int __die(const char *str, struct pt_regs *regs, long err)
{
#ifdef CONFIG_X86_32
unsigned short ss;
unsigned long sp;
#endif
printk(KERN_DEFAULT
"%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
#ifdef CONFIG_PREEMPT
printk("PREEMPT ");
#endif
#ifdef CONFIG_SMP
printk("SMP ");
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
printk("DEBUG_PAGEALLOC ");
#endif
#ifdef CONFIG_KASAN
printk("KASAN");
#endif
printk("\n");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
return 1;
/* FIXME this should probably also need to print into buffer */
print_modules();
show_regs(regs);
#ifdef CONFIG_X86_32
if (user_mode(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
} else {
sp = kernel_stack_pointer(regs);
savesegment(ss, ss);
}
printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
print_symbol("%s", regs->ip);
printk(" SS:ESP %04x:%08lx\n", ss, sp);
#else
/* Executive summary in case the oops scrolled away */
printk(KERN_ALERT "RIP ");
/* FIXME */
printk_address(regs->ip);
printk(" RSP <%016lx>\n", regs->sp);
#endif
return 0;
}
int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
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->ax = 0;
childregs->sp = sp;
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
p->thread.ip = (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);
}
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;
}
int __kprobes __die(const char *str, struct pt_regs *regs, long err)
{
#ifdef CONFIG_X86_32
unsigned short ss;
unsigned long sp;
#endif
printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
#ifdef CONFIG_PREEMPT
printk("PREEMPT ");
#endif
#ifdef CONFIG_SMP
printk("SMP ");
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
printk("DEBUG_PAGEALLOC");
#endif
printk("\n");
sysfs_printk_last_file();
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
return 1;
show_registers(regs);
#ifdef CONFIG_X86_32
if (user_mode_vm(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
} else {
sp = kernel_stack_pointer(regs);
savesegment(ss, ss);
}
printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
print_symbol("%s", regs->ip);
printk(" SS:ESP %04x:%08lx\n", ss, sp);
#else
/* Executive summary in case the oops scrolled away */
printk(KERN_ALERT "RIP ");
printk_address(regs->ip, 1);
printk(" RSP <%016lx>\n", regs->sp);
#endif
return 0;
}
static int
setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
struct pt_regs *regs, unsigned long mask)
{
int tmp, err = 0;
err |= __put_user(regs->xfs, (unsigned int __user *)&sc->fs);
savesegment(gs, tmp);
err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
err |= __put_user(regs->xes, (unsigned int __user *)&sc->es);
err |= __put_user(regs->xds, (unsigned int __user *)&sc->ds);
err |= __put_user(regs->edi, &sc->edi);
err |= __put_user(regs->esi, &sc->esi);
err |= __put_user(regs->ebp, &sc->ebp);
err |= __put_user(regs->esp, &sc->esp);
err |= __put_user(regs->ebx, &sc->ebx);
err |= __put_user(regs->edx, &sc->edx);
err |= __put_user(regs->ecx, &sc->ecx);
err |= __put_user(regs->eax, &sc->eax);
err |= __put_user(current->thread.trap_no, &sc->trapno);
err |= __put_user(current->thread.error_code, &sc->err);
err |= __put_user(regs->eip, &sc->eip);
err |= __put_user(regs->xcs, (unsigned int __user *)&sc->cs);
err |= __put_user(regs->eflags, &sc->eflags);
err |= __put_user(regs->esp, &sc->esp_at_signal);
err |= __put_user(regs->xss, (unsigned int __user *)&sc->ss);
tmp = save_i387(fpstate);
if (tmp < 0)
err = 1;
else
err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
/* non-iBCS2 extensions.. */
err |= __put_user(mask, &sc->oldmask);
err |= __put_user(current->thread.cr2, &sc->cr2);
return err;
}
int __die(const char *str, struct pt_regs *regs, long err)
{
#ifdef CONFIG_X86_32
unsigned short ss;
unsigned long sp;
#endif
printk(KERN_DEFAULT
"%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
return 1;
print_modules();
show_regs(regs);
#ifdef CONFIG_X86_32
if (user_mode(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
} else {
sp = kernel_stack_pointer(regs);
savesegment(ss, ss);
}
printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
print_symbol("%s", regs->ip);
printk(" SS:ESP %04x:%08lx\n", ss, sp);
#else
/* Executive summary in case the oops scrolled away */
printk(KERN_ALERT "RIP ");
printk_address(regs->ip);
printk(" RSP <%016lx>\n", regs->sp);
#endif
return 0;
}
/*
* 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);
}
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;
gs = get_user_gs(regs);
} else {
sp = (unsigned long) (®s->sp);
savesegment(ss, ss);
savesegment(gs, gs);
}
printk("\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, board);
printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
(u16)regs->cs, regs->ip, regs->flags,
smp_processor_id());
print_symbol("EIP is at %s\n", regs->ip);
printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->ax, regs->bx, regs->cx, regs->dx);
