/*
* pgd3val: this is the value of init_mm.pgd[3] in a PV guest. It is optional.
* This to assist debug of modules in the guest. The kernel address
* space seems is always mapped, but modules are not necessarily
* mapped in any arbitraty guest cr3 that we pick if pgd3val is 0.
* Modules should always be addressible if we use cr3 from init_mm.
* Since pgd3val is already a pgd value, cr3->pgd[3], we just need to
* do 2 level lookups.
*
* NOTE: 4 level paging works for 32 PAE guests also because cpu runs in IA32-e
* mode.
* Returns: mfn for the given (pv guest) vaddr
*/
static unsigned long
dbg_pv_va2mfn(dbgva_t vaddr, struct domain *dp, uint64_t pgd3val)
{
l4_pgentry_t l4e, *l4t;
l3_pgentry_t l3e, *l3t;
l2_pgentry_t l2e, *l2t;
l1_pgentry_t l1e, *l1t;
unsigned long cr3 = (pgd3val ? pgd3val : dp->vcpu[0]->arch.cr3);
unsigned long mfn = cr3 >> PAGE_SHIFT;
DBGP2("vaddr:%lx domid:%d cr3:%lx pgd3:%lx\n", vaddr, dp->domain_id,
cr3, pgd3val);
if ( pgd3val == 0 )
{
l4t = mfn_to_virt(mfn);
l4e = l4t[l4_table_offset(vaddr)];
mfn = l4e_get_pfn(l4e);
DBGP2("l4t:%p l4to:%lx l4e:%lx mfn:%lx\n", l4t,
l4_table_offset(vaddr), l4e, mfn);
if ( !(l4e_get_flags(l4e) & _PAGE_PRESENT) )
{
DBGP1("l4 PAGE not present. vaddr:%lx cr3:%lx\n", vaddr, cr3);
return INVALID_MFN;
}
l3t = mfn_to_virt(mfn);
l3e = l3t[l3_table_offset(vaddr)];
mfn = l3e_get_pfn(l3e);
DBGP2("l3t:%p l3to:%lx l3e:%lx mfn:%lx\n", l3t,
l3_table_offset(vaddr), l3e, mfn);
if ( !(l3e_get_flags(l3e) & _PAGE_PRESENT) )
{
DBGP1("l3 PAGE not present. vaddr:%lx cr3:%lx\n", vaddr, cr3);
return INVALID_MFN;
}
}
l2t = mfn_to_virt(mfn);
l2e = l2t[l2_table_offset(vaddr)];
mfn = l2e_get_pfn(l2e);
DBGP2("l2t:%p l2to:%lx l2e:%lx mfn:%lx\n", l2t, l2_table_offset(vaddr),
l2e, mfn);
if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) ||
(l2e_get_flags(l2e) & _PAGE_PSE) )
{
DBGP1("l2 PAGE not present. vaddr:%lx cr3:%lx\n", vaddr, cr3);
return INVALID_MFN;
}
l1t = mfn_to_virt(mfn);
l1e = l1t[l1_table_offset(vaddr)];
mfn = l1e_get_pfn(l1e);
DBGP2("l1t:%p l1to:%lx l1e:%lx mfn:%lx\n", l1t, l1_table_offset(vaddr),
l1e, mfn);
return mfn_valid(mfn) ? mfn : INVALID_MFN;
}
struct consfront_dev *xencons_ring_init(void)
{
int err;
struct consfront_dev *dev;
if (!start_info.console.domU.evtchn)
return 0;
dev = malloc(sizeof(struct consfront_dev));
memset(dev, 0, sizeof(struct consfront_dev));
dev->nodename = "device/console";
dev->dom = 0;
dev->backend = 0;
dev->ring_ref = 0;
#ifdef HAVE_LIBC
dev->fd = -1;
#endif
dev->evtchn = start_info.console.domU.evtchn;
dev->ring = (struct xencons_interface *) mfn_to_virt(start_info.console.domU.mfn);
err = bind_evtchn(dev->evtchn, console_handle_input, dev);
if (err <= 0) {
printk("XEN console request chn bind failed %i\n", err);
free(dev);
return NULL;
}
unmask_evtchn(dev->evtchn);
/* In case we have in-flight data after save/restore... */
notify_daemon(dev);
return dev;
}
static void ixp_install_response(struct ixpfront_info *info, struct ixp_response *iresp) {
struct app_response aresp;
char *rsp_ptr = NULL, *dst_ptr = NULL;
int offset = 0, msg_size = 0;
aresp.status = iresp->status;
/* Copy response here into r_params.presp */
rsp_ptr = mfn_to_virt(pfn_to_mfn(info->shadow[iresp->id].frame[0]));
if(rsp_ptr == NULL)
printk(KERN_ERR "pfn_to_virt returned NULL\n");
dst_ptr = info->shadow[iresp->id].r_params.presp;
msg_size = ((struct des_request *)rsp_ptr)->msg_size;
offset = sizeof(struct des_request) + ((struct des_request *)rsp_ptr)->key_size + ((struct des_request *)rsp_ptr)->iv_size;
rsp_ptr += offset;
memcpy(dst_ptr, rsp_ptr, msg_size);
info->app_cb(info->shadow[iresp->id].r_params.callbk_tag, &aresp);
return;
}
static inline struct xencons_interface *xencons_interface(void)
{
if (start_info.console.domU.evtchn)
return mfn_to_virt(start_info.console.domU.mfn);
else
return NULL;
}
static inline struct xencons_interface *xencons_interface(void)
{
if (console_pfn == ~0ul)
return mfn_to_virt(xen_start_info->console.domU.mfn);
else
return __va(console_pfn << PAGE_SHIFT);
}
int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret;
pte_t *pte;
unsigned long mfn;
ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count);
if (ret)
return ret;
if (xen_feature(XENFEAT_auto_translated_physmap))
return ret;
for (i = 0; i < count; i++) {
/* Do not add to override if the map failed. */
if (map_ops[i].status)
continue;
if (map_ops[i].flags & GNTMAP_contains_pte) {
pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
(map_ops[i].host_addr & ~PAGE_MASK));
mfn = pte_mfn(*pte);
} else {
mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
}
ret = m2p_add_override(mfn, pages[i], kmap_ops ?
