mlx4 problems with 4.2-rc8
I'm seeing this with rc8 on a dual port mlx4 adapter set to IB/Eth mode:
[ 77.883513] IPv6: ADDRCONF(NETDEV_UP): mlx4_roce: link is not ready [ 77.892044] mlx4_en: mlx4_roce: frag:0 - size:1518 prefix:0 stride:1536 [ 77.903129] genirq: Flags mismatch irq 135. 00000000 (mlx4-65@0000:05:00.0) vs. 00000000 (mlx4-65@0000:05:00.0) [ 77.914965] CPU: 0 PID: 1541 Comm: NetworkManager Not tainted 4.2.0-rc8 #58 [ 77.923292] Hardware name: Dell Inc. PowerEdge R820/04K5X5, BIOS 2.2.3 07/09/2014 [ 77.932205] 0000000000000000 00000000c16e3ce1 ffff8820365ab498 ffffffff8167e6ff [ 77.941072] 0000000000000000 ffff8820339e9a00 ffff8820365ab4f8 ffffffff810d2b6e [ 77.949938] 0000000000000246 ffff881032e67aa4 ffff881035e10ba0 00000000c16e3ce1 [ 77.958812] Call Trace: [ 77.962109] [<ffffffff8167e6ff>] dump_stack+0x45/0x57 [ 77.968412] [<ffffffff810d2b6e>] __setup_irq+0x51e/0x590 [ 77.975018] [<ffffffffc03870a0>] ? mlx4_interrupt+0x80/0x80 [mlx4_core] [ 77.983072] [<ffffffff810d2d64>] request_threaded_irq+0xf4/0x1a0 [ 77.990468] [<ffffffffc0385d55>] mlx4_assign_eq+0x135/0x360 [mlx4_core] [ 77.998513] [<ffffffffc0537537>] mlx4_en_activate_cq+0x2a7/0x310 [mlx4_en] [ 78.006853] [<ffffffff8130a2c8>] ? alloc_cpumask_var_node+0x28/0x40 [ 78.014542] [<ffffffff8131e8b9>] ? find_next_bit+0x19/0x20 [ 78.021334] [<ffffffff8130a284>] ? cpumask_next_and+0x34/0x50 [ 78.028425] [<ffffffffc053ae6b>] mlx4_en_start_port+0x1bb/0xb60 [mlx4_en] [ 78.036689] [<ffffffffc037fe01>] ? mlx4_free_cmd_mailbox+0x31/0x40 [mlx4_core] [ 78.045435] [<ffffffffc053bb59>] mlx4_en_open+0x349/0x630 [mlx4_en] [ 78.053107] [<ffffffff815732f9>] __dev_open+0xc9/0x140 [ 78.059538] [<ffffffff81573621>] __dev_change_flags+0xa1/0x160 [ 78.066718] [<ffffffff81573709>] dev_change_flags+0x29/0x60 [ 78.073602] [<ffffffff81580dbe>] do_setlink+0x5be/0xa70 [ 78.080097] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.087859] [<ffffffffc01b1456>] ? mga_dirty_update+0x1e6/0x2f0 [mgag200] [ 78.096112] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.103873] [<ffffffff81582470>] rtnl_newlink+0x4f0/0x880 [ 78.110586] [<ffffffff81582073>] ? rtnl_newlink+0xf3/0x880 [ 78.117372] [<ffffffff81294238>] ? security_capable+0x48/0x60 [ 78.124452] [<ffffffff81081b1d>] ? ns_capable+0x2d/0x60 [ 78.130950] [<ffffffff8157f8c4>] rtnetlink_rcv_msg+0xa4/0x250 [ 78.138028] [<ffffffff812987c0>] ? sock_has_perm+0x70/0x90 [ 78.144824] [<ffffffff8157f820>] ? rtnetlink_rcv+0x40/0x40 [ 78.151615] [<ffffffff815a2bdf>] netlink_rcv_skb+0xaf/0xc0 [ 78.158425] [<ffffffff8157f80c>] rtnetlink_rcv+0x2c/0x40 [ 78.164997] [<ffffffff815a22d1>] netlink_unicast+0x101/0x1f0 [ 78.171937] [<ffffffff815a27c1>] netlink_sendmsg+0x401/0x660 [ 78.178867] [<ffffffff81553e78>] sock_sendmsg+0x38/0x50 [ 78.185335] [<ffffffff815547d5>] ___sys_sendmsg+0x275/0x290 [ 78.192176] [<ffffffff81262c56>] ? sysctl_head_finish+0x46/0x50 [ 78.199411] [<ffffffff81262e08>] ? proc_sys_call_handler+0x88/0xe0 [ 78.206946] [<ffffffff8131854c>] ? lockref_put_or_lock+0x4c/0x80 [ 78.214296] [<ffffffff81555197>] __sys_sendmsg+0x57/0xa0 [ 78.220878] [<ffffffff815551f2>] SyS_sendmsg+0x12/0x20 [ 78.227283] [<ffffffff8168536e>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 78.235114] mlx4_en 0000:05:00.0: Failed assigning an EQ to \xfffffff\xffffffb6Z6 \xffffff88\xffffffff\xffffffff\xffffff84\xffffffa20\xffffff81\xffffffff\xffffffff\xffffffff\xffffffff [ 78.243732] mlx4_en: mlx4_roce: Failed activating Rx CQ [ 78.319027] mlx4_en: mlx4_roce: Failed starting port:2
