x86/mm, x86/mce: Add memcpy_mcsafe()

Make use of the EXTABLE_FAULT exception table entries to write
a kernel copy routine that doesn't crash the system if it
encounters a machine check. Prime use case for this is to copy
from large arrays of non-volatile memory used as storage.

We have to use an unrolled copy loop for now because current
hardware implementations treat a machine check in "rep mov"
as fatal. When that is fixed we can simplify.

Return type is a "bool". True means that we copied OK, false means
that it didn't.

Signed-off-by: Tony Luck <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tony Luck <[email protected]>
Link: http://lkml.kernel.org/r/a44e1055efc2d2a9473307b22c91caa437aa3f8b.1456439214.git.tony.luck@intel.com
Signed-off-by: Ingo Molnar <[email protected]>

Author: aegl

arch/x86/include/asm/string_64.h

@@ -78,6 +78,19 @@ int strcmp(const char *cs, const char *ct);
 #define memset(s, c, n) __memset(s, c, n)
 #endif
 
+/**
+ * memcpy_mcsafe - copy memory with indication if a machine check happened
+ *
+ * @dst:	destination address
+ * @src:	source address
+ * @cnt:	number of bytes to copy
+ *
+ * Low level memory copy function that catches machine checks
+ *
+ * Return true for success, false for fail
+ */
+bool memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_STRING_64_H */

arch/x86/kernel/x8664_ksyms_64.c

@@ -37,6 +37,8 @@ EXPORT_SYMBOL(__copy_user_nocache);
 EXPORT_SYMBOL(_copy_from_user);
 EXPORT_SYMBOL(_copy_to_user);
 
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
+
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(clear_page);
 

arch/x86/lib/memcpy_64.S

@@ -177,3 +177,120 @@ ENTRY(memcpy_orig)
 .Lend:
 	retq
 ENDPROC(memcpy_orig)
+
+#ifndef CONFIG_UML
+/*
+ * memcpy_mcsafe - memory copy with machine check exception handling
+ * Note that we only catch machine checks when reading the source addresses.
+ * Writes to target are posted and don't generate machine checks.
+ */
+ENTRY(memcpy_mcsafe)
+	cmpl $8, %edx
+	/* Less than 8 bytes? Go to byte copy loop */
+	jb .L_no_whole_words
+
+	/* Check for bad alignment of source */
+	testl $7, %esi
+	/* Already aligned */
+	jz .L_8byte_aligned
+
+	/* Copy one byte at a time until source is 8-byte aligned */
+	movl %esi, %ecx
+	andl $7, %ecx
+	subl $8, %ecx
+	negl %ecx
+	subl %ecx, %edx
+.L_copy_leading_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_leading_bytes
+
+.L_8byte_aligned:
+	/* Figure out how many whole cache lines (64-bytes) to copy */
+	movl %edx, %ecx
+	andl $63, %edx
+	shrl $6, %ecx
+	jz .L_no_whole_cache_lines
+
+	/* Loop copying whole cache lines */
+.L_cache_w0: movq (%rsi), %r8
+.L_cache_w1: movq 1*8(%rsi), %r9
+.L_cache_w2: movq 2*8(%rsi), %r10
+.L_cache_w3: movq 3*8(%rsi), %r11
+	movq %r8, (%rdi)
+	movq %r9, 1*8(%rdi)
+	movq %r10, 2*8(%rdi)
+	movq %r11, 3*8(%rdi)
+.L_cache_w4: movq 4*8(%rsi), %r8
+.L_cache_w5: movq 5*8(%rsi), %r9
+.L_cache_w6: movq 6*8(%rsi), %r10
+.L_cache_w7: movq 7*8(%rsi), %r11
+	movq %r8, 4*8(%rdi)
+	movq %r9, 5*8(%rdi)
+	movq %r10, 6*8(%rdi)
+	movq %r11, 7*8(%rdi)
+	leaq 64(%rsi), %rsi
+	leaq 64(%rdi), %rdi
+	decl %ecx
+	jnz .L_cache_w0
+
+	/* Are there any trailing 8-byte words? */
+.L_no_whole_cache_lines:
+	movl %edx, %ecx
+	andl $7, %edx
+	shrl $3, %ecx
+	jz .L_no_whole_words
+
+	/* Copy trailing words */
+.L_copy_trailing_words:
+	movq (%rsi), %r8
+	mov %r8, (%rdi)
+	leaq 8(%rsi), %rsi
+	leaq 8(%rdi), %rdi
+	decl %ecx
+	jnz .L_copy_trailing_words
+
+	/* Any trailing bytes? */
+.L_no_whole_words:
+	andl %edx, %edx
+	jz .L_done_memcpy_trap
+
+	/* Copy trailing bytes */
+	movl %edx, %ecx
+.L_copy_trailing_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_trailing_bytes
+
+	/* Copy successful. Return true */
+.L_done_memcpy_trap:
+	xorq %rax, %rax
+	ret
+ENDPROC(memcpy_mcsafe)
+
+	.section .fixup, "ax"
+	/* Return false for any failure */
+.L_memcpy_mcsafe_fail:
+	mov	$1, %rax
+	ret
+
+	.previous
+
+	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+#endif