From b3b0870ef3ffed72b92415423da864f440f57ad6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 16 Feb 2012 15:45:23 -0800 Subject: i387: do not preload FPU state at task switch time Yes, taking the trap to re-load the FPU/MMX state is expensive, but so is spending several days looking for a bug in the state save/restore code. And the preload code has some rather subtle interactions with both paravirtualization support and segment state restore, so it's not nearly as simple as it should be. Also, now that we no longer necessarily depend on a single bit (ie TS_USEDFPU) for keeping track of the state of the FPU, we migth be able to do better. If we are really switching between two processes that keep touching the FP state, save/restore is inevitable, but in the case of having one process that does most of the FPU usage, we may actually be able to do much better than the preloading. In particular, we may be able to keep track of which CPU the process ran on last, and also per CPU keep track of which process' FP state that CPU has. For modern CPU's that don't destroy the FPU contents on save time, that would allow us to do a lazy restore by just re-enabling the existing FPU state - with no restore cost at all! Signed-off-by: Linus Torvalds --- arch/x86/kernel/process_32.c | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 485204f58cda..324cd722b447 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -299,23 +299,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); - bool preload_fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - __unlazy_fpu(prev_p); - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); - /* * Reload esp0. */ @@ -354,11 +342,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); - /* If we're going to preload the fpu context, make sure clts - is run while we're batching the cpu state updates. */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -368,9 +351,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); - if (preload_fpu) - __math_state_restore(); - /* * Restore %gs if needed (which is common) */ -- cgit v1.2.3 From 34ddc81a230b15c0e345b6b253049db731499f7e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Feb 2012 12:56:35 -0800 Subject: i387: re-introduce FPU state preloading at context switch time After all the FPU state cleanups and finally finding the problem that caused all our FPU save/restore problems, this re-introduces the preloading of FPU state that was removed in commit b3b0870ef3ff ("i387: do not preload FPU state at task switch time"). However, instead of simply reverting the removal, this reimplements preloading with several fixes, most notably - properly abstracted as a true FPU state switch, rather than as open-coded save and restore with various hacks. In particular, implementing it as a proper FPU state switch allows us to optimize the CR0.TS flag accesses: there is no reason to set the TS bit only to then almost immediately clear it again. CR0 accesses are quite slow and expensive, don't flip the bit back and forth for no good reason. - Make sure that the same model works for both x86-32 and x86-64, so that there are no gratuitous differences between the two due to the way they save and restore segment state differently due to architectural differences that really don't matter to the FPU state. - Avoid exposing the "preload" state to the context switch routines, and in particular allow the concept of lazy state restore: if nothing else has used the FPU in the meantime, and the process is still on the same CPU, we can avoid restoring state from memory entirely, just re-expose the state that is still in the FPU unit. That optimized lazy restore isn't actually implemented here, but the infrastructure is set up for it. Of course, older CPU's that use 'fnsave' to save the state cannot take advantage of this, since the state saving also trashes the state. In other words, there is now an actual _design_ to the FPU state saving, rather than just random historical baggage. Hopefully it's easier to follow as a result. Signed-off-by: Linus Torvalds --- arch/x86/include/asm/i387.h | 110 ++++++++++++++++++++++++++++++++++++------- arch/x86/kernel/process_32.c | 5 +- arch/x86/kernel/process_64.c | 5 +- arch/x86/kernel/traps.c | 55 +++++++++++++--------- 4 files changed, 133 insertions(+), 42 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index f5376676f89c..a850b4d8d14d 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -29,6 +29,7 @@ extern unsigned int sig_xstate_size; extern void fpu_init(void); extern void mxcsr_feature_mask_init(void); extern int init_fpu(struct task_struct *child); +extern void __math_state_restore(struct task_struct *); extern void math_state_restore(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); @@ -212,9 +213,10 @@ static inline void fpu_fxsave(struct fpu *fpu) #endif /* CONFIG_X86_64 */ /* - * These must be called with preempt disabled + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact. */ -static inline void fpu_save_init(struct fpu *fpu) +static inline int fpu_save_init(struct fpu *fpu) { if (use_xsave()) { fpu_xsave(fpu); @@ -223,22 +225,33 @@ static inline void fpu_save_init(struct fpu *fpu) * xsave header may indicate the init state of the FP. */ if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return; + return 1; } else if (use_fxsr()) { fpu_fxsave(fpu); } else { asm volatile("fnsave %[fx]; fwait" : [fx] "=m" (fpu->state->fsave)); - return; + return 0; } - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) + /* + * If exceptions are pending, we need to clear them so + * that we don't randomly get exceptions later. + * + * FIXME! Is this perhaps only true for the old-style + * irq13 case? Maybe we could leave the x87 state + * intact otherwise? + */ + if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { asm volatile("fnclex"); + return 0; + } + return 1; } -static inline void __save_init_fpu(struct task_struct *tsk) +static inline int __save_init_fpu(struct task_struct *tsk) { - fpu_save_init(&tsk->thread.fpu); + return fpu_save_init(&tsk->thread.fpu); } static inline int fpu_fxrstor_checking(struct fpu *fpu) @@ -301,20 +314,79 @@ static inline void __thread_fpu_begin(struct task_struct *tsk) } /* - * Signal frame handlers... + * 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_finish() restores the new state as + * necessary. */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); +typedef struct { int preload; } fpu_switch_t; + +/* + * FIXME! We could do a totally lazy restore, but we need to + * add a per-cpu "this was the task that last touched the FPU + * on this CPU" variable, and the task needs to have a "I last + * touched the FPU on this CPU" and check them. + * + * We don't do that yet, so "fpu_lazy_restore()" always returns + * false, but some day.. + */ +#define fpu_lazy_restore(tsk) (0) +#define fpu_lazy_state_intact(tsk) do { } while (0) + +static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new) +{ + fpu_switch_t fpu; + + fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + if (__thread_has_fpu(old)) { + if (__save_init_fpu(old)) + fpu_lazy_state_intact(old); + __thread_clear_has_fpu(old); + old->fpu_counter++; + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + __thread_set_has_fpu(new); + prefetch(new->thread.fpu.state); + } else + stts(); + } else { + old->fpu_counter = 0; + if (fpu.preload) { + if (fpu_lazy_restore(new)) + fpu.preload = 0; + else + prefetch(new->thread.fpu.state); + __thread_fpu_begin(new); + } + } + return fpu; +} -static inline void __unlazy_fpu(struct task_struct *tsk) +/* + * 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. + */ +static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) { - if (__thread_has_fpu(tsk)) { - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - } else - tsk->fpu_counter = 0; + if (fpu.preload) + __math_state_restore(new); } +/* + * Signal frame handlers... + */ +extern int save_i387_xstate(void __user *buf); +extern int restore_i387_xstate(void __user *buf); + static inline void __clear_fpu(struct task_struct *tsk) { if (__thread_has_fpu(tsk)) { @@ -474,7 +546,11 @@ static inline void save_init_fpu(struct task_struct *tsk) static inline void unlazy_fpu(struct task_struct *tsk) { preempt_disable(); - __unlazy_fpu(tsk); + if (__thread_has_fpu(tsk)) { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } else + tsk->fpu_counter = 0; preempt_enable(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 324cd722b447..80bfe1ab0031 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -299,10 +299,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); + fpu_switch_t fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - __unlazy_fpu(prev_p); + fpu = switch_fpu_prepare(prev_p, next_p); /* * Reload esp0. @@ -357,6 +358,8 @@ __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_p, fpu); + percpu_write(current_task, next_p); return prev_p; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 753e803f7197..1fd94bc4279d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -386,8 +386,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); unsigned fsindex, gsindex; + fpu_switch_t fpu; - __unlazy_fpu(prev_p); + fpu = switch_fpu_prepare(prev_p, next_p); /* * Reload esp0, LDT and the page table pointer: @@ -457,6 +458,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; + switch_fpu_finish(next_p, fpu); + /* * Switch the PDA and FPU contexts. */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ad25e51f40c4..77da5b475ad2 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -570,6 +570,37 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void) { } +/* + * This gets called with the process already owning the + * FPU state, and with CR0.TS cleared. It just needs to + * restore the FPU register state. + */ +void __math_state_restore(struct task_struct *tsk) +{ + /* We need a safe address that is cheap to find and that is already + in L1. We've just brought in "tsk->thread.has_fpu", so use that */ +#define safe_address (tsk->thread.has_fpu) + + /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception + is pending. Clear the x87 state here by setting it to fixed + values. safe_address is a random variable that should be in L1 */ + alternative_input( + ASM_NOP8 ASM_NOP2, + "emms\n\t" /* clear stack tags */ + "fildl %P[addr]", /* set F?P to defined value */ + X86_FEATURE_FXSAVE_LEAK, + [addr] "m" (safe_address)); + + /* + * Paranoid restore. send a SIGSEGV if we fail to restore the state. + */ + if (unlikely(restore_fpu_checking(tsk))) { + __thread_fpu_end(tsk); + force_sig(SIGSEGV, tsk); + return; + } +} + /* * 'math_state_restore()' saves the current math information in the * old math state array, and gets the new ones from the current task @@ -584,10 +615,6 @@ void math_state_restore(void) { struct task_struct *tsk = current; - /* We need a safe address that is cheap to find and that is already - in L1. We're just bringing in "tsk->thread.has_fpu", so use that */ -#define safe_address (tsk->thread.has_fpu) - if (!tsk_used_math(tsk)) { local_irq_enable(); /* @@ -604,25 +631,7 @@ void math_state_restore(void) } __thread_fpu_begin(tsk); - - /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. safe_address is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (safe_address)); - - /* - * Paranoid restore. send a SIGSEGV if we fail to restore the state. - */ - if (unlikely(restore_fpu_checking(tsk))) { - __thread_fpu_end(tsk); - force_sig(SIGSEGV, tsk); - return; - } + __math_state_restore(tsk); tsk->fpu_counter++; } -- cgit v1.2.3 From cea20ca3f3181fc36788a15bc65d1062b96a0a6c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 20 Feb 2012 10:24:09 -0800 Subject: i387: fix up some fpu_counter confusion This makes sure we clear the FPU usage counter for newly created tasks, just so that we start off in a known state (for example, don't try to preload the FPU state on the first task switch etc). It also fixes a thinko in when we increment the fpu_counter at task switch time, introduced by commit 34ddc81a230b ("i387: re-introduce FPU state preloading at context switch time"). We should increment the *new* task fpu_counter, not the old task, and only if we decide to use that state (whether lazily or preloaded). Signed-off-by: Linus Torvalds --- arch/x86/include/asm/i387.h | 3 ++- arch/x86/kernel/process_32.c | 1 + arch/x86/kernel/process_64.c | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index a850b4d8d14d..8df95849721d 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -348,10 +348,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta if (__save_init_fpu(old)) fpu_lazy_state_intact(old); __thread_clear_has_fpu(old); - old->fpu_counter++; /* Don't change CR0.TS if we just switch! */ if (fpu.preload) { + new->fpu_counter++; __thread_set_has_fpu(new); prefetch(new->thread.fpu.state); } else @@ -359,6 +359,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta } else { old->fpu_counter = 0; if (fpu.preload) { + new->fpu_counter++; if (fpu_lazy_restore(new)) fpu.preload = 0; else diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 80bfe1ab0031..bc32761bc27a 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -214,6 +214,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, task_user_gs(p) = get_user_gs(regs); + p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 1fd94bc4279d..8ad880b3bc1c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -286,6 +286,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, set_tsk_thread_flag(p, TIF_FORK); + p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); -- cgit v1.2.3 From 7e16838d94b566a17b65231073d179bc04d590c8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Feb 2012 13:27:00 -0800 Subject: i387: support lazy restore of FPU state This makes us recognize when we try to restore FPU state that matches what we already have in the FPU on this CPU, and avoids the restore entirely if so. To do this, we add two new data fields: - a percpu 'fpu_owner_task' variable that gets written any time we update the "has_fpu" field, and thus acts as a kind of back-pointer to the task that owns the CPU. The exception is when we save the FPU state as part of a context switch - if the save can keep the FPU state around, we leave the 'fpu_owner_task' variable pointing at the task whose FP state still remains on the CPU. - a per-thread 'last_cpu' field, that indicates which CPU that thread used its FPU on last. We update this on every context switch (writing an invalid CPU number if the last context switch didn't leave the FPU in a lazily usable state), so we know that *that* thread has done nothing else with the FPU since. These two fields together can be used when next switching back to the task to see if the CPU still matches: if 'fpu_owner_task' matches the task we are switching to, we know that no other task (or kernel FPU usage) touched the FPU on this CPU in the meantime, and if the current CPU number matches the 'last_cpu' field, we know that this thread did no other FP work on any other CPU, so the FPU state on the CPU must match what was saved on last context switch. In that case, we can avoid the 'f[x]rstor' entirely, and just clear the CR0.TS bit. Signed-off-by: Linus Torvalds --- arch/x86/include/asm/i387.h | 35 +++++++++++++++++++++++------------ arch/x86/include/asm/processor.h | 3 ++- arch/x86/kernel/cpu/common.c | 2 ++ arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 5 files changed, 29 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 74c607b37e87..247904945d3f 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -32,6 +32,8 @@ extern int init_fpu(struct task_struct *child); extern void math_state_restore(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); +DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); + extern user_regset_active_fn fpregs_active, xfpregs_active; extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, xstateregs_get; @@ -276,7 +278,7 @@ static inline int restore_fpu_checking(struct task_struct *tsk) "emms\n\t" /* clear stack tags */ "fildl %P[addr]", /* set F?P to defined value */ X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (tsk->thread.has_fpu)); + [addr] "m" (tsk->thread.fpu.has_fpu)); return fpu_restore_checking(&tsk->thread.fpu); } @@ -288,19 +290,21 @@ static inline int restore_fpu_checking(struct task_struct *tsk) */ static inline int __thread_has_fpu(struct task_struct *tsk) { - return tsk->thread.has_fpu; + return tsk->thread.fpu.has_fpu; } /* Must be paired with an 'stts' after! */ static inline void __thread_clear_has_fpu(struct task_struct *tsk) { - tsk->thread.has_fpu = 0; + tsk->thread.fpu.has_fpu = 0; + percpu_write(fpu_owner_task, NULL); } /* Must be paired with a 'clts' before! */ static inline void __thread_set_has_fpu(struct task_struct *tsk) { - tsk->thread.has_fpu = 1; + tsk->thread.fpu.has_fpu = 1; + percpu_write(fpu_owner_task, tsk); } /* @@ -345,18 +349,22 @@ typedef struct { int preload; } fpu_switch_t; * We don't do that yet, so "fpu_lazy_restore()" always returns * false, but some day.. */ -#define fpu_lazy_restore(tsk) (0) -#define fpu_lazy_state_intact(tsk) do { } while (0) +static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) +{ + return new == percpu_read_stable(fpu_owner_task) && + cpu == new->thread.fpu.last_cpu; +} -static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new) +static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) { fpu_switch_t fpu; fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; if (__thread_has_fpu(old)) { - if (__save_init_fpu(old)) - fpu_lazy_state_intact(old); - __thread_clear_has_fpu(old); + if (!__save_init_fpu(old)) + cpu = ~0; + old->thread.fpu.last_cpu = cpu; + old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */ /* Don't change CR0.TS if we just switch! */ if (fpu.preload) { @@ -367,9 +375,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta stts(); } else { old->fpu_counter = 0; + old->thread.fpu.last_cpu = ~0; if (fpu.preload) { new->fpu_counter++; - if (fpu_lazy_restore(new)) + if (fpu_lazy_restore(new, cpu)) fpu.preload = 0; else prefetch(new->thread.fpu.state); @@ -463,8 +472,10 @@ static inline void kernel_fpu_begin(void) __save_init_fpu(me); __thread_clear_has_fpu(me); /* We do 'stts()' in kernel_fpu_end() */ - } else + } else { + percpu_write(fpu_owner_task, NULL); clts(); + } } static inline void kernel_fpu_end(void) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f7c89e231c6c..58545c97d071 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -374,6 +374,8 @@ union thread_xstate { }; struct fpu { + unsigned int last_cpu; + unsigned int has_fpu; union thread_xstate *state; }; @@ -454,7 +456,6 @@ struct thread_struct { unsigned long trap_no; unsigned long error_code; /* floating point and extended processor state */ - unsigned long has_fpu; struct fpu fpu; #ifdef CONFIG_X86_32 /* Virtual 86 mode info */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d43cad74f166..b667148dfad7 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1044,6 +1044,8 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) = DEFINE_PER_CPU(unsigned int, irq_count) = -1; +DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); + /* * Special IST stacks which the CPU switches to when it calls * an IST-marked descriptor entry. Up to 7 stacks (hardware diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index bc32761bc27a..c08d1ff12b7c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -304,7 +304,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - fpu = switch_fpu_prepare(prev_p, next_p); + fpu = switch_fpu_prepare(prev_p, next_p, cpu); /* * Reload esp0. diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 8ad880b3bc1c..cfa5c90c01db 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -389,7 +389,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) unsigned fsindex, gsindex; fpu_switch_t fpu; - fpu = switch_fpu_prepare(prev_p, next_p); + fpu = switch_fpu_prepare(prev_p, next_p, cpu); /* * Reload esp0, LDT and the page table pointer: -- cgit v1.2.3 From 1361b83a13d4d92e53fbb6c877528713e118b821 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2012 13:19:22 -0800 Subject: i387: Split up into exported and internal interfaces While various modules include to get access to things we actually *intend* for them to use, most of that header file was really pretty low-level internal stuff that we really don't want to expose to others. So split the header file into two: the small exported interfaces remain in , while the internal definitions that are only used by core architecture code are now in . The guiding principle for this was to expose functions that we export to modules, and leave them in , while stuff that is used by task switching or was marked GPL-only is in . The fpu-internal.h file could be further split up too, especially since arch/x86/kvm/ uses some of the remaining stuff for its module. But that kvm usage should probably be abstracted out a bit, and at least now the internal FPU accessor functions are much more contained. Even if it isn't perhaps as contained as it _could_ be. Signed-off-by: Linus Torvalds Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1202211340330.5354@i5.linux-foundation.org Signed-off-by: H. Peter Anvin --- arch/x86/ia32/ia32_signal.c | 1 + arch/x86/include/asm/fpu-internal.h | 520 ++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/i387.h | 512 +---------------------------------- arch/x86/kernel/cpu/common.c | 1 + arch/x86/kernel/i387.c | 3 +- arch/x86/kernel/process.c | 1 + arch/x86/kernel/process_32.c | 1 + arch/x86/kernel/process_64.c | 1 + arch/x86/kernel/ptrace.c | 1 + arch/x86/kernel/signal.c | 1 + arch/x86/kernel/traps.c | 1 + arch/x86/kernel/xsave.c | 1 + arch/x86/kvm/vmx.c | 2 +- arch/x86/kvm/x86.c | 1 + arch/x86/power/cpu.c | 1 + 15 files changed, 540 insertions(+), 508 deletions(-) create mode 100644 arch/x86/include/asm/fpu-internal.h (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 65577698cab2..5563ba1cf513 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h new file mode 100644 index 000000000000..4fa88154e4de --- /dev/null +++ b/arch/x86/include/asm/fpu-internal.h @@ -0,0 +1,520 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes , May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _FPU_INTERNAL_H +#define _FPU_INTERNAL_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +extern unsigned int sig_xstate_size; +extern void fpu_init(void); + +DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); + +extern user_regset_active_fn fpregs_active, xfpregs_active; +extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, + xstateregs_get; +extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, + xstateregs_set; + + +/* + * xstateregs_active == fpregs_active. Please refer to the comment + * at the definition of fpregs_active. + */ +#define xstateregs_active fpregs_active + +extern struct _fpx_sw_bytes fx_sw_reserved; +#ifdef CONFIG_IA32_EMULATION +extern unsigned int sig_xstate_ia32_size; +extern struct _fpx_sw_bytes fx_sw_reserved_ia32; +struct _fpstate_ia32; +struct _xstate_ia32; +extern int save_i387_xstate_ia32(void __user *buf); +extern int restore_i387_xstate_ia32(void __user *buf); +#endif + +#ifdef CONFIG_MATH_EMULATION +extern void finit_soft_fpu(struct i387_soft_struct *soft); +#else +static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} +#endif + +#define X87_FSW_ES (1 << 7) /* Exception Summary */ + +static __always_inline __pure bool use_xsaveopt(void) +{ + return static_cpu_has(X86_FEATURE_XSAVEOPT); +} + +static __always_inline __pure bool use_xsave(void) +{ + return static_cpu_has(X86_FEATURE_XSAVE); +} + +static __always_inline __pure bool use_fxsr(void) +{ + return static_cpu_has(X86_FEATURE_FXSR); +} + +extern void __sanitize_i387_state(struct task_struct *); + +static inline void sanitize_i387_state(struct task_struct *tsk) +{ + if (!use_xsaveopt()) + return; + __sanitize_i387_state(tsk); +} + +#ifdef CONFIG_X86_64 +static inline int fxrstor_checking(struct i387_fxsave_struct *fx) +{ + int err; + + /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxrstorq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err) + : [fx] "m" (*fx), "0" (0)); +#else + asm volatile("1: rex64/fxrstor (%[fx])\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err) + : [fx] "R" (fx), "m" (*fx), "0" (0)); +#endif + return err; +} + +static inline int fxsave_user(struct i387_fxsave_struct __user *fx) +{ + int err; + + /* + * Clear the bytes not touched by the fxsave and reserved + * for the SW usage. + */ + err = __clear_user(&fx->sw_reserved, + sizeof(struct _fpx_sw_bytes)); + if (unlikely(err)) + return -EFAULT; + + /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxsaveq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err), [fx] "=m" (*fx) + : "0" (0)); +#else + asm volatile("1: rex64/fxsave (%[fx])\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err), "=m" (*fx) + : [fx] "R" (fx), "0" (0)); +#endif + if (unlikely(err) && + __clear_user(fx, sizeof(struct i387_fxsave_struct))) + err = -EFAULT; + /* No need to clear here because the caller clears USED_MATH */ + return err; +} + +static