Re: KVM_GUEST support breaks page fault tracing

[Dave Hansen]

On 05/08/2014 03:24 PM, Thomas Gleixner wrote:
>> > I noticed on some of my systems that page fault tracing doesn't work:
>> > 
>> > 	cd /sys/kernel/debug/tracing
>> > 	echo 1 > events/exceptions/enable
>> > 	cat trace;
>> > 	# nothing shows up
>> > 
>> > I eventually traced it down to CONFIG_KVM_GUEST.  At least in a KVM VM,
>> > enabling that option breaks page fault tracing, and disabling fixes it.
>> >  I tried on some old kernels and this does not appear to be a
>> > regression: it never worked.
>> > 
>> > Anybody have any theories about what is going on?

Looks like the KVM code calls do_page_fault() directly:

> dotraplinkage void __kprobes
> do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
> {
>         enum ctx_state prev_state;
> 
>         switch (kvm_read_and_reset_pf_reason()) {
>         default:
>                 do_page_fault(regs, error_code);
>                 break;
>         case KVM_PV_REASON_PAGE_NOT_PRESENT:

That seems to explain my problems in a VM.  Any objections to doing
something like the attached patch?


---

 b/arch/x86/include/asm/traps.h |    5 +++++
 b/arch/x86/kernel/kvm.c        |    2 +-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff -puN arch/x86/kernel/kvm.c~muck-with-kvm-guest-code arch/x86/kernel/kvm.c
--- a/arch/x86/kernel/kvm.c~muck-with-kvm-guest-code	2014-05-08 15:03:24.358110394 -0700
+++ b/arch/x86/kernel/kvm.c	2014-05-08 16:03:56.765302785 -0700
@@ -259,7 +259,7 @@ do_async_page_fault(struct pt_regs *regs
 
 	switch (kvm_read_and_reset_pf_reason()) {
 	default:
-		do_page_fault(regs, error_code);
+		trace_do_page_fault(regs, error_code);
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
diff -puN arch/x86/include/asm/traps.h~muck-with-kvm-guest-code arch/x86/include/asm/traps.h
--- a/arch/x86/include/asm/traps.h~muck-with-kvm-guest-code	2014-05-08 16:02:14.873675048 -0700
+++ b/arch/x86/include/asm/traps.h	2014-05-08 16:03:06.519020810 -0700
@@ -74,6 +74,11 @@ dotraplinkage void do_general_protection
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
 #ifdef CONFIG_TRACING
 dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long);
+#else
+static inline void trace_do_page_fault(struct pt_regs *regs, unsigned long error)
+{
+	do_page_fault(regs, error);
+}
 #endif
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
 dotraplinkage void do_coprocessor_error(struct pt_regs *, long);
_