6 files changed, 820 insertions, 0 deletions
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
new file mode 100644
index 00000000..a6a198c3
--- /dev/null
+++ b/arch/x86/power/Makefile
@@ -0,0 +1,7 @@
+# __restore_processor_state() restores %gs after S3 resume and so should not
+# itself be stack-protected
+nostackp := $(call cc-option, -fno-stack-protector)
+CFLAGS_cpu.o	:= $(nostackp)
+
+obj-$(CONFIG_PM_SLEEP)		+= cpu.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate_$(BITS).o hibernate_asm_$(BITS).o
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
new file mode 100644
index 00000000..218cdb16
--- /dev/null
+++ b/arch/x86/power/cpu.c
@@ -0,0 +1,239 @@
+/*
+ * Suspend support specific for i386/x86-64.
+ *
+ * Distribute under GPLv2
+ *
+ * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
+ * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
+ */
+
+#include <linux/suspend.h>
+#include <linux/export.h>
+#include <linux/smp.h>
+
+#include <asm/pgtable.h>
+#include <asm/proto.h>
+#include <asm/mtrr.h>
+#include <asm/page.h>
+#include <asm/mce.h>
+#include <asm/xcr.h>
+#include <asm/suspend.h>
+#include <asm/debugreg.h>
+#include <asm/fpu-internal.h> /* pcntxt_mask */
+
+#ifdef CONFIG_X86_32
+static struct saved_context saved_context;
+
+unsigned long saved_context_ebx;
+unsigned long saved_context_esp, saved_context_ebp;
+unsigned long saved_context_esi, saved_context_edi;
+unsigned long saved_context_eflags;
+#else
+/* CONFIG_X86_64 */
+struct saved_context saved_context;
+#endif
+
+/**
+ *	__save_processor_state - save CPU registers before creating a
+ *		hibernation image and before restoring the memory state from it
+ *	@ctxt - structure to store the registers contents in
+ *
+ *	NOTE: If there is a CPU register the modification of which by the
+ *	boot kernel (ie. the kernel used for loading the hibernation image)
+ *	might affect the operations of the restored target kernel (ie. the one
+ *	saved in the hibernation image), then its contents must be saved by this
+ *	function.  In other words, if kernel A is hibernated and different
+ *	kernel B is used for loading the hibernation image into memory, the
+ *	kernel A's __save_processor_state() function must save all registers
+ *	needed by kernel A, so that it can operate correctly after the resume
+ *	regardless of what kernel B does in the meantime.
+ */
+static void __save_processor_state(struct saved_context *ctxt)
+{
+#ifdef CONFIG_X86_32
+	mtrr_save_fixed_ranges(NULL);
+#endif
+	kernel_fpu_begin();
+
+	/*
+	 * descriptor tables
+	 */
+#ifdef CONFIG_X86_32
+	store_gdt(&ctxt->gdt);
+	store_idt(&ctxt->idt);
+#else
+/* CONFIG_X86_64 */
+	store_gdt((struct desc_ptr *)&ctxt->gdt_limit);
+	store_idt((struct desc_ptr *)&ctxt->idt_limit);
+#endif
+	store_tr(ctxt->tr);
+
+	/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
+	/*
+	 * segment registers
+	 */
+#ifdef CONFIG_X86_32
+	savesegment(es, ctxt->es);
+	savesegment(fs, ctxt->fs);
+	savesegment(gs, ctxt->gs);
+	savesegment(ss, ctxt->ss);
+#else
+/* CONFIG_X86_64 */
+	asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
+	asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
+	asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
+	asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
+	asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
+
+	rdmsrl(MSR_FS_BASE, ctxt->fs_base);
+	rdmsrl(MSR_GS_BASE, ctxt->gs_base);
+	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+	mtrr_save_fixed_ranges(NULL);
+
+	rdmsrl(MSR_EFER, ctxt->efer);
+#endif
+
+	/*
+	 * control registers
+	 */
+	ctxt->cr0 = read_cr0();
+	ctxt->cr2 = read_cr2();
+	ctxt->cr3 = read_cr3();
+#ifdef CONFIG_X86_32
+	ctxt->cr4 = read_cr4_safe();
+#else
+/* CONFIG_X86_64 */
+	ctxt->cr4 = read_cr4();
+	ctxt->cr8 = read_cr8();
+#endif
+	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
+					       &ctxt->misc_enable);
+}
+
+/* Needed by apm.c */
+void save_processor_state(void)
+{
+	__save_processor_state(&saved_context);
+	x86_platform.save_sched_clock_state();
+}
+#ifdef CONFIG_X86_32
+EXPORT_SYMBOL(save_processor_state);
+#endif
+
+static void do_fpu_end(void)
+{
+	/*
+	 * Restore FPU regs if necessary.
