Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1654868

[PATCH 1/3] x86-32: Teach copy_from_user to unroll .size=6/8

Show all headers | View raw

Two exception handling register moves are faster to inline than a call
to __copy_user_ll(). We already apply the conversion for a get_user()
call, so for symmetry we should also apply the optimisation to
copy_from_user.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
---
 arch/x86/include/asm/uaccess_32.h | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index aeda9bb8af50..44d17d1ab07c 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -23,30 +23,47 @@ static __always_inline unsigned long
 raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	if (__builtin_constant_p(n)) {
-		unsigned long ret;
+		unsigned long ret = 0;
 
 		switch (n) {
 		case 1:
-			ret = 0;
 			__uaccess_begin();
 			__get_user_asm_nozero(*(u8 *)to, from, ret,
 					      "b", "b", "=q", 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			ret = 0;
 			__uaccess_begin();
 			__get_user_asm_nozero(*(u16 *)to, from, ret,
 					      "w", "w", "=r", 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			ret = 0;
 			__uaccess_begin();
 			__get_user_asm_nozero(*(u32 *)to, from, ret,
 					      "l", "k", "=r", 4);
 			__uaccess_end();
 			return ret;
+		case 6:
+			__uaccess_begin();
+			__get_user_asm_nozero(*(u32 *)to, from, ret,
+					      "l", "k", "=r", 6);
+			if (likely(!ret))
+				__get_user_asm_nozero(*(u16 *)(4 + (char *)to),
+						      (u16 __user *)(4 + (char __user *)from),
+						      ret, "w", "w", "=r", 2);
+			__uaccess_end();
+			return ret;
+		case 8:
+			__uaccess_begin();
+			__get_user_asm_nozero(*(u32 *)to, from, ret,
+					      "l", "k", "=r", 8);
+			if (likely(!ret))
+				__get_user_asm_nozero(*(u32 *)(4 + (char *)to),
+						      (u32 __user *)(4 + (char __user *)from),
+						      ret, "l", "k", "=r", 4);
+			__uaccess_end();
+			return ret;
 		}
 	}
 	return __copy_user_ll(to, (__force const void *)from, n);
-- 
2.11.0

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

x86: Static optimisations for copy_user Chris Wilson <chris@chris-wilson.co.uk> - 2017-06-01 09:00 +0200
  [PATCH 3/3] x86-64: Inline 6/12 byte copy_user Chris Wilson <chris@chris-wilson.co.uk> - 2017-06-01 09:00 +0200
  [PATCH 1/3] x86-32: Teach copy_from_user to unroll .size=6/8 Chris Wilson <chris@chris-wilson.co.uk> - 2017-06-01 09:10 +0200
  [PATCH 2/3] x86-32: Expand static copy_to_user() Chris Wilson <chris@chris-wilson.co.uk> - 2017-06-01 09:10 +0200

csiph-web