The interface in question is unusable.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 1 line · Doug Ledford
I'm seeing this with rc8 on a dual port mlx4 adapter set to IB/Eth mode:
mmm, both Amir and myself are just finishing vacations... so WB notes are not always lovely as you want them to be, life
Quoted 5 lines
[ 77.883513] IPv6: ADDRCONF(NETDEV_UP): mlx4_roce: link is not ready [ 77.892044] mlx4_en: mlx4_roce: frag:0 - size:1518 prefix:0 stride:1536 [ 77.903129] genirq: Flags mismatch irq 135. 00000000(mlx4-65@0000:05:00.0) vs. 00000000 (mlx4-65@0000:05:00.0)
is this strict regression from some known point in the past on this system/config -- i.e 4.1 or 4.2-rc1?!
Can you please send the mlx4 driver output when you load it with debug prints on? also do things work if you set the ports type to be ib/ib or eth/eth?
send us your compressed .config
Matan, any idea what goes wrong here?
Or.
Quoted 59 lines
[ 77.914965] CPU: 0 PID: 1541 Comm: NetworkManager Not tainted 4.2.0-rc8 #58 [ 77.923292] Hardware name: Dell Inc. PowerEdge R820/04K5X5, BIOS 2.2.3 07/09/2014 [ 77.932205] 0000000000000000 00000000c16e3ce1 ffff8820365ab498 ffffffff8167e6ff [ 77.941072] 0000000000000000 ffff8820339e9a00 ffff8820365ab4f8 ffffffff810d2b6e [ 77.949938] 0000000000000246 ffff881032e67aa4 ffff881035e10ba0 00000000c16e3ce1 [ 77.958812] Call Trace: [ 77.962109] [<ffffffff8167e6ff>] dump_stack+0x45/0x57 [ 77.968412] [<ffffffff810d2b6e>] __setup_irq+0x51e/0x590 [ 77.975018] [<ffffffffc03870a0>] ? mlx4_interrupt+0x80/0x80 [mlx4_core] [ 77.983072] [<ffffffff810d2d64>] request_threaded_irq+0xf4/0x1a0 [ 77.990468] [<ffffffffc0385d55>] mlx4_assign_eq+0x135/0x360 [mlx4_core] [ 77.998513] [<ffffffffc0537537>] mlx4_en_activate_cq+0x2a7/0x310 [mlx4_en] [ 78.006853] [<ffffffff8130a2c8>] ? alloc_cpumask_var_node+0x28/0x40 [ 78.014542] [<ffffffff8131e8b9>] ? find_next_bit+0x19/0x20 [ 78.021334] [<ffffffff8130a284>] ? cpumask_next_and+0x34/0x50 [ 78.028425] [<ffffffffc053ae6b>] mlx4_en_start_port+0x1bb/0xb60 [mlx4_en] [ 78.036689] [<ffffffffc037fe01>] ? mlx4_free_cmd_mailbox+0x31/0x40 [mlx4_core] [ 78.045435] [<ffffffffc053bb59>] mlx4_en_open+0x349/0x630 [mlx4_en] [ 78.053107] [<ffffffff815732f9>] __dev_open+0xc9/0x140 [ 78.059538] [<ffffffff81573621>] __dev_change_flags+0xa1/0x160 [ 78.066718] [<ffffffff81573709>] dev_change_flags+0x29/0x60 [ 78.073602] [<ffffffff81580dbe>] do_setlink+0x5be/0xa70 [ 78.080097] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.087859] [<ffffffffc01b1456>] ? mga_dirty_update+0x1e6/0x2f0 [mgag200] [ 78.096112] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.103873] [<ffffffff81582470>] rtnl_newlink+0x4f0/0x880 [ 78.110586] [<ffffffff81582073>] ? rtnl_newlink+0xf3/0x880 [ 78.117372] [<ffffffff81294238>] ? security_capable+0x48/0x60 [ 