diff options
author | Yishai Hadas <yishaih@mellanox.com> | 2015-02-08 11:49:34 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-02-09 14:03:53 -0800 |
commit | 35f05dabf95ac3ebc4c15bafd6833f7a3046e66f (patch) | |
tree | a39bb7c432f4e36467e61b316050e41ecd408b1f /drivers/infiniband/hw/mlx4/mlx4_ib.h | |
parent | 824c25c1abe70a527646056f6911d181facde9cc (diff) |
IB/mlx4: Reset flow support for IB kernel ULPs
The driver exposes interfaces that directly relate to HW state. Upon fatal
error, consumers of these interfaces (ULPs) that rely on completion of
all their posted work-request could hang, thereby introducing dependencies
in shutdown order. To prevent this from happening, we manage the
relevant resources (CQs, QPs) that are used by the device. Upon a fatal error,
we now generate simulated completions for outstanding WQEs that were not
completed at the time the HW was reset.
It includes invoking the completion event handler for all involved CQs so that
the ULPs will poll those CQs. When polled we return simulated CQEs with
IB_WC_WR_FLUSH_ERR return code enabling ULPs to clean up their resources and
not wait forever for completions upon receiving remove_one.
The above change requires an extra check in the data path to make sure that when
device is in error state, the simulated CQEs will be returned and no further
WQEs will be posted.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/infiniband/hw/mlx4/mlx4_ib.h')
-rw-r--r-- | drivers/infiniband/hw/mlx4/mlx4_ib.h | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 721540c9163d..f829fd935b79 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -110,6 +110,9 @@ struct mlx4_ib_cq { struct mutex resize_mutex; struct ib_umem *umem; struct ib_umem *resize_umem; + /* List of qps that it serves.*/ + struct list_head send_qp_list; + struct list_head recv_qp_list; }; struct mlx4_ib_mr { @@ -300,6 +303,9 @@ struct mlx4_ib_qp { struct mlx4_roce_smac_vlan_info pri; struct mlx4_roce_smac_vlan_info alt; u64 reg_id; + struct list_head qps_list; + struct list_head cq_recv_list; + struct list_head cq_send_list; }; struct mlx4_ib_srq { @@ -535,6 +541,9 @@ struct mlx4_ib_dev { /* lock when destroying qp1_proxy and getting netdev events */ struct mutex qp1_proxy_lock[MLX4_MAX_PORTS]; u8 bond_next_port; + /* protect resources needed as part of reset flow */ + spinlock_t reset_flow_resource_lock; + struct list_head qp_list; }; struct ib_event_work { |