&kmap_ops[i] : NULL);
if (ret)
return ret;
}
return ret;
}
CAMLprim value
caml_console_start_page(value v_unit)
{
CAMLparam1(v_unit);
CAMLlocal1(v_ret);
unsigned char *page = mfn_to_virt(start_info.console.domU.mfn);
v_ret = (value)page;
CAMLreturn(v_ret);
}
CAMLprim value
caml_xenstore_start_page(value v_unit)
{
CAMLparam1(v_unit);
CAMLlocal1(v_ret);
unsigned char *page = mfn_to_virt(start_info.store_mfn);
v_ret = (value)page;
CAMLreturn(v_ret);
}
static int xsd_kva_read(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len;
len = sprintf(page, "0x%p", mfn_to_virt(xen_start_info->store_mfn));
*eof = 1;
return len;
}
CAMLprim value
caml_xenstore_start_page(value v_unit)
{
CAMLparam1(v_unit);
CAMLreturn(caml_ba_alloc_dims(CAML_BA_UINT8 | CAML_BA_C_LAYOUT,
1,
mfn_to_virt(start_info.store_mfn),
(long)PAGE_SIZE));
}
int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret = 0;
bool lazy = false;
pte_t *pte;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
if (kmap_ops &&
!in_interrupt() &&
paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
arch_enter_lazy_mmu_mode();
lazy = true;
}
for (i = 0; i < count; i++) {
unsigned long mfn, pfn;
/* Do not add to override if the map failed. */
if (map_ops[i].status)
continue;
if (map_ops[i].flags & GNTMAP_contains_pte) {
pte = (pte_t *)(mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
(map_ops[i].host_addr & ~PAGE_MASK));
mfn = pte_mfn(*pte);
} else {
mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
}
pfn = page_to_pfn(pages[i]);
WARN_ON(PagePrivate(pages[i]));
SetPagePrivate(pages[i]);
set_page_private(pages[i], mfn);
pages[i]->index = pfn_to_mfn(pfn);
if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
ret = -ENOMEM;
goto out;
}
if (kmap_ops) {
ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
if (ret)
goto out;
}
}
out:
if (lazy)
arch_leave_lazy_mmu_mode();
return ret;
}
CAMLprim value
caml_xenstore_start_page(value v_unit)
{
CAMLparam1(v_unit);
CAMLlocal1(v_ret);
intnat dims[] = { PAGE_SIZE };
unsigned char *page = mfn_to_virt(start_info.store_mfn);
v_ret = caml_ba_alloc(CAML_BA_UINT8 | CAML_BA_C_LAYOUT, 1, page, dims);
CAMLreturn(v_ret);
}
int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret;
bool lazy = false;
pte_t *pte;
unsigned long mfn;
ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count);
if (ret)
return ret;
/* Retry eagain maps */
for (i = 0; i < count; i++)
if (map_ops[i].status == GNTST_eagain)
gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
&map_ops[i].status, __func__);
if (xen_feature(XENFEAT_auto_translated_physmap))
return ret;
if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
arch_enter_lazy_mmu_mode();
lazy = true;
}
for (i = 0; i < count; i++) {
/* Do not add to override if the map failed. */
if (map_ops[i].status)
continue;
if (map_ops[i].flags & GNTMAP_contains_pte) {
pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
(map_ops[i].host_addr & ~PAGE_MASK));
mfn = pte_mfn(*pte);
} else {
mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
}
ret = m2p_add_override(mfn, pages[i], kmap_ops ?
&kmap_ops[i] : NULL);
if (ret)
goto out;
}
out:
if (lazy)
arch_leave_lazy_mmu_mode();
return ret;
}
static int __init xenbus_init(void)
{
int err = 0;
if (!xen_domain())
return -ENODEV;
if (xen_hvm_domain()) {
uint64_t v = 0;
err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
if (err)
goto out_error;
xen_store_evtchn = (int)v;
err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
if (err)
goto out_error;
xen_store_mfn = (unsigned long)v;
xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
} else {
xen_store_evtchn = xen_start_info->store_evtchn;
xen_store_mfn = xen_start_info->store_mfn;
if (xen_store_evtchn)
xenstored_ready = 1;
else {
err = xenstored_local_init();
if (err)
goto out_error;
}
xen_store_interface = mfn_to_virt(xen_store_mfn);
}
/* Initialize the interface to xenstore. */
err = xs_init();
if (err) {
printk(KERN_WARNING
"XENBUS: Error initializing xenstore comms: %i\n", err);
goto out_error;
}
#ifdef CONFIG_XEN_COMPAT_XENFS
/*
* Create xenfs mountpoint in /proc for compatibility with
* utilities that expect to find "xenbus" under "/proc/xen".
