summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-03-03 19:15:05 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2010-03-03 19:15:05 +0300
commita626b46e17d0762d664ce471d40bc506b6e721ab (patch)
tree445f6ac655ea9247d2e27529f23ba02d0991fec0 /arch/x86
parentc1dcb4bb1e3e16e9baee578d9bb040e5fba1063e (diff)
parentdce46a04d55d6358d2d4ab44a4946a19f9425fe2 (diff)
downloadlinux-a626b46e17d0762d664ce471d40bc506b6e721ab.tar.xz
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 ...
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig15
-rw-r--r--arch/x86/include/asm/e820.h5
-rw-r--r--arch/x86/include/asm/pci.h2
-rw-r--r--arch/x86/include/asm/pci_64.h2
-rw-r--r--arch/x86/include/asm/proto.h10
-rw-r--r--arch/x86/kernel/cpu/mtrr/cleanup.c208
-rw-r--r--arch/x86/kernel/e820.c349
-rw-r--r--arch/x86/kernel/head32.c10
-rw-r--r--arch/x86/kernel/mmconf-fam10h_64.c7
-rw-r--r--arch/x86/kernel/pci-dma.c13
-rw-r--r--arch/x86/kernel/setup.c10
-rw-r--r--arch/x86/kernel/setup_percpu.c6
-rw-r--r--arch/x86/mm/init_32.c7
-rw-r--r--arch/x86/mm/init_64.c9
-rw-r--r--arch/x86/mm/numa_32.c3
-rw-r--r--arch/x86/mm/numa_64.c97
-rw-r--r--arch/x86/pci/Makefile3
-rw-r--r--arch/x86/pci/amd_bus.c127
-rw-r--r--arch/x86/pci/bus_numa.c25
-rw-r--r--arch/x86/pci/bus_numa.h9
-rw-r--r--arch/x86/pci/i386.c4
21 files changed, 226 insertions, 695 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0896008f7509..57ccdcec1469 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -184,6 +184,9 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
+config HAVE_EARLY_RES
+ def_bool y
+
config HAVE_INTEL_TXT
def_bool y
depends on EXPERIMENTAL && DMAR && ACPI
@@ -569,6 +572,18 @@ config PARAVIRT_DEBUG
Enable to debug paravirt_ops internals. Specifically, BUG if
a paravirt_op is missing when it is called.
+config NO_BOOTMEM
+ default y
+ bool "Disable Bootmem code"
+ ---help---
+ Use early_res directly instead of bootmem before slab is ready.
+ - allocator (buddy) [generic]
+ - early allocator (bootmem) [generic]
+ - very early allocator (reserve_early*()) [x86]
+ - very very early allocator (early brk model) [x86]
+ So reduce one layer between early allocator to final allocator
+
+
config MEMTEST
bool "Memtest"
---help---
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 761249e396fe..0e22296790d3 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -111,11 +111,8 @@ extern unsigned long end_user_pfn;
extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+#include <linux/early_res.h>
extern unsigned long e820_end_of_ram_pfn(void);
extern unsigned long e820_end_of_low_ram_pfn(void);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index ada8c201d513..b4a00dd4eed5 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -124,6 +124,8 @@ extern void pci_iommu_alloc(void);
#include "pci_64.h"
#endif
+void dma32_reserve_bootmem(void);
+
/* implement the pci_ DMA API in terms of the generic device dma_ one */
#include <asm-generic/pci-dma-compat.h>
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index ae5e40f67daf..fe15cfb21b9b 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -22,8 +22,6 @@ extern int (*pci_config_read)(int seg, int bus, int dev, int fn,
extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
int reg, int len, u32 value);
-extern void dma32_reserve_bootmem(void);
-
#endif /* __KERNEL__ */
#endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 4009f6534f52..6f414ed88620 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -23,14 +23,4 @@ extern int reboot_force;
long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x,y) ((__typeof__(x))((y)-1))
-#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
-#define round_down(x,y) ((x) & ~__round_mask(x,y))
-
#endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 09b1698e0466..06130b52f012 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -22,10 +22,10 @@
#include <linux/pci.h>
#include <linux/smp.h>
#include <linux/cpu.h>
-#include <linux/sort.h>
#include <linux/mutex.h>
#include <linux/uaccess.h>
#include <linux/kvm_para.h>
+#include <linux/range.h>
#include <asm/processor.h>
#include <asm/e820.h>
@@ -34,11 +34,6 @@
#include "mtrr.h"
-struct res_range {
- unsigned long start;
- unsigned long end;
-};
-
struct var_mtrr_range_state {
unsigned long base_pfn;
unsigned long size_pfn;
@@ -56,7 +51,7 @@ struct var_mtrr_state {
