summaryrefslogtreecommitdiff
path: root/arch/arm/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/lib')
-rw-r--r--arch/arm/lib/Makefile15
-rw-r--r--arch/arm/lib/backtrace-clang.S25
-rw-r--r--arch/arm/lib/backtrace.S24
-rw-r--r--arch/arm/lib/bitops.h14
-rw-r--r--arch/arm/lib/call_with_stack.S35
-rw-r--r--arch/arm/lib/copy_from_user.S18
-rw-r--r--arch/arm/lib/copy_template.S67
-rw-r--r--arch/arm/lib/copy_to_user.S16
-rw-r--r--arch/arm/lib/crc-t10dif-core.S468
-rw-r--r--arch/arm/lib/crc-t10dif-glue.c72
-rw-r--r--arch/arm/lib/crc32-core.S306
-rw-r--r--arch/arm/lib/crc32-glue.c123
-rw-r--r--arch/arm/lib/csumpartialcopy.S4
-rw-r--r--arch/arm/lib/csumpartialcopygeneric.S1
-rw-r--r--arch/arm/lib/csumpartialcopyuser.S46
-rw-r--r--arch/arm/lib/delay-loop.S20
-rw-r--r--arch/arm/lib/error-inject.c10
-rw-r--r--arch/arm/lib/findbit.S232
-rw-r--r--arch/arm/lib/memcpy.S17
-rw-r--r--arch/arm/lib/memmove.S66
-rw-r--r--arch/arm/lib/memset.S12
-rw-r--r--arch/arm/lib/testchangebit.S4
-rw-r--r--arch/arm/lib/testclearbit.S4
-rw-r--r--arch/arm/lib/testsetbit.S4
-rw-r--r--arch/arm/lib/uaccess_with_memcpy.c46
-rw-r--r--arch/arm/lib/xor-neon.c13
26 files changed, 1308 insertions, 354 deletions
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 6d2ba454f25b..007874320937 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -36,15 +36,18 @@ else
lib-y += io-readsw-armv4.o io-writesw-armv4.o
endif
-ifeq ($(CONFIG_ARCH_RPC),y)
- AFLAGS_delay-loop.o += -march=armv4
-endif
-
$(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S
$(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S
ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
- NEON_FLAGS := -march=armv7-a -mfloat-abi=softfp -mfpu=neon
- CFLAGS_xor-neon.o += $(NEON_FLAGS)
+ CFLAGS_xor-neon.o += $(CC_FLAGS_FPU)
obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o
endif
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+
+obj-$(CONFIG_CRC32_ARCH) += crc32-arm.o
+crc32-arm-y := crc32-glue.o crc32-core.o
+
+obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-arm.o
+crc-t10dif-arm-y := crc-t10dif-glue.o crc-t10dif-core.o
diff --git a/arch/arm/lib/backtrace-clang.S b/arch/arm/lib/backtrace-clang.S
index 2ff375144b55..290c52a60fc6 100644
--- a/arch/arm/lib/backtrace-clang.S
+++ b/arch/arm/lib/backtrace-clang.S
@@ -17,6 +17,7 @@
#define sv_pc r6
#define mask r7
#define sv_lr r8
+#define loglvl r9
ENTRY(c_backtrace)
@@ -99,6 +100,7 @@ ENDPROC(c_backtrace)
@ to ensure 8 byte alignment
movs frame, r0 @ if frame pointer is zero
beq no_frame @ we have no stack frames
+ mov loglvl, r2
tst r1, #0x10 @ 26 or 32-bit mode?
moveq mask, #0xfc000003
movne mask, #0 @ mask for 32-bit
@@ -142,7 +144,7 @@ for_each_frame: tst frame, mask @ Check for address exceptions
*/
1003: ldr sv_lr, [sv_fp, #4] @ get saved lr from next frame
- ldr r0, [sv_lr, #-4] @ get call instruction
+1004: ldr r0, [sv_lr, #-4] @ get call instruction
ldr r3, .Lopcode+4
and r2, r3, r0 @ is this a bl call
teq r2, r3
@@ -162,11 +164,12 @@ finished_setup:
/*
* Print the function (sv_pc) and where it was called from (sv_lr).
