bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
if (!alloc_p2m(pfn))
return false;
return __set_phys_to_machine(pfn, mfn);
}
return true;
}
void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
return;
}
if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
alloc_p2m(pfn);
if (!__set_phys_to_machine(pfn, mfn))
BUG();
}
}
bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
if (!early_alloc_p2m(pfn))
return false;
if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
return false;
if (!__set_phys_to_machine(pfn, mfn))
return false;
}
return true;
}
static void __init xen_add_extra_mem(u64 start, u64 size)
{
unsigned long pfn;
int i;
for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
/* Add new region. */
if (xen_extra_mem[i].size == 0) {
xen_extra_mem[i].start = start;
xen_extra_mem[i].size = size;
break;
}
/* Append to existing region. */
if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) {
xen_extra_mem[i].size += size;
break;
}
}
if (i == XEN_EXTRA_MEM_MAX_REGIONS)
printk(KERN_WARNING "Warning: not enough extra memory regions\n");
memblock_reserve(start, size);
xen_max_p2m_pfn = PFN_DOWN(start + size);
for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
unsigned long mfn = pfn_to_mfn(pfn);
if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
continue;
WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
pfn, mfn);
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
}
static void __init xen_add_extra_mem(u64 start, u64 size)
{
unsigned long pfn;
int i;
for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
/* */
if (xen_extra_mem[i].size == 0) {
xen_extra_mem[i].start = start;
xen_extra_mem[i].size = size;
break;
}
/* */
if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) {
xen_extra_mem[i].size += size;
break;
}
}
if (i == XEN_EXTRA_MEM_MAX_REGIONS)
printk(KERN_WARNING "Warning: not enough extra memory regions\n");
memblock_reserve(start, size);
xen_max_p2m_pfn = PFN_DOWN(start + size);
for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
unsigned long __init set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e)
{
unsigned long pfn;
if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
return 0;
if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
return pfn_e - pfn_s;
if (pfn_s > pfn_e)
return 0;
for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
{
WARN_ON(!early_alloc_p2m(pfn));
}
early_alloc_p2m_middle(pfn_s, true);
early_alloc_p2m_middle(pfn_e, true);
for (pfn = pfn_s; pfn < pfn_e; pfn++)
if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
break;
if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
"Identity mapping failed. We are %ld short of 1-1 mappings!\n",
(pfn_e - pfn_s) - (pfn - pfn_s)))
printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn);
return pfn - pfn_s;
}
unsigned long __init set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e)
{
unsigned long pfn;
if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
return 0;
if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
return pfn_e - pfn_s;
if (pfn_s > pfn_e)
return 0;
for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
{
unsigned topidx = p2m_top_index(pfn);
unsigned long *mid_mfn_p;
unsigned long **mid;
mid = p2m_top[topidx];
mid_mfn_p = p2m_top_mfn_p[topidx];
if (mid == p2m_mid_missing) {
mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_init(mid);
p2m_top[topidx] = mid;
BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
}
if (mid_mfn_p == p2m_mid_missing_mfn) {
mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_mfn_init(mid_mfn_p);
p2m_top_mfn_p[topidx] = mid_mfn_p;
p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
}
}
__early_alloc_p2m(pfn_s);
__early_alloc_p2m(pfn_e);
for (pfn = pfn_s; pfn < pfn_e; pfn++)
if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
break;
if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
"Identity mapping failed. We are %ld short of 1-1 mappings!\n",
(pfn_e - pfn_s) - (pfn - pfn_s)))
printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn);
return pfn - pfn_s;
}
static int __init xen_free_mfn(unsigned long mfn)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
set_xen_guest_handle(reservation.extent_start, &mfn);
reservation.nr_extents = 1;
return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
}
/*
* This releases a chunk of memory and then does the identity map. It's used
* as a fallback if the remapping fails.
*/
static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
unsigned long end_pfn, unsigned long nr_pages)
{
unsigned long pfn, end;
int ret;
WARN_ON(start_pfn > end_pfn);
/* Release pages first. */
end = min(end_pfn, nr_pages);
for (pfn = start_pfn; pfn < end; pfn++) {
unsigned long mfn = pfn_to_mfn(pfn);
/* Make sure pfn exists to start with */
if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
continue;
ret = xen_free_mfn(mfn);
WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
if (ret == 1) {
xen_released_pages++;
if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY))
break;
} else
break;
}
set_phys_range_identity(start_pfn, end_pfn);
}
static void __init xen_add_extra_mem(unsigned long pages)
{
unsigned long pfn;
u64 size = (u64)pages * PAGE_SIZE;
u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
if (!pages)
return;
e820_add_region(extra_start, size, E820_RAM);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
memblock_reserve(extra_start, size);
xen_extra_mem_size += size;
xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++)
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
phys_addr_t end_addr)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
unsigned long start, end;
unsigned long len = 0;
unsigned long pfn;
int ret;
start = PFN_UP(start_addr);
end = PFN_DOWN(end_addr);
if (end <= start)
return 0;
printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ",
start, end);
for(pfn = start; pfn < end; pfn++) {
unsigned long mfn = pfn_to_mfn(pfn);
/* Make sure pfn exists to start with */
if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
continue;
set_xen_guest_handle(reservation.extent_start, &mfn);
reservation.nr_extents = 1;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
&reservation);
WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
start, end, ret);
if (ret == 1) {
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
len++;
}
}
printk(KERN_CONT "%ld pages freed\n", len);
return len;
}
static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
const struct e820map *e820)
{
phys_addr_t max_addr = PFN_PHYS(max_pfn);
phys_addr_t last_end = ISA_END_ADDRESS;
unsigned long released = 0;
int i;
/* Free any unused memory above the low 1Mbyte. */
for (i = 0; i < e820->nr_map && last_end < max_addr; i++) {
phys_addr_t end = e820->map[i].addr;
end = min(max_addr, end);
if (last_end < end)
released += xen_release_chunk(last_end, end);
last_end = max(last_end, e820->map[i].addr + e820->map[i].size);
}
if (last_end < max_addr)
released += xen_release_chunk(last_end, max_addr);
printk(KERN_INFO "released %ld pages of unused memory\n", released);
return released;
}
static unsigned long __init xen_release_chunk(unsigned long start,
unsigned long end)
{
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 mfn = pfn_to_mfn(pfn);
/* Make sure pfn exists to start with */
if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
continue;
set_xen_guest_handle(reservation.extent_start, &mfn);
reservation.nr_extents = 1;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
&reservation);
WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
if (ret == 1) {
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
len++;
}
}
printk(KERN_INFO "Freeing %lx-%lx pfn range: %lu pages freed\n",
start, end, len);
return len;
}
static unsigned long __init xen_set_identity_and_release(
const struct e820entry *list, size_t map_size, unsigned long nr_pages)
{
phys_addr_t start = 0;
unsigned long released = 0;
unsigned long identity = 0;
const struct e820entry *entry;
int i;
/*
* Combine non-RAM regions and gaps until a RAM region (or the
* end of the map) is reached, then set the 1:1 map and
* release the pages (if available) in those non-RAM regions.
*
* The combined non-RAM regions are rounded to a whole number
* of pages so any partial pages are accessible via the 1:1
* mapping. This is needed for some BIOSes that put (for
* example) the DMI tables in a reserved region that begins on
* a non-page boundary.
*/
for (i = 0, entry = list; i < map_size; i++, entry++) {
phys_addr_t end = entry->addr + entry->size;
if (entry->type == E820_RAM || i == map_size - 1) {
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
if (entry->type == E820_RAM)
end_pfn = PFN_UP(entry->addr);
if (start_pfn < end_pfn) {
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);
}
start = end;
}
}
printk(KERN_INFO "Released %lu pages of unused memory\n", released);
printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
return released;
}
static unsigned long __init xen_release_chunk(unsigned long start,
unsigned long end)
{
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 mfn = pfn_to_mfn(pfn);
/* */
if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
continue;
set_xen_guest_handle(reservation.extent_start, &mfn);
reservation.nr_extents = 1;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
&reservation);
WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
if (ret == 1) {
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
len++;
}
}
printk(KERN_INFO "Freeing %lx-%lx pfn range: %lu pages freed\n",
start, end, len);
return len;
}
static unsigned long __init xen_set_identity_and_release(
const struct e820entry *list, size_t map_size, unsigned long nr_pages)
{
phys_addr_t start = 0;
unsigned long released = 0;
unsigned long identity = 0;
const struct e820entry *entry;
int i;
/*
*/
for (i = 0, entry = list; i < map_size; i++, entry++) {
phys_addr_t end = entry->addr + entry->size;
if (entry->type == E820_RAM || i == map_size - 1) {
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
if (entry->type == E820_RAM)
end_pfn = PFN_UP(entry->addr);
if (start_pfn < end_pfn) {
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);
}
start = end;
}
}
printk(KERN_INFO "Released %lu pages of unused memory\n", released);
printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
return released;
}
static int increase_reservation(unsigned long nr_pages)
{
unsigned long pfn, i;
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);
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 (!PageHighMem(page)) {
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:
return rc < 0 ? rc : rc != nr_pages;
}
static int decrease_reservation(unsigned long nr_pages)
{
unsigned long pfn, i;
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();
/* 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;
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);
}