78.124452] [<ffffffff81081b1d>] ? ns_capable+0x2d/0x60 [ 78.130950] [<ffffffff8157f8c4>] rtnetlink_rcv_msg+0xa4/0x250 [ 78.138028] [<ffffffff812987c0>] ? sock_has_perm+0x70/0x90 [ 78.144824] [<ffffffff8157f820>] ? rtnetlink_rcv+0x40/0x40 [ 78.151615] [<ffffffff815a2bdf>] netlink_rcv_skb+0xaf/0xc0 [ 78.158425] [<ffffffff8157f80c>] rtnetlink_rcv+0x2c/0x40 [ 78.164997] [<ffffffff815a22d1>] netlink_unicast+0x101/0x1f0 [ 78.171937] [<ffffffff815a27c1>] netlink_sendmsg+0x401/0x660 [ 78.178867] [<ffffffff81553e78>] sock_sendmsg+0x38/0x50 [ 78.185335] [<ffffffff815547d5>] ___sys_sendmsg+0x275/0x290 [ 78.192176] [<ffffffff81262c56>] ? sysctl_head_finish+0x46/0x50 [ 78.199411] [<ffffffff81262e08>] ? proc_sys_call_handler+0x88/0xe0 [ 78.206946] [<ffffffff8131854c>] ? lockref_put_or_lock+0x4c/0x80 [ 78.214296] [<ffffffff81555197>] __sys_sendmsg+0x57/0xa0 [ 78.220878] [<ffffffff815551f2>] SyS_sendmsg+0x12/0x20 [ 78.227283] [<ffffffff8168536e>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 78.235114] mlx4_en 0000:05:00.0: Failed assigning an EQ to \xfffffff\xffffffb6Z6 \xffffff88\xffffffff\xffffffff\xffffff84\xffffffa20\xffffff81\xffffffff\xffffffff\xffffffff\xffffffff [ 78.243732] mlx4_en: mlx4_roce: Failed activating Rx CQ [ 78.319027] mlx4_en: mlx4_roce: Failed starting port:2
Quoted 7 lines
The interface in question is unusable.
--
Doug Ledford <[email protected]>GPG KeyID: 0E572FDD
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): CAJ3xEMj5By11L3qbSKxcEiMarB6CeyeERMnuK_vvH11VLLFypw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org
Quoted 6 lines · Or Gerlitz
Quoted 1 line · Doug Ledford
I'm seeing this with rc8 on a dual port mlx4 adapter set to IB/Eth mode:
mmm, both Amir and myself are just finishing vacations... so WB notes are not always lovely as you want them to be, life
Quoted 1 line
Quoted 7 lines
Quoted 4 lines
[ 77.883513] IPv6: ADDRCONF(NETDEV_UP): mlx4_roce: link is not ready [ 77.892044] mlx4_en: mlx4_roce: frag:0 - size:1518 prefix:0 stride:1536 [ 77.903129] genirq: Flags mismatch irq 135. 00000000(mlx4-65@0000:05:00.0) vs. 00000000 (mlx4-65@0000:05:00.0)
is this strict regression from some known point in the past on this system/config -- i.e 4.1 or 4.2-rc1?!
Yes. When I was submitting the 4.2-rc changes this machine worked. This is one of my IB/Eth SRIOV machines. I tested with SRIOV disabled and it didn't effect things.
Quoted 3 lines
Can you please send the mlx4 driver output when you load it with debug prints on? also do things work if you set the ports type to be ib/ib or eth/eth?
It should work as ib/ib given that in ib/eth mode the ib port works. I doubt eth/eth would work, but I'll try and see. OK, Eth/Eth mode fails too (at least on the second port, I can say on the first port for certain as I can't bring it up, it's still plugged into an IB switch). However, now in Eth/Eth mode, attempts to bring up the interface manually at the command line have hung, which it didn't do in IB/Eth mode.
I'll try to ping things down further, but that's what I have so far.
And as requested, the config is attached.
Quoted 75 lines
send us your compressed .config
Matan, any idea what goes wrong here?
Or.
