From d09e8f64653c93da5793c16be19330968f2a32e6 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 15 Sep 2026 14:34:57 +0300 Subject: [PATCH] net/mlx5: devcom, Base component size on linked devices mlx5_devcom_comp_get_size() returns the component's kref count. That kref is bumped in mlx5_devcom_register_component() under comp_list_lock, before the comp_dev is linked onto comp_dev_list_head under comp->sem. The event broadcast (mlx5_devcom_locked_send_event()) walks that list. Hence, a caller can read the expected size, but send_event won't be sent to all peers. In the SD group registration path, this lets a member broadcast its role-election event over an incomplete list, electing a primary that never completes the group, is never marked ready, and leaves the group with a stale primary. Track the number of linked comp_devs in a dedicated counter, maintained under comp->sem together with the list add/remove, and return it from mlx5_devcom_comp_get_size(). Fixes: 9bb1ac80738a ("net/mlx5: devcom, Add component size getter") Signed-off-by: Shay Drory Reviewed-by: Akiva Goldberger Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260915113459.3934760-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index 64f92427602d..75855481522b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -37,6 +37,7 @@ struct mlx5_devcom_comp { struct mlx5_devcom_key key; mlx5_devcom_event_handler_t handler; struct kref ref; + int nr_devs; bool ready; struct rw_semaphore sem; struct lock_class_key lock_key; @@ -170,6 +171,7 @@ devcom_alloc_comp_dev(struct mlx5_devcom_dev *devc, down_write(&comp->sem); list_add_tail(&devcom->list, &comp->comp_dev_list_head); + WRITE_ONCE(comp->nr_devs, comp->nr_devs + 1); up_write(&comp->sem); return devcom; @@ -182,6 +184,7 @@ devcom_free_comp_dev(struct mlx5_devcom_comp_dev *devcom) down_write(&comp->sem); list_del(&devcom->list); + WRITE_ONCE(comp->nr_devs, comp->nr_devs - 1); up_write(&comp->sem); kref_put(&devcom->devc->ref, mlx5_devcom_dev_release); @@ -284,7 +287,7 @@ int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom) { struct mlx5_devcom_comp *comp = devcom->comp; - return kref_read(&comp->ref); + return READ_ONCE(comp->nr_devs); } int mlx5_devcom_locked_send_event(struct mlx5_devcom_comp_dev *devcom,