From: Greg Kroah-Hartman Date: Sun, 13 Aug 2023 16:26:34 +0000 (+0200) Subject: 6.1-stable patches X-Git-Tag: v4.14.323~16 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=7032991e1f8e5b81aa93d05cab6231944d6fa50d;p=thirdparty%2Fkernel%2Fstable-queue.git 6.1-stable patches added patches: nvme-rdma-fix-potential-unbalanced-freeze-unfreeze.patch nvme-tcp-fix-potential-unbalanced-freeze-unfreeze.patch --- diff --git a/queue-6.1/nvme-rdma-fix-potential-unbalanced-freeze-unfreeze.patch b/queue-6.1/nvme-rdma-fix-potential-unbalanced-freeze-unfreeze.patch new file mode 100644 index 00000000000..84109aaf9f6 --- /dev/null +++ b/queue-6.1/nvme-rdma-fix-potential-unbalanced-freeze-unfreeze.patch @@ -0,0 +1,62 @@ +From 29b434d1e49252b3ad56ad3197e47fafff5356a1 Mon Sep 17 00:00:00 2001 +From: Ming Lei +Date: Tue, 11 Jul 2023 17:40:41 +0800 +Subject: nvme-rdma: fix potential unbalanced freeze & unfreeze + +From: Ming Lei + +commit 29b434d1e49252b3ad56ad3197e47fafff5356a1 upstream. + +Move start_freeze into nvme_rdma_configure_io_queues(), and there is +at least two benefits: + +1) fix unbalanced freeze and unfreeze, since re-connection work may +fail or be broken by removal + +2) IO during error recovery can be failfast quickly because nvme fabrics +unquiesces queues after teardown. + +One side-effect is that !mpath request may timeout during connecting +because of queue topo change, but that looks not one big deal: + +1) same problem exists with current code base + +2) compared with !mpath, mpath use case is dominant + +Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic") +Cc: stable@vger.kernel.org +Signed-off-by: Ming Lei +Tested-by: Yi Zhang +Reviewed-by: Sagi Grimberg +Signed-off-by: Keith Busch +Signed-off-by: Greg Kroah-Hartman +--- + drivers/nvme/host/rdma.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/drivers/nvme/host/rdma.c ++++ b/drivers/nvme/host/rdma.c +@@ -923,6 +923,7 @@ static int nvme_rdma_configure_io_queues + goto out_cleanup_tagset; + + if (!new) { ++ nvme_start_freeze(&ctrl->ctrl); + nvme_start_queues(&ctrl->ctrl); + if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) { + /* +@@ -931,6 +932,7 @@ static int nvme_rdma_configure_io_queues + * to be safe. + */ + ret = -ENODEV; ++ nvme_unfreeze(&ctrl->ctrl); + goto out_wait_freeze_timed_out; + } + blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset, +@@ -980,7 +982,6 @@ static void nvme_rdma_teardown_io_queues + bool remove) + { + if (ctrl->ctrl.queue_count > 1) { +- nvme_start_freeze(&ctrl->ctrl); + nvme_stop_queues(&ctrl->ctrl); + nvme_sync_io_queues(&ctrl->ctrl); + nvme_rdma_stop_io_queues(ctrl); diff --git a/queue-6.1/nvme-tcp-fix-potential-unbalanced-freeze-unfreeze.patch b/queue-6.1/nvme-tcp-fix-potential-unbalanced-freeze-unfreeze.patch new file mode 100644 index 00000000000..a7736cea2be --- /dev/null +++ b/queue-6.1/nvme-tcp-fix-potential-unbalanced-freeze-unfreeze.patch @@ -0,0 +1,62 @@ +From 99dc264014d5aed66ee37ddf136a38b5a2b1b529 Mon Sep 17 00:00:00 2001 +From: Ming Lei +Date: Tue, 11 Jul 2023 17:40:40 +0800 +Subject: nvme-tcp: fix potential unbalanced freeze & unfreeze + +From: Ming Lei + +commit 99dc264014d5aed66ee37ddf136a38b5a2b1b529 upstream. + +Move start_freeze into nvme_tcp_configure_io_queues(), and there is +at least two benefits: + +1) fix unbalanced freeze and unfreeze, since re-connection work may +fail or be broken by removal + +2) IO during error recovery can be failfast quickly because nvme fabrics +unquiesces queues after teardown. + +One side-effect is that !mpath request may timeout during connecting +because of queue topo change, but that looks not one big deal: + +1) same problem exists with current code base + +2) compared with !mpath, mpath use case is dominant + +Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic") +Cc: stable@vger.kernel.org +Signed-off-by: Ming Lei +Tested-by: Yi Zhang +Reviewed-by: Sagi Grimberg +Signed-off-by: Keith Busch +Signed-off-by: Greg Kroah-Hartman +--- + drivers/nvme/host/tcp.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/drivers/nvme/host/tcp.c ++++ b/drivers/nvme/host/tcp.c +@@ -1890,6 +1890,7 @@ static int nvme_tcp_configure_io_queues( + goto out_cleanup_connect_q; + + if (!new) { ++ nvme_start_freeze(ctrl); + nvme_start_queues(ctrl); + if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) { + /* +@@ -1898,6 +1899,7 @@ static int nvme_tcp_configure_io_queues( + * to be safe. + */ + ret = -ENODEV; ++ nvme_unfreeze(ctrl); + goto out_wait_freeze_timed_out; + } + blk_mq_update_nr_hw_queues(ctrl->tagset, +@@ -2002,7 +2004,6 @@ static void nvme_tcp_teardown_io_queues( + if (ctrl->queue_count <= 1) + return; + nvme_stop_admin_queue(ctrl); +- nvme_start_freeze(ctrl); + nvme_stop_queues(ctrl); + nvme_sync_io_queues(ctrl); + nvme_tcp_stop_io_queues(ctrl); diff --git a/queue-6.1/series b/queue-6.1/series index 104ee9f9a97..ab5f8aafe67 100644 --- a/queue-6.1/series +++ b/queue-6.1/series @@ -130,3 +130,5 @@ btrfs-properly-clear-end-of-the-unreserved-range-in-cow_file_range.patch btrfs-exit-gracefully-if-reloc-roots-don-t-match.patch btrfs-reject-invalid-reloc-tree-root-keys-with-stack-dump.patch btrfs-set-cache_block_group_error-if-we-find-an-error.patch +nvme-tcp-fix-potential-unbalanced-freeze-unfreeze.patch +nvme-rdma-fix-potential-unbalanced-freeze-unfreeze.patch