Merge branch 'x86-bootmem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-bootmem-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
  early_res: Need to save the allocation name in drop_range_partial()
  sparsemem: Fix compilation on PowerPC
  early_res: Add free_early_partial()
  x86: Fix non-bootmem compilation on PowerPC
  core: Move early_res from arch/x86 to kernel/
  x86: Add find_fw_memmap_area
  Move round_up/down to kernel.h
  x86: Make 32bit support NO_BOOTMEM
  early_res: Enhance check_and_double_early_res
  x86: Move back find_e820_area to e820.c
  x86: Add find_early_area_size
  x86: Separate early_res related code from e820.c
  x86: Move bios page reserve early to head32/64.c
  sparsemem: Put mem map for one node together.
  sparsemem: Put usemap for one node together
  x86: Make 64 bit use early_res instead of bootmem before slab
  x86: Only call dma32_reserve_bootmem 64bit !CONFIG_NUMA
  x86: Make early_node_mem get mem > 4 GB if possible
  x86: Dynamically increase early_res array size
  x86: Introduce max_early_res and early_res_count
  ...
This commit is contained in:
Linus Torvalds
2010-03-03 08:15:05 -08:00
36 changed files with 1571 additions and 730 deletions

View File

@@ -14,8 +14,7 @@ obj-$(CONFIG_X86_VISWS) += visws.o
obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
obj-y += common.o early.o
obj-y += amd_bus.o
obj-$(CONFIG_X86_64) += bus_numa.o
obj-y += amd_bus.o bus_numa.o
ifeq ($(CONFIG_PCI_DEBUG),y)
EXTRA_CFLAGS += -DDEBUG

