/*
* 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 = __KERNEL_DS;
regs.es = __KERNEL_DS;
regs.fs = __KERNEL_PERCPU;
savesegment(gs, regs.gs);
#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 | 0x2;
/* Ok, create the new process.. */
return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL);
}
__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;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
bool preload_fpu;
preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
__unlazy_fpu(prev_p);
if (preload_fpu)
prefetch(next->xstate);
load_sp0(tss, next);
lazy_save_gs(prev->gs);
load_TLS(next, cpu);
if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
set_iopl_mask(next->iopl);
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);
if (preload_fpu)
clts();
arch_end_context_switch(next_p);
if (preload_fpu)
__math_state_restore();
if (prev->gs | next->gs)
lazy_load_gs(next->gs);
percpu_write(current_task, next_p);
return prev_p;
}
/*
* Create a kernel thread
*/
int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
{
struct pt_regs regs;
#ifdef CONFIG_L4_VCPU
unsigned ds, cs;
asm volatile ("mov %%ds, %0; mov %%cs, %1\n" : "=r"(ds), "=r"(cs));
#endif
memset(®s, 0, sizeof(regs));
regs.bx = (unsigned long) fn;
regs.dx = (unsigned long) arg;
#ifdef CONFIG_L4_VCPU
regs.ds = ds;
regs.ds = ds;
regs.es = ds;
#ifdef CONFIG_SMP
regs.fs = (l4x_fiasco_gdt_entry_offset + 2) * 8 + 3;
#else
regs.fs = ds;
#endif
#else
regs.ds = __USER_DS;
regs.es = __USER_DS;
regs.fs = __KERNEL_PERCPU;
regs.gs = __KERNEL_STACK_CANARY;
#endif
regs.orig_ax = -1;
#ifdef CONFIG_L4_VCPU
regs.ip = (unsigned long) kernel_thread_helper;
regs.cs = (cs & ~3) | get_kernel_rpl();
#else
regs.cs = __KERNEL_CS | get_kernel_rpl();
#endif
regs.flags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
/* Ok, create the new process.. */
return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, COPY_THREAD_STACK_SIZE___FLAG_INKERNEL, NULL, NULL);
}
/*H:000
* Welcome to the Host!
*
* By this point your brain has been tickled by the Guest code and numbed by
* the Launcher code; prepare for it to be stretched by the Host code. This is
* the heart. Let's begin at the initialization routine for the Host's lg
* module.
*/
static int __init init(void)
{
int err;
/* Lguest can't run under Xen, VMI or itself. It does Tricky Stuff. */
if (get_kernel_rpl() != 0) {
printk("lguest is afraid of being a guest\n");
return -EPERM;
}
/* First we put the Switcher up in very high virtual memory. */
err = map_switcher();
if (err)
goto out;
/* Now we set up the pagetable implementation for the Guests. */
err = init_pagetables(switcher_page, SHARED_SWITCHER_PAGES);
if (err)
goto unmap;
/* We might need to reserve an interrupt vector. */
err = init_interrupts();
if (err)
goto free_pgtables;
/* /dev/lguest needs to be registered. */
err = lguest_device_init();
if (err)
goto free_interrupts;
/* Finally we do some architecture-specific setup. */
lguest_arch_host_init();
/* All good! */
return 0;
free_interrupts:
free_interrupts();
free_pgtables:
free_pagetables();
unmap:
unmap_switcher();
out:
return err;
}
/*
* 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.bx = (unsigned long) fn;
regs.dx = (unsigned long) arg;
regs.ds = __USER_DS;
regs.es = __USER_DS;
regs.fs = __KERNEL_PERCPU;
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_SF | X86_EFLAGS_PF | 0x2;
/* Ok, create the new process.. */
return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL);
}
__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;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
fpu_switch_t fpu;
fpu = switch_fpu_prepare(prev_p, next_p, cpu);
load_sp0(tss, next);
lazy_save_gs(prev->gs);
load_TLS(next, cpu);
if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
set_iopl_mask(next->iopl);
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);
arch_end_context_switch(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;
}
/*
* 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 %ax) will be the "prev" task after
* the task-switch, and shows up in ret_from_fork in entry.S,
* for example.