*/
proc_mkdir("xen", NULL);
#endif
out_error:
return err;
}
/* Initialise xenbus. */
void init_xenbus(void)
{
int err;
DEBUG("init_xenbus called.\n");
xenstore_buf = mfn_to_virt(start_info.store_mfn);
create_thread("xenstore", xenbus_thread_func, NULL);
DEBUG("buf at %p.\n", xenstore_buf);
err = bind_evtchn(start_info.store_evtchn,
xenbus_evtchn_handler,
NULL);
unmask_evtchn(start_info.store_evtchn);
printk("xenbus initialised on irq %d mfn %#lx\n",
err, start_info.store_mfn);
}
int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
struct page **pages, unsigned int count)
{
int i, ret;
pte_t *pte;
unsigned long mfn;
ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count);
if (ret)
return ret;
if (xen_feature(XENFEAT_auto_translated_physmap))
return ret;
for (i = 0; i < count; i++) {
/* Do not add to override if the map failed. */
if (map_ops[i].status)
continue;
if (map_ops[i].flags & GNTMAP_contains_pte) {
pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
(map_ops[i].host_addr & ~PAGE_MASK));
mfn = pte_mfn(*pte);
} else {
/* If you really wanted to do this:
* mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
*
* The reason we do not implement it is b/c on the
* unmap path (gnttab_unmap_refs) we have no means of
* checking whether the page is !GNTMAP_contains_pte.
*
* That is without some extra data-structure to carry
* the struct page, bool clear_pte, and list_head next
* tuples and deal with allocation/delallocation, etc.
*
* The users of this API set the GNTMAP_contains_pte
* flag so lets just return not supported until it
* becomes neccessary to implement.
*/
return -EOPNOTSUPP;
}
ret = m2p_add_override(mfn, pages[i],
map_ops[i].flags & GNTMAP_contains_pte);
if (ret)
return ret;
}
return ret;
}
int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret = 0;
pte_t *pte;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
if (kmap_ops) {
ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref,
kmap_ops, count);
if (ret)
goto out;
}
for (i = 0; i < count; i++) {
unsigned long mfn, pfn;
/* Do not add to override if the map failed. */
if (map_ops[i].status)
continue;
if (map_ops[i].flags & GNTMAP_contains_pte) {
pte = (pte_t *)(mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
(map_ops[i].host_addr & ~PAGE_MASK));
mfn = pte_mfn(*pte);
} else {
mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
}
pfn = page_to_pfn(pages[i]);
WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned");
if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
ret = -ENOMEM;
goto out;
}
}
out:
return ret;
}
static int __init xenbus_init(void)
{
int err = 0;
unsigned long page = 0;
DPRINTK("");
err = -ENODEV;
if (!xen_domain())
return err;
/*
* Domain0 doesn't have a store_evtchn or store_mfn yet.
*/
if (xen_initial_domain()) {
struct evtchn_alloc_unbound alloc_unbound;
/* Allocate Xenstore page */
page = get_zeroed_page(GFP_KERNEL);
if (!page)
goto out_error;
xen_store_mfn = xen_start_info->store_mfn =
pfn_to_mfn(virt_to_phys((void *)page) >>
PAGE_SHIFT);
/* Next allocate a local port which xenstored can bind to */
alloc_unbound.dom = DOMID_SELF;
alloc_unbound.remote_dom = 0;
err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
&alloc_unbound);
if (err == -ENOSYS)
goto out_error;
BUG_ON(err);
xen_store_evtchn = xen_start_info->store_evtchn =
alloc_unbound.port;
xen_store_interface = mfn_to_virt(xen_store_mfn);
} else {
if (xen_hvm_domain()) {
/*
* Fully allocate the p2m structure for a given pfn. We need to check
* that both the top and mid levels are allocated, and make sure the
* parallel mfn tree is kept in sync. We may race with other cpus, so
* the new pages are installed with cmpxchg; if we lose the race then
* simply free the page we allocated and use the one that's there.
*/
static bool alloc_p2m(unsigned long pfn)
{
unsigned topidx;
unsigned long *top_mfn_p, *mid_mfn;
pte_t *ptep, *pte_pg;
unsigned int level;
unsigned long flags;
unsigned long addr = (unsigned long)(xen_p2m_addr + pfn);
unsigned long p2m_pfn;
ptep = lookup_address(addr, &level);
BUG_ON(!ptep || level != PG_LEVEL_4K);
pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1));
if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) {
/* PMD level is missing, allocate a new one */
ptep = alloc_p2m_pmd(addr, pte_pg);
if (!ptep)
return false;
}
if (p2m_top_mfn && pfn < MAX_P2M_PFN) {
topidx = p2m_top_index(pfn);
top_mfn_p = &p2m_top_mfn[topidx];
mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]);
BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);
if (mid_mfn == p2m_mid_missing_mfn) {
/* Separately check the mid mfn level */
unsigned long missing_mfn;
unsigned long mid_mfn_mfn;
unsigned long old_mfn;
mid_mfn = alloc_p2m_page();
if (!mid_mfn)
return false;
p2m_mid_mfn_init(mid_mfn, p2m_missing);
missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
mid_mfn_mfn = virt_to_mfn(mid_mfn);
old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn);
if (old_mfn != missing_mfn) {
free_p2m_page(mid_mfn);
mid_mfn = mfn_to_virt(old_mfn);
} else {
p2m_top_mfn_p[topidx] = mid_mfn;
}
}
} else {
mid_mfn = NULL;
}
p2m_pfn = pte_pfn(READ_ONCE(*ptep));
if (p2m_pfn == PFN_DOWN(__pa(p2m_identity)) ||
p2m_pfn == PFN_DOWN(__pa(p2m_missing))) {
/* p2m leaf page is missing */
unsigned long *p2m;
p2m = alloc_p2m_page();
if (!p2m)
return false;
if (p2m_pfn == PFN_DOWN(__pa(p2m_missing)))
p2m_init(p2m);
else
p2m_init_identity(p2m, pfn & ~(P2M_PER_PAGE - 1));
spin_lock_irqsave(&p2m_update_lock, flags);
if (pte_pfn(*ptep) == p2m_pfn) {
HYPERVISOR_shared_info->arch.p2m_generation++;
wmb(); /* Tools are synchronizing via p2m_generation. */
set_pte(ptep,
pfn_pte(PFN_DOWN(__pa(p2m)), PAGE_KERNEL));
wmb(); /* Tools are synchronizing via p2m_generation. */
HYPERVISOR_shared_info->arch.p2m_generation++;
if (mid_mfn)
mid_mfn[p2m_mid_index(pfn)] = virt_to_mfn(p2m);
p2m = NULL;
}
spin_unlock_irqrestore(&p2m_update_lock, flags);
if (p2m)
free_p2m_page(p2m);
}
/* Expanded the p2m? */
if (pfn > xen_p2m_last_pfn) {
xen_p2m_last_pfn = pfn;
HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
}
return true;
}
static int __devinit xenbus_probe_init(void)
#endif
{
int err = 0;
#if defined(CONFIG_XEN) || defined(MODULE)
unsigned long page = 0;
#endif
DPRINTK("");
if (!is_running_on_xen())
return -ENODEV;
/* Register ourselves with the kernel bus subsystem */
xenbus_frontend.error = bus_register(&xenbus_frontend.bus);
if (xenbus_frontend.error)
printk(KERN_WARNING
"XENBUS: Error registering frontend bus: %i\n",
xenbus_frontend.error);
xenbus_backend_bus_register();
/*
* Domain0 doesn't have a store_evtchn or store_mfn yet.
