powerpc: Move VMX and VSX asm code to vector.S
Currently, load_up_altivec and give_up_altivec are duplicated
in 32-bit and 64-bit. This creates a common implementation that
is moved away from head_32.S, head_64.S and misc_64.S and into
vector.S, using the same macros we already use for our common
implementation of load_up_fpu.
I also moved the VSX code over to vector.S though in that case
I didn't make it build on 32-bit (yet).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 49ac3d6..ef36cbbc 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -1,5 +1,215 @@
+#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/reg.h>
+#include <asm/asm-offsets.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+
+/*
+ * load_up_altivec(unused, unused, tsk)
+ * Disable VMX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Enables the VMX for use in the kernel on return.
+ * On SMP we know the VMX is free, since we give it up every
+ * switch (ie, no lazy save of the vector registers).
+ */
+_GLOBAL(load_up_altivec)
+ mfmsr r5 /* grab the current MSR */
+ oris r5,r5,MSR_VEC@h
+ 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
+ SAVE_32VRS(0,r5,r4)
+ mfvscr vr0
+ li r10,THREAD_VSCR
+ stvx vr0,r10,r4
+ /* 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
+ * all 1's
+ */
+ mfspr r4,SPRN_VRSAVE
+ cmpdi 0,r4,0
+ bne+ 1f
+ li r4,-1
+ mtspr SPRN_VRSAVE,r4
+1:
+ /* enable use of VMX after return */
+#ifdef CONFIG_PPC32
+ mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */
+ oris r9,r9,MSR_VEC@h
+#else
+ ld r4,PACACURRENT(r13)
+ addi r5,r4,THREAD /* Get THREAD */
+ oris r12,r12,MSR_VEC@h
+ std r12,_MSR(r1)
+#endif
+ li r4,1
+ li r10,THREAD_VSCR
+ stw r4,THREAD_USED_VR(r5)
+ lvx vr0,r10,r5
+ mtvscr vr0
+ REST_32VRS(0,r4,r5)
+#ifndef CONFIG_SMP
+ /* Update last_task_used_math to 'current' */
+ subi r4,r5,THREAD /* Back to 'current' */
+ fromreal(r4)
+ PPC_STL r4,ADDROFF(last_task_used_math)(r3)
+#endif /* CONFIG_SMP */
+ /* restore registers and return */
+ blr
+
+/*
+ * giveup_altivec(tsk)
+ * Disable VMX for the task given as the argument,
+ * and save the vector registers in its thread_struct.
+ * Enables the VMX for use in the kernel on return.
+ */
+_GLOBAL(giveup_altivec)
+ mfmsr r5
+ oris r5,r5,MSR_VEC@h
+ SYNC
+ MTMSRD(r5) /* enable use of VMX now */
+ isync
+ PPC_LCMPI 0,r3,0
+ beqlr- /* if no previous owner, done */
+ addi r3,r3,THREAD /* want THREAD of task */
+ PPC_LL r5,PT_REGS(r3)
+ PPC_LCMPI 0,r5,0
+ SAVE_32VRS(0,r4,r3)
+ mfvscr vr0
+ li r4,THREAD_VSCR
+ stvx vr0,r4,r3
+ beq 1f
+ PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ lis r3,(MSR_VEC|MSR_VSX)@h
+FTR_SECTION_ELSE
+ lis r3,MSR_VEC@h
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
+#else
+ lis r3,MSR_VEC@h
+#endif
+ 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
+
+#ifdef CONFIG_PPC32
+#error This asm code isn't ready for 32-bit kernels
+#endif
+
+/*
+ * load_up_vsx(unused, unused, tsk)
+ * Disable VSX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Reuse the fp and vsx saves, but first check to see if they have
+ * been saved already.
+ */
+_GLOBAL(load_up_vsx)
+/* Load FP and VSX registers if they haven't been done yet */
+ andi. r5,r12,MSR_FP
+ beql+ load_up_fpu /* skip if already loaded */
+ 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
+ stw r6,THREAD_USED_VSR(r4) /* ... also set thread used vsr */
+ /* enable use of VSX after return */
+ oris r12,r12,MSR_VSX@h
+ std r12,_MSR(r1)
+#ifndef CONFIG_SMP
+ /* Update last_task_used_math to 'current' */
+ ld r4,PACACURRENT(r13)
+ std r4,0(r3)
+#endif /* CONFIG_SMP */
+ b fast_exception_return
+
+/*
+ * __giveup_vsx(tsk)
+ * Disable VSX for the task given as the argument.
+ * Does NOT save vsx registers.
+ * Enables the VSX for use in the kernel on return.
+ */
+_GLOBAL(__giveup_vsx)
+ mfmsr r5
+ oris r5,r5,MSR_VSX@h
+ mtmsrd r5 /* enable use of VSX now */
+ isync
+
+ cmpdi 0,r3,0
+ beqlr- /* if no previous owner, done */
+ addi r3,r3,THREAD /* want THREAD of task */
+ ld r5,PT_REGS(r3)
+ cmpdi 0,r5,0
+ beq 1f
+ ld r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ lis r3,MSR_VSX@h
+ 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 */
+
/*
* The routines below are in assembler so we can closely control the