aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/lib')
-rw-r--r--arch/arm/lib/Makefile9
-rw-r--r--arch/arm/lib/backtrace.S20
-rw-r--r--arch/arm/lib/bitops.h10
-rw-r--r--arch/arm/lib/bswapsdi2.S36
-rw-r--r--arch/arm/lib/copy_template.S36
-rw-r--r--arch/arm/lib/csumpartialcopygeneric.S96
-rw-r--r--arch/arm/lib/delay-loop.S1
-rw-r--r--arch/arm/lib/delay.c9
-rw-r--r--arch/arm/lib/io-readsl.S12
-rw-r--r--arch/arm/lib/io-shark.c13
-rw-r--r--arch/arm/lib/io-writesl.S12
-rw-r--r--arch/arm/lib/memmove.S36
-rw-r--r--arch/arm/lib/memset.S100
-rw-r--r--arch/arm/lib/uaccess.S192
-rw-r--r--arch/arm/lib/uaccess_with_memcpy.c41
-rw-r--r--arch/arm/lib/xor-neon.c46
16 files changed, 394 insertions, 275 deletions
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index af72969820b..0573faab96a 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \
ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \
ucmpdi2.o lib1funcs.o div64.o \
io-readsb.o io-writesb.o io-readsl.o io-writesl.o \
- call_with_stack.o
+ call_with_stack.o bswapsdi2.o
mmu-y := clear_user.o copy_page.o getuser.o putuser.o
@@ -41,7 +41,12 @@ else
endif
lib-$(CONFIG_ARCH_RPC) += ecard.o io-acorn.o floppydma.o
-lib-$(CONFIG_ARCH_SHARK) += io-shark.o
$(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S
$(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S
+
+ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
+ NEON_FLAGS := -mfloat-abi=softfp -mfpu=neon
+ CFLAGS_xor-neon.o += $(NEON_FLAGS)
+ obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o
+endif
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
index cd07b5814c2..4102be617fc 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -80,14 +80,14 @@ for_each_frame: tst frame, mask @ Check for address exceptions
ldr r1, [sv_pc, #-4] @ if stmfd sp!, {args} exists,
ldr r3, .Ldsi+4
- teq r3, r1, lsr #10
+ teq r3, r1, lsr #11
ldreq r0, [frame, #-8] @ get sp
subeq r0, r0, #4 @ point at the last arg
bleq .Ldumpstm @ dump saved registers
1004: ldr r1, [sv_pc, #0] @ if stmfd sp!, {..., fp, ip, lr, pc}
ldr r3, .Ldsi @ instruction exists,
- teq r3, r1, lsr #10
+ teq r3, r1, lsr #11
subeq r0, frame, #16
bleq .Ldumpstm @ dump saved registers
@@ -128,11 +128,11 @@ ENDPROC(c_backtrace)
beq 2f
add r7, r7, #1
teq r7, #6
- moveq r7, #1
- moveq r1, #'\n'
- movne r1, #' '
- ldr r3, [stack], #-4
- mov r2, reg
+ moveq r7, #0
+ adr r3, .Lcr
+ addne r3, r3, #1 @ skip newline
+ ldr r2, [stack], #-4
+ mov r1, reg
adr r0, .Lfp
bl printk
2: subs reg, reg, #1
@@ -142,11 +142,11 @@ ENDPROC(c_backtrace)
blne printk
ldmfd sp!, {instr, reg, stack, r7, pc}
-.Lfp: .asciz "%cr%d:%08x"
+.Lfp: .asciz " r%d:%08x%s"
.Lcr: .asciz "\n"
.Lbad: .asciz "Backtrace aborted due to bad frame pointer <%p>\n"
.align
-.Ldsi: .word 0xe92dd800 >> 10 @ stmfd sp!, {... fp, ip, lr, pc}
- .word 0xe92d0000 >> 10 @ stmfd sp!, {}
+.Ldsi: .word 0xe92dd800 >> 11 @ stmfd sp!, {... fp, ip, lr, pc}
+ .word 0xe92d0000 >> 11 @ stmfd sp!, {}
#endif
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index d6408d1ee54..9f12ed1eea8 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -10,6 +10,11 @@ UNWIND( .fnstart )
and r3, r0, #31 @ Get bit offset
mov r0, r0, lsr #5
add r1, r1, r0, lsl #2 @ Get word offset
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+ .arch_extension mp
+ ALT_SMP(W(pldw) [r1])
+ ALT_UP(W(nop))
+#endif
mov r3, r2, lsl r3
1: ldrex r2, [r1]
\instr r2, r2, r3
@@ -32,6 +37,11 @@ UNWIND( .fnstart )
add r1, r1, r0, lsl #2 @ Get word offset
mov r3, r2, lsl r3 @ create mask
smp_dmb
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+ .arch_extension mp
+ ALT_SMP(W(pldw) [r1])
+ ALT_UP(W(nop))
+#endif
1: ldrex r2, [r1]
ands r0, r2, r3 @ save old value of bit
\instr r2, r2, r3 @ toggle bit
