Merge branch 'x86-rep-insns': x86 user copy clarifications

Merge my x86 user copy updates branch.

This cleans up a lot of our x86 memory copy code, particularly for user
accesses.  I've been pushing for microarchitectural support for good
memory copying and clearing for a long while, and it's been visible in
how the kernel has aggressively used 'rep movs' and 'rep stos' whenever
possible.

And that micro-architectural support has been improving over the years,
to the point where on modern CPU's the best option for a memory copy
that would become a function call (as opposed to being something that
can just be turned into individual 'mov' instructions) is now to inline
the string instruction sequence instead.

However, that only makes sense when we have the modern markers for this:
the x86 FSRM and FSRS capabilities ("Fast Short REP MOVS/STOS").

So this cleans up a lot of our historical code, gets rid of the legacy
marker use ("REP_GOOD" and "ERMS") from the memcpy/memset cases, and
replaces it with that modern reality.  Note that REP_GOOD and ERMS end
up still being used by the known large cases (ie page copyin gand
clearing).

The reason much of this ends up being about user memory accesses is that
the normal in-kernel cases are done by the compiler (__builtin_memcpy()
and __builtin_memset()) and getting to the point where we can use our
instruction rewriting to inline those to be string instructions will
need some compiler support.

In contrast, the user accessor functions are all entirely controlled by
the kernel code, so we can change those arbitrarily.

Thanks to Borislav Petkov for feedback on the series, and Jens testing
some of this on micro-architectures I didn't personally have access to.

* x86-rep-insns:
  x86: rewrite '__copy_user_nocache' function
  x86: remove 'zerorest' argument from __copy_user_nocache()
  x86: set FSRS automatically on AMD CPUs that have FSRM
  x86: improve on the non-rep 'copy_user' function
  x86: improve on the non-rep 'clear_user' function
  x86: inline the 'rep movs' in user copies for the FSRM case
  x86: move stac/clac from user copy routines into callers
  x86: don't use REP_GOOD or ERMS for user memory clearing
  x86: don't use REP_GOOD or ERMS for user memory copies
  x86: don't use REP_GOOD or ERMS for small memory clearing
  x86: don't use REP_GOOD or ERMS for small memory copies

1 files changed, 25 insertions, 37 deletions

diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index d13d71af5cf6..0a49a8de9f3c 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -18,32 +18,26 @@
 
 /* Handles exceptions in both to and from, but doesn't do access_ok */
 __must_check unsigned long
-copy_user_enhanced_fast_string(void *to, const void *from, unsigned len);
-__must_check unsigned long
-copy_user_generic_string(void *to, const void *from, unsigned len);
-__must_check unsigned long
-copy_user_generic_unrolled(void *to, const void *from, unsigned len);
+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 len)
+copy_user_generic(void *to, const void *from, unsigned long len)
 {
-	unsigned ret;
-
+	stac();
 	/*
-	 * If CPU has ERMS feature, use copy_user_enhanced_fast_string.
-	 * Otherwise, if CPU has rep_good feature, use copy_user_generic_string.
-	 * Otherwise, use copy_user_generic_unrolled.
+	 * If CPU has FSRM feature, use 'rep movs'.
+	 * Otherwise, use rep_movs_alternative.
 	 */
-	alternative_call_2(copy_user_generic_unrolled,
-			 copy_user_generic_string,
-			 X86_FEATURE_REP_GOOD,
-			 copy_user_enhanced_fast_string,
-			 X86_FEATURE_ERMS,
-			 ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from),
-				     "=d" (len)),
-			 "1" (to), "2" (from), "3" (len)
-			 : "memory", "rcx", "r8", "r9", "r10", "r11");
-	return ret;
+	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", "r8", "r9", "r10", "r11");
+	clac();
+	return len;
 }
 
 static __always_inline __must_check unsigned long
@@ -58,9 +52,7 @@ raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
 	return copy_user_generic((__force void *)dst, src, size);
 }
 
-extern long __copy_user_nocache(void *dst, const void __user *src,
-				unsigned size, int zerorest);
-
+extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size);
 extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
 extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
 			   size_t len);
@@ -69,8 +61,12 @@ static inline int
 __copy_from_user_inatomic_nocache(void *dst, const void __user *src,
 				  unsigned size)
 {
+	long ret;
 	kasan_check_write(dst, size);
-	return __copy_user_nocache(dst, src, size, 0);
+	stac();
+	ret = __copy_user_nocache(dst, src, size);
+	clac();
+	return ret;
 }
 
 static inline int
@@ -85,11 +81,7 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
  */
 
 __must_check unsigned long
-clear_user_original(void __user *addr, unsigned long len);
-__must_check unsigned long
-clear_user_rep_good(void __user *addr, unsigned long len);
-__must_check unsigned long
-clear_user_erms(void __user *addr, unsigned long len);
+rep_stos_alternative(void __user *addr, unsigned long len);
 
 static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size)
 {
@@ -102,16 +94,12 @@ static __always_inline __must_check unsigned long __clear_user(void __user *addr
 	 */
 	asm volatile(
 		"1:\n\t"
-		ALTERNATIVE_3("rep stosb",
-			      "call clear_user_erms",	  ALT_NOT(X86_FEATURE_FSRM),
-			      "call clear_user_rep_good", ALT_NOT(X86_FEATURE_ERMS),
-			      "call clear_user_original", ALT_NOT(X86_FEATURE_REP_GOOD))
+		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)
-		/* rep_good clobbers %rdx */
-	       : "rdx");
+	       : "a" (0));
 
 	clac();