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",
(u16)regs->ds, (u16)regs->es, (u16)regs->fs, 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);
}
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(fs,p->thread.fs);
savesegment(gs,p->thread.gs);
tsk = current;
if (unlikely(test_tsk_thread_flag(tsk, 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;
return -ENOMEM;
}
memcpy(p->thread.io_bitmap_ptr, tsk->thread.io_bitmap_ptr,
IO_BITMAP_BYTES);
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);
}
p->thread.iopl = current->thread.iopl;
err = 0;
out:
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
return err;
}
/*
* Set a given TLS descriptor:
*/
int do_set_thread_area(struct task_struct *p, int idx,
struct user_desc __user *u_info,
int can_allocate)
{
struct user_desc info;
unsigned short __maybe_unused sel, modified_sel;
if (copy_from_user(&info, u_info, sizeof(info)))
return -EFAULT;
if (!tls_desc_okay(&info))
return -EINVAL;
if (idx == -1)
idx = info.entry_number;
/*
* index -1 means the kernel should try to find and
* allocate an empty descriptor:
*/
if (idx == -1 && can_allocate) {
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;
set_tls_desc(p, idx, &info, 1);
/*
* If DS, ES, FS, or GS points to the modified segment, forcibly
* refresh it. Only needed on x86_64 because x86_32 reloads them
* on return to user mode.
*/
modified_sel = (idx << 3) | 3;
if (p == current) {
#ifdef CONFIG_X86_64
savesegment(ds, sel);
if (sel == modified_sel)
loadsegment(ds, sel);
savesegment(es, sel);
if (sel == modified_sel)
loadsegment(es, sel);
savesegment(fs, sel);
if (sel == modified_sel)
loadsegment(fs, sel);
savesegment(gs, sel);
if (sel == modified_sel)
load_gs_index(sel);
#endif
#ifdef CONFIG_X86_32_LAZY_GS
savesegment(gs, sel);
if (sel == modified_sel)
loadsegment(gs, sel);
#endif
} else {
#ifdef CONFIG_X86_64
if (p->thread.fsindex == modified_sel)
p->thread.fsbase = info.base_addr;
if (p->thread.gsindex == modified_sel)
p->thread.gsbase = info.base_addr;
#endif
}
return 0;
}
long vmadump_store_cpu(cr_chkpt_proc_req_t *ctx, struct file *file,
struct pt_regs *regs) {
long bytes = 0, r;
/* Store struct pt_regs */
#ifdef CONFIG_XEN
/* Ensure CS and SS are not Xen-modified, others restore based on CS */
{ struct pt_regs regtmp = *regs;
if (test_thread_flag(TIF_IA32)) {
regtmp.cs = __USER32_CS;
regtmp.ss = __USER32_DS;
} else {
regtmp.cs = __USER_CS;
regtmp.ss = __USER_DS;
}
r = write_kern(ctx, file, ®tmp, sizeof(regtmp));
}
#else
r = write_kern(ctx, file, regs, sizeof(*regs));
#endif
if (r != sizeof(*regs)) goto err;
bytes += r;
/* Store FPU info (and later general "extended state") */
r = vmadump_store_i387(ctx, file);
if (r <= 0) goto err;
bytes += r;
/* Store debugging state */
r = vmadump_store_debugreg(ctx, file);
if (r < 0) goto err;
bytes += r;
/* user(r)sp, since we don't use the ptrace entry path in BLCR */
#if HAVE_THREAD_USERSP
current->thread.usersp = vmad_read_oldrsp();
r = write_kern(ctx, file, ¤t->thread.usersp,
sizeof(current->thread.usersp));
if (r != sizeof(current->thread.usersp)) goto err;
#elif HAVE_THREAD_USERRSP
current->thread.userrsp = vmad_read_oldrsp();
r = write_kern(ctx, file, ¤t->thread.userrsp,
sizeof(current->thread.userrsp));
if (r != sizeof(current->thread.userrsp)) goto err;
#else
#error
#endif
bytes += r;
/* Store all weird segmenty crap */
/* 64-bit offsets for FS and GS */
r = write_kern(ctx, file, ¤t->thread.fs,
sizeof(current->thread.fs));
if (r != sizeof(current->thread.fs)) goto err;
bytes += r;
r = write_kern(ctx, file, ¤t->thread.gs,
sizeof(current->thread.gs));
if (r != sizeof(current->thread.gs)) goto err;
bytes += r;
savesegment(fs,current->thread.fsindex);
savesegment(gs,current->thread.gsindex);
/* 32-bit segment descriptors for FS and GS */
r = write_kern(ctx, file, ¤t->thread.fsindex,
sizeof(current->thread.fsindex));
if (r != sizeof(current->thread.fsindex)) goto err;
bytes += r;
r = write_kern(ctx, file, ¤t->thread.gsindex,
sizeof(current->thread.gsindex));
if (r != sizeof(current->thread.gsindex)) goto err;
bytes += r;
/* TLS segment descriptors */
r = write_kern(ctx, file, ¤t->thread.tls_array,
sizeof(current->thread.tls_array));
if (r != sizeof(current->thread.tls_array)) goto err;
bytes += r;
#if HAVE_THREAD_INFO_SYSENTER_RETURN
{
void *sysenter_return = current_thread_info()->sysenter_return;
r = write_kern(ctx, file, &sysenter_return, sizeof(sysenter_return));
if (r != sizeof(sysenter_return)) goto err;
}
#endif
return bytes;
err:
if (r >= 0) r = -EIO;
return r;
}
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, i;
childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p->thread_info)) - 1;
*childregs = *regs;
childregs->eax = 0;
childregs->esp = esp;
p->set_child_tid = p->clear_child_tid = NULL;
p->thread.esp = (unsigned long) childregs;
p->thread.esp0 = (unsigned long) (childregs+1);
/*
* get the two stack pages, for the virtual stack.
*
* IMPORTANT: this code relies on the fact that the task
* structure is an THREAD_SIZE aligned piece of physical memory.
*/
for (i = 0; i < ARRAY_SIZE(p->thread.stack_page); i++)
p->thread.stack_page[i] =
virt_to_page((unsigned long)p->thread_info + (i*PAGE_SIZE));
p->thread.eip = (unsigned long) ret_from_fork;
p->thread_info->real_stack = p->thread_info;
savesegment(fs,p->thread.fs);
savesegment(gs,p->thread.gs);
tsk = current;
if (unlikely(NULL != tsk->thread.io_bitmap_ptr)) {
p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
if (!p->thread.io_bitmap_ptr) {
p->thread.io_bitmap_max = 0;
return -ENOMEM;
}
memcpy(p->thread.io_bitmap_ptr, tsk->thread.io_bitmap_ptr,
IO_BITMAP_BYTES);
}
/*
* 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);
}
p->thread.io_pl = current->thread.io_pl;
err = 0;
out:
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
return err;
}
int copy_thread(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p)
{
struct pt_regs *childregs = task_stack_page(p) + THREAD_SIZE - sizeof(struct pt_regs) - 8;
struct task_struct *tsk;
int err;
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
p->tinfo.lowest_stack = (unsigned long)task_stack_page(p);
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
p->thread.ip = (unsigned long) ret_from_kernel_thread;
savesegment(gs, childregs->gs);
childregs->ds = __KERNEL_DS;
childregs->es = __KERNEL_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;
}
static int __cpuinit
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
struct vcpu_guest_context *ctxt;
struct desc_struct *gdt;
unsigned long gdt_mfn;
if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
return 0;
ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
if (ctxt == NULL)
return -ENOMEM;
gdt = get_cpu_gdt_table(cpu);
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.ss = __KERNEL_DS;
#ifdef CONFIG_X86_32
ctxt->user_regs.fs = __KERNEL_PERCPU;
savesegment(gs, ctxt->user_regs.gs);
#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
{
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
ctxt->user_regs.ds = __KERNEL_DS;
ctxt->user_regs.es = __KERNEL_DS;
xen_copy_trap_info(ctxt->trap_ctxt);
ctxt->ldt_ents = 0;
BUG_ON((unsigned long)gdt & ~PAGE_MASK);
gdt_mfn = arbitrary_virt_to_mfn(gdt);
make_lowmem_page_readonly(gdt);
make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
ctxt->gdt_frames[0] = gdt_mfn;
ctxt->gdt_ents = GDT_ENTRIES;
ctxt->kernel_ss = __KERNEL_DS;
ctxt->kernel_sp = idle->thread.sp0;
#ifdef CONFIG_X86_32
ctxt->event_callback_cs = __KERNEL_CS;
ctxt->failsafe_callback_cs = __KERNEL_CS;
#endif
ctxt->event_callback_eip =
(unsigned long)xen_hypervisor_callback;
ctxt->failsafe_callback_eip =
(unsigned long)xen_failsafe_callback;
}
ctxt->user_regs.cs = __KERNEL_CS;
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
if (HYPERVISOR_vcpu_op(VCPUOP_initialise, cpu, ctxt))
BUG();
kfree(ctxt);
return 0;
}
/*
* 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(next_p)->flags & _TIF_WORK_CTXSW)
|| test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)))
__switch_to_xtra(next_p, tss);
disable_tsc(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_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;
}
