#include <linux/mm.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
+#include <linux/firmware-map.h>
#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/setup.h>
#include <asm/trampoline.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;
/*
* Add a memory region to the kernel e820 map.
*/
-void __init add_memory_region(u64 start, u64 size, int type)
+static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
+ int type)
{
- int x = e820.nr_map;
+ int x = e820x->nr_map;
- if (x == ARRAY_SIZE(e820.map)) {
+ if (x >= ARRAY_SIZE(e820x->map)) {
printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
return;
}
- e820.map[x].addr = start;
- e820.map[x].size = size;
- e820.map[x].type = type;
- e820.nr_map++;
+ 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)
(unsigned long long) e820.map[i].addr,
(unsigned long long)
(e820.map[i].addr + e820.map[i].size));
- switch (e820.map[i].type) {
- case E820_RAM:
- printk(KERN_CONT "(usable)\n");
- break;
- case E820_RESERVED:
- printk(KERN_CONT "(reserved)\n");
- break;
- case E820_ACPI:
- printk(KERN_CONT "(ACPI data)\n");
- break;
- case E820_NVS:
- printk(KERN_CONT "(ACPI NVS)\n");
- break;
- default:
- printk(KERN_CONT "type %u\n", e820.map[i].type);
- break;
- }
+ e820_print_type(e820.map[i].type);
+ printk(KERN_CONT "\n");
}
}
*/
int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
- int *pnr_map)
+ u32 *pnr_map)
{
struct change_member {
struct e820entry *pbios; /* pointer to original bios entry */
unsigned long long addr; /* address for this change point */
};
-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;
+ 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;
struct change_member *change_tmp;
unsigned long current_type, last_type;
unsigned long long last_addr;
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.
*
* 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.
*/
-int __init copy_e820_map(struct e820entry *biosmap, int nr_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;
- do {
- u64 start = biosmap->addr;
- u64 size = biosmap->size;
- u64 end = start + size;
- u32 type = biosmap->type;
+ return __append_e820_map(biosmap, nr_map);
+}
- /* Overflow in 64 bits? Ignore the memory map. */
- if (start > end)
- return -1;
+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;
- add_memory_region(start, size, type);
- } while (biosmap++, --nr_map);
- return 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);
}
-u64 __init update_memory_range(u64 start, u64 size, unsigned old_type,
- unsigned 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 real_updated_size = 0;
+ u64 real_removed_size = 0;
- BUG_ON(old_type == new_type);
+ if (size > (ULLONG_MAX - start))
+ size = ULLONG_MAX - start;
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
u64 final_start, final_end;
- if (ei->type != old_type)
+
+ if (checktype && ei->type != old_type)
continue;
/* totally covered? */
if (ei->addr >= start &&
(ei->addr + ei->size) <= (start + size)) {
- ei->type = new_type;
- real_updated_size += ei->size;
+ real_removed_size += ei->size;
+ memset(ei, 0, sizeof(struct e820entry));
continue;
}
/* partially covered */
final_end = min(start + size, ei->addr + ei->size);
if (final_start >= final_end)
continue;
- add_memory_region(final_start, final_end - final_start,
- new_type);
- real_updated_size += final_end - final_start;
+ real_removed_size += final_end - final_start;
+
+ ei->size -= final_end - final_start;
+ if (ei->addr < final_start)
+ continue;
+ ei->addr = final_end;
}
- return real_updated_size;
+ return real_removed_size;
}
void __init update_e820(void)
{
- int nr_map;
+ u32 nr_map;
nr_map = e820.nr_map;
if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.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 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.
+ * Search for a gap in the e820 memory space from start_addr to end_addr.
*/
-__init void e820_setup_gap(void)
+__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
+ unsigned long start_addr, unsigned long long end_addr)
{
- unsigned long gapstart, gapsize, round;
unsigned long long last;
- int i;
+ int i = e820.nr_map;
int found = 0;
- last = 0x100000000ull;
- gapstart = 0x10000000;
- gapsize = 0x400000;
- i = e820.nr_map;
+ 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;
+ 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 = (end_pfn << PAGE_SHIFT) + 1024*1024;
- printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit "
- "address range\n"
- KERN_ERR "PCI: Unassigned devices with 32bit resource "
- "registers may break!\n");
+ 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
/*
- * See how much we want to round up: start off with
- * rounding to the next 1MB area.