View File

@@ -2,11 +2,11 @@
#include <linux/pci.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/range.h>
#include <asm/pci_x86.h>
#ifdef CONFIG_X86_64
#include <asm/pci-direct.h>
#endif
#include "bus_numa.h"
@@ -15,60 +15,6 @@
* also get peer root bus resource for io,mmio
*/
#ifdef CONFIG_X86_64
#define RANGE_NUM 16
struct res_range {
size_t start;
size_t end;
};
static void __init update_range(struct res_range *range, size_t start,
size_t end)
{
int i;
int j;
for (j = 0; j < RANGE_NUM; j++) {
if (!range[j].end)
continue;
if (start <= range[j].start && end >= range[j].end) {
range[j].start = 0;
range[j].end = 0;
continue;
}
if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) {
range[j].start = end + 1;
continue;
}
if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) {
range[j].end = start - 1;
continue;
}
if (start > range[j].start && end < range[j].end) {
/* find the new spare */
for (i = 0; i < RANGE_NUM; i++) {
if (range[i].end == 0)
break;
}
if (i < RANGE_NUM) {
range[i].end = range[j].end;
range[i].start = end + 1;
} else {
printk(KERN_ERR "run of slot in ranges\n");
}
range[j].end = start - 1;
continue;
}
}
}
struct pci_hostbridge_probe {
u32 bus;
u32 slot;
@@ -111,6 +57,8 @@ static void __init get_pci_mmcfg_amd_fam10h_range(void)
fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
}
#define RANGE_NUM 16
/**
* early_fill_mp_bus_to_node()
* called before pcibios_scan_root and pci_scan_bus
@@ -130,16 +78,17 @@ static int __init early_fill_mp_bus_info(void)
struct pci_root_info *info;
u32 reg;
struct resource *res;
size_t start;
size_t end;
struct res_range range[RANGE_NUM];
u64 start;
u64 end;
struct range range[RANGE_NUM];
u64 val;
u32 address;
bool found;
if (!early_pci_allowed())
return -1;
found_all_numa_early = 0;
found = false;
for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
u32 id;
u16 device;
@@ -153,12 +102,12 @@ static int __init early_fill_mp_bus_info(void)
device = (id>>16) & 0xffff;
if (pci_probes[i].vendor == vendor &&
pci_probes[i].device == device) {
found_all_numa_early = 1;
found = true;
break;
}
}
if (!found_all_numa_early)
if (!found)
return 0;
pci_root_num = 0;
@@ -196,7 +145,7 @@ static int __init early_fill_mp_bus_info(void)
def_link = (reg >> 8) & 0x03;
memset(range, 0, sizeof(range));
range[0].end = 0xffff;
add_range(range, RANGE_NUM, 0, 0, 0xffff + 1);
/* io port resource */
for (i = 0; i < 4; i++) {
reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3));
@@ -220,13 +169,13 @@ static int __init early_fill_mp_bus_info(void)
info = &pci_root_info[j];
printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n",
node, link, (u64)start, (u64)end);
node, link, start, end);
/* kernel only handle 16 bit only */
if (end > 0xffff)
end = 0xffff;
update_res(info, start, end, IORESOURCE_IO, 1);
update_range(range, start, end);
subtract_range(range, RANGE_NUM, start, end + 1);
}
/* add left over io port range to def node/link, [0, 0xffff] */
/* find the position */
@@ -241,29 +190,32 @@ static int __init early_fill_mp_bus_info(void)
if (!range[i].end)
continue;
update_res(info, range[i].start, range[i].end,
update_res(info, range[i].start, range[i].end - 1,
IORESOURCE_IO, 1);
}
}
memset(range, 0, sizeof(range));
/* 0xfd00000000-0xffffffffff for HT */
range[0].end = (0xfdULL<<32) - 1;
end = cap_resource((0xfdULL<<32) - 1);
end++;
add_range(range, RANGE_NUM, 0, 0, end);
/* need to take out [0, TOM) for RAM*/
address = MSR_K8_TOP_MEM1;
rdmsrl(address, val);
end = (val & 0xffffff800000ULL);
printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20);
printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20);
if (end < (1ULL<<32))
update_range(range, 0, end - 1);
subtract_range(range, RANGE_NUM, 0, end);
/* get mmconfig */
get_pci_mmcfg_amd_fam10h_range();
/* need to take out mmconf range */
if (fam10h_mmconf_end) {
printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
update_range(range, fam10h_mmconf_start, fam10h_mmconf_end);
subtract_range(range, RANGE_NUM, fam10h_mmconf_start,
fam10h_mmconf_end + 1);
}
/* mmio resource */
@@ -293,7 +245,7 @@ static int __init early_fill_mp_bus_info(void)
info = &pci_root_info[j];
printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]",
node, link, (u64)start, (u64)end);
node, link, start, end);
/*
* some sick allocation would have range overlap with fam10h
* mmconf range, so need to update start and end.
@@ -318,14 +270,15 @@ static int __init early_fill_mp_bus_info(void)
/* we got a hole */
endx = fam10h_mmconf_start - 1;
update_res(info, start, endx, IORESOURCE_MEM, 0);
update_range(range, start, endx);
printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx);
subtract_range(range, RANGE_NUM, start,
endx + 1);
printk(KERN_CONT " ==> [%llx, %llx]", start, endx);
start = fam10h_mmconf_end + 1;
changed = 1;
}
if (changed) {
if (start <= end) {
printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", (u64)start, (u64)end);
printk(KERN_CONT " %s [%llx, %llx]", endx ? "and" : "==>", start, end);
} else {
printk(KERN_CONT "%s\n", endx?"":" ==> none");
continue;
@@ -333,8 +286,9 @@ static int __init early_fill_mp_bus_info(void)
}
}
update_res(info, start, end, IORESOURCE_MEM, 1);
update_range(range, start, end);
update_res(info, cap_resource(start), cap_resource(end),
IORESOURCE_MEM, 1);
subtract_range(range, RANGE_NUM, start, end + 1);
printk(KERN_CONT "\n");
}
@@ -348,8 +302,8 @@ static int __init early_fill_mp_bus_info(void)
address = MSR_K8_TOP_MEM2;
rdmsrl(address, val);
end = (val & 0xffffff800000ULL);
printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20);
update_range(range, 1ULL<<32, end - 1);
printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20);
subtract_range(range, RANGE_NUM, 1ULL<<32, end);
}
/*
@@ -368,7 +322,8 @@ static int __init early_fill_mp_bus_info(void)
if (!range[i].end)
continue;
update_res(info, range[i].start, range[i].end,
update_res(info, cap_resource(range[i].start),
cap_resource(range[i].end - 1),
IORESOURCE_MEM, 1);
}
}
@@ -384,24 +339,14 @@ static int __init early_fill_mp_bus_info(void)
info->bus_min, info->bus_max, info->node, info->link);
for (j = 0; j < res_num; j++) {
res = &info->res[j];
printk(KERN_DEBUG "bus: %02x index %x %s: [%llx, %llx]\n",
busnum, j,
(res->flags & IORESOURCE_IO)?"io port":"mmio",
res->start, res->end);
printk(KERN_DEBUG "bus: %02x index %x %pR\n",
busnum, j, res);
}
}
return 0;
}
#else /* !CONFIG_X86_64 */
static int __init early_fill_mp_bus_info(void) { return 0; }
#endif /* !CONFIG_X86_64 */
/* common 32/64 bit code */
#define ENABLE_CF8_EXT_CFG (1ULL << 46)
static void enable_pci_io_ecs(void *unused)