*/
if (is_initial_xendomain()) {
#if defined(CONFIG_XEN) || defined(MODULE)
struct evtchn_alloc_unbound alloc_unbound;
/* Allocate page. */
page = get_zeroed_page(GFP_KERNEL);
if (!page)
return -ENOMEM;
xen_store_mfn = xen_start_info->store_mfn =
pfn_to_mfn(virt_to_phys((void *)page) >>
PAGE_SHIFT);
/* Next allocate a local port which xenstored can bind to */
alloc_unbound.dom = DOMID_SELF;
alloc_unbound.remote_dom = 0;
err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
&alloc_unbound);
if (err == -ENOSYS)
goto err;
BUG_ON(err);
xen_store_evtchn = xen_start_info->store_evtchn =
alloc_unbound.port;
#if defined(CONFIG_PROC_FS) && defined(CONFIG_XEN_PRIVILEGED_GUEST)
/* And finally publish the above info in /proc/xen */
xsd_kva_intf = create_xen_proc_entry("xsd_kva", 0600);
if (xsd_kva_intf) {
memcpy(&xsd_kva_fops, xsd_kva_intf->proc_fops,
sizeof(xsd_kva_fops));
xsd_kva_fops.mmap = xsd_kva_mmap;
xsd_kva_intf->proc_fops = &xsd_kva_fops;
xsd_kva_intf->read_proc = xsd_kva_read;
}
xsd_port_intf = create_xen_proc_entry("xsd_port", 0400);
if (xsd_port_intf)
xsd_port_intf->read_proc = xsd_port_read;
#endif
#else
/* dom0 not yet supported */
#endif
xen_store_interface = mfn_to_virt(xen_store_mfn);
} else {
static int __init pvh_load_kernel(struct domain *d, const module_t *image,
unsigned long image_headroom,
module_t *initrd, void *image_base,
char *cmdline, paddr_t *entry,
paddr_t *start_info_addr)
{
void *image_start = image_base + image_headroom;
unsigned long image_len = image->mod_end;
struct elf_binary elf;
struct elf_dom_parms parms;
paddr_t last_addr;
struct hvm_start_info start_info = { 0 };
struct hvm_modlist_entry mod = { 0 };
struct vcpu *v = d->vcpu[0];
int rc;
if ( (rc = bzimage_parse(image_base, &image_start, &image_len)) != 0 )
{
printk("Error trying to detect bz compressed kernel\n");
return rc;
}
if ( (rc = elf_init(&elf, image_start, image_len)) != 0 )
{
printk("Unable to init ELF\n");
return rc;
}
#ifdef VERBOSE
elf_set_verbose(&elf);
#endif
elf_parse_binary(&elf);
if ( (rc = elf_xen_parse(&elf, &parms)) != 0 )
{
printk("Unable to parse kernel for ELFNOTES\n");
return rc;
}
if ( parms.phys_entry == UNSET_ADDR32 )
{
printk("Unable to find XEN_ELFNOTE_PHYS32_ENTRY address\n");
return -EINVAL;
}
printk("OS: %s version: %s loader: %s bitness: %s\n", parms.guest_os,
parms.guest_ver, parms.loader,
elf_64bit(&elf) ? "64-bit" : "32-bit");
/* Copy the OS image and free temporary buffer. */
elf.dest_base = (void *)(parms.virt_kstart - parms.virt_base);
elf.dest_size = parms.virt_kend - parms.virt_kstart;
elf_set_vcpu(&elf, v);
rc = elf_load_binary(&elf);
if ( rc < 0 )
{
printk("Failed to load kernel: %d\n", rc);
printk("Xen dom0 kernel broken ELF: %s\n", elf_check_broken(&elf));
return rc;
}
last_addr = ROUNDUP(parms.virt_kend - parms.virt_base, PAGE_SIZE);
if ( initrd != NULL )
{
rc = hvm_copy_to_guest_phys(last_addr, mfn_to_virt(initrd->mod_start),
initrd->mod_end, v);
if ( rc )
{
printk("Unable to copy initrd to guest\n");
return rc;
}
mod.paddr = last_addr;
mod.size = initrd->mod_end;
last_addr += ROUNDUP(initrd->mod_end, PAGE_SIZE);
}
/* Free temporary buffers. */
discard_initial_images();
if ( cmdline != NULL )
{
rc = hvm_copy_to_guest_phys(last_addr, cmdline, strlen(cmdline) + 1, v);
if ( rc )
{
printk("Unable to copy guest command line\n");
return rc;
}
start_info.cmdline_paddr = last_addr;
/*
* Round up to 32/64 bits (depending on the guest kernel bitness) so
* the modlist/start_info is aligned.
