From 76cfe60e3ab724313d9fba4cf5ebaf12ad49ea0e Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Nov 04 2022 13:55:06 +0000 Subject: Merge branch 'users/nmoreychaisemartin/SLE15-SP4/for-next' into SLE15-SP4 Pull an IB git-fix from Nicolas Morey-Chaisemartin. --- diff --git a/patches.suse/IB-core-Fix-a-nested-dead-lock-as-part-of-ODP-flow.patch b/patches.suse/IB-core-Fix-a-nested-dead-lock-as-part-of-ODP-flow.patch new file mode 100644 index 0000000..2e444ee --- /dev/null +++ b/patches.suse/IB-core-Fix-a-nested-dead-lock-as-part-of-ODP-flow.patch @@ -0,0 +1,93 @@ +From 85eaeb5058f0f04dffb124c97c86b4f18db0b833 Mon Sep 17 00:00:00 2001 +From: Yishai Hadas +Date: Wed, 24 Aug 2022 09:10:36 +0300 +Subject: [PATCH 1/1] IB/core: Fix a nested dead lock as part of ODP flow +Git-commit: 85eaeb5058f0f04dffb124c97c86b4f18db0b833 +Patch-mainline: v6.0 +References: git-fixes + +Fix a nested dead lock as part of ODP flow by using mmput_async(). + +From the below call trace [1] can see that calling mmput() once we have +the umem_odp->umem_mutex locked as required by +ib_umem_odp_map_dma_and_lock() might trigger in the same task the +exit_mmap()->__mmu_notifier_release()->mlx5_ib_invalidate_range() which +may dead lock when trying to lock the same mutex. + +Moving to use mmput_async() will solve the problem as the above +exit_mmap() flow will be called in other task and will be executed once +the lock will be available. + +[1] +[64843.077665] task:kworker/u133:2 state:D stack: 0 pid:80906 ppid: +2 flags:0x00004000 +[64843.077672] Workqueue: mlx5_ib_page_fault mlx5_ib_eqe_pf_action [mlx5_ib] +[64843.077719] Call Trace: +[64843.077722] +[64843.077724] __schedule+0x23d/0x590 +[64843.077729] schedule+0x4e/0xb0 +[64843.077735] schedule_preempt_disabled+0xe/0x10 +[64843.077740] __mutex_lock.constprop.0+0x263/0x490 +[64843.077747] __mutex_lock_slowpath+0x13/0x20 +[64843.077752] mutex_lock+0x34/0x40 +[64843.077758] mlx5_ib_invalidate_range+0x48/0x270 [mlx5_ib] +[64843.077808] __mmu_notifier_release+0x1a4/0x200 +[64843.077816] exit_mmap+0x1bc/0x200 +[64843.077822] ? walk_page_range+0x9c/0x120 +[64843.077828] ? __cond_resched+0x1a/0x50 +[64843.077833] ? mutex_lock+0x13/0x40 +[64843.077839] ? uprobe_clear_state+0xac/0x120 +[64843.077860] mmput+0x5f/0x140 +[64843.077867] ib_umem_odp_map_dma_and_lock+0x21b/0x580 [ib_core] +[64843.077931] pagefault_real_mr+0x9a/0x140 [mlx5_ib] +[64843.077962] pagefault_mr+0xb4/0x550 [mlx5_ib] +[64843.077992] pagefault_single_data_segment.constprop.0+0x2ac/0x560 +[mlx5_ib] +[64843.078022] mlx5_ib_eqe_pf_action+0x528/0x780 [mlx5_ib] +[64843.078051] process_one_work+0x22b/0x3d0 +[64843.078059] worker_thread+0x53/0x410 +[64843.078065] ? process_one_work+0x3d0/0x3d0 +[64843.078073] kthread+0x12a/0x150 +[64843.078079] ? set_kthread_struct+0x50/0x50 +[64843.078085] ret_from_fork+0x22/0x30 +[64843.078093] + +Fixes: 36f30e486dce ("IB/core: Improve ODP to use hmm_range_fault()") +Reviewed-by: Maor Gottlieb +Signed-off-by: Yishai Hadas +Link: https://lore.kernel.org/r/74d93541ea533ef7daec6f126deb1072500aeb16.1661251841.git.leonro@nvidia.com +Signed-off-by: Leon Romanovsky +Acked-by: Nicolas Morey-Chaisemartin +--- + drivers/infiniband/core/umem_odp.c | 2 +- + kernel/fork.c | 1 + + 2 files changed, 2 insertions(+), 1 deletion(-) + +diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c +index 186ed8859920..d39e16c211e8 100644 +--- a/drivers/infiniband/core/umem_odp.c ++++ b/drivers/infiniband/core/umem_odp.c +@@ -462,7 +462,7 @@ retry: + mutex_unlock(&umem_odp->umem_mutex); + + out_put_mm: +- mmput(owning_mm); ++ mmput_async(owning_mm); + out_put_task: + if (owning_process) + put_task_struct(owning_process); +diff --git a/kernel/fork.c b/kernel/fork.c +index 90c85b17bf69..8a9e92068b15 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1225,6 +1225,7 @@ void mmput_async(struct mm_struct *mm) + schedule_work(&mm->async_put_work); + } + } ++EXPORT_SYMBOL_GPL(mmput_async); + #endif + + /** +-- +2.38.0.1.gee35aeee4b76 + diff --git a/series.conf b/series.conf index 17a4072..f395ade 100644 --- a/series.conf +++ b/series.conf @@ -14935,6 +14935,7 @@ patches.suse/RDMA-cma-Fix-arguments-order-in-net-device-validatio.patch patches.suse/RDMA-srp-Set-scmnd-result-only-when-scmnd-is-not-NUL.patch patches.suse/RDMA-siw-Pass-a-pointer-to-virt_to_page.patch + patches.suse/IB-core-Fix-a-nested-dead-lock-as-part-of-ODP-flow.patch patches.suse/RDMA-irdma-Report-the-correct-max-cqes-from-query-de.patch patches.suse/RDMA-irdma-Return-error-on-MR-deregister-CQP-failure.patch patches.suse/RDMA-irdma-Return-correct-WC-error-for-bind-operatio.patch