summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
authorH. Peter Anvin <hpa@linux.intel.com>2013-02-15 09:25:08 -0800
committerH. Peter Anvin <hpa@linux.intel.com>2013-02-15 09:25:08 -0800
commit0da3e7f526fde7a6522a3038b7ce609fc50f6707 (patch)
treec6e2dacd96fe7eac8312f3d7c22e0995dc423879 /arch/x86/kernel
parent95c9608478d639dcffc14ea47b31bff021a99ed1 (diff)
parent68d00bbebb5a48b7a9056a8c03476a71ecbc30a6 (diff)
Merge branch 'x86/mm2' into x86/mm
x86/mm2 is testing out fine, but has developed conflicts with x86/mm due to patches in adjacent code. Merge them so we can drop x86/mm2 and have a unified branch. Resolved Conflicts: arch/x86/kernel/setup.c
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/boot.c1
-rw-r--r--arch/x86/kernel/amd_gart_64.c5
-rw-r--r--arch/x86/kernel/cpu/amd.c9
-rw-r--r--arch/x86/kernel/cpu/intel.c1
-rw-r--r--arch/x86/kernel/e820.c16
-rw-r--r--arch/x86/kernel/head32.c21
-rw-r--r--arch/x86/kernel/head64.c133
-rw-r--r--arch/x86/kernel/head_64.S210
-rw-r--r--arch/x86/kernel/machine_kexec_64.c171
-rw-r--r--arch/x86/kernel/setup.c231
-rw-r--r--arch/x86/kernel/traps.c9
-rw-r--r--arch/x86/kernel/x86_init.c4
12 files changed, 449 insertions, 362 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index bacf4b0d91f4..cfc755dc1607 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -51,7 +51,6 @@ EXPORT_SYMBOL(acpi_disabled);
#ifdef CONFIG_X86_64
# include <asm/proto.h>
-# include <asm/numa_64.h>
#endif /* X86 */
#define BAD_MADT_ENTRY(entry, end) ( \
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index e66311200cbd..b574b295a2f9 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -768,10 +768,9 @@ int __init gart_iommu_init(void)
aper_base = info.aper_base;
end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT);
- if (end_pfn > max_low_pfn_mapped) {
- start_pfn = (aper_base>>PAGE_SHIFT);
+ start_pfn = PFN_DOWN(aper_base);
+ if (!pfn_range_is_mapped(start_pfn, end_pfn))
init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
- }
pr_info("PCI-DMA: using GART IOMMU.\n");
iommu_size = check_iommu_size(info.aper_base, aper_size);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 15239fffd6fe..eafb084e80f8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -12,7 +12,6 @@
#include <asm/pci-direct.h>
#ifdef CONFIG_X86_64
-# include <asm/numa_64.h>
# include <asm/mmconfig.h>
# include <asm/cacheflush.h>
#endif
@@ -685,12 +684,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
* benefit in doing so.
*/
if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+ unsigned long pfn = tseg >> PAGE_SHIFT;
+
printk(KERN_DEBUG "tseg: %010llx\n", tseg);
- if ((tseg>>PMD_SHIFT) <
- (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
- ((tseg>>PMD_SHIFT) <
- (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
- (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
+ if (pfn_range_is_mapped(pfn, pfn + 1))
set_memory_4k((unsigned long)__va(tseg), 1);
}
}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fdfefa27b948..1905ce98bee0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -17,7 +17,6 @@
#ifdef CONFIG_X86_64
#include <linux/topology.h>
-#include <asm/numa_64.h>
#endif
#include "cpu.h"
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index df06ade26bef..d32abeabbda5 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -835,7 +835,7 @@ static int __init parse_memopt(char *p)
}
early_param("mem", parse_memopt);
-static int __init parse_memmap_opt(char *p)
+static int __init parse_memmap_one(char *p)
{
char *oldp;
u64 start_at, mem_size;
@@ -877,6 +877,20 @@ static int __init parse_memmap_opt(char *p)
return *p == '\0' ? 0 : -EINVAL;
}
+static int __init parse_memmap_opt(char *str)
+{
+ while (str) {
+ char *k = strchr(str, ',');
+
+ if (k)
+ *k++ = 0;
+
+ parse_memmap_one(str);
+ str = k;
+ }
+
+ return 0;
+}
early_param("memmap", parse_memmap_opt);
void __init finish_e820_parsing(void)
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index e17554832991..138463a24877 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -18,6 +18,7 @@
#include <asm/io_apic.h>
#include <asm/bios_ebda.h>
#include <asm/tlbflush.h>
+#include <asm/bootparam_utils.h>
static void __init i386_default_early_setup(void)
{
@@ -30,19 +31,7 @@ static void __init i386_default_early_setup(void)
void __init i386_start_kernel(void)
{
- memblock_reserve(__pa_symbol(_text),
- (unsigned long)__bss_stop - (unsigned long)_text);
-
-#ifdef CONFIG_BLK_DEV_INITRD
- /* Reserve INITRD */
- if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
- /* Assume only end is not page aligned */
- u64 ramdisk_image = boot_params.hdr.ramdisk_image;
- u64 ramdisk_size = boot_params.hdr.ramdisk_size;
- u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
- memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
- }
-#endif
+ sanitize_boot_params(&boot_params);
/* Call the subarch specific early setup function */
switch (boot_params.hdr.hardware_subarch) {
@@ -57,11 +46,5 @@ void __init i386_start_kernel(void)
break;
}
- /*
- * At this point everything still needed from the boot loader
- * or BIOS or kernel text should be early reserved or marked not
- * RAM in e820. All other memory is free game.
