Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
* Oops problem with rxe from 5.10-rc kernel
@ 2020-11-02 23:00 Olga Kornievskaia
  2020-11-03  0:26 ` Jason Gunthorpe
  2020-11-03 16:35 ` Pearson, Robert B
  0 siblings, 2 replies; 4+ messages in thread
From: Olga Kornievskaia @ 2020-11-02 23:00 UTC (permalink / raw)
  To: linux-rdma; +Cc: Olga Kornievskaia

Hi folks,

Is this a known problem? I'm unable to do simple rping over Soft RoCE
starting from 5.10-rc1 kernel (5.9 works).This is an oops from running
the following. I'm also unable to do NFS-over-RDMA.

sudo rping -c -a 192.168.1.105 -v -C 3
recv_buf reg_mr failed
rping_setup_buffers failed: 22

This is the oops
Nov  2 17:49:39 localhost kernel: ------------[ cut here ]------------
Nov  2 17:49:39 localhost kernel: WARNING: CPU: 0 PID: 2613 at
kernel/dma/mapping.c:188 dma_map_sg_attrs+0x37/0x50
Nov  2 17:49:39 localhost kernel: Modules linked in: rpcsec_gss_krb5
nfsv4 dns_resolver nfs lockd grace nfs_ssc rpcrdma rdma_rxe
ip6_udp_tunnel udp_tunnel rdma_ucm rdma_cm iw_cm ib_cm ib_uverbs
ib_core nls_utf8 isofs fuse rfcomm nft_fib_inet nft_fib_ipv4
nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6
nft_reject nft_ct nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 tun
bridge stp llc ip6_tables nft_compat ip_set nf_tables nfnetlink bnep
vmw_vsock_vmci_transport vsock snd_seq_midi snd_seq_midi_event
intel_rapl_msr intel_rapl_common crct10dif_pclmul crc32_pclmul
vmw_balloon ghash_clmulni_intel joydev uvcvideo pcspkr
videobuf2_vmalloc videobuf2_memops videobuf2_v4l2 btusb btrtl btbcm
btintel videobuf2_common snd_ens1371 videodev snd_ac97_codec ac97_bus
snd_seq mc snd_pcm bluetooth rfkill ecdh_generic ecc snd_timer
snd_rawmidi snd_seq_device snd soundcore vmw_vmci i2c_piix4
auth_rpcgss sunrpc ip_tables xfs libcrc32c sr_mod cdrom sg
crc32c_intel ata_generic serio_raw vmwgfx nvme nvme_core t10_pi
Nov  2 17:49:39 localhost kernel: drm_kms_helper syscopyarea
sysfillrect sysimgblt fb_sys_fops cec vmxnet3 ata_piix ahci libahci
ttm drm libata
Nov  2 17:49:39 localhost kernel: CPU: 0 PID: 2613 Comm: rping
Tainted: G        W         5.10.0-rc2+ #21
Nov  2 17:49:39 localhost kernel: Hardware name: VMware, Inc. VMware
Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00
02/27/2020
Nov  2 17:49:39 localhost kernel: RIP: 0010:dma_map_sg_attrs+0x37/0x50
Nov  2 17:49:39 localhost kernel: Code: 85 c0 48 0f 44 05 a9 22 e5 01
83 f9 02 77 19 48 83 bf 48 02 00 00 00 74 11 48 85 c0 75 11 e8 20 19
00 00 85 c0 78 13 c3 0f 0b <0f> 0b 31 c0 c3 48 8b 40 50 e8 7b 50 ab 00
eb e9 0f 0b 0f 1f 80 00
Nov  2 17:49:39 localhost kernel: RSP: 0018:ffffa8958297ba30 EFLAGS: 00010246
Nov  2 17:49:39 localhost kernel: RAX: ffffffff8fc23260 RBX:
000055af0b7aa000 RCX: 0000000000000000
Nov  2 17:49:39 localhost kernel: RDX: 0000000000000001 RSI:
ffff90719c4290c0 RDI: ffff9071a5b3c4e8
Nov  2 17:49:39 localhost kernel: RBP: 0000000000000000 R08:
0000000000000000 R09: 0000000000000000
Nov  2 17:49:39 localhost kernel: R10: ffffe64f807e35c0 R11:
0000000000000000 R12: ffff9071a5b3c000