*/
-1004: mov r0, sv_pc
+ mov r0, sv_pc
mov r1, sv_lr
mov r2, frame
bic r1, r1, mask @ mask PC/LR for the mode
+ mov r3, loglvl
bl dump_backtrace_entry
/*
@@ -183,6 +186,7 @@ finished_setup:
ldr r0, [frame] @ locals are stored in
@ the preceding frame
subeq r0, r0, #4
+ mov r2, loglvl
bleq dump_backtrace_stm @ dump saved registers
/*
@@ -193,11 +197,20 @@ finished_setup:
cmp sv_fp, frame @ next frame must be
mov frame, sv_fp @ above the current frame
+#ifdef CONFIG_IRQSTACKS
+ @
+ @ Kernel stacks may be discontiguous in memory. If the next
+ @ frame is below the previous frame, accept it as long as it
+ @ lives in kernel memory.
+ @
+ cmpls sv_fp, #PAGE_OFFSET
+#endif
bhi for_each_frame
1006: adr r0, .Lbad
- mov r1, frame
- bl printk
+ mov r1, loglvl
+ mov r2, frame
+ bl _printk
no_frame: ldmfd sp!, {r4 - r9, fp, pc}
ENDPROC(c_backtrace)
.pushsection __ex_table,"a"
@@ -205,11 +218,11 @@ ENDPROC(c_backtrace)
.long 1001b, 1006b
.long 1002b, 1006b
.long 1003b, 1006b
- .long 1004b, 1006b
+ .long 1004b, finished_setup
.long 1005b, 1006b
.popsection
-.Lbad: .asciz "Backtrace aborted due to bad frame pointer <%p>\n"
+.Lbad: .asciz "%sBacktrace aborted due to bad frame pointer <%p>\n"
.align
.Lopcode: .word 0xe92d4800 >> 11 @ stmfd sp!, {... fp, lr}
.word 0x0b000000 @ bl if these bits are set
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
index 582925238d65..293a2716bd20 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -18,6 +18,7 @@
#define sv_pc r6
#define mask r7
#define offset r8
+#define loglvl r9
ENTRY(c_backtrace)
@@ -25,9 +26,10 @@ ENTRY(c_backtrace)
ret lr
ENDPROC(c_backtrace)
#else
- stmfd sp!, {r4 - r8, lr} @ Save an extra register so we have a location...
+ stmfd sp!, {r4 - r9, lr} @ Save an extra register so we have a location...
movs frame, r0 @ if frame pointer is zero
beq no_frame @ we have no stack frames
+ mov loglvl, r2
tst r1, #0x10 @ 26 or 32-bit mode?
ARM( moveq mask, #0xfc000003 )
@@ -73,6 +75,7 @@ for_each_frame: tst frame, mask @ Check for address exceptions
ldr r1, [frame, #-4] @ get saved lr
mov r2, frame
bic r1, r1, mask @ mask PC/LR for the mode
+ mov r3, loglvl
bl dump_backtrace_entry
ldr r1, [sv_pc, #-4] @ if stmfd sp!, {args} exists,
@@ -80,12 +83,14 @@ for_each_frame: tst frame, mask @ Check for address exceptions
teq r3, r1, lsr #11
ldreq r0, [frame, #-8] @ get sp
subeq r0, r0, #4 @ point at the last arg
+ mov r2, loglvl
bleq dump_backtrace_stm @ 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 #11
subeq r0, frame, #16
+ mov r2, loglvl
bleq dump_backtrace_stm @ dump saved registers
teq sv_fp, #0 @ zero saved fp means
@@ -93,12 +98,21 @@ for_each_frame: tst frame, mask @ Check for address exceptions
cmp sv_fp, frame @ next frame must be
mov frame, sv_fp @ above the current frame
+#ifdef CONFIG_IRQSTACKS
+ @
+ @ Kernel stacks may be discontiguous in memory. If the next
+ @ frame is below the previous frame, accept it as long as it
+ @ lives in kernel memory.
