Skip to contentSkip to conversation

Fixes hibernation bugs on x86-32 system

PATCH Superseded Chen Yu 3 participants 9 messages Sep 11, 2018 – Sep 18, 2018

Subsystems (2)

v2 of 4 Superseded Latest is v4 →

lore
Share & tools
lore

Chen Yu

author
#0 lore raw

v2 cover Fixes hibernation bugs on x86-32 system

Currently there are mainly three bugs in x86-32 system when doing hibernation:
1. The page copy code is not running in safe page, which might cause hang during resume.
2. There's no text mapping for the final jump address
of the original kernel, which might cause the system jumping into illegal address and causes system hang during resume.
3. The restore kernel switches to its own kernel page table(swapper_pg_dir) rather than the original kernel page table after all the pages been copied back, which might cause invalid virtual-physical mapping issue during resume.

To solve these problems:

1. Copy the code core_restore_code to a safe page, to avoid the instruction code be overwriten when image kernel pages are being copied.
2. Set up temporary text mapping for the image kernel's jump address, so that after all the pages have been copied back, the system could jump to this address.
3. Switch to the original kernel page table during resume.

Furthermore, MD5 hash check for e820 map is also backported from 64bits

Chen Yu (1):
PM / hibernate: Check the success of generating md5 digest before
hibernation

Zhimin Gu (3):
x86, hibernate: Fix nosave_regions setup for hibernation x86, hibernate: Extract the common code of 64/32 bit system x86, hibernate: Backport several fixes from 64bits to 32bits
hibernation

 arch/x86/Kconfig                  |   2 +-
 arch/x86/include/asm/suspend_32.h |   4 +
 arch/x86/kernel/setup.c           |   2 +-
 arch/x86/power/hibernate.c        | 263 ++++++++++++++++++++++++++++++
 arch/x86/power/hibernate_32.c     |  60 ++++---
 arch/x86/power/hibernate_64.c     | 242 +--------------------------
 arch/x86/power/hibernate_asm_32.S |  49 +++++-
 arch/x86/power/hibernate_asm_64.S |   2 +-
 8 files changed, 350 insertions(+), 274 deletions(-)
 create mode 100644 arch/x86/power/hibernate.c
Signature · 1 line
2.17.1
author
#1 lore raw

PATCH v2 1/4 x86, hibernate: Fix nosave_regions setup for hibernation

From: Zhimin Gu <[email protected]>

On 32bit systems, nosave_regions(non RAM areas) located between max_low_pfn and max_pfn are not excluded from hibernation snapshot currently, which may result in a machine check exception when trying to access these unsafe regions during hibernation:

[  612.800453] Disabling lock debugging due to kernel taint
[  612.805786] mce: [Hardware Error]: CPU 0: Machine Check Exception: 5 Bank 6: fe00000000801136
[  612.814344] mce: [Hardware Error]: RIP !INEXACT! 60:<00000000d90be566> {swsusp_save+0x436/0x560}
[  612.823167] mce: [Hardware Error]: TSC 1f5939fe276 ADDR dd000000 MISC 30e0000086
[  612.830677] mce: [Hardware Error]: PROCESSOR 0:306c3 TIME 1529487426 SOCKET 0 APIC 0 microcode 24
[  612.839581] mce: [Hardware Error]: Run the above through 'mcelog --ascii'
[  612.846394] mce: [Hardware Error]: Machine check: Processor context corrupt
[  612.853380] Kernel panic - not syncing: Fatal machine check
[  612.858978] Kernel Offset: 0x18000000 from 0xc1000000 (relocation range: 0xc0000000-0xf7ffdfff)

This is because on 32bit systems, pages above max_low_pfn are regarded as high memeory, and accessing unsafe pages might cause expected MCE. On the problematic 32bit system, there are reserved memory above low memory, which triggered the MCE:

e820 memory mapping:

