linux/arch/x86/kernel/e820.c

1112 lines
28 KiB
C
Raw Normal View History

/*
* Handle the memory map.
* The functions here do the job until bootmem takes over.
*
* Getting sanitize_e820_map() in sync with i386 version by applying change:
* - Provisions for empty E820 memory regions (reported by certain BIOSes).
* Alex Achenbach <xela@slit.de>, December 2002.
* Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
*
*/
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/crash_dump.h>
#include <linux/export.h>
#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/acpi.h>
#include <linux/firmware-map.h>
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-25 20:39:17 +00:00
#include <linux/memblock.h>
#include <linux/sort.h>
#include <asm/e820.h>
x86: extend e820 ealy_res support 32bit move early_res related from e820_64.c to e820.c make edba detection to be done in head32.c remove smp_alloc_memory, because we have fixed trampoline address now. Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com> arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 10 files changed, 320 insertions(+), 319 deletions(-) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-18 08:18:57 +00:00
#include <asm/proto.h>
#include <asm/setup.h>
/*
* The e820 map is the map that gets modified e.g. with command line parameters
* and that is also registered with modifications in the kernel resource tree
* with the iomem_resource as parent.
*
* The e820_saved is directly saved after the BIOS-provided memory map is
* copied. It doesn't get modified afterwards. It's registered for the
* /sys/firmware/memmap interface.
*
* That memory map is not modified and is used as base for kexec. The kexec'd
* kernel should get the same memory map as the firmware provides. Then the
* user can e.g. boot the original kernel with mem=1G while still booting the
* next kernel with full memory.
*/
struct e820map e820;
struct e820map e820_saved;
/* For PCI or other memory-mapped resources */
unsigned long pci_mem_start = 0xaeedbabe;
#ifdef CONFIG_PCI
EXPORT_SYMBOL(pci_mem_start);
#endif
/*
* This function checks if any part of the range <start,end> is mapped
* with type.
*/
int
e820_any_mapped(u64 start, u64 end, unsigned type)
{
int i;
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
if (type && ei->type != type)
continue;
if (ei->addr >= end || ei->addr + ei->size <= start)
continue;
return 1;
}
return 0;
}
EXPORT_SYMBOL_GPL(e820_any_mapped);
/*
* This function checks if the entire range <start,end> is mapped with type.
*
* Note: this function only works correct if the e820 table is sorted and
* not-overlapping, which is the case
*/
int __init e820_all_mapped(u64 start, u64 end, unsigned type)
{
int i;
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
if (type && ei->type != type)
continue;
/* is the region (part) in overlap with the current region ?*/
if (ei->addr >= end || ei->addr + ei->size <= start)
continue;
/* if the region is at the beginning of <start,end> we move
* start to the end of the region since it's ok until there
*/
if (ei->addr <= start)
start = ei->addr + ei->size;
/*
* if start is now at or beyond end, we're done, full
* coverage
*/
if (start >= end)
return 1;
}
return 0;
}
/*
* Add a memory region to the kernel e820 map.
*/
static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
int type)
{
int x = e820x->nr_map;
if (x >= ARRAY_SIZE(e820x->map)) {
printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
return;
}
e820x->map[x].addr = start;
e820x->map[x].size = size;
e820x->map[x].type = type;
e820x->nr_map++;
}
void __init e820_add_region(u64 start, u64 size, int type)
{
__e820_add_region(&e820, start, size, type);
}
static void __init e820_print_type(u32 type)
{
switch (type) {
case E820_RAM:
case E820_RESERVED_KERN:
printk(KERN_CONT "(usable)");
break;
case E820_RESERVED:
printk(KERN_CONT "(reserved)");
break;
case E820_ACPI:
printk(KERN_CONT "(ACPI data)");
break;
case E820_NVS:
printk(KERN_CONT "(ACPI NVS)");
break;
case E820_UNUSABLE:
printk(KERN_CONT "(unusable)");
break;
default:
printk(KERN_CONT "type %u", type);
break;
}
}
void __init e820_print_map(char *who)
{
int i;
for (i = 0; i < e820.nr_map; i++) {
printk(KERN_INFO " %s: %016Lx - %016Lx ", who,
(unsigned long long) e820.map[i].addr,
(unsigned long long)
(e820.map[i].addr + e820.map[i].size));
e820_print_type(e820.map[i].type);
printk(KERN_CONT "\n");
}
}
/*
* Sanitize the BIOS e820 map.
*
* Some e820 responses include overlapping entries. The following
* replaces the original e820 map with a new one, removing overlaps,
* and resolving conflicting memory types in favor of highest
* numbered type.
*
* The input parameter biosmap points to an array of 'struct
* e820entry' which on entry has elements in the range [0, *pnr_map)
* valid, and which has space for up to max_nr_map entries.
* On return, the resulting sanitized e820 map entries will be in
* overwritten in the same location, starting at biosmap.
*
* The integer pointed to by pnr_map must be valid on entry (the
* current number of valid entries located at biosmap) and will
* be updated on return, with the new number of valid entries
* (something no more than max_nr_map.)
*
* The return value from sanitize_e820_map() is zero if it
* successfully 'sanitized' the map entries passed in, and is -1
* if it did nothing, which can happen if either of (1) it was
* only passed one map entry, or (2) any of the input map entries
* were invalid (start + size < start, meaning that the size was
* so big the described memory range wrapped around through zero.)
