1 files changed, 285 insertions, 0 deletions
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
new file mode 100644
index 00000000000..679cef0791c
--- /dev/null
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -0,0 +1,285 @@
+/*
+ * handle transition of Linux booting another kernel
+ * Copyright (C) 2002-2005 Eric Biederman  <ebiederm@xmission.com>
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/mm.h>
+#include <linux/kexec.h>
+#include <linux/string.h>
+#include <linux/gfp.h>
+#include <linux/reboot.h>
+#include <linux/numa.h>
+#include <linux/ftrace.h>
+#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 void free_transition_pgtable(struct kimage *image)
+{
+	free_page((unsigned long)image->arch.pud);
+	free_page((unsigned long)image->arch.pmd);
+	free_page((unsigned long)image->arch.pte);
+}
+
+static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long vaddr, paddr;
+	int result = -ENOMEM;
+
+	vaddr = (unsigned long)relocate_kernel;
+	paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
+	pgd += pgd_index(vaddr);
+	if (!pgd_present(*pgd)) {
+		pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
+		if (!pud)
+			goto err;
+		image->arch.pud = pud;
+		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
+	pud = pud_offset(pgd, vaddr);
+	if (!pud_present(*pud)) {
+		pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+		if (!pmd)
+			goto err;
+		image->arch.pmd = pmd;
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	}
+	pmd = pmd_offset(pud, vaddr);
+	if (!pmd_present(*pmd)) {
+		pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
+		if (!pte)
+			goto err;
+		image->arch.pte = pte;
+		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
+	}
+	pte = pte_offset_kernel(pmd, vaddr);
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+	return 0;
+err:
+	free_transition_pgtable(image);
+	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);
+	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;
+	}
+
+	/*
+	 * 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.
+	 */
+	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);
+}
+
+static void set_idt(void *newidt, u16 limit)
+{
+	struct desc_ptr curidt;
+
+	/* x86-64 supports unaliged loads & stores */
+	curidt.size    = limit;
+	curidt.address = (unsigned long)newidt;
+
+	__asm__ __volatile__ (
+		"lidtq %0\n"
+		: : "m" (curidt)
+		);
+};
+
+
+static void set_gdt(void *newgdt, u16 limit)
+{
+	struct desc_ptr curgdt;
+
+	/* x86-64 supports unaligned loads & stores */
+	curgdt.size    = limit;
+	curgdt.address = (unsigned long)newgdt;
+
+	__asm__ __volatile__ (
+		"lgdtq %0\n"
+		: : "m" (curgdt)
+		);
+};
+
+static void load_segments(void)
+{
+	__asm__ __volatile__ (
+		"\tmovl %0,%%ds\n"
+		"\tmovl %0,%%es\n"
+		"\tmovl %0,%%ss\n"
+		"\tmovl %0,%%fs\n"
+		"\tmovl %0,%%gs\n"
+		: : "a" (__KERNEL_DS) : "memory"
+		);
+}
+
+int machine_kexec_prepare(struct kimage *image)
+{
+	unsigned long start_pgtable;
+	int result;
+
+	/* Calculate the offsets */
+	start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
+
+	/* Setup the identity mapped 64bit page table */
+	result = init_pgtable(image, start_pgtable);
+	if (result)
+		return result;
+
+	return 0;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+	free_transition_pgtable(image);
+}
+
+/*
+ * Do not allocate memory (or fail in any way) in machine_kexec().
+ * We are past the point of no return, committed to rebooting now.
+ */
+void machine_kexec(struct kimage *image)
+{
+	unsigned long page_list[PAGES_NR];
+	void *control_page;
+	int save_ftrace_enabled;
+
+#ifdef CONFIG_KEXEC_JUMP
+	if (image->preserve_context)
+		save_processor_state();
+#endif
+
+	save_ftrace_enabled = __ftrace_enabled_save();
+
+	/* Interrupts aren't acceptable while we reboot */
+	local_irq_disable();
+	hw_breakpoint_disable();
+
+	if (image->preserve_context) {
+#ifdef CONFIG_X86_IO_APIC
+		/*
+		 * We need to put APICs in legacy mode so that we can
+		 * get timer interrupts in second kernel. kexec/kdump
+		 * paths already have calls to disable_IO_APIC() in
+		 * one form or other. kexec jump path also need
+		 * one.
+		 */
+		disable_IO_APIC();
+#endif
+	}
+
+	control_page = page_address(image->control_code_page) + PAGE_SIZE;
+	memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
+
+	page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page);
+	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
+	page_list[PA_TABLE_PAGE] =
+	  (unsigned long)__pa(page_address(image->control_code_page));
+
+	if (image->type == KEXEC_TYPE_DEFAULT)
+		page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
+						<< PAGE_SHIFT);
+
+	/*
+	 * The segment registers are funny things, they have both a
+	 * visible and an invisible part.  Whenever the visible part is
+	 * set to a specific selector, the invisible part is loaded
+	 * with from a table in memory.  At no other time is the
+	 * descriptor table in memory accessed.
+	 *
+	 * I take advantage of this here by force loading the
+	 * segments, before I zap the gdt with an invalid value.
+	 */
+	load_segments();
+	/*
+	 * The gdt & idt are now invalid.
+	 * If you want to load them you must set up your own idt & gdt.
+	 */
+	set_gdt(phys_to_virt(0), 0);
+	set_idt(phys_to_virt(0), 0);
+
+	/* now call it */
+	image->start = relocate_kernel((unsigned long)image->head,
+				       (unsigned long)page_list,
+				       image->start,
+				       image->preserve_context);
+
+#ifdef CONFIG_KEXEC_JUMP
+	if (image->preserve_context)
+		restore_processor_state();
+#endif
+
+	__ftrace_enabled_restore(save_ftrace_enabled);
+}
+
+void arch_crash_save_vmcoreinfo(void)
+{
+	VMCOREINFO_SYMBOL(phys_base);
+	VMCOREINFO_SYMBOL(init_level4_pgt);
+
+#ifdef CONFIG_NUMA
+	VMCOREINFO_SYMBOL(node_data);
+	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
+#endif
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+			      (unsigned long)&_text - __START_KERNEL);
+}
+