linux/arch/x86/kernel/e820_64.c

953 lines
24 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/bootmem.h>
#include <linux/ioport.h>
#include <linux/string.h>
#include <linux/kexec.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/suspend.h>
#include <linux/pfn.h>
#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/trampoline.h>
struct e820map e820;
/*
* PFN of last memory page.
*/
unsigned long end_pfn;
/*
* end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
* The direct mapping extends to max_pfn_mapped, so that we can directly access
* apertures, ACPI and other tables without having to play with fixmaps.
*/
unsigned long max_pfn_mapped;
/*
* Last pfn which the user wants to use.
*/
static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT;
/*
* Early reserved memory areas.
*/
#define MAX_EARLY_RES 20
struct early_res {
unsigned long start, end;
char name[16];
};
static struct early_res early_res[MAX_EARLY_RES] __initdata = {
{ 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */
#ifdef CONFIG_X86_TRAMPOLINE
{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
#endif
{}
};
void __init reserve_early(unsigned long start, unsigned long end, char *name)
{
int i;
struct early_res *r;
for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
r = &early_res[i];
if (end > r->start && start < r->end)
panic("Overlapping early reservations %lx-%lx %s to %lx-%lx %s\n",
start, end - 1, name?name:"", r->start, r->end - 1, r->name);
}
if (i >= MAX_EARLY_RES)
panic("Too many early reservations");
r = &early_res[i];
r->start = start;
r->end = end;
if (name)
strncpy(r->name, name, sizeof(r->name) - 1);
}
void __init free_early(unsigned long start, unsigned long end)
{
struct early_res *r;
int i, j;
for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
r = &early_res[i];
if (start == r->start && end == r->end)
break;
}
if (i >= MAX_EARLY_RES || !early_res[i].end)
panic("free_early on not reserved area: %lx-%lx!", start, end);
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;
}
void __init early_res_to_bootmem(unsigned long start, unsigned long end)
{
int i;
unsigned long final_start, final_end;
for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
struct early_res *r = &early_res[i];
final_start = max(start, r->start);
final_end = min(end, r->end);
if (final_start >= final_end)
continue;
printk(KERN_INFO " early res: %d [%lx-%lx] %s\n", i,
final_start, final_end - 1, r->name);
reserve_bootmem_generic(final_start, final_end - final_start);
}
}
/* Check for already reserved areas */
static inline int __init
bad_addr(unsigned long *addrp, unsigned long size, unsigned long align)
{
int i;
unsigned long addr = *addrp, last;
int changed = 0;
again:
last = addr + size;
for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
struct early_res *r = &early_res[i];
if (last >= r->start && addr < r->end) {
*addrp = addr = round_up(r->end, align);
changed = 1;
goto again;
}
}
return changed;
}
/* Check for already reserved areas */
static inline int __init
bad_addr_size(unsigned long *addrp, unsigned long *sizep, unsigned long align)
{
int i;
unsigned long addr = *addrp, last;
unsigned long size = *sizep;
int changed = 0;
again:
last = addr + size;
for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
struct early_res *r = &early_res[i];
if (last > r->start && addr < r->start) {
size = r->start - addr;
changed = 1;
goto again;
}
if (last > r->end && addr < r->end) {
addr = round_up(r->end, align);
size = last - addr;
changed = 1;
goto again;
}
if (last <= r->end && addr >= r->start) {
(*sizep)++;
return 0;
}
}
if (changed) {
*addrp = addr;
*sizep = size;
}
return changed;
}
/*
* This function checks if any part of the range <start,end> is mapped
* with type.
