From 70fb74a5420f9caa3e001d65004e4b669124283e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 7 Jun 2012 11:54:37 -0400 Subject: 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 Cc: Linus Torvalds Cc: H. Peter Anvin Cc: Thomas Gleixner Signed-off-by: Steven Rostedt --- arch/x86/kernel/nmi.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch/x86/kernel/nmi.c') diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index a15a888..f84f5c5 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -395,6 +395,14 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) * thus there is no race between the first check of state for NOT_RUNNING * and setting it to NMI_EXECUTING. The HW will prevent nested NMIs * at this point. + * + * In case the NMI takes a page fault, we need to save off the CR2 + * because the NMI could have preempted another page fault and corrupt + * the CR2 that is about to be read. As nested NMIs must be restarted + * and they can not take breakpoints or page faults, the update of the + * CR2 must be done before converting the nmi state back to NOT_RUNNING. + * Otherwise, there would be a race of another nested NMI coming in + * after setting state to NOT_RUNNING but before updating the nmi_cr2. */ enum nmi_states { NMI_NOT_RUNNING = 0, @@ -402,6 +410,7 @@ enum nmi_states { NMI_LATCHED, }; static DEFINE_PER_CPU(enum nmi_states, nmi_state); +static DEFINE_PER_CPU(unsigned long, nmi_cr2); #define nmi_nesting_preprocess(regs) \ do { \ @@ -410,11 +419,14 @@ static DEFINE_PER_CPU(enum nmi_states, nmi_state); return; \ } \ this_cpu_write(nmi_state, NMI_EXECUTING); \ + this_cpu_write(nmi_cr2, read_cr2()); \ } while (0); \ nmi_restart: #define nmi_nesting_postprocess() \ do { \ + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \ + write_cr2(this_cpu_read(nmi_cr2)); \ if (this_cpu_dec_return(nmi_state)) \ goto nmi_restart; \ } while (0) -- cgit v1.1