inline void fpu_fxsave(struct fpu *fpu) +{ + /* Using "rex64; fxsave %0" is broken because, if the memory operand + uses any extended registers for addressing, a second REX prefix + will be generated (to the assembler, rex64 followed by semicolon + is a separate instruction), and hence the 64-bitness is lost. */ + +#ifdef CONFIG_AS_FXSAVEQ + /* Using "fxsaveq %0" would be the ideal choice, but is only supported + starting with gas 2.16. */ + __asm__ __volatile__("fxsaveq %0" + : "=m" (fpu->state->fxsave)); +#else + /* Using, as a workaround, the properly prefixed form below isn't + accepted by any binutils version so far released, complaining that + the same type of prefix is used twice if an extended register is + needed for addressing (fix submitted to mainline 2005-11-21). + asm volatile("rex64/fxsave %0" + : "=m" (fpu->state->fxsave)); + This, however, we can work around by forcing the compiler to select + an addressing mode that doesn't require extended registers. */ + asm volatile("rex64/fxsave (%[fx])" + : "=m" (fpu->state->fxsave) + : [fx] "R" (&fpu->state->fxsave)); +#endif +} + +#else /* CONFIG_X86_32 */ + +/* perform fxrstor iff the processor has extended states, otherwise frstor */ +static inline int fxrstor_checking(struct i387_fxsave_struct *fx) +{ + /* + * The "nop" is needed to make the instructions the same + * length. + */ + alternative_input( + "nop ; frstor %1", + "fxrstor %1", + X86_FEATURE_FXSR, + "m" (*fx)); + + return 0; +} + +static inline void fpu_fxsave(struct fpu *fpu) +{ + asm volatile("fxsave %[fx]" + : [fx] "=m" (fpu->state->fxsave)); +} + +#endif /* CONFIG_X86_64 */ + +/* + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact. + */ +static inline int fpu_save_init(struct fpu *fpu) +{ + if (use_xsave()) { + fpu_xsave(fpu); + + /* + * xsave header may indicate the init state of the FP. + */ + if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) + return 1; + } else if (use_fxsr()) { + fpu_fxsave(fpu); + } else { + asm volatile("fnsave %[fx]; fwait" + : [fx] "=m" (fpu->state->fsave)); + return 0; + } + + /* + * If exceptions are pending, we need to clear them so + * that we don't randomly get exceptions later. + * + * FIXME! Is this perhaps only true for the old-style + * irq13 case? Maybe we could leave the x87 state + * intact otherwise? + */ + if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { + asm volatile("fnclex"); + return 0; + } + return 1; +} + +static inline int __save_init_fpu(struct task_struct *tsk) +{ + return fpu_save_init(&tsk->thread.fpu); +} + +static inline int fpu_fxrstor_checking(struct fpu *fpu) +{ + return fxrstor_checking(&fpu->state->fxsave); +} + +static inline int fpu_restore_checking(struct fpu *fpu) +{ + if (use_xsave()) + return fpu_xrstor_checking(fpu); + else + return fpu_fxrstor_checking(fpu); +} + +static inline int restore_fpu_checking(struct task_struct *tsk) +{ + /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception + is pending. Clear the x87 state here by setting it to fixed + values. "m" is a random variable that should be in L1 */ + alternative_input( + ASM_NOP8 ASM_NOP2, + "emms\n\t" /* clear stack tags */ + "fildl %P[addr]", /* set F?P to defined value */ + X86_FEATURE_FXSAVE_LEAK, + [addr] "m" (tsk->thread.fpu.has_fpu)); + + return fpu_restore_checking(&tsk->thread.fpu); +} + +/* + * Software FPU state helpers. Careful: these need to + * be preemption protection *and* they need to be + * properly paired with the CR0.TS changes! + */ +static inline int __thread_has_fpu(struct task_struct *tsk) +{ + return tsk->thread.fpu.has_fpu; +} + +/* Must be paired with an 'stts' after! */ +static inline void __thread_clear_has_fpu(struct task_struct *tsk) +{ + tsk->thread.fpu.has_fpu = 0; + percpu_write(fpu_owner_task, NULL); +} + +/* Must be paired with a 'clts' before! */ +static inline void __thread_set_has_fpu(struct task_struct *tsk) +{ + tsk->thread.fpu.has_fpu = 1; + percpu_write(fpu_owner_task, tsk); +} + +/* + * 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 __thread_fpu_end(struct task_struct *tsk) +{ + __thread_clear_has_fpu(tsk); + stts(); +} + +static inline void __thread_fpu_begin(struct task_struct *tsk) +{ + clts(); + __thread_set_has_fpu(tsk); +} + +/* + * 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_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +/* + * FIXME! We could do a totally lazy restore, but we need to + * add a per-cpu "this was the task that last touched the FPU + * on this CPU" variable, and the task needs to have a "I last + * touched the FPU on this CPU" and check them. + * + * We don't do that yet, so "fpu_lazy_restore()" always returns + * false, but some day.. + */ +static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) +{ + return new == percpu_read_stable(fpu_owner_task) && + cpu == new->thread.fpu.last_cpu; +} + +static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) +{ + fpu_switch_t fpu; + + fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + if (__thread_has_fpu(old)) { + if (!__save_init_fpu(old)) + cpu = ~0; + old->thread.fpu.last_cpu = cpu; + old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */ + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + new->fpu_counter++; + __thread_set_has_fpu(new); + prefetch(new->thread.fpu.state); + } else + stts(); + } else { + old->fpu_counter = 0; + old->thread.fpu.last_cpu = ~0; + if (fpu.preload) { + new->fpu_counter++; + if (fpu_lazy_restore(new, cpu)) + fpu.preload = 0; + else + prefetch(new->thread.fpu.state); + __thread_fpu_begin(new); + } + } + return fpu; +} + +/* + * 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. + */ +static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) +{ + if (fpu.preload) { + if (unlikely(restore_fpu_checking(new))) + __thread_fpu_end(new); + } +} + +/* + * Signal frame handlers... + */ +extern int save_i387_xstate(void __user *buf); +extern int restore_i387_xstate(void __user *buf); + +static inline void __clear_fpu(struct task_struct *tsk) +{ + if (__thread_has_fpu(tsk)) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + __thread_fpu_end(tsk); + } +} + +/* + * The actual user_fpu_begin/end() functions + * need to be preemption-safe. + * + * NOTE! user_fpu_end() must be used only after you + * have saved the FP state, and user_fpu_begin() must + * be used only immediately before restoring it. + * These functions do not do any save/restore on + * their own. + */ +static inline void user_fpu_end(void) +{ + preempt_disable(); + __thread_fpu_end(current); + preempt_enable(); +} + +static inline void user_fpu_begin(void) +{ + preempt_disable(); + if (!user_has_fpu()) + __thread_fpu_begin(current); + preempt_enable(); +} + +/* + * These disable preemption on their own and are safe + */ +static inline void save_init_fpu(struct task_struct *tsk) +{ + WARN_ON_ONCE(!__thread_has_fpu(tsk)); + preempt_disable(); + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + preempt_enable(); +} + +static inline void clear_fpu(struct task_struct *tsk) +{ + preempt_disable(); + __clear_fpu(tsk); + preempt_enable(); +} + +/* + * i387 state interaction + */ +static inline unsigned short get_fpu_cwd(struct task_struct *tsk) +{ + if (cpu_has_fxsr) { + return tsk->thread.fpu.state->fxsave.cwd; + } else { + return (unsigned short)tsk->thread.fpu.state->fsave.cwd; + } +} + +static inline unsigned short get_fpu_swd(struct task_struct *tsk) +{ + if (cpu_has_fxsr) { + return tsk->thread.fpu.state->fxsave.swd; + } else { + return (unsigned short)tsk->thread.fpu.state->fsave.swd; + } +} + +static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) +{ + if (cpu_has_xmm) { + return tsk->thread.fpu.state->fxsave.mxcsr; + } else { + return MXCSR_DEFAULT; + } +} + +static bool fpu_allocated(struct fpu *fpu) +{ + return fpu->state != NULL; +} + +static inline int fpu_alloc(struct fpu *fpu) +{ + if (fpu_allocated(fpu)) + return 0; + fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); + if (!fpu->state) + return -ENOMEM; + WARN_ON((unsigned long)fpu->state & 15); + return 0; +} + +static inline void fpu_free(struct fpu *fpu) +{ + if (fpu->state) { + kmem_cache_free(task_xstate_cachep, fpu->state); + fpu->state = NULL; + } +} + +static inline void fpu_copy(struct fpu *dst, struct fpu *src) +{ + memcpy(dst->state, src->state, xstate_size); +} + +extern void fpu_finit(struct fpu *fpu); + +#endif diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 0c1031d354f2..7ce0798b1b26 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -13,411 +13,15 @@ #ifndef __ASSEMBLY__ #include -#include -#include #include -#include -#include -#include -#include -#include -#include -#include -#include +#include + +struct pt_regs; +struct user_i387_struct; -extern unsigned int sig_xstate_size; -extern void fpu_init(void); -extern void mxcsr_feature_mask_init(void); extern int init_fpu(struct task_struct *child); -extern void math_state_restore(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); - -DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); - -extern user_regset_active_fn fpregs_active, xfpregs_active; -extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, - xstateregs_get; -extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, - xstateregs_set; - -/* - * xstateregs_active == fpregs_active. Please refer to the comment - * at the definition of fpregs_active. - */ -#define xstateregs_active fpregs_active - -extern struct _fpx_sw_bytes fx_sw_reserved; -#ifdef CONFIG_IA32_EMULATION -extern unsigned int sig_xstate_ia32_size; -extern struct _fpx_sw_bytes fx_sw_reserved_ia32; -struct _fpstate_ia32; -struct _xstate_ia32; -extern int save_i387_xstate_ia32(void __user *buf); -extern int restore_i387_xstate_ia32(void __user *buf); -#endif - -#ifdef CONFIG_MATH_EMULATION -extern void finit_soft_fpu(struct i387_soft_struct *soft); -#else -static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} -#endif - -#define X87_FSW_ES (1 << 7) /* Exception Summary */ - -static __always_inline __pure bool use_xsaveopt(void) -{ - return static_cpu_has(X86_FEATURE_XSAVEOPT); -} - -static __always_inline __pure bool use_xsave(void) -{ - return static_cpu_has(X86_FEATURE_XSAVE); -} - -static __always_inline __pure bool use_fxsr(void) -{ - return static_cpu_has(X86_FEATURE_FXSR); -} - -extern void __sanitize_i387_state(struct task_struct *); - -static inline void sanitize_i387_state(struct task_struct *tsk) -{ - if (!use_xsaveopt()) - return; - __sanitize_i387_state(tsk); -} - -#ifdef CONFIG_X86_64 -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - int err; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxrstorq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "m" (*fx), "0" (0)); -#else - asm volatile("1: rex64/fxrstor (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "R" (fx), "m" (*fx), "0" (0)); -#endif - return err; -} - -static inline int fxsave_user(struct i387_fxsave_struct __user *fx) -{ - int err; - - /* - * Clear the bytes not touched by the fxsave and reserved - * for the SW usage. - */ - err = __clear_user(&fx->sw_reserved, - sizeof(struct _fpx_sw_bytes)); - if (unlikely(err)) - return -EFAULT; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxsaveq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), [fx] "=m" (*fx) - : "0" (0)); -#else - asm volatile("1: rex64/fxsave (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), "=m" (*fx) - : [fx] "R" (fx), "0" (0)); -#endif - if (unlikely(err) && - __clear_user(fx, sizeof(struct i387_fxsave_struct))) - err = -EFAULT; - /* No need to clear here because the caller clears USED_MATH */ - return err; -} - -static inline void fpu_fxsave(struct fpu *fpu) -{ - /* Using "rex64; fxsave %0" is broken because, if the memory operand - uses any extended registers for addressing, a second REX prefix - will be generated (to the assembler, rex64 followed by semicolon - is a separate instruction), and hence the 64-bitness is lost. */ - -#ifdef CONFIG_AS_FXSAVEQ - /* Using "fxsaveq %0" would be the ideal choice, but is only supported - starting with gas 2.16. */ - __asm__ __volatile__("fxsaveq %0" - : "=m" (fpu->state->fxsave)); -#else - /* Using, as a workaround, the properly prefixed form below isn't - accepted by any binutils version so far released, complaining that - the same type of prefix is used twice if an extended register is - needed for addressing (fix submitted to mainline 2005-11-21). - asm volatile("rex64/fxsave %0" - : "=m" (fpu->state->fxsave)); - This, however, we can work around by forcing the compiler to select - an addressing mode that doesn't require extended