*/
int
e820_any_mapped(unsigned long start, unsigned long 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(unsigned long start, unsigned long 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;
}
/*
x86_64: make bootmap_start page align v6 boot oopses when a system has 64 or 128 GB of RAM installed: Calling initcall 0xffffffff80bc33b6: sctp_init+0x0/0x711() BUG: unable to handle kernel NULL pointer dereference at 000000000000005f IP: [<ffffffff802bfe55>] proc_register+0xe7/0x10f PGD 0 Oops: 0000 [1] SMP CPU 0 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.24-smp-g5a514e21-dirty #6 RIP: 0010:[<ffffffff802bfe55>] [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP: 0000:ffff810824c57e60 EFLAGS: 00010246 RAX: 000000000000d7d7 RBX: ffff811024c5fa80 RCX: ffff810824c57e08 RDX: 0000000000000000 RSI: 0000000000000195 RDI: ffffffff80cc2460 RBP: ffffffffffffffff R08: 0000000000000000 R09: ffff811024c5fa80 R10: 0000000000000000 R11: 0000000000000002 R12: ffff810824c57e6c R13: 0000000000000000 R14: ffff810824c57ee0 R15: 00000006abd25bee FS: 0000000000000000(0000) GS:ffffffff80b4d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000005f CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff810824c56000, task ffff812024c52000) Stack: ffffffff80a57348 0000019500000000 ffff811024c5fa80 0000000000000000 00000000ffffff97 ffffffff802bfef0 0000000000000000 ffffffffffffffff 0000000000000000 ffffffff80bc3b4b ffff810824c57ee0 ffffffff80bc34a5 Call Trace: [<ffffffff802bfef0>] ? create_proc_entry+0x73/0x8a [<ffffffff80bc3b4b>] ? sctp_snmp_proc_init+0x1c/0x34 [<ffffffff80bc34a5>] ? sctp_init+0xef/0x711 [<ffffffff80b976e3>] ? kernel_init+0x175/0x2e1 [<ffffffff8020ccf8>] ? child_rip+0xa/0x12 [<ffffffff80b9756e>] ? kernel_init+0x0/0x2e1 [<ffffffff8020ccee>] ? child_rip+0x0/0x12 Code: 1e 48 83 7b 38 00 75 08 48 c7 43 38 f0 e8 82 80 48 83 7b 30 00 75 08 48 c7 43 30 d0 e9 82 80 48 c7 c7 60 24 cc 80 e8 bd 5a 54 00 <48> 8b 45 60 48 89 6b 58 48 89 5d 60 48 89 43 50 fe 05 f5 25 a0 RIP [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP <ffff810824c57e60> CR2: 000000000000005f ---[ end trace 02c2d78def82877a ]--- Kernel panic - not syncing: Attempted to kill init! it turns out some variables near end of bss are corrupted already. in System.map we have ffffffff80d40420 b rsi_table ffffffff80d40620 B krb5_seq_lock ffffffff80d40628 b i.20437 ffffffff80d40630 b xprt_rdma_inline_write_padding ffffffff80d40638 b sunrpc_table_header ffffffff80d40640 b zero ffffffff80d40644 b min_memreg ffffffff80d40648 b rpcrdma_tk_lock_g ffffffff80d40650 B sctp_assocs_id_lock ffffffff80d40658 B proc_net_sctp ffffffff80d40660 B sctp_assocs_id ffffffff80d40680 B sysctl_sctp_mem ffffffff80d40690 B sysctl_sctp_rmem ffffffff80d406a0 B sysctl_sctp_wmem ffffffff80d406b0 b sctp_ctl_socket ffffffff80d406b8 b sctp_pf_inet6_specific ffffffff80d406c0 b sctp_pf_inet_specific ffffffff80d406c8 b sctp_af_v4_specific ffffffff80d406d0 b sctp_af_v6_specific ffffffff80d406d8 b sctp_rand.33270 ffffffff80d406dc b sctp_memory_pressure ffffffff80d406e0 b sctp_sockets_allocated ffffffff80d406e4 b sctp_memory_allocated ffffffff80d406e8 b sctp_sysctl_header ffffffff80d406f0 b zero ffffffff80d406f4 A __bss_stop ffffffff80d406f4 A _end and setup_node_bootmem() will use that page 0xd40000 for bootmap Bootmem setup node 0 0000000000000000-0000000828000000 NODE_DATA [000000000008a485 - 0000000000091484] bootmap [0000000000d406f4 - 0000000000e456f3] pages 105 Bootmem setup node 1 0000000828000000-0000001028000000 NODE_DATA [0000000828000000 - 0000000828006fff] bootmap [0000000828007000 - 0000000828106fff] pages 100 Bootmem setup node 2 0000001028000000-0000001828000000 NODE_DATA [0000001028000000 - 0000001028006fff] bootmap [0000001028007000 - 0000001028106fff] pages 100 Bootmem setup node 3 0000001828000000-0000002028000000 NODE_DATA [0000001828000000 - 0000001828006fff] bootmap [0000001828007000 - 0000001828106fff] pages 100 setup_node_bootmem() makes NODE_DATA cacheline aligned, and bootmap is page-aligned. the patch updates find_e820_area() to make sure we can meet the alignment constraints. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-02 00:49:41 +08:00
* Find a free area with specified alignment in a specific range.
