linux/drivers/infiniband/hw/efa
Leon Romanovsky 43d781b9fa RDMA: Allow fail of destroy CQ
Like any other verbs objects, CQ shouldn't fail during destroy, but
mlx5_ib didn't follow this contract with mixed IB verbs objects with
DEVX. Such mix causes to the situation where FW and kernel are fully
interdependent on the reference counting of each side.

Kernel verbs and drivers that don't have DEVX flows shouldn't fail.

Fixes: e39afe3d6d ("RDMA: Convert CQ allocations to be under core responsibility")
Link: https://lore.kernel.org/r/20200907120921.476363-7-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2020-09-09 14:14:29 -03:00
..
efa_admin_cmds_defs.h RDMA/efa: Introduce SRD RNR retry 2020-08-18 14:52:45 -03:00
efa_admin_defs.h RDMA/efa: Unified getters/setters for device structs bitmask access 2020-02-28 12:12:04 -04:00
efa_com_cmd.c RDMA/efa: Introduce SRD RNR retry 2020-08-18 14:52:45 -03:00
efa_com_cmd.h RDMA/efa: Introduce SRD RNR retry 2020-08-18 14:52:45 -03:00
efa_com.c RDMA/efa: Count admin commands errors 2020-05-02 20:32:14 -03:00
efa_com.h RDMA/efa: Count admin commands errors 2020-05-02 20:32:14 -03:00
efa_common_defs.h RDMA/efa: Unified getters/setters for device structs bitmask access 2020-02-28 12:12:04 -04:00
efa_main.c RDMA/efa: Add EFA 0xefa1 PCI ID 2020-07-29 09:23:40 -03:00
efa_regs_defs.h RDMA/efa: Properly document the interrupt mask register 2020-02-28 12:12:12 -04:00
efa_verbs.c RDMA: Allow fail of destroy CQ 2020-09-09 14:14:29 -03:00
efa.h RDMA: Allow fail of destroy CQ 2020-09-09 14:14:29 -03:00
Kconfig RDMA/efa: Add driver to Kconfig/Makefile 2019-05-07 12:47:47 -03:00
Makefile RDMA/efa: Add driver to Kconfig/Makefile 2019-05-07 12:47:47 -03:00