diff --git a/arch/arm/lib/bswapsdi2.S b/arch/arm/lib/bswapsdi2.S
new file mode 100644
index 00000000000..9fcdd154eff
--- /dev/null
+++ b/arch/arm/lib/bswapsdi2.S
@@ -0,0 +1,36 @@
+#include <linux/linkage.h>
+
+#if __LINUX_ARM_ARCH__ >= 6
+ENTRY(__bswapsi2)
+ rev r0, r0
+ bx lr
+ENDPROC(__bswapsi2)
+
+ENTRY(__bswapdi2)
+ rev r3, r0
+ rev r0, r1
+ mov r1, r3
+ bx lr
+ENDPROC(__bswapdi2)
+#else
+ENTRY(__bswapsi2)
+ eor r3, r0, r0, ror #16
+ mov r3, r3, lsr #8
+ bic r3, r3, #0xff00
+ eor r0, r3, r0, ror #8
+ mov pc, lr
+ENDPROC(__bswapsi2)
+
+ENTRY(__bswapdi2)
+ mov ip, r1
+ eor r3, ip, ip, ror #16
+ eor r1, r0, r0, ror #16
+ mov r1, r1, lsr #8
+ mov r3, r3, lsr #8
+ bic r3, r3, #0xff00
+ bic r1, r1, #0xff00
+ eor r1, r1, r0, ror #8
+ eor r0, r3, ip, ror #8
+ mov pc, lr
+ENDPROC(__bswapdi2)
+#endif
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 805e3f8fb00..3bc8eb811a7 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -197,24 +197,24 @@
12: PLD( pld [r1, #124] )
13: ldr4w r1, r4, r5, r6, r7, abort=19f
- mov r3, lr, pull #\pull
+ mov r3, lr, lspull #\pull
subs r2, r2, #32
ldr4w r1, r8, r9, ip, lr, abort=19f
- orr r3, r3, r4, push #\push
- mov r4, r4, pull #\pull
- orr r4, r4, r5, push #\push
- mov r5, r5, pull #\pull
- orr r5, r5, r6, push #\push
- mov r6, r6, pull #\pull
- orr r6, r6, r7, push #\push
- mov r7, r7, pull #\pull
- orr r7, r7, r8, push #\push
- mov r8, r8, pull #\pull
- orr r8, r8, r9, push #\push
- mov r9, r9, pull #\pull
- orr r9, r9, ip, push #\push
- mov ip, ip, pull #\pull
- orr ip, ip, lr, push #\push
+ orr r3, r3, r4, lspush #\push
+ mov r4, r4, lspull #\pull
+ orr r4, r4, r5, lspush #\push
+ mov r5, r5, lspull #\pull
+ orr r5, r5, r6, lspush #\push
+ mov r6, r6, lspull #\pull
+ orr r6, r6, r7, lspush #\push
+ mov r7, r7, lspull #\pull
+ orr r7, r7, r8, lspush #\push
+ mov r8, r8, lspull #\pull
+ orr r8, r8, r9, lspush #\push
+ mov r9, r9, lspull #\pull
+ orr r9, r9, ip, lspush #\push
+ mov ip, ip, lspull #\pull
+ orr ip, ip, lr, lspush #\push
str8w r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
bge 12b
PLD( cmn r2, #96 )
@@ -225,10 +225,10 @@
14: ands ip, r2, #28
beq 16f
-15: mov r3, lr, pull #\pull
+15: mov r3, lr, lspull #\pull
ldr1w r1, lr, abort=21f
subs ip, ip, #4
- orr r3, r3, lr, push #\push
+ orr r3, r3, lr, lspush #\push
str1w r0, r3, abort=21f
bgt 15b
CALGN( cmp r2, #0 )
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index d620a5f22a0..d6e742d2400 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -141,7 +141,7 @@ FN_ENTRY
tst len, #2
mov r5, r4, get_byte_0
beq .Lexit
- adcs sum, sum, r4, push #16
+ adcs sum, sum, r4, lspush #16
strb r5, [dst], #1
mov r5, r4, get_byte_1
strb r5, [dst], #1
@@ -171,23 +171,23 @@ FN_ENTRY
cmp ip, #2
beq .Lsrc2_aligned
bhi .Lsrc3_aligned
- mov r4, r5, pull #8 @ C = 0
+ mov r4, r5, lspull #8 @ C = 0
bics ip, len, #15
beq 2f
1: load4l r5, r6, r7, r8
- 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
- mov r7, r7, pull #8
- orr r7, r7, r8, push #24
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
+ mov r6, r6, lspull #8
+ orr r6, r6, r7, lspush #24
+ mov r7, r7, lspull #8
+ orr r7, r7, r8, lspush #24
stmia dst!, {r4, r5, r6, r7}
adcs sum, sum, r4
adcs sum, sum, r5
adcs sum, sum, r6
adcs sum, sum, r7
- mov r4, r8, pull #8
+ mov r4, r8, lspull #8
sub ip, ip, #16
teq ip, #0
bne 1b
@@ -196,50 +196,50 @@ FN_ENTRY
tst ip, #8
beq 3f
load2l r5, r6
- orr r4, r4, r5, push #24
- mov r5, r5, pull #8
- orr r5, r5, r6, push #24
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
stmia dst!, {r4, r5}
adcs sum, sum, r4
adcs sum, sum, r5
- mov r4, r6, pull #8
+ mov r4, r6, lspull #8
tst ip, #4
beq 4f
3: load1l r5
- orr r4, r4, r5, push #24
+ orr r4, r4, r5, lspush #24