*
* Visually we're performing the following
* (1,2,3,4 = memory types)...
*
* Sample memory map (w/overlaps):
* ____22__________________
* ______________________4_
* ____1111________________
* _44_____________________
* 11111111________________
* ____________________33__
* ___________44___________
* __________33333_________
* ______________22________
* ___________________2222_
* _________111111111______
* _____________________11_
* _________________4______
*
* Sanitized equivalent (no overlap):
* 1_______________________
* _44_____________________
* ___1____________________
* ____22__________________
* ______11________________
* _________1______________
* __________3_____________
* ___________44___________
* _____________33_________
* _______________2________
* ________________1_______
* _________________4______
* ___________________2____
* ____________________33__
* ______________________4_
*/
struct change_member {
struct e820entry *pbios; /* pointer to original bios entry */
unsigned long long addr; /* address for this change point */
};
static int __init cpcompare(const void *a, const void *b)
{
struct change_member * const *app = a, * const *bpp = b;
const struct change_member *ap = *app, *bp = *bpp;
/*
* Inputs are pointers to two elements of change_point[]. If their
* addresses are unequal, their difference dominates. If the addresses
* are equal, then consider one that represents the end of its region
* to be greater than one that does not.
*/
if (ap->addr != bp->addr)
return ap->addr > bp->addr ? 1 : -1;
return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr);
}
int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
u32 *pnr_map)
{
static struct change_member change_point_list[2*E820_X_MAX] __initdata;
static struct change_member *change_point[2*E820_X_MAX] __initdata;
static struct e820entry *overlap_list[E820_X_MAX] __initdata;
static struct e820entry new_bios[E820_X_MAX] __initdata;
unsigned long current_type, last_type;
unsigned long long last_addr;
int chgidx;
int overlap_entries;
int new_bios_entry;
int old_nr, new_nr, chg_nr;
int i;
/* if there's only one memory region, don't bother */
if (*pnr_map < 2)
return -1;
old_nr = *pnr_map;
BUG_ON(old_nr > max_nr_map);
/* bail out if we find any unreasonable addresses in bios map */
for (i = 0; i < old_nr; i++)
if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
return -1;
/* create pointers for initial change-point information (for sorting) */
for (i = 0; i < 2 * old_nr; i++)
change_point[i] = &change_point_list[i];
/* record all known change-points (starting and ending addresses),
omitting those that are for empty memory regions */
chgidx = 0;
for (i = 0; i < old_nr; i++) {
if (biosmap[i].size != 0) {
change_point[chgidx]->addr = biosmap[i].addr;
change_point[chgidx++]->pbios = &biosmap[i];
change_point[chgidx]->addr = biosmap[i].addr +
biosmap[i].size;
change_point[chgidx++]->pbios = &biosmap[i];
}
}
chg_nr = chgidx;
/* sort change-point list by memory addresses (low -> high) */
sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL);
/* create a new bios memory map, removing overlaps */
overlap_entries = 0; /* number of entries in the overlap table */
new_bios_entry = 0; /* index for creating new bios map entries */
last_type = 0; /* start with undefined memory type */
last_addr = 0; /* start with 0 as last starting address */
/* loop through change-points, determining affect on the new bios map */
for (chgidx = 0; chgidx < chg_nr; chgidx++) {
/* keep track of all overlapping bios entries */
if (change_point[chgidx]->addr ==
change_point[chgidx]->pbios->addr) {
/*
* add map entry to overlap list (> 1 entry
* implies an overlap)
*/
overlap_list[overlap_entries++] =
change_point[chgidx]->pbios;
} else {
/*
* remove entry from list (order independent,
* so swap with last)
*/
for (i = 0; i < overlap_entries; i++) {
if (overlap_list[i] ==
change_point[chgidx]->pbios)
overlap_list[i] =
overlap_list[overlap_entries-1];
}
overlap_entries--;
}
/*
* if there are overlapping entries, decide which
* "type" to use (larger value takes precedence --
* 1=usable, 2,3,4,4+=unusable)
*/
current_type = 0;
for (i = 0; i < overlap_entries; i++)
if (overlap_list[i]->type > current_type)
current_type = overlap_list[i]->type;
/*
* continue building up new bios map based on this
* information
*/
if (current_type != last_type) {
if (last_type != 0) {
new_bios[new_bios_entry].size =
change_point[chgidx]->addr - last_addr;
/*
* move forward only if the new size
* was non-zero
*/
if (new_bios[new_bios_entry].size != 0)
/*
* no more space left for new
* bios entries ?
*/
if (++new_bios_entry >= max_nr_map)
break;
}
if (current_type != 0) {
new_bios[new_bios_entry].addr =
change_point[chgidx]->addr;
new_bios[new_bios_entry].type = current_type;
last_addr = change_point[chgidx]->addr;
}
last_type = current_type;
}
}
/* retain count for new bios entries */
new_nr = new_bios_entry;
/* copy new bios mapping into original location */
memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry));
*pnr_map = new_nr;
return 0;
}
static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
{
while (nr_map) {
u64 start = biosmap->addr;
u64 size = biosmap->size;
u64 end = start + size;
u32 type = biosmap->type;
/* Overflow in 64 bits? Ignore the memory map. */
if (start > end)
return -1;
e820_add_region(start, size, type);
biosmap++;
nr_map--;
}
return 0;
}
/*
* Copy the BIOS e820 map into a safe place.