*/
__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;
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);
if (next_p->mm)
load_user_cs_desc(cpu, next_p->mm);
/* we're going to use this soon, after a few expensive things */
if (next_p->fpu_counter > 5)
prefetch(next->xstate);
/*
* Reload esp0.
*/
load_sp0(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.
*/
lazy_save_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_end_context_switch(next_p);
/* 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 (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)
lazy_load_gs(next->gs);
percpu_write(current_task, next_p);
return prev_p;
}
int copy_thread(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p)
{
struct pt_regs *childregs = task_pt_regs(p);
struct task_struct *tsk;
int err;
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
p->thread.ip = (unsigned long) ret_from_kernel_thread;
task_user_gs(p) = __KERNEL_STACK_CANARY;
childregs->ds = __USER_DS;
childregs->es = __USER_DS;
childregs->fs = __KERNEL_PERCPU;
childregs->bx = sp; /* function */
childregs->bp = arg;
childregs->orig_ax = -1;
childregs->cs = __KERNEL_CS | get_kernel_rpl();
childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
p->fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
return 0;
}
*childregs = *current_pt_regs();
childregs->ax = 0;
if (sp)
childregs->sp = sp;
p->thread.ip = (unsigned long) ret_from_fork;
task_user_gs(p) = get_user_gs(current_pt_regs());
p->fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
tsk = current;
err = -ENOMEM;
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
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);
}
err = 0;
/*
* Set a new TLS for the child thread?
*/
if (clone_flags & CLONE_SETTLS)
err = do_set_thread_area(p, -1,
(struct user_desc __user *)childregs->si, 0);
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
return err;
}
/*
* switch_to(x,y) 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 %ax) will be the "prev" task after
* the task-switch, and shows up in ret_from_fork in entry.S,
* for example.
*/
__visible __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;
struct fpu *prev_fpu = &prev->fpu;
struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
fpu_switch_t fpu_switch;
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
/*
* 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.
*/
lazy_save_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);
/*
* If it were not for PREEMPT_ACTIVE we could guarantee that the
* preempt_count of all tasks was equal here and this would not be
* needed.
*/
task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
/*
* 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 fpu__restore(), so the TS bit is up
* to date.
*/
arch_end_context_switch(next_p);
/*
* Reload esp0 and cpu_current_top_of_stack. This changes
* current_thread_info().
*/
load_sp0(tss, next);
this_cpu_write(cpu_current_top_of_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE);
/*
* Restore %gs if needed (which is common)
*/
if (prev->gs | next->gs)
lazy_load_gs(next->gs);
switch_fpu_finish(next_fpu, fpu_switch);
this_cpu_write(current_task, next_p);
return prev_p;
}
/*
* switch_to(x,y) 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 %ax) will be the "prev" task after
* the task-switch, and shows up in ret_from_fork in entry.S,
* for example.
*/
__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;
int cpu = smp_processor_id();
struct tss_struct *tss = init_tss + cpu;
fpu_switch_t fpu;
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
fpu = switch_fpu_prepare(prev_p, next_p, cpu);
/*
* Reload esp0.
*/
load_sp0(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.
*/
lazy_save_gs(prev->gs);
#ifdef CONFIG_PAX_MEMORY_UDEREF
__set_fs(task_thread_info(next_p)->addr_limit);
#endif
/*
* 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);
switch_kmaps(prev_p, next_p);
/*
* 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_end_context_switch(next_p);
this_cpu_write(current_task, next_p);
this_cpu_write(current_tinfo, &next_p->tinfo);
/*
* Restore %gs if needed (which is common)
*/
if (prev->gs | next->gs)
lazy_load_gs(next->gs);
switch_fpu_finish(next_p, fpu);
return prev_p;
}
