scheduling while atomic" followed by a crash

This document (7017749) is provided subject to the disclaimer at the end of this document.

Environment

SUSE Linux Enterprise Server 11 Service Pack 4 (SLES 11 SP4)

Situation

The dmesg or kernel log displays a lot of "scheduling while atomic" error messages:

<3>BUG: scheduling while atomic: kworker/0:1/0/0x10000100

followed by a crash or lockup:

<1>Unable to handle kernel paging request for data at address 0x000000a0
<1>Faulting instruction address: 0xd000000303e7c040
<4>Oops: Kernel access of bad area, sig: 11 [#1]

or

[] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a0
[] IP: [<xxxxxxxxa04e1ee0>] bnx2x_rx_int+0x8c0/0xd00 [bnx2x]
[] PGD 0
[] Oops: 0002 [#1] SMP

Resolution

The kernel update to kernel 3.0.101-77.1 released June 2016 includes the patch to resolve this problem.

Cause

During initialization the bnx2x driver was using atomic allocations instead of GFP_ATOMIC flag. Atomic allocations should be avoided during initialization. A patch with changes from GFP_KERNEL to GFP_ATOMIC corrects the problem.

Disclaimer

This Support Knowledgebase provides a valuable tool for SUSE customers and parties interested in our products and solutions to acquire information, ideas and learn from one another. Materials are provided for informational, personal or non-commercial use within your organization and are presented "AS IS" WITHOUT WARRANTY OF ANY KIND.