- */
-
start_kernel();
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 7b215a50ec1e..57334f4cd3af 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -25,12 +25,83 @@
#include <asm/kdebug.h>
#include <asm/e820.h>
#include <asm/bios_ebda.h>
+#include <asm/bootparam_utils.h>
-static void __init zap_identity_mappings(void)
+/*
+ * Manage page tables very early on.
+ */
+extern pgd_t early_level4_pgt[PTRS_PER_PGD];
+extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
+static unsigned int __initdata next_early_pgt = 2;
+
+/* Wipe all early page tables except for the kernel symbol map */
+static void __init reset_early_page_tables(void)
+{
+ unsigned long i;
+
+ for (i = 0; i < PTRS_PER_PGD-1; i++)
+ early_level4_pgt[i].pgd = 0;
+
+ next_early_pgt = 0;
+
+ write_cr3(__pa(early_level4_pgt));
+}
+
+/* Create a new PMD entry */
+int __init early_make_pgtable(unsigned long address)
{
- pgd_t *pgd = pgd_offset_k(0UL);
- pgd_clear(pgd);
- __flush_tlb_all();
+ unsigned long physaddr = address - __PAGE_OFFSET;
+ unsigned long i;
+ pgdval_t pgd, *pgd_p;
+ pudval_t pud, *pud_p;
+ pmdval_t pmd, *pmd_p;
+
+ /* Invalid address or early pgt is done ? */
+ if (physaddr >= MAXMEM || read_cr3() != __pa(early_level4_pgt))
+ return -1;
+
+again:
+ pgd_p = &early_level4_pgt[pgd_index(address)].pgd;
+ pgd = *pgd_p;
+
+ /*
+ * The use of __START_KERNEL_map rather than __PAGE_OFFSET here is
+ * critical -- __PAGE_OFFSET would point us back into the dynamic
+ * range and we might end up looping forever...
+ */
+ if (pgd)
+ pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
+ else {
+ if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
+ reset_early_page_tables();
+ goto again;
+ }
+
+ pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++];
+ for (i = 0; i < PTRS_PER_PUD; i++)
+ pud_p[i] = 0;
+ *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
+ }
+ pud_p += pud_index(address);
+ pud = *pud_p;
+
+ if (pud)
+ pmd_p = (pmdval_t *)((pud & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
+ else {
+ if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
+ reset_early_page_tables();
+ goto again;
+ }
+
+ pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++];
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ pmd_p[i] = 0;
+ *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
+ }
+ pmd = (physaddr & PMD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL);
+ pmd_p[pmd_index(address)] = pmd;
+
+ return 0;
}
/* Don't add a printk in there. printk relies on the PDA which is not initialized
@@ -41,13 +112,25 @@ static void __init clear_bss(void)
(unsigned long) __bss_stop - (unsigned long) __bss_start);
}
+static unsigned long get_cmd_line_ptr(void)
+{
+ unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
+
+ cmd_line_ptr |= (u64)boot_params.ext_cmd_line_ptr << 32;
+
+ return cmd_line_ptr;
+}
+
static void __init copy_bootdata(char *real_mode_data)
{
char * command_line;
+ unsigned long cmd_line_ptr;
memcpy(&boot_params, real_mode_data, sizeof boot_params);
- if (boot_params.hdr.cmd_line_ptr) {
- command_line = __va(boot_params.hdr.cmd_line_ptr);
+ sanitize_boot_params(&boot_params);
+ cmd_line_ptr = get_cmd_line_ptr();
+ if (cmd_line_ptr) {
+ command_line = __va(cmd_line_ptr);
memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
}
}
@@ -70,14 +153,12 @@ void __init x86_64_start_kernel(char * real_mode_data)
(__START_KERNEL & PGDIR_MASK)));
BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
+ /* Kill off the identity-map trampoline */
+ reset_early_page_tables();
+
/* clear bss before set_intr_gate with early_idt_handler */
clear_bss();
- /* Make NULL pointers segfault */
- zap_identity_mappings();
-
- max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
-
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
#ifdef CONFIG_EARLY_PRINTK
set_intr_gate(i, &early_idt_handlers[i]);
@@ -87,37 +168,25 @@ void __init x86_64_start_kernel(char * real_mode_data)
}
load_idt((const struct desc_ptr *)&idt_descr);
+ copy_bootdata(__va(real_mode_data));
+
if (console_loglevel == 10)
early_printk("Kernel alive\n");
+ clear_page(init_level4_pgt);
+ /* set init_level4_pgt kernel high mapping*/
+ init_level4_pgt[511] = early_level4_pgt[511];
+
x86_64_start_reservations(real_mode_data);
}
void __init x86_64_start_reservations(char *real_mode_data)
{
- copy_bootdata(__va(real_mode_data));
-
- memblock_reserve(__pa_symbol(_text),
- (unsigned long)__bss_stop - (unsigned long)_text);
-
-#ifdef CONFIG_BLK_DEV_INITRD
- /* Reserve INITRD */
- if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
- /* Assume only end is not page aligned */
- unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
- unsigned long ramdisk_size = boot_params.hdr.ramdisk_size;
- unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
- memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
- }
-#endif
+ /* version is always not zero if it is copied */
+ if (!boot_params.hdr.version)
+ copy_bootdata(__va(real_mode_data));
reserve_ebda_region();
- /*
- * At this point everything still needed from the boot loader
- * or BIOS or kernel text should be early reserved or marked not
- * RAM in e820. All other memory is free game.
