From cf5c2e543c7b4a5ec49f547070c0f3f4c95e20ed Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Wed, 10 Jul 2013 09:43:42 +0800 Subject: powerpc/math-emu: Remove the dead code in math.c The math.c is only built when CONFIG_MATH_EMULATION is enabled. So we would never get into the case that CONFIG_MATH_EMULATION is not defined in this file. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/math-emu/math.c | 42 ------------------------------------------ 1 file changed, 42 deletions(-) (limited to 'arch/powerpc/math-emu/math.c') diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c index 0328e66e079..cefb4f2f403 100644 --- a/arch/powerpc/math-emu/math.c +++ b/arch/powerpc/math-emu/math.c @@ -231,47 +231,6 @@ do_mathemu(struct pt_regs *regs) if (get_user(insn, (u32 *)pc)) return -EFAULT; -#ifndef CONFIG_MATH_EMULATION - switch (insn >> 26) { - case LFD: - idx = (insn >> 16) & 0x1f; - sdisp = (insn & 0xffff); - op0 = (void *)¤t->thread.TS_FPR((insn >> 21) & 0x1f); - op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp); - lfd(op0, op1, op2, op3); - break; - case LFDU: - idx = (insn >> 16) & 0x1f; - sdisp = (insn & 0xffff); - op0 = (void *)¤t->thread.TS_FPR((insn >> 21) & 0x1f); - op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp); - lfd(op0, op1, op2, op3); - regs->gpr[idx] = (unsigned long)op1; - break; - case STFD: - idx = (insn >> 16) & 0x1f; - sdisp = (insn & 0xffff); - op0 = (void *)¤t->thread.TS_FPR((insn >> 21) & 0x1f); - op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp); - stfd(op0, op1, op2, op3); - break; - case STFDU: - idx = (insn >> 16) & 0x1f; - sdisp = (insn & 0xffff); - op0 = (void *)¤t->thread.TS_FPR((insn >> 21) & 0x1f); - op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp); - stfd(op0, op1, op2, op3); - regs->gpr[idx] = (unsigned long)op1; - break; - case OP63: - op0 = (void *)¤t->thread.TS_FPR((insn >> 21) & 0x1f); - op1 = (void *)¤t->thread.TS_FPR((insn >> 11) & 0x1f); - fmr(op0, op1, op2, op3); - break; - default: - goto illegal; - } -#else /* CONFIG_MATH_EMULATION */ switch (insn >> 26) { case LFS: func = lfs; type = D; break; case LFSU: func = lfs; type = DU; break; @@ -485,7 +444,6 @@ do_mathemu(struct pt_regs *regs) default: break; } -#endif /* CONFIG_MATH_EMULATION */ regs->nip += 4; return 0; -- cgit v1.2.3-70-g09d2 From f0870c55301da7e27be53d65dc62020a0fba749a Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Wed, 10 Jul 2013 09:43:43 +0800 Subject: powerpc/math-emu: Remove the unneeded check for CONFIG_MATH_EMULATION in math.c The math.c is only built when CONFIG_MATH_EMULATION is enabled. So the #ifdef check for CONFIG_MATH_EMULATION in it seems redundant. Drop all of them. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/math-emu/math.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/powerpc/math-emu/math.c') diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c index cefb4f2f403..3fe8e35287a 100644 --- a/arch/powerpc/math-emu/math.c +++ b/arch/powerpc/math-emu/math.c @@ -154,7 +154,6 @@ FLOATFUNC(fsqrts); #define XEU 15 #define XFLB 10 -#ifdef CONFIG_MATH_EMULATION static int record_exception(struct pt_regs *regs, int eflag) { @@ -212,7 +211,6 @@ record_exception(struct pt_regs *regs, int eflag) return (fpscr & FPSCR_FEX) ? 