Merge tag 'pm-4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These make hibernation on 32-bit x86 systems work in all of the cases
  in which it works on 64-bit x86 ones, update the menu cpuidle governor
  and the "polling" state to make them more efficient, add more hardware
  support to cpufreq drivers and fix issues with some of them, fix a bug
  in the conservative cpufreq governor, fix the operating performance
  points (OPP) framework and make it more stable, update the devfreq
  subsystem to take changes in the APIs used by into account and clean
  up some things all over.

  Specifics:

   - Backport hibernation bug fixes from x86-64 to x86-32 and
     consolidate hibernation handling on x86 to allow 32-bit systems to
     work in all of the cases in which 64-bit ones work (Zhimin Gu, Chen
     Yu).

   - Fix hibernation documentation (Vladimir D. Seleznev).

   - Update the menu cpuidle governor to fix a couple of issues with it,
     make it more efficient in some cases and clean it up (Rafael
     Wysocki).

   - Rework the cpuidle polling state implementation to make it more
     efficient (Rafael Wysocki).

   - Clean up the cpuidle core somewhat (Fieah Lim).

   - Fix the cpufreq conservative governor to take policy limits into
     account properly in some cases (Rafael Wysocki).

   - Add support for retrieving guaranteed performance information to
     the ACPI CPPC library and make the intel_pstate driver use it to
     expose the CPU base frequency via sysfs on systems with the
     hardware-managed P-states (HWP) feature enabled (Srinivas
     Pandruvada).

   - Fix clang warning in the CPPC cpufreq driver (Nathan Chancellor).

   - Get rid of device_node.name printing from cpufreq (Rob Herring).

   - Remove unnecessary unlikely() from the cpufreq core (Igor Stoppa).

   - Add support for the r8a7744 SoC to the cpufreq-dt driver (Biju
     Das).

   - Update the dt-platdev cpufreq driver to allow RK3399 to have
     separate tunables per cluster (Dmitry Torokhov).

   - Fix the dma_alloc_coherent() usage in the tegra186 cpufreq driver
     (Christoph Hellwig).

   - Make the imx6q cpufreq driver read OCOTP through nvmem for
     imx6ul/imx6ull (Anson Huang).

   - Fix several bugs in the operating performance points (OPP)
     framework and make it more stable (Viresh Kumar, Dave Gerlach).

   - Update the devfreq subsystem to take changes in the APIs used by
     into account, fix some issues with it and make it stop print
     device_node.name directly (Bjorn Andersson, Enric Balletbo i Serra,
     Matthias Kaehlcke, Rob Herring, Vincent Donnefort, zhong jiang).

   - Prepare the generic power domains (genpd) framework for dealing
     with domains containing CPUs (Ulf Hansson).

   - Prevent sysfs attributes representing low-power S0 residency
     counters from being exposed if low-power S0 support is not
     indicated in ACPI FADT (Rajneesh Bhardwaj).

   - Get rid of custom CPU features macros for Intel CPUs from the
     intel_idle and RAPL drivers (Andy Shevchenko).

   - Update the tasks freezer to list tasks that refused to freeze and
     caused a system transition to a sleep state to be aborted (Todd
     Brandt).

   - Update the pm-graph set of tools to v5.2 (Todd Brandt).

   - Fix some issues in the cpupower utility (Anders Roxell, Prarit
     Bhargava)"

* tag 'pm-4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (73 commits)
  PM / Domains: Document flags for genpd
  PM / Domains: Deal with multiple states but no governor in genpd
  PM / Domains: Don't treat zero found compatible idle states as an error
  cpuidle: menu: Avoid computations when result will be discarded
  cpuidle: menu: Drop redundant comparison
  cpufreq: tegra186: don't pass GFP_DMA32 to dma_alloc_coherent()
  cpufreq: conservative: Take limits changes into account properly
  Documentation: intel_pstate: Add base_frequency information
  cpufreq: intel_pstate: Add base_frequency attribute
  ACPI / CPPC: Add support for guaranteed performance
  cpuidle: menu: Simplify checks related to the polling state
  PM / tools: sleepgraph and bootgraph: upgrade to v5.2
  PM / tools: sleepgraph: first batch of v5.2 changes
  cpupower: Fix coredump on VMWare
  cpupower: Fix AMD Family 0x17 msr_pstate size
  cpufreq: imx6q: read OCOTP through nvmem for imx6ul/imx6ull
  cpufreq: dt-platdev: allow RK3399 to have separate tunables per cluster
  cpuidle: poll_state: Revise loop termination condition
  cpuidle: menu: Move the latency_req == 0 special case check
  cpuidle: menu: Avoid computations for very close timers
  ...

