powerpc: tracing: Add hypervisor call tracepoints

Add hcall_entry and hcall_exit tracepoints.  This replaces the inline
assembly HCALL_STATS code and converts it to use the new tracepoints.

To keep the disabled case as quick as possible, we embed a status word
in the TOC so we can get at it with a single load.  By doing so we
keep the overhead at a minimum.  Time taken for a null hcall:

No tracepoint code:	135.79 cycles
Disabled tracepoints:	137.95 cycles

For reference, before this patch enabling HCALL_STATS resulted in a null
hcall of 201.44 cycles!

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

1 files changed, 32 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 903eb9e..4b7b6e8 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -39,6 +39,7 @@
 #include <asm/cputable.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
+#include <asm/trace.h>
 
 #include "plpar_wrappers.h"
 #include "pseries.h"
@@ -661,3 +662,34 @@ void arch_free_page(struct page *page, int order)
 EXPORT_SYMBOL(arch_free_page);
 
 #endif
+
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * We optimise our hcall path by placing hcall_tracepoint_refcount
+ * directly in the TOC so we can check if the hcall tracepoints are
+ * enabled via a single load.
+ */
+
+/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
+extern long hcall_tracepoint_refcount;
+
+void hcall_tracepoint_regfunc(void)
+{
+	hcall_tracepoint_refcount++;
+}
+
+void hcall_tracepoint_unregfunc(void)
+{
+	hcall_tracepoint_refcount--;
+}
+
+void __trace_hcall_entry(unsigned long opcode)
+{
+	trace_hcall_entry(opcode);
+}
+
+void __trace_hcall_exit(long opcode, unsigned long retval)
+{
+	trace_hcall_exit(opcode, retval);
+}
+#endif