*/
last_addr += ROUNDUP(strlen(cmdline) + 1, elf_64bit(&elf) ? 8 : 4);
}
if ( initrd != NULL )
{
rc = hvm_copy_to_guest_phys(last_addr, &mod, sizeof(mod), v);
if ( rc )
{
printk("Unable to copy guest modules\n");
return rc;
}
start_info.modlist_paddr = last_addr;
start_info.nr_modules = 1;
last_addr += sizeof(mod);
}
start_info.magic = XEN_HVM_START_MAGIC_VALUE;
start_info.flags = SIF_PRIVILEGED | SIF_INITDOMAIN;
rc = hvm_copy_to_guest_phys(last_addr, &start_info, sizeof(start_info), v);
if ( rc )
{
printk("Unable to copy start info to guest\n");
return rc;
}
*entry = parms.phys_entry;
*start_info_addr = last_addr;
return 0;
}
static void __init setup_mm(unsigned long dtb_paddr, size_t dtb_size)
{
paddr_t ram_start, ram_end, ram_size;
paddr_t contig_start, contig_end;
paddr_t s, e;
unsigned long ram_pages;
unsigned long heap_pages, xenheap_pages, domheap_pages;
unsigned long dtb_pages;
unsigned long boot_mfn_start, boot_mfn_end;
int i;
void *fdt;
if ( !early_info.mem.nr_banks )
early_panic("No memory bank");
/*
* We are going to accumulate two regions here.
*
* The first is the bounds of the initial memory region which is
* contiguous with the first bank. For simplicity the xenheap is
* always allocated from this region.
*
* The second is the complete bounds of the regions containing RAM
* (ie. from the lowest RAM address to the highest), which
* includes any holes.
*
* We also track the number of actual RAM pages (i.e. not counting
* the holes).
*/
ram_size = early_info.mem.bank[0].size;
contig_start = ram_start = early_info.mem.bank[0].start;
contig_end = ram_end = ram_start + ram_size;
for ( i = 1; i < early_info.mem.nr_banks; i++ )
{
paddr_t bank_start = early_info.mem.bank[i].start;
paddr_t bank_size = early_info.mem.bank[i].size;
paddr_t bank_end = bank_start + bank_size;
paddr_t new_ram_size = ram_size + bank_size;
paddr_t new_ram_start = min(ram_start,bank_start);
paddr_t new_ram_end = max(ram_end,bank_end);
/*
* If the new bank is contiguous with the initial contiguous
* region then incorporate it into the contiguous region.
*
* Otherwise we allow non-contigious regions so long as at
* least half of the total RAM region actually contains
* RAM. We actually fudge this slightly and require that
* adding the current bank does not cause us to violate this
* restriction.
*
* This restriction ensures that the frametable (which is not
* currently sparse) does not consume all available RAM.
*/
if ( bank_start == contig_end )
contig_end = bank_end;
else if ( bank_end == contig_start )
contig_start = bank_start;
else if ( 2 * new_ram_size < new_ram_end - new_ram_start )
/* Would create memory map which is too sparse, so stop here. */
break;
ram_size = new_ram_size;
ram_start = new_ram_start;
ram_end = new_ram_end;
}
if ( i != early_info.mem.nr_banks )
{
early_printk("WARNING: only using %d out of %d memory banks\n",
i, early_info.mem.nr_banks);
early_info.mem.nr_banks = i;
}
total_pages = ram_pages = ram_size >> PAGE_SHIFT;
/*
* Locate the xenheap using these constraints:
*
* - must be 32 MiB aligned
* - must not include Xen itself or the boot modules
* - must be at most 1/8 the total RAM in the system
* - must be at least 128M
*
* We try to allocate the largest xenheap possible within these
* constraints.
*/
heap_pages = ram_pages;
xenheap_pages = (heap_pages/8 + 0x1fffUL) & ~0x1fffUL;
xenheap_pages = max(xenheap_pages, 128UL<<(20-PAGE_SHIFT));
do
{
/* xenheap is always in the initial contiguous region */
e = consider_modules(contig_start, contig_end,
pfn_to_paddr(xenheap_pages),
32<<20, 0);
if ( e )
break;
xenheap_pages >>= 1;
} while ( xenheap_pages > 128<<(20-PAGE_SHIFT) );
if ( ! e )
early_panic("Not not enough space for xenheap");
domheap_pages = heap_pages - xenheap_pages;
early_printk("Xen heap: %"PRIpaddr"-%"PRIpaddr" (%lu pages)\n",
e - (pfn_to_paddr(xenheap_pages)), e,
xenheap_pages);
early_printk("Dom heap: %lu pages\n", domheap_pages);
setup_xenheap_mappings((e >> PAGE_SHIFT) - xenheap_pages, xenheap_pages);
/*
* Need a single mapped page for populating bootmem_region_list
* and enough mapped pages for copying the DTB.
