[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[RFC PATCH v1 08/10] pmu.h: expose a hypervisor stacktrace feature



For now this'll only be expected to work when the hypervisor is compiled
with frame pointers, and only when the domain is privileged enough to
profile Xen (i.e. it is the hardware domain running in HV or ALL modes).

The stacktrace feature is a flag, rather than a new mode, and would
simply report a stacktrace of depth 0 in other cases.
Old hypervisors with VPMU 0.1 would also report a stracktrace of depth
0, due to implicit zero-filling of the page that contains 'struct xen_pmu_data'.

This is just the interface, followup commit implements it.

No functional change.

Signed-off-by: Edwin Török <edwin.torok@xxxxxxxxx>
---
 xen/include/public/pmu.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/xen/include/public/pmu.h b/xen/include/public/pmu.h
index 6366a79169..85b2bbed74 100644
--- a/xen/include/public/pmu.h
+++ b/xen/include/public/pmu.h
@@ -80,10 +80,12 @@ DEFINE_XEN_GUEST_HANDLE(xen_pmu_params_t);
  *                              Architectural Performance Events exposed by
  *                              cpuid and listed in the Intel developer's 
manual
  *                              (ignored on AMD).
+ * - XENPMU_FEATURE_HV_STACKTRACE: Hypervisor stacktraces (when compiled with 
frame pointers)
  */
 #define XENPMU_FEATURE_INTEL_BTS  (1<<0)
 #define XENPMU_FEATURE_IPC_ONLY   (1<<1)
 #define XENPMU_FEATURE_ARCH_ONLY  (1<<2)
+#define XENPMU_FEATURE_HV_STACKTRACE (1<<3)
 
 /*
  * Shared PMU data between hypervisor and PV(H) domains.
-- 
2.47.1




 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.