#include <stdarg.h>
+#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/user.h>
-#include <linux/a.out.h>
#include <linux/interrupt.h>
#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/personality.h>
#include <linux/tick.h>
#include <linux/percpu.h>
+#include <linux/prctl.h>
+#include <linux/dmi.h>
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/kdebug.h>
-#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/system.h>
-#include <asm/io.h>
#include <asm/ldt.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/desc.h>
-#include <asm/vm86.h>
#ifdef CONFIG_MATH_EMULATION
#include <asm/math_emu.h>
#endif
#include <asm/tlbflush.h>
#include <asm/cpu.h>
-#include <asm/kdebug.h>
+#include <asm/idle.h>
+#include <asm/syscalls.h>
+#include <asm/ds.h>
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-static int hlt_counter;
-
-unsigned long boot_option_idle_override = 0;
-EXPORT_SYMBOL(boot_option_idle_override);
-
DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
-DEFINE_PER_CPU(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
-
/*
* Return saved PC of a blocked thread.
*/
return ((unsigned long *)tsk->thread.sp)[3];
}
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-EXPORT_SYMBOL(pm_idle);
-static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
-
-void disable_hlt(void)
-{
- hlt_counter++;
-}
-
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
- hlt_counter--;
-}
-
-EXPORT_SYMBOL(enable_hlt);
-
-/*
- * We use this if we don't have any better
- * idle routine..
- */
-void default_idle(void)
-{
- if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
- 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()) {
- ktime_t t0, t1;
- u64 t0n, t1n;
-
- t0 = ktime_get();
- t0n = ktime_to_ns(t0);
- safe_halt(); /* enables interrupts racelessly */
- local_irq_disable();
- t1 = ktime_get();
- t1n = ktime_to_ns(t1);
- sched_clock_idle_wakeup_event(t1n - t0n);
- }
- local_irq_enable();
- current_thread_info()->status |= TS_POLLING;
- } else {
- /* loop is done by the caller */
- cpu_relax();
- }
-}
-#ifdef CONFIG_APM_MODULE
-EXPORT_SYMBOL(default_idle);
-#endif
-
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->work.need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
- cpu_relax();
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <asm/nmi.h>
-/* We don't actually take CPU down, just spin without interrupts. */
-static inline void play_dead(void)
-{
- /* This must be done before dead CPU ack */
- cpu_exit_clear();
- wbinvd();
- mb();
- /* Ack it */
- __get_cpu_var(cpu_state) = CPU_DEAD;
-
- /*
- * With physical CPU hotplug, we should halt the cpu
- */
- local_irq_disable();
- while (1)
- halt();
-}
-#else
+#ifndef CONFIG_SMP
static inline void play_dead(void)
{
BUG();
}
-#endif /* CONFIG_HOTPLUG_CPU */
+#endif
/*
* The idle thread. There's no useful work to be
{
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_stop_sched_tick();
+ tick_nohz_stop_sched_tick(1);
while (!need_resched()) {
- void (*idle)(void);
-
- if (__get_cpu_var(cpu_idle_state))
- __get_cpu_var(cpu_idle_state) = 0;
check_pgt_cache();
rmb();
- idle = pm_idle;
-
- if (rcu_pending(cpu))
- rcu_check_callbacks(cpu, 0);
-
- if (!idle)
- idle = default_idle;
if (cpu_is_offline(cpu))
play_dead();
- __get_cpu_var(irq_stat).idle_timestamp = jiffies;
- idle();
+ local_irq_disable();
+ /* Don't trace irqs off for idle */
+ stop_critical_timings();
+ pm_idle();
+ start_critical_timings();
}
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
}
}
-static void do_nothing(void *unused)
-{
-}
-
-void cpu_idle_wait(void)
-{
- unsigned int cpu, this_cpu = get_cpu();
- cpumask_t map, tmp = current->cpus_allowed;
-
- set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
- put_cpu();
-
- cpus_clear(map);
- for_each_online_cpu(cpu) {
- per_cpu(cpu_idle_state, cpu) = 1;
- cpu_set(cpu, map);
- }
-
- __get_cpu_var(cpu_idle_state) = 0;
-
- wmb();
- do {
- ssleep(1);
- for_each_online_cpu(cpu) {
- if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
- cpu_clear(cpu, map);
- }
- cpus_and(map, map, cpu_online_map);
- /*
- * We waited 1 sec, if a CPU still did not call idle
- * it may be because it is in idle and not waking up
- * because it has nothing to do.
