x86/fpu: Add tracepoints to dump FPU state at key points
I've been carrying this patch around for a bit and it's helped me
solve at least a couple FPU-related bugs. In addition to using
it for debugging, I also drug it out because using AVX (and
AVX2/AVX-512) can have serious power consequences for a modern
core. It's very important to be able to figure out who is using
it.
It's also insanely useful to go out and see who is using a given
feature, like MPX or Memory Protection Keys. If you, for
instance, want to find all processes using protection keys, you
can do:
echo 'xfeatures & 0x200' > filter
Since 0x200 is the protection keys feature bit.
Note that this touches the KVM code. KVM did a CREATE_TRACE_POINTS
and then included a bunch of random headers. If anyone one of
those included other tracepoints, it would have defined the *OTHER*
tracepoints. That's bogus, so move it to the right place.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160601174220.3CDFB90E@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 31ac8e6..116b583 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -18,6 +18,7 @@
#include <asm/fpu/api.h>
#include <asm/fpu/xstate.h>
#include <asm/cpufeature.h>
+#include <asm/trace/fpu.h>
/*
* High level FPU state handling functions:
@@ -524,6 +525,7 @@
fpu->fpregs_active = 0;
this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+ trace_x86_fpu_regs_deactivated(fpu);
}
/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
@@ -533,6 +535,7 @@
fpu->fpregs_active = 1;
this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+ trace_x86_fpu_regs_activated(fpu);
}
/*
@@ -604,11 +607,13 @@
/* But leave fpu_fpregs_owner_ctx! */
old_fpu->fpregs_active = 0;
+ trace_x86_fpu_regs_deactivated(old_fpu);
/* Don't change CR0.TS if we just switch! */
if (fpu.preload) {
new_fpu->counter++;
__fpregs_activate(new_fpu);
+ trace_x86_fpu_regs_activated(new_fpu);
prefetch(&new_fpu->state);
} else {
__fpregs_deactivate_hw();