*/
dtb_pages = (dtb_size + PAGE_SIZE-1) >> PAGE_SHIFT;
boot_mfn_start = xenheap_mfn_end - dtb_pages - 1;
boot_mfn_end = xenheap_mfn_end;
init_boot_pages(pfn_to_paddr(boot_mfn_start), pfn_to_paddr(boot_mfn_end));
/* Copy the DTB. */
fdt = mfn_to_virt(alloc_boot_pages(dtb_pages, 1));
copy_from_paddr(fdt, dtb_paddr, dtb_size, BUFFERABLE);
device_tree_flattened = fdt;
/* Add non-xenheap memory */
for ( i = 0; i < early_info.mem.nr_banks; i++ )
{
paddr_t bank_start = early_info.mem.bank[i].start;
paddr_t bank_end = bank_start + early_info.mem.bank[i].size;
s = bank_start;
while ( s < bank_end )
{
paddr_t n = bank_end;
e = next_module(s, &n);
if ( e == ~(paddr_t)0 )
{
e = n = ram_end;
}
/*
* Module in a RAM bank other than the one which we are
* not dealing with here.
*/
if ( e > bank_end )
e = bank_end;
/* Avoid the xenheap */
if ( s < pfn_to_paddr(xenheap_mfn_start+xenheap_pages)
&& pfn_to_paddr(xenheap_mfn_start) < e )
{
e = pfn_to_paddr(xenheap_mfn_start);
n = pfn_to_paddr(xenheap_mfn_start+xenheap_pages);
}
dt_unreserved_regions(s, e, init_boot_pages, 0);
s = n;
}
}
/* Frame table covers all of RAM region, including holes */
setup_frametable_mappings(ram_start, ram_end);
max_page = PFN_DOWN(ram_end);
/* Add xenheap memory that was not already added to the boot
allocator. */
init_xenheap_pages(pfn_to_paddr(xenheap_mfn_start),
pfn_to_paddr(boot_mfn_start));
end_boot_allocator();
}
static int __init xenbus_init(void)
{
int err = 0;
uint64_t v = 0;
xen_store_domain_type = XS_UNKNOWN;
if (!xen_domain())
return -ENODEV;
xenbus_ring_ops_init();
if (xen_pv_domain())
xen_store_domain_type = XS_PV;
if (xen_hvm_domain())
xen_store_domain_type = XS_HVM;
if (xen_hvm_domain() && xen_initial_domain())
xen_store_domain_type = XS_LOCAL;
if (xen_pv_domain() && !xen_start_info->store_evtchn)
xen_store_domain_type = XS_LOCAL;
if (xen_pv_domain() && xen_start_info->store_evtchn)
xenstored_ready = 1;
switch (xen_store_domain_type) {
case XS_LOCAL:
err = xenstored_local_init();
if (err)
goto out_error;
xen_store_interface = mfn_to_virt(xen_store_mfn);
break;
case XS_PV:
xen_store_evtchn = xen_start_info->store_evtchn;
xen_store_mfn = xen_start_info->store_mfn;
xen_store_interface = mfn_to_virt(xen_store_mfn);
break;
case XS_HVM:
err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
if (err)
goto out_error;
xen_store_evtchn = (int)v;
err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
if (err)
goto out_error;
xen_store_mfn = (unsigned long)v;
xen_store_interface =
xen_remap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
break;
default:
pr_warn("Xenstore state unknown\n");
break;
}
/* Initialize the interface to xenstore. */
err = xs_init();
if (err) {
pr_warn("Error initializing xenstore comms: %i\n", err);
goto out_error;
}
#ifdef CONFIG_XEN_COMPAT_XENFS
/*
* Create xenfs mountpoint in /proc for compatibility with
* utilities that expect to find "xenbus" under "/proc/xen".
*/
proc_mkdir("xen", NULL);
#endif
out_error:
return err;
}
static void __init setup_mm(unsigned long dtb_paddr, size_t dtb_size)
{
paddr_t ram_start, ram_end, ram_size;
paddr_t s, e;
unsigned long ram_pages;
unsigned long heap_pages, xenheap_pages, domheap_pages;
unsigned long dtb_pages;
unsigned long boot_mfn_start, boot_mfn_end;
int i;
void *fdt;
if ( !bootinfo.mem.nr_banks )
panic("No memory bank");
init_pdx();
ram_start = bootinfo.mem.bank[0].start;
ram_size = bootinfo.mem.bank[0].size;
ram_end = ram_start + ram_size;
for ( i = 1; i < bootinfo.mem.nr_banks; i++ )
{
paddr_t bank_start = bootinfo.mem.bank[i].start;
paddr_t bank_size = bootinfo.mem.bank[i].size;
paddr_t bank_end = bank_start + bank_size;
ram_size = ram_size + bank_size;
ram_start = min(ram_start,bank_start);
ram_end = max(ram_end,bank_end);
}
total_pages = ram_pages = ram_size >> PAGE_SHIFT;
/*
* If the user has not requested otherwise via the command line
* then locate the xenheap using these constraints:
*
* - must be 32 MiB aligned
* - must not include Xen itself or the boot modules
* - must be at most 1GB or 1/32 the total RAM in the system if less
* - must be at least 32M
*
* We try to allocate the largest xenheap possible within these
* constraints.
*/
heap_pages = ram_pages;
if ( opt_xenheap_megabytes )
xenheap_pages = opt_xenheap_megabytes << (20-PAGE_SHIFT);
else
{
xenheap_pages = (heap_pages/32 + 0x1fffUL) & ~0x1fffUL;
xenheap_pages = max(xenheap_pages, 32UL<<(20-PAGE_SHIFT));
xenheap_pages = min(xenheap_pages, 1UL<<(30-PAGE_SHIFT));
}
do
{
e = consider_modules(ram_start, ram_end,
pfn_to_paddr(xenheap_pages),
32<<20, 0);
if ( e )
break;
xenheap_pages >>= 1;
} while ( !opt_xenheap_megabytes && xenheap_pages > 32<<(20-PAGE_SHIFT) );
if ( ! e )
panic("Not not enough space for xenheap");
domheap_pages = heap_pages - xenheap_pages;
printk("Xen heap: %"PRIpaddr"-%"PRIpaddr" (%lu pages%s)\n",
e - (pfn_to_paddr(xenheap_pages)), e, xenheap_pages,
opt_xenheap_megabytes ? ", from command-line" : "");
printk("Dom heap: %lu pages\n", domheap_pages);
setup_xenheap_mappings((e >> PAGE_SHIFT) - xenheap_pages, xenheap_pages);
/*
* Need a single mapped page for populating bootmem_region_list
* and enough mapped pages for copying the DTB.
