ARM: 8812/1: Optimise copy_{from/to}_user for !CPU_USE_DOMAINS

ARMv6+ processors do not use CONFIG_CPU_USE_DOMAINS and use privileged
ldr/str instructions in copy_{from/to}_user.  They are currently
unnecessarily using single ldr/str instructions and can use ldm/stm
instructions instead like memcpy does (but with appropriate fixup
tables).

This speeds up a "dd if=foo of=bar bs=32k" on a tmpfs filesystem by
about 4% on my Cortex-A9.

before:134217728 bytes (128.0MB) copied, 0.543848 seconds, 235.4MB/s
before:134217728 bytes (128.0MB) copied, 0.538610 seconds, 237.6MB/s
before:134217728 bytes (128.0MB) copied, 0.544356 seconds, 235.1MB/s
before:134217728 bytes (128.0MB) copied, 0.544364 seconds, 235.1MB/s
before:134217728 bytes (128.0MB) copied, 0.537130 seconds, 238.3MB/s
before:134217728 bytes (128.0MB) copied, 0.533443 seconds, 240.0MB/s
before:134217728 bytes (128.0MB) copied, 0.545691 seconds, 234.6MB/s
before:134217728 bytes (128.0MB) copied, 0.534695 seconds, 239.4MB/s
before:134217728 bytes (128.0MB) copied, 0.540561 seconds, 236.8MB/s
before:134217728 bytes (128.0MB) copied, 0.541025 seconds, 236.6MB/s

 after:134217728 bytes (128.0MB) copied, 0.520445 seconds, 245.9MB/s
 after:134217728 bytes (128.0MB) copied, 0.527846 seconds, 242.5MB/s
 after:134217728 bytes (128.0MB) copied, 0.519510 seconds, 246.4MB/s
 after:134217728 bytes (128.0MB) copied, 0.527231 seconds, 242.8MB/s
 after:134217728 bytes (128.0MB) copied, 0.525030 seconds, 243.8MB/s
 after:134217728 bytes (128.0MB) copied, 0.524236 seconds, 244.2MB/s
 after:134217728 bytes (128.0MB) copied, 0.523659 seconds, 244.4MB/s
 after:134217728 bytes (128.0MB) copied, 0.525018 seconds, 243.8MB/s
 after:134217728 bytes (128.0MB) copied, 0.519249 seconds, 246.5MB/s
 after:134217728 bytes (128.0MB) copied, 0.518527 seconds, 246.9MB/s

Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>

3 files changed, 48 insertions, 8 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 88286dd483ff..28a48e0d4cca 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -243,13 +243,15 @@
 	.endm
 #endif
 
-#define USER(x...)				\
+#define USERL(l, x...)				\
 9999:	x;					\
 	.pushsection __ex_table,"a";		\
 	.align	3;				\
-	.long	9999b,9001f;			\
+	.long	9999b,l;			\
 	.popsection
 
+#define USER(x...)	USERL(9001f, x)
+
 #ifdef CONFIG_SMP
 #define ALT_SMP(instr...)					\
 9998:	instr
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 6709a8d33963..0d4c189c7f4f 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -34,12 +34,13 @@
  *	Number of bytes NOT copied.
  */
 
+#ifdef CONFIG_CPU_USE_DOMAINS
+
 #ifndef CONFIG_THUMB2_KERNEL
 #define LDR1W_SHIFT	0
 #else
 #define LDR1W_SHIFT	1
 #endif
-#define STR1W_SHIFT	0
 
 	.macro ldr1w ptr reg abort
 	ldrusr	\reg, \ptr, 4, abort=\abort
@@ -57,10 +58,30 @@
 	ldr4w \ptr, \reg5, \reg6, \reg7, \reg8, \abort
 	.endm
 
+#else
+
+#define LDR1W_SHIFT	0
+
+	.macro ldr1w ptr reg abort
+	USERL(\abort, W(ldr) \reg, [\ptr], #4)
+	.endm
+
+	.macro ldr4w ptr reg1 reg2 reg3 reg4 abort
+	USERL(\abort, ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4})
+	.endm
+
+	.macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
+	USERL(\abort, ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8})
+	.endm
+
+#endif /* CONFIG_CPU_USE_DOMAINS */
+
 	.macro ldr1b ptr reg cond=al abort
 	ldrusr	\reg, \ptr, 1, \cond, abort=\abort
 	.endm
 
+#define STR1W_SHIFT	0
+
 	.macro str1w ptr reg abort
 	W(str) \reg, [\ptr], #4
 	.endm
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 970abe521197..97a6ff4b7e3c 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -35,11 +35,6 @@
  */
 
 #define LDR1W_SHIFT	0
-#ifndef CONFIG_THUMB2_KERNEL
-#define STR1W_SHIFT	0
-#else
-#define STR1W_SHIFT	1
-#endif
 
 	.macro ldr1w ptr reg abort
 	W(ldr) \reg, [\ptr], #4
@@ -57,6 +52,14 @@
 	ldr\cond\()b \reg, [\ptr], #1
 	.endm
 
+#ifdef CONFIG_CPU_USE_DOMAINS
+
+#ifndef CONFIG_THUMB2_KERNEL
+#define STR1W_SHIFT	0
+#else
+#define STR1W_SHIFT	1
+#endif
+
 	.macro str1w ptr reg abort
 	strusr	\reg, \ptr, 4, abort=\abort
 	.endm
@@ -72,6 +75,20 @@
 	str1w \ptr, \reg8, \abort
 	.endm
 
+#else
+
+#define STR1W_SHIFT	0
+
+	.macro str1w ptr reg abort
+	USERL(\abort, W(str) \reg, [\ptr], #4)
+	.endm
+
+	.macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
+	USERL(\abort, stmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8})
+	.endm
+
+#endif /* CONFIG_CPU_USE_DOMAINS */
+
 	.macro str1b ptr reg cond=al abort
 	strusr	\reg, \ptr, 1, \cond, abort=\abort
 	.endm