1 : 0; } -#endif /* CONFIG_MATH_EMULATION */ int do_mathemu(struct pt_regs *regs) @@ -222,11 +220,9 @@ do_mathemu(struct pt_regs *regs) signed short sdisp; u32 insn = 0; int idx = 0; -#ifdef CONFIG_MATH_EMULATION int (*func)(void *, void *, void *, void *); int type = 0; int eflag, trap; -#endif if (get_user(insn, (u32 *)pc)) return -EFAULT; -- cgit v1.2.3-70-g09d2 From 6761ee3d7e139ec8728e1515bfc5fdcaf3be317e Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Sun, 14 Jul 2013 16:40:06 +0800 Subject: powerpc/math-emu: Move the flush FPU state function into do_mathemu By doing this we can make sure that the FPU state is only flushed to the thread struct when it is really needed. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/traps.c | 9 --------- arch/powerpc/math-emu/math.c | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/math-emu/math.c') diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index f58eaf23e8f..82df498069b 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1134,15 +1134,6 @@ void __kprobes program_check_exception(struct pt_regs *regs) * instruction or only on FP instructions, whether there is a * pattern to occurrences etc. -dgibson 31/Mar/2003 */ - - /* - * If we support a HW FPU, we need to ensure the FP state - * if flushed into the thread_struct before attempting - * emulation - */ -#ifdef CONFIG_PPC_FPU - flush_fp_to_thread(current); -#endif switch (do_mathemu(regs)) { case 0: emulate_single_step(regs); diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c index 3fe8e35287a..f9ef34746f1 100644 --- a/arch/powerpc/math-emu/math.c +++ b/arch/powerpc/math-emu/math.c @@ -420,6 +420,15 @@ do_mathemu(struct pt_regs *regs) goto illegal; } + /* + * If we support a HW FPU, we need to ensure the FP state + * is flushed into the thread_struct before attempting + * emulation + */ +#ifdef CONFIG_PPC_FPU + flush_fp_to_thread(current); +#endif + eflag = func(op0, op1, op2, op3); if (insn & 1) { -- cgit v1.2.3-70-g09d2 From e05c0e81b0628808a7490c35d1803644a18b0405 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 16 Jul 2013 19:57:15 +0800 Subject: powerpc: split She math emulation into two parts For some SoC (such as the FSL BookE) even though there does have a hardware FPU, but not all floating point instructions are implemented. Unfortunately some versions of gcc do use these unimplemented instructions. Then we have to enable the math emulation to workaround this issue. It seems a little redundant to have the support to emulate all the floating point instructions in this case. So split the math emulation into two parts. One is for the SoC which doesn't have FPU at all and the other for the SoC which does have the hardware FPU and only need some special floating point instructions to be emulated. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/Kconfig | 20 ++++++++++++++++++++ arch/powerpc/math-emu/Makefile | 24 ++++++++++++------------ arch/powerpc/math-emu/math.c | 20 ++++++++++++++------ 3 files changed, 46 insertions(+), 18 deletions(-) (limited to 'arch/powerpc/math-emu/math.c') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3bf72cd2c8f..7205989b9b5 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -312,6 +312,26 @@ config MATH_EMULATION such as fsqrt on cores that do have an FPU but do not implement them (such as Freescale BookE). +choice + prompt "Math emulation options" + default MATH_EMULATION_FULL + depends on MATH_EMULATION + +config MATH_EMULATION_FULL + bool "Emulate all the floating point instructions" + ---help--- + Select this option will enable the kernel to support to emulate + all the floating point instructions. If your SoC doesn't have + a FPU, you should select this. + +config MATH_EMULATION_HW_UNIMPLEMENTED + bool "Just emulate the