/* Should be related to MTRR_VAR_RANGES nums */
#define RANGE_NUM 256
-static struct res_range __initdata range[RANGE_NUM];
+static struct range __initdata range[RANGE_NUM];
static int __initdata nr_range;
static struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
@@ -64,152 +59,11 @@ static struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
static int __initdata debug_print;
#define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0)
-
-static int __init
-add_range(struct res_range *range, int nr_range,
- unsigned long start, unsigned long end)
-{
- /* Out of slots: */
- if (nr_range >= RANGE_NUM)
- return nr_range;
-
- range[nr_range].start = start;
- range[nr_range].end = end;
-
- nr_range++;
-
- return nr_range;
-}
-
-static int __init
-add_range_with_merge(struct res_range *range, int nr_range,
- unsigned long start, unsigned long end)
-{
- int i;
-
- /* Try to merge it with old one: */
- for (i = 0; i < nr_range; i++) {
- unsigned long final_start, final_end;
- unsigned long common_start, common_end;
-
- if (!range[i].end)
- continue;
-
- common_start = max(range[i].start, start);
- common_end = min(range[i].end, end);
- if (common_start > common_end + 1)
- continue;
-
- final_start = min(range[i].start, start);
- final_end = max(range[i].end, end);
-
- range[i].start = final_start;
- range[i].end = final_end;
- return nr_range;
- }
-
- /* Need to add it: */
- return add_range(range, nr_range, start, end);
-}
-
-static void __init
-subtract_range(struct res_range *range, unsigned long start, unsigned long end)
-{
- int i, 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;
- }
- }
-}
-
-static int __init cmp_range(const void *x1, const void *x2)
-{
- const struct res_range *r1 = x1;
- const struct res_range *r2 = x2;
- long start1, start2;
-
- start1 = r1->start;
- start2 = r2->start;
-
- return start1 - start2;
-}
-
-static int __init clean_sort_range(struct res_range *range, int az)
-{
- int i, j, k = az - 1, nr_range = 0;
-
- for (i = 0; i < k; i++) {
- if (range[i].end)
- continue;
- for (j = k; j > i; j--) {
- if (range[j].end) {
- k = j;
- break;
- }
- }
- if (j == i)
- break;
- range[i].start = range[k].start;
- range[i].end = range[k].end;
- range[k].start = 0;
- range[k].end = 0;
- k--;
- }
- /* count it */
- for (i = 0; i < az; i++) {
- if (!range[i].end) {
- nr_range = i;
- break;
- }
- }
-
- /* sort them */
- sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
-
- return nr_range;
-}
-
#define BIOS_BUG_MSG KERN_WARNING \
"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
static int __init
-x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
+x86_get_mtrr_mem_range(struct range *range, int nr_range,
unsigned long extra_remove_base,
unsigned long extra_remove_size)
{
@@ -223,14 +77,14 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
continue;
base = range_state[i].base_pfn;
size = range_state[i].size_pfn;
- nr_range = add_range_with_merge(range, nr_range, base,
- base + size - 1);
+ nr_range = add_range_with_merge(range, RANGE_NUM, nr_range,
+ base, base + size);
}
if (debug_print) {
printk(KERN_DEBUG "After WB checking\n");
for (i = 0; i < nr_range; i++)
- printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
- range[i].start, range[i].end + 1);
+ printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+ range[i].start, range[i].end);
}
/* Take out UC ranges: */
@@ -252,19 +106,19 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
size -= (1<<(20-PAGE_SHIFT)) - base;
base = 1<<(20-PAGE_SHIFT);
}
- subtract_range(range, base, base + size - 1);
+ subtract_range(range, RANGE_NUM, base, base + size);
}
if (extra_remove_size)
- subtract_range(range, extra_remove_base,
- extra_remove_base + extra_remove_size - 1);
+ subtract_range(range, RANGE_NUM, extra_remove_base,
+ extra_remove_base + extra_remove_size);
if (debug_print) {
printk(KERN_DEBUG "After UC checking\n");
for (i = 0; i < RANGE_NUM; i++) {
if (!range[i].end)
continue;
- printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
- range[i].start, range[i].end + 1);
+ printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+ range[i].start, range[i].end);
}
}
@@ -273,26 +127,22 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
if (debug_print) {
printk(KERN_DEBUG "After sorting\n");
for (i = 0; i < nr_range; i++)
- printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
- range[i].start, range[i].end + 1);
+ printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+ range[i].start, range[i].end);
}
- /* clear those is not used */
- for (i = nr_range; i < RANGE_NUM; i++)
- memset(&range[i], 0, sizeof(range[i]));
-
return nr_range;
}
#ifdef CONFIG_MTRR_SANITIZER
-static unsigned long __init sum_ranges(struct res_range *range, int nr_range)
+static unsigned long __init sum_ranges(struct range *range, int nr_range)
{
unsigned long sum = 0;
int i;
for (i = 0; i < nr_range; i++)
- sum += range[i].end + 1 - range[i].start;
+ sum += range[i].end - range[i].start;
return sum;
}
@@ -621,7 +471,7 @@ static int __init parse_mtrr_spare_reg(char *arg)
early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg);
static int __init
-x86_setup_var_mtrrs(struct res_range *range, int nr_range,
+x86_setup_var_mtrrs(struct range *range, int nr_range,
u64 chunk_size, u64 gran_size)
{
struct var_mtrr_state var_state;
@@ -639,7 +489,7 @@ x86_setup_var_mtrrs(struct res_range *range, int nr_range,
/* Write the range: */
for (i = 0; i < nr_range; i++) {
set_var_mtrr_range(&var_state, range[i].start,
- range[i].end - range[i].start + 1);
+ range[i].end - range[i].start);
}
/* Write the last range: */
@@ -742,7 +592,7 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
unsigned long x_remove_base,
unsigned long x_remove_size, int i)
{
- static struct res_range range_new[RANGE_NUM];
+ static struct range range_new[RANGE_NUM];
unsigned long range_sums_new;
static int nr_range_new;
int num_reg;
@@ -869,10 +719,10 @@ int __init mtrr_cleanup(unsigned address_bits)
* [0, 1M) should always be covered by var mtrr with WB
* and fixed mtrrs should take effect before var mtrr for it:
*/
- nr_range = add_range_with_merge(range, nr_range, 0,
- (1ULL<<(20 - PAGE_SHIFT)) - 1);
+ nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
+ 1ULL<<(20 - PAGE_SHIFT));
/* Sort the ranges: */
- sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+ sort_range(range, nr_range);
range_sums = sum_ranges(range, nr_range);
printk(KERN_INFO "total RAM covered: %ldM\n",
@@ -1089,9 +939,9 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
nr_range = 0;
if (mtrr_tom2) {
range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT));
- range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1;
- if (highest_pfn < range[nr_range].end + 1)
- highest_pfn = range[nr_range].end + 1;
+ range[nr_range].end = mtrr_tom2 >> PAGE_SHIFT;
+ if (highest_pfn < range[nr_range].end)
+ highest_pfn = range[nr_range].end;
nr_range++;
}
nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0);
@@ -1103,15 +953,15 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
/* Check the holes: */
for (i = 0; i < nr_range - 1; i++) {
- if (range[i].end + 1 < range[i+1].start)
- total_trim_size += real_trim_memory(range[i].end + 1,
+ if (range[i].end < range[i+1].start)
+ total_trim_size += real_trim_memory(range[i].end,
range[i+1].start);
}
/* Check the top: */
i = nr_range - 1;
- if (range[i].end + 1 < end_pfn)
- total_trim_size += real_trim_memory(range[i].end + 1,
+ if (range[i].end < end_pfn)
+ total_trim_size += real_trim_memory(range[i].end,
end_pfn);
if (total_trim_size) {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index a966b753e496..740b440fbd73 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -12,21 +12,13 @@
#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/pfn.h>
#include <linux/suspend.h>
#include <linux/firmware-map.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/setup.h>
-#include <asm/trampoline.h>
/*
* The e820 map is the map that gets modified e.g. with command line parameters
@@ -730,319 +722,44 @@ core_initcall(e820_mark_nvs_memory);
#endif
/*
- * Early reserved memory areas.
- */
-#define MAX_EARLY_RES 32
-
-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", 1 }, /* BIOS data page */
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE)
- /*
- * 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", 1 },
-#endif
-
- {}
-};
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
- 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)
- break;
- }
-
- return i;
-}
-
-/*
- * 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.
+ * Find a free area with specified alignment in a specific range.