Quoted 66 lines
[ 77.914965] CPU: 0 PID: 1541 Comm: NetworkManager Not tainted 4.2.0-rc8 #58 [ 77.923292] Hardware name: Dell Inc. PowerEdge R820/04K5X5, BIOS 2.2.3 07/09/2014 [ 77.932205] 0000000000000000 00000000c16e3ce1 ffff8820365ab498 ffffffff8167e6ff [ 77.941072] 0000000000000000 ffff8820339e9a00 ffff8820365ab4f8 ffffffff810d2b6e [ 77.949938] 0000000000000246 ffff881032e67aa4 ffff881035e10ba0 00000000c16e3ce1 [ 77.958812] Call Trace: [ 77.962109] [<ffffffff8167e6ff>] dump_stack+0x45/0x57 [ 77.968412] [<ffffffff810d2b6e>] __setup_irq+0x51e/0x590 [ 77.975018] [<ffffffffc03870a0>] ? mlx4_interrupt+0x80/0x80 [mlx4_core] [ 77.983072] [<ffffffff810d2d64>] request_threaded_irq+0xf4/0x1a0 [ 77.990468] [<ffffffffc0385d55>] mlx4_assign_eq+0x135/0x360 [mlx4_core] [ 77.998513] [<ffffffffc0537537>] mlx4_en_activate_cq+0x2a7/0x310 [mlx4_en] [ 78.006853] [<ffffffff8130a2c8>] ? alloc_cpumask_var_node+0x28/0x40 [ 78.014542] [<ffffffff8131e8b9>] ? find_next_bit+0x19/0x20 [ 78.021334] [<ffffffff8130a284>] ? cpumask_next_and+0x34/0x50 [ 78.028425] [<ffffffffc053ae6b>] mlx4_en_start_port+0x1bb/0xb60 [mlx4_en] [ 78.036689] [<ffffffffc037fe01>] ? mlx4_free_cmd_mailbox+0x31/0x40 [mlx4_core] [ 78.045435] [<ffffffffc053bb59>] mlx4_en_open+0x349/0x630 [mlx4_en] [ 78.053107] [<ffffffff815732f9>] __dev_open+0xc9/0x140 [ 78.059538] [<ffffffff81573621>] __dev_change_flags+0xa1/0x160 [ 78.066718] [<ffffffff81573709>] dev_change_flags+0x29/0x60 [ 78.073602] [<ffffffff81580dbe>] do_setlink+0x5be/0xa70 [ 78.080097] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.087859] [<ffffffffc01b1456>] ? mga_dirty_update+0x1e6/0x2f0 [mgag200] [ 78.096112] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.103873] [<ffffffff81582470>] rtnl_newlink+0x4f0/0x880 [ 78.110586] [<ffffffff81582073>] ? rtnl_newlink+0xf3/0x880 [ 78.117372] [<ffffffff81294238>] ? security_capable+0x48/0x60 [ 78.124452] [<ffffffff81081b1d>] ? ns_capable+0x2d/0x60 [ 78.130950] [<ffffffff8157f8c4>] rtnetlink_rcv_msg+0xa4/0x250 [ 78.138028] [<ffffffff812987c0>] ? sock_has_perm+0x70/0x90 [ 78.144824] [<ffffffff8157f820>] ? rtnetlink_rcv+0x40/0x40 [ 78.151615] [<ffffffff815a2bdf>] netlink_rcv_skb+0xaf/0xc0 [ 78.158425] [<ffffffff8157f80c>] rtnetlink_rcv+0x2c/0x40 [ 78.164997] [<ffffffff815a22d1>] netlink_unicast+0x101/0x1f0 [ 78.171937] [<ffffffff815a27c1>] netlink_sendmsg+0x401/0x660 [ 78.178867] [<ffffffff81553e78>] sock_sendmsg+0x38/0x50 [ 78.185335] [<ffffffff815547d5>] ___sys_sendmsg+0x275/0x290 [ 78.192176] [<ffffffff81262c56>] ? sysctl_head_finish+0x46/0x50 [ 78.199411] [<ffffffff81262e08>] ? proc_sys_call_handler+0x88/0xe0 [ 78.206946] [<ffffffff8131854c>] ? lockref_put_or_lock+0x4c/0x80 [ 78.214296] [<ffffffff81555197>] __sys_sendmsg+0x57/0xa0 [ 78.220878] [<ffffffff815551f2>] SyS_sendmsg+0x12/0x20 [ 78.227283] [<ffffffff8168536e>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 78.235114] mlx4_en 0000:05:00.0: Failed assigning an EQ to \xfffffff\xffffffb6Z6 \xffffff88\xffffffff\xffffffff\xffffff84\xffffffa20\xffffff81\xffffffff\xffffffff\xffffffff\xffffffff [ 78.243732] mlx4_en: mlx4_roce: Failed activating Rx CQ [ 78.319027] mlx4_en: mlx4_roce: Failed starting port:2The interface in question is unusable.