+ @
+ cmpls sv_fp, #PAGE_OFFSET
+#endif
bhi for_each_frame
1006: adr r0, .Lbad
- mov r1, frame
- bl printk
-no_frame: ldmfd sp!, {r4 - r8, pc}
+ mov r1, loglvl
+ mov r2, frame
+ bl _printk
+no_frame: ldmfd sp!, {r4 - r9, pc}
ENDPROC(c_backtrace)
.pushsection __ex_table,"a"
@@ -109,7 +123,7 @@ ENDPROC(c_backtrace)
.long 1004b, 1006b
.popsection
-.Lbad: .asciz "Backtrace aborted due to bad frame pointer <%p>\n"
+.Lbad: .asciz "%sBacktrace aborted due to bad frame pointer <%p>\n"
.align
.Ldsi: .word 0xe92dd800 >> 11 @ stmfd sp!, {... fp, ip, lr, pc}
.word 0xe92d0000 >> 11 @ stmfd sp!, {}
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 95bd35991288..f069d1b2318e 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -28,7 +28,7 @@ UNWIND( .fnend )
ENDPROC(\name )
.endm
- .macro testop, name, instr, store
+ .macro __testop, name, instr, store, barrier
ENTRY( \name )
UNWIND( .fnstart )
ands ip, r1, #3
@@ -38,7 +38,7 @@ UNWIND( .fnstart )
mov r0, r0, lsr #5
add r1, r1, r0, lsl #2 @ Get word offset
mov r3, r2, lsl r3 @ create mask
- smp_dmb
+ \barrier
#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
.arch_extension mp
ALT_SMP(W(pldw) [r1])
@@ -50,13 +50,21 @@ UNWIND( .fnstart )
strex ip, r2, [r1]
cmp ip, #0
bne 1b
- smp_dmb
+ \barrier
cmp r0, #0
movne r0, #1
2: bx lr
UNWIND( .fnend )
ENDPROC(\name )
.endm
+
+ .macro testop, name, instr, store
+ __testop \name, \instr, \store, smp_dmb
+ .endm
+
+ .macro sync_testop, name, instr, store
+ __testop \name, \instr, \store, __smp_dmb
+ .endm
#else
.macro bitop, name, instr
ENTRY( \name )
diff --git a/arch/arm/lib/call_with_stack.S b/arch/arm/lib/call_with_stack.S
index 28b0341ae786..5030d4e8d126 100644
--- a/arch/arm/lib/call_with_stack.S
+++ b/arch/arm/lib/call_with_stack.S
@@ -8,25 +8,44 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/unwind.h>
/*
* void call_with_stack(void (*fn)(void *), void *arg, void *sp)
*
* Change the stack to that pointed at by sp, then invoke fn(arg) with
* the new stack.
+ *
+ * The sequence below follows the APCS frame convention for frame pointer
+ * unwinding, and implements the unwinder annotations needed by the EABI
+ * unwinder.
*/
-ENTRY(call_with_stack)
- str sp, [r2, #-4]!
- str lr, [r2, #-4]!