*/
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
{
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];
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ u64 addr;
+ u64 ei_start, ei_last;
- /* Continue past non-overlapping ranges */
- if (end <= r->start || start >= r->end)
+ if (ei->type != E820_RAM)
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;
-
- i = find_overlapped_early(start, end);
- if (i >= MAX_EARLY_RES)
- panic("Too many early reservations");
- r = &early_res[i];
- if (r->end)
- panic("Overlapping early reservations "
- "%llx-%llx %s to %llx-%llx %s\n",
- start, end - 1, name?name:"", r->start,
- 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;
-
- i = find_overlapped_early(start, end);
- r = &early_res[i];
- if (i >= MAX_EARLY_RES || r->end != end || r->start != start)
- panic("free_early on not reserved area: %llx-%llx!",
- start, end - 1);
-
- drop_range(i);
-}
-
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
- int i, count;
- u64 final_start, final_end;
-
- 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) {
- printk(KERN_CONT "\n");
- continue;
- }
- printk(KERN_CONT " ==> [%010llx - %010llx]\n",
- final_start, final_end);
- reserve_bootmem_generic(final_start, final_end - final_start,
- BOOTMEM_DEFAULT);
- }
-}
+ ei_last = ei->addr + ei->size;
+ ei_start = ei->addr;
+ addr = find_early_area(ei_start, ei_last, start, end,
+ size, align);
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
- int i;
- u64 addr = *addrp;
- int changed = 0;
- struct early_res *r;
-again:
- i = find_overlapped_early(addr, addr + size);
- r = &early_res[i];
- if (i < MAX_EARLY_RES && r->end) {
- *addrp = addr = round_up(r->end, align);
- changed = 1;
- goto again;
+ if (addr != -1ULL)
+ return addr;
}
- return changed;
+ return -1ULL;
}
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
{
- int i;
- u64 addr = *addrp, last;
- u64 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;
+ return find_e820_area(start, end, size, align);
}
-/*
- * Find a free area with specified alignment in a specific range.
- */
-u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
+u64 __init get_max_mapped(void)
{
- int i;
+ u64 end = max_pfn_mapped;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
- u64 addr, last;
- u64 ei_last;
+ end <<= PAGE_SHIFT;
- 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)
- ;
- last = addr + size;
- if (last > ei_last)
- continue;
- if (last > end)
- continue;
- return addr;
- }
- return -1ULL;
+ return end;
}
-
/*
* Find next free range after *start
*/
@@ -1052,25 +769,19 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
- u64 addr, last;
- u64 ei_last;
+ u64 addr;
+ u64 ei_start, 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;
+ ei_start = ei->addr;
+ addr = find_early_area_size(ei_start, ei_last, start,
+ sizep, align);
+
+ if (addr != -1ULL)
+ return addr;
}
return -1ULL;
@@ -1429,6 +1140,8 @@ void __init e820_reserve_resources_late(void)
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");
}
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 5051b94c9069..adedeef1dedc 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,6 +29,16 @@ static void __init i386_default_early_setup(void)
void __init i386_start_kernel(void)
{
+#ifdef CONFIG_X86_TRAMPOLINE
+ /*
+ * 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)
+ */
+ reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE,
+ "EX TRAMPOLINE");
+#endif
+
reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
#ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 712d15fdc416..71825806cd44 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -7,6 +7,8 @@
#include <linux/string.h>
#include <linux/pci.h>
#include <linux/dmi.h>
+#include <linux/range.h>
+
#include <asm/pci-direct.h>
#include <linux/sort.h>
#include <asm/io.h>
@@ -30,11 +32,6 @@ static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = {
{ 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 },
};
-struct range {
- u64 start;
- u64 end;
-};
-
static int __cpuinit cmp_range(const void *x1, const void *x2)
{
const struct range *r1 = x1;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 75e14e21f61a..1aa966c565f9 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -65,7 +65,7 @@ int dma_set_mask(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(dma_set_mask);
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_64) && !defined(CONFIG_NUMA)
static __initdata void *dma32_bootmem_ptr;
static unsigned long dma32_bootmem_size __initdata = (128ULL<<20);
@@ -116,14 +116,21 @@ static void __init dma32_free_bootmem(void)
dma32_bootmem_ptr = NULL;
dma32_bootmem_size = 0;
}
+#else
+void __init dma32_reserve_bootmem(void)
+{
+}
+static void __init dma32_free_bootmem(void)
+{
+}
+
#endif
void __init pci_iommu_alloc(void)
{
-#ifdef CONFIG_X86_64
/* free the range so iommu could get some range less than 4G */
dma32_free_bootmem();
-#endif
+
if (pci_swiotlb_detect())
goto out;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cb42109a55b4..5d7ba1a449bd 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -969,15 +969,11 @@ void __init setup_arch(char **cmdline_p)