- */
-
start_kernel();
}
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 980053c4b9cc..d94f6d68be2a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -47,14 +47,13 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map)
.code64
.globl startup_64
startup_64:
-
/*
* At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
* and someone has loaded an identity mapped page table
* for us. These identity mapped page tables map all of the
* kernel pages and possibly all of memory.
*
- * %esi holds a physical pointer to real_mode_data.
+ * %rsi holds a physical pointer to real_mode_data.
*
* We come here either directly from a 64bit bootloader, or from
* arch/x86_64/boot/compressed/head.S.
@@ -66,7 +65,8 @@ startup_64:
* tables and then reload them.
*/
- /* Compute the delta between the address I am compiled to run at and the
+ /*
+ * Compute the delta between the address I am compiled to run at and the
* address I am actually running at.
*/
leaq _text(%rip), %rbp
@@ -78,45 +78,62 @@ startup_64:
testl %eax, %eax
jnz bad_address
- /* Is the address too large? */
- leaq _text(%rip), %rdx
- movq $PGDIR_SIZE, %rax
- cmpq %rax, %rdx
- jae bad_address
-
- /* Fixup the physical addresses in the page table
+ /*
+ * Is the address too large?
*/
- addq %rbp, init_level4_pgt + 0(%rip)
- addq %rbp, init_level4_pgt + (L4_PAGE_OFFSET*8)(%rip)
- addq %rbp, init_level4_pgt + (L4_START_KERNEL*8)(%rip)
+ leaq _text(%rip), %rax
+ shrq $MAX_PHYSMEM_BITS, %rax
+ jnz bad_address
- addq %rbp, level3_ident_pgt + 0(%rip)
+ /*
+ * Fixup the physical addresses in the page table
+ */
+ addq %rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip)
addq %rbp, level3_kernel_pgt + (510*8)(%rip)
addq %rbp, level3_kernel_pgt + (511*8)(%rip)
addq %rbp, level2_fixmap_pgt + (506*8)(%rip)
- /* Add an Identity mapping if I am above 1G */
+ /*
+ * Set up the identity mapping for the switchover. These
+ * entries should *NOT* have the global bit set! This also
+ * creates a bunch of nonsense entries but that is fine --
+ * it avoids problems around wraparound.
+ */
leaq _text(%rip), %rdi
- andq $PMD_PAGE_MASK, %rdi
+ leaq early_level4_pgt(%rip), %rbx
movq %rdi, %rax
- shrq $PUD_SHIFT, %rax
- andq $(PTRS_PER_PUD - 1), %rax
- jz ident_complete
+ shrq $PGDIR_SHIFT, %rax
- leaq (level2_spare_pgt - __START_KERNEL_map + _KERNPG_TABLE)(%rbp), %rdx
- leaq level3_ident_pgt(%rip), %rbx
- movq %rdx, 0(%rbx, %rax, 8)
+ leaq (4096 + _KERNPG_TABLE)(%rbx), %rdx
+ movq %rdx, 0(%rbx,%rax,8)
+ movq %rdx, 8(%rbx,%rax,8)
+ addq $4096, %rdx
movq %rdi, %rax
- shrq $PMD_SHIFT, %rax
- andq $(PTRS_PER_PMD - 1), %rax
- leaq __PAGE_KERNEL_IDENT_LARGE_EXEC(%rdi), %rdx
- leaq level2_spare_pgt(%rip), %rbx
- movq %rdx, 0(%rbx, %rax, 8)
-ident_complete:
+ shrq $PUD_SHIFT, %rax
+ andl $(PTRS_PER_PUD-1), %eax
+ movq %rdx, (4096+0)(%rbx,%rax,8)
+ movq %rdx, (4096+8)(%rbx,%rax,8)
+
+ addq $8192, %rbx
+ movq %rdi, %rax
+ shrq $PMD_SHIFT, %rdi
+ addq $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax
+ leaq (_end - 1)(%rip), %rcx
+ shrq $PMD_SHIFT, %rcx
+ subq %rdi, %rcx
+ incl %ecx
+
+1:
+ andq $(PTRS_PER_PMD - 1), %rdi
+ movq %rax, (%rbx,%rdi,8)
+ incq %rdi
+ addq $PMD_SIZE, %rax
+ decl %ecx
+ jnz 1b
/*
* Fixup the kernel text+data virtual addresses. Note that
@@ -124,7 +141,6 @@ ident_complete:
* cleanup_highmap() fixes this up along with the mappings
* beyond _end.
*/
-
leaq level2_kernel_pgt(%rip), %rdi
leaq 4096(%rdi), %r8
/* See if it is a valid page table entry */
@@ -139,17 +155,14 @@ ident_complete:
/* Fixup phys_base */
addq %rbp, phys_base(%rip)
- /* Due to ENTRY(), sometimes the empty space gets filled with
- * zeros. Better take a jmp than relying on empty space being
- * filled with 0x90 (nop)
- */
- jmp secondary_startup_64
+ movq $(early_level4_pgt - __START_KERNEL_map), %rax
+ jmp 1f
ENTRY(secondary_startup_64)
/*
* At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
* and someone has loaded a mapped page table.