+ENTRY(call_with_stack)
+#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC)
+ mov ip, sp
+ push {fp, ip, lr, pc}
+ sub fp, ip, #4
+#else
+UNWIND( .fnstart )
+UNWIND( .save {fpreg, lr} )
+ push {fpreg, lr}
+UNWIND( .setfp fpreg, sp )
+ mov fpreg, sp
+#endif
mov sp, r2
mov r2, r0
mov r0, r1
- badr lr, 1f
- ret r2
+ bl_r r2
-1: ldr lr, [sp]
- ldr sp, [sp, #4]
- ret lr
+#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC)
+ ldmdb fp, {fp, sp, pc}
+#else
+ mov sp, fpreg
+ pop {fpreg, pc}
+UNWIND( .fnend )
+#endif
+ .globl call_with_stack_end
+call_with_stack_end:
ENDPROC(call_with_stack)
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 95b2e1ce559c..270de7debd0f 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -91,26 +91,22 @@
strb\cond \reg, [\ptr], #1
.endm
- .macro enter reg1 reg2
+ .macro enter regs:vararg
mov r3, #0
- stmdb sp!, {r0, r2, r3, \reg1, \reg2}
+UNWIND( .save {r0, r2, r3, \regs} )
+ stmdb sp!, {r0, r2, r3, \regs}
.endm
- .macro usave reg1 reg2
- UNWIND( .save {r0, r2, r3, \reg1, \reg2} )
- .endm
-
- .macro exit reg1 reg2
+ .macro exit regs:vararg
add sp, sp, #8
- ldmfd sp!, {r0, \reg1, \reg2}
+ ldmfd sp!, {r0, \regs}
.endm
.text
ENTRY(arm_copy_from_user)
#ifdef CONFIG_CPU_SPECTRE
- get_thread_info r3
- ldr r3, [r3, #TI_ADDR_LIMIT]
+ ldr r3, =TASK_SIZE
uaccess_mask_range_ptr r1, r2, r3, ip
#endif
@@ -118,7 +114,7 @@ ENTRY(arm_copy_from_user)
ENDPROC(arm_copy_from_user)
- .pushsection .fixup,"ax"
+ .pushsection .text.fixup,"ax"
.align 0
copy_abort_preamble
ldmfd sp!, {r1, r2, r3}
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 810a805d36dc..8fbafb074fe9 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -69,13 +69,10 @@
* than one 32bit instruction in Thumb-2)
*/
-
- UNWIND( .fnstart )
- enter r4, lr
- UNWIND( .fnend )
-
UNWIND( .fnstart )
- usave r4, lr @ in first stmdb block
+ enter r4, UNWIND(fpreg,) lr
+ UNWIND( .setfp fpreg, sp )
+ UNWIND( mov fpreg, sp )
subs r2, r2, #4
blt 8f
@@ -86,12 +83,7 @@
bne 10f
1: subs r2, r2, #(28)
- stmfd sp!, {r5 - r8}
- UNWIND( .fnend )
-
- UNWIND( .fnstart )
- usave r4, lr
- UNWIND( .save {r5 - r8} ) @ in second stmfd block
+ stmfd sp!, {r5, r6, r8, r9}
blt 5f
CALGN( ands ip, r0, #31 )
@@ -110,9 +102,9 @@
PLD( pld [r1, #92] )
3: PLD( pld [r1, #124] )
-4: ldr8w r1, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
+4: ldr8w r1, r3, r4, r5, r6, r8, r9, ip, lr, abort=20f
subs r2, r2, #32
- str8w r0, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
+ str8w r0, r3, r4, r5, r6, r8, r9, ip, lr, abort=20f
bge 3b
PLD( cmn r2, #96 )
PLD( bge 4b )
@@ -132,8 +124,8 @@
ldr1w r1, r4, abort=20f
ldr1w r1, r5, abort=20f
ldr1w r1, r6, abort=20f
- ldr1w r1, r7, abort=20f
ldr1w r1, r8, abort=20f
+ ldr1w r1, r9, abort=20f
ldr1w r1, lr, abort=20f
#if LDR1W_SHIFT < STR1W_SHIFT
@@ -150,17 +142,14 @@
str1w r0, r4, abort=20f
str1w r0, r5, abort=20f
str1w r0, r6, abort=20f
- str1w r0, r7, abort=20f
str1w r0, r8, abort=20f
+ str1w r0, r9, abort=20f
str1w r0, lr, abort=20f
CALGN( bcs 2b )
-7: ldmfd sp!, {r5 - r8}
- UNWIND( .fnend ) @ end of second stmfd block
+7: ldmfd sp!, {r5, r6, r8, r9}
- UNWIND( .fnstart )
- usave r4, lr @ still in first stmdb block
8: movs r2, r2, lsl #31
ldr1b r1, r3, ne, abort=21f