*/
unsigned long __init find_e820_area(unsigned long start, unsigned long end,
unsigned long size, unsigned long align)
{
int i;
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
unsigned long addr, last;
unsigned long ei_last;
if (ei->type != E820_RAM)
continue;
addr = round_up(ei->addr, align);
ei_last = ei->addr + ei->size;
if (addr < start)
addr = round_up(start, align);
if (addr >= ei_last)
continue;
while (bad_addr(&addr, size, align) && addr+size <= ei_last)
;
x86_64: make bootmap_start page align v6 boot oopses when a system has 64 or 128 GB of RAM installed: Calling initcall 0xffffffff80bc33b6: sctp_init+0x0/0x711() BUG: unable to handle kernel NULL pointer dereference at 000000000000005f IP: [<ffffffff802bfe55>] proc_register+0xe7/0x10f PGD 0 Oops: 0000 [1] SMP CPU 0 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.24-smp-g5a514e21-dirty #6 RIP: 0010:[<ffffffff802bfe55>] [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP: 0000:ffff810824c57e60 EFLAGS: 00010246 RAX: 000000000000d7d7 RBX: ffff811024c5fa80 RCX: ffff810824c57e08 RDX: 0000000000000000 RSI: 0000000000000195 RDI: ffffffff80cc2460 RBP: ffffffffffffffff R08: 0000000000000000 R09: ffff811024c5fa80 R10: 0000000000000000 R11: 0000000000000002 R12: ffff810824c57e6c R13: 0000000000000000 R14: ffff810824c57ee0 R15: 00000006abd25bee FS: 0000000000000000(0000) GS:ffffffff80b4d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000005f CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff810824c56000, task ffff812024c52000) Stack: ffffffff80a57348 0000019500000000 ffff811024c5fa80 0000000000000000 00000000ffffff97 ffffffff802bfef0 0000000000000000 ffffffffffffffff 0000000000000000 ffffffff80bc3b4b ffff810824c57ee0 ffffffff80bc34a5 Call Trace: [<ffffffff802bfef0>] ? create_proc_entry+0x73/0x8a [<ffffffff80bc3b4b>] ? sctp_snmp_proc_init+0x1c/0x34 [<ffffffff80bc34a5>] ? sctp_init+0xef/0x711 [<ffffffff80b976e3>] ? kernel_init+0x175/0x2e1 [<ffffffff8020ccf8>] ? child_rip+0xa/0x12 [<ffffffff80b9756e>] ? kernel_init+0x0/0x2e1 [<ffffffff8020ccee>] ? child_rip+0x0/0x12 Code: 1e 48 83 7b 38 00 75 08 48 c7 43 38 f0 e8 82 80 48 83 7b 30 00 75 08 48 c7 43 30 d0 e9 82 80 48 c7 c7 60 24 cc 80 e8 bd 5a 54 00 <48> 8b 45 60 48 89 6b 58 48 89 5d 60 48 89 43 50 fe 05 f5 25 a0 RIP [<ffffffff802bfe55>] proc_register+0xe7/0x10f RSP <ffff810824c57e60> CR2: 000000000000005f ---[ end trace 02c2d78def82877a ]--- Kernel panic - not syncing: Attempted to kill init! it turns out some variables near end of bss are corrupted already. in System.map we have ffffffff80d40420 b rsi_table ffffffff80d40620 B krb5_seq_lock ffffffff80d40628 b i.20437 ffffffff80d40630 b xprt_rdma_inline_write_padding ffffffff80d40638 b sunrpc_table_header ffffffff80d40640 b zero ffffffff80d40644 b min_memreg ffffffff80d40648 b rpcrdma_tk_lock_g ffffffff80d40650 B sctp_assocs_id_lock ffffffff80d40658 