summaryrefslogtreecommitdiff
path: root/arch/arm/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/lib')
-rw-r--r--arch/arm/lib/Makefile26
-rw-r--r--arch/arm/lib/delay-loop.S (renamed from arch/arm/lib/delay.S)20
-rw-r--r--arch/arm/lib/delay.c71
-rw-r--r--arch/arm/lib/io-acorn.S3
-rw-r--r--arch/arm/lib/io-readsw-armv3.S106
-rw-r--r--arch/arm/lib/io-writesw-armv3.S126
-rw-r--r--arch/arm/lib/strncpy_from_user.S43
-rw-r--r--arch/arm/lib/strnlen_user.S40
-rw-r--r--arch/arm/lib/uaccess.S564
9 files changed, 899 insertions, 100 deletions
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 992769ae2599..af72969820b4 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -6,9 +6,8 @@
lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \
csumpartialcopy.o csumpartialcopyuser.o clearbit.o \
- delay.o findbit.o memchr.o memcpy.o \
+ delay.o delay-loop.o findbit.o memchr.o memcpy.o \
memmove.o memset.o memzero.o setbit.o \
- strncpy_from_user.o strnlen_user.o \
strchr.o strrchr.o \
testchangebit.o testclearbit.o testsetbit.o \
ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \
@@ -17,13 +16,30 @@ lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \
call_with_stack.o
mmu-y := clear_user.o copy_page.o getuser.o putuser.o
-mmu-y += copy_from_user.o copy_to_user.o
+
+# the code in uaccess.S is not preemption safe and
+# probably faster on ARMv3 only
+ifeq ($(CONFIG_PREEMPT),y)
+ mmu-y += copy_from_user.o copy_to_user.o
+else
+ifneq ($(CONFIG_CPU_32v3),y)
+ mmu-y += copy_from_user.o copy_to_user.o
+else
+ mmu-y += uaccess.o
+endif
+endif
# using lib_ here won't override already available weak symbols
obj-$(CONFIG_UACCESS_WITH_MEMCPY) += uaccess_with_memcpy.o
-lib-$(CONFIG_MMU) += $(mmu-y)
-lib-y += io-readsw-armv4.o io-writesw-armv4.o
+lib-$(CONFIG_MMU) += $(mmu-y)
+
+ifeq ($(CONFIG_CPU_32v3),y)
+ lib-y += io-readsw-armv3.o io-writesw-armv3.o
+else
+ lib-y += io-readsw-armv4.o io-writesw-armv4.o
+endif
+
lib-$(CONFIG_ARCH_RPC) += ecard.o io-acorn.o floppydma.o
lib-$(CONFIG_ARCH_SHARK) += io-shark.o
diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay-loop.S
index 3c9a05c8d20b..36b668d8e121 100644
--- a/arch/arm/lib/delay.S
+++ b/arch/arm/lib/delay-loop.S
@@ -9,11 +9,11 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
-#include <asm/param.h>
+#include <asm/delay.h>
.text
.LC0: .word loops_per_jiffy
-.LC1: .word (2199023*HZ)>>11
+.LC1: .word UDELAY_MULT
/*
* r0 <= 2000
@@ -21,10 +21,10 @@
* HZ <= 1000
*/
-ENTRY(__udelay)
+ENTRY(__loop_udelay)
ldr r2, .LC1
mul r0, r2, r0
-ENTRY(__const_udelay) @ 0 <= r0 <= 0x7fffff06
+ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0x7fffff06
mov r1, #-1
ldr r2, .LC0
ldr r2, [r2] @ max = 0x01ffffff
@@ -39,12 +39,10 @@ ENTRY(__const_udelay) @ 0 <= r0 <= 0x7fffff06
/*
* loops = r0 * HZ * loops_per_jiffy / 1000000
- *
- * Oh, if only we had a cycle counter...
*/
@ Delay routine
-ENTRY(__delay)
+ENTRY(__loop_delay)
subs r0, r0, #1
#if 0
movls pc, lr
@@ -62,8 +60,8 @@ ENTRY(__delay)
movls pc, lr
subs r0, r0, #1
#endif
- bhi __delay
+ bhi __loop_delay
mov pc, lr
-ENDPROC(__udelay)
-ENDPROC(__const_udelay)
-ENDPROC(__delay)
+ENDPROC(__loop_udelay)
+ENDPROC(__loop_const_udelay)
+ENDPROC(__loop_delay)
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
new file mode 100644
index 000000000000..d6dacc69254e
--- /dev/null
+++ b/arch/arm/lib/delay.c
@@ -0,0 +1,71 @@
+/*
+ * Delay loops based on the OpenRISC implementation.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/timex.h>
+
+/*
+ * Default to the loop-based delay implementation.