- * Give all the remaining CPUS a kick.
- */
- smp_call_function_mask(map, do_nothing, NULL, 0);
- } while (!cpus_empty(map));
-
- set_cpus_allowed(current, tmp);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * 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.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
- if (!need_resched()) {
- __monitor((void *)¤t_thread_info()->flags, 0, 0);
- smp_mb();
- if (!need_resched())
- __mwait(ax, cx);
- }
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
- local_irq_enable();
- mwait_idle_with_hints(0, 0);
-}
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
- if (force_mwait)
- return 1;
- /* Any C1 states supported? */
- return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
- static int selected;
-
- if (selected)
- return;
-#ifdef CONFIG_X86_SMP
- if (pm_idle == poll_idle && smp_num_siblings > 1) {
- printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
- " performance may degrade.\n");
- }
-#endif
- if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
- /*
- * Skip, if setup has overridden idle.
- * One CPU supports mwait => All CPUs supports mwait
- */
- if (!pm_idle) {
- printk(KERN_INFO "using mwait in idle threads.\n");
- pm_idle = mwait_idle;
- }
- }
- selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
- if (!strcmp(str, "poll")) {
- printk("using polling idle threads.\n");
- pm_idle = poll_idle;
- } else if (!strcmp(str, "mwait"))
- force_mwait = 1;
- else
- return -1;
-
- boot_option_idle_override = 1;
- return 0;
-}
-early_param("idle", idle_setup);
-
-void __show_registers(struct pt_regs *regs, int all)
+void __show_regs(struct pt_regs *regs, int all)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
unsigned long d0, d1, d2, d3, d6, d7;
unsigned long sp;
unsigned short ss, gs;
+ const char *board;
if (user_mode_vm(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
- savesegment(gs, gs);
+ gs = get_user_gs(regs);
} else {
sp = (unsigned long) (®s->sp);
savesegment(ss, ss);
}
printk("\n");
- printk("Pid: %d, comm: %s %s (%s %.*s)\n",
+
+ board = dmi_get_system_info(DMI_PRODUCT_NAME);
+ if (!board)
+ board = "";
+ printk("Pid: %d, comm: %s %s (%s %.*s) %s\n",
task_pid_nr(current), current->comm,
print_tainted(), init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
- init_utsname()->version);
+ init_utsname()->version, board);
printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
- 0xffff & regs->cs, regs->ip, regs->flags,
+ (u16)regs->cs, regs->ip, regs->flags,
smp_processor_id());
print_symbol("EIP is at %s\n", regs->ip);
printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
regs->si, regs->di, regs->bp, sp);
printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
- regs->ds & 0xffff, regs->es & 0xffff,
- regs->fs & 0xffff, gs, ss);
+ (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss);
if (!all)
return;
void show_regs(struct pt_regs *regs)
{
- __show_registers(regs, 1);
+ __show_regs(regs, 1);
show_trace(NULL, regs, ®s->sp, regs->bp);
}
/*
* Create a kernel thread
*/
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
+int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
{
struct pt_regs regs;
regs.ds = __USER_DS;
regs.es = __USER_DS;
regs.fs = __KERNEL_PERCPU;
+ regs.gs = __KERNEL_STACK_CANARY;
regs.orig_ax = -1;
regs.ip = (unsigned long) kernel_thread_helper;
regs.cs = __KERNEL_CS | get_kernel_rpl();
}
EXPORT_SYMBOL(kernel_thread);
-/*
- * Free current thread data structures etc..