ldr1b r1, r4, cs, abort=21f
@@ -169,7 +158,7 @@
str1b r0, r4, cs, abort=21f
str1b r0, ip, cs, abort=21f
- exit r4, pc
+ exit r4, UNWIND(fpreg,) pc
9: rsb ip, ip, #4
cmp ip, #2
@@ -189,13 +178,10 @@
ldr1w r1, lr, abort=21f
beq 17f
bgt 18f
- UNWIND( .fnend )
.macro forward_copy_shift pull push
- UNWIND( .fnstart )
- usave r4, lr @ still in first stmdb block
subs r2, r2, #28
blt 14f
@@ -205,12 +191,8 @@
CALGN( subcc r2, r2, ip )
CALGN( bcc 15f )
-11: stmfd sp!, {r5 - r9}
- UNWIND( .fnend )
+11: stmfd sp!, {r5, r6, r8 - r10}
- UNWIND( .fnstart )
- usave r4, lr
- UNWIND( .save {r5 - r9} ) @ in new second stmfd block
PLD( pld [r1, #0] )
PLD( subs r2, r2, #96 )
PLD( pld [r1, #28] )
@@ -219,35 +201,32 @@
PLD( pld [r1, #92] )
12: PLD( pld [r1, #124] )
-13: ldr4w r1, r4, r5, r6, r7, abort=19f
+13: ldr4w r1, r4, r5, r6, r8, abort=19f
mov r3, lr, lspull #\pull
subs r2, r2, #32
- ldr4w r1, r8, r9, ip, lr, abort=19f
+ ldr4w r1, r9, r10, ip, lr, abort=19f
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
+ orr r6, r6, 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
+ orr r9, r9, r10, lspush #\push
+ mov r10, r10, lspull #\pull
+ orr r10, r10, 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
+ str8w r0, r3, r4, r5, r6, r8, r9, r10, ip, abort=19f
bge 12b
PLD( cmn r2, #96 )
PLD( bge 13b )
- ldmfd sp!, {r5 - r9}
- UNWIND( .fnend ) @ end of the second stmfd block
+ ldmfd sp!, {r5, r6, r8 - r10}
- UNWIND( .fnstart )
- usave r4, lr @ still in first stmdb block
14: ands ip, r2, #28
beq 16f
@@ -262,7 +241,6 @@
16: sub r1, r1, #(\push / 8)
b 8b
- UNWIND( .fnend )
.endm
@@ -273,6 +251,7 @@
18: forward_copy_shift pull=24 push=8
+ UNWIND( .fnend )
/*
* Abort preamble and completion macros.
@@ -282,13 +261,13 @@
*/
.macro copy_abort_preamble
-19: ldmfd sp!, {r5 - r9}
+19: ldmfd sp!, {r5, r6, r8 - r10}
b 21f
-20: ldmfd sp!, {r5 - r8}
+20: ldmfd sp!, {r5, r6, r8, r9}
21:
.endm
.macro copy_abort_end
- ldmfd sp!, {r4, pc}
+ ldmfd sp!, {r4, UNWIND(fpreg,) pc}
.endm
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index ebfe4cb3d912..fac49e57cc0b 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -90,18 +90,15 @@
strusr \reg, \ptr, 1, \cond, abort=\abort
.endm
- .macro enter reg1 reg2
+ .macro enter regs:vararg
mov r3, #0
- stmdb sp!, {r0, r2, r3, \reg1, \reg2}
+UNWIND( .save {r0, r2, r3, \regs} )
+ stmdb sp!, {r0, r2, r3, \regs}
.endm
- .macro usave reg1 reg2
- UNWIND( .save {r0, r2, r3, \reg1, \reg2} )
- .endm
-
- .macro exit reg1 reg2
+ .macro exit regs:vararg
add sp, sp, #8
- ldmfd sp!, {r0, \reg1, \reg2}
+ ldmfd sp!, {r0, \regs}
.endm
.text
@@ -109,8 +106,7 @@
ENTRY(__copy_to_user_std)
WEAK(arm_copy_to_user)
#ifdef CONFIG_CPU_SPECTRE
- get_thread_info r3
- ldr r3, [r3, #TI_ADDR_LIMIT]
+ ldr r3, =TASK_SIZE
uaccess_mask_range_ptr r0, r2, r3, ip
#endif
diff --git a/arch/arm/lib/crc-t10dif-core.S b/arch/arm/lib/crc-t10dif-core.S
new file mode 100644
index 000000000000..2bbf2df9c1e2
--- /dev/null
+++ b/arch/arm/lib/crc-t10dif-core.S
@@ -0,0 +1,468 @@
+//
+// Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions
+//
+// Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+// Copyright (C) 2019 Google LLC <ebiggers@google.com>
+//
+// 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.