*
- * %esi holds a physical pointer to real_mode_data.
+ * %rsi holds a physical pointer to real_mode_data.
*
* We come here either from startup_64 (using physical addresses)
* or from trampoline.S (using virtual addresses).
@@ -159,12 +172,14 @@ ENTRY(secondary_startup_64)
* after the boot processor executes this code.
*/
+ movq $(init_level4_pgt - __START_KERNEL_map), %rax
+1:
+
/* Enable PAE mode and PGE */
- movl $(X86_CR4_PAE | X86_CR4_PGE), %eax
- movq %rax, %cr4
+ movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
+ movq %rcx, %cr4
/* Setup early boot stage 4 level pagetables. */
- movq $(init_level4_pgt - __START_KERNEL_map), %rax
addq phys_base(%rip), %rax
movq %rax, %cr3
@@ -196,7 +211,7 @@ ENTRY(secondary_startup_64)
movq %rax, %cr0
/* Setup a boot time stack */
- movq stack_start(%rip),%rsp
+ movq stack_start(%rip), %rsp
/* zero EFLAGS after setting rsp */
pushq $0
@@ -236,15 +251,33 @@ ENTRY(secondary_startup_64)
movl initial_gs+4(%rip),%edx
wrmsr
- /* esi is pointer to real mode structure with interesting info.
+ /* rsi is pointer to real mode structure with interesting info.
pass it to C */
- movl %esi, %edi
+ movq %rsi, %rdi
/* Finally jump to run C code and to be on real kernel address
* Since we are running on identity-mapped space we have to jump
* to the full 64bit address, this is only possible as indirect
* jump. In addition we need to ensure %cs is set so we make this
* a far return.
+ *
+ * Note: do not change to far jump indirect with 64bit offset.
+ *
+ * AMD does not support far jump indirect with 64bit offset.
+ * AMD64 Architecture Programmer's Manual, Volume 3: states only
+ * JMP FAR mem16:16 FF /5 Far jump indirect,
+ * with the target specified by a far pointer in memory.
+ * JMP FAR mem16:32 FF /5 Far jump indirect,
+ * with the target specified by a far pointer in memory.
+ *
+ * Intel64 does support 64bit offset.
+ * Software Developer Manual Vol 2: states:
+ * FF /5 JMP m16:16 Jump far, absolute indirect,
+ * address given in m16:16
+ * FF /5 JMP m16:32 Jump far, absolute indirect,
+ * address given in m16:32.
+ * REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
+ * address given in m16:64.
*/
movq initial_code(%rip),%rax
pushq $0 # fake return address to stop unwinder
@@ -270,13 +303,13 @@ ENDPROC(start_cpu0)
/* SMP bootup changes these two */
__REFDATA
- .align 8
- ENTRY(initial_code)
+ .balign 8
+ GLOBAL(initial_code)
.quad x86_64_start_kernel
- ENTRY(initial_gs)
+ GLOBAL(initial_gs)
.quad INIT_PER_CPU_VAR(irq_stack_union)
- ENTRY(stack_start)
+ GLOBAL(stack_start)
.quad init_thread_union+THREAD_SIZE-8
.word 0
__FINITDATA
@@ -284,7 +317,7 @@ ENDPROC(start_cpu0)
bad_address:
jmp bad_address
- .section ".init.text","ax"
+ __INIT
.globl early_idt_handlers
early_idt_handlers:
# 104(%rsp) %rflags
@@ -321,14 +354,22 @@ ENTRY(early_idt_handler)
pushq %r11 # 0(%rsp)
cmpl $__KERNEL_CS,96(%rsp)
- jne 10f
+ jne 11f
+
+ cmpl $14,72(%rsp) # Page fault?
+ jnz 10f
+ GET_CR2_INTO(%rdi) # can clobber any volatile register if pv
+ call early_make_pgtable
+ andl %eax,%eax
+ jz 20f # All good
+10:
leaq 88(%rsp),%rdi # Pointer to %rip
call early_fixup_exception
andl %eax,%eax
jnz 20f # Found an exception entry
-10:
+11:
#ifdef CONFIG_EARLY_PRINTK
GET_CR2_INTO(%r9) # can clobber any volatile register if pv
movl 80(%rsp),%r8d # error code
@@ -350,7 +391,7 @@ ENTRY(early_idt_handler)
1: hlt
jmp 1b
-20: # Exception table entry found
+20: # Exception table entry found or page table generated
popq %r11
popq %r10
popq %r9
@@ -364,6 +405,8 @@ ENTRY(early_idt_handler)
decl early_recursion_flag(%rip)
INTERRUPT_RETURN
+ __INITDATA
+
.balign 4
early_recursion_flag:
.long 0
@@ -374,11 +417,10 @@ early_idt_msg:
early_idt_ripmsg:
.asciz "RIP %s\n"
#endif /* CONFIG_EARLY_PRINTK */
- .previous
#define NEXT_PAGE(name) \
.balign PAGE_SIZE; \
-ENTRY(name)
+GLOBAL(name)
/* Automate the creation of 1 to 1 mapping pmd entries */
#define PMDS(START, PERM, COUNT) \
@@ -388,24 +430,37 @@ ENTRY(name)
i = i + 1 ; \
.endr
+ __INITDATA
+NEXT_PAGE(early_level4_pgt)
+ .fill 511,8,0
+ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+
+NEXT_PAGE(early_dynamic_pgts)
+ .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
+
.data
- /*
- * This default setting generates an ident mapping at address 0x100000
- * and a mapping for the kernel that precisely maps virtual address
- * 0xffffffff80000000 to physical address 0x000000. (always using
- * 2Mbyte large pages provided by PAE mode)
- */
+
+#ifndef CONFIG_XEN
NEXT_PAGE(init_level4_pgt)
- .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
- .org init_level4_pgt + L4_PAGE_OFFSET*8, 0
- .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
- .org init_level4_pgt + L4_START_KERNEL*8, 0
+ .fill 512,8,0
+#else
+NEXT_PAGE(init_level4_pgt)
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .org init_level4_pgt + L4_PAGE_OFFSET*8, 0
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .org init_level4_pgt + L4_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
- .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
- .fill 511,8,0
+ .fill 511, 8, 0
+NEXT_PAGE(level2_ident_pgt)
+ /* Since I easily can, map the first 1G.
+ * Don't set NX because code runs from these pages.
+ */
+ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
+#endif
NEXT_PAGE(level3_kernel_pgt)
.fill L3_START_KERNEL,8,0
@@ -413,21 +468,6 @@ NEXT_PAGE(level3_kernel_pgt)
.quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
.quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
-NEXT_PAGE(level2_fixmap_pgt)
- .fill 506,8,0
- .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
- /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
- .fill 5,8,0
-
-NEXT_PAGE(level1_fixmap_pgt)
- .fill 512,8,0
-
-NEXT_PAGE(level2_ident_pgt)
- /* Since I easily can, map the first 1G.
- * Don't set NX because code runs from these pages.
- */
- PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
-
NEXT_PAGE(level2_kernel_pgt)
/*
* 512 MB kernel mapping. We spend a full page on this pagetable
@@ -442,11 +482,16 @@ NEXT_PAGE(level2_kernel_pgt)
PMDS(0, __PAGE_KERNEL_LARGE_EXEC,
KERNEL_IMAGE_SIZE/PMD_SIZE)
-NEXT_PAGE(level2_spare_pgt)
- .fill 512, 8, 0
+NEXT_PAGE(level2_fixmap_pgt)
+ .fill 506,8,0
+ .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
+ /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
+ .fill 5,8,0
+
+NEXT_PAGE(level1_fixmap_pgt)
+ .fill 512,8,0
#undef PMDS
-#undef NEXT_PAGE
.data
.align 16
@@ -472,6 +517,5 @@ ENTRY(nmi_idt_table)
.skip IDT_ENTRIES * 16
__PAGE_ALIGNED_BSS
- .align PAGE_SIZE
-ENTRY(empty_zero_page)
+NEXT_PAGE(empty_zero_page)
.skip PAGE_SIZE
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index b3ea9db39db6..4eabc160696f 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -16,125 +16,12 @@
#include <linux/io.h>
#include <linux/suspend.h>
+#include <asm/init.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/debugreg.h>
-static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
- unsigned long addr)
-{
- pud_t *pud;
- pmd_t *pmd;
- struct page *page;
- int result = -ENOMEM;
-
- addr &= PMD_MASK;
- pgd += pgd_index(addr);
- if (!pgd_present(*pgd)) {
- page = kimage_alloc_control_pages(image, 0);
- if (!page)
- goto out;
- pud = (pud_t *)page_address(page);
- clear_page(pud);
- set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
- }
- pud = pud_offset(pgd, addr);
- if (!pud_present(*pud)) {
- page = kimage_alloc_control_pages(image, 0);
- if (!page)
- goto out;
- pmd = (pmd_t *)page_address(page);
- clear_page(pmd);
- set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
- }
- pmd = pmd_offset(pud, addr);
- if (!pmd_present(*pmd))
- set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
- result = 0;
-out:
- return result;
-}
-
-static void init_level2_page(pmd_t *level2p, unsigned long addr)
-{
- unsigned long end_addr;
-
- addr &= PAGE_MASK;
- end_addr = addr + PUD_SIZE;
- while (addr < end_addr) {
- set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
- addr += PMD_SIZE;
- }
-}
-
-static int init_level3_page(struct kimage *image, pud_t *level3p,
- unsigned long addr, unsigned long last_addr)
-{
- unsigned long end_addr;
- int result;
-
- result = 0;
- addr &= PAGE_MASK;
- end_addr = addr + PGDIR_SIZE;
- while ((addr < last_addr) && (addr < end_addr)) {
- struct page *page;
- pmd_t *level2p;
-
- page = kimage_alloc_control_pages(image, 0);
- if (!page) {
- result = -ENOMEM;
- goto out;
- }
- level2p = (pmd_t *)page_address(page);
- init_level2_page(level2p, addr);
- set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE));
- addr += PUD_SIZE;
- }
- /* clear the unused entries */
- while (addr < end_addr) {
- pud_clear(level3p++);
- addr += PUD_SIZE;
- }
-out:
- return result;
-}
-
-
-static int init_level4_page(struct kimage *image, pgd_t *level4p,
- unsigned long addr, unsigned long last_addr)
-{
- unsigned long end_addr;
- int result;
-
- result = 0;
- addr &= PAGE_MASK;
- end_addr = addr + (PTRS_PER_PGD * PGDIR_SIZE);
- while ((addr < last_addr) && (addr < end_addr)) {
- struct page *page;
- pud_t *level3p;
-
- page = kimage_alloc_control_pages(image, 0);
- if (!page) {
- result = -ENOMEM;
- goto out;
- }
- level3p = (pud_t *)page_address(page);
- result = init_level3_page(image, level3p, addr, last_addr);
- if (result)
- goto out;
- set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
- addr += PGDIR_SIZE;
- }
- /* clear the unused entries */
