[Intel-gfx] [PATCH 3/3] x86-64: Inline 6/12 byte copy_user

[Chris Wilson]

Extend the list of replacements for compile-time known sizes to include
6/12 byte copies. These expand to two movs (along with their exception
table) and are cheaper to inline than the function call (similar to the
10 byte copy already handled).

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: "H. Peter Anvin" <hpa at zytor.com>
---
 arch/x86/include/asm/uaccess_64.h | 42 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index c5504b9a472e..ff2d65baa988 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -71,6 +71,16 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 			      ret, "l", "k", "=r", 4);
 		__uaccess_end();
 		return ret;
+	case 6:
+		__uaccess_begin();
+		__get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src,
+			       ret, "l", "k", "=r", 6);
+		if (likely(!ret))
+			__get_user_asm_nozero(*(u16 *)(4 + (char *)dst),
+				       (u16 __user *)(4 + (char __user *)src),
+				       ret, "w", "w", "=r", 2);
+		__uaccess_end();
+		return ret;
 	case 8:
 		__uaccess_begin();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
@@ -87,6 +97,16 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 				       ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
+	case 12:
+		__uaccess_begin();
+		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
+			       ret, "q", "", "=r", 10);
+		if (likely(!ret))
+			__get_user_asm_nozero(*(u32 *)(8 + (char *)dst),
+				       (u32 __user *)(8 + (char __user *)src),
+				       ret, "l", "k", "=r", 4);
+		__uaccess_end();
+		return ret;
 	case 16:
 		__uaccess_begin();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
@@ -128,6 +148,17 @@ raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
 			      ret, "l", "k", "ir", 4);
 		__uaccess_end();
 		return ret;
+	case 6:
+		__uaccess_begin();
+		__put_user_asm(*(u32 *)src, (u32 __user *)dst,
+			       ret, "l", "k", "ir", 6);
+		if (likely(!ret)) {
+			asm("":::"memory");
+			__put_user_asm(2[(u16 *)src], 2 + (u16 __user *)dst,
+				       ret, "w", "w", "ir", 2);
+		}
+		__uaccess_end();
+		return ret;
 	case 8:
 		__uaccess_begin();
 		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
@@ -145,6 +176,17 @@ raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
 		}
 		__uaccess_end();
 		return ret;
+	case 12:
+		__uaccess_begin();
+		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
+			       ret, "q", "", "er", 12);
+		if (likely(!ret)) {
+			asm("":::"memory");
+			__put_user_asm(2[(u32 *)src], 2 + (u32 __user *)dst,
+				       ret, "l", "k", "ir", 4);
+		}
+		__uaccess_end();
+		return ret;
 	case 16:
 		__uaccess_begin();
 		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-- 
2.11.0