+//
+
+// Derived from the x86 version:
+//
+// Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
+//
+// Copyright (c) 2013, Intel Corporation
+//
+// Authors:
+// Erdinc Ozturk <erdinc.ozturk@intel.com>
+// Vinodh Gopal <vinodh.gopal@intel.com>
+// James Guilford <james.guilford@intel.com>
+// Tim Chen <tim.c.chen@linux.intel.com>
+//
+// This software is available to you under a choice of one of two
+// licenses. You may choose to be licensed under the terms of the GNU
+// General Public License (GPL) Version 2, available from the file
+// COPYING in the main directory of this source tree, or the
+// OpenIB.org BSD license below:
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+// * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//
+// * Redistributions in binary form must reproduce the above copyright
+// notice, this list of conditions and the following disclaimer in the
+// documentation and/or other materials provided with the
+// distribution.
+//
+// * Neither the name of the Intel Corporation nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+//
+// THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
+// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
+// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+// LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+// Reference paper titled "Fast CRC Computation for Generic
+// Polynomials Using PCLMULQDQ Instruction"
+// URL: http://www.intel.com/content/dam/www/public/us/en/documents
+// /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
+//
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define CPU_LE(code...)
+#else
+#define CPU_LE(code...) code
+#endif
+
+ .text
+ .arch armv8-a
+ .fpu crypto-neon-fp-armv8
+
+ init_crc .req r0
+ buf .req r1
+ len .req r2
+
+ fold_consts_ptr .req ip
+
+ q0l .req d0
+ q0h .req d1
+ q1l .req d2
+ q1h .req d3
+ q2l .req d4
+ q2h .req d5
+ q3l .req d6
+ q3h .req d7
+ q4l .req d8
+ q4h .req d9
+ q5l .req d10
+ q5h .req d11
+ q6l .req d12
+ q6h .req d13
+ q7l .req d14
+ q7h .req d15
+ q8l .req d16
+ q8h .req d17
+ q9l .req d18
+ q9h .req d19
+ q10l .req d20
+ q10h .req d21
+ q11l .req d22
+ q11h .req d23
+ q12l .req d24
+ q12h .req d25
+
+ FOLD_CONSTS .req q10
+ FOLD_CONST_L .req q10l
+ FOLD_CONST_H .req q10h
+
+ /*
+ * Pairwise long polynomial multiplication of two 16-bit values
+ *
+ * { w0, w1 }, { y0, y1 }
+ *
+ * by two 64-bit values
+ *
+ * { x0, x1, x2, x3, x4, x5, x6, x7 }, { z0, z1, z2, z3, z4, z5, z6, z7 }
+ *
+ * where each vector element is a byte, ordered from least to most
+ * significant. The resulting 80-bit vectors are XOR'ed together.
+ *
+ * This can be implemented using 8x8 long polynomial multiplication, by
+ * reorganizing the input so that each pairwise 8x8 multiplication
+ * produces one of the terms from the decomposition below, and
+ * combining the results of each rank and shifting them into place.
