diff options
| -rw-r--r-- | arch/x86/include/asm/fpu/internal.h | 18 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 54 |
2 files changed, 34 insertions, 38 deletions
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 559dd3018fd4..3e0eedaacdac 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -83,6 +83,7 @@ extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif +extern void save_fpregs_to_fpstate(struct fpu *fpu); #define user_insn(insn, output, input...) \ ({ \ @@ -375,8 +376,6 @@ static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask) return err; } -extern int save_fpregs_to_fpstate(struct fpu *fpu); - static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { @@ -507,12 +506,17 @@ static inline void __fpregs_load_activate(void) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (static_cpu_has(X86_FEATURE_FPU) && !(current->flags & PF_KTHREAD)) { - if (!save_fpregs_to_fpstate(old_fpu)) - old_fpu->last_cpu = -1; - else - old_fpu->last_cpu = cpu; + save_fpregs_to_fpstate(old_fpu); + /* + * The save operation preserved register state, so the + * fpu_fpregs_owner_ctx is still @old_fpu. Store the + * current CPU number in @old_fpu, so the next return + * to user space can avoid the FPU register restore + * when is returns on the same CPU and still owns the + * context. + */ + old_fpu->last_cpu = cpu; - /* But leave fpu_fpregs_owner_ctx! */ trace_x86_fpu_regs_deactivated(old_fpu); } } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index dcf4d6b58180..c290ba27ffef 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -83,16 +83,20 @@ bool irq_fpu_usable(void) EXPORT_SYMBOL(irq_fpu_usable); /* - * These must be called with preempt disabled. Returns - * 'true' if the FPU state is still intact and we can - * keep registers active. + * Save the FPU register state in fpu->state. The register state is + * preserved. * - * The legacy FNSAVE instruction cleared all FPU state - * unconditionally, so registers are essentially destroyed. - * Modern FPU state can be kept in registers, if there are - * no pending FP exceptions. + * Must be called with fpregs_lock() held. + * + * The legacy FNSAVE instruction clears all FPU state unconditionally, so + * register state has to be reloaded. That might be a pointless exercise + * when the FPU is going to be used by another task right after that. But + * this only affects 20+ years old 32bit systems and avoids conditionals all + * over the place. + * + * FXSAVE and all XSAVE variants preserve the FPU register state. */ -int save_fpregs_to_fpstate(struct fpu *fpu) +void save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { os_xsave(&fpu->state.xsave); @@ -103,21 +107,20 @@ int save_fpregs_to_fpstate(struct fpu *fpu) */ if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; - return 1; + return; } if (likely(use_fxsr())) { fxsave(&fpu->state.fxsave); - return 1; + return; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, - * so we have to mark them inactive: + * so we have to reload them from the memory state. */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); - - return 0; + frstor(&fpu->state.fsave); } EXPORT_SYMBOL(save_fpregs_to_fpstate); @@ -133,10 +136,6 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) if (!(current->flags & PF_KTHREAD) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); - /* - * Ignore return value -- we don't care if reg state - * is clobbered. - */ save_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); @@ -171,11 +170,8 @@ void fpu__save(struct fpu *fpu) fpregs_lock(); trace_x86_fpu_before_save(fpu); - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { - if (!save_fpregs_to_fpstate(fpu)) { - copy_kernel_to_fpregs(&fpu->state); - } - } + if (!test_thread_flag(TIF_NEED_FPU_LOAD)) + save_fpregs_to_fpstate(fpu); trace_x86_fpu_after_save(fpu); fpregs_unlock(); @@ -244,20 +240,16 @@ int fpu__copy(struct task_struct *dst, struct task_struct *src) memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* - * If the FPU registers are not current just memcpy() the state. - * Otherwise save current FPU registers directly into the child's FPU - * context, without any memory-to-memory copying. - * - * ( The function 'fails' in the FNSAVE case, which destroys - * register contents so we have to load them back. ) + * If the FPU registers are not owned by current just memcpy() the + * state. Otherwise save the FPU registers directly into the + * child's FPU context, without any memory-to-memory copying. */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); - else if (!save_fpregs_to_fpstate(dst_fpu)) - copy_kernel_to_fpregs(&dst_fpu->state); - + else + save_fpregs_to_fpstate(dst_fpu); fpregs_unlock(); set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); |