *
+	 * Otherwise, re-order of adding wait queue and getting driver tag
+	 * may cause __sbitmap_queue_wake_up() to wake up nothing because
+	 * the waitqueue_active() may not observe us in wait queue.
+	 */
+	smp_mb();
+
+	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.