kevin/linux
1
Fork 0
Code
40d6a14662
linux/arch/x86/kernel/process_32.c
Steven Rostedt 40d6a14662 Kick CPUS that might be sleeping in cpus_idle_wait 
Sometimes cpu_idle_wait gets stuck because it might miss CPUS that are
already in idle, have no tasks waiting to run and have no interrupts going
to them.  This is common on bootup when switching cpu idle governors.

This patch gives those CPUS that don't check in an IPI kick.

 Background:
 -----------
I notice this while developing the mcount patches, that every once in a
while the system would hang. Looking deeper, the hang was always at boot
up when registering init_menu of the cpu_idle menu governor. Talking
with Thomas Gliexner, we discovered that one of the CPUS had no timer
events scheduled for it and it was in idle (running with NO_HZ). So the
CPU would not set the cpu_idle_state bit.

Hitting sysrq-t a few times would eventually route the interrupt to the
stuck CPU and the system would continue.

Note, I would have used the PDA isidle but that is set after the
cpu_idle_state bit is cleared, and would leave a window open where we
may miss being kicked.

hmm, looking closer at this, we still have a small race window between
clearing the cpu_idle_state and disabling interrupts (hence the RFC).

    CPU0:                          CPU 1:
  ---------                       ---------
 cpu_idle_wait():                 cpu_idle():
      |                           __cpu_cpu_var(is_idle) = 1;
      |                           if (__get_cpu_var(cpu_idle_state)) /* == 0 */
 per_cpu(cpu_idle_state, 1) = 1;         |
 if (per_cpu(is_idle, 1)) /* == 1 */     |
 smp_call_function(1)                    |
      |                             receives ipi and runs do_nothing.
 wait on map == empty               idle();
   /* waits forever */

So really we need interrupts off for most of this then. One might think
that we could simply clear the cpu_idle_state from do_nothing, but I'm
assuming that cpu_idle governors can be removed, and this might cause a
race that a governor might be used after the module was removed.

Venki said:

  I think your RFC patch is the right solution here.  As I see it, there is
  no race with your RFC patch.  As long as you call a dummy smp_call_function
  on all CPUs, we should be OK.  We can get rid of cpu_idle_state and the
  current wait forever logic altogether with dummy smp_call_function.  And so
  there wont be any wait forever scenario.

  The whole point of cpu_idle_wait() is to make all CPUs come out of idle
  loop atleast once.  The caller will use cpu_idle_wait something like this.

  // Want to change idle handler

  - Switch global idle handler to always present default_idle

  - call cpu_idle_wait so that all cpus come out of idle for an instant
    and stop using old idle pointer and start using default idle

  - Change the idle handler to a new handler

  - optional cpu_idle_wait if you want all cpus to start using the new
    handler immediately.

Maybe the below 1s patch is safe bet for .24.  But for .25, I would say we
just replace all complicated logic by simple dummy smp_call_function and
remove cpu_idle_state altogether.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <ak@suse.de>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-14 08:52:22 -08:00