- while (addr < end_addr) {
- pgd_clear(level4p++);
- addr += PGDIR_SIZE;
- }
-out:
- return result;
-}
-
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.pud);
@@ -184,22 +71,62 @@ err:
return result;
}
+static void *alloc_pgt_page(void *data)
+{
+ struct kimage *image = (struct kimage *)data;
+ struct page *page;
+ void *p = NULL;
+
+ page = kimage_alloc_control_pages(image, 0);
+ if (page) {
+ p = page_address(page);
+ clear_page(p);
+ }
+
+ return p;
+}
static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
{
+ struct x86_mapping_info info = {
+ .alloc_pgt_page = alloc_pgt_page,
+ .context = image,
+ .pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
+ };
+ unsigned long mstart, mend;
pgd_t *level4p;
int result;
+ int i;
+
level4p = (pgd_t *)__va(start_pgtable);
- result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
- if (result)
- return result;
+ clear_page(level4p);
+ for (i = 0; i < nr_pfn_mapped; i++) {
+ mstart = pfn_mapped[i].start << PAGE_SHIFT;
+ mend = pfn_mapped[i].end << PAGE_SHIFT;
+
+ result = kernel_ident_mapping_init(&info,
+ level4p, mstart, mend);
+ if (result)
+ return result;
+ }
+
/*
- * image->start may be outside 0 ~ max_pfn, for example when
- * jump back to original kernel from kexeced kernel
+ * segments's mem ranges could be outside 0 ~ max_pfn,
+ * for example when jump back to original kernel from kexeced kernel.
+ * or first kernel is booted with user mem map, and second kernel
+ * could be loaded out of that range.
*/
- result = init_one_level2_page(image, level4p, image->start);
- if (result)
- return result;
+ for (i = 0; i < image->nr_segments; i++) {
+ mstart = image->segment[i].mem;
+ mend = mstart + image->segment[i].memsz;
+
+ result = kernel_ident_mapping_init(&info,
+ level4p, mstart, mend);
+
+ if (result)
+ return result;
+ }
+
return init_transition_pgtable(image, level4p);
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0aebd776018e..878cf1d326e5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -108,17 +108,16 @@
#include <asm/topology.h>
#include <asm/apicdef.h>
#include <asm/amd_nb.h>
-#ifdef CONFIG_X86_64
-#include <asm/numa_64.h>
-#endif
#include <asm/mce.h>
#include <asm/alternative.h>
#include <asm/prom.h>
/*
- * 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.
+ * max_low_pfn_mapped: highest direct mapped pfn under 4GB
+ * max_pfn_mapped: highest direct mapped pfn over 4GB
+ *
+ * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * represented by pfn_mapped
*/
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
@@ -276,18 +275,7 @@ void * __init extend_brk(size_t size, size_t align)
return ret;
}
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
- if (direct_gbpages && cpu_has_gbpages)
- printk(KERN_INFO "Using GB pages for direct mapping\n");
- else
- direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
+#ifdef CONFIG_X86_32
static void __init cleanup_highmap(void)
{
}
@@ -306,27 +294,43 @@ static void __init reserve_brk(void)
#ifdef CONFIG_BLK_DEV_INITRD
+static u64 __init get_ramdisk_image(void)
+{
+ u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+
+ ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32;
+
+ return ramdisk_image;
+}
+static u64 __init get_ramdisk_size(void)
+{
+ u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+
+ ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32;
+
+ return ramdisk_size;
+}
+
#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT)
static void __init relocate_initrd(void)
{
/* Assume only end is not page aligned */
- u64 ramdisk_image = boot_params.hdr.ramdisk_image;
- u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+ u64 ramdisk_image = get_ramdisk_image();
+ u64 ramdisk_size = get_ramdisk_size();
u64 area_size = PAGE_ALIGN(ramdisk_size);
- u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
u64 ramdisk_here;
unsigned long slop, clen, mapaddr;
char *p, *q;
- /* We need to move the initrd down into lowmem */
- ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
- PAGE_SIZE);
+ /* We need to move the initrd down into directly mapped mem */
+ ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+ area_size, PAGE_SIZE);
if (!ramdisk_here)
panic("Cannot find place for new RAMDISK of size %lld\n",
ramdisk_size);
