Skip to contentSkip to conversation

powerpc: perf_event: Cleanup copy_page output by hiding setup symbol

PATCH In review Anton Blanchard 3 participants 6 messages Oct 18, 2009 – Oct 20, 2009 PowerPC

lore
Share & tools
lore
#0 lore raw

PATCH 1/3 powerpc: perf_event: Cleanup copy_page output by hiding setup symbol

A lot of hits in "setup" doesn't make much sense, so hide this symbol and allow all the hits to end up in copy_4k_page.

---

arch/powerpc/lib/copypage_64.S +2 -2
Index: linux.trees.git/arch/powerpc/lib/copypage_64.S
===================================================================
@@ -26,11 +26,11 @@
 	srd	r8,r5,r11
 
 	mtctr	r8
-setup:
+.Lsetup:
 	dcbt	r9,r4
 	dcbz	r9,r3
 	add	r9,r9,r12
-	bdnz	setup
+	bdnz	.Lsetup
 END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ)
 	addi	r3,r3,-8
 	srdi    r8,r5,7		/* page is copied in 128 byte strides */
#1 lore raw

PATCH 2/3 powerpc: perf_event: Cleanup output by adding symbols

Add some dummy symbols for the branches at 0xf00, 0xf20 and 0xf40, otherwise hits end up in trap_0e which is confusing to the user.

---

arch/powerpc/kernel/exceptions-64s.S +3 -0
Index: linux.trees.git/arch/powerpc/kernel/exceptions-64s.S
===================================================================
@@ -185,12 +185,15 @@
 	 * prolog code of the PerformanceMonitor one. A little
 	 * trickery is thus necessary
 	 */
+performance_monitor_pSeries_1:
 	. = 0xf00
 	b	performance_monitor_pSeries
 
+altivec_unavailable_pSeries_1:
 	. = 0xf20
 	b	altivec_unavailable_pSeries
 
+vsx_unavailable_pSeries_1:
 	. = 0xf40
 	b	vsx_unavailable_pSeries
 
#2 lore raw

PATCH 3/3 powerpc: perf_event: Hide iseries_check_pending_irqs

If CONFIG_PPC_ISERIES isn't defined we end up with iseries_check_pending_irqs and do_work at the same address. perf ends up picking iseries_check_pending_irqs which creates confusing backtraces. Hide it.

--

arch/powerpc/kernel/entry_64.S +2 -2
Index: linux.trees.git/arch/powerpc/kernel/entry_64.S
===================================================================
@@ -551,7 +551,7 @@ restore:
 BEGIN_FW_FTR_SECTION
 	ld	r5,SOFTE(r1)
 FW_FTR_SECTION_ELSE
-	b	iseries_check_pending_irqs
+	b	.Liseries_check_pending_irqs
 ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 2:
 	TRACE_AND_RESTORE_IRQ(r5);
@@ -623,7 +623,7 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_
 
 #endif /* CONFIG_PPC_BOOK3E */
 
-iseries_check_pending_irqs:
+.Liseries_check_pending_irqs:
 #ifdef CONFIG_PPC_ISERIES
 	ld	r5,SOFTE(r1)
 	cmpdi	0,r5,0
#3 lore raw

Re: [PATCH 3/3] powerpc: perf_event: Hide iseries_check_pending_irqs

Quoted 5 lines · Anton Blanchard

If CONFIG_PPC_ISERIES isn't defined we end up with iseries_check_pending_irqs and do_work at the same address. perf ends up picking iseries_check_pending_irqs which creates confusing backtraces. Hide it.

Just to confirm - these 3 symbol fixes are for the PowerPC tree, not for the perf events tree, right? There's nothing perf specific about the fixes - kgdb, systemtap and other debugging/instrumentation frameworks will benefit from more precise symbol generation too.

Ingo

#4 lore raw

Re: [PATCH 3/3] powerpc: perf_event: Hide iseries_check_pending_irqs

Hi Ingo,

Quoted 4 lines

Just to confirm - these 3 symbol fixes are for the PowerPC tree, not for the perf events tree, right? There's nothing perf specific about the fixes - kgdb, systemtap and other debugging/instrumentation frameworks will benefit from more precise symbol generation too.

Yeah, while they were written to fix perf backtrace issues they are definitely not perf specific. Hopefully Ben will queue them up in his tree for the next merge window :)

Anton

#5 lore raw

Re: [PATCH 3/3] powerpc: perf_event: Hide iseries_check_pending_irqs

Quoted 10 lines · Anton Blanchard

Hi Ingo,

Quoted 4 lines

Just to confirm - these 3 symbol fixes are for the PowerPC tree, not for the perf events tree, right? There's nothing perf specific about the fixes - kgdb, systemtap and other debugging/instrumentation frameworks will benefit from more precise symbol generation too.

Yeah, while they were written to fix perf backtrace issues they are definitely not perf specific. Hopefully Ben will queue them up in his tree for the next merge window :)

Right, I'm overdue for a powerpc-next but with some family issues last couple of week and KS/JLS this week, it' a bit hard :-)

Ben.