+ * e820_reserve_resources_late protect stolen RAM already
*/
- round = 0x100000;
- while ((gapsize >> 4) > round)
- round += round;
- /* Fun with two's complement */
- pci_mem_start = (gapstart + round) & -round;
+ 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, unsigned long pa_data)
+{
+ u32 map_len;
+ int entries;
+ struct e820entry *extmap;
+
+ entries = sdata->len / sizeof(struct e820entry);
+ map_len = sdata->len + sizeof(struct setup_data);
+ if (map_len > PAGE_SIZE)
+ sdata = early_ioremap(pa_data, map_len);
+ extmap = (struct e820entry *)(sdata->data);
+ __append_e820_map(extmap, entries);
+ sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ if (map_len > PAGE_SIZE)
+ early_iounmap(sdata, map_len);
+ printk(KERN_INFO "extended physical RAM map:\n");
+ e820_print_map("extended");
+}
+
#if defined(CONFIG_X86_64) || \
(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
/**
register_nosave_region(pfn, PFN_UP(ei->addr));
pfn = PFN_DOWN(ei->addr + ei->size);
- if (ei->type != E820_RAM)
+ if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
register_nosave_region(PFN_UP(ei->addr), pfn);
if (pfn >= limit_pfn)
}
#endif
+#ifdef CONFIG_HIBERNATION
+/**
+ * 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)
+ hibernate_nvs_register(ei->addr, ei->size);
+ }
+
+ return 0;
+}
+core_initcall(e820_mark_nvs_memory);
+#endif
+
/*
* Early reserved memory areas.
*/
struct early_res {
u64 start, end;
char name[16];
+ char overlap_ok;
};
static struct early_res early_res[MAX_EARLY_RES] __initdata = {
{ 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_TRAMPOLINE)
- { TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
-#endif
-#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
- /*
- * But first pinch a few for the stack/trampoline stuff
- * FIXME: Don't need the extra page at 4K, but need to fix
- * trampoline before removing it. (see the GDT stuff)
- */
- { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE" },
- /*
- * Has to be in very low memory so we can execute
- * real-mode AP code.
- */
- { TRAMPOLINE_BASE, TRAMPOLINE_BASE + PAGE_SIZE, "TRAMPOLINE" },
-#endif
{}
};
return i;
}
-void __init reserve_early(u64 start, u64 end, char *name)
+/*
+ * Drop the i-th range from the early reservation map,
+ * by copying any higher ranges down one over it, and
+ * clearing what had been the last slot.
+ */
+static void __init drop_range(int i)
+{
+ int j;
+
+ for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
+ ;
+
+ memmove(&early_res[i], &early_res[i + 1],
+ (j - 1 - i) * sizeof(struct early_res));
+
+ early_res[j - 1].end = 0;
+}
+
+/*
+ * Split any existing ranges that:
+ * 1) are marked 'overlap_ok', and
+ * 2) overlap with the stated range [start, end)
+ * into whatever portion (if any) of the existing range is entirely
+ * below or entirely above the stated range. Drop the portion
+ * of the existing range that overlaps with the stated range,
+ * which will allow the caller of this routine to then add that
+ * stated range without conflicting with any existing range.
+ */
+static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+{
+ int i;
+ struct early_res *r;
+ u64 lower_start, lower_end;
+ u64 upper_start, upper_end;
+ char name[16];
+
+ for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+ r = &early_res[i];
+
+ /* Continue past non-overlapping ranges */
+ if (end <= r->start || start >= r->end)
+ continue;
+
+ /*
+ * Leave non-ok overlaps as is; let caller
+ * panic "Overlapping early reservations"
+ * when it hits this overlap.
+ */
+ if (!r->overlap_ok)
+ return;
+
+ /*
+ * We have an ok overlap. We will drop it from the early
+ * reservation map, and add back in any non-overlapping
+ * portions (lower or upper) as separate, overlap_ok,
+ * non-overlapping ranges.