+ *
+ * Rank
+ * 0 w0*x0 ^ | y0*z0 ^
+ * 1 (w0*x1 ^ w1*x0) << 8 ^ | (y0*z1 ^ y1*z0) << 8 ^
+ * 2 (w0*x2 ^ w1*x1) << 16 ^ | (y0*z2 ^ y1*z1) << 16 ^
+ * 3 (w0*x3 ^ w1*x2) << 24 ^ | (y0*z3 ^ y1*z2) << 24 ^
+ * 4 (w0*x4 ^ w1*x3) << 32 ^ | (y0*z4 ^ y1*z3) << 32 ^
+ * 5 (w0*x5 ^ w1*x4) << 40 ^ | (y0*z5 ^ y1*z4) << 40 ^
+ * 6 (w0*x6 ^ w1*x5) << 48 ^ | (y0*z6 ^ y1*z5) << 48 ^
+ * 7 (w0*x7 ^ w1*x6) << 56 ^ | (y0*z7 ^ y1*z6) << 56 ^
+ * 8 w1*x7 << 64 | y1*z7 << 64
+ *
+ * The inputs can be reorganized into
+ *
+ * { w0, w0, w0, w0, y0, y0, y0, y0 }, { w1, w1, w1, w1, y1, y1, y1, y1 }
+ * { x0, x2, x4, x6, z0, z2, z4, z6 }, { x1, x3, x5, x7, z1, z3, z5, z7 }
+ *
+ * and after performing 8x8->16 bit long polynomial multiplication of
+ * each of the halves of the first vector with those of the second one,
+ * we obtain the following four vectors of 16-bit elements:
+ *
+ * a := { w0*x0, w0*x2, w0*x4, w0*x6 }, { y0*z0, y0*z2, y0*z4, y0*z6 }
+ * b := { w0*x1, w0*x3, w0*x5, w0*x7 }, { y0*z1, y0*z3, y0*z5, y0*z7 }
+ * c := { w1*x0, w1*x2, w1*x4, w1*x6 }, { y1*z0, y1*z2, y1*z4, y1*z6 }
+ * d := { w1*x1, w1*x3, w1*x5, w1*x7 }, { y1*z1, y1*z3, y1*z5, y1*z7 }
+ *
+ * Results b and c can be XORed together, as the vector elements have
+ * matching ranks. Then, the final XOR can be pulled forward, and
+ * applied between the halves of each of the remaining three vectors,
+ * which are then shifted into place, and XORed together to produce the
+ * final 80-bit result.
+ */
+ .macro pmull16x64_p8, v16, v64
+ vext.8 q11, \v64, \v64, #1
+ vld1.64 {q12}, [r4, :128]
+ vuzp.8 q11, \v64
+ vtbl.8 d24, {\v16\()_L-\v16\()_H}, d24
+ vtbl.8 d25, {\v16\()_L-\v16\()_H}, d25
+ bl __pmull16x64_p8
+ veor \v64, q12, q14
+ .endm
+
+__pmull16x64_p8:
+ vmull.p8 q13, d23, d24
+ vmull.p8 q14, d23, d25
+ vmull.p8 q15, d22, d24
+ vmull.p8 q12, d22, d25
+
+ veor q14, q14, q15
+ veor d24, d24, d25
+ veor d26, d26, d27
+ veor d28, d28, d29
+ vmov.i32 d25, #0
+ vmov.i32 d29, #0
+ vext.8 q12, q12, q12, #14
+ vext.8 q14, q14, q14, #15
+ veor d24, d24, d26
+ bx lr
+ENDPROC(__pmull16x64_p8)
+
+ .macro pmull16x64_p64, v16, v64
+ vmull.p64 q11, \v64\()l, \v16\()_L
+ vmull.p64 \v64, \v64\()h, \v16\()_H
+ veor \v64, \v64, q11
+ .endm
+
+ // Fold reg1, reg2 into the next 32 data bytes, storing the result back
+ // into reg1, reg2.
+ .macro fold_32_bytes, reg1, reg2, p
+ vld1.64 {q8-q9}, [buf]!
+
+ pmull16x64_\p FOLD_CONST, \reg1
+ pmull16x64_\p FOLD_CONST, \reg2
+
+CPU_LE( vrev64.8 q8, q8 )
+CPU_LE( vrev64.8 q9, q9 )
+ vswp q8l, q8h
+ vswp q9l, q9h
+
+ veor.8 \reg1, \reg1, q8
+ veor.8 \reg2, \reg2, q9
+ .endm
+
+ // Fold src_reg into dst_reg, optionally loading the next fold constants
+ .macro fold_16_bytes, src_reg, dst_reg, p, load_next_consts
+ pmull16x64_\p FOLD_CONST, \src_reg
+ .ifnb \load_next_consts
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+ .endif
+ veor.8 \dst_reg, \dst_reg, \src_reg
+ .endm
+
+ .macro crct10dif, p
+ // For sizes less than 256 bytes, we can't fold 128 bytes at a time.
