tmakin/tegra-linux-noble
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

powerpc: Remove UP only lazy floating point and vector optimisations

Browse Source 
The UP only lazy floating point and vector optimisations were written
back when SMP was not common, and neither glibc nor gcc used vector
instructions. Now SMP is very common, glibc aggressively uses vector
instructions and gcc autovectorises.

We want to add new optimisations that apply to both UP and SMP, but
in preparation for that remove these UP only optimisations.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This commit is contained in:
Anton Blanchard
2015-10-29 11:43:57 +11:00
committed by Michael Ellerman
parent 68bfa962bf
commit af1bbc3dd3
9 changed files with 1 additions and 304 deletions
Download Patch File Download Diff File Expand all files Collapse all files
arch/powerpc/kernel/vector.S
-68
View File
@@ -80,39 +80,6 @@ _GLOBAL(load_up_altivec)
MTMSRD(r5) /* enable use of AltiVec now */
isync
/*
* For SMP, we don't do lazy VMX switching because it just gets too
* horrendously complex, especially when a task switches from one CPU
* to another. Instead we call giveup_altvec in switch_to.
* VRSAVE isn't dealt with here, that is done in the normal context
* switch code. Note that we could rely on vrsave value to eventually
* avoid saving all of the VREGs here...
*/
#ifndef CONFIG_SMP
LOAD_REG_ADDRBASE(r3, last_task_used_altivec)
toreal(r3)
PPC_LL r4,ADDROFF(last_task_used_altivec)(r3)
PPC_LCMPI 0,r4,0
beq 1f
/* Save VMX state to last_task_used_altivec's THREAD struct */
toreal(r4)
addi r4,r4,THREAD
addi r6,r4,THREAD_VRSTATE
SAVE_32VRS(0,r5,r6)
mfvscr v0
li r10,VRSTATE_VSCR
stvx v0,r10,r6
/* Disable VMX for last_task_used_altivec */
PPC_LL r5,PT_REGS(r4)
toreal(r5)
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
lis r10,MSR_VEC@h
andc r4,r4,r10
PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
1:
#endif /* CONFIG_SMP */
/* Hack: if we get an altivec unavailable trap with VRSAVE
* set to all zeros, we assume this is a broken application
* that fails to set it properly, and thus we switch it to
@@ -141,12 +108,6 @@ _GLOBAL(load_up_altivec)
lvx v0,r10,r6
mtvscr v0
REST_32VRS(0,r4,r6)
#ifndef CONFIG_SMP
/* Update last_task_used_altivec to 'current' */
subi r4,r5,THREAD /* Back to 'current' */
fromreal(r4)
PPC_STL r4,ADDROFF(last_task_used_altivec)(r3)
#endif /* CONFIG_SMP */
/* restore registers and return */
blr
@@ -199,11 +160,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
andc r4,r4,r3 /* disable FP for previous task */
PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
1:
#ifndef CONFIG_SMP
li r5,0
LOAD_REG_ADDRBASE(r4,last_task_used_altivec)
PPC_STL r5,ADDROFF(last_task_used_altivec)(r4)
#endif /* CONFIG_SMP */
blr
#ifdef CONFIG_VSX
@@ -226,20 +182,6 @@ _GLOBAL(load_up_vsx)
andis. r5,r12,MSR_VEC@h
beql+ load_up_altivec /* skip if already loaded */
#ifndef CONFIG_SMP
ld r3,last_task_used_vsx@got(r2)
ld r4,0(r3)
cmpdi 0,r4,0
beq 1f
/* Disable VSX for last_task_used_vsx */
addi r4,r4,THREAD
ld r5,PT_REGS(r4)
ld r4,_MSR-STACK_FRAME_OVERHEAD(r5)
lis r6,MSR_VSX@h
andc r6,r4,r6
std r6,_MSR-STACK_FRAME_OVERHEAD(r5)
1:
#endif /* CONFIG_SMP */
ld r4,PACACURRENT(r13)
addi r4,r4,THREAD /* Get THREAD */
li r6,1
@@ -247,11 +189,6 @@ _GLOBAL(load_up_vsx)
/* enable use of VSX after return */
oris r12,r12,MSR_VSX@h
std r12,_MSR(r1)
#ifndef CONFIG_SMP
/* Update last_task_used_vsx to 'current' */
ld r4,PACACURRENT(r13)
std r4,0(r3)
#endif /* CONFIG_SMP */
b fast_exception_return
/*
@@ -277,11 +214,6 @@ _GLOBAL(__giveup_vsx)
andc r4,r4,r3 /* disable VSX for previous task */
std r4,_MSR-STACK_FRAME_OVERHEAD(r5)
1:
#ifndef CONFIG_SMP
li r5,0
ld r4,last_task_used_vsx@got(r2)
std r5,0(r4)
#endif /* CONFIG_SMP */
blr
#endif /* CONFIG_VSX */