*
* Sanity-check it while we're at it..
*
* If we're lucky and live on a modern system, the setup code
* will have given us a memory map that we can use to properly
* set up memory. If we aren't, we'll fake a memory map.
*/
static int __init append_e820_map(struct e820entry *biosmap, int nr_map)
{
/* Only one memory region (or negative)? Ignore it */
if (nr_map < 2)
return -1;
return __append_e820_map(biosmap, nr_map);
}
static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
u64 size, unsigned old_type,
unsigned new_type)
{
u64 end;
unsigned int i;
u64 real_updated_size = 0;
BUG_ON(old_type == new_type);
if (size > (ULLONG_MAX - start))
size = ULLONG_MAX - start;
end = start + size;
printk(KERN_DEBUG "e820 update range: %016Lx - %016Lx ",
(unsigned long long) start,
(unsigned long long) end);
e820_print_type(old_type);
printk(KERN_CONT " ==> ");
e820_print_type(new_type);
printk(KERN_CONT "\n");
for (i = 0; i < e820x->nr_map; i++) {
struct e820entry *ei = &e820x->map[i];
u64 final_start, final_end;
u64 ei_end;
if (ei->type != old_type)
continue;
ei_end = ei->addr + ei->size;
/* totally covered by new range? */
if (ei->addr >= start && ei_end <= end) {
ei->type = new_type;
real_updated_size += ei->size;
continue;
}
/* new range is totally covered? */
if (ei->addr < start && ei_end > end) {
__e820_add_region(e820x, start, size, new_type);
__e820_add_region(e820x, end, ei_end - end, ei->type);
ei->size = start - ei->addr;
real_updated_size += size;
continue;
}
/* partially covered */
final_start = max(start, ei->addr);
final_end = min(end, ei_end);
if (final_start >= final_end)
continue;
__e820_add_region(e820x, final_start, final_end - final_start,
new_type);
real_updated_size += final_end - final_start;
/*
* left range could be head or tail, so need to update
* size at first.
*/
ei->size -= final_end - final_start;
if (ei->addr < final_start)
continue;
ei->addr = final_end;
}
return real_updated_size;
}
u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
unsigned new_type)
{
return __e820_update_range(&e820, start, size, old_type, new_type);
}
static u64 __init e820_update_range_saved(u64 start, u64 size,
unsigned old_type, unsigned new_type)
{
return __e820_update_range(&e820_saved, start, size, old_type,
new_type);
}
/* make e820 not cover the range */
u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
int checktype)
{
int i;
u64 end;
u64 real_removed_size = 0;
if (size > (ULLONG_MAX - start))
size = ULLONG_MAX - start;
end = start + size;
printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
(unsigned long long) start,
(unsigned long long) end);
if (checktype)
e820_print_type(old_type);
printk(KERN_CONT "\n");
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
u64 final_start, final_end;
u64 ei_end;
if (checktype && ei->type != old_type)
continue;
ei_end = ei->addr + ei->size;
/* totally covered? */
if (ei->addr >= start && ei_end <= end) {
real_removed_size += ei->size;
memset(ei, 0, sizeof(struct e820entry));
continue;
}
/* new range is totally covered? */
if (ei->addr < start && ei_end > end) {
e820_add_region(end, ei_end - end, ei->type);
ei->size = start - ei->addr;
real_removed_size += size;
continue;
}
/* partially covered */
final_start = max(start, ei->addr);
final_end = min(end, ei_end);
if (final_start >= final_end)
continue;
real_removed_size += final_end - final_start;
/*
* left range could be head or tail, so need to update
* size at first.
*/
ei->size -= final_end - final_start;
if (ei->addr < final_start)
continue;
ei->addr = final_end;
}
return real_removed_size;
}
void __init update_e820(void)
{
u32 nr_map;
nr_map = e820.nr_map;
if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
return;
e820.nr_map = nr_map;
printk(KERN_INFO "modified physical RAM map:\n");
e820_print_map("modified");
}
static void __init update_e820_saved(void)
{
u32 nr_map;
nr_map = e820_saved.nr_map;
if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map))
return;
e820_saved.nr_map = nr_map;
}
#define MAX_GAP_END 0x100000000ull
/*
* Search for a gap in the e820 memory space from start_addr to end_addr.
*/
__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
unsigned long start_addr, unsigned long long end_addr)
{
unsigned long long last;
int i = e820.nr_map;
int found = 0;
last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;
while (--i >= 0) {
unsigned long long start = e820.map[i].addr;
unsigned long long end = start + e820.map[i].size;
if (end < start_addr)
continue;
/*
* Since "last" is at most 4GB, we know we'll
* fit in 32 bits if this condition is true
*/
if (last > end) {
unsigned long gap = last - end;
if (gap >= *gapsize) {
*gapsize = gap;
*gapstart = end;
found = 1;
}
}
if (start < last)
last = start;
}
return found;
}
/*
* Search for the biggest gap in the low 32 bits of the e820
* memory space. We pass this space to PCI to assign MMIO resources
* for hotplug or unconfigured devices in.
* Hopefully the BIOS let enough space left.
