* [PATCH 1/4] powerpc: Hide some system call labels from profile tools
@ 2012-04-05 4:23 Anton Blanchard
2012-04-05 4:24 ` [PATCH 2/4] powerpc: No need to save XER in a system call Anton Blanchard
` (2 more replies)
0 siblings, 3 replies; 5+ messages in thread
From: Anton Blanchard @ 2012-04-05 4:23 UTC (permalink / raw)
To: benh, paulus, linuxppc-dev
syscall_dotrace_cont and syscall_error_cont tend to complicate perf
output so make them local.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
Index: linux-build/arch/powerpc/kernel/entry_64.S
===================================================================
--- linux-build.orig/arch/powerpc/kernel/entry_64.S 2012-03-22 22:41:21.209137690 +1100
+++ linux-build/arch/powerpc/kernel/entry_64.S 2012-03-22 22:47:04.479314599 +1100
@@ -154,7 +154,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLP
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_T_OR_A
bne- syscall_dotrace
-syscall_dotrace_cont:
+.Lsyscall_dotrace_cont:
cmpldi 0,r0,NR_syscalls
bge- syscall_enosys
@@ -211,7 +211,7 @@ syscall_exit:
cmpld r3,r11
ld r5,_CCR(r1)
bge- syscall_error
-syscall_error_cont:
+.Lsyscall_error_cont:
ld r7,_NIP(r1)
BEGIN_FTR_SECTION
stdcx. r0,0,r1 /* to clear the reservation */
@@ -246,7 +246,7 @@ syscall_error:
oris r5,r5,0x1000 /* Set SO bit in CR */
neg r3,r3
std r5,_CCR(r1)
- b syscall_error_cont
+ b .Lsyscall_error_cont
/* Traced system call support */
syscall_dotrace:
@@ -268,7 +268,7 @@ syscall_dotrace:
addi r9,r1,STACK_FRAME_OVERHEAD
clrrdi r10,r1,THREAD_SHIFT
ld r10,TI_FLAGS(r10)
- b syscall_dotrace_cont
+ b .Lsyscall_dotrace_cont
syscall_enosys:
li r3,-ENOSYS
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 2/4] powerpc: No need to save XER in a system call
2012-04-05 4:23 [PATCH 1/4] powerpc: Hide some system call labels from profile tools Anton Blanchard
@ 2012-04-05 4:24 ` Anton Blanchard
2012-04-05 4:25 ` [PATCH 3/4] powerpc: Better scheduling of CR save code in system call path Anton Blanchard
2012-04-05 4:26 ` [PATCH 4/4] powerpc: No need to preserve count register across system call Anton Blanchard
2 siblings, 0 replies; 5+ messages in thread
From: Anton Blanchard @ 2012-04-05 4:24 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev
The XER is a volatile register so there is no need to save and restore
it over a system call - zero it out in the exception stack frame
instead.
This should fix a 5 cycle stall of the mfxer/std seen on POWER7.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
Index: linux-build/arch/powerpc/kernel/entry_64.S
===================================================================
--- linux-build.orig/arch/powerpc/kernel/entry_64.S 2012-03-22 22:47:04.479314599 +1100
+++ linux-build/arch/powerpc/kernel/entry_64.S 2012-03-22 22:47:08.379384827 +1100
@@ -82,6 +82,7 @@ system_call_common:
std r11,GPR10(r1)
std r11,GPR11(r1)
std r11,GPR12(r1)
+ std r11,_XER(r1)
std r9,GPR13(r1)
mfcr r9
mflr r10
@@ -89,9 +90,7 @@ system_call_common:
std r9,_CCR(r1)
std r10,_LINK(r1)
std r11,_TRAP(r1)
- mfxer r9
mfctr r10
- std r9,_XER(r1)
std r10,_CTR(r1)
std r3,ORIG_GPR3(r1)
ld r2,PACATOC(r13)
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH 3/4] powerpc: Better scheduling of CR save code in system call path
2012-04-05 4:23 [PATCH 1/4] powerpc: Hide some system call labels from profile tools Anton Blanchard
2012-04-05 4:24 ` [PATCH 2/4] powerpc: No need to save XER in a system call Anton Blanchard
@ 2012-04-05 4:25 ` Anton Blanchard
2012-04-05 13:44 ` [PATCH 3/4 v2] " Anton Blanchard
2012-04-05 4:26 ` [PATCH 4/4] powerpc: No need to preserve count register across system call Anton Blanchard
2 siblings, 1 reply; 5+ messages in thread
From: Anton Blanchard @ 2012-04-05 4:25 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev
At the moment system call entry looks like:
crclr so
...
mfcr r9
...
std r9,_CCR(r1)
commit bd19c8994a82 ([POWERPC] system call micro optimisation) put
some space between the crclr and mfcr in order to avoid a stall.
There is still a stall seen between the mfcr and std. We can avoid
the crclr by doing it in a GPR with rlwinm which gives us more room
to better schedule the sequence.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
Index: linux-build/arch/powerpc/kernel/entry_64.S
===================================================================
--- linux-build.orig/arch/powerpc/kernel/entry_64.S 2012-03-22 22:47:08.379384827 +1100
+++ linux-build/arch/powerpc/kernel/entry_64.S 2012-03-22 22:47:15.023504471 +1100
@@ -63,15 +63,9 @@ system_call_common:
std r0,GPR0(r1)
std r10,GPR1(r1)
ACCOUNT_CPU_USER_ENTRY(r10, r11)
- /*
- * This "crclr so" clears CR0.SO, which is the error indication on
- * return from this system call. There must be no cmp instruction
- * between it and the "mfcr r9" below, otherwise if XER.SO is set,
- * CR0.SO will get set, causing all system calls to appear to fail.