str r4, [dst], #4
adcs sum, sum, r4
- mov r4, r5, pull #8
+ mov r4, r5, lspull #8
4: ands len, len, #3
beq .Ldone
mov r5, r4, get_byte_0
tst len, #2
beq .Lexit
- adcs sum, sum, r4, push #16
+ adcs sum, sum, r4, lspush #16
strb r5, [dst], #1
mov r5, r4, get_byte_1
strb r5, [dst], #1
mov r5, r4, get_byte_2
b .Lexit
-.Lsrc2_aligned: mov r4, r5, pull #16
+.Lsrc2_aligned: mov r4, r5, lspull #16
adds sum, sum, #0
bics ip, len, #15
beq 2f
1: load4l r5, r6, r7, r8
- 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
- mov r7, r7, pull #16
- orr r7, r7, r8, push #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
+ mov r6, r6, lspull #16
+ orr r6, r6, r7, lspush #16
+ mov r7, r7, lspull #16
+ orr r7, r7, r8, lspush #16
stmia dst!, {r4, r5, r6, r7}
adcs sum, sum, r4
adcs sum, sum, r5
adcs sum, sum, r6
adcs sum, sum, r7
- mov r4, r8, pull #16
+ mov r4, r8, lspull #16
sub ip, ip, #16
teq ip, #0
bne 1b
@@ -248,20 +248,20 @@ FN_ENTRY
tst ip, #8
beq 3f
load2l r5, r6
- orr r4, r4, r5, push #16
- mov r5, r5, pull #16
- orr r5, r5, r6, push #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
stmia dst!, {r4, r5}
adcs sum, sum, r4
adcs sum, sum, r5
- mov r4, r6, pull #16
+ mov r4, r6, lspull #16
tst ip, #4
beq 4f
3: load1l r5
- orr r4, r4, r5, push #16
+ orr r4, r4, r5, lspush #16
str r4, [dst], #4
adcs sum, sum, r4
- mov r4, r5, pull #16
+ mov r4, r5, lspull #16
4: ands len, len, #3
beq .Ldone
mov r5, r4, get_byte_0
@@ -276,24 +276,24 @@ FN_ENTRY
load1b r5
b .Lexit
-.Lsrc3_aligned: mov r4, r5, pull #24
+.Lsrc3_aligned: mov r4, r5, lspull #24
adds sum, sum, #0
bics ip, len, #15
beq 2f
1: load4l r5, r6, r7, r8
- 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
- mov r7, r7, pull #24
- orr r7, r7, r8, push #8
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
+ mov r6, r6, lspull #24
+ orr r6, r6, r7, lspush #8
+ mov r7, r7, lspull #24
+ orr r7, r7, r8, lspush #8
stmia dst!, {r4, r5, r6, r7}
adcs sum, sum, r4
adcs sum, sum, r5
adcs sum, sum, r6
adcs sum, sum, r7
- mov r4, r8, pull #24
+ mov r4, r8, lspull #24
sub ip, ip, #16
teq ip, #0
bne 1b
@@ -302,20 +302,20 @@ FN_ENTRY
tst ip, #8
beq 3f
load2l r5, r6
- orr r4, r4, r5, push #8
- mov r5, r5, pull #24
- orr r5, r5, r6, push #8
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
stmia dst!, {r4, r5}
adcs sum, sum, r4
adcs sum, sum, r5
- mov r4, r6, pull #24
+ mov r4, r6, lspull #24
tst ip, #4
beq 4f
3: load1l r5
- orr r4, r4, r5, push #8
+ orr r4, r4, r5, lspush #8
str r4, [dst], #4
adcs sum, sum, r4
- mov r4, r5, pull #24
+ mov r4, r5, lspull #24
4: ands len, len, #3
beq .Ldone
mov r5, r4, get_byte_0
@@ -326,7 +326,7 @@ FN_ENTRY
load1l r4
mov r5, r4, get_byte_0
strb r5, [dst], #1
- adcs sum, sum, r4, push #24
+ adcs sum, sum, r4, lspush #24
mov r5, r4, get_byte_1
b .Lexit
FN_EXIT
diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
index 36b668d8e12..bc1033b897b 100644
--- a/arch/arm/lib/delay-loop.S
+++ b/arch/arm/lib/delay-loop.S
@@ -40,6 +40,7 @@ ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0x7fffff06
/*
* loops = r0 * HZ * loops_per_jiffy / 1000000
*/
+ .align 3
@ Delay routine
ENTRY(__loop_delay)
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index 0dc53854a5d..5306de35013 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -58,7 +58,7 @@ static void __timer_delay(unsigned long cycles)
static void __timer_const_udelay(unsigned long xloops)
{
unsigned long long loops = xloops;
- loops *= loops_per_jiffy;
+ loops *= arm_delay_ops.ticks_per_jiffy;
__timer_delay(loops >> UDELAY_SHIFT);
}
@@ -73,17 +73,20 @@ void __init register_current_timer_delay(const struct delay_timer *timer)
pr_info("Switching to timer-based delay loop\n");
delay_timer = timer;
lpj_fine = timer->freq / HZ;