+ */
+
+ /* 1. Note any non-overlapping (lower or upper) ranges. */
+ strncpy(name, r->name, sizeof(name) - 1);
+
+ lower_start = lower_end = 0;
+ upper_start = upper_end = 0;
+ if (r->start < start) {
+ lower_start = r->start;
+ lower_end = start;
+ }
+ if (r->end > end) {
+ upper_start = end;
+ upper_end = r->end;
+ }
+
+ /* 2. Drop the original ok overlapping range */
+ drop_range(i);
+
+ i--; /* resume for-loop on copied down entry */
+
+ /* 3. Add back in any non-overlapping ranges. */
+ if (lower_end)
+ reserve_early_overlap_ok(lower_start, lower_end, name);
+ if (upper_end)
+ reserve_early_overlap_ok(upper_start, upper_end, name);
+ }
+}
+
+static void __init __reserve_early(u64 start, u64 end, char *name,
+ int overlap_ok)
{
int i;
struct early_res *r;
r->end - 1, r->name);
r->start = start;
r->end = end;
+ r->overlap_ok = overlap_ok;
if (name)
strncpy(r->name, name, sizeof(r->name) - 1);
}
+/*
+ * A few early reservtations come here.
+ *
+ * The 'overlap_ok' in the name of this routine does -not- mean it
+ * is ok for these reservations to overlap an earlier reservation.
+ * Rather it means that it is ok for subsequent reservations to
+ * overlap this one.
+ *
+ * Use this entry point to reserve early ranges when you are doing
+ * so out of "Paranoia", reserving perhaps more memory than you need,
+ * just in case, and don't mind a subsequent overlapping reservation
+ * that is known to be needed.
+ *
+ * The drop_overlaps_that_are_ok() call here isn't really needed.
+ * It would be needed if we had two colliding 'overlap_ok'
+ * reservations, so that the second such would not panic on the
+ * overlap with the first. We don't have any such as of this
+ * writing, but might as well tolerate such if it happens in
+ * the future.
+ */
+void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
+{
+ drop_overlaps_that_are_ok(start, end);
+ __reserve_early(start, end, name, 1);
+}
+
+/*
+ * Most early reservations come here.
+ *
+ * We first have drop_overlaps_that_are_ok() drop any pre-existing
+ * 'overlap_ok' ranges, so that we can then reserve this memory
+ * range without risk of panic'ing on an overlapping overlap_ok
+ * early reservation.
+ */
+void __init reserve_early(u64 start, u64 end, char *name)
+{
+ if (start >= end)
+ return;
+
+ drop_overlaps_that_are_ok(start, end);
+ __reserve_early(start, end, name, 0);
+}
+
void __init free_early(u64 start, u64 end)
{
struct early_res *r;
- int i, j;
+ int i;
i = find_overlapped_early(start, end);
r = &early_res[i];
panic("free_early on not reserved area: %llx-%llx!",
start, end - 1);
- for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
- ;
-
- memmove(&early_res[i], &early_res[i + 1],
- (j - 1 - i) * sizeof(struct early_res));
-
- early_res[j - 1].end = 0;
-}
-
-int __init page_is_reserved_early(unsigned long pagenr)
-{
- u64 start = (u64)pagenr << PAGE_SHIFT;
- int i;
- struct early_res *r;
-
- i = find_overlapped_early(start, start + PAGE_SIZE);
- r = &early_res[i];
- return (i < MAX_EARLY_RES && r->end);
+ drop_range(i);
}
void __init early_res_to_bootmem(u64 start, u64 end)
{
- int i;
+ int i, count;
u64 final_start, final_end;
- for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+
+ count = 0;
+ for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++)
+ count++;
+
+ printk(KERN_INFO "(%d early reservations) ==> bootmem [%010llx - %010llx]\n",
+ count, start, end);
+ for (i = 0; i < count; i++) {
struct early_res *r = &early_res[i];
+ printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i,
+ r->start, r->end, r->name);
final_start = max(start, r->start);
final_end = min(end, r->end);
- if (final_start >= final_end)
+ if (final_start >= final_end) {
+ printk(KERN_CONT "\n");
continue;
- printk(KERN_INFO " early res: %d [%llx-%llx] %s\n", i,
- final_start, final_end - 1, r->name);
+ }
+ printk(KERN_CONT " ==> [%010llx - %010llx]\n",
+ final_start, final_end);
reserve_bootmem_generic(final_start, final_end - final_start,
BOOTMEM_DEFAULT);
}
continue;
return addr;
}
- return -1UL;
+ return -1ULL;
}
/*
u64 addr;
u64 start;
- start = startt;
- while (size < sizet)
+ for (start = startt; ; start += size) {
start = find_e820_area_size(start, &size, align);
+ if (!(start + 1))
+ return 0;
+ if (size >= sizet)
+ break;
+ }
- if (size < sizet)
+#ifdef CONFIG_X86_32
+ if (start >= MAXMEM)
return 0;
+ if (start + size > MAXMEM)
+ size = MAXMEM - start;
+#endif
addr = round_down(start + size - sizet, align);
- update_memory_range(addr, sizet, E820_RAM, E820_RESERVED);
+ if (addr < start)
+ return 0;
+ e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
+ e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
printk(KERN_INFO "update e820 for early_reserve_e820\n");
update_e820();
+ update_e820_saved();
return addr;
}
#endif
/*
- * Last pfn which the user wants to use.