*/
dtb_pages = (dtb_size + PAGE_SIZE-1) >> PAGE_SHIFT;
boot_mfn_start = xenheap_mfn_end - dtb_pages - 1;
boot_mfn_end = xenheap_mfn_end;
init_boot_pages(pfn_to_paddr(boot_mfn_start), pfn_to_paddr(boot_mfn_end));
/* Copy the DTB. */
fdt = mfn_to_virt(alloc_boot_pages(dtb_pages, 1));
copy_from_paddr(fdt, dtb_paddr, dtb_size);
device_tree_flattened = fdt;
/* Add non-xenheap memory */
for ( i = 0; i < bootinfo.mem.nr_banks; i++ )
{
paddr_t bank_start = bootinfo.mem.bank[i].start;
paddr_t bank_end = bank_start + bootinfo.mem.bank[i].size;
s = bank_start;
while ( s < bank_end )
{
paddr_t n = bank_end;
e = next_module(s, &n);
if ( e == ~(paddr_t)0 )
{
e = n = ram_end;
}
/*
* Module in a RAM bank other than the one which we are
* not dealing with here.
*/
if ( e > bank_end )
e = bank_end;
/* Avoid the xenheap */
if ( s < pfn_to_paddr(xenheap_mfn_start+xenheap_pages)
&& pfn_to_paddr(xenheap_mfn_start) < e )
{
e = pfn_to_paddr(xenheap_mfn_start);
n = pfn_to_paddr(xenheap_mfn_start+xenheap_pages);
}
dt_unreserved_regions(s, e, init_boot_pages, 0);
s = n;
}
}
/* Frame table covers all of RAM region, including holes */
setup_frametable_mappings(ram_start, ram_end);
max_page = PFN_DOWN(ram_end);
/* Add xenheap memory that was not already added to the boot
allocator. */
init_xenheap_pages(pfn_to_paddr(xenheap_mfn_start),
pfn_to_paddr(boot_mfn_start));
}
/* Add xenheap memory that was not already added to the boot
allocator. */
init_xenheap_pages(pfn_to_paddr(xenheap_mfn_start),
pfn_to_paddr(boot_mfn_start));
}
#else /* CONFIG_ARM_64 */
static void __init setup_mm(unsigned long dtb_paddr, size_t dtb_size)
{
paddr_t ram_start = ~0;
paddr_t ram_end = 0;
paddr_t ram_size = 0;
int bank;
unsigned long dtb_pages;
void *fdt;
init_pdx();
total_pages = 0;
for ( bank = 0 ; bank < bootinfo.mem.nr_banks; bank++ )
{
paddr_t bank_start = bootinfo.mem.bank[bank].start;
paddr_t bank_size = bootinfo.mem.bank[bank].size;
paddr_t bank_end = bank_start + bank_size;
paddr_t s, e;
ram_size = ram_size + bank_size;
ram_start = min(ram_start,bank_start);
ram_end = max(ram_end,bank_end);
setup_xenheap_mappings(bank_start>>PAGE_SHIFT, bank_size>>PAGE_SHIFT);
s = bank_start;
while ( s < bank_end )
{
paddr_t n = bank_end;
e = next_module(s, &n);
if ( e == ~(paddr_t)0 )
{
e = n = bank_end;
}
if ( e > bank_end )
e = bank_end;
xenheap_mfn_end = e;
dt_unreserved_regions(s, e, init_boot_pages, 0);
s = n;
}
}
total_pages += ram_size >> PAGE_SHIFT;
xenheap_virt_end = XENHEAP_VIRT_START + ram_end - ram_start;
xenheap_mfn_start = ram_start >> PAGE_SHIFT;
xenheap_mfn_end = ram_end >> PAGE_SHIFT;
/*
* Need enough mapped pages for copying the DTB.
*/
dtb_pages = (dtb_size + PAGE_SIZE-1) >> PAGE_SHIFT;
/* Copy the DTB. */
fdt = mfn_to_virt(alloc_boot_pages(dtb_pages, 1));
copy_from_paddr(fdt, dtb_paddr, dtb_size);
device_tree_flattened = fdt;
setup_frametable_mappings(ram_start, ram_end);
max_page = PFN_DOWN(ram_end);
}
static int __init xenbus_probe_init(void)
{
int err = 0;
DPRINTK("");
err = -ENODEV;
if (!xen_domain())
goto out_error;
/* Register ourselves with the kernel bus subsystem */
err = bus_register(&xenbus_frontend.bus);
if (err)
goto out_error;
err = xenbus_backend_bus_register();
if (err)
goto out_unreg_front;
/*
* Domain0 doesn't have a store_evtchn or store_mfn yet.
