diff options
author | Steven Rostedt <srostedt@redhat.com> | 2012-06-07 17:54:37 +0200 |
---|---|---|
committer | Steven Rostedt <rostedt@goodmis.org> | 2012-06-09 00:51:12 +0200 |
commit | 70fb74a5420f9caa3e001d65004e4b669124283e (patch) | |
tree | a099c86b2e63dc5d6246b8efe07a5b3e91b1301e /net/nfc/llcp/sock.c | |
parent | x86: Remove cmpxchg from i386 NMI nesting code (diff) | |
download | linux-70fb74a5420f9caa3e001d65004e4b669124283e.tar.xz linux-70fb74a5420f9caa3e001d65004e4b669124283e.zip |
x86: Save cr2 in NMI in case NMIs take a page fault (for i386)
Avi Kivity reported that page faults in NMIs could cause havic if
the NMI preempted another page fault handler:
The recent changes to NMI allow exceptions to take place in NMI
handlers, but I think that a #PF (say, due to access to vmalloc space)
is still problematic. Consider the sequence
#PF (cr2 set by processor)
NMI
...
#PF (cr2 clobbered)
do_page_fault()
IRET
...
IRET
do_page_fault()
address = read_cr2()
The last line reads the overwritten cr2 value.
This is the i386 version, which has the luxury of doing the work
in C code.
Link: http://lkml.kernel.org/r/4FBB8C40.6080304@redhat.com
Reported-by: Avi Kivity <avi@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Diffstat (limited to 'net/nfc/llcp/sock.c')
0 files changed, 0 insertions, 0 deletions