+ */
+struct arm_delay_ops arm_delay_ops = {
+ .delay = __loop_delay,
+ .const_udelay = __loop_const_udelay,
+ .udelay = __loop_udelay,
+};
+
+#ifdef ARCH_HAS_READ_CURRENT_TIMER
+static void __timer_delay(unsigned long cycles)
+{
+ cycles_t start = get_cycles();
+
+ while ((get_cycles() - start) < cycles)
+ cpu_relax();
+}
+
+static void __timer_const_udelay(unsigned long xloops)
+{
+ unsigned long long loops = xloops;
+ loops *= loops_per_jiffy;
+ __timer_delay(loops >> UDELAY_SHIFT);
+}
+
+static void __timer_udelay(unsigned long usecs)
+{
+ __timer_const_udelay(usecs * UDELAY_MULT);
+}
+
+void __init init_current_timer_delay(unsigned long freq)
+{
+ pr_info("Switching to timer-based delay loop\n");
+ lpj_fine = freq / HZ;
+ arm_delay_ops.delay = __timer_delay;
+ arm_delay_ops.const_udelay = __timer_const_udelay;
+ arm_delay_ops.udelay = __timer_udelay;
+}
+
+unsigned long __cpuinit calibrate_delay_is_known(void)
+{
+ return lpj_fine;
+}
+#endif
diff --git a/arch/arm/lib/io-acorn.S b/arch/arm/lib/io-acorn.S
index 1b197ea7aab3..69719bad674d 100644
--- a/arch/arm/lib/io-acorn.S
+++ b/arch/arm/lib/io-acorn.S
@@ -11,13 +11,14 @@
*
*/
#include <linux/linkage.h>
+#include <linux/kern_levels.h>
#include <asm/assembler.h>
.text
.align
.Liosl_warning:
- .ascii "<4>insl/outsl not implemented, called from %08lX\0"
+ .ascii KERN_WARNING "insl/outsl not implemented, called from %08lX\0"
.align
/*
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
new file mode 100644
index 000000000000..88487c8c4f23
--- /dev/null
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -0,0 +1,106 @@
+/*
+ * linux/arch/arm/lib/io-readsw-armv3.S
+ *
+ * Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.Linsw_bad_alignment:
+ adr r0, .Linsw_bad_align_msg
+ mov r2, lr
+ b panic
+.Linsw_bad_align_msg:
+ .asciz "insw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+ .align
+
+.Linsw_align: tst r1, #1
+ bne .Linsw_bad_alignment
+
+ ldr r3, [r0]
+ strb r3, [r1], #1
+ mov r3, r3, lsr #8
+ strb r3, [r1], #1
+
+ subs r2, r2, #1
+ moveq pc, lr
+
+ENTRY(__raw_readsw)
+ teq r2, #0 @ do we have to check for the zero len?
+ moveq pc, lr
+ tst r1, #3
+ bne .Linsw_align
+
+.Linsw_aligned: mov ip, #0xff
+ orr ip, ip, ip, lsl #8
+ stmfd sp!, {r4, r5, r6, lr}
+
+ subs r2, r2, #8
+ bmi .Lno_insw_8
+
+.Linsw_8_lp: ldr r3, [r0]
+ and r3, r3, ip
+ ldr r4, [r0]
+ orr r3, r3, r4, lsl #16
+
+ ldr r4, [r0]
+ and r4, r4, ip
+ ldr r5, [r0]
+ orr r4, r4, r5, lsl #16
+
+ ldr r5, [r0]
+ and r5, r5, ip
+ ldr r6, [r0]
+ orr r5, r5, r6, lsl #16
+
+ ldr r6, [r0]
+ and r6, r6, ip
+ ldr lr, [r0]
+ orr r6, r6, lr, lsl #16
+
+ stmia r1!, {r3 - r6}
+
+ subs r2, r2, #8
+ bpl .Linsw_8_lp
+
+ tst r2, #7
+ ldmeqfd sp!, {r4, r5, r6, pc}
+
+.Lno_insw_8: tst r2, #4
+ beq .Lno_insw_4
+
+ ldr r3, [r0]
+ and r3, r3, ip
+ ldr r4, [r0]
+ orr r3, r3, r4, lsl #16
+
+ ldr r4, [r0]
+ and r4, r4, ip
+ ldr r5, [r0]
+ orr r4, r4, r5, lsl #16
+