+	 */
+	kernel_fpu_end();
+}
+
+static void fix_processor_context(void)
+{
+	int cpu = smp_processor_id();
+	struct tss_struct *t = &per_cpu(init_tss, cpu);
+
+	set_tss_desc(cpu, t);	/*
+				 * This just modifies memory; should not be
+				 * necessary. But... This is necessary, because
+				 * 386 hardware has concept of busy TSS or some
+				 * similar stupidity.
+				 */
+
+#ifdef CONFIG_X86_64
+	get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9;
+
+	syscall_init();				/* This sets MSR_*STAR and related */
+#endif
+	load_TR_desc();				/* This does ltr */
+	load_LDT(&current->active_mm->context);	/* This does lldt */
+}
+
+/**
+ *	__restore_processor_state - restore the contents of CPU registers saved
+ *		by __save_processor_state()
+ *	@ctxt - structure to load the registers contents from
+ */
+static void __restore_processor_state(struct saved_context *ctxt)
+{
+	if (ctxt->misc_enable_saved)
+		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
+	/*
+	 * control registers
+	 */
+	/* cr4 was introduced in the Pentium CPU */
+#ifdef CONFIG_X86_32
+	if (ctxt->cr4)
+		write_cr4(ctxt->cr4);
+#else
+/* CONFIG X86_64 */
+	wrmsrl(MSR_EFER, ctxt->efer);
+	write_cr8(ctxt->cr8);
+	write_cr4(ctxt->cr4);
+#endif
+	write_cr3(ctxt->cr3);
+	write_cr2(ctxt->cr2);
+	write_cr0(ctxt->cr0);
+
+	/*
+	 * now restore the descriptor tables to their proper values
+	 * ltr is done i fix_processor_context().
+	 */
+#ifdef CONFIG_X86_32
+	load_gdt(&ctxt->gdt);
+	load_idt(&ctxt->idt);
+#else
+/* CONFIG_X86_64 */
+	load_gdt((const struct desc_ptr *)&ctxt->gdt_limit);
+	load_idt((const struct desc_ptr *)&ctxt->idt_limit);
+#endif
+
+	/*
+	 * segment registers
+	 */
+#ifdef CONFIG_X86_32
+	loadsegment(es, ctxt->es);
+	loadsegment(fs, ctxt->fs);
+	loadsegment(gs, ctxt->gs);
+	loadsegment(ss, ctxt->ss);
+
+	/*
+	 * sysenter MSRs
+	 */
+	if (boot_cpu_has(X86_FEATURE_SEP))
+		enable_sep_cpu();
+#else
+/* CONFIG_X86_64 */
+	asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
+	asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
+	asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
+	load_gs_index(ctxt->gs);
+	asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
+
+	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
+	wrmsrl(MSR_GS_BASE, ctxt->gs_base);
+	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+#endif
+
+	/*
+	 * restore XCR0 for xsave capable cpu's.
+	 */
+	if (cpu_has_xsave)
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
+
+	fix_processor_context();
+
+	do_fpu_end();
+	x86_platform.restore_sched_clock_state();
+	mtrr_bp_restore();
+}
+
+/* Needed by apm.c */
+void restore_processor_state(void)
+{
+	__restore_processor_state(&saved_context);
+}
+#ifdef CONFIG_X86_32
+EXPORT_SYMBOL(restore_processor_state);
+#endif
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
new file mode 100644
index 00000000..74202c19
--- /dev/null
+++ b/arch/x86/power/hibernate_32.c
@@ -0,0 +1,176 @@
+/*
+ * Hibernation support specific for i386 - temporary page tables
+ *
+ * Distribute under GPLv2
+ *
+ * Copyright (c) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ */
+
+#include <linux/gfp.h>
+#include <linux/suspend.h>
+#include <linux/bootmem.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/mmzone.h>
+
+/* Defined in hibernate_asm_32.S */
+extern int restore_image(void);
+
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
+
+/* Pointer to the temporary resume page tables */
+pgd_t *resume_pg_dir;
+
+/* The following three functions are based on the analogous code in
+ * arch/x86/mm/init_32.c
+ */
+
+/*
+ * Create a middle page table on a resume-safe page and put a pointer to it in
+ * the given global directory entry.  This only returns the gd entry
+ * in non-PAE compilation mode, since the middle layer is folded.
