This is a note to let you know that I've just added the patch titled nvme-mpath: replace direct_make_request with generic_make_request to the 5.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: nvme-mpath-replace-direct_make_request-with-generic_make_request.patch and it can be found in the queue-5.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From sagi@xxxxxxxxxxx Fri Apr 9 11:33:14 2021 From: Sagi Grimberg <sagi@xxxxxxxxxxx> Date: Fri, 2 Apr 2021 13:08:41 -0700 Subject: nvme-mpath: replace direct_make_request with generic_make_request To: <stable@xxxxxxxxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx>, Keith Busch <kbusch@xxxxxxxxxx>, linux-nvme@xxxxxxxxxxxxxxxxxxx Message-ID: <20210402200841.347696-1-sagi@xxxxxxxxxxx> From: Sagi Grimberg <sagi@xxxxxxxxxxx> The below patches caused a regression in a multipath setup: Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic") Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic") These patches on their own are correct because they fixed a controller reset regression. When we reset/teardown a controller, we must freeze and quiesce the namespaces request queues to make sure that we safely stop inflight I/O submissions. Freeze is mandatory because if our hctx map changed between reconnects, blk_mq_update_nr_hw_queues will immediately attempt to freeze the queue, and if it still has pending submissions (that are still quiesced) it will hang. This is what the above patches fixed. However, by freezing the namespaces request queues, and only unfreezing them when we successfully reconnect, inflight submissions that are running concurrently can now block grabbing the nshead srcu until either we successfully reconnect or ctrl_loss_tmo expired (or the user explicitly disconnected). This caused a deadlock [1] when a different controller (different path on the same subsystem) became live (i.e. optimized/non-optimized). This is because nvme_mpath_set_live needs to synchronize the nshead srcu before requeueing I/O in order to make sure that current_path is visible to future (re)submisions. However the srcu lock is taken by a blocked submission on a frozen request queue, and we have a deadlock. In recent kernels (v5.9+) direct_make_request was replaced by submit_bio_noacct which does not have this issue because it bio_list will be active when nvme-mpath calls submit_bio_noacct on the bottom device (because it was populated when submit_bio was triggered on it. Hence, we need to fix all the kernels that were before submit_bio_noacct was introduced. [1]: Workqueue: nvme-wq nvme_tcp_reconnect_ctrl_work [nvme_tcp] Call Trace: __schedule+0x293/0x730 schedule+0x33/0xa0 schedule_timeout+0x1d3/0x2f0 wait_for_completion+0xba/0x140 __synchronize_srcu.part.21+0x91/0xc0 synchronize_srcu_expedited+0x27/0x30 synchronize_srcu+0xce/0xe0 nvme_mpath_set_live+0x64/0x130 [nvme_core] nvme_update_ns_ana_state+0x2c/0x30 [nvme_core] nvme_update_ana_state+0xcd/0xe0 [nvme_core] nvme_parse_ana_log+0xa1/0x180 [nvme_core] nvme_read_ana_log+0x76/0x100 [nvme_core] nvme_mpath_init+0x122/0x180 [nvme_core] nvme_init_identify+0x80e/0xe20 [nvme_core] nvme_tcp_setup_ctrl+0x359/0x660 [nvme_tcp] nvme_tcp_reconnect_ctrl_work+0x24/0x70 [nvme_tcp] Signed-off-by: Sagi Grimberg <sagi@xxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/nvme/host/multipath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -330,7 +330,7 @@ static blk_qc_t nvme_ns_head_make_reques trace_block_bio_remap(bio->bi_disk->queue, bio, disk_devt(ns->head->disk), bio->bi_iter.bi_sector); - ret = direct_make_request(bio); + ret = generic_make_request(bio); } else if (nvme_available_path(head)) { dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n"); Patches currently in stable-queue which might be from sagi@xxxxxxxxxxx are queue-5.4/nvme-mpath-replace-direct_make_request-with-generic_make_request.patch