Nov  2 17:49:39 localhost kernel: R13: 0000000000000000 R14:
ffff9071f14c1000 R15: ffff907199f82d00
Nov  2 17:49:39 localhost kernel: FS:  00007f869a842740(0000)
GS:ffff9071fbe00000(0000) knlGS:0000000000000000
Nov  2 17:49:39 localhost kernel: CS:  0010 DS: 0000 ES: 0000 CR0:
0000000080050033
Nov  2 17:49:39 localhost kernel: CR2: 00007f8697eddfb8 CR3:
00000000716b6005 CR4: 00000000001706f0
Nov  2 17:49:39 localhost kernel: Call Trace:
Nov  2 17:49:39 localhost kernel: ib_umem_get+0x343/0x3b0 [ib_uverbs]
Nov  2 17:49:39 localhost kernel: rxe_mem_init_user+0x4a/0x1e0 [rdma_rxe]
Nov  2 17:49:39 localhost kernel: rxe_reg_user_mr+0x8e/0x150 [rdma_rxe]
Nov  2 17:49:39 localhost kernel: ib_uverbs_reg_mr+0x156/0x280 [ib_uverbs]
Nov  2 17:49:39 localhost kernel:
ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xcc/0x130 [ib_uverbs]
Nov  2 17:49:39 localhost kernel: ? __check_object_size+0x46/0x180
Nov  2 17:49:39 localhost kernel: ib_uverbs_run_method+0x6f6/0x7a0 [ib_uverbs]
Nov  2 17:49:39 localhost kernel: ?
ib_uverbs_handler_UVERBS_METHOD_QUERY_CONTEXT+0xd0/0xd0 [ib_uverbs]
Nov  2 17:49:39 localhost kernel: ? alloc_commit_idr_uobject+0x21/0x30
[ib_uverbs]
Nov  2 17:49:39 localhost kernel: ib_uverbs_cmd_verbs+0x195/0x360 [ib_uverbs]
Nov  2 17:49:39 localhost kernel: ib_uverbs_ioctl+0xa7/0x110 [ib_uverbs]
Nov  2 17:49:39 localhost kernel: __x64_sys_ioctl+0x84/0xc0
Nov  2 17:49:39 localhost kernel: do_syscall_64+0x33/0x40
Nov  2 17:49:39 localhost kernel: entry_SYSCALL_64_after_hwframe+0x44/0xa9
Nov  2 17:49:39 localhost kernel: RIP: 0033:0x7f8699d1087b
Nov  2 17:49:39 localhost kernel: Code: 0f 1e fa 48 8b 05 0d 96 2c 00
64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f
1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d dd 95
2c 00 f7 d8 64 89 01 48
Nov  2 17:49:39 localhost kernel: RSP: 002b:00007ffd271e0578 EFLAGS:
00000246 ORIG_RAX: 0000000000000010
Nov  2 17:49:39 localhost kernel: RAX: ffffffffffffffda RBX:
00007ffd271e05d0 RCX: 00007f8699d1087b
Nov  2 17:49:39 localhost kernel: RDX: 00007ffd271e05f0 RSI:
00000000c0181b01 RDI: 0000000000000004
Nov  2 17:49:39 localhost kernel: RBP: 00007ffd271e0608 R08:
0000000000000028 R09: 00007ffd271e0784
Nov  2 17:49:40 localhost kernel: R10: 00000000ffffffff R11:
0000000000000246 R12: 00007f8690005110
Nov  2 17:49:40 localhost kernel: R13: 00007ffd271e05d0 R14:
00007ffd271e0798 R15: 0000000000000001
Nov  2 17:49:40 localhost kernel: CPU: 0 PID: 2613 Comm: rping
Tainted: G        W         5.10.0-rc2+ #21
Nov  2 17:49:40 localhost kernel: Hardware name: VMware, Inc. VMware
Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00
02/27/2020
Nov  2 17:49:40 localhost kernel: Call Trace:
Nov  2 17:49:40 localhost kernel: dump_stack+0x57/0x6a
Nov  2 17:49:40 localhost kernel: __warn.cold.14+0xe/0x3d
Nov  2 17:49:40 localhost kernel: ? dma_map_sg_attrs+0x37/0x50
Nov  2 17:49:40 localhost kernel: report_bug+0xbd/0xf0
Nov  2 17:49:40 localhost kernel: handle_bug+0x44/0x80
Nov  2 17:49:40 localhost kernel: exc_invalid_op+0x13/0x60