+ */
+static pmd_t *resume_one_md_table_init(pgd_t *pgd)
+{
+	pud_t *pud;
+	pmd_t *pmd_table;
+
+#ifdef CONFIG_X86_PAE
+	pmd_table = (pmd_t *)get_safe_page(GFP_ATOMIC);
+	if (!pmd_table)
+		return NULL;
+
+	set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
+	pud = pud_offset(pgd, 0);
+
+	BUG_ON(pmd_table != pmd_offset(pud, 0));
+#else
+	pud = pud_offset(pgd, 0);
+	pmd_table = pmd_offset(pud, 0);
+#endif
+
+	return pmd_table;
+}
+
+/*
+ * Create a page table on a resume-safe page and place a pointer to it in
+ * a middle page directory entry.
+ */
+static pte_t *resume_one_page_table_init(pmd_t *pmd)
+{
+	if (pmd_none(*pmd)) {
+		pte_t *page_table = (pte_t *)get_safe_page(GFP_ATOMIC);
+		if (!page_table)
+			return NULL;
+
+		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
+
+		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
+
+		return page_table;
+	}
+
+	return pte_offset_kernel(pmd, 0);
+}
+
+/*
+ * This maps the physical memory to kernel virtual address space, a total
+ * of max_low_pfn pages, by creating page tables starting from address
+ * PAGE_OFFSET.  The page tables are allocated out of resume-safe pages.
+ */
+static int resume_physical_mapping_init(pgd_t *pgd_base)
+{
+	unsigned long pfn;
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pte_t *pte;
+	int pgd_idx, pmd_idx;
+
+	pgd_idx = pgd_index(PAGE_OFFSET);
+	pgd = pgd_base + pgd_idx;
+	pfn = 0;
+
+	for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
+		pmd = resume_one_md_table_init(pgd);
+		if (!pmd)
+			return -ENOMEM;
+
+		if (pfn >= max_low_pfn)
+			continue;
+
+		for (pmd_idx = 0; pmd_idx < PTRS_PER_PMD; pmd++, pmd_idx++) {
+			if (pfn >= max_low_pfn)
+				break;
+
+			/* Map with big pages if possible, otherwise create
+			 * normal page tables.
+			 * NOTE: We can mark everything as executable here
+			 */
+			if (cpu_has_pse) {
+				set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC));
+				pfn += PTRS_PER_PTE;
+			} else {
+				pte_t *max_pte;
+
+				pte = resume_one_page_table_init(pmd);
+				if (!pte)
+					return -ENOMEM;
+
+				max_pte = pte + PTRS_PER_PTE;
+				for (; pte < max_pte; pte++, pfn++) {
+					if (pfn >= max_low_pfn)
+						break;
+
+					set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+				}
+			}
+		}
+	}
+
+	resume_map_numa_kva(pgd_base);
+
+	return 0;
+}
+
+static inline void resume_init_first_level_page_table(pgd_t *pg_dir)
+{
+#ifdef CONFIG_X86_PAE
+	int i;
+
+	/* Init entries of the first-level page table to the zero page */
+	for (i = 0; i < PTRS_PER_PGD; i++)
+		set_pgd(pg_dir + i,
+			__pgd(__pa(empty_zero_page) | _PAGE_PRESENT));
+#endif
+}
+
+int swsusp_arch_resume(void)
+{
+	int error;
+
+	resume_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	if (!resume_pg_dir)
+		return -ENOMEM;
+
+	resume_init_first_level_page_table(resume_pg_dir);
+	error = resume_physical_mapping_init(resume_pg_dir);
+	if (error)
+		return error;
+
+	/* We have got enough memory and from now on we cannot recover */
+	restore_image();
+	return 0;
+}
+
+/*
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
new file mode 100644
index 00000000..460f314d
--- /dev/null
+++ b/arch/x86/power/hibernate_64.c
@@ -0,0 +1,171 @@
+/*
+ * Hibernation support for x86-64
+ *
+ * Distribute under GPLv2
+ *
+ * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
+ * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
+ */
+
+#include <linux/gfp.h>
+#include <linux/smp.h>
+#include <linux/suspend.h>
+#include <asm/proto.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/mtrr.h>
+#include <asm/suspend.h>
+
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
+
+/* Defined in hibernate_asm_64.S */
+extern int restore_image(void);
+
+/*
+ * Address to jump to in the last phase of restore in order to get to the image
+ * kernel's text (this value is passed in the image header).
