#include <linux/pm.h>
#include <linux/clockchips.h>
#include <linux/random.h>
-#include <trace/power.h>
-#include <asm/system.h>
+#include <linux/user-return-notifier.h>
+#include <linux/dmi.h>
+#include <linux/utsname.h>
+#include <linux/stackprotector.h>
+#include <linux/tick.h>
+#include <linux/cpuidle.h>
+#include <trace/events/power.h>
+#include <linux/hw_breakpoint.h>
+#include <asm/cpu.h>
#include <asm/apic.h>
#include <asm/syscalls.h>
#include <asm/idle.h>
#include <asm/uaccess.h>
#include <asm/i387.h>
+#include <asm/fpu-internal.h>
+#include <asm/debugreg.h>
+#include <asm/nmi.h>
-unsigned long idle_halt;
-EXPORT_SYMBOL(idle_halt);
-unsigned long idle_nomwait;
-EXPORT_SYMBOL(idle_nomwait);
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data..cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
-struct kmem_cache *task_xstate_cachep;
+#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);
-DEFINE_TRACE(power_start);
-DEFINE_TRACE(power_end);
+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);
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
+ int ret;
+
*dst = *src;
- if (src->thread.xstate) {
- dst->thread.xstate = kmem_cache_alloc(task_xstate_cachep,
- GFP_KERNEL);
- if (!dst->thread.xstate)
- return -ENOMEM;
- WARN_ON((unsigned long)dst->thread.xstate & 15);
- memcpy(dst->thread.xstate, src->thread.xstate, xstate_size);
+ if (fpu_allocated(&src->thread.fpu)) {
+ memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
+ ret = fpu_alloc(&dst->thread.fpu);
+ if (ret)
+ return ret;
+ fpu_copy(&dst->thread.fpu, &src->thread.fpu);
}
return 0;
}
void free_thread_xstate(struct task_struct *tsk)
{
- if (tsk->thread.xstate) {
- kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
- tsk->thread.xstate = NULL;
- }
+ fpu_free(&tsk->thread.fpu);
}
-void free_thread_info(struct thread_info *ti)
+void arch_release_task_struct(struct task_struct *tsk)
{
- free_thread_xstate(ti->task);
- free_pages((unsigned long)ti, get_order(THREAD_SIZE));
+ free_thread_xstate(tsk);
}
void arch_task_cache_init(void)
task_xstate_cachep =
kmem_cache_create("task_xstate", xstate_size,
__alignof__(union thread_xstate),
- SLAB_PANIC, NULL);
+ SLAB_PANIC | SLAB_NOTRACK, NULL);
}
/*
put_cpu();
kfree(bp);
}
+}
+
+void show_regs_common(void)
+{
+ const char *vendor, *product, *board;
+
+ vendor = dmi_get_system_info(DMI_SYS_VENDOR);
+ if (!vendor)
+ vendor = "";
+ product = dmi_get_system_info(DMI_PRODUCT_NAME);
+ if (!product)
+ product = "";
+
+ /* Board Name is optional */
+ board = dmi_get_system_info(DMI_BOARD_NAME);
- ds_exit_thread(current);
+ printk(KERN_CONT "\n");
+ printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s",
+ current->pid, current->comm, print_tainted(),
+ init_utsname()->release,
+ (int)strcspn(init_utsname()->version, " "),
+ init_utsname()->version);
+ printk(KERN_CONT " %s %s", vendor, product);
+ if (board)
+ printk(KERN_CONT "/%s", board);
+ printk(KERN_CONT "\n");
}
void flush_thread(void)
{
struct task_struct *tsk = current;
-#ifdef CONFIG_X86_64
- if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
- clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
- if (test_tsk_thread_flag(tsk, TIF_IA32)) {
- clear_tsk_thread_flag(tsk, TIF_IA32);
- } else {
- set_tsk_thread_flag(tsk, TIF_IA32);
- current_thread_info()->status |= TS_COMPAT;
- }
- }
-#endif
-
- clear_tsk_thread_flag(tsk, TIF_DEBUG);
-
- tsk->thread.debugreg0 = 0;
- tsk->thread.debugreg1 = 0;
- tsk->thread.debugreg2 = 0;
- tsk->thread.debugreg3 = 0;
- tsk->thread.debugreg6 = 0;
- tsk->thread.debugreg7 = 0;
+ flush_ptrace_hw_breakpoint(tsk);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
/*
* Forget coprocessor state..