10 files changed, 334 insertions, 247 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a0be022f91d..e8de5de1057f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2422,7 +2422,7 @@ menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
 	def_bool y
-	depends on X86_64 && HIBERNATION
+	depends on HIBERNATION
 
 source "kernel/power/Kconfig"
 
diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h
index ecffe81ff65c..a892494ca5e4 100644
--- a/arch/x86/include/asm/suspend.h
+++ b/arch/x86/include/asm/suspend.h
@@ -4,3 +4,11 @@
 #else
 # include <asm/suspend_64.h>
 #endif
+extern unsigned long restore_jump_address __visible;
+extern unsigned long jump_address_phys;
+extern unsigned long restore_cr3 __visible;
+extern unsigned long temp_pgt __visible;
+extern unsigned long relocated_restore_code __visible;
+extern int relocate_restore_code(void);
+/* Defined in hibernate_asm_32/64.S */
+extern asmlinkage __visible int restore_image(void);
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 8be6afb58471..fdbd9d7b7bca 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -32,4 +32,8 @@ struct saved_context {
 	unsigned long return_address;
 } __attribute__((packed));
 
+/* routines for saving/restoring kernel state */
+extern char core_restore_code[];
+extern char restore_registers[];
+
 #endif /* _ASM_X86_SUSPEND_32_H */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4866badb235..90ecc108bc8a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1251,7 +1251,7 @@ void __init setup_arch(char **cmdline_p)
 	x86_init.hyper.guest_late_init();
 
 	e820__reserve_resources();
-	e820__register_nosave_regions(max_low_pfn);
+	e820__register_nosave_regions(max_pfn);
 
 	x86_init.resources.reserve_resources();
 