+ stmia r1!, {r3, r4}
+
+.Lno_insw_4: tst r2, #2
+ beq .Lno_insw_2
+
+ ldr r3, [r0]
+ and r3, r3, ip
+ ldr r4, [r0]
+ orr r3, r3, r4, lsl #16
+
+ str r3, [r1], #4
+
+.Lno_insw_2: tst r2, #1
+ ldrne r3, [r0]
+ strneb r3, [r1], #1
+ movne r3, r3, lsr #8
+ strneb r3, [r1]
+
+ ldmfd sp!, {r4, r5, r6, pc}
+
+
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
new file mode 100644
index 000000000000..49b800419e32
--- /dev/null
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -0,0 +1,126 @@
+/*
+ * linux/arch/arm/lib/io-writesw-armv3.S
+ *
+ * Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.Loutsw_bad_alignment:
+ adr r0, .Loutsw_bad_align_msg
+ mov r2, lr
+ b panic
+.Loutsw_bad_align_msg:
+ .asciz "outsw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+ .align
+
+.Loutsw_align: tst r1, #1
+ bne .Loutsw_bad_alignment
+
+ add r1, r1, #2
+
+ ldr r3, [r1, #-4]
+ mov r3, r3, lsr #16
+ orr r3, r3, r3, lsl #16
+ str r3, [r0]
+ subs r2, r2, #1
+ moveq pc, lr
+
+ENTRY(__raw_writesw)
+ teq r2, #0 @ do we have to check for the zero len?
+ moveq pc, lr
+ tst r1, #3
+ bne .Loutsw_align
+
+ stmfd sp!, {r4, r5, r6, lr}
+
+ subs r2, r2, #8
+ bmi .Lno_outsw_8
+
+.Loutsw_8_lp: ldmia r1!, {r3, r4, r5, r6}
+
+ mov ip, r3, lsl #16
+ orr ip, ip, ip, lsr #16
+ str ip, [r0]
+
+ mov ip, r3, lsr #16
+ orr ip, ip, ip, lsl #16
+ str ip, [r0]
+
+ mov ip, r4, lsl #16
+ orr ip, ip, ip, lsr #16
+ str ip, [r0]
+
+ mov ip, r4, lsr #16
+ orr ip, ip, ip, lsl #16
+ str ip, [r0]
+
+ mov ip, r5, lsl #16
+ orr ip, ip, ip, lsr #16
+ str ip, [r0]
+
+ mov ip, r5, lsr #16
+ orr ip, ip, ip, lsl #16
+ str ip, [r0]
+
+ mov ip, r6, lsl #16
+ orr ip, ip, ip, lsr #16
+ str ip, [r0]
+
+ mov ip, r6, lsr #16
+ orr ip, ip, ip, lsl #16
+ str ip, [r0]
+
+ subs r2, r2, #8
+ bpl .Loutsw_8_lp
+
+ tst r2, #7
+ ldmeqfd sp!, {r4, r5, r6, pc}
+
+.Lno_outsw_8: tst r2, #4
+ beq .Lno_outsw_4
+
+ ldmia r1!, {r3, r4}
+
+ mov ip, r3, lsl #16
+ orr ip, ip, ip, lsr #16
+ str ip, [r0]
+
+ mov ip, r3, lsr #16
+ orr ip, ip, ip, lsl #16
+ str ip, [r0]
+
+ mov ip, r4, lsl #16
+ orr ip, ip, ip, lsr #16
+ str ip, [r0]
+
+ mov ip, r4, lsr #16
+ orr ip, ip, ip, lsl #16
+ str ip, [r0]
+
+.Lno_outsw_4: tst r2, #2
+ beq .Lno_outsw_2
+
+ ldr r3, [r1], #4
+
+ mov ip, r3, lsl #16
+ orr ip, ip, ip, lsr #16
+ str ip, [r0]
+
+ mov ip, r3, lsr #16
+ orr ip, ip, ip, lsl #16
+ str ip, [r0]
+
+.Lno_outsw_2: tst r2, #1
+
+ ldrne r3, [r1]
+
+ movne ip, r3, lsl #16
+ orrne ip, ip, ip, lsr #16
+ strne ip, [r0]
+
+ ldmfd sp!, {r4, r5, r6, pc}
diff --git a/arch/arm/lib/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S
deleted file mode 100644
index f202d7bd1647..000000000000
--- a/arch/arm/lib/strncpy_from_user.S
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * linux/arch/arm/lib/strncpy_from_user.S
- *
- * Copyright (C) 1995-2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
- .text
- .align 5
-
-/*
- * Copy a string from user space to kernel space.
