Description of problem:

When tested on CXGB4 IW device, all mvapich2 benchmarks fail with the following error message.

"Error creating SRQ: Invalid argument (22)"

Version-Release number of selected component (if applicable):

Clients: rdma-dev-13
Servers: rdma-qe-12

DISTRO=RHEL-8.7.0-20220424.1

+ [22-05-05 13:51:48] cat /etc/redhat-release
Red Hat Enterprise Linux release 8.7 Beta (Ootpa)

+ [22-05-05 13:51:48] uname -a
Linux rdma-dev-13.rdma.lab.eng.rdu2.redhat.com 4.18.0-384.el8.x86_64 #1 SMP Wed Apr 20 16:08:47 EDT 2022 x86_64 x86_64 x86_64 GNU/Linux

+ [22-05-05 13:51:48] cat /proc/cmdline
BOOT_IMAGE=(hd0,msdos1)/vmlinuz-4.18.0-384.el8.x86_64 root=/dev/mapper/rhel_rdma-dev13-root ro intel_idle.max_cstate=0 intremap=no_x2apic_optout processor.max_cstate=0 console=tty0 rd_NO_PLYMOUTH crashkernel=auto resume=/dev/mapper/rhel_rdmadev-13-swap rd.lvm.lv=rhel_rdma-dev-13/root rd.lvm.lv=rhel_rdma-dev-13/swap console=ttyS1,115200n81

+ [22-05-05 13:51:48] rpm -q rdma-core linux-firmware
rdma-core-37.2-1.el8.x86_64
linux-firmware-20220210-107.git6342082c.el8.noarch

+ [22-05-05 13:51:48] tail /sys/class/infiniband/cxgb4_0/fw_ver
1.26.6.0
+ [22-05-05 13:51:48] lspci
+ [22-05-05 13:51:48] grep -i -e ethernet -e infiniband -e omni -e ConnectX
03:00.0 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5717 Gigabit Ethernet PCIe (rev 10)
03:00.1 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5717 Gigabit Ethernet PCIe (rev 10)
05:00.0 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
05:00.1 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
05:00.2 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
05:00.3 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller
05:00.4 Ethernet controller: Chelsio Communications Inc T62100-LP-CR Unified Wire Ethernet Controller

Installed:
mpitests-mvapich2-5.8-1.el8.x86_64 mvapich2-2.3.6-1.el8.x86_64

How reproducible:

100%

Steps to Reproduce:
1. bring up the RDMA hosts mentioned above with RHEL8.7 build
2. set up RDMA hosts for mvapich2 benchamrk tests
3. run one of the mvapich2 benchmark with "mpirun" command, as the following:

timeout --preserve-status --kill-after=5m 3m mpirun -hostfile /root/hfile_one_core -np 2 mpitests-IMB-MPI1 PingPong -time 1.5

Actual results:

[rdma-qe-12.rdma.lab.eng.rdu2.redhat.com:mpi_rank_0][rdma_param_handle_heterogeneity] All nodes involved in the job were detected to be homogeneous in terms of processors and interconnects. Setting MV2_HOMOGENEOUS_CLUSTER=1 can improve job startup performance on such systems. The following link has more details on enhancing job startup performance. http://mvapich.cse.ohio-state.edu/performance/job-startup/.
[rdma-qe-12.rdma.lab.eng.rdu2.redhat.com:mpi_rank_0][rdma_param_handle_heterogeneity] To suppress this warning, please set MV2_SUPPRESS_JOB_STARTUP_PERFORMANCE_WARNING to 1

[rdma-qe-12.rdma.lab.eng.rdu2.redhat.com:mpi_rank_0][create_srq] src/mpid/ch3/channels/mrail/src/gen2/rdma_iba_priv.c:271: Error creating SRQ
: Invalid argument (22)

[mpiexec@rdma-dev-13.rdma.lab.eng.rdu2.redhat.com] HYDU_sock_write (utils/sock/sock.c:294): write error (Bad file descriptor)
[mpiexec@rdma-dev-13.rdma.lab.eng.rdu2.redhat.com] HYD_pmcd_pmiserv_send_signal (pm/pmiserv/pmiserv_cb.c:177): unable to write data to proxy
[mpiexec@rdma-dev-13.rdma.lab.eng.rdu2.redhat.com] ui_cmd_cb (pm/pmiserv/pmiserv_pmci.c:79): unable to send signal downstream
[mpiexec@rdma-dev-13.rdma.lab.eng.rdu2.redhat.com] HYDT_dmxu_poll_wait_for_event (tools/demux/demux_poll.c:76): callback returned error status
[mpiexec@rdma-dev-13.rdma.lab.eng.rdu2.redhat.com] HYD_pmci_wait_for_completion (pm/pmiserv/pmiserv_pmci.c:198): error waiting for event
[mpiexec@rdma-dev-13.rdma.lab.eng.rdu2.redhat.com] main (ui/mpich/mpiexec.c:340): process manager error waiting for completion
+ [22-05-05 13:54:57] __MPI_check_result 255 mpitests-mvapich2 IMB-MPI1 PingPong mpirun /root/hfile_one_core

Expected results:

Normal execution of benchmark test with stats output

Additional info:

Same behavior exists on RHEL-8.6 builds