diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index fc14a38c7ccf..91441d9cbaae 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -256,6 +256,8 @@ struct thread_struct { unsigned long evr[32]; /* upper 32-bits of SPE regs */ u64 acc; /* Accumulator */ unsigned long spefscr; /* SPE & eFP status */ + unsigned long spefscr_last; /* SPEFSCR value on last prctl + call or trap return */ int used_spe; /* set if process has used spe */ #endif /* CONFIG_SPE */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -317,7 +319,9 @@ struct thread_struct { (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack) #ifdef CONFIG_SPE -#define SPEFSCR_INIT .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, +#define SPEFSCR_INIT \ + .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, \ + .spefscr_last = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, #else #define SPEFSCR_INIT #endif diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3386d8ab7eb0..b08c0d03530f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1175,6 +1175,19 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) if (val & PR_FP_EXC_SW_ENABLE) { #ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); tsk->thread.fpexc_mode = val & (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); return 0; @@ -1206,9 +1219,22 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) #ifdef CONFIG_SPE - if (cpu_has_feature(CPU_FTR_SPE)) + if (cpu_has_feature(CPU_FTR_SPE)) { + /* + * When the sticky exception bits are set + * directly by userspace, it must call prctl + * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE + * in the existing prctl settings) or + * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in + * the bits being set). functions + * saving and restoring the whole + * floating-point environment need to do so + * anyway to restore the prctl settings from + * the saved environment. + */ + tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); val = tsk->thread.fpexc_mode; - else + } else return -EINVAL; #else return -EINVAL; diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c index a73f0884d358..59835c625dc6 100644 --- a/arch/powerpc/math-emu/math_efp.c +++ b/arch/powerpc/math-emu/math_efp.c @@ -630,9 +630,27 @@ int do_spe_mathemu(struct pt_regs *regs) regs->ccr |= (IR << ((7 - ((speinsn >> 23) & 0x7)) << 2)); update_regs: - __FPU_FPSCR &= ~FP_EX_MASK; + /* + * If the "invalid" exception sticky bit was set by the + * processor for non-finite input, but was not set before the + * instruction being emulated, clear it. Likewise for the + * "underflow" bit, which may have been set by the processor + * for exact underflow, not just inexact underflow when the + * flag should be set for IEEE 754 semantics. Other sticky + * exceptions will only be set by the processor when they are + * correct according to IEEE 754 semantics, and we must not + * clear sticky bits that were already set before the emulated + * instruction as they represent the user-visible sticky + * exception status. "inexact" traps to kernel are not + * required for IEEE semantics and are not enabled by default, + * so the "inexact" sticky bit may have been set by a previous + * instruction without the kernel being aware of it. + */ + __FPU_FPSCR + &= ~(FP_EX_INVALID | FP_EX_UNDERFLOW) | current->thread.spefscr_last; __FPU_FPSCR |= (FP_CUR_EXCEPTIONS & FP_EX_MASK); mtspr(SPRN_SPEFSCR, __FPU_FPSCR); + current->thread.spefscr_last = __FPU_FPSCR; current->thread.evr[fc] = vc.wp[0]; regs->gpr[fc] = vc.wp[1];