- loops_per_jiffy = lpj_fine;
+
+ /* cpufreq may scale loops_per_jiffy, so keep a private copy */
+ arm_delay_ops.ticks_per_jiffy = lpj_fine;
arm_delay_ops.delay = __timer_delay;
arm_delay_ops.const_udelay = __timer_const_udelay;
arm_delay_ops.udelay = __timer_udelay;
+
delay_calibrated = true;
} else {
pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");
}
}
-unsigned long __cpuinit calibrate_delay_is_known(void)
+unsigned long calibrate_delay_is_known(void)
{
delay_calibrated = true;
return lpj_fine;
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 5fb97e7f9f4..7a7430950c7 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -47,25 +47,25 @@ ENTRY(__raw_readsl)
strb ip, [r1], #1
4: subs r2, r2, #1
- mov ip, r3, pull #24
+ mov ip, r3, lspull #24
ldrne r3, [r0]
- orrne ip, ip, r3, push #8
+ orrne ip, ip, r3, lspush #8
strne ip, [r1], #4
bne 4b
b 8f
5: subs r2, r2, #1
- mov ip, r3, pull #16
+ mov ip, r3, lspull #16
ldrne r3, [r0]
- orrne ip, ip, r3, push #16
+ orrne ip, ip, r3, lspush #16
strne ip, [r1], #4
bne 5b
b 7f
6: subs r2, r2, #1
- mov ip, r3, pull #8
+ mov ip, r3, lspull #8
ldrne r3, [r0]
- orrne ip, ip, r3, push #24
+ orrne ip, ip, r3, lspush #24
strne ip, [r1], #4
bne 6b
diff --git a/arch/arm/lib/io-shark.c b/arch/arm/lib/io-shark.c
deleted file mode 100644
index 824253948f5..00000000000
--- a/arch/arm/lib/io-shark.c
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * linux/arch/arm/lib/io-shark.c
- *
- * by Alexander Schulz
- *
- * derived from:
- * linux/arch/arm/lib/io-ebsa.S
- * Copyright (C) 1995, 1996 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.
- */
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index 8d3b7813725..d0d104a0dd1 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -41,26 +41,26 @@ ENTRY(__raw_writesl)
blt 5f
bgt 6f
-4: mov ip, r3, pull #16
+4: mov ip, r3, lspull #16
ldr r3, [r1], #4
subs r2, r2, #1
- orr ip, ip, r3, push #16
+ orr ip, ip, r3, lspush #16
str ip, [r0]
bne 4b
mov pc, lr
-5: mov ip, r3, pull #8
+5: mov ip, r3, lspull #8
ldr r3, [r1], #4
subs r2, r2, #1
- orr ip, ip, r3, push #24
+ orr ip, ip, r3, lspush #24
str ip, [r0]
bne 5b
mov pc, lr
-6: mov ip, r3, pull #24
+6: mov ip, r3, lspull #24
ldr r3, [r1], #4
subs r2, r2, #1
- orr ip, ip, r3, push #8
+ orr ip, ip, r3, lspush #8
str ip, [r0]
bne 6b
mov pc, lr
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 938fc14f962..d1fc0c0c342 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -147,24 +147,24 @@ ENTRY(memmove)
12: PLD( pld [r1, #-128] )
13: ldmdb r1!, {r7, r8, r9, ip}
- mov lr, r3, push #\push
+ mov lr, r3, lspush #\push
subs r2, r2, #32
ldmdb r1!, {r3, r4, r5, r6}
- orr lr, lr, ip, pull #\pull
- mov ip, ip, push #\push
- orr ip, ip, r9, pull #\pull
- mov r9, r9, push #\push
- orr r9, r9, r8, pull #\pull
- mov r8, r8, push #\push
- orr r8, r8, r7, pull #\pull
- mov r7, r7, push #\push
- orr r7, r7, r6, pull #\pull
- mov r6, r6, push #\push
- orr r6, r6, r5, pull #\pull
- mov r5, r5, push #\push
- orr r5, r5, r4, pull #\pull
- mov r4, r4, push #\push
- orr r4, r4, r3, pull #\pull
+ orr lr, lr, ip, lspull #\pull
+ mov ip, ip, lspush #\push
+ orr ip, ip, r9, lspull #\pull
+ mov r9, r9, lspush #\push
+ orr r9, r9, r8, lspull #\pull
+ mov r8, r8, lspush #\push
+ orr r8, r8, r7, lspull #\pull
+ mov r7, r7, lspush #\push
+ orr r7, r7, r6, lspull #\pull
+ mov r6, r6, lspush #\push
+ orr r6, r6, r5, lspull #\pull
+ mov r5, r5, lspush #\push
+ orr r5, r5, r4, lspull #\pull
+ mov r4, r4, lspush #\push
+ orr r4, r4, r3, lspull #\pull
stmdb r0!, {r4 - r9, ip, lr}
bge 12b
PLD( cmn r2, #96 )
@@ -175,10 +175,10 @@ ENTRY(memmove)
14: ands ip, r2, #28
beq 16f
-15: mov lr, r3, push #\push
+15: mov lr, r3, lspush #\push
ldr r3, [r1, #-4]!
