We hit a divide 0 error in ofed 5.1.2.3.7.1. But dim.c and rdma_dim.c seem same as upstream. CallTrace: Hardware name: H3C R4900 G3/RS33M2C9S, BIOS 2.00.37P21 03/12/2020 task: ffff880194b78000 task.stack: ffffc90006714000 RIP: 0010:backport_rdma_dim+0x10e/0x240 [mlx_compat] RSP: 0018:ffff880c10e83ec0 EFLAGS: 00010202 RAX: 0000000000002710 RBX: ffff88096cd7f780 RCX: 0000000000000064 RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000000001 RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 000000001d7c6c09 R13: ffff88096cd7f780 R14: ffff880b174fe800 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff880c10e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000a0965b00 CR3: 000000000200a003 CR4: 00000000007606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <IRQ> ib_poll_handler+0x43/0x80 [ib_core] irq_poll_softirq+0xae/0x110 __do_softirq+0xd1/0x28c irq_exit+0xde/0xf0 do_IRQ+0x54/0xe0 common_interrupt+0x8f/0x8f </IRQ> ? cpuidle_enter_state+0xd9/0x2a0 ? cpuidle_enter_state+0xc7/0x2a0 ? do_idle+0x170/0x1d0 ? cpu_startup_entry+0x6f/0x80 ? start_secondary+0x1b9/0x210 ? secondary_startup_64+0xa5/0xb0 Code: 0f 87 e1 00 00 00 8b 4c 24 14 44 8b 43 14 89 c8 4d 63 c8 44 29 c0 99 31 d0 29 d0 31 d2 48 98 48 8d 04 80 48 8d 04 80 48 c1 e0 02 <49> f7 f1 48 83 f8 0a 0f 86 c1 00 00 00 44 39 c1 7f 10 48 89 df RIP: backport_rdma_dim+0x10e/0x240 [mlx_compat] RSP: ffff880c10e83ec0 crash> struct dim ffff88096cd7f780 struct dim { state = 1 '\001', prev_stats = { ppms = 2142150514, bpms = 391112768, epms = -30709, cpms = 1, cpe_ratio = 0 }, start_sample = { time = 51174507127193614, pkt_ctr = 0, byte_ctr = 0, event_ctr = 1, comp_ctr = 494693321 }, measuring_sample = { time = 51174507266581985, pkt_ctr = 0, byte_ctr = 0, event_ctr = 65, comp_ctr = 494693385 }, work = { data = { counter = 128 }, entry = { next = 0xffff88096cd7f7d0, prev = 0xffff88096cd7f7d0 }, func = 0xffffffffa02b9f80 }, priv = 0xffff880b174fe800, profile_ix = 1 '\001', mode = 0 '\000', tune_state = 2 '\002', steps_right = 1 '\001', steps_left = 1 '\001', tired = 0 '\000' } Fixes: f4915455dcf0 ("linux/dim: Implement RDMA adaptive moderation (DIM)") Signed-off-by: Tao Liu <thomas.liu@xxxxxxxxx> --- lib/dim/rdma_dim.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/dim/rdma_dim.c b/lib/dim/rdma_dim.c index 15462d54758d..a657b106343c 100644 --- a/lib/dim/rdma_dim.c +++ b/lib/dim/rdma_dim.c @@ -34,6 +34,9 @@ static int rdma_dim_stats_compare(struct dim_stats *curr, return (curr->cpms > prev->cpms) ? DIM_STATS_BETTER : DIM_STATS_WORSE; + if (!prev->cpe_ratio) + return DIM_STATS_SAME; + if (IS_SIGNIFICANT_DIFF(curr->cpe_ratio, prev->cpe_ratio)) return (curr->cpe_ratio > prev->cpe_ratio) ? DIM_STATS_BETTER : DIM_STATS_WORSE; -- 2.30.1 (Apple Git-130)