+ */
+unsigned long restore_jump_address;
+
+/*
+ * Value of the cr3 register from before the hibernation (this value is passed
+ * in the image header).
+ */
+unsigned long restore_cr3;
+
+pgd_t *temp_level4_pgt;
+
+void *relocated_restore_code;
+
+static int res_phys_pud_init(pud_t *pud, unsigned long address, unsigned long end)
+{
+	long i, j;
+
+	i = pud_index(address);
+	pud = pud + i;
+	for (; i < PTRS_PER_PUD; pud++, i++) {
+		unsigned long paddr;
+		pmd_t *pmd;
+
+		paddr = address + i*PUD_SIZE;
+		if (paddr >= end)
+			break;
+
+		pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+		if (!pmd)
+			return -ENOMEM;
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+		for (j = 0; j < PTRS_PER_PMD; pmd++, j++, paddr += PMD_SIZE) {
+			unsigned long pe;
+
+			if (paddr >= end)
+				break;
+			pe = __PAGE_KERNEL_LARGE_EXEC | paddr;
+			pe &= __supported_pte_mask;
+			set_pmd(pmd, __pmd(pe));
+		}
+	}
+	return 0;
+}
+
+static int set_up_temporary_mappings(void)
+{
+	unsigned long start, end, next;
+	int error;
+
+	temp_level4_pgt = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	if (!temp_level4_pgt)
+		return -ENOMEM;
+
+	/* It is safe to reuse the original kernel mapping */
+	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
+		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+
+	/* Set up the direct mapping from scratch */
+	start = (unsigned long)pfn_to_kaddr(0);
+	end = (unsigned long)pfn_to_kaddr(max_pfn);
+
+	for (; start < end; start = next) {
+		pud_t *pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+		if (!pud)
+			return -ENOMEM;
+		next = start + PGDIR_SIZE;
+		if (next > end)
+			next = end;
+		if ((error = res_phys_pud_init(pud, __pa(start), __pa(next))))
+			return error;
+		set_pgd(temp_level4_pgt + pgd_index(start),
+			mk_kernel_pgd(__pa(pud)));
+	}
+	return 0;
+}
+
+int swsusp_arch_resume(void)
+{
+	int error;
+
+	/* We have got enough memory and from now on we cannot recover */
+	if ((error = set_up_temporary_mappings()))
+		return error;
+
+	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+	memcpy(relocated_restore_code, &core_restore_code,
+	       &restore_registers - &core_restore_code);
+
+	restore_image();
+	return 0;
+}
+
+/*
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}
+
+struct restore_data_record {
+	unsigned long jump_address;
+	unsigned long cr3;
+	unsigned long magic;
+};
+
+#define RESTORE_MAGIC	0x0123456789ABCDEFUL
+
+/**
+ *	arch_hibernation_header_save - populate the architecture specific part
+ *		of a hibernation image header
+ *	@addr: address to save the data at
+ */
+int arch_hibernation_header_save(void *addr, unsigned int max_size)
+{
+	struct restore_data_record *rdr = addr;
+
+	if (max_size < sizeof(struct restore_data_record))
+		return -EOVERFLOW;
+	rdr->jump_address = restore_jump_address;
+	rdr->cr3 = restore_cr3;
+	rdr->magic = RESTORE_MAGIC;
+	return 0;
+}
+
+/**
+ *	arch_hibernation_header_restore - read the architecture specific data
+ *		from the hibernation image header
+ *	@addr: address to read the data from
+ */
+int arch_hibernation_header_restore(void *addr)
+{
+	struct restore_data_record *rdr = addr;
+
+	restore_jump_address = rdr->jump_address;
+	restore_cr3 = rdr->cr3;
+	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
+}
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
new file mode 100644
index 00000000..ad47daea
--- /dev/null
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -0,0 +1,80 @@
+/*
+ * This may not use any stack, nor any variable that is not "NoSave":
+ *
+ * Its rewriting one kernel image with another. What is stack in "old"
+ * image could very well be data page in "new" image, and overwriting
+ * your own stack under you is bad idea.
+ */
+
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page_types.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
+
+.text
+
+ENTRY(swsusp_arch_suspend)
+	movl %esp, saved_context_esp
+	movl %ebx, saved_context_ebx
+	movl %ebp, saved_context_ebp
+	movl %esi, saved_context_esi
+	movl %edi, saved_context_edi
+	pushfl
+	popl saved_context_eflags
+
+	call swsusp_save
+	ret
+
+ENTRY(restore_image)
+	movl	mmu_cr4_features, %ecx
+	movl	resume_pg_dir, %eax
+	subl	$__PAGE_OFFSET, %eax
+	movl	%eax, %cr3
+
+	jecxz	1f	# cr4 Pentium and higher, skip if zero
+	andl	$~(X86_CR4_PGE), %ecx
+	movl	%ecx, %cr4;  # turn off PGE
+	movl	%cr3, %eax;  # flush TLB
+	movl	%eax, %cr3
+1:
+	movl	restore_pblist, %edx
+	.p2align 4,,7
+
+copy_loop:
+	testl	%edx, %edx
+	jz	done
+
+	movl	pbe_address(%edx), %esi
+	movl	pbe_orig_address(%edx), %edi
+
+	movl	$1024, %ecx
+	rep
+	movsl
+
+	movl	pbe_next(%edx), %edx
+	jmp	copy_loop
+	.p2align 4,,7
+
+done:
+	/* go back to the original page tables */
+	movl	$swapper_pg_dir, %eax
+	subl	$__PAGE_OFFSET, %eax
+	movl	%eax, %cr3
+	movl	mmu_cr4_features, %ecx
+	jecxz	1f	# cr4 Pentium and higher, skip if zero
+	movl	%ecx, %cr4;  # turn PGE back on
+1:
+
+	movl saved_context_esp, %esp
+	movl saved_context_ebp, %ebp
+	movl saved_context_ebx, %ebx
+	movl saved_context_esi, %esi
+	movl saved_context_edi, %edi
+
+	pushl saved_context_eflags
+	popfl
+
+	xorl	%eax, %eax
+
+	ret
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
new file mode 100644
index 00000000..9356547d
--- /dev/null
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -0,0 +1,147 @@
+/*
+ * Hibernation support for x86-64
+ *
+ * Distribute under GPLv2.
+ *
+ * Copyright 2007 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright 2005 Andi Kleen <ak@suse.de>
+ * Copyright 2004 Pavel Machek <pavel@suse.cz>
+ *
+ * swsusp_arch_resume must not use any stack or any nonlocal variables while
+ * copying pages:
+ *
+ * Its rewriting one kernel image with another. What is stack in "old"
+ * image could very well be data page in "new" image, and overwriting
+ * your own stack under you is bad idea.
