Description of problem:

When tested on BCM57508 device, all mvapich2 benchmarks fail with "Segmentation fault" error.

The HW tested was rdma-dev-25/26 pair.

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

Clients: rdma-dev-26
Servers: rdma-dev-25

DISTRO=RHEL-8.7.0-20220424.1

+ [22-05-06 03:31:59] cat /etc/redhat-release
Red Hat Enterprise Linux release 8.7 Beta (Ootpa)

+ [22-05-06 03:31:59] uname -a
Linux rdma-dev-26.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

+ [22-05-06 03:31:59] cat /proc/cmdline
BOOT_IMAGE=(hd0,msdos1)/vmlinuz-4.18.0-384.el8.x86_64 root=/dev/mapper/rhel_rdma-dev26-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-26-swap rd.lvm.lv=rhel_rdma-dev-26/root rd.lvm.lv=rhel_rdma-dev-26/swap console=ttyS1,115200n81

+ [22-05-06 03:31:59] rpm -q rdma-core linux-firmware
rdma-core-37.2-1.el8.x86_64
linux-firmware-20220210-107.git6342082c.el8.noarch

+ [22-05-06 03:31:59] tail /sys/class/infiniband/bnxt_re0/fw_ver /sys/class/infiniband/bnxt_re1/fw_ver
==> /sys/class/infiniband/bnxt_re0/fw_ver <==
219.0.112.0

==> /sys/class/infiniband/bnxt_re1/fw_ver <==
219.0.112.0

+ [22-05-06 03:31:59] lspci
+ [22-05-06 03:31:59] grep -i -e ethernet -e infiniband -e omni -e ConnectX
02:00.0 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5720 Gigabit Ethernet PCIe
02:00.1 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5720 Gigabit Ethernet PCIe
03:00.0 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5720 Gigabit Ethernet PCIe
03:00.1 Ethernet controller: Broadcom Inc. and subsidiaries NetXtreme BCM5720 Gigabit Ethernet PCIe
04:00.0 Ethernet controller: Broadcom Inc. and subsidiaries BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb Ethernet (rev 11)
04:00.1 Ethernet controller: Broadcom Inc. and subsidiaries BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb Ethernet (rev 11)

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-dev-25.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-dev-25.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
#----------------------------------------------------------------

1. Intel(R) MPI Benchmarks 2021.3, MPI-1 part
   #----------------------------------------------------------------
2. Date : Fri May 6 03:32:15 2022
3. Machine : x86_64
4. System : Linux
5. Release : 4.18.0-384.el8.x86_64
6. Version : #1 SMP Wed Apr 20 16:08:47 EDT 2022
7. MPI Version : 3.1
8. MPI Thread Environment:

1. Calling sequence was:

1. mpitests-IMB-MPI1 PingPong -time 1.5

1. Minimum message length in bytes: 0
2. Maximum message length in bytes: 4194304
   #
3. MPI_Datatype : MPI_BYTE
4. MPI_Datatype for reductions : MPI_FLOAT
5. MPI_Op : MPI_SUM

1. List of Benchmarks to run:

1. PingPong

#---------------------------------------------------

1. Benchmarking PingPong
2. #processes = 2
   #---------------------------------------------------
   #bytes #repetitions t[usec] Mbytes/sec
   0 1000 2.92 0.00
   1 1000 2.94 0.34
   2 1000 2.94 0.68
   4 1000 2.93 1.36
   8 1000 2.94 2.73
   16 1000 2.94 5.44
   32 1000 2.96 10.81
   64 1000 2.96 21.62
   128 1000 3.44 37.20
   256 1000 3.48 73.51
   512 1000 3.57 143.60
   1024 1000 3.73 274.43
   2048 1000 3.88 528.35
   4096 1000 4.29 953.83
   8192 1000 5.43 1509.79
   16384 1000 11.16 1467.86
   32768 1000 12.60 2600.57
   65536 640 15.51 4224.57
   131072 320 21.28 6158.76
   262144 160 32.91 7964.41
   524288 80 55.89 9380.00
   1048576 40 101.84 10296.26
   2097152 20 193.79 10821.96
   4194304 10 377.88 11099.52

1. All processes entering MPI_Finalize

[rdma-dev-26.rdma.lab.eng.rdu2.redhat.com:mpi_rank_1][error_sighandler] Caught error: Segmentation fault (signal 11)
[rdma-dev-25.rdma.lab.eng.rdu2.redhat.com:mpi_rank_0][error_sighandler] Caught error: Segmentation fault (signal 11)

===================================================================================
= BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
= PID 9759 RUNNING AT 172.31.45.126
= EXIT CODE: 139
= CLEANING UP REMAINING PROCESSES
= YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
[proxy:0:0@rdma-dev-25.rdma.lab.eng.rdu2.redhat.com] HYD_pmcd_pmip_control_cmd_cb (pm/pmiserv/pmip_cb.c:911): assert (!closed) failed
[proxy:0:0@rdma-dev-25.rdma.lab.eng.rdu2.redhat.com] HYDT_dmxu_poll_wait_for_event (tools/demux/demux_poll.c:76): callback returned error status
[proxy:0:0@rdma-dev-25.rdma.lab.eng.rdu2.redhat.com] main (pm/pmiserv/pmip.c:202): demux engine error waiting for event
YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)
This typically refers to a problem with your application.
Please see the FAQ page for debugging suggestions
+ [22-05-06 03:32:16] __MPI_check_result 139 mpitests-mvapich2 IMB-MPI1 PingPong mpirun /root/hfile_one_core

Expected results:

Normal execution of the benchmark with stats output

Additional info:

Same behavior exists on RHEL8.6 builds