Huy Nguyen bb7e22a8ab IB/mlx5: Fix long EEH recover time with NVMe offloads ... On NVMe offloads connection with many IO queues, EEH takes long time to recover. The culprit is the synchronize_srcu in the destroy_mkey. The solution is to use synchronize_srcu only for ODP mkey. Fixes: b4cfe447d4 ("IB/mlx5: Implement on demand paging by adding support for MMU notifiers") Signed-off-by: Huy Nguyen <huyn@mellanox.com> Reviewed-by: Daniel Jurgens <danielj@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>		2018-12-20 16:28:47 -07:00
..
bnxt_re	RDMA/bnxt_re: Increase depth of control path command queue	2018-12-19 16:37:33 -07:00
cxgb3	RDMA: Cleanup undesired pd->uobject usage	2018-12-18 19:15:48 -07:00
cxgb4	RDMA: Cleanup undesired pd->uobject usage	2018-12-18 19:15:48 -07:00
hfi1	RDMA: Mark if create address handle is in a sleepable context	2018-12-19 16:17:19 -07:00
hns	RDMA: Mark if destroy address handle is in a sleepable context	2018-12-19 16:28:03 -07:00
i40iw	RDMA: Cleanup undesired pd->uobject usage	2018-12-18 19:15:48 -07:00
mlx4	RDMA: Mark if destroy address handle is in a sleepable context	2018-12-19 16:28:03 -07:00
mlx5	IB/mlx5: Fix long EEH recover time with NVMe offloads	2018-12-20 16:28:47 -07:00
mthca	RDMA: Mark if destroy address handle is in a sleepable context	2018-12-19 16:28:03 -07:00
nes	RDMA: Cleanup undesired pd->uobject usage	2018-12-18 19:15:48 -07:00
ocrdma	RDMA: Mark if destroy address handle is in a sleepable context	2018-12-19 16:28:03 -07:00
qedr	RDMA: Mark if destroy address handle is in a sleepable context	2018-12-19 16:28:03 -07:00
qib	RDMA: Mark if destroy address handle is in a sleepable context	2018-12-19 16:28:03 -07:00
usnic	IB/usnic: Fix potential deadlock	2018-12-19 16:30:16 -07:00
vmw_pvrdma	RDMA: Mark if destroy address handle is in a sleepable context	2018-12-19 16:28:03 -07:00
Makefile	License cleanup: add SPDX GPL-2.0 license identifier to files with no license	2017-11-02 11:10:55 +01:00