[    0.000000] BIOS-e820: [mem 0x0000000000000000-0x000000000009d7ff] usable
[    0.000000] BIOS-e820: [mem 0x000000000009d800-0x000000000009ffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000000e0000-0x00000000000fffff] reserved
[    0.000000] BIOS-e820: [mem 0x0000000000100000-0x00000000d160cfff] usable
[    0.000000] BIOS-e820: [mem 0x00000000d160d000-0x00000000d1613fff] ACPI NVS
[    0.000000] BIOS-e820: [mem 0x00000000d1614000-0x00000000d1a44fff] usable
[    0.000000] BIOS-e820: [mem 0x00000000d1a45000-0x00000000d1ecffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000d1ed0000-0x00000000d7eeafff] usable
[    0.000000] BIOS-e820: [mem 0x00000000d7eeb000-0x00000000d7ffffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000d8000000-0x00000000d875ffff] usable
[    0.000000] BIOS-e820: [mem 0x00000000d8760000-0x00000000d87fffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000d8800000-0x00000000d8fadfff] usable
[    0.000000] BIOS-e820: [mem 0x00000000d8fae000-0x00000000d8ffffff] ACPI data
[    0.000000] BIOS-e820: [mem 0x00000000d9000000-0x00000000da71bfff] usable
[    0.000000] BIOS-e820: [mem 0x00000000da71c000-0x00000000da7fffff] ACPI NVS
[    0.000000] BIOS-e820: [mem 0x00000000da800000-0x00000000dbb8bfff] usable
[    0.000000] BIOS-e820: [mem 0x00000000dbb8c000-0x00000000dbffffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000dd000000-0x00000000df1fffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000f8000000-0x00000000fbffffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000fec00000-0x00000000fec00fff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000fed00000-0x00000000fed03fff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000fed1c000-0x00000000fed1ffff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000fee00000-0x00000000fee00fff] reserved
[    0.000000] BIOS-e820: [mem 0x00000000ff000000-0x00000000ffffffff] reserved
[    0.000000] BIOS-e820: [mem 0x0000000100000000-0x000000041edfffff] usable

Fix this problem by changing pfn limit from max_low_pfn to max_pfn. This fix does not impact 64bit system because on 64bit max_low_pfn is the same as max_pfn.

---
 arch/x86/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kernel/setup.c +1 -1
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();
 
Signature · 1 line
2.17.1
author
#2 lore raw

PATCH v2 2/4 PM / hibernate: Check the success of generating md5 digest before hibernation

In reply to Chen Yu

Currently if get_e820_md5() fails, then it will hibernate nevertheless. Actually the error code should be propagated to upper caller so that the hibernation could be aware of the result and terminates the process if md5 digest fails.

---
 arch/x86/power/hibernate_64.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)
arch/x86/power/hibernate_64.c +8 -4
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;
 }
Signature · 1 line
2.17.1
#3 lore raw

Re: [PATCH 2/4][v2] PM / hibernate: Check the success of generating md5 digest before hibernation

arch/x86/power/hibernate_64.c static bool hibernation_e820_mismatch(void *buf) · line 310

Quoted 6 lines · Chen Yu

static bool hibernation_e820_mismatch(void *buf)

arch/x86/power/hibernate_64.c +1 -0
@@ -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;

What's the point of initializing ret?

arch/x86/power/hibernate_64.c int arch_hibernation_header_save(void *addr, unsigned int max_size) · line 342

Quoted 12 lines
arch/x86/power/hibernate_64.c +3 -1
 	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;

And what;s the point of ret at all?

	return hibernation_e820_save();

is effectivly the same.

Thanks,

tglx

author
#4 lore raw

Re: [PATCH 2/4][v2] PM / hibernate: Check the success of generating md5 digest before hibernation

Hi Thomas,

Quoted 21 lines · Thomas Gleixner

arch/x86/power/hibernate_64.c static bool hibernation_e820_mismatch(void *buf) · line 310

Quoted 6 lines · Chen Yu

static bool hibernation_e820_mismatch(void *buf)

arch/x86/power/hibernate_64.c +1 -0
@@ -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;

What's the point of initializing ret?

Quoted 11 lines
arch/x86/power/hibernate_64.c +3 -1
 	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;
 
Quoted 8 lines

arch/x86/power/hibernate_64.c int arch_hibernation_header_save(void *addr, unsigned int max_size) · line 342

Quoted 1 line
arch/x86/power/hibernate_64.c +0 -0
 	return 0;

And what;s the point of ret at all?

	return hibernation_e820_save();

is effectivly the same.

ret is useless, will change to 'return hibernation_e820_save()' here. Thanks,
Yu

Quoted 3 lines

Thanks,

tglx

author
#5 lore raw

PATCH v2 3/4 x86, hibernate: Extract the common code of 64/32 bit system

In reply to Chen Yu

From: Zhimin Gu <[email protected]>

Reduce the hibernation code duplication between x86-32 and x86-64 by extracting the common code into hibernate.c.

No functional change.

---
 arch/x86/power/hibernate.c        | 265 ++++++++++++++++++++++++++++++
 arch/x86/power/hibernate_32.c     |  23 +--
 arch/x86/power/hibernate_64.c     | 246 +--------------------------
 arch/x86/power/hibernate_asm_64.S |   2 +-
 4 files changed, 269 insertions(+), 267 deletions(-)
 create mode 100644 arch/x86/power/hibernate.c
arch/x86/power/hibernate.c new file +265 -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
arch/x86/power/hibernate_32.c +1 -22
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);
-}
arch/x86/power/hibernate_64.c +2 -244

261 lines not on this page · raw message

arch/x86/power/hibernate_asm_64.S +1 -1
index fd369a6e9ff8..3008baa2fa95 100644
@@ -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 */
Signature · 1 line
2.17.1
#6 lore raw

Re: [PATCH 3/4][v2] x86, hibernate: Extract the common code of 64/32 bit system

Quoted 301 lines · CEST Chen Yu

From: Zhimin Gu <[email protected]>

Reduce the hibernation code duplication between x86-32 and x86-64 by extracting the common code into hibernate.c.