#endif
initmem_init(0, max_pfn, acpi, k8);
+#ifndef CONFIG_NO_BOOTMEM
+ early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+#endif
-#ifdef CONFIG_X86_64
- /*
- * dma32_reserve_bootmem() allocates bootmem which may conflict
- * with the crashkernel command line, so do that after
- * reserve_crashkernel()
- */
dma32_reserve_bootmem();
-#endif
reserve_ibft_region();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 35abcb8b00e9..ef6370b00e70 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -137,7 +137,13 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
static void __init pcpu_fc_free(void *ptr, size_t size)
{
+#ifdef CONFIG_NO_BOOTMEM
+ u64 start = __pa(ptr);
+ u64 end = start + size;
+ free_early_partial(start, end);
+#else
free_bootmem(__pa(ptr), size);
+#endif
}
static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2226f2c70ea3..5cb3f0f54f47 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -750,6 +750,7 @@ static void __init zone_sizes_init(void)
free_area_init_nodes(max_zone_pfns);
}
+#ifndef CONFIG_NO_BOOTMEM
static unsigned long __init setup_node_bootmem(int nodeid,
unsigned long start_pfn,
unsigned long end_pfn,
@@ -766,13 +767,14 @@ static unsigned long __init setup_node_bootmem(int nodeid,
printk(KERN_INFO " node %d bootmap %08lx - %08lx\n",
nodeid, bootmap, bootmap + bootmap_size);
free_bootmem_with_active_regions(nodeid, end_pfn);
- early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
return bootmap + bootmap_size;
}
+#endif
void __init setup_bootmem_allocator(void)
{
+#ifndef CONFIG_NO_BOOTMEM
int nodeid;
unsigned long bootmap_size, bootmap;
/*
@@ -784,11 +786,13 @@ void __init setup_bootmem_allocator(void)
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+#endif
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
+#ifndef CONFIG_NO_BOOTMEM
for_each_online_node(nodeid) {
unsigned long start_pfn, end_pfn;
@@ -806,6 +810,7 @@ void __init setup_bootmem_allocator(void)
bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
bootmap);
}
+#endif
after_bootmem = 1;
}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 69ddfbd91135..e9b040e1cde5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -572,6 +572,7 @@ kernel_physical_mapping_init(unsigned long start,
void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
int acpi, int k8)
{
+#ifndef CONFIG_NO_BOOTMEM
unsigned long bootmap_size, bootmap;
bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
@@ -579,13 +580,15 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
PAGE_SIZE);
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
+ reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
/* don't touch min_low_pfn */
bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
0, end_pfn);
e820_register_active_regions(0, start_pfn, end_pfn);
free_bootmem_with_active_regions(0, end_pfn);
- early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
- reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
+#else
+ e820_register_active_regions(0, start_pfn, end_pfn);
+#endif
}
#endif
@@ -974,7 +977,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
if (pmd_none(*pmd)) {
pte_t entry;
- p = vmemmap_alloc_block(PMD_SIZE, node);
+ p = vmemmap_alloc_block_buf(PMD_SIZE, node);
if (!p)
return -ENOMEM;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index b20760ca7244..809baaaf48b1 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -418,7 +418,10 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
for_each_online_node(nid) {
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
+ NODE_DATA(nid)->node_id = nid;
+#ifndef CONFIG_NO_BOOTMEM
NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
+#endif
}
setup_bootmem_allocator();
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 3307ea8bd43a..8948f47fde05 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -163,30 +163,48 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
unsigned long end, unsigned long size,
unsigned long align)
{
- unsigned long mem = find_e820_area(start, end, size, align);
- void *ptr;
+ unsigned long mem;
+ /*
+ * put it on high as possible
+ * something will go with NODE_DATA
+ */
+ if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
+ start = MAX_DMA_PFN<<PAGE_SHIFT;
+ if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
+ end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+ start = MAX_DMA32_PFN<<PAGE_SHIFT;
+ mem = find_e820_area(start, end, size, align);
+ if (mem != -1L)
+ return __va(mem);
+
+ /* extend the search scope */
+ end = max_pfn_mapped << PAGE_SHIFT;
+ if (end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+ start = MAX_DMA32_PFN<<PAGE_SHIFT;
+ else
+ start = MAX_DMA_PFN<<PAGE_SHIFT;
+ mem = find_e820_area(start, end, size, align);
if (mem != -1L)
return __va(mem);
- ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
- if (ptr == NULL) {
- printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
+ printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
size, nodeid);