subs ip, ip, #4
- orr lr, lr, r3, pull #\pull
+ orr lr, lr, r3, lspull #\pull
str lr, [r0, #-4]!
bgt 15b
CALGN( cmp r2, #0 )
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 650d5923ab8..94b0650ea98 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -14,27 +14,15 @@
.text
.align 5
- .word 0
-
-1: subs r2, r2, #4 @ 1 do we have enough
- blt 5f @ 1 bytes to align with?
- cmp r3, #2 @ 1
- strltb r1, [r0], #1 @ 1
- strleb r1, [r0], #1 @ 1
- strb r1, [r0], #1 @ 1
- add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3))
-/*
- * The pointer is now aligned and the length is adjusted. Try doing the
- * memset again.
- */
ENTRY(memset)
ands r3, r0, #3 @ 1 unaligned?
- bne 1b @ 1
+ mov ip, r0 @ preserve r0 as return value
+ bne 6f @ 1
/*
- * we know that the pointer in r0 is aligned to a word boundary.
+ * we know that the pointer in ip is aligned to a word boundary.
*/
- orr r1, r1, r1, lsl #8
+1: orr r1, r1, r1, lsl #8
orr r1, r1, r1, lsl #16
mov r3, r1
cmp r2, #16
@@ -43,29 +31,28 @@ ENTRY(memset)
#if ! CALGN(1)+0
/*
- * We need an extra register for this loop - save the return address and
- * use the LR
+ * We need 2 extra registers for this loop - use r8 and the LR
*/
- str lr, [sp, #-4]!
- mov ip, r1
+ stmfd sp!, {r8, lr}
+ mov r8, r1
mov lr, r1
2: subs r2, r2, #64
- stmgeia r0!, {r1, r3, ip, lr} @ 64 bytes at a time.
- stmgeia r0!, {r1, r3, ip, lr}
- stmgeia r0!, {r1, r3, ip, lr}
- stmgeia r0!, {r1, r3, ip, lr}
+ stmgeia ip!, {r1, r3, r8, lr} @ 64 bytes at a time.
+ stmgeia ip!, {r1, r3, r8, lr}
+ stmgeia ip!, {r1, r3, r8, lr}
+ stmgeia ip!, {r1, r3, r8, lr}
bgt 2b
- ldmeqfd sp!, {pc} @ Now <64 bytes to go.
+ ldmeqfd sp!, {r8, pc} @ Now <64 bytes to go.
/*
* No need to correct the count; we're only testing bits from now on
*/
tst r2, #32
- stmneia r0!, {r1, r3, ip, lr}
- stmneia r0!, {r1, r3, ip, lr}
+ stmneia ip!, {r1, r3, r8, lr}
+ stmneia ip!, {r1, r3, r8, lr}
tst r2, #16
- stmneia r0!, {r1, r3, ip, lr}
- ldr lr, [sp], #4
+ stmneia ip!, {r1, r3, r8, lr}
+ ldmfd sp!, {r8, lr}
#else
@@ -74,54 +61,63 @@ ENTRY(memset)
* whole cache lines at once.
*/
- stmfd sp!, {r4-r7, lr}
+ stmfd sp!, {r4-r8, lr}
mov r4, r1
mov r5, r1
mov r6, r1
mov r7, r1
- mov ip, r1
+ mov r8, r1
mov lr, r1
cmp r2, #96
- tstgt r0, #31
+ tstgt ip, #31
ble 3f
- and ip, r0, #31
- rsb ip, ip, #32
- sub r2, r2, ip
- movs ip, ip, lsl #(32 - 4)
- stmcsia r0!, {r4, r5, r6, r7}
- stmmiia r0!, {r4, r5}
- tst ip, #(1 << 30)
- mov ip, r1
- strne r1, [r0], #4
+ and r8, ip, #31
+ rsb r8, r8, #32
+ sub r2, r2, r8
+ movs r8, r8, lsl #(32 - 4)
+ stmcsia ip!, {r4, r5, r6, r7}
+ stmmiia ip!, {r4, r5}
+ tst r8, #(1 << 30)
+ mov r8, r1
+ strne r1, [ip], #4
3: subs r2, r2, #64
- stmgeia r0!, {r1, r3-r7, ip, lr}
- stmgeia r0!, {r1, r3-r7, ip, lr}
+ stmgeia ip!, {r1, r3-r8, lr}
+ stmgeia ip!, {r1, r3-r8, lr}
bgt 3b
- ldmeqfd sp!, {r4-r7, pc}
+ ldmeqfd sp!, {r4-r8, pc}
tst r2, #32
- stmneia r0!, {r1, r3-r7, ip, lr}
+ stmneia ip!, {r1, r3-r8, lr}
tst r2, #16
- stmneia r0!, {r4-r7}
- ldmfd sp!, {r4-r7, lr}
+ stmneia ip!, {r4-r7}
+ ldmfd sp!, {r4-r8, lr}
#endif
4: tst r2, #8
- stmneia r0!, {r1, r3}
+ stmneia ip!, {r1, r3}
tst r2, #4
- strne r1, [r0], #4
+ strne r1, [ip], #4
/*
* When we get here, we've got less than 4 bytes to zero. We
* may have an unaligned pointer as well.