B proc_net_sctp ffffffff80d40660 B sctp_assocs_id ffffffff80d40680 B sysctl_sctp_mem ffffffff80d40690 B sysctl_sctp_rmem ffffffff80d406a0 B sysctl_sctp_wmem ffffffff80d406b0 b sctp_ctl_socket ffffffff80d406b8 b sctp_pf_inet6_specific ffffffff80d406c0 b sctp_pf_inet_specific ffffffff80d406c8 b sctp_af_v4_specific ffffffff80d406d0 b sctp_af_v6_specific ffffffff80d406d8 b sctp_rand.33270 ffffffff80d406dc b sctp_memory_pressure ffffffff80d406e0 b sctp_sockets_allocated ffffffff80d406e4 b sctp_memory_allocated ffffffff80d406e8 b sctp_sysctl_header ffffffff80d406f0 b zero ffffffff80d406f4 A __bss_stop ffffffff80d406f4 A _end and setup_node_bootmem() will use that page 0xd40000 for bootmap Bootmem setup node 0 0000000000000000-0000000828000000 NODE_DATA [000000000008a485 - 0000000000091484] bootmap [0000000000d406f4 - 0000000000e456f3] pages 105 Bootmem setup node 1 0000000828000000-0000001028000000 NODE_DATA [0000000828000000 - 0000000828006fff] bootmap [0000000828007000 - 0000000828106fff] pages 100 Bootmem setup node 2 0000001028000000-0000001828000000 NODE_DATA [0000001028000000 - 0000001028006fff] bootmap [0000001028007000 - 0000001028106fff] pages 100 Bootmem setup node 3 0000001828000000-0000002028000000 NODE_DATA [0000001828000000 - 0000001828006fff] bootmap [0000001828007000 - 0000001828106fff] pages 100 setup_node_bootmem() makes NODE_DATA cacheline aligned, and bootmap is page-aligned. the patch updates find_e820_area() to make sure we can meet the alignment constraints. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-02 00:49:41 +08:00
last = addr + size;
if (last > ei_last)
continue;
if (last > end)
continue;
return addr;
}
return -1UL;
}
/*
* Find next free range after *start
*/
unsigned long __init find_e820_area_size(unsigned long start,
unsigned long *sizep,
unsigned long align)
{
int i;
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
unsigned long addr, last;
unsigned long ei_last;
if (ei->type != E820_RAM)
continue;
addr = round_up(ei->addr, align);
ei_last = ei->addr + ei->size;
if (addr < start)
addr = round_up(start, align);
if (addr >= ei_last)
continue;
*sizep = ei_last - addr;
while (bad_addr_size(&addr, sizep, align) &&
addr + *sizep <= ei_last)
;
last = addr + *sizep;
if (last > ei_last)
continue;
return addr;
}
return -1UL;
}
/*
* Find the highest page frame number we have available
*/
unsigned long __init e820_end_of_ram(void)
{
unsigned long end_pfn;
end_pfn = find_max_pfn_with_active_regions();
if (end_pfn > max_pfn_mapped)
max_pfn_mapped = end_pfn;
if (max_pfn_mapped > MAXMEM>>PAGE_SHIFT)
max_pfn_mapped = MAXMEM>>PAGE_SHIFT;
if (end_pfn > end_user_pfn)
end_pfn = end_user_pfn;
if (end_pfn > max_pfn_mapped)
end_pfn = max_pfn_mapped;
printk(KERN_INFO "max_pfn_mapped = %lu\n", max_pfn_mapped);
return end_pfn;
}
/*
* Mark e820 reserved areas as busy for the resource manager.