prev = &prev_p->thread;
next = &next_p->thread;
- if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) ||
- test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR))
- ds_switch_to(prev_p, next_p);
- else if (next->debugctlmsr != prev->debugctlmsr)
- update_debugctlmsr(next->debugctlmsr);
-
- 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);
+ if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^
+ test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) {
+ unsigned long debugctl = get_debugctlmsr();
+
+ debugctl &= ~DEBUGCTLMSR_BTF;
+ if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP))
+ debugctl |= DEBUGCTLMSR_BTF;
+
+ update_debugctlmsr(debugctl);
}
if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
*/
memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
}
+ propagate_user_return_notify(prev_p, next_p);
}
int sys_fork(struct pt_regs *regs)
NULL, NULL);
}
+long
+sys_clone(unsigned long clone_flags, unsigned long newsp,
+ void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
+{
+ if (!newsp)
+ newsp = regs->sp;
+ return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
+}
+
+/*
+ * This gets run with %si containing the
+ * function to call, and %di containing
+ * the "args".
+ */
+extern void kernel_thread_helper(void);
+
+/*
+ * Create a kernel thread
+ */
+int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
+{
+ struct pt_regs regs;
+
+ memset(®s, 0, sizeof(regs));
+
+ regs.si = (unsigned long) fn;
+ regs.di = (unsigned long) arg;
+
+#ifdef CONFIG_X86_32
+ regs.ds = __USER_DS;
+ regs.es = __USER_DS;
+ regs.fs = __KERNEL_PERCPU;
+ regs.gs = __KERNEL_STACK_CANARY;
+#else
+ regs.ss = __KERNEL_DS;
+#endif
+
+ regs.orig_ax = -1;
+ regs.ip = (unsigned long) kernel_thread_helper;
+ regs.cs = __KERNEL_CS | get_kernel_rpl();
+ regs.flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+
+ /* Ok, create the new process.. */
+ return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL);
+}
+EXPORT_SYMBOL(kernel_thread);
+
+/*
+ * sys_execve() executes a new program.
+ */
+long sys_execve(const char __user *name,
+ const char __user *const __user *argv,
+ const char __user *const __user *envp, struct pt_regs *regs)
+{
+ long error;
+ char *filename;
+
+ filename = getname(name);
+ error = PTR_ERR(filename);
+ if (IS_ERR(filename))
+ return error;
+ error = do_execve(filename, argv, envp, regs);
+
+#ifdef CONFIG_X86_32
+ if (error == 0) {
+ /* Make sure we don't return using sysenter.. */
+ set_thread_flag(TIF_IRET);
+ }
+#endif
+
+ putname(filename);
+ return error;
+}
/*
* Idle related variables and functions
*/
-unsigned long boot_option_idle_override = 0;
+unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
EXPORT_SYMBOL(boot_option_idle_override);
/*
* Powermanagement idle function, if any..
*/
void (*pm_idle)(void);
+#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(pm_idle);
+#endif
-#ifdef CONFIG_X86_32
-/*
- * This halt magic was a workaround for ancient floppy DMA
- * wreckage. It should be safe to remove.