- return NULL;
- }
- return ptr;
+
+ return NULL;
}
/* Initialize bootmem allocator for a node */
void __init
setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
{
- unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+ unsigned long start_pfn, last_pfn, nodedata_phys;
const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
- unsigned long bootmap_start, nodedata_phys;
- void *bootmap;
int nid;
+#ifndef CONFIG_NO_BOOTMEM
+ unsigned long bootmap_start, bootmap_pages, bootmap_size;
+ void *bootmap;
+#endif
if (!end)
return;
@@ -200,7 +218,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
start = roundup(start, ZONE_ALIGN);
- printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
+ printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid,
start, end);
start_pfn = start >> PAGE_SHIFT;
@@ -211,14 +229,21 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
if (node_data[nodeid] == NULL)
return;
nodedata_phys = __pa(node_data[nodeid]);
+ reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
nodedata_phys + pgdat_size - 1);
+ nid = phys_to_nid(nodedata_phys);
+ if (nid != nodeid)
+ printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid);
memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
- NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+ NODE_DATA(nodeid)->node_id = nodeid;
NODE_DATA(nodeid)->node_start_pfn = start_pfn;
NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
+#ifndef CONFIG_NO_BOOTMEM
+ NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+
/*
* Find a place for the bootmem map
* nodedata_phys could be on other nodes by alloc_bootmem,
@@ -227,11 +252,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
* of alloc_bootmem, that could clash with reserved range
*/
bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
- nid = phys_to_nid(nodedata_phys);
- if (nid == nodeid)
- bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
- else
- bootmap_start = roundup(start, PAGE_SIZE);
+ bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
/*
* SMP_CACHE_BYTES could be enough, but init_bootmem_node like
* to use that to align to PAGE_SIZE
@@ -239,18 +260,13 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
bootmap = early_node_mem(nodeid, bootmap_start, end,
bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
if (bootmap == NULL) {
- if (nodedata_phys < start || nodedata_phys >= end) {
- /*
- * only need to free it if it is from other node
- * bootmem
- */
- if (nid != nodeid)
- free_bootmem(nodedata_phys, pgdat_size);
- }
+ free_early(nodedata_phys, nodedata_phys + pgdat_size);
node_data[nodeid] = NULL;
return;
}
bootmap_start = __pa(bootmap);
+ reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
+ "BOOTMAP");
bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
bootmap_start >> PAGE_SHIFT,
@@ -259,31 +275,12 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
printk(KERN_INFO " bootmap [%016lx - %016lx] pages %lx\n",
bootmap_start, bootmap_start + bootmap_size - 1,
bootmap_pages);
-
- free_bootmem_with_active_regions(nodeid, end);
-
- /*
- * convert early reserve to bootmem reserve earlier
- * otherwise early_node_mem could use early reserved mem
- * on previous node
- */
- early_res_to_bootmem(start, end);
-
- /*
- * in some case early_node_mem could use alloc_bootmem
- * to get range on other node, don't reserve that again
- */
- if (nid != nodeid)
- printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid);
- else
- reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys,
- pgdat_size, BOOTMEM_DEFAULT);
nid = phys_to_nid(bootmap_start);
if (nid != nodeid)
printk(KERN_INFO " bootmap(%d) on node %d\n", nodeid, nid);
- else
- reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
- bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+
+ free_bootmem_with_active_regions(nodeid, end);
+#endif
node_set_online(nodeid);
}
@@ -709,6 +706,10 @@ unsigned long __init numa_free_all_bootmem(void)
for_each_online_node(i)
pages += free_all_bootmem_node(NODE_DATA(i));
+#ifdef CONFIG_NO_BOOTMEM
+ pages += free_all_memory_core_early(MAX_NUMNODES);
+#endif
+
return pages;
}
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 39fba37f702f..0b7d3e9593e1 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -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
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 95ecbd495955..fc1e8fe07e5c 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -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)
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 12d54ff3654d..64a122883896 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -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;
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index 731b64ee8d84..804a4b40c31a 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -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
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 5a8fbf8d4cac..dece3eb9c906 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -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.