/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
char * __init xen_memory_setup(void)
{
static struct e820entry map[E820MAX] __initdata;
static struct e820entry map_raw[E820MAX] __initdata;
unsigned long max_pfn = xen_start_info->nr_pages;
unsigned long long mem_end;
int rc;
struct xen_memory_map memmap;
unsigned long extra_pages = 0;
unsigned long extra_limit;
unsigned long identity_pages = 0;
int i;
int op;
max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
mem_end = PFN_PHYS(max_pfn);
memmap.nr_entries = E820MAX;
set_xen_guest_handle(memmap.buffer, map);
op = xen_initial_domain() ?
XENMEM_machine_memory_map :
XENMEM_memory_map;
rc = HYPERVISOR_memory_op(op, &memmap);
if (rc == -ENOSYS) {
BUG_ON(xen_initial_domain());
memmap.nr_entries = 1;
map[0].addr = 0ULL;
map[0].size = mem_end;
/* 8MB slack (to balance backend allocations). */
map[0].size += 8ULL << 20;
map[0].type = E820_RAM;
rc = 0;
}
BUG_ON(rc);
memcpy(map_raw, map, sizeof(map));
e820.nr_map = 0;
xen_extra_mem_start = mem_end;
for (i = 0; i < memmap.nr_entries; i++) {
unsigned long long end;
/* Guard against non-page aligned E820 entries. */
if (map[i].type == E820_RAM)
map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE;
end = map[i].addr + map[i].size;
if (map[i].type == E820_RAM && end > mem_end) {
/* RAM off the end - may be partially included */
u64 delta = min(map[i].size, end - mem_end);
map[i].size -= delta;
end -= delta;
extra_pages += PFN_DOWN(delta);
/*
* Set RAM below 4GB that is not for us to be unusable.
* This prevents "System RAM" address space from being
* used as potential resource for I/O address (happens
* when 'allocate_resource' is called).
*/
if (delta &&
(xen_initial_domain() && end < 0x100000000ULL))
e820_add_region(end, delta, E820_UNUSABLE);
}
if (map[i].size > 0 && end > xen_extra_mem_start)
xen_extra_mem_start = end;
/* Add region if any remains */
if (map[i].size > 0)
e820_add_region(map[i].addr, map[i].size, map[i].type);
}
/* Align the balloon area so that max_low_pfn does not get set
* to be at the _end_ of the PCI gap at the far end (fee01000).
* Note that xen_extra_mem_start gets set in the loop above to be
* past the last E820 region. */
if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32)))
xen_extra_mem_start = (1ULL<<32);
/*
* In domU, the ISA region is normal, usable memory, but we
* reserve ISA memory anyway because too many things poke
* about in there.
*
* In Dom0, the host E820 information can leave gaps in the
* ISA range, which would cause us to release those pages. To
* avoid this, we unconditionally reserve them here.
*/
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
/*
* Reserve Xen bits:
* - mfn_list
* - xen_start_info
* See comment above "struct start_info" in <xen/interface/xen.h>
*/
memblock_reserve(__pa(xen_start_info->mfn_list),
xen_start_info->pt_base - xen_start_info->mfn_list);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
extra_limit = xen_get_max_pages();
if (max_pfn + extra_pages > extra_limit) {
if (extra_limit > max_pfn)
extra_pages = extra_limit - max_pfn;
else
extra_pages = 0;
}
extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820);
/*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size. On non-highmem systems, the base
* size is the full initial memory allocation; on highmem it
* is limited to the max size of lowmem, so that it doesn't
* get completely filled.
*
* In principle there could be a problem in lowmem systems if
* the initial memory is also very large with respect to
* lowmem, but we won't try to deal with that here.
*/
extra_limit = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
max_pfn + extra_pages);
if (extra_limit >= max_pfn)
extra_pages = extra_limit - max_pfn;
else
extra_pages = 0;
xen_add_extra_mem(extra_pages);
/*
* Set P2M for all non-RAM pages and E820 gaps to be identity
* type PFNs. We supply it with the non-sanitized version
* of the E820.
*/
identity_pages = xen_set_identity(map_raw, memmap.nr_entries);
printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages);
return "Xen";
}
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
char * __init xen_memory_setup(void)
{
static struct e820entry map[E820MAX] __initdata;
unsigned long max_pfn = xen_start_info->nr_pages;
unsigned long long mem_end;
int rc;
struct xen_memory_map memmap;
unsigned long max_pages;
unsigned long last_pfn = 0;
unsigned long extra_pages = 0;
unsigned long populated;
int i;
int op;
max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
mem_end = PFN_PHYS(max_pfn);
memmap.nr_entries = E820MAX;
set_xen_guest_handle(memmap.buffer, map);
op = xen_initial_domain() ?
XENMEM_machine_memory_map :
XENMEM_memory_map;
rc = HYPERVISOR_memory_op(op, &memmap);
if (rc == -ENOSYS) {
BUG_ON(xen_initial_domain());
memmap.nr_entries = 1;
map[0].addr = 0ULL;
map[0].size = mem_end;
/* 8MB slack (to balance backend allocations). */
map[0].size += 8ULL << 20;
map[0].type = E820_RAM;
rc = 0;
}
BUG_ON(rc);
/*
* Xen won't allow a 1:1 mapping to be created to UNUSABLE
* regions, so if we're using the machine memory map leave the
* region as RAM as it is in the pseudo-physical map.
*
* UNUSABLE regions in domUs are not handled and will need
* a patch in the future.
*/
if (xen_initial_domain())
xen_ignore_unusable(map, memmap.nr_entries);
/* Make sure the Xen-supplied memory map is well-ordered. */
sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
max_pages = xen_get_max_pages();
if (max_pages > max_pfn)
extra_pages += max_pages - max_pfn;
/*
* Set P2M for all non-RAM pages and E820 gaps to be identity
* type PFNs. Any RAM pages that would be made inaccesible by
* this are first released.
*/
xen_released_pages = xen_set_identity_and_release(
map, memmap.nr_entries, max_pfn);
/*
* Populate back the non-RAM pages and E820 gaps that had been
* released. */
populated = xen_populate_chunk(map, memmap.nr_entries,
max_pfn, &last_pfn, xen_released_pages);
xen_released_pages -= populated;
extra_pages += xen_released_pages;
if (last_pfn > max_pfn) {
max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
mem_end = PFN_PHYS(max_pfn);
}
/*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size. On non-highmem systems, the base
* size is the full initial memory allocation; on highmem it
* is limited to the max size of lowmem, so that it doesn't
* get completely filled.
*
* In principle there could be a problem in lowmem systems if
* the initial memory is also very large with respect to
* lowmem, but we won't try to deal with that here.
*/
extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages);
i = 0;
while (i < memmap.nr_entries) {
u64 addr = map[i].addr;
u64 size = map[i].size;
u32 type = map[i].type;
if (type == E820_RAM) {
if (addr < mem_end) {
size = min(size, mem_end - addr);
} else if (extra_pages) {
size = min(size, (u64)extra_pages * PAGE_SIZE);
extra_pages -= size / PAGE_SIZE;
xen_add_extra_mem(addr, size);
} else
type = E820_UNUSABLE;
}
xen_align_and_add_e820_region(addr, size, type);
map[i].addr += size;
map[i].size -= size;
if (map[i].size == 0)
i++;
}
/*
* In domU, the ISA region is normal, usable memory, but we
* reserve ISA memory anyway because too many things poke
* about in there.
*/
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
/*
* Reserve Xen bits:
* - mfn_list
* - xen_start_info
* See comment above "struct start_info" in <xen/interface/xen.h>
* We tried to make the the memblock_reserve more selective so
* that it would be clear what region is reserved. Sadly we ran
* in the problem wherein on a 64-bit hypervisor with a 32-bit
* initial domain, the pt_base has the cr3 value which is not
* neccessarily where the pagetable starts! As Jan put it: "
* Actually, the adjustment turns out to be correct: The page
* tables for a 32-on-64 dom0 get allocated in the order "first L1",
* "first L2", "first L3", so the offset to the page table base is
* indeed 2. When reading xen/include/public/xen.h's comment
* very strictly, this is not a violation (since there nothing is said
* that the first thing in the page table space is pointed to by
* pt_base; I admit that this seems to be implied though, namely
* do I think that it is implied that the page table space is the
* range [pt_base, pt_base + nt_pt_frames), whereas that
* range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames),
* which - without a priori knowledge - the kernel would have
* difficulty to figure out)." - so lets just fall back to the
* easy way and reserve the whole region.
*/
memblock_reserve(__pa(xen_start_info->mfn_list),
xen_start_info->pt_base - xen_start_info->mfn_list);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
return "Xen";
}
char * __init xen_memory_setup(void)
{
static struct e820entry map[E820MAX] __initdata;
unsigned long max_pfn = xen_start_info->nr_pages;
unsigned long long mem_end;
int rc;
struct xen_memory_map memmap;
unsigned long max_pages;
unsigned long extra_pages = 0;
int i;
int op;
max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
mem_end = PFN_PHYS(max_pfn);
memmap.nr_entries = E820MAX;
set_xen_guest_handle(memmap.buffer, map);
op = xen_initial_domain() ?
XENMEM_machine_memory_map :
XENMEM_memory_map;
rc = HYPERVISOR_memory_op(op, &memmap);
if (rc == -ENOSYS) {
BUG_ON(xen_initial_domain());
memmap.nr_entries = 1;
map[0].addr = 0ULL;
map[0].size = mem_end;
/* */
map[0].size += 8ULL << 20;
map[0].type = E820_RAM;
rc = 0;
}
BUG_ON(rc);
/* */
sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
max_pages = xen_get_max_pages();
if (max_pages > max_pfn)
extra_pages += max_pages - max_pfn;
/*
*/
xen_released_pages = xen_set_identity_and_release(
map, memmap.nr_entries, max_pfn);
extra_pages += xen_released_pages;
/*
*/
extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages);
i = 0;
while (i < memmap.nr_entries) {
u64 addr = map[i].addr;
u64 size = map[i].size;
u32 type = map[i].type;
if (type == E820_RAM) {
if (addr < mem_end) {
size = min(size, mem_end - addr);
} else if (extra_pages) {
size = min(size, (u64)extra_pages * PAGE_SIZE);
extra_pages -= size / PAGE_SIZE;
xen_add_extra_mem(addr, size);
} else
type = E820_UNUSABLE;
}
xen_align_and_add_e820_region(addr, size, type);
map[i].addr += size;
map[i].size -= size;
if (map[i].size == 0)
i++;
}
/*
*/
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
/*
*/
memblock_reserve(__pa(xen_start_info->mfn_list),
xen_start_info->pt_base - xen_start_info->mfn_list);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
return "Xen";
}
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
char * __init xen_memory_setup(void)
{
static struct e820entry map[E820MAX] __initdata;
unsigned long max_pfn = xen_start_info->nr_pages;
unsigned long long mem_end;
int rc;
struct xen_memory_map memmap;
unsigned long max_pages;
unsigned long last_pfn = 0;
unsigned long extra_pages = 0;
unsigned long populated;
int i;
int op;
max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
mem_end = PFN_PHYS(max_pfn);
memmap.nr_entries = E820MAX;
set_xen_guest_handle(memmap.buffer, map);
op = xen_initial_domain() ?
XENMEM_machine_memory_map :
XENMEM_memory_map;
rc = HYPERVISOR_memory_op(op, &memmap);
if (rc == -ENOSYS) {
BUG_ON(xen_initial_domain());
memmap.nr_entries = 1;
map[0].addr = 0ULL;
map[0].size = mem_end;
/* 8MB slack (to balance backend allocations). */
map[0].size += 8ULL << 20;
map[0].type = E820_RAM;
rc = 0;
}
BUG_ON(rc);
/* Make sure the Xen-supplied memory map is well-ordered. */
sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
max_pages = xen_get_max_pages();
if (max_pages > max_pfn)
extra_pages += max_pages - max_pfn;
/*
* Set P2M for all non-RAM pages and E820 gaps to be identity
* type PFNs. Any RAM pages that would be made inaccesible by
* this are first released.
*/
xen_released_pages = xen_set_identity_and_release(
map, memmap.nr_entries, max_pfn);
/*
* Populate back the non-RAM pages and E820 gaps that had been
* released. */
populated = xen_populate_chunk(map, memmap.nr_entries,
max_pfn, &last_pfn, xen_released_pages);
xen_released_pages -= populated;
extra_pages += xen_released_pages;
if (last_pfn > max_pfn) {
max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
mem_end = PFN_PHYS(max_pfn);
}
/*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size. On non-highmem systems, the base
* size is the full initial memory allocation; on highmem it
* is limited to the max size of lowmem, so that it doesn't
* get completely filled.
*
* In principle there could be a problem in lowmem systems if
* the initial memory is also very large with respect to
* lowmem, but we won't try to deal with that here.
*/
extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages);
i = 0;
while (i < memmap.nr_entries) {
u64 addr = map[i].addr;
u64 size = map[i].size;
u32 type = map[i].type;
if (type == E820_RAM) {
if (addr < mem_end) {
size = min(size, mem_end - addr);
} else if (extra_pages) {
size = min(size, (u64)extra_pages * PAGE_SIZE);
extra_pages -= size / PAGE_SIZE;
xen_add_extra_mem(addr, size);
} else
type = E820_UNUSABLE;
}
xen_align_and_add_e820_region(addr, size, type);
map[i].addr += size;
map[i].size -= size;
if (map[i].size == 0)
i++;
}
/*
* In domU, the ISA region is normal, usable memory, but we
* reserve ISA memory anyway because too many things poke
* about in there.
*/
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
/*
* Reserve Xen bits:
* - mfn_list
* - xen_start_info
* See comment above "struct start_info" in <xen/interface/xen.h>
*/
memblock_reserve(__pa(xen_start_info->mfn_list),
xen_start_info->pt_base - xen_start_info->mfn_list);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
return "Xen";
}
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
char * __init xen_memory_setup(void)
{
unsigned long max_pfn, pfn_s, n_pfns;
phys_addr_t mem_end, addr, size, chunk_size;
u32 type;
int rc;
struct xen_memory_map memmap;
unsigned long max_pages;
unsigned long extra_pages = 0;
int i;
int op;
xen_parse_512gb();
max_pfn = xen_get_pages_limit();
max_pfn = min(max_pfn, xen_start_info->nr_pages);
mem_end = PFN_PHYS(max_pfn);
memmap.nr_entries = E820MAX;
set_xen_guest_handle(memmap.buffer, xen_e820_map);
op = xen_initial_domain() ?
XENMEM_machine_memory_map :
XENMEM_memory_map;
rc = HYPERVISOR_memory_op(op, &memmap);
if (rc == -ENOSYS) {
BUG_ON(xen_initial_domain());
memmap.nr_entries = 1;
xen_e820_map[0].addr = 0ULL;
xen_e820_map[0].size = mem_end;
/* 8MB slack (to balance backend allocations). */
xen_e820_map[0].size += 8ULL << 20;
xen_e820_map[0].type = E820_RAM;
rc = 0;
}
BUG_ON(rc);
BUG_ON(memmap.nr_entries == 0);
xen_e820_map_entries = memmap.nr_entries;
/*
* Xen won't allow a 1:1 mapping to be created to UNUSABLE
* regions, so if we're using the machine memory map leave the
* region as RAM as it is in the pseudo-physical map.
*
* UNUSABLE regions in domUs are not handled and will need
* a patch in the future.
*/
if (xen_initial_domain())
xen_ignore_unusable();
/* Make sure the Xen-supplied memory map is well-ordered. */
sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
&xen_e820_map_entries);
max_pages = xen_get_max_pages();
/* How many extra pages do we need due to remapping? */
max_pages += xen_count_remap_pages(max_pfn);
if (max_pages > max_pfn)
extra_pages += max_pages - max_pfn;
/*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size. On non-highmem systems, the base
* size is the full initial memory allocation; on highmem it
* is limited to the max size of lowmem, so that it doesn't
* get completely filled.
*
* Make sure we have no memory above max_pages, as this area
* isn't handled by the p2m management.
*
* In principle there could be a problem in lowmem systems if
* the initial memory is also very large with respect to
* lowmem, but we won't try to deal with that here.
*/
extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages, max_pages - max_pfn);
i = 0;
addr = xen_e820_map[0].addr;
size = xen_e820_map[0].size;
while (i < xen_e820_map_entries) {
bool discard = false;
chunk_size = size;
type = xen_e820_map[i].type;
if (type == E820_RAM) {
if (addr < mem_end) {
chunk_size = min(size, mem_end - addr);
} else if (extra_pages) {
chunk_size = min(size, PFN_PHYS(extra_pages));
pfn_s = PFN_UP(addr);
n_pfns = PFN_DOWN(addr + chunk_size) - pfn_s;
extra_pages -= n_pfns;
xen_add_extra_mem(pfn_s, n_pfns);
xen_max_p2m_pfn = pfn_s + n_pfns;
} else
discard = true;
}
if (!discard)
xen_align_and_add_e820_region(addr, chunk_size, type);
addr += chunk_size;
size -= chunk_size;
if (size == 0) {
i++;
if (i < xen_e820_map_entries) {
addr = xen_e820_map[i].addr;
size = xen_e820_map[i].size;
}
}
}
/*
* Set the rest as identity mapped, in case PCI BARs are
* located here.
*/
set_phys_range_identity(addr / PAGE_SIZE, ~0ul);
/*
* In domU, the ISA region is normal, usable memory, but we
* reserve ISA memory anyway because too many things poke
* about in there.
*/
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
/*
* Check whether the kernel itself conflicts with the target E820 map.
* Failing now is better than running into weird problems later due
* to relocating (and even reusing) pages with kernel text or data.
*/
if (xen_is_e820_reserved(__pa_symbol(_text),
__pa_symbol(__bss_stop) - __pa_symbol(_text))) {
xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n");
BUG();
}
/*
* Check for a conflict of the hypervisor supplied page tables with
* the target E820 map.
*/
xen_pt_check_e820();
xen_reserve_xen_mfnlist();
/* Check for a conflict of the initrd with the target E820 map. */
if (xen_is_e820_reserved(boot_params.hdr.ramdisk_image,
boot_params.hdr.ramdisk_size)) {
phys_addr_t new_area, start, size;
new_area = xen_find_free_area(boot_params.hdr.ramdisk_size);
if (!new_area) {
xen_raw_console_write("Can't find new memory area for initrd needed due to E820 map conflict\n");
BUG();
}
start = boot_params.hdr.ramdisk_image;
size = boot_params.hdr.ramdisk_size;
xen_phys_memcpy(new_area, start, size);
pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n",
start, start + size, new_area, new_area + size);
memblock_free(start, size);
boot_params.hdr.ramdisk_image = new_area;
boot_params.ext_ramdisk_image = new_area >> 32;
}