View File

@@ -1,11 +1,11 @@
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/range.h>
#include "bus_numa.h"
int pci_root_num;
struct pci_root_info pci_root_info[PCI_ROOT_NR];
int found_all_numa_early;
void x86_pci_root_bus_res_quirks(struct pci_bus *b)
{
@@ -21,10 +21,6 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
if (!pci_root_num)
return;
/* for amd, if only one root bus, don't need to do anything */
if (pci_root_num < 2 && found_all_numa_early)
return;
for (i = 0; i < pci_root_num; i++) {
if (pci_root_info[i].bus_min == b->number)
break;
@@ -52,8 +48,8 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
}
}
void __devinit update_res(struct pci_root_info *info, size_t start,
size_t end, unsigned long flags, int merge)
void __devinit update_res(struct pci_root_info *info, resource_size_t start,
resource_size_t end, unsigned long flags, int merge)
{
int i;
struct resource *res;
@@ -61,25 +57,28 @@ void __devinit update_res(struct pci_root_info *info, size_t start,
if (start > end)
return;
if (start == MAX_RESOURCE)
return;
if (!merge)
goto addit;
/* try to merge it with old one */
for (i = 0; i < info->res_num; i++) {
size_t final_start, final_end;
size_t common_start, common_end;
resource_size_t final_start, final_end;
resource_size_t common_start, common_end;
res = &info->res[i];
if (res->flags != flags)
continue;
common_start = max((size_t)res->start, start);
common_end = min((size_t)res->end, end);
common_start = max(res->start, start);
common_end = min(res->end, end);
if (common_start > common_end + 1)
continue;
final_start = min((size_t)res->start, start);
final_end = max((size_t)res->end, end);
final_start = min(res->start, start);
final_end = max(res->end, end);
res->start = final_start;
res->end = final_end;

View File

@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_64
#ifndef __BUS_NUMA_H
#define __BUS_NUMA_H
/*
* sub bus (transparent) will use entres from 3 to store extra from
* root, so need to make sure we have enough slot there.
@@ -19,8 +19,7 @@ struct pci_root_info {
#define PCI_ROOT_NR 4
extern int pci_root_num;
extern struct pci_root_info pci_root_info[PCI_ROOT_NR];
extern int found_all_numa_early;
extern void update_res(struct pci_root_info *info, size_t start,
size_t end, unsigned long flags, int merge);
extern void update_res(struct pci_root_info *info, resource_size_t start,
resource_size_t end, unsigned long flags, int merge);
#endif

View File

@@ -255,10 +255,6 @@ void __init pcibios_resource_survey(void)
*/
fs_initcall(pcibios_assign_resources);
void __weak x86_pci_root_bus_res_quirks(struct pci_bus *b)
{
}
/*
* If we set up a device for bus mastering, we need to check the latency
* timer as certain crappy BIOSes forget to set it properly.