diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/crypto/crc32c-intel_glue.c | 22 | ||||
| -rw-r--r-- | arch/x86/include/asm/cpufeatures.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/internal.h | 139 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/types.h | 11 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/xstate.h | 17 | ||||
| -rw-r--r-- | arch/x86/include/asm/trace/fpu.h | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 47 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/init.c | 91 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/signal.c | 8 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/xstate.c | 9 | ||||
| -rw-r--r-- | arch/x86/kernel/process_32.c | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/process_64.c | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/smpboot.c | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/cpuid.c | 4 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 14 |
15 files changed, 75 insertions, 306 deletions
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 0857b1a1de3b..c194d5717ae5 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -48,26 +48,13 @@ #ifdef CONFIG_X86_64 /* * use carryless multiply version of crc32c when buffer - * size is >= 512 (when eager fpu is enabled) or - * >= 1024 (when eager fpu is disabled) to account + * size is >= 512 to account * for fpu state save/restore overhead. */ -#define CRC32C_PCL_BREAKEVEN_EAGERFPU 512 -#define CRC32C_PCL_BREAKEVEN_NOEAGERFPU 1024 +#define CRC32C_PCL_BREAKEVEN 512 asmlinkage unsigned int crc_pcl(const u8 *buffer, int len, unsigned int crc_init); -static int crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_EAGERFPU; -#if defined(X86_FEATURE_EAGER_FPU) -#define set_pcl_breakeven_point() \ -do { \ - if (!use_eager_fpu()) \ - crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU; \ -} while (0) -#else -#define set_pcl_breakeven_point() \ - (crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU) -#endif #endif /* CONFIG_X86_64 */ static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length) @@ -190,7 +177,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data, * use faster PCL version if datasize is large enough to * overcome kernel fpu state save/restore overhead */ - if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) { + if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) { kernel_fpu_begin(); *crcp = crc_pcl(data, len, *crcp); kernel_fpu_end(); @@ -202,7 +189,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data, static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out) { - if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) { + if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) { kernel_fpu_begin(); *(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp)); kernel_fpu_end(); @@ -261,7 +248,6 @@ static int __init crc32c_intel_mod_init(void) alg.update = crc32c_pcl_intel_update; alg.finup = crc32c_pcl_intel_finup; alg.digest = crc32c_pcl_intel_digest; - set_pcl_breakeven_point(); } #endif return crypto_register_shash(&alg); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1188bc849ee3..b212b862314a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -104,7 +104,7 @@ #define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ #define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ -#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */ +/* free, was #define X86_FEATURE_EAGER_FPU ( 3*32+29) * "eagerfpu" Non lazy FPU restore */ #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 2737366ea583..d4a684997497 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -60,11 +60,6 @@ extern u64 fpu__get_supported_xfeatures_mask(void); /* * FPU related CPU feature flag helper routines: */ -static __always_inline __pure bool use_eager_fpu(void) -{ - return static_cpu_has(X86_FEATURE_EAGER_FPU); -} - static __always_inline __pure bool use_xsaveopt(void) { return static_cpu_has(X86_FEATURE_XSAVEOPT); @@ -484,42 +479,42 @@ extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size) DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* - * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx, - * on this CPU. + * The in-register FPU state for an FPU context on a CPU is assumed to be + * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx + * matches the FPU. * - * This will disable any lazy FPU state restore of the current FPU state, - * but if the current thread owns the FPU, it will still be saved by. + * If the FPU register state is valid, the kernel can skip restoring the + * FPU state from memory. + * + * Any code that clobbers the