Dakshaja Uppalapati 2638a32348 RDMA/iw_cxgb4: Fix refcount underflow while destroying cqs. ... Previous atomic increment/decrement logic expects the atomic count to be '0' after the final decrement. Replacing atomic count with refcount does not allow that, as refcount_dec() considers count of 1 as underflow and triggers a kernel splat. Fix the current refcount logic by using the usual pattern of decrementing the refcount and test if it is '0' on the final deref in c4iw_destroy_cq(). Use wait_for_completion() instead of wait_event(). Fixes: 7183451f84 ("RDMA/cxgb4: Use refcount_t instead of atomic_t for reference counting") Link: https://lore.kernel.org/r/1628167412-12114-1-git-send-email-dakshaja@chelsio.com Signed-off-by: Dakshaja Uppalapati <dakshaja@chelsio.com> Reviewed-by: Potnuri Bharat Teja <bharat@chelsio.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>		2021-08-05 22:33:00 -03:00
..
core	RDMA/cma: Revert INIT-INIT patch	2021-08-02 12:45:22 -03:00
hw	RDMA/iw_cxgb4: Fix refcount underflow while destroying cqs.	2021-08-05 22:33:00 -03:00
sw	RDMA/rxe: Restore setting tot_len in the IPv4 header	2021-08-02 12:45:22 -03:00
ulp	SCSI misc on 20210702	2021-07-02 15:14:36 -07:00
Kconfig	RDMA/irdma: Add irdma Kconfig/Makefile and remove i40iw	2021-06-02 20:06:36 -03:00
Makefile	treewide: Add SPDX license identifier - Makefile/Kconfig	2019-05-21 10:50:46 +02:00