- /* Note: this includes all the lowmem currently occupied by
+ /* Note: this includes all the mem currently occupied by
the initrd, we rely on that fact to keep the data intact. */
memblock_reserve(ramdisk_here, area_size);
initrd_start = ramdisk_here + PAGE_OFFSET;
@@ -336,17 +340,7 @@ static void __init relocate_initrd(void)
q = (char *)initrd_start;
- /* Copy any lowmem portion of the initrd */
- if (ramdisk_image < end_of_lowmem) {
- clen = end_of_lowmem - ramdisk_image;
- p = (char *)__va(ramdisk_image);
- memcpy(q, p, clen);
- q += clen;
- ramdisk_image += clen;
- ramdisk_size -= clen;
- }
-
- /* Copy the highmem portion of the initrd */
+ /* Copy the initrd */
while (ramdisk_size) {
slop = ramdisk_image & ~PAGE_MASK;
clen = ramdisk_size;
@@ -360,22 +354,35 @@ static void __init relocate_initrd(void)
ramdisk_image += clen;
ramdisk_size -= clen;
}
- /* high pages is not converted by early_res_to_bootmem */
- ramdisk_image = boot_params.hdr.ramdisk_image;
- ramdisk_size = boot_params.hdr.ramdisk_size;
+
+ ramdisk_image = get_ramdisk_image();
+ ramdisk_size = get_ramdisk_size();
printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
" [mem %#010llx-%#010llx]\n",
ramdisk_image, ramdisk_image + ramdisk_size - 1,
ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
+static void __init early_reserve_initrd(void)
+{
+ /* Assume only end is not page aligned */
+ u64 ramdisk_image = get_ramdisk_image();
+ u64 ramdisk_size = get_ramdisk_size();
+ u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
+
+ if (!boot_params.hdr.type_of_loader ||
+ !ramdisk_image || !ramdisk_size)
+ return; /* No initrd provided by bootloader */
+
+ memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
+}
static void __init reserve_initrd(void)
{
/* Assume only end is not page aligned */
- u64 ramdisk_image = boot_params.hdr.ramdisk_image;
- u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+ u64 ramdisk_image = get_ramdisk_image();
+ u64 ramdisk_size = get_ramdisk_size();
u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
- u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
+ u64 mapped_size;
if (!boot_params.hdr.type_of_loader ||
!ramdisk_image || !ramdisk_size)
@@ -383,22 +390,18 @@ static void __init reserve_initrd(void)
initrd_start = 0;
- if (ramdisk_size >= (end_of_lowmem>>1)) {
+ mapped_size = memblock_mem_size(max_pfn_mapped);
+ if (ramdisk_size >= (mapped_size>>1))
panic("initrd too large to handle, "
"disabling initrd (%lld needed, %lld available)\n",
- ramdisk_size, end_of_lowmem>>1);
- }
+ ramdisk_size, mapped_size>>1);
printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
ramdisk_end - 1);
-
- if (ramdisk_end <= end_of_lowmem) {
- /* All in lowmem, easy case */
- /*
- * don't need to reserve again, already reserved early
- * in i386_start_kernel
- */
+ if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image),
+ PFN_DOWN(ramdisk_end))) {
+ /* All are mapped, easy case */
initrd_start = ramdisk_image + PAGE_OFFSET;
initrd_end = initrd_start + ramdisk_size;
return;
@@ -409,6 +412,9 @@ static void __init reserve_initrd(void)
memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
}
#else
+static void __init early_reserve_initrd(void)
+{
+}
static void __init reserve_initrd(void)
{
}
@@ -419,8 +425,6 @@ static void __init parse_setup_data(void)
struct setup_data *data;
u64 pa_data;
- if (boot_params.hdr.version < 0x0209)
- return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
u32 data_len, map_len;
@@ -456,8 +460,6 @@ static void __init e820_reserve_setup_data(void)
u64 pa_data;
int found = 0;
- if (boot_params.hdr.version < 0x0209)
- return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, sizeof(*data));
@@ -481,8 +483,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
struct setup_data *data;
u64 pa_data;
- if (boot_params.hdr.version < 0x0209)
- return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, sizeof(*data));
@@ -501,17 +501,51 @@ static void __init memblock_x86_reserve_range_setup_data(void)
/*
* Keep the crash kernel below this limit. On 32 bits earlier kernels
* would limit the kernel to the low 512 MiB due to mapping restrictions.
- * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this
- * limit once kexec-tools are fixed.