registers. */ - asm volatile("rex64/fxsave (%[fx])" - : "=m" (fpu->state->fxsave) - : [fx] "R" (&fpu->state->fxsave)); -#endif -} - -#else /* CONFIG_X86_32 */ - -/* perform fxrstor iff the processor has extended states, otherwise frstor */ -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - /* - * The "nop" is needed to make the instructions the same - * length. - */ - alternative_input( - "nop ; frstor %1", - "fxrstor %1", - X86_FEATURE_FXSR, - "m" (*fx)); - - return 0; -} - -static inline void fpu_fxsave(struct fpu *fpu) -{ - asm volatile("fxsave %[fx]" - : [fx] "=m" (fpu->state->fxsave)); -} - -#endif /* CONFIG_X86_64 */ - -/* - * These must be called with preempt disabled. Returns - * 'true' if the FPU state is still intact. - */ -static inline int fpu_save_init(struct fpu *fpu) -{ - if (use_xsave()) { - fpu_xsave(fpu); - - /* - * xsave header may indicate the init state of the FP. - */ - if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return 1; - } else if (use_fxsr()) { - fpu_fxsave(fpu); - } else { - asm volatile("fnsave %[fx]; fwait" - : [fx] "=m" (fpu->state->fsave)); - return 0; - } - - /* - * If exceptions are pending, we need to clear them so - * that we don't randomly get exceptions later. - * - * FIXME! Is this perhaps only true for the old-style - * irq13 case? Maybe we could leave the x87 state - * intact otherwise? - */ - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { - asm volatile("fnclex"); - return 0; - } - return 1; -} - -static inline int __save_init_fpu(struct task_struct *tsk) -{ - return fpu_save_init(&tsk->thread.fpu); -} - -static inline int fpu_fxrstor_checking(struct fpu *fpu) -{ - return fxrstor_checking(&fpu->state->fxsave); -} - -static inline int fpu_restore_checking(struct fpu *fpu) -{ - if (use_xsave()) - return fpu_xrstor_checking(fpu); - else - return fpu_fxrstor_checking(fpu); -} - -static inline int restore_fpu_checking(struct task_struct *tsk) -{ - /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. "m" is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (tsk->thread.fpu.has_fpu)); - - return fpu_restore_checking(&tsk->thread.fpu); -} - -/* - * Software FPU state helpers. Careful: these need to - * be preemption protection *and* they need to be - * properly paired with the CR0.TS changes! - */ -static inline int __thread_has_fpu(struct task_struct *tsk) -{ - return tsk->thread.fpu.has_fpu; -} - -/* Must be paired with an 'stts' after! */ -static inline void __thread_clear_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 0; - percpu_write(fpu_owner_task, NULL); -} - -/* Must be paired with a 'clts' before! */ -static inline void __thread_set_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 1; - percpu_write(fpu_owner_task, tsk); -} - -/* - * 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 __thread_fpu_end(struct task_struct *tsk) -{ - __thread_clear_has_fpu(tsk); - stts(); -} - -static inline void __thread_fpu_begin(struct task_struct *tsk) -{ - clts(); - __thread_set_has_fpu(tsk); -} - -/* - * 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_finish() restores the new state as - * necessary. - */ -typedef struct { int preload; } fpu_switch_t; - -/* - * FIXME! We could do a totally lazy restore, but we need to - * add a per-cpu "this was the task that last touched the FPU - * on this CPU" variable, and the task needs to have a "I last - * touched the FPU on this CPU" and check them. - * - * We don't do that yet, so "fpu_lazy_restore()" always returns - * false, but some day.. - */ -static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) -{ - return new == percpu_read_stable(fpu_owner_task) && - cpu == new->thread.fpu.last_cpu; -} - -static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) -{ - fpu_switch_t fpu; - - fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; - if (__thread_has_fpu(old)) { - if (!__save_init_fpu(old)) - cpu = ~0; - old->thread.fpu.last_cpu = cpu; - old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */ - - /* Don't change CR0.TS if we just switch! */ - if (fpu.preload) { - new->fpu_counter++; - __thread_set_has_fpu(new); - prefetch(new->thread.fpu.state); - } else - stts(); - } else { - old->fpu_counter = 0; - old->thread.fpu.last_cpu = ~0; - if (fpu.preload) { - new->fpu_counter++; - if (fpu_lazy_restore(new, cpu)) - fpu.preload = 0; - else - prefetch(new->thread.fpu.state); - __thread_fpu_begin(new); - } - } - return fpu; -} - -/* - * 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. - */ -static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) -{ - if (fpu.preload) { - if (unlikely(restore_fpu_checking(new))) - __thread_fpu_end(new); - } -} - -/* - * Signal frame handlers... - */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); - -static inline void __clear_fpu(struct task_struct *tsk) -{ - if (__thread_has_fpu(tsk)) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - __thread_fpu_end(tsk); - } -} +extern void math_state_restore(void); extern bool irq_fpu_usable(void); extern void kernel_fpu_begin(void); @@ -463,118 +67,14 @@ static inline void irq_ts_restore(int TS_state) * we can just assume we have FPU access - typically * to save the FP state - we'll just take a #NM * fault and get the FPU access back. - * - * The actual user_fpu_begin/end() functions - * need to be preemption-safe, though. - * - * NOTE! user_fpu_end() must be used only after you - * have saved the FP state, and user_fpu_begin() must - * be used only immediately before restoring it. - * These functions do not do any save/restore on - * their own. */ static inline int user_has_fpu(void) { - return __thread_has_fpu(current); -} - -static inline void user_fpu_end(void) -{ - preempt_disable(); - __thread_fpu_end(current); - preempt_enable(); -} - -static inline void user_fpu_begin(void) -{ - preempt_disable(); - if (!user_has_fpu()) - __thread_fpu_begin(current); - preempt_enable(); -} - -/* - * These disable preemption on their own and are safe - */ -static inline void save_init_fpu(struct task_struct *tsk) -{ - WARN_ON_ONCE(!__thread_has_fpu(tsk)); - preempt_disable(); - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - preempt_enable(); + return current->thread.fpu.has_fpu; } extern void unlazy_fpu(struct task_struct *tsk); -static inline void clear_fpu(struct task_struct *tsk) -{ - preempt_disable(); - __clear_fpu(tsk); - preempt_enable(); -} - -/* - * i387 state interaction - */ -static inline unsigned short get_fpu_cwd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.cwd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.swd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) -{ - if (cpu_has_xmm) { - return tsk->thread.fpu.state->fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - -static bool fpu_allocated(struct fpu *fpu) -{ - return fpu->state != NULL; -} - -static inline int fpu_alloc(struct fpu *fpu) -{ - if (fpu_allocated(fpu)) - return 0; - fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); - if (!fpu->state) - return -ENOMEM; - WARN_ON((unsigned long)fpu->state & 15); - return 0; -} - -static inline void fpu_free(struct fpu *fpu) -{ - if (fpu->state) { - kmem_cache_free(task_xstate_cachep, fpu->state); - fpu->state = NULL; - } -} - -static inline void fpu_copy(struct fpu *dst, struct fpu *src) -{ - memcpy(dst->state, src->state, xstate_size); -} - -extern void fpu_finit(struct fpu *fpu); - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_I387_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cb71b01ab66e..89620b1725d4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 17b7549c4134..7734bcbb5a3a 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #ifdef CONFIG_X86_64 @@ -124,7 +125,7 @@ EXPORT_SYMBOL_GPL(xstate_size); unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32); static struct i387_fxsave_struct fx_scratch __cpuinitdata; -void __cpuinit mxcsr_feature_mask_init(void) +static void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 15763af7bfe3..c38d84e01022 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -21,6 +21,7 @@ #include #include #include +#include #include struct kmem_cache *task_xstate_cachep; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c08d1ff12b7c..ee32dee7a0a3 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #ifdef CONFIG_MATH_EMULATION #include diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index cfa5c90c01db..5bad3c71e48f 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 50267386b766..78f05e438be5 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 46a01bdc27e2..25edcfc9ba5b 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4bbe04d96744..ec61d4c1b93b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 711091114119..e62728e30b01 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -6,6 +6,7 @@ #include #include #include +#include #ifdef CONFIG_IA32_EMULATION #include #endif diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3b4c8d8ad906..246490f643b6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1457,7 +1457,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif - if (__thread_has_fpu(current)) + if (user_has_fpu()) clts(); load_gdt(&__get_cpu_var(host_gdt)); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9cbfc0698118..b937b6179d80 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -57,6 +57,7 @@ #include #include #include +#include /* Ugh! */ #include #include #include diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index f10c0afa1cb4..4889655ba784 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -20,6 +20,7 @@ #include #include #include +#include /* pcntxt_mask */ #ifdef CONFIG_X86_32 static struct saved_context saved_context; -- cgit v1.2.3 From bd2f55361f18347e890d52ff9cfd8895455ec11b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 21 Mar 2011 12:33:18 +0100 Subject: sched/rt: Use schedule_preempt_disabled() Coccinelle based conversion. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-24swm5zut3h9c4a6s46x8rws@git.kernel.org Signed-off-by: Ingo Molnar --- arch/arm/kernel/process.c | 4 +--- arch/avr32/kernel/process.c | 4 +--- arch/blackfin/kernel/process.c | 4 +--- arch/cris/kernel/process.c | 4 +--- arch/frv/kernel/process.c | 4 +--- arch/h8300/kernel/process.c | 4 +--- arch/ia64/kernel/process.c | 4 +--- arch/m32r/kernel/process.c | 4 +--- arch/m68k/kernel/process_mm.c | 4 +--- arch/m68k/kernel/process_no.c | 4 +--- arch/microblaze/kernel/process.c | 4 +--- arch/mips/kernel/process.c | 4 +--- arch/mn10300/kernel/process.c | 4 +--- arch/parisc/kernel/process.c | 4 +--- arch/powerpc/kernel/idle.c | 8 ++++---- arch/powerpc/platforms/iseries/setup.c | 8 ++------ arch/s390/kernel/process.c | 4 +--- arch/score/kernel/process.c | 4 +--- arch/sh/kernel/idle.c | 4 +--- arch/sparc/kernel/process_32.c | 8 ++------ arch/sparc/kernel/process_64.c | 10 ++++------ arch/tile/kernel/process.c | 4 +--- arch/x86/kernel/process_32.c | 4 +--- arch/x86/kernel/process_64.c | 4 +--- arch/xtensa/kernel/process.c | 4 +--- init/main.c | 5 +---- kernel/mutex.c | 4 +--- kernel/softirq.c | 4 +--- 28 files changed, 36 insertions(+), 95 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 971d65c253a9..c2ae3cd331fe 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -239,9 +239,7 @@ void cpu_idle(void) leds_event(led_idle_end); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index ea3395750324..92c5af98a6f7 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -40,9 +40,7 @@ void cpu_idle(void) cpu_idle_sleep(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 8dd0416673cb..a80a643f3691 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -94,9 +94,7 @@ void cpu_idle(void) idle(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index aa585e4e979e..d8f50ff6fadd 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -115,9 +115,7 @@ void cpu_idle (void) idle = default_idle; idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 3901df1213c0..29cc49783787 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -92,9 +92,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 933bd388efb2..1a173b35f475 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -81,9 +81,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6d33c5cc94f0..9dc52b63fc87 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -330,9 +330,7 @@ cpu_idle (void) normal_xtp(); #endif } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); if (cpu_is_offline(cpu)) play_dead(); diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 422bea9f1dbc..3a4a32b27208 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -90,9 +90,7 @@ void cpu_idle (void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process_mm.c b/arch/m68k/kernel/process_mm.c index 099283ee1a8f..fe4186b5fc32 100644 --- a/arch/m68k/kernel/process_mm.c +++ b/arch/m68k/kernel/process_mm.c @@ -78,9 +78,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process_no.c b/arch/m68k/kernel/process_no.c index 5e1078cabe0e..f7fe6c348595 100644 --- a/arch/m68k/kernel/process_no.c +++ b/arch/m68k/kernel/process_no.c @@ -73,9 +73,7 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 7dcb5bfffb75..9155f7d92669 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -110,9 +110,7 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 7955409051c4..61f1cb45a1d5 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -80,9 +80,7 @@ void __noreturn cpu_idle(void) #endif rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 28eec3102535..cac401d37f75 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -123,9 +123,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 62c60b87d039..d4b94b395c16 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -71,9 +71,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 0a48bf5db6c8..65035141552b 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -101,11 +101,11 @@ void cpu_idle(void) ppc64_runlatch_on(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - if (cpu_should_die()) + if (cpu_should_die()) { + preempt_enable_no_resched(); cpu_die(); - schedule(); - preempt_disable(); + } + schedule_preempt_disabled(); } } diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index 8fc62586a973..a5fbf4cb6329 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -584,9 +584,7 @@ static void iseries_shared_idle(void) if (hvlpevent_is_pending()) process_iSeries_events(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -615,9 +613,7 @@ static void iseries_dedicated_idle(void) ppc64_runlatch_on(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index e795933eb2cb..7618085b4164 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -97,9 +97,7 @@ void cpu_idle(void) tick_nohz_idle_exit(); if (test_thread_flag(TIF_MCCK_PENDING)) s390_handle_mcck(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index 25d08030a883..2707023c7563 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -53,9 +53,7 @@ void __noreturn cpu_idle(void) while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 406508d4ce74..7e4892826563 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -114,9 +114,7 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index f793742eec2b..935fdbcd88c2 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } @@ -138,9 +136,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 39d8b05201a2..ab9a29268213 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -104,15 +104,13 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(cpu)) + if (cpu_is_offline(cpu)) { + preempt_enable_no_resched(); cpu_play_dead(); + } #endif - - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 4c1ac6e5347a..6ae495ef2b99 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -108,9 +108,7 @@ void cpu_idle(void) } rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c08d1ff12b7c..49888fefe794 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -119,9 +119,7 @@ void cpu_idle(void) } rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index cfa5c90c01db..e34257c70c28 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -156,9 +156,7 @@ void cpu_idle(void) } tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 47041e7c088c..2c9004770c4e 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) platform_idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/init/main.c b/init/main.c index ff49a6dacfbb..4990f7ec776a 100644 --- a/init/main.c +++ b/init/main.c @@ -374,11 +374,8 @@ static noinline void __init_refok rest_init(void) * at least once to get things moving: */ init_idle_bootup_task(current); - preempt_enable_no_resched(); - schedule(); - + schedule_preempt_disabled(); /* Call into cpu_idle with preempt disabled */ - preempt_disable(); cpu_idle(); } diff --git a/kernel/mutex.c b/kernel/mutex.c index 89096dd8786f..a307cc9c9526 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -240,9 +240,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); spin_lock_mutex(&lock->wait_lock, flags); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 4eb3a0fa351e..79b524767a24 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -744,9 +744,7 @@ static int run_ksoftirqd(void * __bind_cpu) while (!kthread_should_stop()) { preempt_disable(); if (!local_softirq_pending()) { - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } __set_current_state(TASK_RUNNING); -- cgit v1.2.3 From 90e240142bd31ff10aeda5a280a53153f4eff004 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Sun, 25 Mar 2012 23:00:04 +0200 Subject: x86: Merge the x86_32 and x86_64 cpu_idle() functions Both functions are mostly identical. The differences are: - x86_32's cpu_idle() makes use of check_pgt_cache(), which is a nop on both x86_32 and x86_64. - x86_64's cpu_idle() uses enter/__exit_idle/(), on x86_32 these function are a nop. - In contrast to x86_32, x86_64 calls rcu_idle_enter/exit() in the innermost loop because idle notifications need RCU. Calling these function on x86_32 also in the innermost loop does not hurt. So we can merge both functions. Signed-off-by: Richard Weinberger Acked-by: Frederic Weisbecker Cc: paulmck@linux.vnet.ibm.com Cc: josh@joshtriplett.org Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1332709204-22496-1-git-send-email-richard@nod.at Signed-off-by: Ingo Molnar --- arch/x86/include/asm/idle.h | 1 + arch/x86/kernel/process.c | 114 +++++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/process_32.c | 58 ---------------------- arch/x86/kernel/process_64.c | 107 ---------------------------------------- 4 files changed, 115 insertions(+), 165 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h index f49253d75710..c5d1785373ed 100644 --- a/arch/x86/include/asm/idle.h +++ b/arch/x86/include/asm/idle.h @@ -14,6 +14,7 @@ void exit_idle(void); #else /* !CONFIG_X86_64 */ static inline void enter_idle(void) { } static inline void exit_idle(void) { } +static inline void __exit_idle(void) { } #endif /* CONFIG_X86_64 */ void amd_e400_remove_cpu(int cpu); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 14baf78d5a1f..29309c42b9e5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -12,6 +12,9 @@ #include #include #include +#include +#include +#include #include #include #include @@ -23,6 +26,24 @@ #include #include #include +#include + +#ifdef CONFIG_X86_64 +static DEFINE_PER_CPU(unsigned char, is_idle); +static ATOMIC_NOTIFIER_HEAD(idle_notifier); + +void idle_notifier_register(struct notifier_block *n) +{ + atomic_notifier_chain_register(&idle_notifier, n); +} +EXPORT_SYMBOL_GPL(idle_notifier_register); + +void idle_notifier_unregister(struct notifier_block *n) +{ + atomic_notifier_chain_unregister(&idle_notifier, n); +} +EXPORT_SYMBOL_GPL(idle_notifier_unregister); +#endif struct kmem_cache *task_xstate_cachep; EXPORT_SYMBOL_GPL(task_xstate_cachep); @@ -371,6 +392,99 @@ static inline int hlt_use_halt(void) } #endif +#ifndef CONFIG_SMP +static inline void play_dead(void) +{ + BUG(); +} +#endif + +#ifdef CONFIG_X86_64 +void enter_idle(void) +{ + percpu_write(is_idle, 1); + atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); +} + +static void __exit_idle(void) +{ + if (x86_test_and_clear_bit_percpu(0, is_idle) == 0) + return; + atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); +} + +/* Called from interrupts to signify idle end */ +void exit_idle(void) +{ + /* idle loop has pid 0 */ + if (current->pid) + return; + __exit_idle(); +} +#endif + +/* + * The idle thread. There's no useful work to be + * done, so just try to conserve power and have a + * low exit latency (ie sit in a loop waiting for + * somebody to say that they'd like to reschedule) + */ +void cpu_idle(void) +{ + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. CPU0 already has it initialized but no harm in + * doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); + current_thread_info()->status |= TS_POLLING; + + while (1) { + tick_nohz_idle_enter(); + + while (!need_resched()) { + rmb(); + + if (cpu_is_offline(smp_processor_id())) + play_dead(); + + /* + * Idle routines should keep interrupts disabled + * from here on, until they go to idle. + * Otherwise, idle callbacks can misfire. + */ + local_touch_nmi(); + local_irq_disable(); + + enter_idle(); + + /* Don't trace irqs off for idle */ + stop_critical_timings(); + + /* enter_idle() needs rcu for notifiers */ + rcu_idle_enter(); + + if (cpuidle_idle_call()) + pm_idle(); + + rcu_idle_exit(); + start_critical_timings(); + + /* In many cases the interrupt that ended idle + has already called exit_idle. But some idle + loops can be woken up without interrupt. */ + __exit_idle(); + } + + tick_nohz_idle_exit(); + preempt_enable_no_resched(); + schedule(); + preempt_disable(); + } +} + /* * We use this if we don't have any better * idle routine.. diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 9d7d4842bfaf..ea207c245aa4 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -9,7 +9,6 @@ * This file handles the architecture-dependent parts of process handling.. */ -#include #include #include #include @@ -31,14 +30,12 @@ #include #include #include -#include #include #include #include #include #include #include -#include #include #include @@ -58,7 +55,6 @@ #include #include #include -#include asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); @@ -70,60 +66,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return ((unsigned long *)tsk->thread.sp)[3]; } -#ifndef CONFIG_SMP -static inline void play_dead(void) -{ - BUG(); -} -#endif - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - int cpu = smp_processor_id(); - - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. CPU0 already has it initialized but no harm in - * doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); - - current_thread_info()->status |= TS_POLLING; - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) { - - check_pgt_cache(); - rmb(); - - if (cpu_is_offline(cpu)) - play_dead(); - - local_touch_nmi(); - local_irq_disable(); - /* Don't trace irqs off for idle */ - stop_critical_timings(); - if (cpuidle_idle_call()) - pm_idle(); - start_critical_timings(); - } - rcu_idle_exit(); - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } -} - void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 292da13fc5aa..ce5e34f2beca 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -14,7 +14,6 @@ * This file handles the architecture-dependent parts of process handling.. */ -#include #include #include #include @@ -32,12 +31,10 @@ #include #include #include -#include #include #include #include #include -#include #include #include @@ -52,114 +49,10 @@ #include #include #include -#include asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); -static DEFINE_PER_CPU(unsigned char, is_idle); - -static ATOMIC_NOTIFIER_HEAD(idle_notifier); - -void idle_notifier_register(struct notifier_block *n) -{ - atomic_notifier_chain_register(&idle_notifier, n); -} -EXPORT_SYMBOL_GPL(idle_notifier_register); - -void idle_notifier_unregister(struct notifier_block *n) -{ - atomic_notifier_chain_unregister(&idle_notifier, n); -} -EXPORT_SYMBOL_GPL(idle_notifier_unregister); - -void enter_idle(void) -{ - percpu_write(is_idle, 1); - atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); -} - -static void __exit_idle(void) -{ - if (x86_test_and_clear_bit_percpu(0, is_idle) == 0) - return; - atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); -} - -/* Called from interrupts to signify idle end */ -void exit_idle(void) -{ - /* idle loop has pid 0 */ - if (current->pid) - return; - __exit_idle(); -} - -#ifndef CONFIG_SMP -static inline void play_dead(void) -{ - BUG(); -} -#endif - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - current_thread_info()->status |= TS_POLLING; - - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. CPU0 already has it initialized but no harm in - * doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - while (!need_resched()) { - - rmb(); - - if (cpu_is_offline(smp_processor_id())) - play_dead(); - /* - * Idle routines should keep interrupts disabled - * from here on, until they go to idle. - * Otherwise, idle callbacks can misfire. - */ - local_touch_nmi(); - local_irq_disable(); - enter_idle(); - /* Don't trace irqs off for idle */ - stop_critical_timings(); - - /* enter_idle() needs rcu for notifiers */ - rcu_idle_enter(); - - if (cpuidle_idle_call()) - pm_idle(); - - rcu_idle_exit(); - start_critical_timings(); - - /* In many cases the interrupt that ended idle - has already called exit_idle. But some idle - loops can be woken up without interrupt. */ - __exit_idle(); - } - - tick_nohz_idle_exit(); - schedule_preempt_disabled(); - } -} /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, int all) -- cgit v1.2.3 From f05e798ad4c09255f590f5b2c00a7ca6c172f983 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 28 Mar 2012 18:11:12 +0100 Subject: Disintegrate asm/system.h for X86 Disintegrate asm/system.h for X86. Signed-off-by: David Howells Acked-by: H. Peter Anvin cc: x86@kernel.org --- arch/x86/ia32/ia32_aout.c | 1 - arch/x86/include/asm/apic.h | 1 - arch/x86/include/asm/auxvec.h | 7 + arch/x86/include/asm/barrier.h | 116 +++++++ arch/x86/include/asm/bug.h | 4 + arch/x86/include/asm/cacheflush.h | 1 + arch/x86/include/asm/elf.h | 1 - arch/x86/include/asm/exec.h | 1 + arch/x86/include/asm/futex.h | 1 - arch/x86/include/asm/i387.h | 1 - arch/x86/include/asm/local.h | 1 - arch/x86/include/asm/mc146818rtc.h | 1 - arch/x86/include/asm/processor.h | 31 +- arch/x86/include/asm/segment.h | 58 +++- arch/x86/include/asm/special_insns.h | 199 ++++++++++++ arch/x86/include/asm/stackprotector.h | 1 - arch/x86/include/asm/switch_to.h | 129 ++++++++ arch/x86/include/asm/system.h | 527 +------------------------------ arch/x86/include/asm/tlbflush.h | 2 +- arch/x86/include/asm/virtext.h | 1 - arch/x86/kernel/acpi/cstate.c | 1 + arch/x86/kernel/apm_32.c | 1 - arch/x86/kernel/cpu/mcheck/p5.c | 1 - arch/x86/kernel/cpu/mcheck/therm_throt.c | 1 - arch/x86/kernel/cpu/mcheck/winchip.c | 1 - arch/x86/kernel/cpu/mtrr/generic.c | 1 - arch/x86/kernel/cpuid.c | 1 - arch/x86/kernel/i8259.c | 1 - arch/x86/kernel/irqinit.c | 1 - arch/x86/kernel/kgdb.c | 1 - arch/x86/kernel/ldt.c | 1 - arch/x86/kernel/machine_kexec_32.c | 1 - arch/x86/kernel/mca_32.c | 1 - arch/x86/kernel/module.c | 1 - arch/x86/kernel/msr.c | 1 - arch/x86/kernel/paravirt.c | 1 + arch/x86/kernel/pci-calgary_64.c | 1 - arch/x86/kernel/process.c | 1 - arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- arch/x86/kernel/ptrace.c | 1 - arch/x86/kernel/setup.c | 1 - arch/x86/kernel/tce_64.c | 1 + arch/x86/kernel/tls.c | 1 - arch/x86/kernel/traps.c | 1 - arch/x86/mm/init.c | 1 - arch/x86/mm/init_32.c | 1 - arch/x86/mm/init_64.c | 1 - arch/x86/mm/pgtable_32.c | 1 - arch/x86/power/hibernate_32.c | 1 - 50 files changed, 554 insertions(+), 562 deletions(-) create mode 100644 arch/x86/include/asm/barrier.h create mode 100644 arch/x86/include/asm/exec.h create mode 100644 arch/x86/include/asm/special_insns.h create mode 100644 arch/x86/include/asm/switch_to.h (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 4c2e59a420b9..d511d951a052 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -26,7 +26,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a9371c91718c..4b2caeefe1a2 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #define ARCH_APICTIMER_STOPS_ON_C3 1 diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h index 1316b4c35425..77203ac352de 100644 --- a/arch/x86/include/asm/auxvec.h +++ b/arch/x86/include/asm/auxvec.h @@ -9,4 +9,11 @@ #endif #define AT_SYSINFO_EHDR 33 +/* entries in ARCH_DLINFO: */ +#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) +# define AT_VECTOR_SIZE_ARCH 2 +#else /* else it's non-compat x86-64 */ +# define AT_VECTOR_SIZE_ARCH 1 +#endif + #endif /* _ASM_X86_AUXVEC_H */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h new file mode 100644 index 000000000000..c6cd358a1eec --- /dev/null +++ b/arch/x86/include/asm/barrier.h @@ -0,0 +1,116 @@ +#ifndef _ASM_X86_BARRIER_H +#define _ASM_X86_BARRIER_H + +#include +#include + +/* + * Force strict CPU ordering. + * And yes, this is required on UP too when we're talking + * to devices. + */ + +#ifdef CONFIG_X86_32 +/* + * Some non-Intel clones support out of order store. wmb() ceases to be a + * nop for these. + */ +#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) +#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#else +#define mb() asm volatile("mfence":::"memory") +#define rmb() asm volatile("lfence":::"memory") +#define wmb() asm volatile("sfence" ::: "memory") +#endif + +/** + * read_barrier_depends - Flush all pending reads that subsequents reads + * depend on. + * + * No data-dependent reads from memory-like regions are ever reordered + * over this barrier. All reads preceding this primitive are guaranteed + * to access memory (but not necessarily other CPUs' caches) before any + * reads following this primitive that depend on the data return by + * any of the preceding reads. This primitive is much lighter weight than + * rmb() on most CPUs, and is never heavier weight than is + * rmb(). + * + * These ordering constraints are respected by both the local CPU + * and the compiler. + * + * Ordering is not guaranteed by anything other than these primitives, + * not even by data dependencies. See the documentation for + * memory_barrier() for examples and URLs to more information. + * + * For example, the following code would force ordering (the initial + * value of "a" is zero, "b" is one, and "p" is "&a"): + * + * + * CPU 0 CPU 1 + * + * b = 2; + * memory_barrier(); + * p = &b; q = p; + * read_barrier_depends(); + * d = *q; + * + * + * because the read of "*q" depends on the read of "p" and these + * two reads are separated by a read_barrier_depends(). However, + * the following code, with the same initial values for "a" and "b": + * + * + * CPU 0 CPU 1 + * + * a = 2; + * memory_barrier(); + * b = 3; y = b; + * read_barrier_depends(); + * x = a; + * + * + * does not enforce ordering, since there is no data dependency between + * the read of "a" and the read of "b". Therefore, on some CPUs, such + * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() + * in cases like this where there are no data dependencies. + **/ + +#define read_barrier_depends() do { } while (0) + +#ifdef CONFIG_SMP +#define smp_mb() mb() +#ifdef CONFIG_X86_PPRO_FENCE +# define smp_rmb() rmb() +#else +# define smp_rmb() barrier() +#endif +#ifdef CONFIG_X86_OOSTORE +# define smp_wmb() wmb() +#else +# define smp_wmb() barrier() +#endif +#define smp_read_barrier_depends() read_barrier_depends() +#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) +#else +#define smp_mb() barrier() +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_read_barrier_depends() do { } while (0) +#define set_mb(var, value) do { var = value; barrier(); } while (0) +#endif + +/* + * Stop RDTSC speculation. This is needed when you need to use RDTSC + * (or get_cycles or vread that possibly accesses the TSC) in a defined + * code region. + * + * (Could use an alternative three way for this if there was one.) + */ +static __always_inline void rdtsc_barrier(void) +{ + alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); + alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); +} + +#endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index f654d1bb17fb..11e1152222d0 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -36,4 +36,8 @@ do { \ #endif /* !CONFIG_BUG */ #include + + +extern void show_regs_common(void); + #endif /* _ASM_X86_BUG_H */ diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 4e12668711e5..9863ee3747da 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -3,6 +3,7 @@ /* Caches aren't brain-dead on the intel. */ #include +#include #ifdef CONFIG_X86_PAT /* diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 5f962df30d0f..f27f79abe021 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -84,7 +84,6 @@ extern unsigned int vdso_enabled; (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486)) #include -#include #ifdef CONFIG_X86_32 #include diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h new file mode 100644 index 000000000000..54c2e1db274a --- /dev/null +++ b/arch/x86/include/asm/exec.h @@ -0,0 +1 @@ +/* define arch_align_stack() here */ diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index d09bb03653f0..71ecbcba1a4e 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -9,7 +9,6 @@ #include #include #include -#include #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \ asm volatile("1:\t" insn "\n" \ diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 7ce0798b1b26..257d9cca214f 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -14,7 +14,6 @@ #include #include -#include struct pt_regs; struct user_i387_struct; diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 9cdae5d47e8f..c8bed0da434a 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -3,7 +3,6 @@ #include -#include #include #include diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 0e8e85bb7c51..d354fb781c57 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -5,7 +5,6 @@ #define _ASM_X86_MC146818RTC_H #include -#include #include #include diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 95da14f7ee85..78e30ea492b2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -14,13 +14,13 @@ struct mm_struct; #include #include #include -#include #include #include #include #include #include #include +#include #include #include @@ -29,6 +29,15 @@ struct mm_struct; #include #include #include +#include + +/* + * We handle most unaligned accesses in hardware. On the other hand + * unaligned DMA can be quite expensive on some Nehalem processors. + * + * Based on this we disable the IP header alignment in network drivers. + */ +#define NET_IP_ALIGN 0 #define HBP_NUM 4 /* @@ -1022,4 +1031,24 @@ extern bool cpu_has_amd_erratum(const int *); #define cpu_has_amd_erratum(x) (false) #endif /* CONFIG_CPU_SUP_AMD */ +#ifdef CONFIG_X86_32 +/* + * disable hlt during certain critical i/o operations + */ +#define HAVE_DISABLE_HLT +#endif + +void disable_hlt(void); +void enable_hlt(void); + +void cpu_idle_wait(void); + +extern unsigned long arch_align_stack(unsigned long sp); +extern void free_init_pages(char *what, unsigned long begin, unsigned long end); + +void default_idle(void); +bool set_pm_idle_to_default(void); + +void stop_this_cpu(void *dummy); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 5e641715c3fe..165466233ab0 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -212,7 +212,61 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10]; -#endif -#endif + +/* + * Load a segment. Fall back on loading the zero + * segment if something goes wrong.. + */ +#define loadsegment(seg, value) \ +do { \ + unsigned short __val = (value); \ + \ + asm volatile(" \n" \ + "1: movl %k0,%%" #seg " \n" \ + \ + ".section .fixup,\"ax\" \n" \ + "2: xorl %k0,%k0 \n" \ + " jmp 1b \n" \ + ".previous \n" \ + \ + _ASM_EXTABLE(1b, 2b) \ + \ + : "+r" (__val) : : "memory"); \ +} while (0) + +/* + * Save a segment register away + */ +#define savesegment(seg, value) \ + asm("mov %%" #seg ",%0":"=r" (value) : : "memory") + +/* + * x86_32 user gs accessors. + */ +#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_32_LAZY_GS +#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) +#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) +#define task_user_gs(tsk) ((tsk)->thread.gs) +#define lazy_save_gs(v) savesegment(gs, (v)) +#define lazy_load_gs(v) loadsegment(gs, (v)) +#else /* X86_32_LAZY_GS */ +#define get_user_gs(regs) (u16)((regs)->gs) +#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) +#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) +#define lazy_save_gs(v) do { } while (0) +#define lazy_load_gs(v) do { } while (0) +#endif /* X86_32_LAZY_GS */ +#endif /* X86_32 */ + +static inline unsigned long get_limit(unsigned long segment) +{ + unsigned long __limit; + asm("lsll %1,%0" : "=r" (__limit) : "r" (segment)); + return __limit + 1; +} + +#endif /* !