FPU registers or updates the in-memory + * FPU state for a task MUST let the rest of the kernel know that the + * FPU registers are no longer valid for this task. + * + * Either one of these invalidation functions is enough. Invalidate + * a resource you control: CPU if using the CPU for something else + * (with preemption disabled), FPU for the current task, or a task that + * is prevented from running by the current task. */ -static inline void __cpu_disable_lazy_restore(unsigned int cpu) +static inline void __cpu_invalidate_fpregs_state(void) { - per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL; + __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } -static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu) -{ - return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; -} - - -/* - * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation' - * idiom, which is then paired with the sw-flag (fpregs_active) later on: - */ - -static inline void __fpregs_activate_hw(void) +static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { - if (!use_eager_fpu()) - clts(); + fpu->last_cpu = -1; } -static inline void __fpregs_deactivate_hw(void) +static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { - if (!use_eager_fpu()) - stts(); + return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } -/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */ -static inline void __fpregs_deactivate(struct fpu *fpu) +/* + * These generally need preemption protection to work, + * do try to avoid using these on their own: + */ +static inline void fpregs_deactivate(struct fpu *fpu) { WARN_ON_FPU(!fpu->fpregs_active); @@ -528,8 +523,7 @@ static inline void __fpregs_deactivate(struct fpu *fpu) trace_x86_fpu_regs_deactivated(fpu); } -/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */ -static inline void __fpregs_activate(struct fpu *fpu) +static inline void fpregs_activate(struct fpu *fpu) { WARN_ON_FPU(fpu->fpregs_active); @@ -554,51 +548,19 @@ static inline int fpregs_active(void) } /* - * Encapsulate the CR0.TS handling together with the - * software flag. - * - * These generally need preemption protection to work, - * do try to avoid using these on their own. - */ -static inline void fpregs_activate(struct fpu *fpu) -{ - __fpregs_activate_hw(); - __fpregs_activate(fpu); -} - -static inline void fpregs_deactivate(struct fpu *fpu) -{ - __fpregs_deactivate(fpu); - __fpregs_deactivate_hw(); -} - -/* * FPU state switching for scheduling. * * This is a two-stage process: * - * - switch_fpu_prepare() saves the old state and - * sets the new state of the CR0.TS bit. This is - * done within the context of the old process. + * - switch_fpu_prepare() saves the old state. + * This is done within the context of the old process. * * - switch_fpu_finish() restores the new state as * necessary. */ -typedef struct { int preload; } fpu_switch_t; - -static inline fpu_switch_t -switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) +static inline void +switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - fpu_switch_t fpu; - - /* - * 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 = static_cpu_has(X86_FEATURE_FPU) && - new_fpu->fpstate_active && - (use_eager_fpu() || new_fpu->counter > 5); - if (old_fpu->fpregs_active) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; @@ -608,29 +570,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) /* But leave fpu_fpregs_owner_ctx! */ old_fpu->fpregs_active = 0; trace_x86_fpu_regs_deactivated(old_fpu); - - /* Don't change CR0.TS if we just switch! */ - if (fpu.preload) { - new_fpu->counter++; - __fpregs_activate(new_fpu); - trace_x86_fpu_regs_activated(new_fpu); - prefetch(&new_fpu->state); - } else { - __fpregs_deactivate_hw(); - } - } else { - old_fpu->counter = 0; + } else old_fpu->last_cpu = -1; - if (fpu.preload) { - new_fpu->counter++; - if (fpu_want_lazy_restore(new_fpu, cpu)) - fpu.preload = 0; - else - prefetch(&new_fpu->state); - fpregs_activate(new_fpu); - } - } - return fpu; } /* @@ -638,15 +579,19 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) */ /* - * By the time this gets called, we've already cleared CR0.TS and - * given the process the FPU if we are going to preload the FPU - * state - all we need to do is to conditionally restore the register - * state itself. + * Set up the userspace FPU context for the new task, if the task + * has used the FPU. */ -static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch) +static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu) { - if (fpu_switch.preload) - copy_kernel_to_fpregs(&new_fpu->state); + bool preload = static_cpu_has(X86_FEATURE_FPU) && + new_fpu->fpstate_active; + + if (preload) { + if (!fpregs_state_valid(new_fpu, cpu)) + copy_kernel_to_fpregs(&new_fpu->state); + fpregs_activate(new_fpu); + } } /* diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 48df486b02f9..e31332d6f0e8 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -322,17 +322,6 @@ struct fpu { unsigned char fpregs_active; /* - * @counter: - * - * This counter contains the number of consecutive context switches - * during which the FPU stays used. If this is over a threshold, the - * lazy FPU restore logic becomes eager, to save the trap overhead. - * This is an unsigned char so that after 256 iterations the counter - * wraps and the context switch behavior turns lazy again; this is to - * deal with bursty apps that only use the FPU for a short time: - */ - unsigned char counter; - /* * @state: * * In-memory copy of all FPU registers that we save/restore diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 430bacf73074..1b2799e0699a 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -21,21 +21,16 @@ /* Supervisor features */ #define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT) -/* Supported features which support lazy state saving */ -#define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ +/* All currently supported features */ +#define XCNTXT_MASK (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ - XFEATURE_MASK_Hi16_ZMM) - -/* Supported features which require eager state saving */ -#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | \ - XFEATURE_MASK_BNDCSR | \ - XFEATURE_MASK_PKRU) - -/* All currently supported features */ -#define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER) + XFEATURE_MASK_Hi16_ZMM | \ + XFEATURE_MASK_PKRU | \ + XFEATURE_MASK_BNDREGS | \ + XFEATURE_MASK_BNDCSR) #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 9217ab1f5bf6..342e59789fcd 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -14,7 +14,6 @@ DECLARE_EVENT_CLASS(x86_fpu, __field(struct fpu *, fpu) __field(bool, fpregs_active) __field(bool, fpstate_active) - __field(int, counter) __field(u64, xfeatures) __field(u64, xcomp_bv) ), @@ -23,17 +22,15 @@ DECLARE_EVENT_CLASS(x86_fpu, __entry->fpu = fpu; __entry->fpregs_active = fpu->fpregs_active; __entry->fpstate_active = fpu->fpstate_active; - __entry->counter = fpu->counter; if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), - TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d counter: %d xfeatures: %llx xcomp_bv: %llx", + TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, __entry->fpregs_active, __entry->fpstate_active, - __entry->counter, __entry->xfeatures, __entry->xcomp_bv ) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 47004010ad5d..52f5684405c1 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -58,27 +58,9 @@ static bool kernel_fpu_disabled(void) return this_cpu_read(in_kernel_fpu); } -/* - * Were we in an interrupt that interrupted kernel mode? - * - * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that - * pair does nothing at all: the thread must not have fpu (so - * that we don't try to save the FPU state), and TS must - * be set (so that the clts/stts pair does nothing that is - * visible in the interrupted kernel thread). - * - * Except for the eagerfpu case when we return true; in the likely case - * the thread has FPU but we are not going to set/clear TS. - */ static bool interrupted_kernel_fpu_idle(void) { - if (kernel_fpu_disabled()) - return false; - - if (use_eager_fpu()) - return true; - - return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS); + return !kernel_fpu_disabled(); } /* @@ -125,8 +107,7 @@ void __kernel_fpu_begin(void) */ copy_fpregs_to_fpstate(fpu); } else { - this_cpu_write(fpu_fpregs_owner_ctx, NULL); - __fpregs_activate_hw(); + __cpu_invalidate_fpregs_state(); } } EXPORT_SYMBOL(__kernel_fpu_begin); @@ -137,8 +118,6 @@ void __kernel_fpu_end(void) if (fpu->fpregs_active) copy_kernel_to_fpregs(&fpu->state); - else - __fpregs_deactivate_hw(); kernel_fpu_enable(); } @@ -200,10 +179,7 @@ void fpu__save(struct fpu *fpu) trace_x86_fpu_before_save(fpu); if (fpu->fpregs_active) { if (!copy_fpregs_to_fpstate(fpu)) { - if (use_eager_fpu()) - copy_kernel_to_fpregs(&fpu->state); - else - fpregs_deactivate(fpu); + copy_kernel_to_fpregs(&fpu->state); } } trace_x86_fpu_after_save(fpu); @@ -247,7 +223,6 @@ EXPORT_SYMBOL_GPL(fpstate_init); 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; @@ -260,8 +235,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Don't let 'init optimized' areas of the XSAVE area * leak into the child task: */ - if (use_eager_fpu()) - memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); + memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* * Save current FPU registers directly into the child @@ -283,10 +257,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size); - if (use_eager_fpu()) - copy_kernel_to_fpregs(&src_fpu->state); - else - fpregs_deactivate(src_fpu); + copy_kernel_to_fpregs(&src_fpu->state); } preempt_enable(); @@ -366,7 +337,7 @@ void fpu__activate_fpstate_write(struct fpu *fpu) if (fpu->fpstate_active) { /* Invalidate any lazy state: */ - fpu->last_cpu = -1; + __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); @@ -409,7 +380,7 @@ void fpu__current_fpstate_write_begin(void) * ensures we will not be lazy and skip a XRSTOR in the * future. */ - fpu->last_cpu = -1; + __fpu_invalidate_fpregs_state(fpu); } /* @@ -459,7 +430,6 @@ void fpu__restore(struct fpu *fpu) trace_x86_fpu_before_restore(fpu); fpregs_activate(fpu); copy_kernel_to_fpregs(&fpu->state); - fpu->counter++; trace_x86_fpu_after_restore(fpu); kernel_fpu_enable(); } @@ -477,7 +447,6 @@ EXPORT_SYMBOL_GPL(fpu__restore); void fpu__drop(struct fpu *fpu) { preempt_disable(); - fpu->counter = 0; if (fpu->fpregs_active) { /* Ignore delayed exceptions from user space */ @@ -521,7 +490,7 @@ void fpu__clear(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ - if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) { + if (!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 2f2b8c7ccb85..1a09d133c801 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -15,10 +15,7 @@ */ static void fpu__init_cpu_ctx_switch(void) { - if (!boot_cpu_has(X86_FEATURE_EAGER_FPU)) - stts(); - else - clts(); + clts(); } /* @@ -233,82 +230,16 @@ static void __init fpu__init_system_xstate_size_legacy(void) } /* - * FPU context switching strategies: - * - * Against popular belief, we don't do lazy FPU saves, due to the - * task migration complications it brings on SMP - we only do - * lazy FPU restores. - * - * 'lazy' is the traditional strategy, which is based on setting - * CR0::TS to 1 during context-switch (instead of doing a full - * restore of the FPU state), which causes the first FPU instruction - * after the context switch (whenever it is executed) to fault - at - * which point we lazily restore the FPU state into FPU registers. - * - * Tasks are of course under no obligation to execute FPU instructions, - * so it can easily happen that another context-switch occurs without - * a single FPU instruction being executed. If we eventually switch - * back to the original task (that still owns the FPU) then we have - * not only saved the restores along the way, but we also have the - * FPU ready to be used for the original task. - * - * '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 - * state saving and restoration in hardware: they can detect both - * unused and untouched FPU state and optimize accordingly. - * - * [ Note that even in 'lazy' mode we might optimize context switches - * 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 { ENABLE, DISABLE } eagerfpu = ENABLE; - -/* * Find supported xfeatures based on cpu features and command-line input. * This must be called after fpu__init_parse_early_param() is called and * xfeatures_mask is enumerated. */ u64 __init fpu__get_supported_xfeatures_mask(void) { - /* Support all xfeatures known to us */ - if (eagerfpu != DISABLE) - return XCNTXT_MASK; - - /* Warning of xfeatures being disabled for no eagerfpu mode */ - if (xfeatures_mask & XFEATURE_MASK_EAGER) { - pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", - xfeatures_mask & XFEATURE_MASK_EAGER); - } - - /* Return a mask that masks out all features requiring eagerfpu mode */ - return ~XFEATURE_MASK_EAGER; -} - -/* - * Disable features dependent on eagerfpu. - */ -static void __init fpu__clear_eager_fpu_features(void) -{ - setup_clear_cpu_cap(X86_FEATURE_MPX); + return XCNTXT_MASK; } -/* - * Pick the FPU context switching strategy: - * - * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of - * the following is true: - * - * (1) the cpu has xsaveopt, as it has the optimization and doing eager - * FPU switching has a relatively low cost compared to a plain xsave; - * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU - * switching. Should the kernel boot with noxsaveopt, we support MPX - * with eager FPU switching at a higher cost. - */ +/* Legacy code to initialize eager fpu mode. */ static void __init fpu__init_system_ctx_switch(void) { static bool on_boot_cpu __initdata = 1; @@ -317,17 +248,6 @@ static void __init fpu__init_system_ctx_switch(void) on_boot_cpu = 0; WARN_ON_FPU(current->thread.fpu.fpstate_active); - - if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE) - eagerfpu = ENABLE; - - if (xfeatures_mask & XFEATURE_MASK_EAGER) - eagerfpu = ENABLE; - - if (eagerfpu == ENABLE) - setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); - - printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy"); } /* @@ -336,11 +256,6 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { - if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) { - eagerfpu = DISABLE; - fpu__clear_eager_fpu_features(); - } - if (cmdline_find_option_bool(boot_command_line, "no387")) setup_clear_cpu_cap(X86_FEATURE_FPU); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a184c210efba..83c23c230b4c 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -340,11 +340,9 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } fpu->fpstate_active = 1; - if (use_eager_fpu()) { - preempt_disable(); - fpu__restore(fpu); - preempt_enable(); - } + preempt_disable(); + fpu__restore(fpu); + preempt_enable(); return err; } else { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 124aa5c593f8..17ad31fd0a9f 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -888,15 +888,6 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; - /* - * For most XSAVE components, this would be an arduous task: - * brining fpstate up to date with fpregs, updating fpstate, - * then re-populating fpregs. But, for components that are - * never lazily managed, we can just access the fpregs - * directly. PKRU is never managed lazily, so we can just - * manipulate it directly. Make sure it stays that way. - */ - WARN_ON_ONCE(!use_eager_fpu()); /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index bd7be8efdc4c..7dc8c9c3d801 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -232,11 +232,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - fpu_switch_t fpu_switch; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); + switch_fpu_prepare(prev_fpu, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -295,7 +294,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (prev->gs | next->gs) lazy_load_gs(next->gs); - switch_fpu_finish(next_fpu, fpu_switch); + switch_fpu_finish(next_fpu, cpu); this_cpu_write(current_task, next_p); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b3760b3c1ca0..9c3a7b04e59e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -265,9 +265,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); unsigned prev_fsindex, prev_gsindex; - fpu_switch_t fpu_switch; - fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); + switch_fpu_prepare(prev_fpu, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -417,7 +416,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) prev->gsbase = 0; prev->gsindex = prev_gsindex; - switch_fpu_finish(next_fpu, fpu_switch); + switch_fpu_finish(next_fpu, cpu); /* * Switch the PDA and FPU contexts. diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 951f093a96fe..5943bb7637cd 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1111,7 +1111,7 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) return err; /* the FPU context is blank, nobody can own it */ - __cpu_disable_lazy_restore(cpu); + per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL; common_cpu_up(cpu, tidle); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index afa7bbb596cd..0aefb626fa8f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -16,7 +16,6 @@ #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> -#include <asm/fpu/internal.h> /* For use_eager_fpu. Ugh! */ #include <asm/user.h> #include <asm/fpu/xstate.h> #include "cpuid.h" @@ -114,8 +113,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - if (use_eager_fpu()) - kvm_x86_ops->fpu_activate(vcpu); + kvm_x86_ops->fpu_activate(vcpu); /* * The existing code assumes virtual address is 48-bit in the canonical diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c633de84dd7..d5700263dad2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7386,25 +7386,13 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - if (!vcpu->guest_fpu_loaded) { - vcpu->fpu_counter = 0; + if (!vcpu->guest_fpu_loaded) return; - } vcpu->guest_fpu_loaded = 0; copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; - /* - * If using eager FPU mode, or if the guest is a frequent user - * of the FPU, just leave the FPU active for next time. - * Every 255 times fpu_counter rolls over to 0; a guest that uses - * the FPU in bursts will revert to loading it on demand. - */ - if (!use_eager_fpu()) { - if (++vcpu->fpu_counter < 5) - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); - } trace_kvm_fpu(0); } |