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index a4701389562c..37923d715741 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -7,4 +7,4 @@ 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
+obj-$(CONFIG_HIBERNATION)	+= hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
new file mode 100644
index 000000000000..bcddf09b5aa3
--- /dev/null
+++ b/arch/x86/power/hibernate.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hibernation support for x86
+ *
+ * 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 <linux/scatterlist.h>
+#include <linux/kdebug.h>
+
+#include <crypto/hash.h>
+
+#include <asm/e820/api.h>
+#include <asm/init.h>
+#include <asm/proto.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/mtrr.h>
+#include <asm/sections.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+/*
+ * 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 __visible;
+unsigned long jump_address_phys;
+
+/*
+ * Value of the cr3 register from before the hibernation (this value is passed
+ * in the image header).
+ */
+unsigned long restore_cr3 __visible;
+unsigned long temp_pgt __visible;
+unsigned long relocated_restore_code __visible;
+
+/**
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn;
+	unsigned long nosave_end_pfn;
+
+	nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+	nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+
+	return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn;
+}
+
+
+#define MD5_DIGEST_SIZE 16
+
+struct restore_data_record {
+	unsigned long jump_address;
+	unsigned long jump_address_phys;
+	unsigned long cr3;
+	unsigned long magic;
+	u8 e820_digest[MD5_DIGEST_SIZE];
+};
+
+#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
+/**
+ * get_e820_md5 - calculate md5 according to given e820 table
+ *
+ * @table: the e820 table to be calculated
+ * @buf: the md5 result to be stored to
+ */
+static int get_e820_md5(struct e820_table *table, void *buf)
+{
+	struct crypto_shash *tfm;
+	struct shash_desc *desc;
+	int size;
+	int ret = 0;
+
+	tfm = crypto_alloc_shash("md5", 0, 0);
+	if (IS_ERR(tfm))
+		return -ENOMEM;
+
+	desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
+		       GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto free_tfm;
+	}
+
+	desc->tfm = tfm;
+	desc->flags = 0;
+
+	size = offsetof(struct e820_table, entries) +
+		sizeof(struct e820_entry) * table->nr_entries;
+
+	if (crypto_shash_digest(desc, (u8 *)table, size, buf))
+		ret = -EINVAL;
+
+	kzfree(desc);
+
+free_tfm:
+	crypto_free_shash(tfm);
+	return ret;
+}
+
+static int hibernation_e820_save(void *buf)
+{
+	return get_e820_md5(e820_table_firmware, buf);
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+	int ret;
+	u8 result[MD5_DIGEST_SIZE];
+
+	memset(result, 0, MD5_DIGEST_SIZE);
+	/* If there is no digest in suspend kernel, let it go. */
+	if (!memcmp(result, buf, MD5_DIGEST_SIZE))
+		return false;
+
+	ret = get_e820_md5(e820_table_firmware, result);
+	if (ret)
+		return true;
+
+	return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
+}
+#else
+static int hibernation_e820_save(void *buf)
+{
+	return 0;
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+	/* If md5 is not builtin for restore kernel, let it go. */
+	return false;
+}
+#endif
+
+#ifdef CONFIG_X86_64
+#define RESTORE_MAGIC	0x23456789ABCDEF01UL
+#else
+#define RESTORE_MAGIC	0x12345678UL
+#endif
+
+/**
+ *	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->magic = RESTORE_MAGIC;
+	rdr->jump_address = (unsigned long)restore_registers;
+	rdr->jump_address_phys = __pa_symbol(restore_registers);
+
+	/*
+	 * The restore code fixes up CR3 and CR4 in the following sequence:
+	 *
+	 * [in hibernation asm]
+	 * 1. CR3 <= temporary page tables
+	 * 2. CR4 <= mmu_cr4_features (from the kernel that restores us)
+	 * 3. CR3 <= rdr->cr3
+	 * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel)
+	 * [in restore_processor_state()]
+	 * 5. CR4 <= saved CR4
+	 * 6. CR3 <= saved CR3
+	 *
+	 * Our mmu_cr4_features has CR4.PCIDE=0, and toggling
+	 * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so
+	 * rdr->cr3 needs to point to valid page tables but must not
+	 * have any of the PCID bits set.
+	 */
+	rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK;
+
+	return hibernation_e820_save(rdr->e820_digest);
+}
+
+/**
+ *	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;
+
+	if (rdr->magic != RESTORE_MAGIC) {
+		pr_crit("Unrecognized hibernate image header format!\n");
+		return -EINVAL;
+	}
+
+	restore_jump_address = rdr->jump_address;
+	jump_address_phys = rdr->jump_address_phys;
+	restore_cr3 = rdr->cr3;
+
+	if (hibernation_e820_mismatch(rdr->e820_digest)) {
+		pr_crit("Hibernate inconsistent memory map detected!\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+int relocate_restore_code(void)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	relocated_restore_code = get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+
+	memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
+
+	/* Make the page containing the relocated code executable */
+	pgd = (pgd_t *)__va(read_cr3_pa()) +
+		pgd_index(relocated_restore_code);
+	p4d = p4d_offset(pgd, relocated_restore_code);
+	if (p4d_large(*p4d)) {
+		set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
+		goto out;
+	}
+	pud = pud_offset(p4d, relocated_restore_code);
+	if (pud_large(*pud)) {
+		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+		goto out;
+	}
+	pmd = pmd_offset(pud, relocated_restore_code);
+	if (pmd_large(*pmd)) {
+		set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		goto out;
+	}
+	pte = pte_offset_kernel(pmd, relocated_restore_code);
+	set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+out:
+	__flush_tlb_all();
+	return 0;
+}
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index afc4ed7b1578..15695e30f982 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -14,9 +14,7 @@
 #include <asm/pgtable.h>
 #include <asm/mmzone.h>
 #include <asm/sections.h>
-
-/* Defined in hibernate_asm_32.S */
-extern int restore_image(void);
+#include <asm/suspend.h>
 
 /* Pointer to the temporary resume page tables */
 pgd_t *resume_pg_dir;
@@ -145,6 +143,32 @@ static inline void resume_init_first_level_page_table(pgd_t *pg_dir)
 #endif
 }
 
+static int set_up_temporary_text_mapping(pgd_t *pgd_base)
+{
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_base + pgd_index(restore_jump_address);
+
+	pmd = resume_one_md_table_init(pgd);
+	if (!pmd)
+		return -ENOMEM;
+
+	if (boot_cpu_has(X86_FEATURE_PSE)) {
+		set_pmd(pmd + pmd_index(restore_jump_address),
+		__pmd((jump_address_phys & PMD_MASK) | pgprot_val(PAGE_KERNEL_LARGE_EXEC)));
+	} else {
+		pte = resume_one_page_table_init(pmd);
+		if (!pte)
+			return -ENOMEM;
+		set_pte(pte + pte_index(restore_jump_address),
+		__pte((jump_address_phys & PAGE_MASK) | pgprot_val(PAGE_KERNEL_EXEC)));
+	}
+
+	return 0;
+}
+
 asmlinkage int swsusp_arch_resume(void)
 {
 	int error;
@@ -154,22 +178,22 @@ asmlinkage int swsusp_arch_resume(void)
 		return -ENOMEM;
 
 	resume_init_first_level_page_table(resume_pg_dir);
+
+	error = set_up_temporary_text_mapping(resume_pg_dir);
+	if (error)
+		return error;
+
 	error = resume_physical_mapping_init(resume_pg_dir);
 	if (error)
 		return error;
 
