i386: move power

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 385 insertions, 0 deletions

diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
new file mode 100644
index 00000000000..d764ec95006
--- /dev/null
+++ b/arch/x86/power/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_PM)		+= cpu.o
+obj-$(CONFIG_HIBERNATION)	+= swsusp.o suspend.o
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
new file mode 100644
index 00000000000..998fd3ec0d6
--- /dev/null
+++ b/arch/x86/power/cpu.c
@@ -0,0 +1,133 @@
+/*
+ * Suspend support specific for i386.
+ *
+ * Distribute under GPLv2
+ *
+ * Copyright (c) 2002 Pavel Machek <pavel@suse.cz>
+ * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
+ */
+
+#include <linux/module.h>
+#include <linux/suspend.h>
+#include <asm/mtrr.h>
+#include <asm/mce.h>
+
+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;
+
+void __save_processor_state(struct saved_context *ctxt)
+{
+	mtrr_save_fixed_ranges(NULL);
+	kernel_fpu_begin();
+
+	/*
+	 * descriptor tables
+	 */
+ 	store_gdt(&ctxt->gdt);
+ 	store_idt(&ctxt->idt);
+ 	store_tr(ctxt->tr);
+
+	/*
+	 * segment registers
+	 */
+ 	savesegment(es, ctxt->es);
+ 	savesegment(fs, ctxt->fs);
+ 	savesegment(gs, ctxt->gs);
+ 	savesegment(ss, ctxt->ss);
+
+	/*
+	 * control registers 
+	 */
+	ctxt->cr0 = read_cr0();
+	ctxt->cr2 = read_cr2();
+	ctxt->cr3 = read_cr3();
+	ctxt->cr4 = read_cr4();
+}
+
+void save_processor_state(void)
+{
+	__save_processor_state(&saved_context);
+}
+
+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. */
+
+	load_TR_desc();				/* This does ltr */
+	load_LDT(&current->active_mm->context);	/* This does lldt */
+
+	/*
+	 * Now maybe reload the debug registers
+	 */
+	if (current->thread.debugreg[7]){
+		set_debugreg(current->thread.debugreg[0], 0);
+		set_debugreg(current->thread.debugreg[1], 1);
+		set_debugreg(current->thread.debugreg[2], 2);
+		set_debugreg(current->thread.debugreg[3], 3);
+		/* no 4 and 5 */
+		set_debugreg(current->thread.debugreg[6], 6);
+		set_debugreg(current->thread.debugreg[7], 7);
+	}
+
+}
+
+void __restore_processor_state(struct saved_context *ctxt)
+{
+	/*
+	 * control registers
+	 */
+	write_cr4(ctxt->cr4);
+	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().
+	 */
+ 	load_gdt(&ctxt->gdt);
+ 	load_idt(&ctxt->idt);
+
+	/*
+	 * segment registers
+	 */
+ 	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();
+
+	fix_processor_context();
+	do_fpu_end();
+	mtrr_ap_init();
+	mcheck_init(&boot_cpu_data);
+}
+
+void restore_processor_state(void)
+{
+	__restore_processor_state(&saved_context);
+}
+
+/* Needed by apm.c */
+EXPORT_SYMBOL(save_processor_state);
+EXPORT_SYMBOL(restore_processor_state);
diff --git a/arch/x86/power/suspend.c b/arch/x86/power/suspend.c
new file mode 100644
index 00000000000..a0020b913f3
--- /dev/null
+++ b/arch/x86/power/suspend.c
@@ -0,0 +1,172 @@
+/*
+ * Suspend support specific for i386 - temporary page tables
+ *
+ * Distribute under GPLv2
+ *
+ * Copyright (c) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ */
+
+#include <linux/suspend.h>
+#include <linux/bootmem.h>
+
+#include <asm/system.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+/* Defined in arch/i386/power/swsusp.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/i386/mm/init.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));
+				}
+			}
+		}
+	}
+	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/swsusp.S b/arch/x86/power/swsusp.S
new file mode 100644
index 00000000000..53662e05b39
--- /dev/null
+++ b/arch/x86/power/swsusp.S
@@ -0,0 +1,78 @@
+.text
+
+/* Originally gcc generated, modified by hand
+ *
+ * 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.h>
+#include <asm/asm-offsets.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	resume_pg_dir, %ecx
+	subl	$__PAGE_OFFSET, %ecx
+	movl	%ecx, %cr3
+
+	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, %ecx
+	subl	$__PAGE_OFFSET, %ecx
+	movl	%ecx, %cr3
+	/* Flush TLB, including "global" things (vmalloc) */
+	movl	mmu_cr4_features, %eax
+	movl	%eax, %edx
+	andl	$~(1<<7), %edx;  # PGE
+	movl	%edx, %cr4;  # turn off PGE
+	movl	%cr3, %ecx;  # flush TLB
+	movl	%ecx, %cr3
+	movl	%eax, %cr4;  # turn PGE back on
+
+	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