*/
5: tst r2, #2
- strneb r1, [r0], #1
- strneb r1, [r0], #1
+ strneb r1, [ip], #1
+ strneb r1, [ip], #1
tst r2, #1
- strneb r1, [r0], #1
+ strneb r1, [ip], #1
mov pc, lr
+
+6: subs r2, r2, #4 @ 1 do we have enough
+ blt 5b @ 1 bytes to align with?
+ cmp r3, #2 @ 1
+ strltb r1, [ip], #1 @ 1
+ strleb r1, [ip], #1 @ 1
+ strb r1, [ip], #1 @ 1
+ add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3))
+ b 1b
ENDPROC(memset)
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index 5c908b1cb8e..e50520904b7 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -117,9 +117,9 @@ USER( TUSER( strgtb) r3, [r0], #1) @ May fault
.Lc2u_1fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lc2u_1nowords
- mov r3, r7, pull #8
+ mov r3, r7, lspull #8
ldr r7, [r1], #4
- orr r3, r3, r7, push #24
+ orr r3, r3, r7, lspush #24
USER( TUSER( str) r3, [r0], #4) @ May fault
mov ip, r0, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -131,30 +131,30 @@ USER( TUSER( str) r3, [r0], #4) @ May fault
subs ip, ip, #16
blt .Lc2u_1rem8lp
-.Lc2u_1cpy8lp: mov r3, r7, pull #8
+.Lc2u_1cpy8lp: mov r3, r7, lspull #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
+ orr r3, r3, r4, lspush #24
+ mov r4, r4, lspull #8
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
+ mov r6, r6, lspull #8
+ orr r6, r6, r7, lspush #24
stmia r0!, {r3 - r6} @ Shouldnt fault
bpl .Lc2u_1cpy8lp
.Lc2u_1rem8lp: tst ip, #8
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
ldmneia r1!, {r4, r7}
- orrne r3, r3, r4, push #24
- movne r4, r4, pull #8
- orrne r4, r4, r7, push #24
+ orrne r3, r3, r4, lspush #24
+ movne r4, r4, lspull #8
+ orrne r4, r4, r7, lspush #24
stmneia r0!, {r3 - r4} @ Shouldnt fault
tst ip, #4
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
ldrne r7, [r1], #4
- orrne r3, r3, r7, push #24
+ orrne r3, r3, r7, lspush #24
TUSER( strne) r3, [r0], #4 @ Shouldnt fault
ands ip, ip, #3
beq .Lc2u_1fupi
@@ -172,9 +172,9 @@ USER( TUSER( strgtb) r3, [r0], #1) @ May fault
.Lc2u_2fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lc2u_2nowords
- mov r3, r7, pull #16
+ mov r3, r7, lspull #16
ldr r7, [r1], #4
- orr r3, r3, r7, push #16
+ orr r3, r3, r7, lspush #16
USER( TUSER( str) r3, [r0], #4) @ May fault
mov ip, r0, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -186,30 +186,30 @@ USER( TUSER( str) r3, [r0], #4) @ May fault
subs ip, ip, #16
blt .Lc2u_2rem8lp
-.Lc2u_2cpy8lp: mov r3, r7, pull #16
+.Lc2u_2cpy8lp: mov r3, r7, lspull #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
+ orr r3, r3, r4, lspush #16
+ mov r4, r4, lspull #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
+ mov r6, r6, lspull #16
+ orr r6, r6, r7, lspush #16
stmia r0!, {r3 - r6} @ Shouldnt fault
bpl .Lc2u_2cpy8lp
.Lc2u_2rem8lp: tst ip, #8
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
ldmneia r1!, {r4, r7}
- orrne r3, r3, r4, push #16
- movne r4, r4, pull #16
- orrne r4, r4, r7, push #16
+ orrne r3, r3, r4, lspush #16
+ movne r4, r4, lspull #16
+ orrne r4, r4, r7, lspush #16
stmneia r0!, {r3 - r4} @ Shouldnt fault
tst ip, #4
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
ldrne r7, [r1], #4
- orrne r3, r3, r7, push #16
+ orrne r3, r3, r7, lspush #16
TUSER( strne) r3, [r0], #4 @ Shouldnt fault
ands ip, ip, #3
beq .Lc2u_2fupi
@@ -227,9 +227,9 @@ USER( TUSER( strgtb) r3, [r0], #1) @ May fault
.Lc2u_3fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lc2u_3nowords
- mov r3, r7, pull #24
+ mov r3, r7, lspull #24
ldr r7, [r1], #4
- orr r3, r3, r7, push #8
+ orr r3, r3, r7, lspush #8
USER( TUSER( str) r3, [r0], #4) @ May fault
mov ip, r0, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -241,30 +241,30 @@ USER( TUSER( str) r3, [r0], #4) @ May fault
subs ip, ip, #16
blt .Lc2u_3rem8lp
-.Lc2u_3cpy8lp: mov r3, r7, pull #24
+.Lc2u_3cpy8lp: mov r3, r7, lspull #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
+ orr r3, r3, r4, lspush #8
+ mov r4, r4, lspull #24