- */
-static int hlt_counter;
-void disable_hlt(void)
+static inline int hlt_use_halt(void)
{
- hlt_counter++;
+ return 1;
}
-EXPORT_SYMBOL(disable_hlt);
-void enable_hlt(void)
+#ifndef CONFIG_SMP
+static inline void play_dead(void)
{
- hlt_counter--;
+ BUG();
}
-EXPORT_SYMBOL(enable_hlt);
+#endif
-static inline int hlt_use_halt(void)
+#ifdef CONFIG_X86_64
+void enter_idle(void)
{
- return (!hlt_counter && boot_cpu_data.hlt_works_ok);
+ this_cpu_write(is_idle, 1);
+ atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}
-#else
-static inline int hlt_use_halt(void)
+
+static void __exit_idle(void)
{
- return 1;
+ 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..
void default_idle(void)
{
if (hlt_use_halt()) {
- struct power_trace it;
-
- trace_power_start(&it, POWER_CSTATE, 1);
+ trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
+ trace_cpu_idle_rcuidle(1, smp_processor_id());
current_thread_info()->status &= ~TS_POLLING;
/*
* TS_POLLING-cleared state must be visible before we
else
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
- trace_power_end(&it);
+ trace_power_end_rcuidle(smp_processor_id());
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
} else {
local_irq_enable();
/* loop is done by the caller */
EXPORT_SYMBOL(default_idle);
#endif
+bool set_pm_idle_to_default(void)
+{
+ bool ret = !!pm_idle;
+
+ pm_idle = default_idle;
+
+ return ret;
+}
void stop_this_cpu(void *dummy)
{
local_irq_disable();
}
}
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
- smp_mb();
- /* kick all the CPUs so that they exit out of pm_idle */
- smp_call_function(do_nothing, NULL, 1);
-}
-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)
-{
- struct power_trace it;
-
- trace_power_start(&it, POWER_CSTATE, (ax>>4)+1);
- if (!need_resched()) {
- if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
- clflush((void *)¤t_thread_info()->flags);
-
- __monitor((void *)¤t_thread_info()->flags, 0, 0);
- smp_mb();
- if (!need_resched())
- __mwait(ax, cx);
- }
- trace_power_end(&it);
-}
-
/* Default MONITOR/MWAIT with no hints, used for default C1 state */
static void mwait_idle(void)
{
- struct power_trace it;
if (!need_resched()) {
- trace_power_start(&it, POWER_CSTATE, 1);
- if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+ trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
+ trace_cpu_idle_rcuidle(1, smp_processor_id());
+ if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)¤t_thread_info()->flags);
__monitor((void *)¤t_thread_info()->flags, 0, 0);
__sti_mwait(0, 0);
else
local_irq_enable();
- trace_power_end(&it);
+ trace_power_end_rcuidle(smp_processor_id());
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
} else
local_irq_enable();
}
*/
static void poll_idle(void)
{
- struct power_trace it;
-
- trace_power_start(&it, POWER_CSTATE, 0);
+ trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id());
+ trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
while (!need_resched())
cpu_relax();
- trace_power_end(&it);
+ trace_power_end_rcuidle(smp_processor_id());
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
/*
*
* idle=mwait overrides this decision and forces the usage of mwait.
*/
-static int __cpuinitdata force_mwait;
#define MWAIT_INFO 0x05
#define MWAIT_ECX_EXTENDED_INFO 0x01
#define MWAIT_EDX_C1 0xf0
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+int mwait_usable(const struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
- if (force_mwait)
+ /* Use mwait if idle=mwait boot option is given */
+ if (boot_option_idle_override == IDLE_FORCE_MWAIT)
return 1;
+ /*
+ * Any idle= boot option other than idle=mwait means that we must not
+ * use mwait. Eg: idle=halt or idle=poll or idle=nomwait
+ */
+ if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+ return 0;
+
if (c->cpuid_level < MWAIT_INFO)
return 0;
return (edx & MWAIT_EDX_C1);
}
-/*
- * Check for AMD CPUs, which have potentially C1E support
- */
-static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