*/
void __init e820_reserve_resources(void)
{
int i;
struct resource *res;
res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map);
for (i = 0; i < e820.nr_map; i++) {
switch (e820.map[i].type) {
case E820_RAM: res->name = "System RAM"; break;
case E820_ACPI: res->name = "ACPI Tables"; break;
case E820_NVS: res->name = "ACPI Non-volatile Storage"; break;
default: res->name = "reserved";
}
res->start = e820.map[i].addr;
res->end = res->start + e820.map[i].size - 1;
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
insert_resource(&iomem_resource, res);
res++;
}
}
/*
* Find the ranges of physical addresses that do not correspond to
* e820 RAM areas and mark the corresponding pages as nosave for software
* suspend and suspend to RAM.
*
* 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(void)
{
int i;
unsigned long paddr;
paddr = round_down(e820.map[0].addr + e820.map[0].size, PAGE_SIZE);
for (i = 1; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
if (paddr < ei->addr)
register_nosave_region(PFN_DOWN(paddr),
PFN_UP(ei->addr));
paddr = round_down(ei->addr + ei->size, PAGE_SIZE);
if (ei->type != E820_RAM)
register_nosave_region(PFN_UP(ei->addr),
PFN_DOWN(paddr));
if (paddr >= (end_pfn << PAGE_SHIFT))
break;
}
}
/*
* Finds an active region in the address range from start_pfn to end_pfn and
* returns its range in ei_startpfn and ei_endpfn for the e820 entry.
*/
static int __init e820_find_active_region(const struct e820entry *ei,
unsigned long start_pfn,
unsigned long end_pfn,
unsigned long *ei_startpfn,
unsigned long *ei_endpfn)
{
*ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
*ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE) >> PAGE_SHIFT;
/* Skip map entries smaller than a page */
if (*ei_startpfn >= *ei_endpfn)
return 0;
/* Check if max_pfn_mapped should be updated */
if (ei->type != E820_RAM && *ei_endpfn > max_pfn_mapped)
max_pfn_mapped = *ei_endpfn;
/* Skip if map is outside the node */
if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
*ei_startpfn >= end_pfn)
return 0;
/* Check for overlaps */
if (*ei_startpfn < start_pfn)
*ei_startpfn = start_pfn;
if (*ei_endpfn > end_pfn)
*ei_endpfn = end_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;
}
/* Walk the e820 map and register active regions within a node */
void __init
e820_register_active_regions(int nid, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long ei_startpfn;
unsigned long ei_endpfn;
int i;
for (i = 0; i < e820.nr_map; i++)
if (e820_find_active_region(&e820.map[i],
start_pfn, end_pfn,
&ei_startpfn, &ei_endpfn))
add_active_range(nid, ei_startpfn, ei_endpfn);
}
/*
* Add a memory region to the kernel e820 map.
*/
void __init add_memory_region(unsigned long start, unsigned long size, int type)
{
int x = e820.nr_map;
if (x == E820MAX) {
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++;
}
/*
* Find the hole size (in bytes) in the memory range.
* @start: starting address of the memory range to scan
* @end: ending address of the memory range to scan
*/
unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long end_pfn = end >> PAGE_SHIFT;
unsigned long ei_startpfn, ei_endpfn, ram = 0;
int i;
for (i = 0; i < e820.nr_map; i++) {
if (e820_find_active_region(&e820.map[i],
start_pfn, end_pfn,
&ei_startpfn, &ei_endpfn))
ram += ei_endpfn - ei_startpfn;
}
return end - start - (ram << PAGE_SHIFT);
}
static 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));
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;
}
}
}
/*
* Sanitize the BIOS e820 map.
*
* Some e820 responses include overlapping entries. The following
* replaces the original e820 map with a new one, removing overlaps.