+ */
+
+	.text
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page_types.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
+
+ENTRY(swsusp_arch_suspend)
+	movq	$saved_context, %rax
+	movq	%rsp, pt_regs_sp(%rax)
+	movq	%rbp, pt_regs_bp(%rax)
+	movq	%rsi, pt_regs_si(%rax)
+	movq	%rdi, pt_regs_di(%rax)
+	movq	%rbx, pt_regs_bx(%rax)
+	movq	%rcx, pt_regs_cx(%rax)
+	movq	%rdx, pt_regs_dx(%rax)
+	movq	%r8, pt_regs_r8(%rax)
+	movq	%r9, pt_regs_r9(%rax)
+	movq	%r10, pt_regs_r10(%rax)
+	movq	%r11, pt_regs_r11(%rax)
+	movq	%r12, pt_regs_r12(%rax)
+	movq	%r13, pt_regs_r13(%rax)
+	movq	%r14, pt_regs_r14(%rax)
+	movq	%r15, pt_regs_r15(%rax)
+	pushfq
+	popq	pt_regs_flags(%rax)
+
+	/* save the address of restore_registers */
+	movq	$restore_registers, %rax
+	movq	%rax, restore_jump_address(%rip)
+	/* save cr3 */
+	movq	%cr3, %rax
+	movq	%rax, restore_cr3(%rip)
+
+	call swsusp_save
+	ret
+
+ENTRY(restore_image)
+	/* switch to temporary page tables */
+	movq	$__PAGE_OFFSET, %rdx
+	movq	temp_level4_pgt(%rip), %rax
+	subq	%rdx, %rax
+	movq	%rax, %cr3
+	/* Flush TLB */
+	movq	mmu_cr4_features(%rip), %rax
+	movq	%rax, %rdx
+	andq	$~(X86_CR4_PGE), %rdx
+	movq	%rdx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3;
+	movq	%rax, %cr4;  # turn PGE back on
+
+	/* prepare to jump to the image kernel */
+	movq	restore_jump_address(%rip), %rax
+	movq	restore_cr3(%rip), %rbx
+
+	/* prepare to copy image data to their original locations */
+	movq	restore_pblist(%rip), %rdx
+	movq	relocated_restore_code(%rip), %rcx
+	jmpq	*%rcx
+
+	/* code below has been relocated to a safe page */
+ENTRY(core_restore_code)
+loop:
+	testq	%rdx, %rdx
+	jz	done
+
+	/* get addresses from the pbe and copy the page */
+	movq	pbe_address(%rdx), %rsi
+	movq	pbe_orig_address(%rdx), %rdi
+	movq	$(PAGE_SIZE >> 3), %rcx
+	rep
+	movsq
+
+	/* progress to the next pbe */
+	movq	pbe_next(%rdx), %rdx
+	jmp	loop
+done:
+	/* jump to the restore_registers address from the image header */
+	jmpq	*%rax
+	/*
+	 * NOTE: This assumes that the boot kernel's text mapping covers the
+	 * image kernel's page containing restore_registers and the address of
+	 * this page is the same as in the image kernel's text mapping (it
+	 * should always be true, because the text mapping is linear, starting
+	 * from 0, and is supposed to cover the entire kernel text for every
+	 * kernel).
+	 *
+	 * code below belongs to the image kernel
+	 */
+
+ENTRY(restore_registers)
+	/* go back to the original page tables */
+	movq    %rbx, %cr3
+
+	/* Flush TLB, including "global" things (vmalloc) */
+	movq	mmu_cr4_features(%rip), %rax
+	movq	%rax, %rdx
+	andq	$~(X86_CR4_PGE), %rdx
+	movq	%rdx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3
+	movq	%rax, %cr4;  # turn PGE back on
+
+	/* We don't restore %rax, it must be 0 anyway */
+	movq	$saved_context, %rax
+	movq	pt_regs_sp(%rax), %rsp
+	movq	pt_regs_bp(%rax), %rbp
+	movq	pt_regs_si(%rax), %rsi
+	movq	pt_regs_di(%rax), %rdi
+	movq	pt_regs_bx(%rax), %rbx
+	movq	pt_regs_cx(%rax), %rcx
+	movq	pt_regs_dx(%rax), %rdx
+	movq	pt_regs_r8(%rax), %r8
+	movq	pt_regs_r9(%rax), %r9
+	movq	pt_regs_r10(%rax), %r10
+	movq	pt_regs_r11(%rax), %r11
+	movq	pt_regs_r12(%rax), %r12
+	movq	pt_regs_r13(%rax), %r13
+	movq	pt_regs_r14(%rax), %r14
+	movq	pt_regs_r15(%rax), %r15
+	pushq	pt_regs_flags(%rax)
+	popfq
+
+	xorq	%rax, %rax
+
+	/* tell the hibernation core that we've just restored the memory */
+	movq	%rax, in_suspend(%rip)
+
+	ret