Nov  2 17:49:40 localhost kernel: asm_exc_invalid_op+0x12/0x20
Nov  2 17:49:40 localhost kernel: RIP: 0010:dma_map_sg_attrs+0x37/0x50
Nov  2 17:49:40 localhost kernel: Code: 85 c0 48 0f 44 05 a9 22 e5 01
83 f9 02 77 19 48 83 bf 48 02 00 00 00 74 11 48 85 c0 75 11 e8 20 19
00 00 85 c0 78 13 c3 0f 0b <0f> 0b 31 c0 c3 48 8b 40 50 e8 7b 50 ab 00
eb e9 0f 0b 0f 1f 80 00
Nov  2 17:49:40 localhost kernel: RSP: 0018:ffffa8958297ba30 EFLAGS: 00010246
Nov  2 17:49:40 localhost kernel: RAX: ffffffff8fc23260 RBX:
000055af0b7aa000 RCX: 0000000000000000
Nov  2 17:49:40 localhost kernel: RDX: 0000000000000001 RSI:
ffff90719c4290c0 RDI: ffff9071a5b3c4e8
Nov  2 17:49:40 localhost kernel: RBP: 0000000000000000 R08:
0000000000000000 R09: 0000000000000000
Nov  2 17:49:40 localhost kernel: R10: ffffe64f807e35c0 R11:
0000000000000000 R12: ffff9071a5b3c000
Nov  2 17:49:40 localhost kernel: R13: 0000000000000000 R14:
ffff9071f14c1000 R15: ffff907199f82d00
Nov  2 17:49:40 localhost kernel: ib_umem_get+0x343/0x3b0 [ib_uverbs]
Nov  2 17:49:40 localhost kernel: rxe_mem_init_user+0x4a/0x1e0 [rdma_rxe]
Nov  2 17:49:40 localhost kernel: rxe_reg_user_mr+0x8e/0x150 [rdma_rxe]
Nov  2 17:49:40 localhost kernel: ib_uverbs_reg_mr+0x156/0x280 [ib_uverbs]
Nov  2 17:49:40 localhost kernel:
ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xcc/0x130 [ib_uverbs]
Nov  2 17:49:40 localhost kernel: ? __check_object_size+0x46/0x180
Nov  2 17:49:40 localhost kernel: ib_uverbs_run_method+0x6f6/0x7a0 [ib_uverbs]
Nov  2 17:49:40 localhost kernel: ?
ib_uverbs_handler_UVERBS_METHOD_QUERY_CONTEXT+0xd0/0xd0 [ib_uverbs]
Nov  2 17:49:40 localhost kernel: ? alloc_commit_idr_uobject+0x21/0x30
[ib_uverbs]
Nov  2 17:49:40 localhost kernel: ib_uverbs_cmd_verbs+0x195/0x360 [ib_uverbs]
Nov  2 17:49:40 localhost kernel: ib_uverbs_ioctl+0xa7/0x110 [ib_uverbs]
Nov  2 17:49:40 localhost kernel: __x64_sys_ioctl+0x84/0xc0
Nov  2 17:49:40 localhost kernel: do_syscall_64+0x33/0x40
Nov  2 17:49:40 localhost kernel: entry_SYSCALL_64_after_hwframe+0x44/0xa9
Nov  2 17:49:40 localhost kernel: RIP: 0033:0x7f8699d1087b
Nov  2 17:49:40 localhost kernel: Code: 0f 1e fa 48 8b 05 0d 96 2c 00
64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f
1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d dd 95
2c 00 f7 d8 64 89 01 48
Nov  2 17:49:40 localhost kernel: RSP: 002b:00007ffd271e0578 EFLAGS:
00000246 ORIG_RAX: 0000000000000010
Nov  2 17:49:40 localhost kernel: RAX: ffffffffffffffda RBX:
00007ffd271e05d0 RCX: 00007f8699d1087b
Nov  2 17:49:40 localhost kernel: RDX: 00007ffd271e05f0 RSI:
00000000c0181b01 RDI: 0000000000000004
Nov  2 17:49:40 localhost kernel: RBP: 00007ffd271e0608 R08:
0000000000000028 R09: 00007ffd271e0784
Nov  2 17:49:40 localhost kernel: R10: 00000000ffffffff R11:
0000000000000246 R12: 00007f8690005110
Nov  2 17:49:40 localhost kernel: R13: 00007ffd271e05d0 R14:
00007ffd271e0798 R15: 0000000000000001
Nov  2 17:49:40 localhost kernel: ---[ end trace 62d4cee803ba06f3 ]---
Nov  2 17:49:40 localhost kernel: rdma_rxe: err -12 from rxe_umem_get