--
Doug Ledford <[email protected]>GPG KeyID: 0E572FDD
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 30 lines · Doug Ledford
Quoted 6 lines · Or Gerlitz
Quoted 1 line · Doug Ledford
I'm seeing this with rc8 on a dual port mlx4 adapter set to IB/Eth mode:
mmm, both Amir and myself are just finishing vacations... so WB notes are not always lovely as you want them to be, life
Quoted 1 line
Quoted 7 lines
Quoted 4 lines
[ 77.883513] IPv6: ADDRCONF(NETDEV_UP): mlx4_roce: link is not ready [ 77.892044] mlx4_en: mlx4_roce: frag:0 - size:1518 prefix:0 stride:1536 [ 77.903129] genirq: Flags mismatch irq 135. 00000000(mlx4-65@0000:05:00.0) vs. 00000000 (mlx4-65@0000:05:00.0)
is this strict regression from some known point in the past on this system/config -- i.e 4.1 or 4.2-rc1?!
Yes. When I was submitting the 4.2-rc changes this machine worked. This is one of my IB/Eth SRIOV machines. I tested with SRIOV disabled and it didn't effect things.
Quoted 3 lines
Can you please send the mlx4 driver output when you load it with debug prints on? also do things work if you set the ports type to be ib/ib or eth/eth?
It should work as ib/ib given that in ib/eth mode the ib port works. I doubt eth/eth would work, but I'll try and see. OK, Eth/Eth mode fails too (at least on the second port, I can say on the first port for certain as I can't bring it up, it's still plugged into an IB switch). However, now in Eth/Eth mode, attempts to bring up the interface manually at the command line have hung, which it didn't do in IB/Eth mode.
Quoted 81 lines
I'll try to ping things down further, but that's what I have so far.
And as requested, the config is attached.
Quoted 75 lines
send us your compressed .config
Matan, any idea what goes wrong here?
Or.
Quoted 66 lines
[ 77.914965] CPU: 0 PID: 1541 Comm: NetworkManager Not tainted 4.2.0-rc8 #58 [ 77.923292] Hardware name: Dell Inc. PowerEdge R820/04K5X5, BIOS 2.2.3 07/09/2014 [ 77.932205] 0000000000000000 00000000c16e3ce1 ffff8820365ab498 ffffffff8167e6ff [ 77.941072] 0000000000000000 ffff8820339e9a00 ffff8820365ab4f8 ffffffff810d2b6e [ 77.949938] 0000000000000246 ffff881032e67aa4 ffff881035e10ba0 00000000c16e3ce1 [ 77.958812] Call Trace: [ 77.962109] [<ffffffff8167e6ff>] dump_stack+0x45/0x57 [ 77.968412] [<ffffffff810d2b6e>] __setup_irq+0x51e/0x590 [ 77.975018] [<ffffffffc03870a0>] ? mlx4_interrupt+0x80/0x80 [mlx4_core] [ 77.983072] [<ffffffff810d2d64>] request_threaded_irq+0xf4/0x1a0 [ 77.990468] [<ffffffffc0385d55>] mlx4_assign_eq+0x135/0x360 [mlx4_core] [ 77.998513] [<ffffffffc0537537>] mlx4_en_activate_cq+0x2a7/0x310 [mlx4_en] [ 78.006853] [<ffffffff8130a2c8>] ? alloc_cpumask_var_node+0x28/0x40 [ 78.014542] [<ffffffff8131e8b9>] ? find_next_bit+0x19/0x20 [ 78.021334] [<ffffffff8130a284>] ? cpumask_next_and+0x34/0x50 [ 78.028425] [<ffffffffc053ae6b>] mlx4_en_start_port+0x1bb/0xb60 [mlx4_en] [ 78.036689] [<ffffffffc037fe01>] ? mlx4_free_cmd_mailbox+0x31/0x40 [mlx4_core] [ 78.045435] [<ffffffffc053bb59>] mlx4_en_open+0x349/0x630 [mlx4_en] [ 78.053107] [<ffffffff815732f9>] __dev_open+0xc9/0x140 [ 78.059538] [<ffffffff81573621>] __dev_change_flags+0xa1/0x160 [ 78.066718] [<ffffffff81573709>] dev_change_flags+0x29/0x60 [ 78.073602] [<ffffffff81580dbe>] do_setlink+0x5be/0xa70 [ 78.080097] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.087859] [<ffffffffc01b1456>] ? mga_dirty_update+0x1e6/0x2f0 [mgag200] [ 78.096112] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.103873] [<ffffffff81582470>] rtnl_newlink+0x4f0/0x880 [ 