- * r0 = dst, r1 = src, r2 = byte length
- * returns the number of characters copied (strlen of copied string),
- * -EFAULT on exception, or "len" if we fill the whole buffer
- */
-ENTRY(__strncpy_from_user)
- mov ip, r1
-1: subs r2, r2, #1
- ldrusr r3, r1, 1, pl
- bmi 2f
- strb r3, [r0], #1
- teq r3, #0
- bne 1b
- sub r1, r1, #1 @ take NUL character out of count
-2: sub r0, r1, ip
- mov pc, lr
-ENDPROC(__strncpy_from_user)
-
- .pushsection .fixup,"ax"
- .align 0
-9001: mov r3, #0
- strb r3, [r0, #0] @ null terminate
- mov r0, #-EFAULT
- mov pc, lr
- .popsection
-
diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S
deleted file mode 100644
index 0ecbb459c4f1..000000000000
--- a/arch/arm/lib/strnlen_user.S
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * linux/arch/arm/lib/strnlen_user.S
- *
- * Copyright (C) 1995-2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
- .text
- .align 5
-
-/* Prototype: unsigned long __strnlen_user(const char *str, long n)
- * Purpose : get length of a string in user memory
- * Params : str - address of string in user memory
- * Returns : length of string *including terminator*
- * or zero on exception, or n + 1 if too long
- */
-ENTRY(__strnlen_user)
- mov r2, r0
-1:
- ldrusr r3, r0, 1
- teq r3, #0
- beq 2f
- subs r1, r1, #1
- bne 1b
- add r0, r0, #1
-2: sub r0, r0, r2
- mov pc, lr
-ENDPROC(__strnlen_user)
-
- .pushsection .fixup,"ax"
- .align 0
-9001: mov r0, #0
- mov pc, lr
- .popsection
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
new file mode 100644
index 000000000000..5c908b1cb8ed
--- /dev/null
+++ b/arch/arm/lib/uaccess.S
@@ -0,0 +1,564 @@
+/*
+ * linux/arch/arm/lib/uaccess.S
+ *
+ * Copyright (C) 1995, 1996,1997,1998 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Routines to block copy data to/from user memory
+ * These are highly optimised both for the 4k page size
+ * and for various alignments.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+#include <asm/domain.h>
+
+ .text
+
+#define PAGE_SHIFT 12
+
+/* Prototype: int __copy_to_user(void *to, const char *from, size_t n)
+ * Purpose : copy a block to user memory from kernel memory
+ * Params : to - user memory
+ * : from - kernel memory
+ * : n - number of bytes to copy
+ * Returns : Number of bytes NOT copied.
+ */
+
+.Lc2u_dest_not_aligned:
+ rsb ip, ip, #4
+ cmp ip, #2
+ ldrb r3, [r1], #1
+USER( TUSER( strb) r3, [r0], #1) @ May fault
+ ldrgeb r3, [r1], #1
+USER( TUSER( strgeb) r3, [r0], #1) @ May fault
+ ldrgtb r3, [r1], #1
+USER( TUSER( strgtb) r3, [r0], #1) @ May fault
+ sub r2, r2, ip
+ b .Lc2u_dest_aligned
+
+ENTRY(__copy_to_user)
+ stmfd sp!, {r2, r4 - r7, lr}
+ cmp r2, #4
+ blt .Lc2u_not_enough
+ ands ip, r0, #3
+ bne .Lc2u_dest_not_aligned
+.Lc2u_dest_aligned:
+
+ ands ip, r1, #3
+ bne .Lc2u_src_not_aligned
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lc2u_0fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lc2u_0nowords