+	temp_pgt = __pa(resume_pg_dir);
+
+	error = relocate_restore_code();
+	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
index f8e3b668d20b..239f424ccb29 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -26,26 +26,6 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-/* Defined in hibernate_asm_64.S */
-extern asmlinkage __visible 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 __visible;
-unsigned long jump_address_phys;
-
-/*
- * Value of the cr3 register from before the hibernation (this value is passed
- * in the image header).
- */
-unsigned long restore_cr3 __visible;
-
-unsigned long temp_level4_pgt __visible;
-
-unsigned long relocated_restore_code __visible;
-
 static int set_up_temporary_text_mapping(pgd_t *pgd)
 {
 	pmd_t *pmd;
@@ -141,46 +121,7 @@ static int set_up_temporary_mappings(void)
 			return result;
 	}
 
-	temp_level4_pgt = __pa(pgd);
-	return 0;
-}
-
-static int relocate_restore_code(void)
-{
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	relocated_restore_code = get_safe_page(GFP_ATOMIC);
-	if (!relocated_restore_code)
-		return -ENOMEM;
-
-	memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
-
-	/* Make the page containing the relocated code executable */
-	pgd = (pgd_t *)__va(read_cr3_pa()) +
-		pgd_index(relocated_restore_code);
-	p4d = p4d_offset(pgd, relocated_restore_code);
-	if (p4d_large(*p4d)) {
-		set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
-		goto out;
-	}
-	pud = pud_offset(p4d, relocated_restore_code);
-	if (pud_large(*pud)) {
-		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
-		goto out;
-	}
-	pmd = pmd_offset(pud, relocated_restore_code);
-	if (pmd_large(*pmd)) {
-		set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
-		goto out;
-	}
-	pte = pte_offset_kernel(pmd, relocated_restore_code);
-	set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
-out:
-	__flush_tlb_all();
+	temp_pgt = __pa(pgd);
 	return 0;
 }
 
@@ -200,166 +141,3 @@ asmlinkage int swsusp_arch_resume(void)
 	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);
-}
-
-#define MD5_DIGEST_SIZE 16
-
-struct restore_data_record {
-	unsigned long jump_address;
-	unsigned long jump_address_phys;
-	unsigned long cr3;
-	unsigned long magic;
-	u8 e820_digest[MD5_DIGEST_SIZE];
-};
-
-#define RESTORE_MAGIC	0x23456789ABCDEF01UL
-
-#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
-/**
- * get_e820_md5 - calculate md5 according to given e820 table
- *
- * @table: the e820 table to be calculated
- * @buf: the md5 result to be stored to
- */
-static int get_e820_md5(struct e820_table *table, void *buf)
-{
-	struct crypto_shash *tfm;
-	struct shash_desc *desc;
-	int size;
-	int ret = 0;
-
-	tfm = crypto_alloc_shash("md5", 0, 0);
-	if (IS_ERR(tfm))
-		return -ENOMEM;
-
-	desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
-		       GFP_KERNEL);
-	if (!desc) {
-		ret = -ENOMEM;
-		goto free_tfm;
-	}
-
-	desc->tfm = tfm;
-	desc->flags = 0;
-
-	size = offsetof(struct e820_table, entries) +
-		sizeof(struct e820_entry) * table->nr_entries;
-
-	if (crypto_shash_digest(desc, (u8 *)table, size, buf))
-		ret = -EINVAL;
-
-	kzfree(desc);
-
-free_tfm:
-	crypto_free_shash(tfm);
-	return ret;
-}
-
-static void hibernation_e820_save(void *buf)
-{
-	get_e820_md5(e820_table_firmware, buf);
-}
-
-static bool hibernation_e820_mismatch(void *buf)
-{
-	int ret;
-	u8 result[MD5_DIGEST_SIZE];
-
-	memset(result, 0, MD5_DIGEST_SIZE);
-	/* If there is no digest in suspend kernel, let it go. */
-	if (!memcmp(result, buf, MD5_DIGEST_SIZE))
-		return false;
-
-	ret = get_e820_md5(e820_table_firmware, result);
-	if (ret)
-		return true;
-
-	return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
-}
-#else
-static void hibernation_e820_save(void *buf)
-{
-}
-
-static bool hibernation_e820_mismatch(void *buf)
-{
-	/* If md5 is not builtin for restore kernel, let it go. */
-	return false;
-}
-#endif
-
-/**
- *	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 = (unsigned long)restore_registers;
-	rdr->jump_address_phys = __pa_symbol(restore_registers);
-
-	/*
-	 * The restore code fixes up CR3 and CR4 in the following sequence:
-	 *
-	 * [in hibernation asm]
-	 * 1. CR3 <= temporary page tables
-	 * 2. CR4 <= mmu_cr4_features (from the kernel that restores us)
-	 * 3. CR3 <= rdr->cr3
-	 * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel)
-	 * [in restore_processor_state()]
-	 * 5. CR4 <= saved CR4
-	 * 6. CR3 <= saved CR3
-	 *
-	 * Our mmu_cr4_features has CR4.PCIDE=0, and toggling
-	 * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so
-	 * rdr->cr3 needs to point to valid page tables but must not
-	 * have any of the PCID bits set.
-	 */
-	rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK;
-
-	rdr->magic = RESTORE_MAGIC;
-
-	hibernation_e820_save(rdr->e820_digest);
-
-	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;
-	jump_address_phys = rdr->jump_address_phys;
-	restore_cr3 = rdr->cr3;
-
-	if (rdr->magic != RESTORE_MAGIC) {
-		pr_crit("Unrecognized hibernate image header format!\n");
-		return -EINVAL;
-	}
-
-	if (hibernation_e820_mismatch(rdr->e820_digest)) {
-		pr_crit("Hibernate inconsistent memory map detected!\n");
-		return -ENODEV;
-	}
-
-	return 0;
-}
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 6e56815e13a0..6fe383002125 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -12,6 +12,7 @@
 #include <asm/page_types.h>
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
+#include <asm/frame.h>
 