78.110586] [<ffffffff81582073>] ? rtnl_newlink+0xf3/0x880 [ 78.117372] [<ffffffff81294238>] ? security_capable+0x48/0x60 [ 78.124452] [<ffffffff81081b1d>] ? ns_capable+0x2d/0x60 [ 78.130950] [<ffffffff8157f8c4>] rtnetlink_rcv_msg+0xa4/0x250 [ 78.138028] [<ffffffff812987c0>] ? sock_has_perm+0x70/0x90 [ 78.144824] [<ffffffff8157f820>] ? rtnetlink_rcv+0x40/0x40 [ 78.151615] [<ffffffff815a2bdf>] netlink_rcv_skb+0xaf/0xc0 [ 78.158425] [<ffffffff8157f80c>] rtnetlink_rcv+0x2c/0x40 [ 78.164997] [<ffffffff815a22d1>] netlink_unicast+0x101/0x1f0 [ 78.171937] [<ffffffff815a27c1>] netlink_sendmsg+0x401/0x660 [ 78.178867] [<ffffffff81553e78>] sock_sendmsg+0x38/0x50 [ 78.185335] [<ffffffff815547d5>] ___sys_sendmsg+0x275/0x290 [ 78.192176] [<ffffffff81262c56>] ? sysctl_head_finish+0x46/0x50 [ 78.199411] [<ffffffff81262e08>] ? proc_sys_call_handler+0x88/0xe0 [ 78.206946] [<ffffffff8131854c>] ? lockref_put_or_lock+0x4c/0x80 [ 78.214296] [<ffffffff81555197>] __sys_sendmsg+0x57/0xa0 [ 78.220878] [<ffffffff815551f2>] SyS_sendmsg+0x12/0x20 [ 78.227283] [<ffffffff8168536e>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 78.235114] mlx4_en 0000:05:00.0: Failed assigning an EQ to \xfffffff\xffffffb6Z6 \xffffff88\xffffffff\xffffffff\xffffff84\xffffffa20\xffffff81\xffffffff\xffffffff\xffffffff\xffffffff [ 78.243732] mlx4_en: mlx4_roce: Failed activating Rx CQ [ 78.319027] mlx4_en: mlx4_roce: Failed starting port:2The interface in question is unusable.
--
Doug Ledford <[email protected]>GPG KeyID: 0E572FDD
Actually, it looks like the dump stack we've got before [1] was fixed. This happens when the mlx4 driver is used in setups where number of cores >= 32. Doug, is that the case?
[1] http://www.spinics.net/lists/netdev/msg341171.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): 55E3FDAB.10706-VPRAkNaXOzVWk0Htik3J/[email protected]
Quoted 125 lines · Matan Barak
Quoted 34 lines · Doug Ledford
Quoted 8 lines · Or Gerlitz
Quoted 2 lines · Doug Ledford
I'm seeing this with rc8 on a dual port mlx4 adapter set to IB/Eth mode:
mmm, both Amir and myself are just finishing vacations... so WB notes are not always lovely as you want them to be, life
Quoted 1 line
Quoted 8 lines
Quoted 5 lines
[ 77.883513] IPv6: ADDRCONF(NETDEV_UP): mlx4_roce: link is not ready [ 77.892044] mlx4_en: mlx4_roce: frag:0 - size:1518 prefix:0 stride:1536 [ 77.903129] genirq: Flags mismatch irq 135. 00000000(mlx4-65@0000:05:00.0) vs. 00000000 (mlx4-65@0000:05:00.0)
is this strict regression from some known point in the past on this system/config -- i.e 4.1 or 4.2-rc1?!
Yes. When I was submitting the 4.2-rc changes this machine worked. This is one of my IB/Eth SRIOV machines. I tested with SRIOV disabled and it didn't effect things.
Quoted 3 lines
Can you please send the mlx4 driver output when you load it with debug prints on? also do things work if you set the ports type to be ib/ib or eth/eth?
It should work as ib/ib given that in ib/eth mode the ib port works. I doubt eth/eth would work, but I'll try and see. OK, Eth/Eth mode fails too (at least on the second port, I can say on the first port for certain as I can't bring it up, it's still plugged into an IB switch). However, now in Eth/Eth mode, attempts to bring up the interface manually at the command line have hung, which it didn't do in IB/Eth mode.
Quoted 87 lines
I'll try to ping things down further, but that's what I have so far.
And as requested, the config is attached.
Quoted 81 lines
send us your compressed .config
Matan, any idea what goes wrong here?
Or.
