Fixes hibernation bugs on x86-32 system

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 issue should also exist on 64bits systems, if there are reserved regions above 4GB.

Acked-by Chen Yu <[email protected]>

Signed-off-by Zhimin Gu <[email protected]>

Fix this problem by changing pfn limit from max_low_pfn to max_pfn. This issue should also exist on 64bits systems, if there are reserved regions above 4GB.

Quoted 4 lines · Gu Zhimin

Fix this problem by changing pfn limit from max_low_pfn to max_pfn. This issue should also exist on 64bits systems, if there are reserved regions above 4GB.

Should? Can we please have facts and not some half baken assumptions?

On 64bit max_low_pfn is the same as max_pfn. See init_mem_mapping().

Thanks,

tglx

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.

Suggested-by Pavel Machek <[email protected]>

Acked-by Chen Yu <[email protected]>

Signed-off-by Zhimin Gu <[email protected]>

arch/x86/power/hibernate.c new file +86 -0

+}
+
+#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;
+

arch/x86/power/hibernate.c line 4

Quoted 10 lines · Gu Zhimin

arch/x86/power/hibernate.c new file +4 -0

new file mode 100644
index 0000000..6f91f7b
@@ -0,0 +1,255 @@
+/*
+ * Hibernation support for x86
+ *
+ * Distribute under GPLv2

We have SPDX identifiers for that and not some randomly chosen license hint.

arch/x86/power/hibernate.c line 56

Quoted 3 lines

arch/x86/power/hibernate.c new file +3 -0

+
+/*
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section

This is a half baken kernel doc header.

arch/x86/power/hibernate.c line 9

Quoted 2 lines

arch/x86/power/hibernate.c new file +2 -0

+ */
+

Random new line.

arch/x86/power/hibernate.c line 62

Quoted 4 lines

arch/x86/power/hibernate.c new file +4 -0

+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;

Instead of blindly copying stuff please fix it so it matches kernel coding rules.

arch/x86/power/hibernate.c line 63

Quoted 1 line

arch/x86/power/hibernate.c new file +1 -0

+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);

The brackets are pointless

Quoted 91 lines

arch/x86/power/hibernate.c new file +91 -0

+}
+
+#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;

arch/x86/power/hibernate.c line 159

Quoted 5 lines

arch/x86/power/hibernate.c new file +5 -0

+}
+
+static void hibernation_e820_save(void *buf)
+{
+	get_e820_md5(e820_table_firmware, buf);

So if get_e820_md5() fails, then it will hibernate nevertheless. Why is that error code not propagated?

Thanks,

tglx