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
+ mov r6, r6, lspull #24
+ orr r6, r6, r7, lspush #8
stmia r0!, {r3 - r6} @ Shouldnt fault
bpl .Lc2u_3cpy8lp
.Lc2u_3rem8lp: tst ip, #8
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
ldmneia r1!, {r4, r7}
- orrne r3, r3, r4, push #8
- movne r4, r4, pull #24
- orrne r4, r4, r7, push #8
+ orrne r3, r3, r4, lspush #8
+ movne r4, r4, lspull #24
+ orrne r4, r4, r7, lspush #8
stmneia r0!, {r3 - r4} @ Shouldnt fault
tst ip, #4
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
ldrne r7, [r1], #4
- orrne r3, r3, r7, push #8
+ orrne r3, r3, r7, lspush #8
TUSER( strne) r3, [r0], #4 @ Shouldnt fault
ands ip, ip, #3
beq .Lc2u_3fupi
@@ -382,9 +382,9 @@ USER( TUSER( ldr) r7, [r1], #4) @ May fault
.Lcfu_1fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lcfu_1nowords
- mov r3, r7, pull #8
+ mov r3, r7, lspull #8
USER( TUSER( ldr) r7, [r1], #4) @ May fault
- orr r3, r3, r7, push #24
+ orr r3, r3, r7, lspush #24
str r3, [r0], #4
mov ip, r1, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -396,30 +396,30 @@ USER( TUSER( ldr) r7, [r1], #4) @ May fault
subs ip, ip, #16
blt .Lcfu_1rem8lp
-.Lcfu_1cpy8lp: mov r3, r7, pull #8
+.Lcfu_1cpy8lp: mov r3, r7, lspull #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
+ orr r3, r3, r4, lspush #24
+ mov r4, r4, lspull #8
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
+ mov r6, r6, lspull #8
+ orr r6, r6, r7, lspush #24
stmia r0!, {r3 - r6}
bpl .Lcfu_1cpy8lp
.Lcfu_1rem8lp: tst ip, #8
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
ldmneia r1!, {r4, r7} @ Shouldnt fault
- orrne r3, r3, r4, push #24
- movne r4, r4, pull #8
- orrne r4, r4, r7, push #24
+ orrne r3, r3, r4, lspush #24
+ movne r4, r4, lspull #8
+ orrne r4, r4, r7, lspush #24
stmneia r0!, {r3 - r4}
tst ip, #4
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
USER( TUSER( ldrne) r7, [r1], #4) @ May fault
- orrne r3, r3, r7, push #24
+ orrne r3, r3, r7, lspush #24
strne r3, [r0], #4
ands ip, ip, #3
beq .Lcfu_1fupi
@@ -437,9 +437,9 @@ USER( TUSER( ldrne) r7, [r1], #4) @ May fault
.Lcfu_2fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lcfu_2nowords
- mov r3, r7, pull #16
+ mov r3, r7, lspull #16
USER( TUSER( ldr) r7, [r1], #4) @ May fault
- orr r3, r3, r7, push #16
+ orr r3, r3, r7, lspush #16
str r3, [r0], #4
mov ip, r1, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -452,30 +452,30 @@ USER( TUSER( ldr) r7, [r1], #4) @ May fault
blt .Lcfu_2rem8lp
-.Lcfu_2cpy8lp: mov r3, r7, pull #16
+.Lcfu_2cpy8lp: mov r3, r7, lspull #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
+ orr r3, r3, r4, lspush #16
+ mov r4, r4, lspull #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
+ mov r6, r6, lspull #16
+ orr r6, r6, r7, lspush #16
stmia r0!, {r3 - r6}
bpl .Lcfu_2cpy8lp
.Lcfu_2rem8lp: tst ip, #8
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
ldmneia r1!, {r4, r7} @ Shouldnt fault
- orrne r3, r3, r4, push #16
- movne r4, r4, pull #16
- orrne r4, r4, r7, push #16
+ orrne r3, r3, r4, lspush #16
+ movne r4, r4, lspull #16
+ orrne r4, r4, r7, lspush #16
stmneia r0!, {r3 - r4}
tst ip, #4
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
USER( TUSER( ldrne) r7, [r1], #4) @ May fault
- orrne r3, r3, r7, push #16
+ orrne r3, r3, r7, lspush #16
strne r3, [r0], #4
ands ip, ip, #3
beq .Lcfu_2fupi
@@ -493,9 +493,9 @@ USER( TUSER( ldrgtb) r3, [r1], #0) @ May fault
.Lcfu_3fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lcfu_3nowords
- mov r3, r7, pull #24
+ mov r3, r7, lspull #24
USER( TUSER( ldr) r7, [r1], #4) @ May fault
- orr r3, r3, r7, push #8
+ orr r3, r3, r7, lspush #8
str r3, [r0], #4
mov ip, r1, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -507,30 +507,30 @@ USER( TUSER( ldr) r7, [r1], #4) @ May fault
subs ip, ip, #16
blt .Lcfu_3rem8lp
-.Lcfu_3cpy8lp: mov r3, r7, pull #24
+.Lcfu_3cpy8lp: mov r3, r7, lspull #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
+ orr r3, r3, r4, lspush #8