*/
#ifdef CONFIG_X86_32
# define CRASH_KERNEL_ADDR_MAX (512 << 20)
#else
-# define CRASH_KERNEL_ADDR_MAX (896 << 20)
+# define CRASH_KERNEL_ADDR_MAX MAXMEM
#endif
+static void __init reserve_crashkernel_low(void)
+{
+#ifdef CONFIG_X86_64
+ const unsigned long long alignment = 16<<20; /* 16M */
+ unsigned long long low_base = 0, low_size = 0;
+ unsigned long total_low_mem;
+ unsigned long long base;
+ int ret;
+
+ total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+ ret = parse_crashkernel_low(boot_command_line, total_low_mem,
+ &low_size, &base);
+ if (ret != 0 || low_size <= 0)
+ return;
+
+ low_base = memblock_find_in_range(low_size, (1ULL<<32),
+ low_size, alignment);
+
+ if (!low_base) {
+ pr_info("crashkernel low reservation failed - No suitable area found.\n");
+
+ return;
+ }
+
+ memblock_reserve(low_base, low_size);
+ pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
+ (unsigned long)(low_size >> 20),
+ (unsigned long)(low_base >> 20),
+ (unsigned long)(total_low_mem >> 20));
+ crashk_low_res.start = low_base;
+ crashk_low_res.end = low_base + low_size - 1;
+ insert_resource(&iomem_resource, &crashk_low_res);
+#endif
+}
+
static void __init reserve_crashkernel(void)
{
+ const unsigned long long alignment = 16<<20; /* 16M */
unsigned long long total_mem;
unsigned long long crash_size, crash_base;
int ret;
@@ -525,8 +559,6 @@ static void __init reserve_crashkernel(void)
/* 0 means: find the address automatically */
if (crash_base <= 0) {
- const unsigned long long alignment = 16<<20; /* 16M */
-
/*
* kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
*/
@@ -537,6 +569,7 @@ static void __init reserve_crashkernel(void)
pr_info("crashkernel reservation failed - No suitable area found.\n");
return;
}
+
} else {
unsigned long long start;
@@ -558,6 +591,9 @@ static void __init reserve_crashkernel(void)
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
insert_resource(&iomem_resource, &crashk_res);
+
+ if (crash_base >= (1ULL<<32))
+ reserve_crashkernel_low();
}
#else
static void __init reserve_crashkernel(void)
@@ -708,6 +744,27 @@ static void __init trim_bios_range(void)
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
}
+/* called before trim_bios_range() to spare extra sanitize */
+static void __init e820_add_kernel_range(void)
+{
+ u64 start = __pa_symbol(_text);
+ u64 size = __pa_symbol(_end) - start;
+
+ /*
+ * Complain if .text .data and .bss are not marked as E820_RAM and
+ * attempt to fix it by adding the range. We may have a confused BIOS,
+ * or the user may have used memmap=exactmap or memmap=xxM$yyM to
+ * exclude kernel range. If we really are running on top non-RAM,
+ * we will crash later anyways.
+ */
+ if (e820_all_mapped(start, start + size, E820_RAM))
+ return;
+
+ pr_warn(".text .data .bss are not marked as E820_RAM!\n");
+ e820_remove_range(start, size, E820_RAM, 0);
+ e820_add_region(start, size, E820_RAM);
+}
+
static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
static int __init parse_reservelow(char *p)
@@ -752,6 +809,17 @@ static void __init trim_low_memory_range(void)
void __init setup_arch(char **cmdline_p)
{
+ memblock_reserve(__pa_symbol(_text),
+ (unsigned long)__bss_stop - (unsigned long)_text);
+
+ early_reserve_initrd();
+
+ /*
+ * At this point everything still needed from the boot loader
+ * or BIOS or kernel text should be early reserved or marked not
+ * RAM in e820. All other memory is free game.
+ */
+
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
visws_early_detect();
@@ -910,6 +978,7 @@ void __init setup_arch(char **cmdline_p)
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
+ e820_add_kernel_range();
trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
@@ -959,6 +1028,8 @@ void __init setup_arch(char **cmdline_p)
reserve_ibft_region();
+ early_alloc_pgt_buf();
+
/*
* Need to conclude brk, before memblock_x86_fill()
* it could use memblock_find_in_range, could overlap with
@@ -968,7 +1039,7 @@ void __init setup_arch(char **cmdline_p)
cleanup_highmap();
- memblock.current_limit = get_max_mapped();
+ memblock.current_limit = ISA_END_ADDRESS;
memblock_x86_fill();
/*
@@ -985,42 +1056,22 @@ void __init setup_arch(char **cmdline_p)
setup_bios_corruption_check();
#endif
+#ifdef CONFIG_X86_32
printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
(max_pfn_mapped<<PAGE_SHIFT) - 1);
+#endif
- setup_real_mode();
+ reserve_real_mode();
trim_platform_memory_ranges();
trim_low_memory_range();
- init_gbpages();
-
- /* max_pfn_mapped is updated here */
- max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
- max_pfn_mapped = max_low_pfn_mapped;
-
-#ifdef CONFIG_X86_64
- if (max_pfn > max_low_pfn) {
- int i;
- unsigned long start, end;
- unsigned long start_pfn, end_pfn;
-
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
- NULL) {
+ init_mem_mapping();
- end = PFN_PHYS(end_pfn);
- if (end <= (1UL<<32))
- continue;
+ early_trap_pf_init();
- start = PFN_PHYS(start_pfn);
- max_pfn_mapped = init_memory_mapping(
- max((1UL<<32), start), end);
- }
+ setup_real_mode();
- /* can we preseve max_low_pfn ?*/
- max_low_pfn = max_pfn;
- }
-#endif
memblock.current_limit = get_max_mapped();
dma_contiguous_reserve(0);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ecffca11f4e9..68bda7a84159 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -688,10 +688,19 @@ void __init early_trap_init(void)
set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
/* int3 can be called from all */
set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+#ifdef CONFIG_X86_32
set_intr_gate(X86_TRAP_PF, &page_fault);
+#endif
load_idt(&idt_descr);
}
+void __init early_trap_pf_init(void)
+{
+#ifdef CONFIG_X86_64
+ set_intr_gate(X86_TRAP_PF, &page_fault);
+#endif
+}
+
void __init trap_init(void)
{
int i;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 7a3d075a814a..50cf83ecd32e 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -62,10 +62,6 @@ struct x86_init_ops x86_init __initdata = {
.banner = default_banner,
},
- .mapping = {
- .pagetable_reserve = native_pagetable_reserve,
- },
-
.paging = {
.pagetable_init = native_pagetable_init,
},