* [PATCH] bypass hcall stats until cpu features have run
@ 2007-03-20 19:29 Anton Blanchard
0 siblings, 0 replies; only message in thread
From: Anton Blanchard @ 2007-03-20 19:29 UTC (permalink / raw)
To: linuxppc-dev; +Cc: paulus
I noticed that we execute hcalls before cpu feature code has run (eg for
setting up the bolted kernel region). Create an unconditional branch
that we nop out all the time to fix this.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
Index: linux-2.6/arch/powerpc/platforms/pseries/hvCall.S
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/pseries/hvCall.S 2007-03-08 09:08:11.000000000 -0600
+++ linux-2.6/arch/powerpc/platforms/pseries/hvCall.S 2007-03-08 09:15:12.000000000 -0600
@@ -30,9 +30,14 @@
/*
* postcall is performed immediately before function return which
- * allows liberal use of volatile registers.
+ * allows liberal use of volatile registers. We branch around this
+ * in early init (eg when populating the MMU hashtable) by using an
+ * unconditional cpu feature.
*/
#define HCALL_INST_POSTCALL \
+BEGIN_FTR_SECTION; \
+ b 1f; \
+END_FTR_SECTION(0, 1); \
ld r4,STK_PARM(r3)(r1); /* validate opcode */ \
cmpldi cr7,r4,MAX_HCALL_OPCODE; \
bgt- cr7,1f; \
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2007-03-20 19:29 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-03-20 19:29 [PATCH] bypass hcall stats until cpu features have run Anton Blanchard
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).