*/
__init void e820_setup_gap(void)
{
unsigned long gapstart, gapsize;
int found;
gapstart = 0x10000000;
gapsize = 0x400000;
found = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END);
#ifdef CONFIG_X86_64
if (!found) {
gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
printk(KERN_ERR
"PCI: Warning: Cannot find a gap in the 32bit address range\n"
"PCI: Unassigned devices with 32bit resource registers may break!\n");
}
#endif
/*
* e820_reserve_resources_late protect stolen RAM already
*/
pci_mem_start = gapstart;
printk(KERN_INFO
"Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
pci_mem_start, gapstart, gapsize);
}
/**
* Because of the size limitation of struct boot_params, only first
* 128 E820 memory entries are passed to kernel via
* boot_params.e820_map, others are passed via SETUP_E820_EXT node of
* linked list of struct setup_data, which is parsed here.
*/
void __init parse_e820_ext(struct setup_data *sdata)
{
int entries;
struct e820entry *extmap;
entries = sdata->len / sizeof(struct e820entry);
extmap = (struct e820entry *)(sdata->data);
__append_e820_map(extmap, entries);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
printk(KERN_INFO "extended physical RAM map:\n");
e820_print_map("extended");
}
#if defined(CONFIG_X86_64) || \
(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
/**
* Find the ranges of physical addresses that do not correspond to
* e820 RAM areas and mark the corresponding pages as nosave for
* hibernation (32 bit) or software suspend and suspend to RAM (64 bit).
*
* This function requires the e820 map to be sorted and without any
* overlapping entries and assumes the first e820 area to be RAM.
*/
void __init e820_mark_nosave_regions(unsigned long limit_pfn)
{
int i;
unsigned long pfn;
pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
for (i = 1; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
if (pfn < PFN_UP(ei->addr))
register_nosave_region(pfn, PFN_UP(ei->addr));
pfn = PFN_DOWN(ei->addr + ei->size);
if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
register_nosave_region(PFN_UP(ei->addr), pfn);
if (pfn >= limit_pfn)
break;
}
}
#endif
x86: extend e820 ealy_res support 32bit move early_res related from e820_64.c to e820.c make edba detection to be done in head32.c remove smp_alloc_memory, because we have fixed trampoline address now. Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com> arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 10 files changed, 320 insertions(+), 319 deletions(-) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-18 08:18:57 +00:00
#ifdef CONFIG_ACPI
/**
* Mark ACPI NVS memory region, so that we can save/restore it during
* hibernation and the subsequent resume.
*/
static int __init e820_mark_nvs_memory(void)
{
int i;
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
if (ei->type == E820_NVS)
acpi_nvs_register(ei->addr, ei->size);
}
return 0;
}
core_initcall(e820_mark_nvs_memory);
#endif
/*
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-25 20:39:17 +00:00
* pre allocated 4k and reserved it in memblock and e820_saved
*/
u64 __init early_reserve_e820(u64 size, u64 align)
{
u64 addr;
addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
if (addr) {
e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
update_e820_saved();
}
return addr;
}
#ifdef CONFIG_X86_32
# ifdef CONFIG_X86_PAE
# define MAX_ARCH_PFN (1ULL<<(36-PAGE_SHIFT))
# else
# define MAX_ARCH_PFN (1ULL<<(32-PAGE_SHIFT))
# endif
#else /* CONFIG_X86_32 */
# define MAX_ARCH_PFN MAXMEM>>PAGE_SHIFT
#endif
/*
* Find the highest page frame number we have available
*/
static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
{
int i;
unsigned long last_pfn = 0;
unsigned long max_arch_pfn = MAX_ARCH_PFN;
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
unsigned long start_pfn;
unsigned long end_pfn;
if (ei->type != type)
continue;
start_pfn = ei->addr >> PAGE_SHIFT;
end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
if (start_pfn >= limit_pfn)
continue;
if (end_pfn > limit_pfn) {
last_pfn = limit_pfn;
break;
}
if (end_pfn > last_pfn)
last_pfn = end_pfn;
}
if (last_pfn > max_arch_pfn)
last_pfn = max_arch_pfn;
printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
last_pfn, max_arch_pfn);
return last_pfn;
}
unsigned long __init e820_end_of_ram_pfn(void)
{
return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