No functional change.

---
 arch/x86/power/hibernate.c        | 265 ++++++++++++++++++++++++++++++
 arch/x86/power/hibernate_32.c     |  23 +--
 arch/x86/power/hibernate_64.c     | 246 +--------------------------
 arch/x86/power/hibernate_asm_64.S |   2 +-
 4 files changed, 269 insertions(+), 267 deletions(-)
 create mode 100644 arch/x86/power/hibernate.c
arch/x86/power/hibernate.c new file +265 -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
arch/x86/power/hibernate_32.c +0 -2
index afc4ed7b1578..e0e7b9aea22a 100644
@@ -6,17 +6,7 @@
  * Copyright (c) 2006 Rafael J. Wysocki <[email protected]>
  */
 
-#include <linux/gfp.h>
-#include <linux/suspend.h>

arch/x86/power/hibernate_32.c line 9

Quoted 10 lines
arch/x86/power/hibernate_32.c +1 -9
-#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"

I don't particularly like this.

Why excatly do you need to include the C file here?

Also, the way this change is made makes it quite hard to review, as the new code is not exactly the same as the code being removed, so it is hard to say whether or not there really are no functional changes as claimed.

This is sensitive code, mind you, and really hard to debug if anything goes wrong. Please be super-careful about changing it.

Thanks,
Rafael

author
#7 lore raw

Re: [PATCH 3/4][v2] x86, hibernate: Extract the common code of 64/32 bit system

Hi,

Quoted 6 lines · Rafael J. Wysocki
Quoted 5 lines · CEST Chen Yu

From: Zhimin Gu <[email protected]>

Reduce the hibernation code duplication between x86-32 and x86-64 by extracting the common code into hibernate.c.

Quoted 8 lines
Quoted 3 lines

No functional change.

+#include "hibernate.c"

I don't particularly like this.

Why excatly do you need to include the C file here?

OK, I've removed this in a new version.

Quoted 4 lines

Also, the way this change is made makes it quite hard to review, as the new code is not exactly the same as the code being removed, so it is hard to say whether or not there really are no functional changes as claimed.

I've splitted the patch into several sub-patches and reorganized the code to make it more readable on a new version.

Quoted 4 lines

This is sensitive code, mind you, and really hard to debug if anything goes wrong. Please be super-careful about changing it.

Ok, will test on several platforms and send out the modification. Best,
Yu

Quoted 3 lines

Thanks,
Rafael

author
#8 lore raw

PATCH v2 4/4 x86, hibernate: Backport several fixes from 64bits to 32bits hibernation

In reply to Chen Yu

From: Zhimin Gu <[email protected]>

Currently there are mainly three bugs in 32bits system when doing hibernation:
1. The page copy code is not running in safe page, which might cause hang during resume.
2. There's no text mapping for the final jump address
of the original kernel, which might cause the system jumping into illegal address and causes system hang during resume.
3. The restore kernel switches to its own kernel page table(swapper_pg_dir) rather than the original kernel page table after all the pages been copied back, which might cause invalid virtual-physical mapping issue during resume.

To solve these problems:

1. Copy the code core_restore_code to a safe page, to avoid the instruction code been overwritten when image kernel pages are being copied.
2. Set up temporary text mapping for the image kernel's jump address, so that after all the pages have been copied back, the system could jump to this address.
3. Switch to the original kernel page table during resume.

Furthermore, MD5 hash check for e820 map is also backported from 64bits system.

Cc "Rafael J. Wysocki" <[email protected]>
Cc Thomas Gleixner <[email protected]>
---
 arch/x86/Kconfig                  |  2 +-
 arch/x86/include/asm/suspend_32.h |  4 +++
 arch/x86/power/hibernate.c        |  2 --
 arch/x86/power/hibernate_32.c     | 37 +++++++++++++++++++++++
 arch/x86/power/hibernate_asm_32.S | 49 +++++++++++++++++++++++++------
 5 files changed, 82 insertions(+), 12 deletions(-)
arch/x86/Kconfig +1 -1
index 1a0be022f91d..e8de5de1057f 100644
@@ -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"
 
arch/x86/include/asm/suspend_32.h +4 -0
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 */
arch/x86/power/hibernate.c +0 -2
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
arch/x86/power/hibernate_32.c +37 -0
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;
arch/x86/power/hibernate_asm_32.S +40 -9

85 lines not on this page · raw message

Signature · 1 line
2.17.1