- */
-void exit_thread(void)
-{
- /* The process may have allocated an io port bitmap... nuke it. */
- if (unlikely(test_thread_flag(TIF_IO_BITMAP))) {
- struct task_struct *tsk = current;
- struct thread_struct *t = &tsk->thread;
- int cpu = get_cpu();
- struct tss_struct *tss = &per_cpu(init_tss, cpu);
-
- kfree(t->io_bitmap_ptr);
- t->io_bitmap_ptr = NULL;
- clear_thread_flag(TIF_IO_BITMAP);
- /*
- * Careful, clear this in the TSS too:
- */
- memset(tss->io_bitmap, 0xff, tss->io_bitmap_max);
- t->io_bitmap_max = 0;
- tss->io_bitmap_owner = NULL;
- tss->io_bitmap_max = 0;
- tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
- put_cpu();
- }
-}
-
-void flush_thread(void)
-{
- struct task_struct *tsk = current;
-
- tsk->thread.debugreg0 = 0;
- tsk->thread.debugreg1 = 0;
- tsk->thread.debugreg2 = 0;
- tsk->thread.debugreg3 = 0;
- tsk->thread.debugreg6 = 0;
- tsk->thread.debugreg7 = 0;
- memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
- clear_tsk_thread_flag(tsk, TIF_DEBUG);
- /*
- * Forget coprocessor state..
- */
- clear_fpu(tsk);
- clear_used_math();
-}
-
void release_thread(struct task_struct *dead_task)
{
BUG_ON(dead_task->mm);
int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
unsigned long unused,
- struct task_struct * p, struct pt_regs * regs)
+ struct task_struct *p, struct pt_regs *regs)
{
- struct pt_regs * childregs;
+ struct pt_regs *childregs;
struct task_struct *tsk;
int err;
p->thread.ip = (unsigned long) ret_from_fork;
- savesegment(gs, p->thread.gs);
+ task_user_gs(p) = get_user_gs(regs);
tsk = current;
if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
- return err;
-}
-#ifdef CONFIG_SECCOMP
-static void hard_disable_TSC(void)
-{
- write_cr4(read_cr4() | X86_CR4_TSD);
-}
-void disable_TSC(void)
-{
- preempt_disable();
- if (!test_and_set_thread_flag(TIF_NOTSC))
- /*
- * Must flip the CPU state synchronously with
- * TIF_NOTSC in the current running context.
- */
- hard_disable_TSC();
- preempt_enable();
-}
-static void hard_enable_TSC(void)
-{
- write_cr4(read_cr4() & ~X86_CR4_TSD);
-}
-#endif /* CONFIG_SECCOMP */
-
-static noinline void
-__switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
- struct tss_struct *tss)
-{
- struct thread_struct *prev, *next;
- unsigned long debugctl;
-
- prev = &prev_p->thread;
- next = &next_p->thread;
-
- debugctl = prev->debugctlmsr;
- if (next->ds_area_msr != prev->ds_area_msr) {
- /* we clear debugctl to make sure DS
- * is not in use when we change it */
- debugctl = 0;
- wrmsrl(MSR_IA32_DEBUGCTLMSR, 0);
- wrmsr(MSR_IA32_DS_AREA, next->ds_area_msr, 0);
- }
-
- if (next->debugctlmsr != debugctl)
- wrmsr(MSR_IA32_DEBUGCTLMSR, next->debugctlmsr, 0);
-
- if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
- set_debugreg(next->debugreg0, 0);
- set_debugreg(next->debugreg1, 1);
- set_debugreg(next->debugreg2, 2);
- set_debugreg(next->debugreg3, 3);
- /* no 4 and 5 */
- set_debugreg(next->debugreg6, 6);
- set_debugreg(next->debugreg7, 7);
- }
-
-#ifdef CONFIG_SECCOMP
- if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
- test_tsk_thread_flag(next_p, TIF_NOTSC)) {
- /* prev and next are different */
- if (test_tsk_thread_flag(next_p, TIF_NOTSC))
- hard_disable_TSC();
- else
- hard_enable_TSC();
- }
-#endif
+ ds_copy_thread(p, current);
- if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
- ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
+ clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
+ p->thread.debugctlmsr = 0;
- if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
- ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-
-
- if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
- /*
- * Disable the bitmap via an invalid offset. We still cache
- * the previous bitmap owner and the IO bitmap contents:
- */
- tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
- return;
- }
+ return err;
+}
- if (likely(next == tss->io_bitmap_owner)) {
- /*
- * Previous owner of the bitmap (hence the bitmap content)
- * matches the next task, we dont have to do anything but
- * to set a valid offset in the TSS:
- */
- tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
- return;
- }
+void
+start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
+{
+ set_user_gs(regs, 0);
+ regs->fs = 0;
+ set_fs(USER_DS);
+ regs->ds = __USER_DS;
+ regs->es = __USER_DS;
+ regs->ss = __USER_DS;
+ regs->cs = __USER_CS;
+ regs->ip = new_ip;
+ regs->sp = new_sp;
/*
- * Lazy TSS's I/O bitmap copy. We set an invalid offset here
- * and we let the task to get a GPF in case an I/O instruction
- * is performed. The handler of the GPF will verify that the
- * faulting task has a valid I/O bitmap and, it true, does the
- * real copy and restart the instruction. This will save us
- * redundant copies when the currently switched task does not
- * perform any I/O during its timeslice.
