Merge tag 'v4.18' into rdma.git for-next

Resolve merge conflicts from the -rc cycle against the rdma.git tree:

Conflicts:
 drivers/infiniband/core/uverbs_cmd.c
  - New ifs added to ib_uverbs_ex_create_flow in -rc and for-next
  - Merge removal of file->ucontext in for-next with new code in -rc
 drivers/infiniband/core/uverbs_main.c
  - for-next removed code from ib_uverbs_write() that was modified
    in for-rc

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

9 files changed, 68 insertions, 35 deletions

diff --git a/block/bio.c b/block/bio.c
index 9710e275f230..047c5dca6d90 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -903,25 +903,27 @@ int bio_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_add_page);
 
 /**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * Pins pages from *iter and appends them to @bio's bvec array. The
  * pages will have to be released using put_page() when done.
+ * For multi-segment *iter, this function only adds pages from the
+ * the next non-empty segment of the iov iterator.
  */
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	size_t offset, diff;
+	size_t offset;
 	ssize_t size;
 
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
-	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
 
 	/*
 	 * Deep magic below:  We need to walk the pinned pages backwards
@@ -934,21 +936,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size += size;
 	bio->bi_vcnt += nr_pages;
 
-	diff = (nr_pages * PAGE_SIZE - offset) - size;
-	while (nr_pages--) {
-		bv[nr_pages].bv_page = pages[nr_pages];
-		bv[nr_pages].bv_len = PAGE_SIZE;
-		bv[nr_pages].bv_offset = 0;
+	while (idx--) {
+		bv[idx].bv_page = pages[idx];
+		bv[idx].bv_len = PAGE_SIZE;
+		bv[idx].bv_offset = 0;
 	}
 
 	bv[0].bv_offset += offset;
 	bv[0].bv_len -= offset;
-	if (diff)
-		bv[bio->bi_vcnt - 1].bv_len -= diff;
+	bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
 
 	iov_iter_advance(iter, size);
 	return 0;
 }
+
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ * The function tries, but does not guarantee, to pin as many pages as
+ * fit into the bio, or are requested in *iter, whatever is smaller.
+ * If MM encounters an error pinning the requested pages, it stops.
+ * Error is returned only if 0 pages could be pinned.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short orig_vcnt = bio->bi_vcnt;
+
+	do {
+		int ret = __bio_iov_iter_get_pages(bio, iter);
+
+		if (unlikely(ret))
+			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
+
+	} while (iov_iter_count(iter) && !bio_full(bio));
+
+	return 0;
+}
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
@@ -1807,9 +1834,6 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
-	if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
-		bio->bi_next = NULL;
-
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
@@ -1869,6 +1893,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 		bio_integrity_trim(split);
 
 	bio_advance(bio, split->bi_iter.bi_size);
+	bio->bi_iter.bi_done = 0;
 
 	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
 		bio_set_flag(split, BIO_TRACE_COMPLETION);
diff --git a/block/blk-core.c b/block/blk-core.c
index cf0ee764b908..ee33590f54eb 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -273,10 +273,6 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	/*
-	 * XXX this code looks suspicious - it's not consistent with advancing
-	 * req->bio in caller
-	 */
 	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
 		bio_endio(bio);
 }
@@ -2159,11 +2155,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 	if (part->policy && op_is_write(bio_op(bio))) {
 		char b[BDEVNAME_SIZE];
 
-		printk(KERN_ERR
+		WARN_ONCE(1,
 		       "generic_make_request: Trying to write "
 			"to read-only block-device %s (partno %d)\n",
 			bio_devname(bio, b), part->partno);
-		return true;
+		/* Older lvm-tools actually trigger this */
+		return false;
 	}
 
 	return false;
@@ -3081,10 +3078,8 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		struct bio *bio = req->bio;
 		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_iter.bi_size) {
+		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
-			bio->bi_next = NULL;
-		}
 
