Skip to contentSkip to conversation

NVMe RDMA OPA: kmemleak observed with connect/reset_controller/disconnect

bug report Yi Zhang 3 participants 3 messages Mar 4, 2020 – Mar 6, 2020 1 message not in the archive

Subsystems (2)
lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

Yi Zhang

author
#1 lore raw

Hello

I would like to report a kmemleak issue found on NVMe RDMA OPA environment, here is the log, let me know if you need more info

unreferenced object 0xffffc90006639000 (size 12288):
comm "kworker/u128:0", pid 8, jiffies 4295777598 (age 589.085s) hex dump (first 32 bytes):

    4d 00 00 00 4d 00 00 00 00 c0 08 ac 8b 88 ff ff  M...M...........
    00 00 00 00 80 00 00 00 00 00 00 00 10 00 00 00  ................
  backtrace:
    [<0000000035a3d625>] __vmalloc_node_range+0x361/0x720
    [<000000002942ce4f>] __vmalloc_node.constprop.30+0x63/0xb0
    [<00000000f228f784>] rvt_create_cq+0x98a/0xd80 [rdmavt]
    [<00000000b84aec66>] __ib_alloc_cq_user+0x281/0x1260 [ib_core]
    [<00000000ef3764be>] nvme_rdma_cm_handler+0xdb7/0x1b80 [nvme_rdma]
    [<00000000936b401c>] cma_cm_event_handler+0xb7/0x550 [rdma_cm]
    [<00000000d9c40b7b>] addr_handler+0x195/0x310 [rdma_cm]
    [<00000000c7398a03>] process_one_req+0xdd/0x600 [ib_core]
    [<000000004d29675b>] process_one_work+0x920/0x1740
    [<00000000efedcdb5>] worker_thread+0x87/0xb40
    [<000000005688b340>] kthread+0x327/0x3f0
    [<0000000043a168d6>] ret_from_fork+0x3a/0x50
unreferenced object 0xffffc90008581000 (size 36864):
  comm "kworker/u128:0", pid 8, jiffies 4295778075 (age 588.608s)
  hex dump (first 32 bytes):
    84 00 00 00 84 00 00 00 40 01 36 5d 84 88 ff ff  [email protected]]....
    00 00 00 00 00 00 00 00 00 00 00 00 40 04 00 00  ............@...
  backtrace:
    [<0000000035a3d625>] __vmalloc_node_range+0x361/0x720
    [<000000002942ce4f>] __vmalloc_node.constprop.30+0x63/0xb0
    [<00000000f228f784>] rvt_create_cq+0x98a/0xd80 [rdmavt]
    [<00000000b84aec66>] __ib_alloc_cq_user+0x281/0x1260 [ib_core]
    [<00000000ef3764be>] nvme_rdma_cm_handler+0xdb7/0x1b80 [nvme_rdma]
    [<00000000936b401c>] cma_cm_event_handler+0xb7/0x550 [rdma_cm]
    [<00000000d9c40b7b>] addr_handler+0x195/0x310 [rdma_cm]
    [<00000000c7398a03>] process_one_req+0xdd/0x600 [ib_core]
    [<000000004d29675b>] process_one_work+0x920/0x1740
    [<00000000efedcdb5>] worker_thread+0x87/0xb40
    [<000000005688b340>] kthread+0x327/0x3f0
    [<0000000043a168d6>] ret_from_fork+0x3a/0x50

Best Regards,
Yi Zhang

_______________________________________________
linux-nvme mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-nvme

maintainer
#2 lore raw

CCing Linux-rdma as I don't think anyone in nvme will have a clue to whats going on here...

Quoted 46 lines · Yi Zhang

Hello

I would like to report a kmemleak issue found on NVMe RDMA OPA environment, here is the log, let me know if you need more info

unreferenced object 0xffffc90006639000 (size 12288):

   comm "kworker/u128:0", pid 8, jiffies 4295777598 (age 589.085s)
   hex dump (first 32 bytes):
     4d 00 00 00 4d 00 00 00 00 c0 08 ac 8b 88 ff ff  M...M...........
     00 00 00 00 80 00 00 00 00 00 00 00 10 00 00 00  ................
   backtrace:
     [<0000000035a3d625>] __vmalloc_node_range+0x361/0x720
     [<000000002942ce4f>] __vmalloc_node.constprop.30+0x63/0xb0
     [<00000000f228f784>] rvt_create_cq+0x98a/0xd80 [rdmavt]
     [<00000000b84aec66>] __ib_alloc_cq_user+0x281/0x1260 [ib_core]
     [<00000000ef3764be>] nvme_rdma_cm_handler+0xdb7/0x1b80 [nvme_rdma]
     [<00000000936b401c>] cma_cm_event_handler+0xb7/0x550 [rdma_cm]
     [<00000000d9c40b7b>] addr_handler+0x195/0x310 [rdma_cm]
     [<00000000c7398a03>] process_one_req+0xdd/0x600 [ib_core]
     [<000000004d29675b>] process_one_work+0x920/0x1740
     [<00000000efedcdb5>] worker_thread+0x87/0xb40
     [<000000005688b340>] kthread+0x327/0x3f0
     [<0000000043a168d6>] ret_from_fork+0x3a/0x50
unreferenced object 0xffffc90008581000 (size 36864):
   comm "kworker/u128:0", pid 8, jiffies 4295778075 (age 588.608s)
   hex dump (first 32 bytes):
     84 00 00 00 84 00 00 00 40 01 36 5d 84 88 ff ff  [email protected]]....
     00 00 00 00 00 00 00 00 00 00 00 00 40 04 00 00  ............@...
   backtrace:
     [<0000000035a3d625>] __vmalloc_node_range+0x361/0x720
     [<000000002942ce4f>] __vmalloc_node.constprop.30+0x63/0xb0
     [<00000000f228f784>] rvt_create_cq+0x98a/0xd80 [rdmavt]
     [<00000000b84aec66>] __ib_alloc_cq_user+0x281/0x1260 [ib_core]
     [<00000000ef3764be>] nvme_rdma_cm_handler+0xdb7/0x1b80 [nvme_rdma]
     [<00000000936b401c>] cma_cm_event_handler+0xb7/0x550 [rdma_cm]
     [<00000000d9c40b7b>] addr_handler+0x195/0x310 [rdma_cm]
     [<00000000c7398a03>] process_one_req+0xdd/0x600 [ib_core]
     [<000000004d29675b>] process_one_work+0x920/0x1740
     [<00000000efedcdb5>] worker_thread+0x87/0xb40
     [<000000005688b340>] kthread+0x327/0x3f0
     [<0000000043a168d6>] ret_from_fork+0x3a/0x50

Best Regards,
Yi Zhang

#3 lore raw
Quoted 3 lines · Sagi Grimberg

CCing Linux-rdma as I don't think anyone in nvme will have a clue to whats going on here...

We will take a look at it. Thanks for forwarding!

-Denny