RDMA/addr: Change addr_wq back to unordered workqueue

Commit 5fff41e1f89d ("IB/core: Fix race condition in resolving IP to MAC")
changed the workqueue "addr_wq" to a single-threaded wq.
Commit e19c0d237873 ("RDMA/rdma_cm: Remove process_req and timer sorting")
eliminated global work and started using per-req work.
Now we no longer have the race, change "addr_wq" back to multi-threaded
workqueue to speed up multiple addr resolutions.

Signed-off-by: Surabhi Gogte <sgogte@purestorage.com>
Link: https://patch.msgid.link/20260410001549.3149060-1-sgogte@purestorage.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index a40a765f0307288775365272ee418edcb150ec28..9f6f03f4120480e032172415d4968e413426ae67 100644 (file)
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -850,7 +850,7 @@ static struct notifier_block nb = {
 
 int addr_init(void)
 {
-       addr_wq = alloc_ordered_workqueue("ib_addr", 0);
+       addr_wq = alloc_workqueue("ib_addr", WQ_UNBOUND, 0);
        if (!addr_wq)
                return -ENOMEM;