perf/x86/intel/pt: Handle VMX better

Since commit:

  1c5ac21a0e ("perf/x86/intel/pt: Don't die on VMXON")

... PT events depend on re-scheduling to get enabled after a VMX session
has taken place. This is, in particular, a problem for CPU context events,
which don't normally get re-scheduled, unless there is a reason.

This patch changes the VMX handling so that PT event gets re-enabled
when VMX root mode exits.

Also, notify the user when there's a gap in PT data due to VMX root
mode by flagging AUX records as partial.

In combination with vmm_exclusive=0 parameter of the kvm_intel driver,
this will result in trace gaps only for the duration of the guest's
timeslices.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20170220133352.17995-5-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 0218728..354e9ff 100644 (file)
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -411,6 +411,7 @@ static u64 pt_config_filters(struct perf_event *event)
 
 static void pt_config(struct perf_event *event)
 {
+       struct pt *pt = this_cpu_ptr(&pt_ctx);
        u64 reg;
 
        if (!event->hw.itrace_started) {
@@ -429,11 +430,15 @@ static void pt_config(struct perf_event *event)
        reg |= (event->attr.config & PT_CONFIG_MASK);
 
        event->hw.config = reg;
-       wrmsrl(MSR_IA32_RTIT_CTL, reg);
+       if (READ_ONCE(pt->vmx_on))
+               perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
+       else
+               wrmsrl(MSR_IA32_RTIT_CTL, reg);
 }
 
 static void pt_config_stop(struct perf_event *event)
 {
+       struct pt *pt = this_cpu_ptr(&pt_ctx);
        u64 ctl = READ_ONCE(event->hw.config);
 
        /* may be already stopped by a PMI */
@@ -441,7 +446,8 @@ static void pt_config_stop(struct perf_event *event)
                return;
 
        ctl &= ~RTIT_CTL_TRACEEN;
-       wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+       if (!READ_ONCE(pt->vmx_on))
+               wrmsrl(MSR_IA32_RTIT_CTL, ctl);
 
        WRITE_ONCE(event->hw.config, ctl);
 
@@ -1174,12 +1180,6 @@ void intel_pt_interrupt(void)
        if (!READ_ONCE(pt->handle_nmi))
                return;
 
-       /*
-        * If VMX is on and PT does not support it, don't touch anything.
-        */
-       if (READ_ONCE(pt->vmx_on))
-               return;
-
        if (!event)
                return;
 
@@ -1239,12 +1239,19 @@ void intel_pt_handle_vmx(int on)
        local_irq_save(flags);
        WRITE_ONCE(pt->vmx_on, on);
 
-       if (on) {
-               /* prevent pt_config_stop() from writing RTIT_CTL */
-               event = pt->handle.event;
-               if (event)
-                       event->hw.config = 0;
-       }
+       /*
+        * If an AUX transaction is in progress, it will contain
+        * gap(s), so flag it PARTIAL to inform the user.
+        */
+       event = pt->handle.event;
+       if (event)
+               perf_aux_output_flag(&pt->handle,
+                                    PERF_AUX_FLAG_PARTIAL);
+
+       /* Turn PTs back on */
+       if (!on && event)
+               wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config);
+
        local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(intel_pt_handle_vmx);
@@ -1259,9 +1266,6 @@ static void pt_event_start(struct perf_event *event, int mode)
        struct pt *pt = this_cpu_ptr(&pt_ctx);
        struct pt_buffer *buf;
 
-       if (READ_ONCE(pt->vmx_on))
-               return;
-
        buf = perf_aux_output_begin(&pt->handle, event);
        if (!buf)
                goto fail_stop;