diff options
| -rw-r--r-- | arch/x86/include/asm/fpu/internal.h | 3 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 52 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/init.c | 13 | ||||
| -rw-r--r-- | arch/x86/kernel/traps.c | 3 |
4 files changed, 35 insertions, 36 deletions
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index c2e46eb96b6d..a2124343edf5 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -590,7 +590,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) * If the task has used the math, pre-load the FPU on xsave processors * or if the past 5 consecutive context-switches used math. */ - fpu.preload = new_fpu->fpstate_active && + fpu.preload = static_cpu_has(X86_FEATURE_FPU) && + new_fpu->fpstate_active && (use_eager_fpu() || new_fpu->counter > 5); if (old_fpu->fpregs_active) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d5804adfa6da..0b1b9abd4d5f 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -114,6 +114,10 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); if (fpu->fpregs_active) { + /* + * Ignore return value -- we don't care if reg state + * is clobbered. + */ copy_fpregs_to_fpstate(fpu); } else { this_cpu_write(fpu_fpregs_owner_ctx, NULL); @@ -189,8 +193,12 @@ void fpu__save(struct fpu *fpu) preempt_disable(); if (fpu->fpregs_active) { - if (!copy_fpregs_to_fpstate(fpu)) - fpregs_deactivate(fpu); + if (!copy_fpregs_to_fpstate(fpu)) { + if (use_eager_fpu()) + copy_kernel_to_fpregs(&fpu->state); + else + fpregs_deactivate(fpu); + } } preempt_enable(); } @@ -223,14 +231,15 @@ void fpstate_init(union fpregs_state *state) } EXPORT_SYMBOL_GPL(fpstate_init); -/* - * Copy the current task's FPU state to a new task's FPU context. - * - * In both the 'eager' and the 'lazy' case we save hardware registers - * directly to the destination buffer. - */ -static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) +int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { + dst_fpu->counter = 0; + dst_fpu->fpregs_active = 0; + dst_fpu->last_cpu = -1; + + if (!src_fpu->fpstate_active || !cpu_has_fpu) + return 0; + WARN_ON_FPU(src_fpu != ¤t->thread.fpu); /* @@ -243,10 +252,9 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * - * If the FPU context got destroyed in the process (FNSAVE - * done on old CPUs) then copy it back into the source - * context and mark the current task for lazy restore. + * In lazy mode, if the FPU context isn't loaded into + * fpregs, CR0.TS will be set and do_device_not_available + * will load the FPU context. * * We have to do all this with preemption disabled, * mostly because of the FNSAVE case, because in that @@ -259,19 +267,13 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { memcpy(&src_fpu->state, &dst_fpu->state, xstate_size); - fpregs_deactivate(src_fpu); + + if (use_eager_fpu()) + copy_kernel_to_fpregs(&src_fpu->state); + else + fpregs_deactivate(src_fpu); } preempt_enable(); -} - -int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) -{ - dst_fpu->counter = 0; - dst_fpu->fpregs_active = 0; - dst_fpu->last_cpu = -1; - - if (src_fpu->fpstate_active && cpu_has_fpu) - fpu_copy(dst_fpu, src_fpu); return 0; } @@ -425,7 +427,7 @@ void fpu__clear(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ - if (!use_eager_fpu()) { + if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) { /* FPU state will be reallocated lazily at the first use. */ fpu__drop(fpu); } else { diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index bd08fb77073d..54c86fffbf9f 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -262,7 +262,10 @@ static void __init fpu__init_system_xstate_size_legacy(void) * not only saved the restores along the way, but we also have the * FPU ready to be used for the original task. * - * 'eager' switching is used on modern CPUs, there we switch the FPU + * 'lazy' is deprecated because it's almost never a performance win + * and it's much more complicated than 'eager'. + * + * 'eager' switching is by default on all CPUs, there we switch the FPU * state during every context switch, regardless of whether the task * has used FPU instructions in that time slice or not. This is done * because modern FPU context saving instructions are able to optimize @@ -273,7 +276,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) * to use 'eager' restores, if we detect that a task is using the FPU * frequently. See the fpu->counter logic in fpu/internal.h for that. ] */ -static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; +static enum { ENABLE, DISABLE } eagerfpu = ENABLE; /* * Find supported xfeatures based on cpu features and command-line input. @@ -344,15 +347,9 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { - /* - * No need to check "eagerfpu=auto" again, since it is the - * initial default. - */ if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) { eagerfpu = DISABLE; fpu__clear_eager_fpu_features(); - } else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) { - eagerfpu = ENABLE; } if (cmdline_find_option_bool(boot_command_line, "no387")) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 5c9ca2bb9fe9..06cbe25861f1 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -792,10 +792,9 @@ dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION - if (read_cr0() & X86_CR0_EM) { + if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) { struct math_emu_info info = { }; cond_local_irq_enable(regs); |