X-Git-Url: http://git.onelab.eu/?p=linux-2.6.git;a=blobdiff_plain;f=arch%2Fx86_64%2Fkernel%2Fprocess.c;fp=arch%2Fx86_64%2Fkernel%2Fprocess.c;h=9966a28cc0740e57fda59fee051cd4a26cd0babb;hp=818ab9e66aed256ea3b854547b277be28e888417;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hpb=76828883507a47dae78837ab5dec5a5b4513c667 diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index 818ab9e66..9966a28cc 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -10,7 +10,6 @@ * Andi Kleen. * * CPU hotplug support - ashok.raj@intel.com - * $Id: process.c,v 1.38 2002/01/15 10:08:03 ak Exp $ */ /* @@ -35,8 +34,8 @@ #include #include #include -#include #include +#include #include #include @@ -55,7 +54,8 @@ asmlinkage extern void ret_from_fork(void); -unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; +unsigned long kernel_thread_flags = + CLONE_VM | CLONE_UNTRACED | CLONE_KTHREAD; unsigned long boot_option_idle_override = 0; EXPORT_SYMBOL(boot_option_idle_override); @@ -64,48 +64,41 @@ EXPORT_SYMBOL(boot_option_idle_override); * Powermanagement idle function, if any.. */ void (*pm_idle)(void); +EXPORT_SYMBOL(pm_idle); static DEFINE_PER_CPU(unsigned int, cpu_idle_state); -static struct notifier_block *idle_notifier; -static DEFINE_SPINLOCK(idle_notifier_lock); +static ATOMIC_NOTIFIER_HEAD(idle_notifier); void idle_notifier_register(struct notifier_block *n) { - unsigned long flags; - spin_lock_irqsave(&idle_notifier_lock, flags); - notifier_chain_register(&idle_notifier, n); - spin_unlock_irqrestore(&idle_notifier_lock, flags); + atomic_notifier_chain_register(&idle_notifier, n); } EXPORT_SYMBOL_GPL(idle_notifier_register); void idle_notifier_unregister(struct notifier_block *n) { - unsigned long flags; - spin_lock_irqsave(&idle_notifier_lock, flags); - notifier_chain_unregister(&idle_notifier, n); - spin_unlock_irqrestore(&idle_notifier_lock, flags); + atomic_notifier_chain_unregister(&idle_notifier, n); } EXPORT_SYMBOL(idle_notifier_unregister); -enum idle_state { CPU_IDLE, CPU_NOT_IDLE }; -static DEFINE_PER_CPU(enum idle_state, idle_state) = CPU_NOT_IDLE; - void enter_idle(void) { - __get_cpu_var(idle_state) = CPU_IDLE; - notifier_call_chain(&idle_notifier, IDLE_START, NULL); + write_pda(isidle, 1); + atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); } static void __exit_idle(void) { - __get_cpu_var(idle_state) = CPU_NOT_IDLE; - notifier_call_chain(&idle_notifier, IDLE_END, NULL); + if (test_and_clear_bit_pda(0, isidle) == 0) + return; + atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); } /* Called from interrupts to signify idle end */ void exit_idle(void) { - if (current->pid | read_pda(irqcount)) + /* idle loop has pid 0 */ + if (current->pid) return; __exit_idle(); } @@ -114,20 +107,22 @@ void exit_idle(void) * We use this if we don't have any better * idle routine.. */ -void default_idle(void) +static void default_idle(void) { - local_irq_enable(); - - clear_thread_flag(TIF_POLLING_NRFLAG); - smp_mb__after_clear_bit(); - while (!need_resched()) { - local_irq_disable(); - if (!need_resched()) - safe_halt(); - else - local_irq_enable(); - } - set_thread_flag(TIF_POLLING_NRFLAG); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we + * test NEED_RESCHED: + */ + smp_mb(); + local_irq_disable(); + if (!need_resched()) { + /* Enables interrupts one instruction before HLT. + x86 special cases this so there is no race. */ + safe_halt(); + } else + local_irq_enable(); + current_thread_info()->status |= TS_POLLING; } /* @@ -138,21 +133,13 @@ void default_idle(void) static void poll_idle (void) { local_irq_enable(); - - asm volatile( - "2:" - "testl %0,%1;" - "rep; nop;" - "je 2b;" - : : - "i" (_TIF_NEED_RESCHED), - "m" (current_thread_info()->flags)); + cpu_relax(); } void cpu_idle_wait(void) { unsigned int cpu, this_cpu = get_cpu(); - cpumask_t map; + cpumask_t map, tmp = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); put_cpu(); @@ -175,6 +162,8 @@ void cpu_idle_wait(void) } cpus_and(map, map, cpu_online_map); } while (!cpus_empty(map)); + + set_cpus_allowed(current, tmp); } EXPORT_SYMBOL_GPL(cpu_idle_wait); @@ -210,8 +199,7 @@ static inline void play_dead(void) */ void cpu_idle (void) { - set_thread_flag(TIF_POLLING_NRFLAG); - + current_thread_info()->status |= TS_POLLING; /* endless idle loop with no priority at all */ while (1) { while (!need_resched()) { @@ -226,8 +214,17 @@ void cpu_idle (void) idle = default_idle; 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_irq_disable(); enter_idle(); idle(); + /* 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(); } @@ -243,17 +240,32 @@ void cpu_idle (void) * We execute MONITOR against need_resched and enter optimized wait state * through MWAIT. Whenever someone changes need_resched, we would be woken * up from MWAIT (without an IPI). + * + * New with Core Duo processors, MWAIT can take some hints based on CPU + * capability. */ -static void mwait_idle(void) +void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { - local_irq_enable(); + if (!need_resched()) { + __monitor((void *)¤t_thread_info()->flags, 0, 0); + smp_mb(); + if (!need_resched()) + __mwait(eax, ecx); + } +} - while (!need_resched()) { +/* Default MONITOR/MWAIT with no hints, used for default C1 state */ +static void mwait_idle(void) +{ + if (!need_resched()) { __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); - if (need_resched()) - break; - __mwait(0, 0); + if (!need_resched()) + __sti_mwait(0, 0); + else + local_irq_enable(); + } else { + local_irq_enable(); } } @@ -297,14 +309,14 @@ void __show_regs(struct pt_regs * regs) printk("\n"); print_modules(); - printk("Pid: %d, comm: %.20s %s %s %.*s\n", - current->pid, current->comm, print_tainted(), - system_utsname.release, - (int)strcspn(system_utsname.version, " "), - system_utsname.version); + printk("Pid: %d:#%u, comm: %.20s %s %s %.*s\n", + current->pid, current->xid, current->comm, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip); printk_address(regs->rip); - printk("\nRSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp, + printk("RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp, regs->eflags); printk("RAX: %016lx RBX: %016lx RCX: %016lx\n", regs->rax, regs->rbx, regs->rcx); @@ -342,7 +354,7 @@ void show_regs(struct pt_regs *regs) { printk("CPU %d:", smp_processor_id()); __show_regs(regs); - show_trace(®s->rsp); + show_trace(NULL, regs, (void *)(regs + 1)); } /* @@ -353,18 +365,12 @@ void exit_thread(void) struct task_struct *me = current; struct thread_struct *t = &me->thread; - /* - * Remove function-return probe instances associated with this task - * and put them back on the free list. Do not insert an exit probe for - * this function, it will be disabled by kprobe_flush_task if you do. - */ - kprobe_flush_task(me); - if (me->thread.io_bitmap_ptr) { struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); kfree(t->io_bitmap_ptr); t->io_bitmap_ptr = NULL; + clear_thread_flag(TIF_IO_BITMAP); /* * Careful, clear this in the TSS too: */ @@ -379,8 +385,12 @@ void flush_thread(void) struct task_struct *tsk = current; struct thread_info *t = current_thread_info(); - if (t->flags & _TIF_ABI_PENDING) + if (t->flags & _TIF_ABI_PENDING) { t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32); + if (t->flags & _TIF_IA32) + current_thread_info()->status |= TS_COMPAT; + } + t->flags &= ~_TIF_DEBUG; tsk->thread.debugreg0 = 0; tsk->thread.debugreg1 = 0; @@ -473,7 +483,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, asm("mov %%es,%0" : "=m" (p->thread.es)); asm("mov %%ds,%0" : "=m" (p->thread.ds)); - if (unlikely(me->thread.io_bitmap_ptr != NULL)) { + if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); if (!p->thread.io_bitmap_ptr) { p->thread.io_bitmap_max = 0; @@ -481,6 +491,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, } memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr, IO_BITMAP_BYTES); + set_tsk_thread_flag(p, TIF_IO_BITMAP); } /* @@ -508,7 +519,41 @@ out: /* * This special macro can be used to load a debugging register */ -#define loaddebug(thread,r) set_debug(thread->debugreg ## r, r) +#define loaddebug(thread,r) set_debugreg(thread->debugreg ## r, r) + +static inline void __switch_to_xtra(struct task_struct *prev_p, + struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + + prev = &prev_p->thread, + next = &next_p->thread; + + if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { + loaddebug(next, 0); + loaddebug(next, 