arm: Only load TLS values when needed

[André Hentschel]

Am 15.08.2013 20:27, schrieb André Hentschel:
> Hi Jonathan,
> 
> Am 15.08.2013 19:29, schrieb Jonathan Austin:
>> Hi André
>> What I've *not* tested:
>> * As this CPU does not have the tls register, I haven't run any tests that try to read/write it, but we wouldn't expect that to work, right?
>> * Haven't tried a V7 platform, as I understand you've already done that.
>> * Haven't verified it still builds for v4 (which was the problem for ldrd in the past and now we've put it back, so that's important)
> 
> It shouldn't matter as v4 would not use the v6 codepath, would it?
> 
>> * Performance impact
> 
> I only could test it on v7, would be interesting to see some v6, v5, ... "benchmarks", though.
> 

I did some "benchmarks" on my pandaboard(armv7) and it turns out that ldrd is slightly slower than two ldr.
So with this in mind the best thing is most likely the easiest one, so what about this untested patch below?
(It intends to improve the situation for tls_none and tls_software)

diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 83259b8..1dd50f8 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -3,17 +3,21 @@
 
 #ifdef __ASSEMBLY__
 #include <asm/asm-offsets.h>
-	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
+	.macro switch_tls_none, prev, next, tp, tpuser, tmp1, tmp2
 	.endm
 
-	.macro switch_tls_v6k, base, tp, tpuser, tmp1, tmp2
+	.macro switch_tls_v6k, prev, next, tp, tpuser, tmp1, tmp2
+	ldr	\tp, [\next, #TI_TP_VALUE]
+	ldr	\tpuser, [\next, #TI_TP_VALUE + 4]
 	mrc	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
 	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
 	mcr	p15, 0, \tpuser, c13, c0, 2	@ and the user r/w register
-	str	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
+	str	\tmp2, [\prev, #TI_TP_VALUE + 4] @ save it
 	.endm
 
-	.macro switch_tls_v6, base, tp, tpuser, tmp1, tmp2
+	.macro switch_tls_v6, prev, next, tp, tpuser, tmp1, tmp2
+	ldr	\tp, [\next, #TI_TP_VALUE]
+	ldr	\tpuser, [\next, #TI_TP_VALUE + 4]
 	ldr	\tmp1, =elf_hwcap
 	ldr	\tmp1, [\tmp1, #0]
 	mov	\tmp2, #0xffff0fff
@@ -22,10 +26,11 @@
 	mrcne	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
 	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
 	mcrne	p15, 0, \tpuser, c13, c0, 2	@ set user r/w register
-	strne	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
+	strne	\tmp2, [\prev, #TI_TP_VALUE + 4] @ save it
 	.endm
 
-	.macro switch_tls_software, base, tp, tpuser, tmp1, tmp2
+	.macro switch_tls_software, prev, next, tp, tpuser, tmp1, tmp2
+	ldr	\tp, [\next, #TI_TP_VALUE]
 	mov	\tmp1, #0xffff0fff
 	str	\tp, [\tmp1, #-15]		@ set TLS value at 0xffff0ff0
 	.endm
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 9cbe70c..4df8976 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -690,12 +690,10 @@ ENTRY(__switch_to)
  THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
  THUMB(	str	sp, [ip], #4		   )
  THUMB(	str	lr, [ip], #4		   )
-	ldr	r4, [r2, #TI_TP_VALUE]
-	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
-	switch_tls r1, r4, r5, r3, r7
+	switch_tls r1, r2, r4, r5, r3, r7
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
 	ldr	r7, [r2, #TI_TASK]
 	ldr	r8, =__stack_chk_guard