int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
unsigned long max_nr_gframes,
void **__shared)
{
void *shared = *__shared;
unsigned long addr;
unsigned long i;
if (shared == NULL)
*__shared = shared = gnttab_shared_vm_area.area->addr;
addr = (unsigned long)shared;
for (i = 0; i < nr_gframes; i++) {
set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i],
mfn_pte(frames[i], PAGE_KERNEL));
addr += PAGE_SIZE;
}
return 0;
}
static unsigned long __init xen_do_chunk(unsigned long start,
unsigned long end, bool release)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
unsigned long len = 0;
unsigned long pfn;
int ret;
for (pfn = start; pfn < end; pfn++) {
unsigned long frame;
unsigned long mfn = pfn_to_mfn(pfn);
if (release) {
/* Make sure pfn exists to start with */
if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
continue;
frame = mfn;
} else {
if (mfn != INVALID_P2M_ENTRY)
continue;
frame = pfn;
}
set_xen_guest_handle(reservation.extent_start, &frame);
reservation.nr_extents = 1;
ret = HYPERVISOR_memory_op(release ? XENMEM_decrease_reservation : XENMEM_populate_physmap,
&reservation);
WARN(ret != 1, "Failed to %s pfn %lx err=%d\n",
release ? "release" : "populate", pfn, ret);
if (ret == 1) {
if (!early_set_phys_to_machine(pfn, release ? INVALID_P2M_ENTRY : frame)) {
if (release)
break;
set_xen_guest_handle(reservation.extent_start, &frame);
reservation.nr_extents = 1;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
&reservation);
break;
}
len++;
} else
break;
}
if (len)
printk(KERN_INFO "%s %lx-%lx pfn range: %lu pages %s\n",
release ? "Freeing" : "Populating",
start, end, len,
release ? "freed" : "added");
return len;
}
static unsigned long __init xen_release_chunk(unsigned long start,
unsigned long end)
{
return xen_do_chunk(start, end, true);
}
static unsigned long __init xen_populate_chunk(
const struct e820entry *list, size_t map_size,
unsigned long max_pfn, unsigned long *last_pfn,
unsigned long credits_left)
{
const struct e820entry *entry;
unsigned int i;
unsigned long done = 0;
unsigned long dest_pfn;
for (i = 0, entry = list; i < map_size; i++, entry++) {
unsigned long s_pfn;
unsigned long e_pfn;
unsigned long pfns;
long capacity;
if (credits_left <= 0)
break;
if (entry->type != E820_RAM)
continue;
e_pfn = PFN_DOWN(entry->addr + entry->size);
/* We only care about E820 after the xen_start_info->nr_pages */
if (e_pfn <= max_pfn)
continue;
s_pfn = PFN_UP(entry->addr);
/* If the E820 falls within the nr_pages, we want to start
* at the nr_pages PFN.
* If that would mean going past the E820 entry, skip it
*/
if (s_pfn <= max_pfn) {
capacity = e_pfn - max_pfn;
dest_pfn = max_pfn;
} else {
capacity = e_pfn - s_pfn;
dest_pfn = s_pfn;
}
if (credits_left < capacity)
capacity = credits_left;
pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
done += pfns;
*last_pfn = (dest_pfn + pfns);
if (pfns < capacity)
break;
credits_left -= pfns;
}
return done;
}
static void __init xen_set_identity_and_release_chunk(
unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
unsigned long *released, unsigned long *identity)
{
unsigned long pfn;
/*
* If the PFNs are currently mapped, the VA mapping also needs
* to be updated to be 1:1.
*/
for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
(void)HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
mfn_pte(pfn, PAGE_KERNEL_IO), 0);
if (start_pfn < nr_pages)
*released += xen_release_chunk(
start_pfn, min(end_pfn, nr_pages));
*identity += set_phys_range_identity(start_pfn, end_pfn);
}
static int increase_reservation(unsigned long nr_pages)
{
unsigned long pfn, i, flags;
struct page *page;
long rc;
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
if (nr_pages > ARRAY_SIZE(frame_list))
nr_pages = ARRAY_SIZE(frame_list);
spin_lock_irqsave(&xen_reservation_lock, flags);
page = balloon_first_page();
for (i = 0; i < nr_pages; i++) {
BUG_ON(page == NULL);
frame_list[i] = page_to_pfn(page);
page = balloon_next_page(page);
}
set_xen_guest_handle(reservation.extent_start, frame_list);
reservation.nr_extents = nr_pages;
rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
if (rc < 0)
goto out;
for (i = 0; i < rc; i++) {
page = balloon_retrieve();
BUG_ON(page == NULL);
pfn = page_to_pfn(page);
BUG_ON(!xen_feature(XENFEAT_auto_translated_physmap) &&
phys_to_machine_mapping_valid(pfn));
set_phys_to_machine(pfn, frame_list[i]);
/* Link back into the page tables if not highmem. */
if (pfn < max_low_pfn) {
int ret;
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
mfn_pte(frame_list[i], PAGE_KERNEL),
0);
BUG_ON(ret);
}
/* Relinquish the page back to the allocator. */
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
}
balloon_stats.current_pages += rc;
out:
spin_unlock_irqrestore(&xen_reservation_lock, flags);
return rc < 0 ? rc : rc != nr_pages;
}
static int decrease_reservation(unsigned long nr_pages)
{
unsigned long pfn, i, flags;
struct page *page;
int need_sleep = 0;
int ret;
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
if (nr_pages > ARRAY_SIZE(frame_list))
nr_pages = ARRAY_SIZE(frame_list);
for (i = 0; i < nr_pages; i++) {
if ((page = alloc_page(GFP_BALLOON)) == NULL) {
nr_pages = i;
need_sleep = 1;
break;
}
pfn = page_to_pfn(page);
frame_list[i] = pfn_to_mfn(pfn);
scrub_page(page);
if (!PageHighMem(page)) {
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
__pte_ma(0), 0);
BUG_ON(ret);
}
}
/* Ensure that ballooned highmem pages don't have kmaps. */
kmap_flush_unused();
flush_tlb_all();
spin_lock_irqsave(&xen_reservation_lock, flags);
/* No more mappings: invalidate P2M and add to balloon. */
for (i = 0; i < nr_pages; i++) {
pfn = mfn_to_pfn(frame_list[i]);
set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
balloon_append(pfn_to_page(pfn));
}
set_xen_guest_handle(reservation.extent_start, frame_list);
reservation.nr_extents = nr_pages;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
BUG_ON(ret != nr_pages);
balloon_stats.current_pages -= nr_pages;
spin_unlock_irqrestore(&xen_reservation_lock, flags);
return need_sleep;
}
/*
* We avoid multiple worker processes conflicting via the balloon mutex.
* We may of course race updates of the target counts (which are protected
* by the balloon lock), or with changes to the Xen hard limit, but we will
* recover from these in time.
*/
static void balloon_process(struct work_struct *work)
{
int need_sleep = 0;
long credit;
mutex_lock(&balloon_mutex);
do {
credit = current_target() - balloon_stats.current_pages;
if (credit > 0)
need_sleep = (increase_reservation(credit) != 0);
if (credit < 0)
need_sleep = (decrease_reservation(-credit) != 0);
#ifndef CONFIG_PREEMPT
if (need_resched())
schedule();
#endif
} while ((credit != 0) && !need_sleep);
/* Schedule more work if there is some still to be done. */
if (current_target() != balloon_stats.current_pages)
mod_timer(&balloon_timer, jiffies + HZ);
mutex_unlock(&balloon_mutex);
}
/*
* Helper function to update the p2m and m2p tables and kernel mapping.
*/
static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn)
{
struct mmu_update update = {
.ptr = ((uint64_t)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE,
.val = pfn
};
/* Update p2m */
if (!set_phys_to_machine(pfn, mfn)) {
WARN(1, "Failed to set p2m mapping for pfn=%ld mfn=%ld\n",
pfn, mfn);
BUG();
}
/* Update m2p */
if (HYPERVISOR_mmu_update(&update, 1, NULL, DOMID_SELF) < 0) {
WARN(1, "Failed to set m2p mapping for mfn=%ld pfn=%ld\n",
mfn, pfn);
BUG();
}
/* Update kernel mapping, but not for highmem. */
if (pfn >= PFN_UP(__pa(high_memory - 1)))
return;
if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT),
mfn_pte(mfn, PAGE_KERNEL), 0)) {
WARN(1, "Failed to update kernel mapping for mfn=%ld pfn=%ld\n",
mfn, pfn);
BUG();
}
}
/*
* This function updates the p2m and m2p tables with an identity map from
* start_pfn to start_pfn+size and prepares remapping the underlying RAM of the
* original allocation at remap_pfn. The information needed for remapping is
* saved in the memory itself to avoid the need for allocating buffers. The
* complete remap information is contained in a list of MFNs each containing
* up to REMAP_SIZE MFNs and the start target PFN for doing the remap.
* This enables us to preserve the original mfn sequence while doing the
* remapping at a time when the memory management is capable of allocating
* virtual and physical memory in arbitrary amounts, see 'xen_remap_memory' and
* its callers.
*/
static void __init xen_do_set_identity_and_remap_chunk(
unsigned long start_pfn, unsigned long size, unsigned long remap_pfn)
{
unsigned long buf = (unsigned long)&xen_remap_buf;
unsigned long mfn_save, mfn;
unsigned long ident_pfn_iter, remap_pfn_iter;
unsigned long ident_end_pfn = start_pfn + size;
unsigned long left = size;
unsigned int i, chunk;
WARN_ON(size == 0);
BUG_ON(xen_feature(XENFEAT_auto_translated_physmap));
mfn_save = virt_to_mfn(buf);
for (ident_pfn_iter = start_pfn, remap_pfn_iter = remap_pfn;
ident_pfn_iter < ident_end_pfn;
ident_pfn_iter += REMAP_SIZE, remap_pfn_iter += REMAP_SIZE) {
chunk = (left < REMAP_SIZE) ? left : REMAP_SIZE;
/* Map first pfn to xen_remap_buf */
mfn = pfn_to_mfn(ident_pfn_iter);
set_pte_mfn(buf, mfn, PAGE_KERNEL);
/* Save mapping information in page */
xen_remap_buf.next_area_mfn = xen_remap_mfn;
xen_remap_buf.target_pfn = remap_pfn_iter;
xen_remap_buf.size = chunk;
for (i = 0; i < chunk; i++)
xen_remap_buf.mfns[i] = pfn_to_mfn(ident_pfn_iter + i);
/* Put remap buf into list. */
xen_remap_mfn = mfn;
/* Set identity map */
set_phys_range_identity(ident_pfn_iter, ident_pfn_iter + chunk);
left -= chunk;
}
/* Restore old xen_remap_buf mapping */
set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
}
/*
* Associate a virtual page frame with a given physical page frame
* and protection flags for that frame.
*/
void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
{
set_pte_vaddr(vaddr, mfn_pte(mfn, flags));
}
static unsigned long __init xen_do_chunk(unsigned long start,
unsigned long end, bool release)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
unsigned long len = 0;
int xlated_phys = xen_feature(XENFEAT_auto_translated_physmap);
unsigned long pfn;
int ret;
for (pfn = start; pfn < end; pfn++) {
unsigned long frame;
unsigned long mfn = pfn_to_mfn(pfn);
if (release) {
/* Make sure pfn exists to start with */
if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
continue;
frame = mfn;
} else {
if (!xlated_phys && mfn != INVALID_P2M_ENTRY)
continue;
frame = pfn;
}
set_xen_guest_handle(reservation.extent_start, &frame);
reservation.nr_extents = 1;
ret = HYPERVISOR_memory_op(release ? XENMEM_decrease_reservation : XENMEM_populate_physmap,
&reservation);
WARN(ret != 1, "Failed to %s pfn %lx err=%d\n",
release ? "release" : "populate", pfn, ret);
if (ret == 1) {
if (!early_set_phys_to_machine(pfn, release ? INVALID_P2M_ENTRY : frame)) {
if (release)
break;
set_xen_guest_handle(reservation.extent_start, &frame);
reservation.nr_extents = 1;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
&reservation);
break;
}
len++;
} else
break;
}
if (len)
printk(KERN_INFO "%s %lx-%lx pfn range: %lu pages %s\n",
release ? "Freeing" : "Populating",
start, end, len,
release ? "freed" : "added");
return len;
}
static unsigned long __init xen_release_chunk(unsigned long start,
unsigned long end)
{
/*
* Xen already ballooned out the E820 non RAM regions for us
* and set them up properly in EPT.
*/
if (xen_feature(XENFEAT_auto_translated_physmap))
return end - start;
return xen_do_chunk(start, end, true);
}
static unsigned long __init xen_populate_chunk(
const struct e820entry *list, size_t map_size,
unsigned long max_pfn, unsigned long *last_pfn,
unsigned long credits_left)
{
const struct e820entry *entry;
unsigned int i;
unsigned long done = 0;
unsigned long dest_pfn;
for (i = 0, entry = list; i < map_size; i++, entry++) {
unsigned long s_pfn;
unsigned long e_pfn;
unsigned long pfns;
long capacity;
if (credits_left <= 0)
break;
if (entry->type != E820_RAM)
continue;
e_pfn = PFN_DOWN(entry->addr + entry->size);
/* We only care about E820 after the xen_start_info->nr_pages */
if (e_pfn <= max_pfn)
continue;
s_pfn = PFN_UP(entry->addr);
/* If the E820 falls within the nr_pages, we want to start
* at the nr_pages PFN.
* If that would mean going past the E820 entry, skip it
*/
if (s_pfn <= max_pfn) {
capacity = e_pfn - max_pfn;
dest_pfn = max_pfn;
} else {
capacity = e_pfn - s_pfn;
dest_pfn = s_pfn;
}
if (credits_left < capacity)
capacity = credits_left;
pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
done += pfns;
*last_pfn = (dest_pfn + pfns);
if (pfns < capacity)
break;
credits_left -= pfns;
}
return done;
}
static void __init xen_set_identity_and_release_chunk(
unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
unsigned long *released, unsigned long *identity)
{
unsigned long pfn;
/*
* If the PFNs are currently mapped, clear the mappings
* (except for the ISA region which must be 1:1 mapped) to
* release the refcounts (in Xen) on the original frames.
*/
/*
* PVH E820 matches the hypervisor's P2M which means we need to
* account for the proper values of *release and *identity.
*/
for (pfn = start_pfn; !xen_feature(XENFEAT_auto_translated_physmap) &&
pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
pte_t pte = __pte_ma(0);
if (pfn < PFN_UP(ISA_END_ADDRESS))
pte = mfn_pte(pfn, PAGE_KERNEL_IO);
(void)HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT), pte, 0);
}
if (start_pfn < nr_pages)
*released += xen_release_chunk(
start_pfn, min(end_pfn, nr_pages));
*identity += set_phys_range_identity(start_pfn, end_pfn);
}