- */
- crclr so
std r2,GPR2(r1)
std r3,GPR3(r1)
+ mfcr r2
std r4,GPR4(r1)
std r5,GPR5(r1)
std r6,GPR6(r1)
@@ -84,15 +78,19 @@ system_call_common:
std r11,GPR12(r1)
std r11,_XER(r1)
std r9,GPR13(r1)
- mfcr r9
mflr r10
li r11,0xc01
- std r9,_CCR(r1)
+ /*
+ * This clears CR0.SO, which is the error indication on return
+ * from this system call.
+ */
+ rlwinm r2,r2,0,4,2
std r10,_LINK(r1)
std r11,_TRAP(r1)
mfctr r10
std r10,_CTR(r1)
std r3,ORIG_GPR3(r1)
+ std r2,_CCR(r1)
ld r2,PACATOC(r13)
addi r9,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH 3/4 v2] powerpc: Better scheduling of CR save code in system call path
2012-04-05 4:25 ` [PATCH 3/4] powerpc: Better scheduling of CR save code in system call path Anton Blanchard
@ 2012-04-05 13:44 ` Anton Blanchard
0 siblings, 0 replies; 5+ messages in thread
From: Anton Blanchard @ 2012-04-05 13:44 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev
At the moment system call entry looks like:
crclr so
...
mfcr r9
...
std r9,_CCR(r1)
commit bd19c8994a82 ([POWERPC] system call micro optimisation) put
some space between the crclr and mfcr in order to avoid a stall.
There is still a stall seen between the mfcr and std. We can avoid
the crclr by doing it in a GPR with rlwinm which gives us more room
to better schedule the sequence.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
v2:
Milton pointed out that rlwinm copies the low 32bits into the top
32bits and this might confuse ptracers. We tossed around a few ideas
but his suggestion of using rldimi sounds good to me.
Index: linux-build/arch/powerpc/kernel/entry_64.S
===================================================================
--- linux-build.orig/arch/powerpc/kernel/entry_64.S 2012-04-05 14:03:05.123678148 +1000
+++ linux-build/arch/powerpc/kernel/entry_64.S 2012-04-05 23:38:09.182681076 +1000
@@ -63,15 +63,9 @@ system_call_common:
std r0,GPR0(r1)
std r10,GPR1(r1)
ACCOUNT_CPU_USER_ENTRY(r10, r11)
- /*
- * This "crclr so" clears CR0.SO, which is the error indication on
- * return from this system call. There must be no cmp instruction
- * between it and the "mfcr r9" below, otherwise if XER.SO is set,
- * CR0.SO will get set, causing all system calls to appear to fail.
- */
- crclr so
std r2,GPR2(r1)
std r3,GPR3(r1)
+ mfcr r2
std r4,GPR4(r1)
std r5,GPR5(r1)
std r6,GPR6(r1)
@@ -84,15 +78,19 @@ system_call_common:
std r11,GPR12(r1)
std r11,_XER(r1)
std r9,GPR13(r1)
- mfcr r9
mflr r10
+ /*
+ * This clears CR0.SO (bit 28), which is the error indication on
+ * return from this system call.
+ */
+ rldimi r2,r11,28,(63-28)
li r11,0xc01
- std r9,_CCR(r1)
std r10,_LINK(r1)
std r11,_TRAP(r1)
mfctr r10
std r10,_CTR(r1)
std r3,ORIG_GPR3(r1)
+ std r2,_CCR(r1)
ld r2,PACATOC(r13)
addi r9,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH 4/4] powerpc: No need to preserve count register across system call
2012-04-05 4:23 [PATCH 1/4] powerpc: Hide some system call labels from profile tools Anton Blanchard
2012-04-05 4:24 ` [PATCH 2/4] powerpc: No need to save XER in a system call Anton Blanchard
2012-04-05 4:25 ` [PATCH 3/4] powerpc: Better scheduling of CR save code in system call path Anton Blanchard
@ 2012-04-05 4:26 ` Anton Blanchard
2 siblings, 0 replies; 5+ messages in thread
From: Anton Blanchard @ 2012-04-05 4:26 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev
The count register is volatile so we don't need to preserve it.
Store zero to the entry in the exception frame.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
Index: linux-build/arch/powerpc/kernel/entry_64.S
===================================================================
--- linux-build.orig/arch/powerpc/kernel/entry_64.S 2012-03-22 22:47:15.023504471 +1100
+++ linux-build/arch/powerpc/kernel/entry_64.S 2012-03-22 22:47:17.899556262 +1100
@@ -77,6 +77,7 @@ system_call_common:
std r11,GPR11(r1)
std r11,GPR12(r1)
std r11,_XER(r1)
+ std r11,_CTR(r1)
std r9,GPR13(r1)
mflr r10
li r11,0xc01
@@ -87,8 +88,6 @@ system_call_common:
rlwinm r2,r2,0,4,2
std r10,_LINK(r1)
std r11,_TRAP(r1)
- mfctr r10
- std r10,_CTR(r1)
std r3,ORIG_GPR3(r1)
std r2,_CCR(r1)
ld r2,PACATOC(r13)
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2012-04-05 13:44 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-04-05 4:23 [PATCH 1/4] powerpc: Hide some system call labels from profile tools Anton Blanchard
2012-04-05 4:24 ` [PATCH 2/4] powerpc: No need to save XER in a system call Anton Blanchard
2012-04-05 4:25 ` [PATCH 3/4] powerpc: Better scheduling of CR save code in system call path Anton Blanchard
2012-04-05 13:44 ` [PATCH 3/4 v2] " Anton Blanchard
2012-04-05 4:26 ` [PATCH 4/4] powerpc: No need to preserve count register across system call 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).