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: Oops problem with rxe from 5.10-rc kernel
  2020-11-02 23:00 Oops problem with rxe from 5.10-rc kernel Olga Kornievskaia
@ 2020-11-03  0:26 ` Jason Gunthorpe
  2020-11-03 16:37   ` Pearson, Robert B
  2020-11-03 16:35 ` Pearson, Robert B
  1 sibling, 1 reply; 4+ messages in thread
From: Jason Gunthorpe @ 2020-11-03  0:26 UTC (permalink / raw)
  To: Olga Kornievskaia; +Cc: linux-rdma

On Mon, Nov 02, 2020 at 06:00:02PM -0500, Olga Kornievskaia wrote:
> Hi folks,
> 
> Is this a known problem? I'm unable to do simple rping over Soft RoCE
> starting from 5.10-rc1 kernel (5.9 works).This is an oops from running
> the following. I'm also unable to do NFS-over-RDMA.

Yes, it should be fixed in rc3

Jason

^ permalink raw reply	[flat|nested] 4+ messages in thread

* RE: Oops problem with rxe from 5.10-rc kernel
  2020-11-02 23:00 Oops problem with rxe from 5.10-rc kernel Olga Kornievskaia
  2020-11-03  0:26 ` Jason Gunthorpe
@ 2020-11-03 16:35 ` Pearson, Robert B
  1 sibling, 0 replies; 4+ messages in thread
From: Pearson, Robert B @ 2020-11-03 16:35 UTC (permalink / raw)
  To: Olga Kornievskaia, linux-rdma; +Cc: jgg@nvidia.com

> -----Original Message-----
> From: Olga Kornievskaia <aglo@umich.edu> 
> Sent: Monday, November 2, 2020 5:00 PM
> To: linux-rdma <linux-rdma@vger.kernel.org>
> Cc: Olga Kornievskaia <aglo@umich.edu>
> Subject: Oops problem with rxe from 5.10-rc kernel
>
> Hi folks,
>
> Is this a known problem? I'm unable to do simple rping over Soft RoCE starting from 5.10-rc1 kernel (5.9 works).
> This is an oops from running the following. I'm also > unable to do NFS-over-RDMA.
>
> sudo rping -c -a 192.168.1.105 -v -C 3
> recv_buf reg_mr failed
> rping_setup_buffers failed: 22

Unfortunately rxe got left in a broken state in 5.10.0-rc1. 
You can patch it or wait until rc2. Feel free to email me for the details.

Bob Pearson
rpearson@hpe.com

^ permalink raw reply	[flat|nested] 4+ messages in thread

* RE: Oops problem with rxe from 5.10-rc kernel
  2020-11-03  0:26 ` Jason Gunthorpe
@ 2020-11-03 16:37   ` Pearson, Robert B
  0 siblings, 0 replies; 4+ messages in thread
From: Pearson, Robert B @ 2020-11-03 16:37 UTC (permalink / raw)
  To: Jason Gunthorpe, Olga Kornievskaia; +Cc: linux-rdma



-----Original Message-----
From: Jason Gunthorpe <jgg@ziepe.ca> 
Sent: Monday, November 2, 2020 6:26 PM
To: Olga Kornievskaia <aglo@umich.edu>
Cc: linux-rdma <linux-rdma@vger.kernel.org>
Subject: Re: Oops problem with rxe from 5.10-rc kernel

On Mon, Nov 02, 2020 at 06:00:02PM -0500, Olga Kornievskaia wrote:
> Hi folks,
> 
> Is this a known problem? I'm unable to do simple rping over Soft RoCE 
> starting from 5.10-rc1 kernel (5.9 works).This is an oops from running 
> the following. I'm also unable to do NFS-over-RDMA.

Yes, it should be fixed in rc3

Jason

Jason knows better than I. so its rc3.

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2020-11-03 16:37 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2020-11-02 23:00 Oops problem with rxe from 5.10-rc kernel Olga Kornievskaia
2020-11-03  0:26 ` Jason Gunthorpe
2020-11-03 16:37   ` Pearson, Robert B
2020-11-03 16:35 ` Pearson, Robert B

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox