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>
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index b558c31..9b01c0e 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -76,6 +76,51 @@
 	TP_printk("pt_regs=%p", __entry->regs)
 );
 
+#ifdef CONFIG_PPC_PSERIES
+extern void hcall_tracepoint_regfunc(void);
+extern void hcall_tracepoint_unregfunc(void);
+
+TRACE_EVENT_FN(hcall_entry,
+
+	TP_PROTO(unsigned long opcode),
+
+	TP_ARGS(opcode),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+	),
+
+	TP_printk("opcode=%lu", __entry->opcode),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+
+TRACE_EVENT_FN(hcall_exit,
+
+	TP_PROTO(unsigned long opcode, unsigned long retval),
+
+	TP_ARGS(opcode, retval),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+		__field(unsigned long, retval)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+		__entry->retval = retval;
+	),
+
+	TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+#endif
+
 #endif /* _TRACE_POWERPC_H */
 
 #undef TRACE_INCLUDE_PATH