1); + loaddebug(next, 2); + loaddebug(next, 3); + /* no 4 and 5 */ + loaddebug(next, 6); + loaddebug(next, 7); + } + + if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { + /* + * Copy the relevant range of the IO bitmap. + * Normally this is 128 bytes or less: + */ + memcpy(tss->io_bitmap, next->io_bitmap_ptr, + max(prev->io_bitmap_max, next->io_bitmap_max)); + } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + /* + * Clear any possible leftover bits: + */ + memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + } +} /* * switch_to(x,y) should switch tasks from x to y. @@ -527,6 +572,10 @@ __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); + /* we're going to use this soon, after a few expensive things */ + if (next_p->fpu_counter>5) + prefetch(&next->i387.fxsave); + /* * Reload esp0, LDT and the page table pointer: */ @@ -583,54 +632,40 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) prev->gsindex = gsindex; } + /* Must be after DS reload */ + unlazy_fpu(prev_p); + /* - * Switch the PDA context. + * Switch the PDA and FPU contexts. */ prev->userrsp = read_pda(oldrsp); write_pda(oldrsp, next->userrsp); write_pda(pcurrent, next_p); - /* This must be here to ensure both math_state_restore() and - kernel_fpu_begin() work consistently. - And the AMD workaround requires it to be after DS reload. */ - unlazy_fpu(prev_p); - write_pda(kernelstack, - task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET); - + (unsigned long)task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET); +#ifdef CONFIG_CC_STACKPROTECTOR + write_pda(stack_canary, next_p->stack_canary); /* - * Now maybe reload the debug registers + * Build time only check to make sure the stack_canary is at + * offset 40 in the pda; this is a gcc ABI requirement */ - if (unlikely(next->debugreg7)) { - loaddebug(next, 0); - loaddebug(next, 1); - loaddebug(next, 2); - loaddebug(next, 3); - /* no 4 and 5 */ - loaddebug(next, 6); - loaddebug(next, 7); - } - + BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40); +#endif - /* - * Handle the IO bitmap - */ - if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) { - if (next->io_bitmap_ptr) - /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: - */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - else { - /* - * Clear any possible leftover bits: - */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); - } - } + /* + * Now maybe reload the debug registers and handle I/O bitmaps + */ + if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW)) + || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) + __switch_to_xtra(prev_p, next_p, tss); + /* 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 + */ + if (next_p->fpu_counter>5) + math_state_restore(); return prev_p; } @@ -649,11 +684,6 @@ long sys_execve(char __user *name, char __user * __user *argv, if (IS_ERR(filename)) return error; error = do_execve(filename, argv, envp, ®s); - if (error == 0) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; - task_unlock(current); - } putname(filename); return error; } @@ -664,12 +694,6 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); - - /* TBD: overwrites user setup. Should have two bits. - But 64bit processes have always behaved this way, - so it's not too bad. The main problem is just that - 32bit childs are affected again. */ - current->personality &= ~READ_IMPLIES_EXEC; } asmlinkage long sys_fork(struct pt_regs *regs) @@ -798,10 +822,16 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) } case ARCH_GET_GS: { unsigned long base; + unsigned gsindex; if (task->thread.gsindex == GS_TLS_SEL) base = read_32bit_tls(task, GS_TLS); - else if (doit) - rdmsrl(MSR_KERNEL_GS_BASE, base); + else if (doit) { + asm("movl %%gs,%0" : "=r" (gsindex)); + if (gsindex) + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + base = task->thread.gs; + } else base = task->thread.gs; ret = put_user(base, (unsigned long __user *)addr); @@ -841,7 +871,7 @@ int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) unsigned long arch_align_stack(unsigned long sp) { - if (randomize_va_space) + if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) sp -= get_random_int() % 8192; return sp & ~0xf; }