netdev - Re: [Problem] Broadcom BCM5762 Ethernet tg3 times out with stack trace

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CANeD+K_hYMuC_AqB97fjBt+NXCMi5r8KzCNpcvFBk5obKL_k=w@mail.gmail.com>
Date:   Fri, 12 May 2017 18:12:22 -0500
From:   Daniel Kim <dkim@...ymechanix.com>
To:     Michael Chan <michael.chan@...adcom.com>
Cc:     Siva Reddy Kallam <siva.kallam@...adcom.com>,
        Prashant Sreedharan <prashant@...adcom.com>,
        Michael Chan <mchan@...adcom.com>,
        Linux Netdev List <netdev@...r.kernel.org>
Subject: Re: [Problem] Broadcom BCM5762 Ethernet tg3 times out with stack trace

I believe I do have IOMMU enabled. At least the dmesg output seems to
imply that I do:
[    1.141948] iommu: Adding device 0000:00:02.0 to group 0
[    1.142033] iommu: Adding device 0000:00:10.0 to group 1
[    1.142074] iommu: Adding device 0000:00:10.1 to group 1
[    1.142119] iommu: Adding device 0000:00:11.0 to group 2
[    1.142172] iommu: Adding device 0000:00:12.0 to group 3
[    1.142184] iommu: Adding device 0000:00:12.2 to group 3
[    1.142234] iommu: Adding device 0000:00:13.0 to group 4
[    1.142247] iommu: Adding device 0000:00:13.2 to group 4
[    1.142303] iommu: Adding device 0000:00:14.0 to group 5
[    1.142315] iommu: Adding device 0000:00:14.2 to group 5
[    1.142328] iommu: Adding device 0000:00:14.3 to group 5
[    1.142373] iommu: Adding device 0000:00:14.4 to group 6
[    1.142417] iommu: Adding device 0000:00:14.5 to group 7
[    1.142529] iommu: Adding device 0000:00:15.0 to group 8
[    1.142570] iommu: Adding device 0000:00:15.2 to group 8
[    1.142639] iommu: Adding device 0000:00:18.0 to group 9
[    1.142653] iommu: Adding device 0000:00:18.1 to group 9
[    1.142668] iommu: Adding device 0000:00:18.2 to group 9
[    1.142682] iommu: Adding device 0000:00:18.3 to group 9
[    1.142695] iommu: Adding device 0000:00:18.4 to group 9
[    1.142712] iommu: Adding device 0000:00:18.5 to group 9
[    1.142725] iommu: Adding device 0000:01:00.0 to group 0
[    1.142733] iommu: Adding device 0000:01:00.1 to group 0
[    1.142840] iommu: Adding device 0000:04:00.0 to group 8
[    1.143305] AMD-Vi: Found IOMMU at 0000:00:00.2 cap 0x40

The last kernel I used where the NIC mostly worked was 4.4.0 (x86-64).
Even when it worked, it had this issue we've experienced since v3.13
where the NIC would suddenly become unresponsive. It won't be
considered disconnected from the network, but RX/TX packets, errors,
dropped, etc. values displayed with ifconfig would show a number that
looked suspiciously close to 32-bit INT_MAX.

Since v4.8, I can trigger it much faster and it now prints out a call
stack and other messages into dmesg.