}
unsigned long __init e820_end_of_low_ram_pfn(void)
{
return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
}
static void early_panic(char *msg)
{
early_printk(msg);
panic(msg);
}
static int userdef __initdata;
/* "mem=nopentium" disables the 4MB page tables. */
static int __init parse_memopt(char *p)
{
u64 mem_size;
if (!p)
return -EINVAL;
if (!strcmp(p, "nopentium")) {
#ifdef CONFIG_X86_32
setup_clear_cpu_cap(X86_FEATURE_PSE);
return 0;
#else
printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
return -EINVAL;
#endif
}
userdef = 1;
mem_size = memparse(p, &p);
/* don't remove all of memory when handling "mem={invalid}" param */
if (mem_size == 0)
return -EINVAL;
e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
return 0;
}
early_param("mem", parse_memopt);
static int __init parse_memmap_opt(char *p)
{
char *oldp;
u64 start_at, mem_size;
if (!p)
return -EINVAL;
x86: fix memmap=exactmap boot argument When using kdump modifying the e820 map is yielding strange results. For example starting with BIOS-provided physical RAM map: BIOS-e820: 0000000000000100 - 0000000000093400 (usable) BIOS-e820: 0000000000093400 - 00000000000a0000 (reserved) BIOS-e820: 0000000000100000 - 000000003fee0000 (usable) BIOS-e820: 000000003fee0000 - 000000003fef3000 (ACPI data) BIOS-e820: 000000003fef3000 - 000000003ff80000 (ACPI NVS) BIOS-e820: 000000003ff80000 - 0000000040000000 (reserved) BIOS-e820: 00000000e0000000 - 00000000f0000000 (reserved) BIOS-e820: 00000000fec00000 - 00000000fec10000 (reserved) BIOS-e820: 00000000fee00000 - 00000000fee01000 (reserved) BIOS-e820: 00000000ff000000 - 0000000100000000 (reserved) and booting with args memmap=exactmap memmap=640K@0K memmap=5228K@16384K memmap=125188K@22252K memmap=76K#1047424K memmap=564K#1047500K resulted in: user-defined physical RAM map: user: 0000000000000000 - 0000000000093400 (usable) user: 0000000000093400 - 00000000000a0000 (reserved) user: 0000000000100000 - 000000003fee0000 (usable) user: 000000003fee0000 - 000000003fef3000 (ACPI data) user: 000000003fef3000 - 000000003ff80000 (ACPI NVS) user: 000000003ff80000 - 0000000040000000 (reserved) user: 00000000e0000000 - 00000000f0000000 (reserved) user: 00000000fec00000 - 00000000fec10000 (reserved) user: 00000000fee00000 - 00000000fee01000 (reserved) user: 00000000ff000000 - 0000000100000000 (reserved) But should have resulted in: user-defined physical RAM map: user: 0000000000000000 - 00000000000a0000 (usable) user: 0000000001000000 - 000000000151b000 (usable) user: 00000000015bb000 - 0000000008ffc000 (usable) user: 000000003fee0000 - 000000003ff80000 (ACPI data) This is happening because of an improper usage of strcmp() in the e820 parsing code. The strcmp() always returns !0 and never resets the value for e820.nr_map and returns an incorrect user-defined map. This patch fixes the problem. Signed-off-by: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-09 13:56:08 +00:00
if (!strncmp(p, "exactmap", 8)) {
#ifdef CONFIG_CRASH_DUMP
/*
* If we are doing a crash dump, we still need to know
* the real mem size before original memory map is
* reset.
*/
saved_max_pfn = e820_end_of_ram_pfn();
#endif
e820.nr_map = 0;
userdef = 1;
return 0;
}
oldp = p;
mem_size = memparse(p, &p);
if (p == oldp)
return -EINVAL;
userdef = 1;
if (*p == '@') {
start_at = memparse(p+1, &p);
e820_add_region(start_at, mem_size, E820_RAM);
} else if (*p == '#') {
start_at = memparse(p+1, &p);
e820_add_region(start_at, mem_size, E820_ACPI);
} else if (*p == '$') {
start_at = memparse(p+1, &p);
e820_add_region(start_at, mem_size, E820_RESERVED);
} else
e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
return *p == '\0' ? 0 : -EINVAL;
}
early_param("memmap", parse_memmap_opt);
void __init finish_e820_parsing(void)
{
if (userdef) {
u32 nr = e820.nr_map;
if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0)
early_panic("Invalid user supplied memory map");
e820.nr_map = nr;
printk(KERN_INFO "user-defined physical RAM map:\n");
e820_print_map("user");
}
}
static inline const char *e820_type_to_string(int e820_type)
{
switch (e820_type) {
case E820_RESERVED_KERN:
case E820_RAM: return "System RAM";
case E820_ACPI: return "ACPI Tables";
case E820_NVS: return "ACPI Non-volatile Storage";
case E820_UNUSABLE: return "Unusable memory";
default: return "reserved";
}
}
/*
* Mark e820 reserved areas as busy for the resource manager.