*
*/
static int __init sanitize_e820_map(struct e820entry *biosmap, char *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*E820MAX] __initdata;
static struct change_member *change_point[2*E820MAX] __initdata;
static struct e820entry *overlap_list[E820MAX] __initdata;
static struct e820entry new_bios[E820MAX] __initdata;
struct change_member *change_tmp;
unsigned long current_type, last_type;
unsigned long long last_addr;
int chgidx, still_changing;
int overlap_entries;
int new_bios_entry;
int old_nr, new_nr, chg_nr;
int i;
/*
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_
*/
/* if there's only one memory region, don't bother */
if (*pnr_map < 2)
return -1;
old_nr = *pnr_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) */
still_changing = 1;
while (still_changing) {
still_changing = 0;
for (i = 1; i < chg_nr; i++) {
unsigned long long curaddr, lastaddr;
unsigned long long curpbaddr, lastpbaddr;
curaddr = change_point[i]->addr;
lastaddr = change_point[i - 1]->addr;
curpbaddr = change_point[i]->pbios->addr;
lastpbaddr = change_point[i - 1]->pbios->addr;
/*
* swap entries, when:
*
* curaddr > lastaddr or
* curaddr == lastaddr and curaddr == curpbaddr and
* lastaddr != lastpbaddr
*/
if (curaddr < lastaddr ||
(curaddr == lastaddr && curaddr == curpbaddr &&
lastaddr != lastpbaddr)) {
change_tmp = change_point[i];
change_point[i] = change_point[i-1];
change_point[i-1] = change_tmp;
still_changing = 1;
}
}
}
/* 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 >= E820MAX)
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;
}
/*
* 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 copy_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;
/* Overflow in 64 bits? Ignore the memory map. */
if (start > end)
return -1;
add_memory_region(start, size, type);
} while (biosmap++, --nr_map);
return 0;
}
static void early_panic(char *msg)
{
early_printk(msg);
panic(msg);
}
/* We're not void only for x86 32-bit compat */
char * __init machine_specific_memory_setup(void)
{
char *who = "BIOS-e820";
/*
* 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
*/
sanitize_e820_map(boot_params.e820_map, &boot_params.e820_entries);
if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) < 0)
early_panic("Cannot find a valid memory map");
printk(KERN_INFO "BIOS-provided physical RAM map:\n");
e820_print_map(who);
/* In case someone cares... */
return who;
}
static int __init parse_memopt(char *p)
{
if (!p)
return -EINVAL;
end_user_pfn = memparse(p, &p);
end_user_pfn >>= PAGE_SHIFT;
return 0;
}
early_param("mem", parse_memopt);
static int userdef __initdata;
static int __init parse_memmap_opt(char *p)
{
char *oldp;
unsigned long long start_at, mem_size;
if (!strcmp(p, "exactmap")) {
#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();
#endif
max_pfn_mapped = 0;
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);
add_memory_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);
} 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);
}
return *p == '\0' ? 0 : -EINVAL;
}
early_param("memmap", parse_memmap_opt);
[PATCH] x86-64: fix section mismatch warnings Fix the following section mismatch warnings on x86_64: (build using defconfig) WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:mtrr_bp_init from .text between 'identify_cpu' (at offset 0x65eb) and 'IRQ0x20_interrupt' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data: from .text between 'finish_e820_parsing' (at offset 0x7dc2) and 'early_panic' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:e820_print_map from .text between 'finish_e820_parsing' (at offset 0x7de1) and 'early_panic' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:num_processors from .text between 'acpi_unmap_lsapic' (at offset 0xc88f) and 'acpi_register_ioapic' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:disabled_cpus from .text between 'MP_processor_info' (at offset 0x11f35) and 'mp_register_lapic' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:num_processors from .text between 'MP_processor_info' (at offset 0x11f6e) and 'mp_register_lapic' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:num_processors from .text between 'MP_processor_info' (at offset 0x11f93) and 'mp_register_lapic' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fix_aperture from .text between 'gart_parse_options' (at offset 0x15517) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fix_aperture from .text between 'gart_parse_options' (at offset 