- */
-unsigned long __initdata end_user_pfn = MAX_ARCH_PFN;
-
-/*
* Find the highest page frame number we have available
*/
-unsigned long __init e820_end_of_ram(void)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
{
- unsigned long last_pfn;
+ int i;
+ unsigned long last_pfn = 0;
unsigned long max_arch_pfn = MAX_ARCH_PFN;
- last_pfn = find_max_pfn_with_active_regions();
+ 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;
- if (last_pfn > end_user_pfn)
- last_pfn = end_user_pfn;
- printk(KERN_INFO "last_pfn = %lu max_arch_pfn = %lu\n",
+ 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);
+}
/*
* Finds an active region in the address range from start_pfn to last_pfn and
* returns its range in ei_startpfn and ei_endpfn for the e820 entry.
if (*ei_endpfn > last_pfn)
*ei_endpfn = last_pfn;
- /* Obey end_user_pfn to save on memmap */
- if (*ei_startpfn >= end_user_pfn)
- return 0;
- if (*ei_endpfn > end_user_pfn)
- *ei_endpfn = end_user_pfn;
-
return 1;
}
panic(msg);
}
+static int userdef __initdata;
+
/* "mem=nopentium" disables the 4MB page tables. */
static int __init parse_memopt(char *p)
{
}
#endif
+ userdef = 1;
mem_size = memparse(p, &p);
- end_user_pfn = mem_size>>PAGE_SHIFT;
+ e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+
return 0;
}
early_param("mem", parse_memopt);
-static int userdef __initdata;
-
static int __init parse_memmap_opt(char *p)
{
char *oldp;
u64 start_at, mem_size;
- if (!strcmp(p, "exactmap")) {
+ if (!p)
+ return -EINVAL;
+
+ 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.
*/
- e820_register_active_regions(0, 0, -1UL);
- saved_max_pfn = e820_end_of_ram();
- remove_all_active_ranges();
+ saved_max_pfn = e820_end_of_ram_pfn();
#endif
e820.nr_map = 0;
userdef = 1;
userdef = 1;
if (*p == '@') {
start_at = memparse(p+1, &p);
- add_memory_region(start_at, mem_size, E820_RAM);
+ e820_add_region(start_at, mem_size, E820_RAM);
} else if (*p == '#') {
start_at = memparse(p+1, &p);
- add_memory_region(start_at, mem_size, E820_ACPI);
+ e820_add_region(start_at, mem_size, E820_ACPI);
} else if (*p == '$') {
start_at = memparse(p+1, &p);
- add_memory_region(start_at, mem_size, E820_RESERVED);
- } else {
- end_user_pfn = (mem_size >> PAGE_SHIFT);
- }
+ 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) {
- int nr = e820.nr_map;
+ 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_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;
+
+ 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()
+ */
+ if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) {
+ res->flags |= IORESOURCE_BUSY;
+ insert_resource(&iomem_resource, res);
+ }
+ 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)
+ 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;
+ 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);
+}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff