diff options
Diffstat (limited to 'arch/powerpc/kernel/fpu.S')
| -rw-r--r-- | arch/powerpc/kernel/fpu.S | 143 |
1 files changed, 124 insertions, 19 deletions
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 821e152e093..9ad236e5d2c 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -23,6 +23,98 @@ #include <asm/thread_info.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/ptrace.h> + +#ifdef CONFIG_VSX +#define __REST_32FPVSRS(n,c,base) \ +BEGIN_FTR_SECTION \ + b 2f; \ +END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ + REST_32FPRS(n,base); \ + b 3f; \ +2: REST_32VSRS(n,c,base); \ +3: + +#define __SAVE_32FPVSRS(n,c,base) \ +BEGIN_FTR_SECTION \ + b 2f; \ +END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ + SAVE_32FPRS(n,base); \ + b 3f; \ +2: SAVE_32VSRS(n,c,base); \ +3: +#else +#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base) +#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base) +#endif +#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base) +#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base) + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +/* void do_load_up_transact_fpu(struct thread_struct *thread) + * + * This is similar to load_up_fpu but for the transactional version of the FP + * register set. It doesn't mess with the task MSR or valid flags. + * Furthermore, we don't do lazy FP with TM currently. + */ +_GLOBAL(do_load_up_transact_fpu) + mfmsr r6 + ori r5,r6,MSR_FP +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r5,r5,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + SYNC + MTMSRD(r5) + + addi r7,r3,THREAD_TRANSACT_FPSTATE + lfd fr0,FPSTATE_FPSCR(r7) + MTFSF_L(fr0) + REST_32FPVSRS(0, R4, R7) + + /* FP/VSX off again */ + MTMSRD(r6) + SYNC + + blr +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +/* + * Enable use of the FPU, and VSX if possible, for the caller. + */ +_GLOBAL(fp_enable) + mfmsr r3 + ori r3,r3,MSR_FP +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r3,r3,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + SYNC + MTMSRD(r3) + isync /* (not necessary for arch 2.02 and later) */ + blr + +/* + * Load state from memory into FP registers including FPSCR. + * Assumes the caller has enabled FP in the MSR. + */ +_GLOBAL(load_fp_state) + lfd fr0,FPSTATE_FPSCR(r3) + MTFSF_L(fr0) + REST_32FPVSRS(0, R4, R3) + blr + +/* + * Store FP state into memory, including FPSCR + * Assumes the caller has enabled FP in the MSR. + */ +_GLOBAL(store_fp_state) + SAVE_32FPVSRS(0, R4, R3) + mffs fr0 + stfd fr0,FPSTATE_FPSCR(r3) + blr /* * This task wants to use the FPU now. @@ -30,10 +122,17 @@ * and save its floating-point registers in its thread_struct. * Load up this task's FP registers from its thread_struct, * enable the FPU for the current task and return to the task. + * Note that on 32-bit this can only use registers that will be + * restored by fast_exception_return, i.e. r3 - r6, r10 and r11. */ _GLOBAL(load_up_fpu) mfmsr r5 ori r5,r5,MSR_FP +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r5,r5,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif SYNC MTMSRD(r5) /* enable use of fpu now */ isync @@ -50,9 +149,10 @@ _GLOBAL(load_up_fpu) beq 1f toreal(r4) addi r4,r4,THREAD /* want last_task_used_math->thread */ - SAVE_32FPRS(0, r4) + addi r10,r4,THREAD_FPSTATE + SAVE_32FPVSRS(0, R5, R10) mffs fr0 - stfd fr0,THREAD_FPSCR(r4) + stfd fr0,FPSTATE_FPSCR(r10) PPC_LL r5,PT_REGS(r4) toreal(r5) PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) @@ -63,7 +163,7 @@ _GLOBAL(load_up_fpu) #endif /* CONFIG_SMP */ /* enable use of FP after return */ #ifdef CONFIG_PPC32 - mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */ + mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */ lwz r4,THREAD_FPEXC_MODE(r5) ori r9,r9,MSR_FP /* enable FP for current */ or r9,r9,r4 @@ -75,9 +175,10 @@ _GLOBAL(load_up_fpu) or r12,r12,r4 std r12,_MSR(r1) #endif - lfd fr0,THREAD_FPSCR(r5) + addi r10,r5,THREAD_FPSTATE + lfd fr0,FPSTATE_FPSCR(r10) MTFSF_L(fr0) - REST_32FPRS(0, r5) + REST_32FPVSRS(0, R4, R10) #ifndef CONFIG_SMP subi r4,r5,THREAD fromreal(r4) @@ -85,7 +186,7 @@ _GLOBAL(load_up_fpu) #endif /* CONFIG_SMP */ /* restore registers and return */ /* we haven't used ctr or xer or lr */ - b fast_exception_return + blr /* * giveup_fpu(tsk) @@ -96,6 +197,11 @@ _GLOBAL(load_up_fpu) _GLOBAL(giveup_fpu) mfmsr r5 ori r5,r5,MSR_FP +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r5,r5,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif SYNC_601 ISYNC_601 MTMSRD(r5) /* enable use of fpu now */ @@ -104,14 +210,23 @@ _GLOBAL(giveup_fpu) PPC_LCMPI 0,r3,0 beqlr- /* if no previous owner, done */ addi r3,r3,THREAD /* want THREAD of task */ + PPC_LL r6,THREAD_FPSAVEAREA(r3) PPC_LL r5,PT_REGS(r3) - PPC_LCMPI 0,r5,0 - SAVE_32FPRS(0, r3) + PPC_LCMPI 0,r6,0 + bne 2f + addi r6,r3,THREAD_FPSTATE +2: PPC_LCMPI 0,r5,0 + SAVE_32FPVSRS(0, R4, R6) mffs fr0 - stfd fr0,THREAD_FPSCR(r3) + stfd fr0,FPSTATE_FPSCR(r6) beq 1f PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) li r3,MSR_FP|MSR_FE0|MSR_FE1 +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + oris r3,r3,MSR_VSX@h +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif andc r4,r4,r3 /* disable FP for previous task */ PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) 1: @@ -125,24 +240,14 @@ _GLOBAL(giveup_fpu) /* * These are used in the alignment trap handler when emulating * single-precision loads and stores. - * We restore and save the fpscr so the task gets the same result - * and exceptions as if the cpu had performed the load or store. */ _GLOBAL(cvt_fd) - lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ - MTFSF_L(0) lfs 0,0(r3) stfd 0,0(r4) - mffs 0 - stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */ blr _GLOBAL(cvt_df) - lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ - MTFSF_L(0) lfd 0,0(r3) stfs 0,0(r4) - mffs 0 - stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */ blr |