__ASSEMBLY__ */ +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SEGMENT_H */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h new file mode 100644 index 000000000000..41fc93a2e225 --- /dev/null +++ b/arch/x86/include/asm/special_insns.h @@ -0,0 +1,199 @@ +#ifndef _ASM_X86_SPECIAL_INSNS_H +#define _ASM_X86_SPECIAL_INSNS_H + + +#ifdef __KERNEL__ + +static inline void native_clts(void) +{ + asm volatile("clts"); +} + +/* + * Volatile isn't enough to prevent the compiler from reordering the + * read/write functions for the control registers and messing everything up. + * A memory clobber would solve the problem, but would prevent reordering of + * all loads stores around it, which can hurt performance. Solution is to + * use a variable and mimic reads and writes to it to enforce serialization + */ +static unsigned long __force_order; + +static inline unsigned long native_read_cr0(void) +{ + unsigned long val; + asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr0(unsigned long val) +{ + asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr2(void) +{ + unsigned long val; + asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr2(unsigned long val) +{ + asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr3(void) +{ + unsigned long val; + asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr3(unsigned long val) +{ + asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr4(void) +{ + unsigned long val; + asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline unsigned long native_read_cr4_safe(void) +{ + unsigned long val; + /* This could fault if %cr4 does not exist. In x86_64, a cr4 always + * exists, so it will never fail. */ +#ifdef CONFIG_X86_32 + asm volatile("1: mov %%cr4, %0\n" + "2:\n" + _ASM_EXTABLE(1b, 2b) + : "=r" (val), "=m" (__force_order) : "0" (0)); +#else + val = native_read_cr4(); +#endif + return val; +} + +static inline void native_write_cr4(unsigned long val) +{ + asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); +} + +#ifdef CONFIG_X86_64 +static inline unsigned long native_read_cr8(void) +{ + unsigned long cr8; + asm volatile("movq %%cr8,%0" : "=r" (cr8)); + return cr8; +} + +static inline void native_write_cr8(unsigned long val) +{ + asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); +} +#endif + +static inline void native_wbinvd(void) +{ + asm volatile("wbinvd": : :"memory"); +} + +extern void native_load_gs_index(unsigned); + +#ifdef CONFIG_PARAVIRT +#include +#else + +static inline unsigned long read_cr0(void) +{ + return native_read_cr0(); +} + +static inline void write_cr0(unsigned long x) +{ + native_write_cr0(x); +} + +static inline unsigned long read_cr2(void) +{ + return native_read_cr2(); +} + +static inline void write_cr2(unsigned long x) +{ + native_write_cr2(x); +} + +static inline unsigned long read_cr3(void) +{ + return native_read_cr3(); +} + +static inline void write_cr3(unsigned long x) +{ + native_write_cr3(x); +} + +static inline unsigned long read_cr4(void) +{ + return native_read_cr4(); +} + +static inline unsigned long read_cr4_safe(void) +{ + return native_read_cr4_safe(); +} + +static inline void write_cr4(unsigned long x) +{ + native_write_cr4(x); +} + +static inline void wbinvd(void) +{ + native_wbinvd(); +} + +#ifdef CONFIG_X86_64 + +static inline unsigned long read_cr8(void) +{ + return native_read_cr8(); +} + +static inline void write_cr8(unsigned long x) +{ + native_write_cr8(x); +} + +static inline void load_gs_index(unsigned selector) +{ + native_load_gs_index(selector); +} + +#endif + +/* Clear the 'TS' bit */ +static inline void clts(void) +{ + native_clts(); +} + +#endif/* CONFIG_PARAVIRT */ + +#define stts() write_cr0(read_cr0() | X86_CR0_TS) + +static inline void clflush(volatile void *__p) +{ + asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); +} + +#define nop() asm volatile ("nop") + + +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_SPECIAL_INSNS_H */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 157517763565..b5d9533d2c38 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -38,7 +38,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h new file mode 100644 index 000000000000..4ec45b3abba1 --- /dev/null +++ b/arch/x86/include/asm/switch_to.h @@ -0,0 +1,129 @@ +#ifndef _ASM_X86_SWITCH_TO_H +#define _ASM_X86_SWITCH_TO_H + +struct task_struct; /* one of the stranger aspects of C forward declarations */ +struct task_struct *__switch_to(struct task_struct *prev, + struct task_struct *next); +struct tss_struct; +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss); + +#ifdef CONFIG_X86_32 + +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movl %P[task_canary](%[next]), %%ebx\n\t" \ + "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" +#define __switch_canary_oparam \ + , [stack_canary] "=m" (stack_canary.canary) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + +/* + * Saving eflags is important. It switches not only IOPL between tasks, + * it also protects other tasks from NT leaking through sysenter etc. + */ +#define switch_to(prev, next, last) \ +do { \ + /* \ + * Context-switching clobbers all registers, so we clobber \ + * them explicitly, via unused output variables. \ + * (EAX and EBP is not listed because EBP is saved/restored \ + * explicitly for wchan access and EAX is the return value of \ + * __switch_to()) \ + */ \ + unsigned long ebx, ecx, edx, esi, edi; \ + \ + asm volatile("pushfl\n\t" /* save flags */ \ + "pushl %%ebp\n\t" /* save EBP */ \ + "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ + "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ + "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ + "pushl %[next_ip]\n\t" /* restore EIP */ \ + __switch_canary \ + "jmp __switch_to\n" /* regparm call */ \ + "1:\t" \ + "popl %%ebp\n\t" /* restore EBP */ \ + "popfl\n" /* restore flags */ \ + \ + /* output parameters */ \ + : [prev_sp] "=m" (prev->thread.sp), \ + [prev_ip] "=m" (prev->thread.ip), \ + "=a" (last), \ + \ + /* clobbered output registers: */ \ + "=b" (ebx), "=c" (ecx), "=d" (edx), \ + "=S" (esi), "=D" (edi) \ + \ + __switch_canary_oparam \ + \ + /* input parameters: */ \ + : [next_sp] "m" (next->thread.sp), \ + [next_ip] "m" (next->thread.ip), \ + \ + /* regparm parameters for __switch_to(): */ \ + [prev] "a" (prev), \ + [next] "d" (next) \ + \ + __switch_canary_iparam \ + \ + : /* reloaded segment registers */ \ + "memory"); \ +} while (0) + +#else /* CONFIG_X86_32 */ + +/* frame pointer must be last for get_wchan */ +#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" +#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" + +#define __EXTRA_CLOBBER \ + , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ + "r12", "r13", "r14", "r15" + +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movq %P[task_canary](%%rsi),%%r8\n\t" \ + "movq %%r8,"__percpu_arg([gs_canary])"\n\t" +#define __switch_canary_oparam \ + , [gs_canary] "=m" (irq_stack_union.stack_canary) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + +/* Save restore flags to clear handle leaking NT */ +#define switch_to(prev, next, last) \ + asm volatile(SAVE_CONTEXT \ + "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ + "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ + "call __switch_to\n\t" \ + "movq "__percpu_arg([current_task])",%%rsi\n\t" \ + __switch_canary \ + "movq %P[thread_info](%%rsi),%%r8\n\t" \ + "movq %%rax,%%rdi\n\t" \ + "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ + "jnz ret_from_fork\n\t" \ + RESTORE_CONTEXT \ + : "=a" (last) \ + __switch_canary_oparam \ + : [next] "S" (next), [prev] "D" (prev), \ + [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ + [ti_flags] "i" (offsetof(struct thread_info, flags)), \ + [_tif_fork] "i" (_TIF_FORK), \ + [thread_info] "i" (offsetof(struct task_struct, stack)), \ + [current_task] "m" (current_task) \ + __switch_canary_iparam \ + : "memory", "cc" __EXTRA_CLOBBER) + +#endif /* CONFIG_X86_32 */ + +#endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index 2d2f01ce6dcb..0d84f9e42fde 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -1,523 +1,6 @@ -#ifndef _ASM_X86_SYSTEM_H -#define _ASM_X86_SYSTEM_H - -#include -#include -#include +/* FILE TO BE DELETED. DO NOT ADD STUFF HERE! */ +#include #include -#include - -#include -#include - -/* entries in ARCH_DLINFO: */ -#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) -# define AT_VECTOR_SIZE_ARCH 2 -#else /* else it's non-compat x86-64 */ -# define AT_VECTOR_SIZE_ARCH 1 -#endif - -struct task_struct; /* one of the stranger aspects of C forward declarations */ -struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *next); -struct tss_struct; -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss); -extern void show_regs_common(void); - -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movl %P[task_canary](%[next]), %%ebx\n\t" \ - "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" -#define __switch_canary_oparam \ - , [stack_canary] "=m" (stack_canary.canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* - * Saving eflags is important. It switches not only IOPL between tasks, - * it also protects other tasks from NT leaking through sysenter etc. - */ -#define switch_to(prev, next, last) \ -do { \ - /* \ - * Context-switching clobbers all registers, so we clobber \ - * them explicitly, via unused output variables. \ - * (EAX and EBP is not listed because EBP is saved/restored \ - * explicitly for wchan access and EAX is the return value of \ - * __switch_to()) \ - */ \ - unsigned long ebx, ecx, edx, esi, edi; \ - \ - asm volatile("pushfl\n\t" /* save flags */ \ - "pushl %%ebp\n\t" /* save EBP */ \ - "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ - "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ - "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ - "pushl %[next_ip]\n\t" /* restore EIP */ \ - __switch_canary \ - "jmp __switch_to\n" /* regparm call */ \ - "1:\t" \ - "popl %%ebp\n\t" /* restore EBP */ \ - "popfl\n" /* restore flags */ \ - \ - /* output parameters */ \ - : [prev_sp] "=m" (prev->thread.sp), \ - [prev_ip] "=m" (prev->thread.ip), \ - "=a" (last), \ - \ - /* clobbered output registers: */ \ - "=b" (ebx), "=c" (ecx), "=d" (edx), \ - "=S" (esi), "=D" (edi) \ - \ - __switch_canary_oparam \ - \ - /* input parameters: */ \ - : [next_sp] "m" (next->thread.sp), \ - [next_ip] "m" (next->thread.ip), \ - \ - /* regparm parameters for __switch_to(): */ \ - [prev] "a" (prev), \ - [next] "d" (next) \ - \ - __switch_canary_iparam \ - \ - : /* reloaded segment registers */ \ - "memory"); \ -} while (0) - -/* - * disable hlt during certain critical i/o operations - */ -#define HAVE_DISABLE_HLT -#else - -/* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" - -#define __EXTRA_CLOBBER \ - , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15" - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movq %P[task_canary](%%rsi),%%r8\n\t" \ - "movq %%r8,"__percpu_arg([gs_canary])"\n\t" -#define __switch_canary_oparam \ - , [gs_canary] "=m" (irq_stack_union.stack_canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* Save restore flags to clear handle leaking NT */ -#define switch_to(prev, next, last) \ - asm volatile(SAVE_CONTEXT \ - "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ - "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ - "call __switch_to\n\t" \ - "movq "__percpu_arg([current_task])",%%rsi\n\t" \ - __switch_canary \ - "movq %P[thread_info](%%rsi),%%r8\n\t" \ - "movq %%rax,%%rdi\n\t" \ - "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ - "jnz ret_from_fork\n\t" \ - RESTORE_CONTEXT \ - : "=a" (last) \ - __switch_canary_oparam \ - : [next] "S" (next), [prev] "D" (prev), \ - [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ - [ti_flags] "i" (offsetof(struct thread_info, flags)), \ - [_tif_fork] "i" (_TIF_FORK), \ - [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [current_task] "m" (current_task) \ - __switch_canary_iparam \ - : "memory", "cc" __EXTRA_CLOBBER) -#endif - -#ifdef __KERNEL__ - -extern void native_load_gs_index(unsigned); - -/* - * Load a segment. Fall back on loading the zero - * segment if something goes wrong.. - */ -#define loadsegment(seg, value) \ -do { \ - unsigned short __val = (value); \ - \ - asm volatile(" \n" \ - "1: movl %k0,%%" #seg " \n" \ - \ - ".section .fixup,\"ax\" \n" \ - "2: xorl %k0,%k0 \n" \ - " jmp 1b \n" \ - ".previous \n" \ - \ - _ASM_EXTABLE(1b, 2b) \ - \ - : "+r" (__val) : : "memory"); \ -} while (0) - -/* - * Save a segment register away - */ -#define savesegment(seg, value) \ - asm("mov %%" #seg ",%0":"=r" (value) : : "memory") - -/* - * x86_32 user gs accessors. - */ -#ifdef CONFIG_X86_32 -#ifdef CONFIG_X86_32_LAZY_GS -#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) -#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) -#define task_user_gs(tsk) ((tsk)->thread.gs) -#define lazy_save_gs(v) savesegment(gs, (v)) -#define lazy_load_gs(v) loadsegment(gs, (v)) -#else /* X86_32_LAZY_GS */ -#define get_user_gs(regs) (u16)((regs)->gs) -#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) -#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) -#define lazy_save_gs(v) do { } while (0) -#define lazy_load_gs(v) do { } while (0) -#endif /* X86_32_LAZY_GS */ -#endif /* X86_32 */ - -static inline unsigned long get_limit(unsigned long segment) -{ - unsigned long __limit; - asm("lsll %1,%0" : "=r" (__limit) : "r" (segment)); - return __limit + 1; -} - -static inline void native_clts(void) -{ - asm volatile("clts"); -} - -/* - * Volatile isn't enough to prevent the compiler from reordering the - * read/write functions for the control registers and messing everything up. - * A memory clobber would solve the problem, but would prevent reordering of - * all loads stores around it, which can hurt performance. Solution is to - * use a variable and mimic reads and writes to it to enforce serialization - */ -static unsigned long __force_order; - -static inline unsigned long native_read_cr0(void) -{ - unsigned long val; - asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr0(unsigned long val) -{ - asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr2(void) -{ - unsigned long val; - asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr2(unsigned long val) -{ - asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr3(void) -{ - unsigned long val; - asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr3(unsigned long val) -{ - asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr4(void) -{ - unsigned long val; - asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline unsigned long native_read_cr4_safe(void) -{ - unsigned long val; - /* This could fault if %cr4 does not exist. In x86_64, a cr4 always - * exists, so it will never fail. */ -#ifdef CONFIG_X86_32 - asm volatile("1: mov %%cr4, %0\n" - "2:\n" - _ASM_EXTABLE(1b, 2b) - : "=r" (val), "=m" (__force_order) : "0" (0)); -#else - val = native_read_cr4(); -#endif - return val; -} - -static inline void native_write_cr4(unsigned long val) -{ - asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); -} - -#ifdef CONFIG_X86_64 -static inline unsigned long native_read_cr8(void) -{ - unsigned long cr8; - asm volatile("movq %%cr8,%0" : "=r" (cr8)); - return cr8; -} - -static inline void native_write_cr8(unsigned long val) -{ - asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); -} -#endif - -static inline void native_wbinvd(void) -{ - asm volatile("wbinvd": : :"memory"); -} - -#ifdef CONFIG_PARAVIRT -#include -#else - -static inline unsigned long read_cr0(void) -{ - return native_read_cr0(); -} - -static inline void write_cr0(unsigned long x) -{ - native_write_cr0(x); -} - -static inline unsigned long read_cr2(void) -{ - return native_read_cr2(); -} - -static inline void write_cr2(unsigned long x) -{ - native_write_cr2(x); -} - -static inline unsigned long read_cr3(void) -{ - return native_read_cr3(); -} - -static inline void write_cr3(unsigned long x) -{ - native_write_cr3(x); -} - -static inline unsigned long read_cr4(void) -{ - return native_read_cr4(); -} - -static inline unsigned long read_cr4_safe(void) -{ - return native_read_cr4_safe(); -} - -static inline void write_cr4(unsigned long x) -{ - native_write_cr4(x); -} - -static inline void wbinvd(void) -{ - native_wbinvd(); -} - -#ifdef CONFIG_X86_64 - -static inline unsigned long read_cr8(void) -{ - return native_read_cr8(); -} - -static inline void write_cr8(unsigned long x) -{ - native_write_cr8(x); -} - -static inline void load_gs_index(unsigned selector) -{ - native_load_gs_index(selector); -} - -#endif - -/* Clear the 'TS' bit */ -static inline void clts(void) -{ - native_clts(); -} - -#endif/* CONFIG_PARAVIRT */ - -#define stts() write_cr0(read_cr0() | X86_CR0_TS) - -#endif /* __KERNEL__ */ - -static inline void clflush(volatile void *__p) -{ - asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); -} - -#define nop() asm volatile ("nop") - -void disable_hlt(void); -void enable_hlt(void); - -void cpu_idle_wait(void); - -extern unsigned long arch_align_stack(unsigned long sp); -extern void free_init_pages(char *what, unsigned long begin, unsigned long end); - -void default_idle(void); -bool set_pm_idle_to_default(void); - -void stop_this_cpu(void *dummy); - -/* - * Force strict CPU ordering. - * And yes, this is required on UP too when we're talking - * to devices. - */ -#ifdef CONFIG_X86_32 -/* - * Some non-Intel clones support out of order store. wmb() ceases to be a - * nop for these. - */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) -#else -#define mb() asm volatile("mfence":::"memory") -#define rmb() asm volatile("lfence":::"memory") -#define wmb() asm volatile("sfence" ::: "memory") -#endif - -/** - * read_barrier_depends - Flush all pending reads that subsequents reads - * depend on. - * - * No data-dependent reads from memory-like regions are ever reordered - * over this barrier. All reads preceding this primitive are guaranteed - * to access memory (but not necessarily other CPUs' caches) before any - * reads following this primitive that depend on the data return by - * any of the preceding reads. This primitive is much lighter weight than - * rmb() on most CPUs, and is never heavier weight than is - * rmb(). - * - * These ordering constraints are respected by both the local CPU - * and the compiler. - * - * Ordering is not guaranteed by anything other than these primitives, - * not even by data dependencies. See the documentation for - * memory_barrier() for examples and URLs to more information. - * - * For example, the following code would force ordering (the initial - * value of "a" is zero, "b" is one, and "p" is "&a"): - * - * - * CPU 0 CPU 1 - * - * b = 2; - * memory_barrier(); - * p = &b; q = p; - * read_barrier_depends(); - * d = *q; - * - * - * because the read of "*q" depends on the read of "p" and these - * two reads are separated by a read_barrier_depends(). However, - * the following code, with the same initial values for "a" and "b": - * - * - * CPU 0 CPU 1 - * - * a = 2; - * memory_barrier(); - * b = 3; y = b; - * read_barrier_depends(); - * x = a; - * - * - * does not enforce ordering, since there is no data dependency between - * the read of "a" and the read of "b". Therefore, on some CPUs, such - * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() - * in cases like this where there are no data dependencies. - **/ - -#define read_barrier_depends() do { } while (0) - -#ifdef CONFIG_SMP -#define smp_mb() mb() -#ifdef CONFIG_X86_PPRO_FENCE -# define smp_rmb() rmb() -#else -# define smp_rmb() barrier() -#endif -#ifdef CONFIG_X86_OOSTORE -# define smp_wmb() wmb() -#else -# define smp_wmb() barrier() -#endif -#define smp_read_barrier_depends() read_barrier_depends() -#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do { } while (0) -#define set_mb(var, value) do { var = value; barrier(); } while (0) -#endif - -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - * - * (Could use an alternative three way for this if there was one.) - */ -static __always_inline void rdtsc_barrier(void) -{ - alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); - alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); -} - -/* - * We handle most unaligned accesses in hardware. On the other hand - * unaligned DMA can be quite expensive on some Nehalem processors. - * - * Based on this we disable the IP header alignment in network drivers. - */ -#define NET_IP_ALIGN 0 -#endif /* _ASM_X86_SYSTEM_H */ +#include +#include +#include diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 169be8938b96..c0e108e08079 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -5,7 +5,7 @@ #include #include -#include +#include #ifdef CONFIG_PARAVIRT #include diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index e0f9aa16358b..5da71c27cc59 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -16,7 +16,6 @@ #define _ASM_X86_VIRTEX_H #include -#include #include #include diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index f50e7fb2a201..d2b7f27781bc 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -14,6 +14,7 @@ #include #include #include +#include /* * Initialize bm_flags based on the CPU cache properties diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5d56931a15b3..459e78cbf61e 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -231,7 +231,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 5c0e6533d9bc..2d5454cd2c4f 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -9,7 +9,6 @@ #include #include -#include #include #include diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 67bb17a37a0a..47a1870279aa 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -25,7 +25,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 54060f565974..2d7998fb628c 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -8,7 +8,6 @@ #include #include -#include #include #include diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 97b26356e9ee..75772ae6c65f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index a524353d93f2..39472dd2323f 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -43,7 +43,6 @@ #include #include -#include static struct class *cpuid_class; diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 610485223bdb..36d1853e91af 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -15,7 +15,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 313fb5cddbce..99b85b423bbf 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -16,7 +16,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index faba5771acad..4425a12ece43 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -46,7 +46,6 @@ #include #include -#include #include #include diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ea697263b373..ebc987398923 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -15,7 +15,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index a3fa43ba5d3b..5b19e4d78b00 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c index 177183cbb6ae..7eb1e2b97827 100644 --- a/arch/x86/kernel/mca_32.c +++ b/arch/x86/kernel/mca_32.c @@ -43,7 +43,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 925179f871de..f21fd94ac897 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -26,7 +26,6 @@ #include #include -#include #include #include diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 96356762a51d..eb113693f043 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -40,7 +40,6 @@ #include #include -#include static struct class *msr_class; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index ada2f99388dd..2b26485f0c11 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -37,6 +37,7 @@ #include #include #include +#include /* nop stub */ void _paravirt_nop(void) diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 726494b58345..6ac5782f4d6b 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 14baf78d5a1f..9b24f36eb55f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 9d7d4842bfaf..aae4f4bbbe88 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -41,7 +41,6 @@ #include #include -#include #include #include #include @@ -59,6 +58,7 @@ #include #include #include +#include asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 292da13fc5aa..61270e8d428a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -40,7 +40,6 @@ #include #include -#include #include #include #include @@ -53,6 +52,7 @@ #include #include #include +#include asmlinkage extern void ret_from_fork(void); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 78f05e438be5..8a634c887652 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -24,7 +24,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 88638883176a..8cbeb7209c3e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -90,7 +90,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index 9e540fee7009..ab40954e113e 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -34,6 +34,7 @@ #include #include #include +#include /* flush a tce at 'tceaddr' to main memory */ static inline void flush_tce(void* tceaddr) diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6bb7b8579e70..73920e4c6dc5 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -6,7 +6,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ec61d4c1b93b..860f126ca233 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -50,7 +50,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 6cabf6570d64..4f0cec7e4ffb 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8663f6c47ccb..575d86f85ce4 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 436a0309db33..fc18be0f6f29 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -35,7 +35,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index cac718499256..a69bcb8c7621 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -10,7 +10,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 3769079874d8..74202c1910cd 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -10,7 +10,6 @@ #include #include -#include #include #include #include -- cgit v1.2.3