A malicious user could create a special stack layout that fools the perf_callchain_user_64 function into an infinite loop, tying up that particular CPU and the process can not be killed. A kernel patch was committed upstream capping the maximum userlevel stacktrace collected by perf to PERF_MAX_STACK_DEPTH on 64bit powerpc architectures. This affects all ppc64 kernels that support perf. This seems to be kind of local DOS that can be resolved when the system is rebooted. References: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=9a5cbce421a283e6aea3c4007f141735bf9da8c3 CVE assignment: http://seclists.org/oss-sec/2015/q3/410
Statement: This issue does not affect the Linux kernels as shipped with Red Hat Enterprise Linux 5, 6 and Red Hat Enterprise MRG 2. This issue affects the Linux kernels as shipped with Red Hat Enterprise Linux 7 and may be addressed in a future update.
Created kernel tracking bugs for this issue: Affects: fedora-all [bug 1253892]
CVE assignment: http://seclists.org/oss-sec/2015/q3/410
This issue has been addressed in the following products: Red Hat Enterprise Linux 7 Via RHSA-2015:2152 https://rhn.redhat.com/errata/RHSA-2015-2152.html