Quoted 72 lines
[ 77.914965] CPU: 0 PID: 1541 Comm: NetworkManager Not tainted 4.2.0-rc8 #58 [ 77.923292] Hardware name: Dell Inc. PowerEdge R820/04K5X5, BIOS 2.2.3 07/09/2014 [ 77.932205] 0000000000000000 00000000c16e3ce1 ffff8820365ab498 ffffffff8167e6ff [ 77.941072] 0000000000000000 ffff8820339e9a00 ffff8820365ab4f8 ffffffff810d2b6e [ 77.949938] 0000000000000246 ffff881032e67aa4 ffff881035e10ba0 00000000c16e3ce1 [ 77.958812] Call Trace: [ 77.962109] [<ffffffff8167e6ff>] dump_stack+0x45/0x57 [ 77.968412] [<ffffffff810d2b6e>] __setup_irq+0x51e/0x590 [ 77.975018] [<ffffffffc03870a0>] ? mlx4_interrupt+0x80/0x80 [mlx4_core] [ 77.983072] [<ffffffff810d2d64>] request_threaded_irq+0xf4/0x1a0 [ 77.990468] [<ffffffffc0385d55>] mlx4_assign_eq+0x135/0x360 [mlx4_core] [ 77.998513] [<ffffffffc0537537>] mlx4_en_activate_cq+0x2a7/0x310 [mlx4_en] [ 78.006853] [<ffffffff8130a2c8>] ? alloc_cpumask_var_node+0x28/0x40 [ 78.014542] [<ffffffff8131e8b9>] ? find_next_bit+0x19/0x20 [ 78.021334] [<ffffffff8130a284>] ? cpumask_next_and+0x34/0x50 [ 78.028425] [<ffffffffc053ae6b>] mlx4_en_start_port+0x1bb/0xb60 [mlx4_en] [ 78.036689] [<ffffffffc037fe01>] ? mlx4_free_cmd_mailbox+0x31/0x40 [mlx4_core] [ 78.045435] [<ffffffffc053bb59>] mlx4_en_open+0x349/0x630 [mlx4_en] [ 78.053107] [<ffffffff815732f9>] __dev_open+0xc9/0x140 [ 78.059538] [<ffffffff81573621>] __dev_change_flags+0xa1/0x160 [ 78.066718] [<ffffffff81573709>] dev_change_flags+0x29/0x60 [ 78.073602] [<ffffffff81580dbe>] do_setlink+0x5be/0xa70 [ 78.080097] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.087859] [<ffffffffc01b1456>] ? mga_dirty_update+0x1e6/0x2f0 [mgag200] [ 78.096112] [<ffffffffc01b158f>] ? mga_imageblit+0x2f/0x40 [mgag200] [ 78.103873] [<ffffffff81582470>] rtnl_newlink+0x4f0/0x880 [ 78.110586] [<ffffffff81582073>] ? rtnl_newlink+0xf3/0x880 [ 78.117372] [<ffffffff81294238>] ? security_capable+0x48/0x60 [ 78.124452] [<ffffffff81081b1d>] ? ns_capable+0x2d/0x60 [ 78.130950] [<ffffffff8157f8c4>] rtnetlink_rcv_msg+0xa4/0x250 [ 78.138028] [<ffffffff812987c0>] ? sock_has_perm+0x70/0x90 [ 78.144824] [<ffffffff8157f820>] ? rtnetlink_rcv+0x40/0x40 [ 78.151615] [<ffffffff815a2bdf>] netlink_rcv_skb+0xaf/0xc0 [ 78.158425] [<ffffffff8157f80c>] rtnetlink_rcv+0x2c/0x40 [ 78.164997] [<ffffffff815a22d1>] netlink_unicast+0x101/0x1f0 [ 78.171937] [<ffffffff815a27c1>] netlink_sendmsg+0x401/0x660 [ 78.178867] [<ffffffff81553e78>] sock_sendmsg+0x38/0x50 [ 78.185335] [<ffffffff815547d5>] ___sys_sendmsg+0x275/0x290 [ 78.192176] [<ffffffff81262c56>] ? sysctl_head_finish+0x46/0x50 [ 78.199411] [<ffffffff81262e08>] ? proc_sys_call_handler+0x88/0xe0 [ 78.206946] [<ffffffff8131854c>] ? lockref_put_or_lock+0x4c/0x80 [ 78.214296] [<ffffffff81555197>] __sys_sendmsg+0x57/0xa0 [ 78.220878] [<ffffffff815551f2>] SyS_sendmsg+0x12/0x20 [ 78.227283] [<ffffffff8168536e>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 78.235114] mlx4_en 0000:05:00.0: Failed assigning an EQ to\xfffffff\xffffffb6Z6 \xffffff88\xffffffff\xffffffff\xffffff84\xffffffa20\xffffff81\xffffffff\xffffffff\xffffffff\xffffffff
[ 78.243732] mlx4_en: mlx4_roce: Failed activating Rx CQ [ 78.319027] mlx4_en: mlx4_roce: Failed starting port:2The interface in question is unusable.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
Quoted 4 lines
Actually, it looks like the dump stack we've got before [1] was fixed. This happens when the mlx4 driver is used in setups where number of cores >= 32.
Doug, is that the case?
Indeed, 48 cores on this machine.
Quoted 1 line
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 9 lines · Doug Ledford
Quoted 5 lines · Matan Barak
Actually, it looks like the dump stack we've got before [1] was fixed. This happens when the mlx4 driver is used in setups where number of cores >= 32.