+ ldr r3, [r1], #4
+USER( TUSER( str) r3, [r0], #4) @ May fault
+ mov ip, r0, lsl #32 - PAGE_SHIFT @ On each page, use a ld/st??t instruction
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lc2u_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #32
+ blt .Lc2u_0rem8lp
+
+.Lc2u_0cpy8lp: ldmia r1!, {r3 - r6}
+ stmia r0!, {r3 - r6} @ Shouldnt fault
+ ldmia r1!, {r3 - r6}
+ subs ip, ip, #32
+ stmia r0!, {r3 - r6} @ Shouldnt fault
+ bpl .Lc2u_0cpy8lp
+
+.Lc2u_0rem8lp: cmn ip, #16
+ ldmgeia r1!, {r3 - r6}
+ stmgeia r0!, {r3 - r6} @ Shouldnt fault
+ tst ip, #8
+ ldmneia r1!, {r3 - r4}
+ stmneia r0!, {r3 - r4} @ Shouldnt fault
+ tst ip, #4
+ ldrne r3, [r1], #4
+ TUSER( strne) r3, [r0], #4 @ Shouldnt fault
+ ands ip, ip, #3
+ beq .Lc2u_0fupi
+.Lc2u_0nowords: teq ip, #0
+ beq .Lc2u_finished
+.Lc2u_nowords: cmp ip, #2
+ ldrb r3, [r1], #1
+USER( TUSER( strb) r3, [r0], #1) @ May fault
+ ldrgeb r3, [r1], #1
+USER( TUSER( strgeb) r3, [r0], #1) @ May fault
+ ldrgtb r3, [r1], #1
+USER( TUSER( strgtb) r3, [r0], #1) @ May fault
+ b .Lc2u_finished
+
+.Lc2u_not_enough:
+ movs ip, r2
+ bne .Lc2u_nowords
+.Lc2u_finished: mov r0, #0
+ ldmfd sp!, {r2, r4 - r7, pc}
+
+.Lc2u_src_not_aligned:
+ bic r1, r1, #3
+ ldr r7, [r1], #4
+ cmp ip, #2
+ bgt .Lc2u_3fupi
+ beq .Lc2u_2fupi
+.Lc2u_1fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lc2u_1nowords
+ mov r3, r7, pull #8
+ ldr r7, [r1], #4
+ orr r3, r3, r7, push #24
+USER( TUSER( str) r3, [r0], #4) @ May fault
+ mov ip, r0, lsl #32 - PAGE_SHIFT
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lc2u_1fupi
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #16
+ blt .Lc2u_1rem8lp
+
+.Lc2u_1cpy8lp: mov r3, r7, pull #8
+ ldmia r1!, {r4 - r7}
+ subs ip, ip, #16
+ orr r3, r3, r4, push #24
+ mov r4, r4, pull #8
+ orr r4, r4, r5, push #24
+ mov r5, r5, pull #8
+ orr r5, r5, r6, push #24
+ mov r6, r6, pull #8
+ orr r6, r6, r7, push #24
+ stmia r0!, {r3 - r6} @ Shouldnt fault
+ bpl .Lc2u_1cpy8lp
+
+.Lc2u_1rem8lp: tst ip, #8
+ movne r3, r7, pull #8
+ ldmneia r1!, {r4, r7}
+ orrne r3, r3, r4, push #24
+ movne r4, r4, pull #8
+ orrne r4, r4, r7, push #24
+ stmneia r0!, {r3 - r4} @ Shouldnt fault
+ tst ip, #4
+ movne r3, r7, pull #8
+ ldrne r7, [r1], #4
+ orrne r3, r3, r7, push #24
+ TUSER( strne) r3, [r0], #4 @ Shouldnt fault
+ ands ip, ip, #3
+ beq .Lc2u_1fupi
+.Lc2u_1nowords: mov r3, r7, get_byte_1
+ teq ip, #0
+ beq .Lc2u_finished
+ cmp ip, #2
+USER( TUSER( strb) r3, [r0], #1) @ May fault
+ movge r3, r7, get_byte_2
+USER( TUSER( strgeb) r3, [r0], #1) @ May fault
+ movgt r3, r7, get_byte_3
+USER( TUSER( strgtb) r3, [r0], #1) @ May fault
+ b .Lc2u_finished
+
+.Lc2u_2fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lc2u_2nowords
+ mov r3, r7, pull #16
+ ldr r7, [r1], #4
+ orr r3, r3, r7, push #16
+USER( TUSER( str) r3, [r0], #4) @ May fault
+ mov ip, r0, lsl #32 - PAGE_SHIFT