-{
- if (c->x86_vendor != X86_VENDOR_AMD)
- return 0;
-
- if (c->x86 < 0x0F)
- return 0;
-
- /* Family 0x0f models < rev F do not have C1E */
- if (c->x86 == 0x0f && c->x86_model < 0x40)
- return 0;
-
- return 1;
-}
+bool amd_e400_c1e_detected;
+EXPORT_SYMBOL(amd_e400_c1e_detected);
-static cpumask_var_t c1e_mask;
-static int c1e_detected;
+static cpumask_var_t amd_e400_c1e_mask;
-void c1e_remove_cpu(int cpu)
+void amd_e400_remove_cpu(int cpu)
{
- if (c1e_mask != NULL)
- cpumask_clear_cpu(cpu, c1e_mask);
+ if (amd_e400_c1e_mask != NULL)
+ cpumask_clear_cpu(cpu, amd_e400_c1e_mask);
}
/*
- * C1E aware idle routine. We check for C1E active in the interrupt
+ * AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt
* pending message MSR. If we detect C1E, then we handle it the same
* way as C3 power states (local apic timer and TSC stop)
*/
-static void c1e_idle(void)
+static void amd_e400_idle(void)
{
if (need_resched())
return;
- if (!c1e_detected) {
+ if (!amd_e400_c1e_detected) {
u32 lo, hi;
rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+
if (lo & K8_INTP_C1E_ACTIVE_MASK) {
- c1e_detected = 1;
+ amd_e400_c1e_detected = true;
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
mark_tsc_unstable("TSC halt in AMD C1E");
printk(KERN_INFO "System has AMD C1E enabled\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E);
}
}
- if (c1e_detected) {
+ if (amd_e400_c1e_detected) {
int cpu = smp_processor_id();
- if (!cpumask_test_cpu(cpu, c1e_mask)) {
- cpumask_set_cpu(cpu, c1e_mask);
+ if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
+ cpumask_set_cpu(cpu, amd_e400_c1e_mask);
/*
- * Force broadcast so ACPI can not interfere. Needs
- * to run with interrupts enabled as it uses
- * smp_function_call.
+ * Force broadcast so ACPI can not interfere.
*/
- local_irq_enable();
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
&cpu);
printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
cpu);
- local_irq_disable();
}
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
{
#ifdef CONFIG_SMP
if (pm_idle == poll_idle && smp_num_siblings > 1) {
- printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
+ printk_once(KERN_WARNING "WARNING: polling idle and HT enabled,"
" performance may degrade.\n");
}
#endif
*/
printk(KERN_INFO "using mwait in idle threads.\n");
pm_idle = mwait_idle;
- } else if (check_c1e_idle(c)) {
- printk(KERN_INFO "using C1E aware idle routine\n");
- pm_idle = c1e_idle;
+ } else if (cpu_has_amd_erratum(amd_erratum_400)) {
+ /* E400: APIC timer interrupt does not wake up CPU from C1e */
+ printk(KERN_INFO "using AMD E400 aware idle routine\n");
+ pm_idle = amd_e400_idle;
} else
pm_idle = default_idle;
}
-void __init init_c1e_mask(void)
+void __init init_amd_e400_c1e_mask(void)
{
- /* If we're using c1e_idle, we need to allocate c1e_mask. */
- if (pm_idle == c1e_idle) {
- alloc_cpumask_var(&c1e_mask, GFP_KERNEL);
- cpumask_clear(c1e_mask);
- }
+ /* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
+ if (pm_idle == amd_e400_idle)
+ zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
}
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 if (!strcmp(str, "halt")) {
+ boot_option_idle_override = IDLE_POLL;
+ } else if (!strcmp(str, "mwait")) {
+ boot_option_idle_override = IDLE_FORCE_MWAIT;
+ WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n");
+ } else if (!strcmp(str, "halt")) {
/*
* When the boot option of idle=halt is added, halt is
* forced to be used for CPU idle. In such case CPU C2/C3
* the boot_option_idle_override.
*/
pm_idle = default_idle;
- idle_halt = 1;
- return 0;
+ boot_option_idle_override = IDLE_HALT;
} else if (!strcmp(str, "nomwait")) {
/*
* If the boot option of "idle=nomwait" is added,
* states. In such case it won't touch the variable
* of boot_option_idle_override.
*/
- idle_nomwait = 1;
- return 0;
+ boot_option_idle_override = IDLE_NOMWAIT;
} else
return -1;
- boot_option_idle_override = 1;
return 0;
}
early_param("idle", idle_setup);