+ mov r4, r4, lspull #24
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
+ mov r6, r6, lspull #24
+ orr r6, r6, r7, lspush #8
stmia r0!, {r3 - r6}
subs ip, ip, #16
bpl .Lcfu_3cpy8lp
.Lcfu_3rem8lp: tst ip, #8
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
ldmneia r1!, {r4, r7} @ Shouldnt fault
- orrne r3, r3, r4, push #8
- movne r4, r4, pull #24
- orrne r4, r4, r7, push #8
+ orrne r3, r3, r4, lspush #8
+ movne r4, r4, lspull #24
+ orrne r4, r4, r7, lspush #8
stmneia r0!, {r3 - r4}
tst ip, #4
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
USER( TUSER( ldrne) r7, [r1], #4) @ May fault
- orrne r3, r3, r7, push #8
+ orrne r3, r3, r7, lspush #8
strne r3, [r0], #4
ands ip, ip, #3
beq .Lcfu_3fupi
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 025f742dd4d..3e58d710013 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -18,6 +18,7 @@
#include <linux/hardirq.h> /* for in_atomic() */
#include <linux/gfp.h>
#include <linux/highmem.h>
+#include <linux/hugetlb.h>
#include <asm/current.h>
#include <asm/page.h>
@@ -40,7 +41,35 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
return 0;
pmd = pmd_offset(pud, addr);
- if (unlikely(pmd_none(*pmd) || pmd_bad(*pmd)))
+ if (unlikely(pmd_none(*pmd)))
+ return 0;
+
+ /*
+ * A pmd can be bad if it refers to a HugeTLB or THP page.
+ *
+ * Both THP and HugeTLB pages have the same pmd layout
+ * and should not be manipulated by the pte functions.
+ *
+ * Lock the page table for the destination and check
+ * to see that it's still huge and whether or not we will
+ * need to fault on write, or if we have a splitting THP.
+ */
+ if (unlikely(pmd_thp_or_huge(*pmd))) {
+ ptl = &current->mm->page_table_lock;
+ spin_lock(ptl);
+ if (unlikely(!pmd_thp_or_huge(*pmd)
+ || pmd_hugewillfault(*pmd)
+ || pmd_trans_splitting(*pmd))) {
+ spin_unlock(ptl);
+ return 0;
+ }
+
+ *ptep = NULL;
+ *ptlp = ptl;
+ return 1;
+ }
+
+ if (unlikely(pmd_bad(*pmd)))
return 0;
pte = pte_offset_map_lock(current->mm, pmd, addr, &ptl);
@@ -94,7 +123,10 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
from += tocopy;
n -= tocopy;
- pte_unmap_unlock(pte, ptl);
+ if (pte)
+ pte_unmap_unlock(pte, ptl);
+ else
+ spin_unlock(ptl);
}
if (!atomic)
up_read(&current->mm->mmap_sem);
@@ -147,7 +179,10 @@ __clear_user_memset(void __user *addr, unsigned long n)
addr += tocopy;
n -= tocopy;
- pte_unmap_unlock(pte, ptl);
+ if (pte)
+ pte_unmap_unlock(pte, ptl);
+ else
+ spin_unlock(ptl);
}
up_read(&current->mm->mmap_sem);
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
new file mode 100644
index 00000000000..2c40aeab3ea
--- /dev/null
+++ b/arch/arm/lib/xor-neon.c
@@ -0,0 +1,46 @@
+/*
+ * linux/arch/arm/lib/xor-neon.c
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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/raid/xor.h>
+#include <linux/module.h>
+
+MODULE_LICENSE("GPL");
+
+#ifndef __ARM_NEON__
+#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+#endif
+
+/*
+ * Pull in the reference implementations while instructing GCC (through
+ * -ftree-vectorize) to attempt to exploit implicit parallelism and emit
+ * NEON instructions.
+ */
+#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#pragma GCC optimize "tree-vectorize"
+#else
+/*
+ * While older versions of GCC do not generate incorrect code, they fail to
+ * recognize the parallel nature of these functions, and emit plain ARM code,
+ * which is known to be slower than the optimized ARM code in asm-arm/xor.h.
+ */
+#warning This code requires at least version 4.6 of GCC
+#endif
+
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#include <asm-generic/xor.h>
+
+struct xor_block_template const xor_block_neon_inner = {
+ .name = "__inner_neon__",
+ .do_2 = xor_8regs_2,
+ .do_3 = xor_8regs_3,
+ .do_4 = xor_8regs_4,
+ .do_5 = xor_8regs_5,
+};
+EXPORT_SYMBOL(xor_block_neon_inner);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 22:55:51 +0000