*/
static struct resource __initdata *e820_res;
void __init e820_reserve_resources(void)
{
int i;
struct resource *res;
u64 end;
res = alloc_bootmem(sizeof(struct resource) * e820.nr_map);
e820_res = res;
for (i = 0; i < e820.nr_map; i++) {
end = e820.map[i].addr + e820.map[i].size - 1;
if (end != (resource_size_t)end) {
res++;
continue;
}
res->name = e820_type_to_string(e820.map[i].type);
res->start = e820.map[i].addr;
res->end = end;
x86: Clean up late e820 resource allocation This makes the late e820 resources use 'insert_resource_expand_to_fit()' instead of doing a 'reserve_region_with_split()', and also avoids marking them as IORESOURCE_BUSY. This results in us being perfectly happy to use pre-existing PCI resources even if they were marked as being in a reserved region, while still avoiding any _new_ allocations in the reserved regions. It also makes for a simpler and more accurate resource tree. Example resource allocation from Jonathan Corbet, who has firmware that has an e820 reserved entry that covered a big range (e0000000-fed003ff), and that had various PCI resources in it set up by firmware. With old kernels, the reserved range would force us to re-allocate all pre-existing PCI resources, and his reserved range would end up looking like this: e0000000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 where only the pre-allocated special regions (IOAPIC and HPET) were kept around. With 2.6.28-rc2, which uses 'reserve_region_with_split()', Jonathan's resource tree looked like this: e0000000-fe7fffff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe800000-fe8fffff : reserved fe900000-fe9d9aff : reserved fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9b00-fe9d9bff : reserved fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : reserved fe9da000-fe9dafff : 0000:00:03.3 fe9da000-fe9dafff : reserved fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : reserved fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : reserved fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : reserved fea00000-fea7ffff : 0000:00:02.0 fea00000-fea7ffff : reserved fea80000-feafffff : 0000:00:02.1 fea80000-feafffff : reserved feb00000-febfffff : 0000:00:02.0 feb00000-febfffff : reserved fec00000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 and because the reserved entry had been split and moved into the individual resources, and because it used the IORESOURCE_BUSY flag, the drivers that actually wanted to _use_ those resources couldn't actually attach to them: e1000e 0000:00:19.0: BAR 0: can't reserve mem region [0xfe9e0000-0xfe9fffff] HDA Intel 0000:00:1b.0: BAR 0: can't reserve mem region [0xfe9dc000-0xfe9dffff] with this patch, the resource tree instead becomes e0000000-fed003ff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : ehci_hcd fe9da000-fe9dafff : 0000:00:03.3 fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : e1000e fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : ICH HD audio fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : e1000e fea00000-fea7ffff : 0000:00:02.0 fea80000-feafffff : 0000:00:02.1 feb00000-febfffff : 0000:00:02.0 fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 ie the one reserved region now ends up surrounding all the PCI resources that were allocated inside of it by firmware, and because it is not marked BUSY, drivers have no problem attaching to the pre-allocated resources. Reported-and-tested-by: Jonathan Corbet <corbet@lwn.net> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-01 17:17:22 +00:00
res->flags = IORESOURCE_MEM;
/*
* don't register the region that could be conflicted with
* pci device BAR resource and insert them later in
* pcibios_resource_survey()
*/
x86: Clean up late e820 resource allocation This makes the late e820 resources use 'insert_resource_expand_to_fit()' instead of doing a 'reserve_region_with_split()', and also avoids marking them as IORESOURCE_BUSY. This results in us being perfectly happy to use pre-existing PCI resources even if they were marked as being in a reserved region, while still avoiding any _new_ allocations in the reserved regions. It also makes for a simpler and more accurate resource tree. Example resource allocation from Jonathan Corbet, who has firmware that has an e820 reserved entry that covered a big range (e0000000-fed003ff), and that had various PCI resources in it set up by firmware. With old kernels, the reserved range would force us to re-allocate all pre-existing PCI resources, and his reserved range would end up looking like this: e0000000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 where only the pre-allocated special regions (IOAPIC and HPET) were kept around. With 2.6.28-rc2, which uses 'reserve_region_with_split()', Jonathan's resource tree looked like this: e0000000-fe7fffff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe800000-fe8fffff : reserved fe900000-fe9d9aff : reserved fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9b00-fe9d9bff : reserved fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : reserved fe9da000-fe9dafff : 0000:00:03.3 fe9da000-fe9dafff : reserved fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : reserved fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : reserved fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : reserved fea00000-fea7ffff : 0000:00:02.0 fea00000-fea7ffff : reserved fea80000-feafffff : 0000:00:02.1 fea80000-feafffff : reserved feb00000-febfffff : 0000:00:02.0 feb00000-febfffff : reserved fec00000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 and because the reserved entry had been split and moved into the individual resources, and because it used the IORESOURCE_BUSY flag, the drivers that actually wanted to _use_ those resources couldn't actually attach to them: e1000e 0000:00:19.0: BAR 0: can't reserve mem region [0xfe9e0000-0xfe9fffff] HDA Intel 0000:00:1b.0: BAR 0: can't reserve mem region [0xfe9dc000-0xfe9dffff] with this patch, the resource tree instead becomes e0000000-fed003ff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : ehci_hcd fe9da000-fe9dafff : 0000:00:03.3 fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : e1000e fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : ICH HD audio fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : e1000e fea00000-fea7ffff : 0000:00:02.0 fea80000-feafffff : 0000:00:02.1 feb00000-febfffff : 0000:00:02.0 fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 ie the one reserved region now ends up surrounding all the PCI resources that were allocated inside of it by firmware, and because it is not marked BUSY, drivers have no problem attaching to the pre-allocated resources. Reported-and-tested-by: Jonathan Corbet <corbet@lwn.net> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-01 17:17:22 +00:00
if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) {
res->flags |= IORESOURCE_BUSY;
insert_resource(&iomem_resource, res);
x86: Clean up late e820 resource allocation This makes the late e820 resources use 'insert_resource_expand_to_fit()' instead of doing a 'reserve_region_with_split()', and also avoids marking them as IORESOURCE_BUSY. This results in us being perfectly happy to use pre-existing PCI resources even if they were marked as being in a reserved region, while still avoiding any _new_ allocations in the reserved regions. It also makes for a simpler and more accurate resource tree. Example resource allocation from Jonathan Corbet, who has firmware that has an e820 reserved entry that covered a big range (e0000000-fed003ff), and that had various PCI resources in it set up by firmware. With old kernels, the reserved range would force us to re-allocate all pre-existing PCI resources, and his reserved range would end up looking like this: e0000000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 where only the pre-allocated special regions (IOAPIC and HPET) were kept around. With 2.6.28-rc2, which uses 'reserve_region_with_split()', Jonathan's resource tree looked like this: e0000000-fe7fffff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe800000-fe8fffff : reserved fe900000-fe9d9aff : reserved fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9b00-fe9d9bff : reserved fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : reserved fe9da000-fe9dafff : 0000:00:03.3 fe9da000-fe9dafff : reserved fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : reserved fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : reserved fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : reserved fea00000-fea7ffff : 0000:00:02.0 fea00000-fea7ffff : reserved fea80000-feafffff : 0000:00:02.1 fea80000-feafffff : reserved feb00000-febfffff : 0000:00:02.0 feb00000-febfffff : reserved fec00000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 and because the reserved entry had been split and moved into the individual resources, and because it used the IORESOURCE_BUSY flag, the drivers that actually wanted to _use_ those resources couldn't actually attach to them: e1000e 0000:00:19.0: BAR 0: can't reserve mem region [0xfe9e0000-0xfe9fffff] HDA Intel 0000:00:1b.0: BAR 0: can't reserve mem region [0xfe9dc000-0xfe9dffff] with this patch, the resource tree instead becomes e0000000-fed003ff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : ehci_hcd fe9da000-fe9dafff : 0000:00:03.3 fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : e1000e fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : ICH HD audio fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : e1000e fea00000-fea7ffff : 0000:00:02.0 fea80000-feafffff : 0000:00:02.1 feb00000-febfffff : 0000:00:02.0 fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 ie the one reserved region now ends up surrounding all the PCI resources that were allocated inside of it by firmware, and because it is not marked BUSY, drivers have no problem attaching to the pre-allocated resources. Reported-and-tested-by: Jonathan Corbet <corbet@lwn.net> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-01 17:17:22 +00:00
}
res++;
}
for (i = 0; i < e820_saved.nr_map; i++) {
struct e820entry *entry = &e820_saved.map[i];
firmware_map_add_early(entry->addr,
entry->addr + entry->size - 1,
e820_type_to_string(entry->type));
}
}
/* How much should we pad RAM ending depending on where it is? */
static unsigned long ram_alignment(resource_size_t pos)
{
unsigned long mb = pos >> 20;
/* To 64kB in the first megabyte */
if (!mb)
return 64*1024;
/* To 1MB in the first 16MB */
if (mb < 16)
return 1024*1024;
/* To 64MB for anything above that */
return 64*1024*1024;
}
#define MAX_RESOURCE_SIZE ((resource_size_t)-1)
void __init e820_reserve_resources_late(void)
{
int i;
struct resource *res;
res = e820_res;
for (i = 0; i < e820.nr_map; i++) {
if (!res->parent && res->end)
x86: Clean up late e820 resource allocation This makes the late e820 resources use 'insert_resource_expand_to_fit()' instead of doing a 'reserve_region_with_split()', and also avoids marking them as IORESOURCE_BUSY. This results in us being perfectly happy to use pre-existing PCI resources even if they were marked as being in a reserved region, while still avoiding any _new_ allocations in the reserved regions. It also makes for a simpler and more accurate resource tree. Example resource allocation from Jonathan Corbet, who has firmware that has an e820 reserved entry that covered a big range (e0000000-fed003ff), and that had various PCI resources in it set up by firmware. With old kernels, the reserved range would force us to re-allocate all pre-existing PCI resources, and his reserved range would end up looking like this: e0000000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 where only the pre-allocated special regions (IOAPIC and HPET) were kept around. With 2.6.28-rc2, which uses 'reserve_region_with_split()', Jonathan's resource tree looked like this: e0000000-fe7fffff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe800000-fe8fffff : reserved fe900000-fe9d9aff : reserved fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9b00-fe9d9bff : reserved fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : reserved fe9da000-fe9dafff : 0000:00:03.3 fe9da000-fe9dafff : reserved fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : reserved fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : reserved fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : reserved fea00000-fea7ffff : 0000:00:02.0 fea00000-fea7ffff : reserved fea80000-feafffff : 0000:00:02.1 fea80000-feafffff : reserved feb00000-febfffff : 0000:00:02.0 feb00000-febfffff : reserved fec00000-fed003ff : reserved fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 and because the reserved entry had been split and moved into the individual resources, and because it used the IORESOURCE_BUSY flag, the drivers that actually wanted to _use_ those resources couldn't actually attach to them: e1000e 0000:00:19.0: BAR 0: can't reserve mem region [0xfe9e0000-0xfe9fffff] HDA Intel 0000:00:1b.0: BAR 0: can't reserve mem region [0xfe9dc000-0xfe9dffff] with this patch, the resource tree instead becomes e0000000-fed003ff : reserved fe800000-fe8fffff : PCI Bus 0000:01 fe9d9b00-fe9d9bff : 0000:00:1f.3 fe9d9c00-fe9d9fff : 0000:00:1a.7 fe9d9c00-fe9d9fff : ehci_hcd fe9da000-fe9dafff : 0000:00:03.3 fe9db000-fe9dbfff : 0000:00:19.0 fe9db000-fe9dbfff : e1000e fe9dc000-fe9dffff : 0000:00:1b.0 fe9dc000-fe9dffff : ICH HD audio fe9e0000-fe9fffff : 0000:00:19.0 fe9e0000-fe9fffff : e1000e fea00000-fea7ffff : 0000:00:02.0 fea80000-feafffff : 0000:00:02.1 feb00000-febfffff : 0000:00:02.0 fec00000-fec00fff : IOAPIC 0 fed00000-fed003ff : HPET 0 ie the one reserved region now ends up surrounding all the PCI resources that were allocated inside of it by firmware, and because it is not marked BUSY, drivers have no problem attaching to the pre-allocated resources. Reported-and-tested-by: Jonathan Corbet <corbet@lwn.net> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-01 17:17:22 +00:00
insert_resource_expand_to_fit(&iomem_resource, res);
res++;
}
/*
* Try to bump up RAM regions to reasonable boundaries to
* avoid stolen RAM:
*/
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *entry = &e820.map[i];
u64 start, end;
if (entry->type != E820_RAM)
continue;
start = entry->addr + entry->size;
end = round_up(start, ram_alignment(start)) - 1;
if (end > MAX_RESOURCE_SIZE)
end = MAX_RESOURCE_SIZE;
if (start >= end)
continue;
printk(KERN_DEBUG "reserve RAM buffer: %016llx - %016llx ",
start, end);
reserve_region_with_split(&iomem_resource, start, end,
"RAM buffer");
}
}
char *__init default_machine_specific_memory_setup(void)
{
char *who = "BIOS-e820";
u32 new_nr;
/*
* Try to copy the BIOS-supplied E820-map.
