From 3b4a8cd51e59c1c342c51b241bbb96c6ac24a147 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sat, 5 Sep 2009 20:24:50 -0700 Subject: IB/mlx4: Don't allow userspace open while recovering from catastrophic error Userspace apps are supposed to release all ib device resources if they receive a fatal async event (IBV_EVENT_DEVICE_FATAL). However, the app has no way of knowing when the device has come back up, except to repeatedly attempt ibv_open_device() until it succeeds. However, currently there is no protection against the open succeeding while the device is in being removed following the fatal event. In this case, the open will succeed, but as a result the device waits in the middle of its removal until the new app releases its resources -- and the new app will not do so, since the open succeeded at a point following the fatal event generation. This patch adds an "active" flag to the device. The active flag is set to false (in the fatal event flow) before the "fatal" event is generated, so any subsequent ibv_dev_open() call to the device will fail until the device comes back up, thus preventing the above deadlock. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/main.c | 6 ++++++ drivers/infiniband/hw/mlx4/mlx4_ib.h | 1 + 2 files changed, 7 insertions(+) (limited to 'drivers/infiniband/hw') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index ae3d7590346..313ce7fb273 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -342,6 +342,9 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev, struct mlx4_ib_alloc_ucontext_resp resp; int err; + if (!dev->ib_active) + return ERR_PTR(-EAGAIN); + resp.qp_tab_size = dev->dev->caps.num_qps; resp.bf_reg_size = dev->dev->caps.bf_reg_size; resp.bf_regs_per_page = dev->dev->caps.bf_regs_per_page; @@ -673,6 +676,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) goto err_reg; } + ibdev->ib_active = true; + return ibdev; err_reg: @@ -729,6 +734,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, break; case MLX4_DEV_EVENT_CATASTROPHIC_ERROR: + ibdev->ib_active = false; ibev.event = IB_EVENT_DEVICE_FATAL; break; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 8a7dd6795fa..3486d7675e5 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -175,6 +175,7 @@ struct mlx4_ib_dev { spinlock_t sm_lock; struct mutex cap_mask_mutex; + bool ib_active; }; static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev) -- cgit v1.2.3-70-g09d2