Fixes hibernation bugs on x86-32 system

index b4866badb235..90ecc108bc8a 100644
@@ -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();
 

index f8e3b668d20b..dc12dc57889e 100644
@@ -265,9 +265,9 @@ static int get_e820_md5(struct e820_table *table, void *buf)
 	return ret;
 }
 
-static void hibernation_e820_save(void *buf)
+static int hibernation_e820_save(void *buf)
 {
-	get_e820_md5(e820_table_firmware, buf);
+	return get_e820_md5(e820_table_firmware, buf);
 }
 
 static bool hibernation_e820_mismatch(void *buf)

@@ -287,8 +287,9 @@ static bool hibernation_e820_mismatch(void *buf)
 	return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
 }
 #else
-static void hibernation_e820_save(void *buf)
+static int hibernation_e820_save(void *buf)
 {
+	return 0;
 }
 
 static bool hibernation_e820_mismatch(void *buf)

@@ -306,6 +307,7 @@ static bool hibernation_e820_mismatch(void *buf)
 int arch_hibernation_header_save(void *addr, unsigned int max_size)
 {
 	struct restore_data_record *rdr = addr;
+	int ret = -EINVAL;
 
 	if (max_size < sizeof(struct restore_data_record))
 		return -EOVERFLOW;

@@ -333,7 +335,9 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 
 	rdr->magic = RESTORE_MAGIC;
 
-	hibernation_e820_save(rdr->e820_digest);
+	ret = hibernation_e820_save(rdr->e820_digest);
+	if (ret)
+		return ret;
 
 	return 0;
 }

new file mode 100644
index 000000000000..6aeac4d3c9df
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hibernation support for x86
+ *
+ * Copyright (c) 2007 Rafael J. Wysocki <[email protected]>
+ * Copyright (c) 2002 Pavel Machek <[email protected]>
+ * Copyright (c) 2001 Patrick Mochel <[email protected]>
+ */
+
+#include <linux/gfp.h>
+#include <linux/smp.h>
+#include <linux/suspend.h>
+#include <linux/scatterlist.h>
+#include <linux/kdebug.h>
+#include <linux/bootmem.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>
+#include <asm/mmzone.h>
+
+/* Defined in hibernate_asm_64.S or hibernate_asm_32.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_pgt __visible;
+unsigned long relocated_restore_code __visible;
+
+#ifdef CONFIG_X86_32
+	#define RESTORE_MAGIC	0x12345678UL
+#else
+	#define RESTORE_MAGIC	0x23456789ABCDEF01UL
+#endif
+
+/**
+ * pfn_is_nosave - check if given pfn is in the 'nosave' section
+ * @pfn:	the page frame number to be checked
+ *
+ * returns non-zero if the pfn is in the 'nosave' section,
+ * otherwise returns zero
+ */
+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;
+}
+
+#ifdef CONFIG_X86_64
+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();
+	return 0;
+}
+
+#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
+
+/**
+ *	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;
+	int ret = -EINVAL;
+
+	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;
+
+	ret = hibernation_e820_save(rdr->e820_digest);
+	if (ret)
+		return ret;
+
+	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;
+}
+#endif

index afc4ed7b1578..e0e7b9aea22a 100644
@@ -6,17 +6,7 @@
  * Copyright (c) 2006 Rafael J. Wysocki <[email protected]>
  */
 
-#include <linux/gfp.h>
-#include <linux/suspend.h>
-#include <linux/bootmem.h>
-
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/mmzone.h>
-#include <asm/sections.h>
-
-/* Defined in hibernate_asm_32.S */
-extern int restore_image(void);
+#include "hibernate.c"
 
 /* Pointer to the temporary resume page tables */
 pgd_t *resume_pg_dir;

@@ -162,14 +152,3 @@ 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);
-}

261 lines not on this page · raw message

index 8be6afb58471..fdbd9d7b7bca 100644
@@ -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 */

index 6aeac4d3c9df..d719d156114b 100644
@@ -69,7 +69,6 @@ int pfn_is_nosave(unsigned long pfn)
 	return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn;
 }
 
-#ifdef CONFIG_X86_64
 static int relocate_restore_code(void)
 {
 	pgd_t *pgd;

@@ -262,4 +261,3 @@ int arch_hibernation_header_restore(void *addr)
 
 	return 0;
 }
-#endif

index e0e7b9aea22a..d692700047bf 100644
@@ -135,6 +135,32 @@ 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;

@@ -144,10 +170,21 @@ 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;