@@ -1,6 +1,51 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_STRING_H
+#define _ASM_X86_STRING_H
+
+#include <asm/asm.h>
+#include <asm/alternative.h>
+
#ifdef CONFIG_X86_32
# include <asm/string_32.h>
#else
# include <asm/string_64.h>
#endif
+
+#ifdef CONFIG_X86_64
+#define ALT_64(orig, alt, feat) ALTERNATIVE(orig, alt, feat)
+#else
+#define ALT_64(orig, alt, feat) orig
+#endif
+
+static __always_inline void *__inline_memcpy(void *to, const void *from, size_t len)
+{
+ void *ret = to;
+
+ asm volatile("1:\n\t"
+ ALT_64("rep movsb",
+ "call rep_movs_alternative", ALT_NOT(X86_FEATURE_FSRM))
+ "2:\n\t"
+ _ASM_EXTABLE_UA(1b, 2b)
+ :"+c" (len), "+D" (to), "+S" (from), ASM_CALL_CONSTRAINT
+ : : "memory", _ASM_AX);
+
+ return ret + len;
+}
+
+static __always_inline void *__inline_memset(void *addr, int v, size_t len)
+{
+ void *ret = addr;
+
+ asm volatile("1:\n\t"
+ ALT_64("rep stosb",
+ "call rep_stos_alternative", ALT_NOT(X86_FEATURE_FSRM))
+ "2:\n\t"
+ _ASM_EXTABLE_UA(1b, 2b)
+ : "+c" (len), "+D" (addr), ASM_CALL_CONSTRAINT
+ : "a" ((uint8_t)v)
+ : "memory", _ASM_SI);
+
+ return ret + len;
+}
+
+#endif /* _ASM_X86_STRING_H */
@@ -13,6 +13,7 @@
#include <asm/page.h>
#include <asm/percpu.h>
#include <asm/runtime-const.h>
+#include <asm/string.h>
/*
* Virtual variable: there's no actual backing store for this,
@@ -118,21 +119,12 @@ rep_movs_alternative(void *to, const void *from, unsigned len);
static __always_inline __must_check unsigned long
copy_user_generic(void *to, const void *from, unsigned long len)
{
+ void *ret;
+
stac();
- /*
- * If CPU has FSRM feature, use 'rep movs'.
- * Otherwise, use rep_movs_alternative.
- */
- asm volatile(
- "1:\n\t"
- ALTERNATIVE("rep movsb",
- "call rep_movs_alternative", ALT_NOT(X86_FEATURE_FSRM))
- "2:\n"
- _ASM_EXTABLE_UA(1b, 2b)
- :"+c" (len), "+D" (to), "+S" (from), ASM_CALL_CONSTRAINT
- : : "memory", "rax");
+ ret = __inline_memcpy(to, from, len);
clac();
- return len;
+ return ret - to;
}
static __always_inline __must_check unsigned long
@@ -178,25 +170,14 @@ rep_stos_alternative(void __user *addr, unsigned long len);
static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size)
{
+ void *ret;
+
might_fault();
stac();
-
- /*
- * No memory constraint because it doesn't change any memory gcc
- * knows about.
- */
- asm volatile(
- "1:\n\t"
- ALTERNATIVE("rep stosb",
- "call rep_stos_alternative", ALT_NOT(X86_FEATURE_FSRS))
- "2:\n"
- _ASM_EXTABLE_UA(1b, 2b)
- : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT
- : "a" (0));
-
+ ret = __inline_memset(addr, 0, size);
clac();
- return size;
+ return ret - addr;
}
static __always_inline unsigned long clear_user(void __user *to, unsigned long n)
@@ -55,17 +55,23 @@ SYM_FUNC_END(clear_page_erms)
EXPORT_SYMBOL_GPL(clear_page_erms)
/*
- * Default clear user-space.
+ * Default memset.
* Input:
* rdi destination
+ * rsi scratch
* rcx count
- * rax is zero
+ * al is value
*
* Output:
* rcx: uncleared bytes or 0 if successful.
*/
SYM_FUNC_START(rep_stos_alternative)
ANNOTATE_NOENDBR
+
+ movzbq %al, %rsi
+ movabs $0x0101010101010101, %rax
+ mulq %rsi
+
cmpq $64,%rcx
jae .Lunrolled
Extract memcpy and memset functions from copy_user_generic() and __clear_user(). They can be used as inline memcpy and memset instead of the GCC builtins whenever necessary. LASS requires them to handle text_poke. Originally-by: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/all/20241029184840.GJ14555@noisy.programming.kicks-ass.net/ Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> --- arch/x86/include/asm/string.h | 45 +++++++++++++++++++++++++++++++ arch/x86/include/asm/uaccess_64.h | 37 +++++++------------------ arch/x86/lib/clear_page_64.S | 10 +++++-- 3 files changed, 62 insertions(+), 30 deletions(-)