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
@@ -3479,6 +3474,10 @@ static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 	dst->cpu = src->cpu;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
+	if (src->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		dst->rq_flags |= RQF_SPECIAL_PAYLOAD;
+		dst->special_vec = src->special_vec;
+	}
 	dst->nr_phys_segments = src->nr_phys_segments;
 	dst->ioprio = src->ioprio;
 	dst->extra_len = src->extra_len;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index ffa622366922..1c4532e92938 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -356,7 +356,7 @@ static const char *const blk_mq_rq_state_name_array[] = {
 
 static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
 {
-	if (WARN_ON_ONCE((unsigned int)rq_state >
+	if (WARN_ON_ONCE((unsigned int)rq_state >=
 			 ARRAY_SIZE(blk_mq_rq_state_name_array)))
 		return "(?)";
 	return blk_mq_rq_state_name_array[rq_state];
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 09b2ee6694fb..3de0836163c2 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -271,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * test and set the bit before assining ->rqs[].
 	 */
 	rq = tags->rqs[bitnr];
-	if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
+	if (rq && blk_mq_request_started(rq))
 		iter_data->fn(rq, iter_data->data, reserved);
 
 	return true;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 70c65bb6c013..654b0dc7e001 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -558,10 +558,8 @@ static void __blk_mq_complete_request(struct request *rq)
 	bool shared = false;
 	int cpu;
 
-	if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) !=
-			MQ_RQ_IN_FLIGHT)
+	if (!blk_mq_mark_complete(rq))
 		return;
-
 	if (rq->internal_tag != -1)
 		blk_mq_sched_completed_request(rq);
 
@@ -781,7 +779,6 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
 	}
 
-	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_add_timer(req);
 }
 
@@ -1076,6 +1073,9 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 
 #define BLK_MQ_RESOURCE_DELAY	3		/* ms units */
 
+/*
+ * Returns true if we did some work AND can potentially do more.
+ */
 bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			     bool got_budget)
 {
@@ -1206,8 +1206,17 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			blk_mq_run_hw_queue(hctx, true);
 		else if (needs_restart && (ret == BLK_STS_RESOURCE))
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
+
+		return false;
 	}
 
+	/*
+	 * If the host/device is unable to accept more work, inform the
+	 * caller of that.
+	 */
+	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+		return false;
+
 	return (queued + errors) != 0;
 }
 
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 01e2b353a2b9..15c1f5e12eb8 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -144,6 +144,7 @@ do_local:
 
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(__blk_complete_request);
 
 /**
  * blk_complete_request - end I/O on a request
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 4b8a48d48ba1..f2cfd56e1606 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -210,6 +210,7 @@ void blk_add_timer(struct request *req)
 	if (!req->timeout)
 		req->timeout = q->rq_timeout;
 
+	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_rq_set_deadline(req, jiffies + req->timeout);
 
 	/*
diff --git a/block/bsg.c b/block/bsg.c
index 66602c489956..3da540faf673 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -267,8 +267,6 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode)
 	} else if (hdr->din_xfer_len) {
 		ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr->din_xferp),
 				hdr->din_xfer_len, GFP_KERNEL);
-	} else {
-		ret = blk_rq_map_user(q, rq, NULL, NULL, 0, GFP_KERNEL);
 	}
 
 	if (ret)
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 945f4b8610e0..e0de4dd448b3 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -877,7 +877,7 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 		return 0;
 	}
 
-	if (n > resp->num) {
+	if (n >= resp->num) {
 		pr_debug("Response has %d tokens. Can't access %d\n",
 			 resp->num, n);
 		return 0;
@@ -916,7 +916,7 @@ static u64 response_get_u64(const struct parsed_resp *resp, int n)
 		return 0;
 	}
 
-	if (n > resp->num) {
+	if (n >= resp->num) {
 		pr_debug("Response has %d tokens. Can't access %d\n",
 			 resp->num, n);
 		return 0;