+ * Free the old FP and other extended state
*/
- tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
+ free_thread_xstate(current);
}
+EXPORT_SYMBOL_GPL(start_thread);
+
/*
* switch_to(x,yn) should switch tasks from x to y.
* the task-switch, and shows up in ret_from_fork in entry.S,
* for example.
*/
-struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
+__notrace_funcgraph struct task_struct *
+__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
*next = &next_p->thread;
/* we're going to use this soon, after a few expensive things */
if (next_p->fpu_counter > 5)
- prefetch(&next->i387.fxsave);
+ prefetch(next->xstate);
/*
* Reload esp0.
* used %fs or %gs (it does not today), or if the kernel is
* running inside of a hypervisor layer.
*/
- savesegment(gs, prev->gs);
+ lazy_save_gs(prev->gs);
/*
* Load the per-thread Thread-Local Storage descriptor.
/* 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
+ *
+ * tsk_used_math() checks prevent calling math_state_restore(),
+ * which can sleep in the case of !tsk_used_math()
*/
- if (next_p->fpu_counter > 5)
+ if (tsk_used_math(next_p) && next_p->fpu_counter > 5)
math_state_restore();
/*
* Restore %gs if needed (which is common)
*/
if (prev->gs | next->gs)
- loadsegment(gs, next->gs);
+ lazy_load_gs(next->gs);
- x86_write_percpu(current_task, next_p);
+ percpu_write(current_task, next_p);
return prev_p;
}
-asmlinkage int sys_fork(struct pt_regs regs)
-{
- return do_fork(SIGCHLD, regs.sp, ®s, 0, NULL, NULL);
-}
-
-asmlinkage int sys_clone(struct pt_regs regs)
+int sys_clone(struct pt_regs *regs)
{
unsigned long clone_flags;
unsigned long newsp;
int __user *parent_tidptr, *child_tidptr;
- clone_flags = regs.bx;
- newsp = regs.cx;
- parent_tidptr = (int __user *)regs.dx;
- child_tidptr = (int __user *)regs.di;
+ clone_flags = regs->bx;
+ newsp = regs->cx;
+ parent_tidptr = (int __user *)regs->dx;
+ child_tidptr = (int __user *)regs->di;
if (!newsp)
- newsp = regs.sp;
- return do_fork(clone_flags, newsp, ®s, 0, parent_tidptr, child_tidptr);
-}
-
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-asmlinkage int sys_vfork(struct pt_regs regs)
-{
- return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.sp, ®s, 0, NULL, NULL);
+ newsp = regs->sp;
+ return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr);
}
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(struct pt_regs regs)
+int sys_execve(struct pt_regs *regs)
{
int error;
- char * filename;
+ char *filename;
- filename = getname((char __user *) regs.bx);
+ filename = getname((char __user *) regs->bx);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
error = do_execve(filename,
- (char __user * __user *) regs.cx,
- (char __user * __user *) regs.dx,
- ®s);
+ (char __user * __user *) regs->cx,
+ (char __user * __user *) regs->dx,
+ regs);
if (error == 0) {
/* Make sure we don't return using sysenter.. */
set_thread_flag(TIF_IRET);