aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/head64.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/head64.c')
-rw-r--r--arch/x86/kernel/head64.c196
1 files changed, 130 insertions, 66 deletions
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index ad2440832de..eda1a865641 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -11,6 +11,8 @@
#include <linux/string.h>
#include <linux/percpu.h>
#include <linux/start_kernel.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
#include <asm/processor.h>
#include <asm/proto.h>
@@ -22,12 +24,86 @@
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/e820.h>
+#include <asm/bios_ebda.h>
+#include <asm/bootparam_utils.h>
+#include <asm/microcode.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;
+pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
+
+/* Wipe all early page tables except for the kernel symbol map */
+static void __init reset_early_page_tables(void)
{
- pgd_t *pgd = pgd_offset_k(0UL);
- pgd_clear(pgd);
- __flush_tlb_all();
+ 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)
+{
+ 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) + early_pmd_flags;
+ pmd_p[pmd_index(address)] = pmd;
+
+ return 0;
}
/* Don't add a printk in there. printk relies on the PDA which is not initialized
@@ -38,93 +114,81 @@ 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);
}
}
-#define EBDA_ADDR_POINTER 0x40E
-
-static __init void reserve_ebda(void)
+asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
{
- unsigned ebda_addr, ebda_size;
+ int i;
/*
- * there is a real-mode segmented pointer pointing to the
- * 4K EBDA area at 0x40E
+ * Build-time sanity checks on the kernel image and module
+ * area mappings. (these are purely build-time and produce no code)
*/
- ebda_addr = *(unsigned short *)__va(EBDA_ADDR_POINTER);
- ebda_addr <<= 4;
-
- if (!ebda_addr)
- return;
-
- ebda_size = *(unsigned short *)__va(ebda_addr);
-
- /* Round EBDA up to pages */
- if (ebda_size == 0)
- ebda_size = 1;
- ebda_size <<= 10;
- ebda_size = round_up(ebda_size + (ebda_addr & ~PAGE_MASK), PAGE_SIZE);
- if (ebda_size > 64*1024)
- ebda_size = 64*1024;
-
- reserve_early(ebda_addr, ebda_addr + ebda_size, "EBDA");
-}
-
-void __init x86_64_start_kernel(char * real_mode_data)
-{
- int i;
+ BUILD_BUG_ON(MODULES_VADDR < __START_KERNEL_map);
+ BUILD_BUG_ON(MODULES_VADDR - __START_KERNEL_map < KERNEL_IMAGE_SIZE);
+ BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE);
+ BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0);
+ BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0);
+ BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
+ BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
+ (__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();
-
- /* Cleanup the over mapped high alias */
- cleanup_highmap();
-
- for (i = 0; i < IDT_ENTRIES; i++) {
-#ifdef CONFIG_EARLY_PRINTK
- set_intr_gate(i, &early_idt_handlers[i]);
-#else
- set_intr_gate(i, early_idt_handler);
-#endif
- }
+ for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
+ set_intr_gate(i, early_idt_handlers[i]);
load_idt((const struct desc_ptr *)&idt_descr);
- early_printk("Kernel alive\n");
+ copy_bootdata(__va(real_mode_data));
- for (i = 0; i < NR_CPUS; i++)
- cpu_pda(i) = &boot_cpu_pda[i];
+ /*
+ * Load microcode early on BSP.
+ */
+ load_ucode_bsp();
- pda_init(0);
- copy_bootdata(__va(real_mode_data));
+ if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
+ early_printk("Kernel alive\n");
- reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
+ clear_page(init_level4_pgt);
+ /* set init_level4_pgt kernel high mapping*/
+ init_level4_pgt[511] = early_level4_pgt[511];
- /* Reserve INITRD */
- if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
- unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
- unsigned long ramdisk_size = boot_params.hdr.ramdisk_size;
- unsigned long ramdisk_end = ramdisk_image + ramdisk_size;
- reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
- }
+ x86_64_start_reservations(real_mode_data);
+}
- reserve_ebda();
+void __init x86_64_start_reservations(char *real_mode_data)
+{
+ /* version is always not zero if it is copied */
+ if (!boot_params.hdr.version)
+ copy_bootdata(__va(real_mode_data));
- /*
- * 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.
- */
+ reserve_ebda_region();
start_kernel();
}