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lc2u_2fupi
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #16
+ blt .Lc2u_2rem8lp
+
+.Lc2u_2cpy8lp: mov r3, r7, pull #16
+ ldmia r1!, {r4 - r7}
+ subs ip, ip, #16
+ orr r3, r3, r4, push #16
+ mov r4, r4, pull #16
+ orr r4, r4, r5, push #16
+ mov r5, r5, pull #16
+ orr r5, r5, r6, push #16
+ mov r6, r6, pull #16
+ orr r6, r6, r7, push #16
+ stmia r0!, {r3 - r6} @ Shouldnt fault
+ bpl .Lc2u_2cpy8lp
+
+.Lc2u_2rem8lp: tst ip, #8
+ movne r3, r7, pull #16
+ ldmneia r1!, {r4, r7}
+ orrne r3, r3, r4, push #16
+ movne r4, r4, pull #16
+ orrne r4, r4, r7, push #16
+ stmneia r0!, {r3 - r4} @ Shouldnt fault
+ tst ip, #4
+ movne r3, r7, pull #16
+ ldrne r7, [r1], #4
+ orrne r3, r3, r7, push #16
+ TUSER( strne) r3, [r0], #4 @ Shouldnt fault
+ ands ip, ip, #3
+ beq .Lc2u_2fupi
+.Lc2u_2nowords: mov r3, r7, get_byte_2
+ teq ip, #0
+ beq .Lc2u_finished
+ cmp ip, #2
+USER( TUSER( strb) r3, [r0], #1) @ May fault
+ movge r3, r7, get_byte_3
+USER( TUSER( strgeb) r3, [r0], #1) @ May fault
+ ldrgtb r3, [r1], #0
+USER( TUSER( strgtb) r3, [r0], #1) @ May fault
+ b .Lc2u_finished
+
+.Lc2u_3fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lc2u_3nowords
+ mov r3, r7, pull #24
+ ldr r7, [r1], #4
+ orr r3, r3, r7, push #8
+USER( TUSER( str) r3, [r0], #4) @ May fault
+ mov ip, r0, lsl #32 - PAGE_SHIFT
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lc2u_3fupi
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #16
+ blt .Lc2u_3rem8lp
+
+.Lc2u_3cpy8lp: mov r3, r7, pull #24
+ ldmia r1!, {r4 - r7}
+ subs ip, ip, #16
+ orr r3, r3, r4, push #8
+ mov r4, r4, pull #24
+ orr r4, r4, r5, push #8
+ mov r5, r5, pull #24
+ orr r5, r5, r6, push #8
+ mov r6, r6, pull #24
+ orr r6, r6, r7, push #8
+ stmia r0!, {r3 - r6} @ Shouldnt fault
+ bpl .Lc2u_3cpy8lp
+
+.Lc2u_3rem8lp: tst ip, #8
+ movne r3, r7, pull #24
+ ldmneia r1!, {r4, r7}
+ orrne r3, r3, r4, push #8
+ movne r4, r4, pull #24
+ orrne r4, r4, r7, push #8
+ stmneia r0!, {r3 - r4} @ Shouldnt fault
+ tst ip, #4
+ movne r3, r7, pull #24
+ ldrne r7, [r1], #4
+ orrne r3, r3, r7, push #8
+ TUSER( strne) r3, [r0], #4 @ Shouldnt fault
+ ands ip, ip, #3
+ beq .Lc2u_3fupi
+.Lc2u_3nowords: mov r3, r7, get_byte_3
+ teq ip, #0
+ beq .Lc2u_finished
+ cmp ip, #2
+USER( TUSER( strb) r3, [r0], #1) @ May fault
+ ldrgeb r3, [r1], #1
+USER( TUSER( strgeb) r3, [r0], #1) @ May fault
+ ldrgtb r3, [r1], #0
+USER( TUSER( strgtb) r3, [r0], #1) @ May fault
+ b .Lc2u_finished
+ENDPROC(__copy_to_user)
+
+ .pushsection .fixup,"ax"
+ .align 0
+9001: ldmfd sp!, {r0, r4 - r7, pc}
+ .popsection
+
+/* Prototype: unsigned long __copy_from_user(void *to,const void *from,unsigned long n);
+ * Purpose : copy a block from user memory to kernel memory
+ * Params : to - kernel memory
+ * : from - user memory
+ * : n - number of bytes to copy
+ * Returns : Number of bytes NOT copied.