*
* Otherwise fake a memory map; one section from 0k->640k,
* the next section from 1mb->appropriate_mem_k
*/
new_nr = boot_params.e820_entries;
sanitize_e820_map(boot_params.e820_map,
ARRAY_SIZE(boot_params.e820_map),
&new_nr);
boot_params.e820_entries = new_nr;
if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
< 0) {
u64 mem_size;
/* compare results from other methods and take the greater */
if (boot_params.alt_mem_k
< boot_params.screen_info.ext_mem_k) {
mem_size = boot_params.screen_info.ext_mem_k;
who = "BIOS-88";
} else {
mem_size = boot_params.alt_mem_k;
who = "BIOS-e801";
}
e820.nr_map = 0;
e820_add_region(0, LOWMEMSIZE(), E820_RAM);
e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
}
/* In case someone cares... */
return who;
}
void __init setup_memory_map(void)
{
char *who;
who = x86_init.resources.memory_setup();
memcpy(&e820_saved, &e820, sizeof(struct e820map));
printk(KERN_INFO "BIOS-provided physical RAM map:\n");
e820_print_map(who);
}
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-25 20:39:17 +00:00
void __init memblock_x86_fill(void)
{
int i;
u64 end;
/*
* EFI may have more than 128 entries
* We are safe to enable resizing, beause memblock_x86_fill()
* is rather later for x86
*/
memblock: s/memblock_analyze()/memblock_allow_resize()/ and update users The only function of memblock_analyze() is now allowing resize of memblock region arrays. Rename it to memblock_allow_resize() and update its users. * The following users remain the same other than renaming. arm/mm/init.c::arm_memblock_init() microblaze/kernel/prom.c::early_init_devtree() powerpc/kernel/prom.c::early_init_devtree() openrisc/kernel/prom.c::early_init_devtree() sh/mm/init.c::paging_init() sparc/mm/init_64.c::paging_init() unicore32/mm/init.c::uc32_memblock_init() * In the following users, analyze was used to update total size which is no longer necessary. powerpc/kernel/machine_kexec.c::reserve_crashkernel() powerpc/kernel/prom.c::early_init_devtree() powerpc/mm/init_32.c::MMU_init() powerpc/mm/tlb_nohash.c::__early_init_mmu() powerpc/platforms/ps3/mm.c::ps3_mm_add_memory() powerpc/platforms/embedded6xx/wii.c::wii_memory_fixups() sh/kernel/machine_kexec.c::reserve_crashkernel() * x86/kernel/e820.c::memblock_x86_fill() was directly setting memblock_can_resize before populating memblock and calling analyze afterwards. Call memblock_allow_resize() before start populating. memblock_can_resize is now static inside memblock.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: "H. Peter Anvin" <hpa@zytor.com>
2011-12-08 18:22:08 +00:00
memblock_allow_resize();
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-25 20:39:17 +00:00
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
end = ei->addr + ei->size;
if (end != (resource_size_t)end)
continue;
if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
continue;
memblock_add(ei->addr, ei->size);
}
memblock_dump_all();
}
void __init memblock_find_dma_reserve(void)
{
#ifdef CONFIG_X86_64
u64 nr_pages = 0, nr_free_pages = 0;
unsigned long start_pfn, end_pfn;
phys_addr_t start, end;
int i;
u64 u;
/*
* need to find out used area below MAX_DMA_PFN
* need to use memblock to get free size in [0, MAX_DMA_PFN]
* at first, and assume boot_mem will not take below MAX_DMA_PFN
*/
for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN);
end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN);
nr_pages += end_pfn - start_pfn;
}
for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) {
start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
if (start_pfn < end_pfn)
nr_free_pages += end_pfn - start_pfn;
}
set_dma_reserve(nr_pages - nr_free_pages);
#endif
}