 .text
 
@@ -24,13 +25,30 @@ ENTRY(swsusp_arch_suspend)
 	pushfl
 	popl saved_context_eflags
 
+	/* save cr3 */
+	movl	%cr3, %eax
+	movl	%eax, restore_cr3
+
+	FRAME_BEGIN
 	call swsusp_save
+	FRAME_END
 	ret
+ENDPROC(swsusp_arch_suspend)
 
 ENTRY(restore_image)
+	/* prepare to jump to the image kernel */
+	movl	restore_jump_address, %ebx
+	movl	restore_cr3, %ebp
+
 	movl	mmu_cr4_features, %ecx
-	movl	resume_pg_dir, %eax
-	subl	$__PAGE_OFFSET, %eax
+
+	/* jump to relocated restore code */
+	movl	relocated_restore_code, %eax
+	jmpl	*%eax
+
+/* code below has been relocated to a safe page */
+ENTRY(core_restore_code)
+	movl	temp_pgt, %eax
 	movl	%eax, %cr3
 
 	jecxz	1f	# cr4 Pentium and higher, skip if zero
@@ -49,7 +67,7 @@ copy_loop:
 	movl	pbe_address(%edx), %esi
 	movl	pbe_orig_address(%edx), %edi
 
-	movl	$1024, %ecx
+	movl	$(PAGE_SIZE >> 2), %ecx
 	rep
 	movsl
 
@@ -58,10 +76,13 @@ copy_loop:
 	.p2align 4,,7
 
 done:
+	jmpl	*%ebx
+
+	/* code below belongs to the image kernel */
+	.align PAGE_SIZE
+ENTRY(restore_registers)
 	/* go back to the original page tables */
-	movl	$swapper_pg_dir, %eax
-	subl	$__PAGE_OFFSET, %eax
-	movl	%eax, %cr3
+	movl	%ebp, %cr3
 	movl	mmu_cr4_features, %ecx
 	jecxz	1f	# cr4 Pentium and higher, skip if zero
 	movl	%ecx, %cr4;  # turn PGE back on
@@ -82,4 +103,8 @@ done:
 
 	xorl	%eax, %eax
 
+	/* tell the hibernation core that we've just restored the memory */
+	movl	%eax, in_suspend
+
 	ret
+ENDPROC(restore_registers)
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index fd369a6e9ff8..3008baa2fa95 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -59,7 +59,7 @@ ENTRY(restore_image)
 	movq	restore_cr3(%rip), %r9
 
 	/* prepare to switch to temporary page tables */
-	movq	temp_level4_pgt(%rip), %rax
+	movq	temp_pgt(%rip), %rax
 	movq	mmu_cr4_features(%rip), %rbx
 
 	/* prepare to copy image data to their original locations */