block: recalculate segment count for multi-segment discards correctly

mainline inclusion
from mainline-5.12-rc5
commit	a958937f
category: bugfix
bugzilla: 51373
CVE: NA

-------------------------------------------------

When a stacked block device inserts a request into another block device
using blk_insert_cloned_request, the request's nr_phys_segments field gets
recalculated by a call to blk_recalc_rq_segments in
blk_cloned_rq_check_limits. But blk_recalc_rq_segments does not know how to
handle multi-segment discards. For disk types which can handle
multi-segment discards like nvme, this results in discard requests which
claim a single segment when it should report several, triggering a warning
in nvme and causing nvme to fail the discard from the invalid state.

 WARNING: CPU: 5 PID: 191 at drivers/nvme/host/core.c:700 nvme_setup_discard+0x170/0x1e0 [nvme_core]
 ...
 nvme_setup_cmd+0x217/0x270 [nvme_core]
 nvme_loop_queue_rq+0x51/0x1b0 [nvme_loop]
 __blk_mq_try_issue_directly+0xe7/0x1b0
 blk_mq_request_issue_directly+0x41/0x70
 ? blk_account_io_start+0x40/0x50
 dm_mq_queue_rq+0x200/0x3e0
 blk_mq_dispatch_rq_list+0x10a/0x7d0
 ? __sbitmap_queue_get+0x25/0x90
 ? elv_rb_del+0x1f/0x30
 ? deadline_remove_request+0x55/0xb0
 ? dd_dispatch_request+0x181/0x210
 __blk_mq_do_dispatch_sched+0x144/0x290
 ? bio_attempt_discard_merge+0x134/0x1f0
 __blk_mq_sched_dispatch_requests+0x129/0x180
 blk_mq_sched_dispatch_requests+0x30/0x60
 __blk_mq_run_hw_queue+0x47/0xe0
 __blk_mq_delay_run_hw_queue+0x15b/0x170
 blk_mq_sched_insert_requests+0x68/0xe0
 blk_mq_flush_plug_list+0xf0/0x170
 blk_finish_plug+0x36/0x50
 xlog_cil_committed+0x19f/0x290 [xfs]
 xlog_cil_process_committed+0x57/0x80 [xfs]
 xlog_state_do_callback+0x1e0/0x2a0 [xfs]
 xlog_ioend_work+0x2f/0x80 [xfs]
 process_one_work+0x1b6/0x350
 worker_thread+0x53/0x3e0
 ? process_one_work+0x350/0x350
 kthread+0x11b/0x140
 ? __kthread_bind_mask+0x60/0x60
 ret_from_fork+0x22/0x30

This patch fixes blk_recalc_rq_segments to be aware of devices which can
have multi-segment discards. It calculates the correct discard segment
count by counting the number of bio as each discard bio is considered its
own segment.

Fixes: 1e739730 ("block: optionally merge discontiguous discard bios into a single request")
Signed-off-by: NDavid Jeffery <djeffery@redhat.com>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NLaurence Oberman <loberman@redhat.com>
Link: https://lore.kernel.org/r/20210211143807.GA115624@redhatSigned-off-by: NJens Axboe <axboe@kernel.dk>

Conflicts:
        block/blk-merge.c
Signed-off-by: NBaokun Li <libaokun1@huawei.com>
Reviewed-by: NYufen Yu <yuyufen@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

block/blk-merge.c

@@ -235,7 +235,8 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 {
 	struct bio_vec bv, bvprv = { NULL };
 	int cluster, prev = 0;
-	unsigned int seg_size, nr_phys_segs;
+	unsigned int nr_phys_segs = 0;
+	unsigned int seg_size;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
 
@@ -245,6 +246,12 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
+		if (queue_max_discard_segments(q) > 1) {
+			for_each_bio(bio)
+				nr_phys_segs++;
+			return nr_phys_segs;
+		}
+		return 1;
 	case REQ_OP_WRITE_ZEROES:
 		return 0;
 	case REQ_OP_WRITE_SAME:
@@ -254,7 +261,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	fbio = bio;
 	cluster = blk_queue_cluster(q);
 	seg_size = 0;
-	nr_phys_segs = 0;
 	for_each_bio(bio) {
 		bio_for_each_segment(bv, bio, iter) {
 			/*