powerpc/pseries: Use jump labels for hcall tracepoints
hcall tracepoints add quite a few instructions to our hcall path:
plpar_hcall:
mr r2,r2
mfcr r0
stw r0,8(r1)
b 164 <---- start
ld r12,0(r2)
std r12,32(r1)
cmpdi r12,0
beq 164 <---- end
...
We have an unconditional branch that gets noped out during boot and
a load/compare/branch. We also store the tracepoint value to the
stack for the hcall_exit path to use.
By using jump labels we can simplify this to just a single nop that
gets replaced with a branch when the tracepoint is enabled:
plpar_hcall:
mr r2,r2
mfcr r0
stw r0,8(r1)
nop <----
...
If jump labels are not enabled, we fall back to the old method.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index b02af9e..fbfcef5 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -26,6 +26,7 @@
#include <linux/dma-mapping.h>
#include <linux/console.h>
#include <linux/export.h>
+#include <linux/static_key.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/page.h>
@@ -649,6 +650,19 @@
#endif
#ifdef CONFIG_TRACEPOINTS
+#ifdef CONFIG_JUMP_LABEL
+struct static_key hcall_tracepoint_key = STATIC_KEY_INIT;
+
+void hcall_tracepoint_regfunc(void)
+{
+ static_key_slow_inc(&hcall_tracepoint_key);
+}
+
+void hcall_tracepoint_unregfunc(void)
+{
+ static_key_slow_dec(&hcall_tracepoint_key);
+}
+#else
/*
* We optimise our hcall path by placing hcall_tracepoint_refcount
* directly in the TOC so we can check if the hcall tracepoints are
@@ -658,13 +672,6 @@
/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
extern long hcall_tracepoint_refcount;
-/*
- * Since the tracing code might execute hcalls we need to guard against
- * recursion. One example of this are spinlocks calling H_YIELD on
- * shared processor partitions.
- */
-static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
-
void hcall_tracepoint_regfunc(void)
{
hcall_tracepoint_refcount++;
@@ -674,6 +681,15 @@
{
hcall_tracepoint_refcount--;
}
+#endif
+
+/*
+ * Since the tracing code might execute hcalls we need to guard against
+ * recursion. One example of this are spinlocks calling H_YIELD on
+ * shared processor partitions.
+ */
+static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
+
void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
{