Doug, is that the case?
Indeed, 48 cores on this machine.
so do we have bingo here? the patch is in the net-next tree (and we can't put it in 4.2 only through -stable since 4.2 is released by now), does it solves the problem?
Or.
Quoted 1 line
Quoted 1 line
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): CAJ3xEMjp+3Y0y2d-K-zi9SnBSshN_C5x5KLY3oCpD_XriDCsWw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org
Quoted 7 lines · Or Gerlitz
Quoted 5 lines · Doug Ledford
Quoted 3 lines · Matan Barak
Actually, it looks like the dump stack we've got before [1] was fixed. This happens when the mlx4 driver is used in setups where number of cores >= 32.
Quoted 7 lines
Quoted 3 lines
Quoted 1 line
Doug, is that the case?
Indeed, 48 cores on this machine.
so do we have bingo here? the patch is in the net-next tree (and we can't put it in 4.2 only through -stable since 4.2 is released by now), does it solves the problem?
Yes, it solved the problem. I pulled the patch into my testing branch to confirm.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 10 lines · Doug Ledford
Quoted 9 lines · Or Gerlitz
Quoted 7 lines · Doug Ledford
Quoted 5 lines · Matan Barak
Actually, it looks like the dump stack we've got before [1] was fixed. This happens when the mlx4 driver is used in setups where number of cores >= 32.
Doug, is that the case?
Quoted 8 lines
Quoted 5 lines
Quoted 1 line
Indeed, 48 cores on this machine.
so do we have bingo here? the patch is in the net-next tree (and we can't put it in 4.2 only through -stable since 4.2 is released by now), does it solves the problem?
Yes, it solved the problem. I pulled the patch into my testing branch to confirm.
Good. Something is still strange w.r.t your environment... you said that when you were submitting the 4.2-rc changes this machine worked, however the problematic code in mlx4_enable_msi_x existed there by the time you made that testing, Matan - agree?
Or.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): CAJ3xEMh-EXsoWsMhSf2ho_U_tz5tCUz2iWK+YZ3d76j5B7HJxg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org
Quoted 20 lines · Or Gerlitz
Quoted 10 lines · Doug Ledford
Quoted 9 lines · Or Gerlitz
Quoted 7 lines · Doug Ledford
Quoted 5 lines · Matan Barak
Actually, it looks like the dump stack we've got before [1] was fixed. This happens when the mlx4 driver is used in setups where number of cores >= 32.
Doug, is that the case?
Quoted 8 lines
Quoted 5 lines
Quoted 1 line
Indeed, 48 cores on this machine.
so do we have bingo here? the patch is in the net-next tree (and we can't put it in 4.2 only through -stable since 4.2 is released by now), does it solves the problem?
Yes, it solved the problem. I pulled the patch into my testing branch to confirm.
Quoted 6 lines
Good. Something is still strange w.r.t your environment... you said that when you were submitting the 4.2-rc changes this machine worked, however the problematic code in
mlx4_enable_msi_xexisted there by the time you made that testing, Matan - agree?Or.
If I recall, this code was sent through linux-net mailing list. So it's possible the different branches weren't rebased, isn't it?
Quoted 4 lines
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): CAAKD3BCbZpzG3g+H3xkuBM+Y9G14DZ=tJXeaGe5_ccQpiqWmCQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org
Quoted 2 lines · Matan Barak
If I recall, this code was sent through linux-net mailing list. So it's possible the different branches weren't rebased, isn't it?
but the code was merged for 4.2-rc1 -- so Doug, this means that when you did the 4.2-rc work you haven't rebased to 4.2-rc1 -- if this is indeed the case,
such practice is problematic, agree?
Or.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): CAJ3xEMg1qoCrkMoymnbe_ww50Cg7yjOf4y3fTSb7ngoqbCZ1Hg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org
Quoted 9 lines · Or Gerlitz
Quoted 2 lines · Matan Barak
If I recall, this code was sent through linux-net mailing list. So it's possible the different branches weren't rebased, isn't it?
but the code was merged for 4.2-rc1 -- so Doug, this means that when you did the 4.2-rc work you haven't rebased to 4.2-rc1 -- if this is indeed the case,
such practice is problematic, agree?
That depends. Early on in the rc series, I don't rebase for testing. Later on in the rc series, I do. However, that's all moot because it isn't why I didn't see this in the 4.2 rc series. I only have one machine with > 32 CPUs, and it's intended to be a highly reliable/stable machine. I don't always use it for testing new kernels. In this particular case, I needed to move it from a RHEL kernel to an upstream kernel to isolate a different issue, and hence I ran across this problem. My more common test machines would have never seen the issue I reported.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD