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_x86_reserve_range(start, start + size, "XEN EXTRA");
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);
}
}
char * __init xen_memory_setup(void)
{
unsigned long max_pfn = xen_start_info->nr_pages;
max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
e820.nr_map = 0;
e820_add_region(0, PFN_PHYS((u64)max_pfn), E820_RAM);
/*
* Even though this is normal, usable memory under Xen, reserve
* ISA memory anyway because too many things think they can 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_x86_reserve_range(__pa(xen_start_info->mfn_list),
__pa(xen_start_info->pt_base),
"XEN START INFO");
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
xen_return_unused_memory(xen_start_info->nr_pages, &e820);
return "Xen";
}
/**
* memblock에 특정 크기만큼 할당
*
* @return 할당한 가상주소
*/
static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
u64 goal, u64 limit)
{
void *ptr; /**< 가상주소 */
u64 addr; /**< 물리주소 */
/* limit는 현재 메모리의 한계 */
if (limit > memblock.current_limit)
limit = memblock.current_limit;
addr = find_memory_core_early(nid, size, align, goal, limit);
if (addr == MEMBLOCK_ERROR)
return NULL;
ptr = phys_to_virt(addr);
memset(ptr, 0, size);
memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
/*
* The min_count is set to 0 so that bootmem allocated blocks
* are never reported as leaks.
*/
/* memory leak이 발생하는 경우를 리포팅.
*
* FIXME: min_count(3번째 인자)가 0이면, 리포팅을 하지 않고,
* -1이면, 무시인데, 이 경우에 굳이 쓰이는지 알수 없음. */
kmemleak_alloc(ptr, size, 0, 0);
return ptr;
}
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_x86_reserve_range(start, start + size, "XEN EXTRA");
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);
}
static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
{
printk(KERN_INFO " %016llx bad mem addr %010llx - %010llx reserved\n",
(unsigned long long) pattern,
(unsigned long long) start_bad,
(unsigned long long) end_bad);
memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM");
}
void __init i386_start_kernel(void)
{
memblock_init();
memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
#ifdef CONFIG_BLK_DEV_INITRD
/* Reserve INITRD */
if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
/* Assume only end is not page aligned */
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
}
#endif
/* Call the subarch specific early setup function */
switch (boot_params.hdr.hardware_subarch) {
case X86_SUBARCH_MRST:
x86_mrst_early_setup();
break;
case X86_SUBARCH_CE4100:
x86_ce4100_early_setup();
break;
default:
i386_default_early_setup();
break;
}
/*
* At this point everything still needed from the boot loader
* or BIOS or kernel text should be early reserved or marked not
* RAM in e820. All other memory is free game.
*/
start_kernel();
}
static __init void xen_add_extra_mem(unsigned long pages)
{
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_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA");
xen_extra_mem_size += size;
xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
}
void __init reserve_ebda_region(void)
{
unsigned int lowmem, ebda_addr;
/*
* To determine the position of the EBDA and the
* end of conventional memory, we need to look at
* the BIOS data area. In a paravirtual environment
* that area is absent. We'll just have to assume
* that the paravirt case can handle memory setup
* correctly, without our help.
*/
if (paravirt_enabled())
return;
/* end of low (conventional) memory */
lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
lowmem <<= 10;
/* start of EBDA area */
ebda_addr = get_bios_ebda();
/*
* Note: some old Dells seem to need 4k EBDA without
* reporting so, so just consider the memory above 0x9f000
* to be off limits (bugzilla 2990).
*/
/* If the EBDA address is below 128K, assume it is bogus */
if (ebda_addr < INSANE_CUTOFF)
ebda_addr = LOWMEM_CAP;
/* If lowmem is less than 128K, assume it is bogus */
if (lowmem < INSANE_CUTOFF)
lowmem = LOWMEM_CAP;
/* Use the lower of the lowmem and EBDA markers as the cutoff */
lowmem = min(lowmem, ebda_addr);
lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
/* reserve all memory between lowmem and the 1MB mark */
memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");
}
/**
* acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation
*
* We allocate a page from the first 1MB of memory for the wakeup
* routine for when we come back from a sleep state. The
* runtime allocator allows specification of <16MB pages, but not
* <1MB pages.
*/
void __init acpi_reserve_wakeup_memory(void)
{
phys_addr_t mem;
if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
printk(KERN_ERR
"ACPI: Wakeup code way too big, S3 disabled.\n");
return;
}
mem = memblock_find_in_range(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
if (mem == MEMBLOCK_ERROR) {
printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
return;
}
acpi_realmode = (unsigned long) phys_to_virt(mem);
acpi_wakeup_address = mem;
memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
}
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_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA");
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);
}
void __init reserve_ebda_region(void)
{
unsigned int lowmem, ebda_addr;
/*
* To determine the position of the EBDA and the
* end of conventional memory, we need to look at
* the BIOS data area. In a paravirtual environment
* that area is absent. We'll just have to assume
* that the paravirt case can handle memory setup
* correctly, without our help.
*/
if (paravirt_enabled())
return;
/* end of low (conventional) memory */
lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
lowmem <<= 10;
/* start of EBDA area */
ebda_addr = get_bios_ebda();
/* Fixup: bios puts an EBDA in the top 64K segment */
/* of conventional memory, but does not adjust lowmem. */
if ((lowmem - ebda_addr) <= 0x10000)
lowmem = ebda_addr;
/* Fixup: bios does not report an EBDA at all. */
/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
if ((ebda_addr == 0) && (lowmem >= 0x9f000))
lowmem = 0x9f000;
/* Paranoia: should never happen, but... */
if ((lowmem == 0) || (lowmem >= 0x100000))
lowmem = 0x9f000;
/* reserve all memory between lowmem and the 1MB mark */
memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");
}
static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
u64 goal, u64 limit)
{
void *ptr;
u64 addr;
if (limit > memblock.current_limit)
limit = memblock.current_limit;
addr = memblock_find_in_range_node(goal, limit, size, align, nid);
if (!addr)
return NULL;
ptr = phys_to_virt(addr);
memset(ptr, 0, size);
memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
/*
* The min_count is set to 0 so that bootmem allocated blocks
* are never reported as leaks.
*/
kmemleak_alloc(ptr, size, 0, 0);
return ptr;
}
/**
* 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 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;
/* 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);
extra_pages += xen_released_pages;
/*
* 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_x86_reserve_range(__pa(xen_start_info->mfn_list),
__pa(xen_start_info->pt_base),
"XEN START INFO");
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;
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_x86_reserve_range(__pa(xen_start_info->mfn_list),
__pa(xen_start_info->pt_base),
"XEN START INFO");
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 extra_pages = 0;
unsigned long extra_limit;
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);
e820.nr_map = 0;
xen_extra_mem_start = mem_end;
for (i = 0; i < memmap.nr_entries; i++) {
unsigned long long end = map[i].addr + map[i].size;
if (map[i].type == E820_RAM) {
if (map[i].addr < mem_end && end > mem_end) {
/* Truncate region to max_mem. */
u64 delta = end - mem_end;
map[i].size -= delta;
extra_pages += PFN_DOWN(delta);
end = mem_end;
}
}
if (end > xen_extra_mem_start)
xen_extra_mem_start = end;
/* If region is non-RAM or below mem_end, add what remains */
if ((map[i].type != E820_RAM || map[i].addr < mem_end) &&
map[i].size > 0)
e820_add_region(map[i].addr, map[i].size, map[i].type);
}
/*
* 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_x86_reserve_range(__pa(xen_start_info->mfn_list),
__pa(xen_start_info->pt_base),
"XEN START INFO");
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
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;
if (!xen_initial_domain())
xen_add_extra_mem(extra_pages);
return "Xen";
}