+ */
+.Lcfu_dest_not_aligned:
+ rsb ip, ip, #4
+ cmp ip, #2
+USER( TUSER( ldrb) r3, [r1], #1) @ May fault
+ strb r3, [r0], #1
+USER( TUSER( ldrgeb) r3, [r1], #1) @ May fault
+ strgeb r3, [r0], #1
+USER( TUSER( ldrgtb) r3, [r1], #1) @ May fault
+ strgtb r3, [r0], #1
+ sub r2, r2, ip
+ b .Lcfu_dest_aligned
+
+ENTRY(__copy_from_user)
+ stmfd sp!, {r0, r2, r4 - r7, lr}
+ cmp r2, #4
+ blt .Lcfu_not_enough
+ ands ip, r0, #3
+ bne .Lcfu_dest_not_aligned
+.Lcfu_dest_aligned:
+ ands ip, r1, #3
+ bne .Lcfu_src_not_aligned
+
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lcfu_0fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lcfu_0nowords
+USER( TUSER( ldr) r3, [r1], #4)
+ str r3, [r0], #4
+ mov ip, r1, lsl #32 - PAGE_SHIFT @ On each page, use a ld/st??t instruction
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lcfu_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #32
+ blt .Lcfu_0rem8lp
+
+.Lcfu_0cpy8lp: ldmia r1!, {r3 - r6} @ Shouldnt fault
+ stmia r0!, {r3 - r6}
+ ldmia r1!, {r3 - r6} @ Shouldnt fault
+ subs ip, ip, #32
+ stmia r0!, {r3 - r6}
+ bpl .Lcfu_0cpy8lp
+
+.Lcfu_0rem8lp: cmn ip, #16
+ ldmgeia r1!, {r3 - r6} @ Shouldnt fault
+ stmgeia r0!, {r3 - r6}
+ tst ip, #8
+ ldmneia r1!, {r3 - r4} @ Shouldnt fault
+ stmneia r0!, {r3 - r4}
+ tst ip, #4
+ TUSER( ldrne) r3, [r1], #4 @ Shouldnt fault
+ strne r3, [r0], #4
+ ands ip, ip, #3
+ beq .Lcfu_0fupi
+.Lcfu_0nowords: teq ip, #0
+ beq .Lcfu_finished
+.Lcfu_nowords: cmp ip, #2
+USER( TUSER( ldrb) r3, [r1], #1) @ May fault
+ strb r3, [r0], #1
+USER( TUSER( ldrgeb) r3, [r1], #1) @ May fault
+ strgeb r3, [r0], #1
+USER( TUSER( ldrgtb) r3, [r1], #1) @ May fault
+ strgtb r3, [r0], #1
+ b .Lcfu_finished
+
+.Lcfu_not_enough:
+ movs ip, r2
+ bne .Lcfu_nowords
+.Lcfu_finished: mov r0, #0
+ add sp, sp, #8
+ ldmfd sp!, {r4 - r7, pc}
+
+.Lcfu_src_not_aligned:
+ bic r1, r1, #3
+USER( TUSER( ldr) r7, [r1], #4) @ May fault
+ cmp ip, #2
+ bgt .Lcfu_3fupi
+ beq .Lcfu_2fupi
+.Lcfu_1fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lcfu_1nowords
+ mov r3, r7, pull #8
+USER( TUSER( ldr) r7, [r1], #4) @ May fault
+ orr r3, r3, r7, push #24
+ str r3, [r0], #4
+ mov ip, r1, lsl #32 - PAGE_SHIFT
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lcfu_1fupi
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #16
+ blt .Lcfu_1rem8lp
+
+.Lcfu_1cpy8lp: mov r3, r7, pull #8
+ ldmia r1!, {r4 - r7} @ Shouldnt fault
+ subs ip, ip, #16
+ orr r3, r3, r4, push #24
+ mov r4, r4, pull #8
+ orr r4, r4, r5, push #24
+ mov r5, r5, pull #8
+ orr r5, r5, r6, push #24
+ mov r6, r6, pull #8
+ orr r6, r6, r7, push #24
+ stmia r0!, {r3 - r6}
+ bpl .Lcfu_1cpy8lp
+
+.Lcfu_1rem8lp: tst ip, #8
+ movne r3, r7, pull #8
+ ldmneia r1!, {r4, r7} @ Shouldnt fault
+ orrne r3, r3, r4, push #24
+ movne r4, r4, pull #8
+ orrne r4, r4, r7, push #24
+ stmneia r0!, {r3 - r4}
+ tst ip, #4
+ movne r3, r7, pull #8
+USER( TUSER( ldrne) r7, [r1], #4) @ May fault
+ orrne r3, r3, r7, push #24
+ strne r3, [r0], #4
+ ands ip, ip, #3
+ beq .Lcfu_1fupi
+.Lcfu_1nowords: mov r3, r7, get_byte_1
+ teq ip, #0
+ beq .Lcfu_finished
+ cmp ip, #2
+ strb r3, [r0], #1
+ movge r3, r7, get_byte_2