*/
if (xen_initial_domain()) {
/* dom0 not yet supported */
} else {
xenstored_ready = 1;
xen_store_evtchn = xen_start_info->store_evtchn;
xen_store_mfn = xen_start_info->store_mfn;
}
xen_store_interface = mfn_to_virt(xen_store_mfn);
/* Initialize the interface to xenstore. */
err = xs_init();
if (err) {
printk(KERN_WARNING
"XENBUS: Error initializing xenstore comms: %i\n", err);
goto out_unreg_back;
}
if (!xen_initial_domain())
xenbus_probe(NULL);
#ifdef CONFIG_XEN_COMPAT_XENFS
/*
* Create xenfs mountpoint in /proc for compatibility with
* utilities that expect to find "xenbus" under "/proc/xen".
*/
proc_mkdir("xen", NULL);
#endif
return 0;
out_unreg_back:
xenbus_backend_bus_unregister();
out_unreg_front:
bus_unregister(&xenbus_frontend.bus);
out_error:
return err;
}
/* Add xenheap memory that was not already added to the boot
allocator. */
init_xenheap_pages(pfn_to_paddr(xenheap_mfn_start),
pfn_to_paddr(boot_mfn_start));
end_boot_allocator();
}
#else /* CONFIG_ARM_64 */
static void __init setup_mm(unsigned long dtb_paddr, size_t dtb_size)
{
paddr_t ram_start = ~0;
paddr_t ram_end = 0;
paddr_t ram_size = 0;
int bank;
unsigned long dtb_pages;
void *fdt;
total_pages = 0;
for ( bank = 0 ; bank < early_info.mem.nr_banks; bank++ )
{
paddr_t bank_start = early_info.mem.bank[bank].start;
paddr_t bank_size = early_info.mem.bank[bank].size;
paddr_t bank_end = bank_start + bank_size;
paddr_t s, e;
paddr_t new_ram_size = ram_size + bank_size;
paddr_t new_ram_start = min(ram_start,bank_start);
paddr_t new_ram_end = max(ram_end,bank_end);
/*
* We allow non-contigious regions so long as at least half of
* the total RAM region actually contains RAM. We actually
* fudge this slightly and require that adding the current
* bank does not cause us to violate this restriction.
*
* This restriction ensures that the frametable (which is not
* currently sparse) does not consume all available RAM.
*/
if ( bank > 0 && 2 * new_ram_size < new_ram_end - new_ram_start )
/* Would create memory map which is too sparse, so stop here. */
break;
ram_start = new_ram_start;
ram_end = new_ram_end;
ram_size = new_ram_size;
setup_xenheap_mappings(bank_start>>PAGE_SHIFT, bank_size>>PAGE_SHIFT);
s = bank_start;
while ( s < bank_end )
{
paddr_t n = bank_end;
e = next_module(s, &n);
if ( e == ~(paddr_t)0 )
{
e = n = bank_end;
}
if ( e > bank_end )
e = bank_end;
xenheap_mfn_end = e;
dt_unreserved_regions(s, e, init_boot_pages, 0);
s = n;
}
}
if ( bank != early_info.mem.nr_banks )
{
early_printk("WARNING: only using %d out of %d memory banks\n",
bank, early_info.mem.nr_banks);
early_info.mem.nr_banks = bank;
}
total_pages += ram_size >> PAGE_SHIFT;
xenheap_virt_end = XENHEAP_VIRT_START + ram_end - ram_start;
xenheap_mfn_start = ram_start >> PAGE_SHIFT;
xenheap_mfn_end = ram_end >> PAGE_SHIFT;
xenheap_max_mfn(xenheap_mfn_end);
/*
* Need enough mapped pages for copying the DTB.
*/
dtb_pages = (dtb_size + PAGE_SIZE-1) >> PAGE_SHIFT;
/* Copy the DTB. */
fdt = mfn_to_virt(alloc_boot_pages(dtb_pages, 1));
copy_from_paddr(fdt, dtb_paddr, dtb_size, BUFFERABLE);
device_tree_flattened = fdt;
setup_frametable_mappings(ram_start, ram_end);
max_page = PFN_DOWN(ram_end);
end_boot_allocator();
}
static __cpuinit int
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.ds = __USER_DS;
ctxt->user_regs.es = __USER_DS;
ctxt->user_regs.ss = __KERNEL_DS;
#ifdef CONFIG_X86_32
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
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->user_regs.cs = __KERNEL_CS;
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
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;
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;
}
static inline struct xencons_interface *xencons_interface(void)
{
return mfn_to_virt(xen_start_info->console.domU.mfn);
}
static int
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
struct vcpu_guest_context *ctxt;
struct desc_struct *gdt;
unsigned long gdt_mfn;
/* used to tell cpu_init() that it can proceed with initialization */
cpumask_set_cpu(cpu, cpu_callout_mask);
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_rw(cpu);
#ifdef CONFIG_X86_32
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#endif
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
/*
* Bring up the CPU in cpu_bringup_and_idle() with the stack
* pointing just below where pt_regs would be if it were a normal
* kernel entry.
*/
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
ctxt->user_regs.ds = __USER_DS;
ctxt->user_regs.es = __USER_DS;
ctxt->user_regs.ss = __KERNEL_DS;
ctxt->user_regs.cs = __KERNEL_CS;
ctxt->user_regs.esp = (unsigned long)task_pt_regs(idle);
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;
/*
* Set SS:SP that Xen will use when entering guest kernel mode
* from guest user mode. Subsequent calls to load_sp0() can
* change this value.
*/
ctxt->kernel_ss = __KERNEL_DS;
ctxt->kernel_sp = task_top_of_stack(idle);
#ifdef CONFIG_X86_32
ctxt->event_callback_cs = __KERNEL_CS;
ctxt->failsafe_callback_cs = __KERNEL_CS;
#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->event_callback_eip =
(unsigned long)xen_hypervisor_callback;
ctxt->failsafe_callback_eip =
(unsigned long)xen_failsafe_callback;
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
BUG();
kfree(ctxt);
return 0;
}