FPU unimplemented instructions" + ---help--- + Select this if you know there does have a hardware FPU on your + SoC, but some floating point instructions are not implemented by that. + +endchoice + config PPC_TRANSACTIONAL_MEM bool "Transactional Memory support for POWERPC" depends on PPC_BOOK3S_64 diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile index 8d035d2d42a..1b46ab4f641 100644 --- a/arch/powerpc/math-emu/Makefile +++ b/arch/powerpc/math-emu/Makefile @@ -1,15 +1,15 @@ - -obj-$(CONFIG_MATH_EMULATION) += fabs.o fadd.o fadds.o fcmpo.o fcmpu.o \ - fctiw.o fctiwz.o fdiv.o fdivs.o \ - fmadd.o fmadds.o fmsub.o fmsubs.o \ - fmul.o fmuls.o fnabs.o fneg.o \ - fnmadd.o fnmadds.o fnmsub.o fnmsubs.o \ - fres.o fre.o frsp.o fsel.o lfs.o \ - frsqrte.o frsqrtes.o \ - fsqrt.o fsqrts.o fsub.o fsubs.o \ - mcrfs.o mffs.o mtfsb0.o mtfsb1.o \ - mtfsf.o mtfsfi.o stfiwx.o stfs.o \ - math.o fmr.o lfd.o stfd.o +math-emu-common-objs = math.o fre.o fsqrt.o fsqrts.o frsqrtes.o mtfsf.o mtfsfi.o +obj-$(CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED) += $(math-emu-common-objs) +obj-$(CONFIG_MATH_EMULATION_FULL) += $(math-emu-common-objs) fabs.o fadd.o \ + fadds.o fcmpo.o fcmpu.o fctiw.o \ + fctiwz.o fdiv.o fdivs.o fmadd.o \ + fmadds.o fmsub.o fmsubs.o fmul.o \ + fmuls.o fnabs.o fneg.o fnmadd.o \ + fnmadds.o fnmsub.o fnmsubs.o fres.o \ + frsp.o fsel.o lfs.o frsqrte.o fsub.o \ + fsubs.o mcrfs.o mffs.o mtfsb0.o \ + mtfsb1.o stfiwx.o stfs.o math.o \ + fmr.o lfd.o stfd.o obj-$(CONFIG_SPE) += math_efp.o diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c index f9ef34746f1..49eb2ac08fd 100644 --- a/arch/powerpc/math-emu/math.c +++ b/arch/powerpc/math-emu/math.c @@ -13,6 +13,20 @@ #define FLOATFUNC(x) extern int x(void *, void *, void *, void *) +/* The instructions list which may be not implemented by a hardware FPU */ +FLOATFUNC(fre); +FLOATFUNC(frsqrtes); +FLOATFUNC(fsqrt); +FLOATFUNC(fsqrts); +FLOATFUNC(mtfsf); +FLOATFUNC(mtfsfi); + +#ifdef CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED +#undef FLOATFUNC(x) +#define FLOATFUNC(x) static inline int x(void *op1, void *op2, void *op3, \ + void *op4) { } +#endif + FLOATFUNC(fadd); FLOATFUNC(fadds); FLOATFUNC(fdiv); @@ -42,8 +56,6 @@ FLOATFUNC(mcrfs); FLOATFUNC(mffs); FLOATFUNC(mtfsb0); FLOATFUNC(mtfsb1); -FLOATFUNC(mtfsf); -FLOATFUNC(mtfsfi); FLOATFUNC(lfd); FLOATFUNC(lfs); @@ -58,13 +70,9 @@ FLOATFUNC(fnabs); FLOATFUNC(fneg); /* Optional */ -FLOATFUNC(fre); FLOATFUNC(fres); FLOATFUNC(frsqrte); -FLOATFUNC(frsqrtes); FLOATFUNC(fsel); -FLOATFUNC(fsqrt); -FLOATFUNC(fsqrts); #define OP31 0x1f /* 31 */ -- cgit v1.2.3-70-g09d2 From 037f0eed57c3f35367ac32275e45f24e297549e9 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Sun, 14 Jul 2013 17:02:05 +0800 Subject: powerpc: Make flush_fp_to_thread() nop when CONFIG_PPC_FPU is disabled In the current kernel, the function flush_fp_to_thread() is not dependent on CONFIG_PPC_FPU. So most invocations of this function is not wrapped by CONFIG_PPC_FPU. Even through we don't really save the FPRs to the thread struct if CONFIG_PPC_FPU is not enabled, but there does have some runtime overhead such as the check for tsk->thread.regs and preempt disable and enable. It really make no sense to do that. So make it a nop when CONFIG_PPC_FPU is disabled. Also remove the wrapped #ifdef CONFIG_PPC_FPU when invoking this function. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/switch_to.h | 7 ++++++- arch/powerpc/kernel/process.c | 2 ++ arch/powerpc/math-emu/math.c | 3 +-- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/math-emu/math.c') diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 33e1cd82358..39cf0f6cc37 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -19,7 +19,6 @@ extern struct task_struct *_switch(struct thread_struct *prev, extern void giveup_fpu(struct task_struct *); extern void load_up_fpu(void); extern void enable_kernel_fp(void); -extern void flush_fp_to_thread(struct task_struct *); extern void enable_kernel_altivec(void); extern void load_up_altivec(struct task_struct *); extern int emulate_altivec(struct pt_regs *); @@ -37,6 +36,12 @@ static inline void discard_lazy_cpu_state(void) } #endif +#ifdef CONFIG_PPC_FPU +extern void flush_fp_to_thread(struct task_struct *); +#else +static inline void flush_fp_to_thread(struct task_struct *t) { } +#endif + #ifdef CONFIG_ALTIVEC extern void flush_altivec_to_thread(struct task_struct *); extern void giveup_altivec(struct task_struct *); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index c517dbe705f..0ec255a81c6 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -74,6 +74,7 @@ struct task_struct *last_task_used_vsx = NULL; struct task_struct *last_task_used_spe = NULL; #endif +#ifdef CONFIG_PPC_FPU /* * Make sure the floating-point register state in the * the thread_struct is up to date for task tsk. @@ -107,6 +108,7 @@ void flush_fp_to_thread(struct task_struct *tsk) } } EXPORT_SYMBOL_GPL(flush_fp_to_thread); +#endif void enable_kernel_fp(void) { diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c index 49eb2ac08fd..bc901623d8d 100644 --- a/arch/powerpc/math-emu/math.c +++ b/arch/powerpc/math-emu/math.c @@ -7,6 +7,7 @@ #include #include +#include #include #include @@ -433,9 +434,7 @@ do_mathemu(struct pt_regs *regs) * is flushed into the thread_struct before attempting * emulation */ -#ifdef CONFIG_PPC_FPU flush_fp_to_thread(current); -#endif eflag = func(op0, op1, op2, op3); -- cgit v1.2.3-70-g09d2 From cc7059b5ea730edde256deb94a42f8e9e732d9b8 Mon Sep 17 00:00:00 2001 From: James Yang Date: Thu, 4 Jul 2013 16:18:44 -0500 Subject: powerpc/math-emu: Fix load/store indexed emulation Load/store indexed instructions where the index register RA=R0, such as "lfdx f1,0,r3", are not illegal. Load/store indexed with update instructions where the index register RA=R0, such as "lfdux f1,0,r3", are invalid, and, to be consistent with existing math-emu behavior for other invalid instruction forms, will signal as illegal. Signed-off-by: James Yang Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/math-emu/math.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/math-emu/math.c') diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c index bc901623d8d..ab151f04050 100644 --- a/arch/powerpc/math-emu/math.c +++ b/arch/powerpc/math-emu/math.c @@ -380,21 +380,16 @@ do_mathemu(struct pt_regs *regs) case XE: idx = (insn >> 16) & 0x1f; op0 = (void *)¤t->thread.TS_FPR((insn >> 21) & 0x1f); - if (!idx) { - if (((insn >> 1) & 0x3ff) == STFIWX) - op1 = (void *)(regs->gpr[(insn >> 11) & 0x1f]); - else - goto illegal; - } else { - op1 = (void *)(regs->gpr[idx] + regs->gpr[(insn >> 11) & 0x1f]); - } - + op1 = (void *)((idx ? regs->gpr[idx] : 0) + + regs->gpr[(insn >> 11) & 0x1f]); break; case XEU: idx = (insn >> 16) & 0x1f; + if (!idx) + goto illegal; op0 = (void *)¤t->thread.TS_FPR((insn >> 21) & 0x1f); - op1 = (void *)((idx ? regs->gpr[idx] : 0) + op1 = (void *)(regs->gpr[idx] + regs->gpr[(insn >> 11) & 0x1f]); break; -- cgit v1.2.3-70-g09d2