+ strgeb r3, [r0], #1
+ movgt r3, r7, get_byte_3
+ strgtb r3, [r0], #1
+ b .Lcfu_finished
+
+.Lcfu_2fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lcfu_2nowords
+ mov r3, r7, pull #16
+USER( TUSER( ldr) r7, [r1], #4) @ May fault
+ orr r3, r3, r7, push #16
+ str r3, [r0], #4
+ mov ip, r1, lsl #32 - PAGE_SHIFT
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lcfu_2fupi
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #16
+ blt .Lcfu_2rem8lp
+
+
+.Lcfu_2cpy8lp: mov r3, r7, pull #16
+ ldmia r1!, {r4 - r7} @ Shouldnt fault
+ subs ip, ip, #16
+ orr r3, r3, r4, push #16
+ mov r4, r4, pull #16
+ orr r4, r4, r5, push #16
+ mov r5, r5, pull #16
+ orr r5, r5, r6, push #16
+ mov r6, r6, pull #16
+ orr r6, r6, r7, push #16
+ stmia r0!, {r3 - r6}
+ bpl .Lcfu_2cpy8lp
+
+.Lcfu_2rem8lp: tst ip, #8
+ movne r3, r7, pull #16
+ ldmneia r1!, {r4, r7} @ Shouldnt fault
+ orrne r3, r3, r4, push #16
+ movne r4, r4, pull #16
+ orrne r4, r4, r7, push #16
+ stmneia r0!, {r3 - r4}
+ tst ip, #4
+ movne r3, r7, pull #16
+USER( TUSER( ldrne) r7, [r1], #4) @ May fault
+ orrne r3, r3, r7, push #16
+ strne r3, [r0], #4
+ ands ip, ip, #3
+ beq .Lcfu_2fupi
+.Lcfu_2nowords: mov r3, r7, get_byte_2
+ teq ip, #0
+ beq .Lcfu_finished
+ cmp ip, #2
+ strb r3, [r0], #1
+ movge r3, r7, get_byte_3
+ strgeb r3, [r0], #1
+USER( TUSER( ldrgtb) r3, [r1], #0) @ May fault
+ strgtb r3, [r0], #1
+ b .Lcfu_finished
+
+.Lcfu_3fupi: subs r2, r2, #4
+ addmi ip, r2, #4
+ bmi .Lcfu_3nowords
+ mov r3, r7, pull #24
+USER( TUSER( ldr) r7, [r1], #4) @ May fault
+ orr r3, r3, r7, push #8
+ str r3, [r0], #4
+ mov ip, r1, lsl #32 - PAGE_SHIFT
+ rsb ip, ip, #0
+ movs ip, ip, lsr #32 - PAGE_SHIFT
+ beq .Lcfu_3fupi
+ cmp r2, ip
+ movlt ip, r2
+ sub r2, r2, ip
+ subs ip, ip, #16
+ blt .Lcfu_3rem8lp
+
+.Lcfu_3cpy8lp: mov r3, r7, pull #24
+ ldmia r1!, {r4 - r7} @ Shouldnt fault
+ orr r3, r3, r4, push #8
+ mov r4, r4, pull #24
+ orr r4, r4, r5, push #8
+ mov r5, r5, pull #24
+ orr r5, r5, r6, push #8
+ mov r6, r6, pull #24
+ orr r6, r6, r7, push #8
+ stmia r0!, {r3 - r6}
+ subs ip, ip, #16
+ bpl .Lcfu_3cpy8lp
+
+.Lcfu_3rem8lp: tst ip, #8
+ movne r3, r7, pull #24
+ ldmneia r1!, {r4, r7} @ Shouldnt fault
+ orrne r3, r3, r4, push #8
+ movne r4, r4, pull #24
+ orrne r4, r4, r7, push #8
+ stmneia r0!, {r3 - r4}
+ tst ip, #4
+ movne r3, r7, pull #24
+USER( TUSER( ldrne) r7, [r1], #4) @ May fault
+ orrne r3, r3, r7, push #8
+ strne r3, [r0], #4
+ ands ip, ip, #3
+ beq .Lcfu_3fupi
+.Lcfu_3nowords: mov r3, r7, get_byte_3
+ teq ip, #0
+ beq .Lcfu_finished
+ cmp ip, #2
+ strb r3, [r0], #1
+USER( TUSER( ldrgeb) r3, [r1], #1) @ May fault
+ strgeb r3, [r0], #1
+USER( TUSER( ldrgtb) r3, [r1], #1) @ May fault
+ strgtb r3, [r0], #1
+ b .Lcfu_finished
+ENDPROC(__copy_from_user)
+
+ .pushsection .fixup,"ax"
+ .align 0
+ /*
+ * We took an exception. r0 contains a pointer to
+ * the byte not copied.
+ */
+9001: ldr r2, [sp], #4 @ void *to
+ sub r2, r0, r2 @ bytes copied
+ ldr r1, [sp], #4 @ unsigned long count
+ subs r4, r1, r2 @ bytes left to copy
+ movne r1, r4
+ blne __memzero
+ mov r0, r4
+ ldmfd sp!, {r4 - r7, pc}
+ .popsection
+