aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/kprobes/core.c
diff options
context:
space:
mode:
authorDenys Vlasenko <dvlasenk@redhat.com>2015-02-12 20:18:52 +0100
committerIngo Molnar <mingo@kernel.org>2015-02-18 20:55:53 +0100
commit5154d4f2adfdabe5aeb247e5b2b6b10fae5f6d50 (patch)
treeee49d0012951d79f28da41dbfed7d24845b2185b /arch/x86/kernel/kprobes/core.c
parentuprobes/x86: Fix 1-byte opcode tables (diff)
downloadlinux-dev-5154d4f2adfdabe5aeb247e5b2b6b10fae5f6d50.tar.xz
linux-dev-5154d4f2adfdabe5aeb247e5b2b6b10fae5f6d50.zip
uprobes/x86: Fix 2-byte opcode table
Enabled probing of lar, lsl, popcnt, lddqu, prefetch insns. They should be safe to probe, they throw no exceptions. Enabled probing of 3-byte opcodes 0f 38-3f xx - these are vector isns, so should be safe. Enabled probing of many currently undefined 0f xx insns. At the rate new vector instructions are getting added, we don't want to constantly enable more bits. We want to only occasionally *disable* ones which for some reason can't be probed. This includes 0f 24,26 opcodes, which are undefined since Pentium. On 486, they were "mov to/from test register". Explained more fully what 0f 78,79 opcodes are. Explained what 0f ae opcode is. (It's unclear why we don't allow probing it, but let's not change it for now). Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1423768732-32194-3-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to '')
0 files changed, 0 insertions, 0 deletions