1 files changed, 99 insertions, 32 deletions

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 849fc9e63c2f..57334f4cd3af 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -27,11 +27,81 @@
 #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 
@@ -42,14 +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);
 	sanitize_boot_params(&boot_params);
-	if (boot_params.hdr.cmd_line_ptr) {
-		command_line = __va(boot_params.hdr.cmd_line_ptr);
+	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);
 	}
 }
@@ -72,14 +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]);
@@ -89,37 +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),
-			 __pa_symbol(&__bss_stop) - __pa_symbol(&_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();
 }