0x1552c) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x1553d) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x15552) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x15561) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x15577) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fallback_aper_force from .text between 'gart_parse_options' (at offset 0x1558a) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fallback_aper_order from .text between 'gart_parse_options' (at offset 0x155bf) and 'iommu_full' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:timer_over_8254 from .text between 'ati_bugs' (at offset 0x16344) and 'via_bugs' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:timer_over_8254 from .text between 'ati_bugs' (at offset 0x16356) and 'via_bugs' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'via_bugs' (at offset 0x16380) and 'nvidia_bugs' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_disabled from .text between 'via_bugs' (at offset 0x16397) and 'nvidia_bugs' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:acpi_use_timer_override from .text between 'nvidia_bugs' (at offset 0x163a7) and 'arch_unregister_cpu' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:nvidia_hpet_check from .text between 'nvidia_bugs' (at offset 0x163b1) and 'arch_unregister_cpu' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data: from .text between 'nvidia_bugs' (at offset 0x163be) and 'arch_unregister_cpu' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data: from .text between 'nvidia_bugs' (at offset 0x163d1) and 'arch_unregister_cpu' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:acpi_skip_timer_override from .text between 'nvidia_bugs' (at offset 0x163e1) and 'arch_unregister_cpu' WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:quirk_intel_irqbalance from .text between 'intel_bugs' (at offset 0x1633c) and 'ati_bugs' But adds: WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:get_mtrr_state from .text between 'mtrr_bp_init' (at offset 0xb887) and 'ipi_handler' The warnings does not show up during a normal build due to kbuild failing to check for section mismatch in vmlinux. To see these warnings run: scripts/mod/modpost arch/x86_64/kernel/built-in.o kbuild will be fixed but the 'noise-level' had to be decresed first. There remains a few section mismatch warnigns for x86_64 for areas where I did not feel confident. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andi Kleen <ak@suse.de>
2007-03-17 04:07:36 +08:00
void __init finish_e820_parsing(void)
{
if (userdef) {
char nr = e820.nr_map;
if (sanitize_e820_map(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");
}
}
void __init update_memory_range(u64 start, u64 size, unsigned old_type,
unsigned new_type)
{
int i;
BUG_ON(old_type == new_type);
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
u64 final_start, final_end;
if (ei->type != old_type)
continue;
/* totally covered? */
if (ei->addr >= start && ei->size <= size) {
ei->type = new_type;
continue;
}
/* partially covered */
final_start = max(start, ei->addr);
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);
}
}
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 20:33:09 +08:00
void __init update_e820(void)
{
u8 nr_map;
nr_map = e820.nr_map;
if (sanitize_e820_map(e820.map, &nr_map))
return;
e820.nr_map = nr_map;
printk(KERN_INFO "modified physical RAM map:\n");
e820_print_map("modified");
}
unsigned long pci_mem_start = 0xaeedbabe;
EXPORT_SYMBOL(pci_mem_start);
/*
* 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, round;
unsigned long last;
int i;
int found = 0;
last = 0x100000000ull;
gapstart = 0x10000000;
gapsize = 0x400000;
i = e820.nr_map;
while (--i >= 0) {
unsigned long long start = e820.map[i].addr;
unsigned long long end = start + e820.map[i].size;
/*
* 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;
}
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");
}
/*
* See how much we want to round up: start off with
* rounding to the next 1MB area.
*/
round = 0x100000;
while ((gapsize >> 4) > round)
round += round;
/* Fun with two's complement */
pci_mem_start = (gapstart + round) & -round;
printk(KERN_INFO
"Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
pci_mem_start, gapstart, gapsize);
}
int __init arch_get_ram_range(int slot, u64 *addr, u64 *size)
{
int i;
if (slot < 0 || slot >= e820.nr_map)
return -1;
for (i = slot; i < e820.nr_map; i++) {
if (e820.map[i].type != E820_RAM)
continue;
break;
}
if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT))
return -1;
*addr = e820.map[i].addr;
*size = min_t(u64, e820.map[i].size + e820.map[i].addr,
max_pfn << PAGE_SHIFT) - *addr;
return i + 1;
}