985 lines
24 KiB
C
Raw Blame History

/*
* Copyright (C) 1995 Linus Torvalds
*
* Pentium III FXSR, SSE support
* Gareth Hughes <gareth@valinux.com>, May 2000
*/
/*
* This file handles the architecture-dependent parts of process handling..
*/
#include <stdarg.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/stddef.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/reboot.h>
#include <linux/init.h>
#include <linux/mc146818rtc.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/random.h>
#include <linux/personality.h>
#include <linux/tick.h>
#include <linux/percpu.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 <linux/err.h>
#include <asm/tlbflush.h>
#include <asm/cpu.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.
*/
unsigned long thread_saved_pc(struct task_struct *tsk)
{
return ((unsigned long *)tsk->thread.esp)[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())
safe_halt(); /* enables interrupts racelessly */
else
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
static inline void play_dead(void)
{
BUG();
}
#endif /* CONFIG_HOTPLUG_CPU */
/*
* 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();
current_thread_info()->status |= TS_POLLING;
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_stop_sched_tick();
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 (!idle)
idle = default_idle;
if (cpu_is_offline(cpu))
play_dead();
__get_cpu_var(irq_stat).idle_timestamp = jiffies;
idle();
}
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
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, 0, 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 eax, unsigned long ecx)
{
if (!need_resched()) {
__monitor((void *)&current_thread_info()->flags, 0, 0);
smp_mb();
if (!need_resched())
__mwait(eax, ecx);
}
}
/* 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);
}
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_MWAIT)) {
printk("monitor/mwait feature present.\n");
/*
* Skip, if setup has overridden idle.
* One CPU supports mwait => All CPUs supports mwait
*/
if (!pm_idle) {
printk("using mwait in idle threads.\n");
pm_idle = mwait_idle;
}
}
}
static int __init idle_setup(char *str)
{
if (!strcmp(str, "poll")) {
printk("using polling idle threads.\n");
pm_idle = poll_idle;
#ifdef CONFIG_X86_SMP
if (smp_num_siblings > 1)
printk("WARNING: polling idle and HT enabled, performance may degrade.\n");
#endif
} 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)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
unsigned long d0, d1, d2, d3, d6, d7;
unsigned long esp;
unsigned short ss, gs;
if (user_mode_vm(regs)) {
esp = regs->esp;
ss = regs->xss & 0xffff;
savesegment(gs, gs);
} else {
esp = (unsigned long) (&regs->esp);
savesegment(ss, ss);
savesegment(gs, gs);
}
printk("\n");
printk("Pid: %d, comm: %s %s (%s %.*s)\n",
task_pid_nr(current), current->comm,
print_tainted(), init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
0xffff & regs->xcs, regs->eip, regs->eflags,
smp_processor_id());
print_symbol("EIP is at %s\n", regs->eip);
printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->eax, regs->ebx, regs->ecx, regs->edx);
printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
regs->esi, regs->edi, regs->ebp, esp);
printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
regs->xds & 0xffff, regs->xes & 0xffff,
regs->xfs & 0xffff, gs, ss);
if (!all)
return;
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = read_cr3();
cr4 = read_cr4_safe();
printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
cr0, cr2, cr3, cr4);
get_debugreg(d0, 0);
get_debugreg(d1, 1);
get_debugreg(d2, 2);
get_debugreg(d3, 3);
printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
d0, d1, d2, d3);
get_debugreg(d6, 6);
get_debugreg(d7, 7);
printk("DR6: %08lx DR7: %08lx\n",
d6, d7);
}
void show_regs(struct pt_regs *regs)
{
__show_registers(regs, 1);
show_trace(NULL, regs, &regs->esp);
}
/*
* This gets run with %ebx containing the
* function to call, and %edx 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(&regs, 0, sizeof(regs));
regs.ebx = (unsigned long) fn;
regs.edx = (unsigned long) arg;
regs.xds = __USER_DS;
regs.xes = __USER_DS;
regs.xfs = __KERNEL_PERCPU;
regs.orig_eax = -1;
regs.eip = (unsigned long) kernel_thread_helper;
regs.xcs = __KERNEL_CS | get_kernel_rpl();
regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
/* Ok, create the new process.. */
return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
}
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;
memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
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);
release_vm86_irqs(dead_task);
}
/*
* This gets called before we allocate a new thread and copy
* the current task into it.
*/
void prepare_to_copy(struct task_struct *tsk)
{
unlazy_fpu(tsk);
}
int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
unsigned long unused,
struct task_struct * p, struct pt_regs * regs)
{
struct pt_regs * childregs;
struct task_struct *tsk;
int err;
childregs = task_pt_regs(p);
*childregs = *regs;
childregs->eax = 0;
childregs->esp = esp;
p->thread.esp = (unsigned long) childregs;
p->thread.esp0 = (unsigned long) (childregs+1);
p->thread.eip = (unsigned long) ret_from_fork;
savesegment(gs,p->thread.gs);
tsk = current;
if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
IO_BITMAP_BYTES, GFP_KERNEL);
if (!p->thread.io_bitmap_ptr) {
p->thread.io_bitmap_max = 0;
return -ENOMEM;
}
set_tsk_thread_flag(p, TIF_IO_BITMAP);
}
/*
* Set a new TLS for the child thread?
*/
if (clone_flags & CLONE_SETTLS) {
struct desc_struct *desc;
struct user_desc info;
int idx;
err = -EFAULT;
if (copy_from_user(&info, (void __user *)childregs->esi, sizeof(info)))
goto out;
err = -EINVAL;
if (LDT_empty(&info))
goto out;
idx = info.entry_number;
if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
goto out;
desc = p->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
desc->a = LDT_entry_a(&info);
desc->b = LDT_entry_b(&info);
}
err = 0;
out:
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
return err;
}
/*
* fill in the user structure for a core dump..
*/
void dump_thread(struct pt_regs * regs, struct user * dump)
{
int i;
/* changed the size calculations - should hopefully work better. lbt */
dump->magic = CMAGIC;
dump->start_code = 0;
dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
dump->u_dsize -= dump->u_tsize;
dump->u_ssize = 0;
for (i = 0; i < 8; i++)
dump->u_debugreg[i] = current->thread.debugreg[i];
if (dump->start_stack < TASK_SIZE)
dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;
dump->regs.ebx = regs->ebx;
dump->regs.ecx = regs->ecx;
dump->regs.edx = regs->edx;
dump->regs.esi = regs->esi;
dump->regs.edi = regs->edi;
dump->regs.ebp = regs->ebp;
dump->regs.eax = regs->eax;
dump->regs.ds = regs->xds;
dump->regs.es = regs->xes;
dump->regs.fs = regs->xfs;
savesegment(gs,dump->regs.gs);
dump->regs.orig_eax = regs->orig_eax;
dump->regs.eip = regs->eip;
dump->regs.cs = regs->xcs;
dump->regs.eflags = regs->eflags;
dump->regs.esp = regs->esp;
dump->regs.ss = regs->xss;
dump->u_fpvalid = dump_fpu (regs, &dump->i387);
}
EXPORT_SYMBOL(dump_thread);
/*
* Capture the user space registers if the task is not running (in user space)
*/
int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
{
struct pt_regs ptregs = *task_pt_regs(tsk);
ptregs.xcs &= 0xffff;
ptregs.xds &= 0xffff;
ptregs.xes &= 0xffff;
ptregs.xss &= 0xffff;
elf_core_copy_regs(regs, &ptregs);
return 1;
}
#ifdef CONFIG_SECCOMP
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();
}
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 *next;
next = &next_p->thread;
if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
set_debugreg(next->debugreg[0], 0);
set_debugreg(next->debugreg[1], 1);
set_debugreg(next->debugreg[2], 2);
set_debugreg(next->debugreg[3], 3);
/* no 4 and 5 */
set_debugreg(next->debugreg[6], 6);
set_debugreg(next->debugreg[7], 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
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;
}
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;
}
/*
* 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.
*/
tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
}
/*
* switch_to(x,yn) should switch tasks from x to y.
*
* We fsave/fwait so that an exception goes off at the right time
* (as a call from the fsave or fwait in effect) rather than to
* the wrong process. Lazy FP saving no longer makes any sense
* with modern CPU's, and this simplifies a lot of things (SMP
* and UP become the same).
*
* NOTE! We used to use the x86 hardware context switching. The
* reason for not using it any more becomes apparent when you
* try to recover gracefully from saved state that is no longer
* valid (stale segment register values in particular). With the
* hardware task-switch, there is no way to fix up bad state in
* a reasonable manner.
*
* The fact that Intel documents the hardware task-switching to
* be slow is a fairly red herring - this code is not noticeably
* faster. However, there _is_ some room for improvement here,
* so the performance issues may eventually be a valid point.
* More important, however, is the fact that this allows us much
* more flexibility.
*
* The return value (in %eax) will be the "prev" task after
* the task-switch, and shows up in ret_from_fork in entry.S,
* for example.
*/
struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
*next = &next_p->thread;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
__unlazy_fpu(prev_p);
/* we're going to use this soon, after a few expensive things */
if (next_p->fpu_counter > 5)
prefetch(&next->i387.fxsave);
/*
* Reload esp0.
*/
load_esp0(tss, next);
/*
* Save away %gs. No need to save %fs, as it was saved on the
* stack on entry. No need to save %es and %ds, as those are
* always kernel segments while inside the kernel. Doing this
* before setting the new TLS descriptors avoids the situation
* where we temporarily have non-reloadable segments in %fs
* and %gs. This could be an issue if the NMI handler ever
* used %fs or %gs (it does not today), or if the kernel is
* running inside of a hypervisor layer.
*/
savesegment(gs, prev->gs);
/*
* Load the per-thread Thread-Local Storage descriptor.
*/
load_TLS(next, cpu);
/*
* Restore IOPL if needed. In normal use, the flags restore
* in the switch assembly will handle this. But if the kernel
* is running virtualized at a non-zero CPL, the popf will
* not restore flags, so it must be done in a separate step.
*/
if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
set_iopl_mask(next->iopl);
/*
* Now maybe handle debug registers and/or IO bitmaps
*/
if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
__switch_to_xtra(prev_p, next_p, tss);
/*
* Leave lazy mode, flushing any hypercalls made here.
* This must be done before restoring TLS segments so
* the GDT and LDT are properly updated, and must be
* done before math_state_restore, so the TS bit is up
* to date.
*/
arch_leave_lazy_cpu_mode();
/* 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();
/*
* Restore %gs if needed (which is common)
*/
if (prev->gs | next->gs)
loadsegment(gs, next->gs);
x86_write_percpu(current_task, next_p);
return prev_p;
}
asmlinkage int sys_fork(struct pt_regs regs)
{
return do_fork(SIGCHLD, regs.esp, &regs, 0, NULL, NULL);
}
asmlinkage int sys_clone(struct pt_regs regs)
{
unsigned long clone_flags;
unsigned long newsp;
int __user *parent_tidptr, *child_tidptr;
clone_flags = regs.ebx;
newsp = regs.ecx;
parent_tidptr = (int __user *)regs.edx;
child_tidptr = (int __user *)regs.edi;
if (!newsp)
newsp = regs.esp;
return do_fork(clone_flags, newsp, &regs, 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.esp, &regs, 0, NULL, NULL);
}
/*
* sys_execve() executes a new program.
*/
asmlinkage int sys_execve(struct pt_regs regs)
{
int error;
char * filename;
filename = getname((char __user *) regs.ebx);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
error = do_execve(filename,
(char __user * __user *) regs.ecx,
(char __user * __user *) regs.edx,
&regs);
if (error == 0) {
task_lock(current);
current->ptrace &= ~PT_DTRACE;
task_unlock(current);
/* Make sure we don't return using sysenter.. */
set_thread_flag(TIF_IRET);
}
putname(filename);
out:
return error;
}
#define top_esp (THREAD_SIZE - sizeof(unsigned long))
#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long))
unsigned long get_wchan(struct task_struct *p)
{
unsigned long ebp, esp, eip;
unsigned long stack_page;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
stack_page = (unsigned long)task_stack_page(p);
esp = p->thread.esp;
if (!stack_page || esp < stack_page || esp > top_esp+stack_page)
return 0;
/* include/asm-i386/system.h:switch_to() pushes ebp last. */
ebp = *(unsigned long *) esp;
do {
if (ebp < stack_page || ebp > top_ebp+stack_page)
return 0;
eip = *(unsigned long *) (ebp+4);
if (!in_sched_functions(eip))
return eip;
ebp = *(unsigned long *) ebp;
} while (count++ < 16);
return 0;
}
/*
* sys_alloc_thread_area: get a yet unused TLS descriptor index.
*/
static int get_free_idx(void)
{
struct thread_struct *t = &current->thread;
int idx;
for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
if (desc_empty(t->tls_array + idx))
return idx + GDT_ENTRY_TLS_MIN;
return -ESRCH;
}
/*
* Set a given TLS descriptor:
*/
asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
{
struct thread_struct *t = &current->thread;
struct user_desc info;
struct desc_struct *desc;
int cpu, idx;
if (copy_from_user(&info, u_info, sizeof(info)))
return -EFAULT;
idx = info.entry_number;
/*
* index -1 means the kernel should try to find and
* allocate an empty descriptor:
*/
if (idx == -1) {
idx = get_free_idx();
if (idx < 0)
return idx;
if (put_user(idx, &u_info->entry_number))
return -EFAULT;
}
if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
return -EINVAL;
desc = t->tls_array + idx - GDT_ENTRY_TLS_MIN;
/*
* We must not get preempted while modifying the TLS.
*/
cpu = get_cpu();
if (LDT_empty(&info)) {
desc->a = 0;
desc->b = 0;
} else {
desc->a = LDT_entry_a(&info);
desc->b = LDT_entry_b(&info);
}
load_TLS(t, cpu);
put_cpu();
return 0;
}
/*
* Get the current Thread-Local Storage area:
*/
#define GET_BASE(desc) ( \
(((desc)->a >> 16) & 0x0000ffff) | \
(((desc)->b << 16) & 0x00ff0000) | \
( (desc)->b & 0xff000000) )
#define GET_LIMIT(desc) ( \
((desc)->a & 0x0ffff) | \
((desc)->b & 0xf0000) )
#define GET_32BIT(desc) (((desc)->b >> 22) & 1)
#define GET_CONTENTS(desc) (((desc)->b >> 10) & 3)
#define GET_WRITABLE(desc) (((desc)->b >> 9) & 1)
#define GET_LIMIT_PAGES(desc) (((desc)->b >> 23) & 1)
#define GET_PRESENT(desc) (((desc)->b >> 15) & 1)
#define GET_USEABLE(desc) (((desc)->b >> 20) & 1)
asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
{
struct user_desc info;
struct desc_struct *desc;
int idx;
if (get_user(idx, &u_info->entry_number))
return -EFAULT;
if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
return -EINVAL;
memset(&info, 0, sizeof(info));
desc = current->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
info.entry_number = idx;
info.base_addr = GET_BASE(desc);
info.limit = GET_LIMIT(desc);
info.seg_32bit = GET_32BIT(desc);
info.contents = GET_CONTENTS(desc);
info.read_exec_only = !GET_WRITABLE(desc);
info.limit_in_pages = GET_LIMIT_PAGES(desc);
info.seg_not_present = !GET_PRESENT(desc);
info.useable = GET_USEABLE(desc);
if (copy_to_user(u_info, &info, sizeof(info)))
return -EFAULT;
return 0;
}
unsigned long arch_align_stack(unsigned long sp)
{
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
sp -= get_random_int() % 8192;
return sp & ~0xf;
}
View Git Blame Copy Permalink