+ cmp len, #256
+ blt .Lless_than_256_bytes\@
+
+ mov_l fold_consts_ptr, .Lfold_across_128_bytes_consts
+
+ // Load the first 128 data bytes. Byte swapping is necessary to make
+ // the bit order match the polynomial coefficient order.
+ vld1.64 {q0-q1}, [buf]!
+ vld1.64 {q2-q3}, [buf]!
+ vld1.64 {q4-q5}, [buf]!
+ vld1.64 {q6-q7}, [buf]!
+CPU_LE( vrev64.8 q0, q0 )
+CPU_LE( vrev64.8 q1, q1 )
+CPU_LE( vrev64.8 q2, q2 )
+CPU_LE( vrev64.8 q3, q3 )
+CPU_LE( vrev64.8 q4, q4 )
+CPU_LE( vrev64.8 q5, q5 )
+CPU_LE( vrev64.8 q6, q6 )
+CPU_LE( vrev64.8 q7, q7 )
+ vswp q0l, q0h
+ vswp q1l, q1h
+ vswp q2l, q2h
+ vswp q3l, q3h
+ vswp q4l, q4h
+ vswp q5l, q5h
+ vswp q6l, q6h
+ vswp q7l, q7h
+
+ // XOR the first 16 data *bits* with the initial CRC value.
+ vmov.i8 q8h, #0
+ vmov.u16 q8h[3], init_crc
+ veor q0h, q0h, q8h
+
+ // Load the constants for folding across 128 bytes.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+
+ // Subtract 128 for the 128 data bytes just consumed. Subtract another
+ // 128 to simplify the termination condition of the following loop.
+ sub len, len, #256
+
+ // While >= 128 data bytes remain (not counting q0-q7), fold the 128
+ // bytes q0-q7 into them, storing the result back into q0-q7.
+.Lfold_128_bytes_loop\@:
+ fold_32_bytes q0, q1, \p
+ fold_32_bytes q2, q3, \p
+ fold_32_bytes q4, q5, \p
+ fold_32_bytes q6, q7, \p
+ subs len, len, #128
+ bge .Lfold_128_bytes_loop\@
+
+ // Now fold the 112 bytes in q0-q6 into the 16 bytes in q7.
+
+ // Fold across 64 bytes.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+ fold_16_bytes q0, q4, \p
+ fold_16_bytes q1, q5, \p
+ fold_16_bytes q2, q6, \p
+ fold_16_bytes q3, q7, \p, 1
+ // Fold across 32 bytes.
+ fold_16_bytes q4, q6, \p
+ fold_16_bytes q5, q7, \p, 1
+ // Fold across 16 bytes.
+ fold_16_bytes q6, q7, \p
+
+ // Add 128 to get the correct number of data bytes remaining in 0...127
+ // (not counting q7), following the previous extra subtraction by 128.
+ // Then subtract 16 to simplify the termination condition of the
+ // following loop.
+ adds len, len, #(128-16)
+
+ // While >= 16 data bytes remain (not counting q7), fold the 16 bytes q7
+ // into them, storing the result back into q7.
+ blt .Lfold_16_bytes_loop_done\@
+.Lfold_16_bytes_loop\@:
+ pmull16x64_\p FOLD_CONST, q7
+ vld1.64 {q0}, [buf]!
+CPU_LE( vrev64.8 q0, q0 )
+ vswp q0l, q0h
+ veor.8 q7, q7, q0
+ subs len, len, #16
+ bge .Lfold_16_bytes_loop\@
+
+.Lfold_16_bytes_loop_done\@:
+ // Add 16 to get the correct number of data bytes remaining in 0...15
+ // (not counting q7), following the previous extra subtraction by 16.
+ adds len, len, #16
+ beq .Lreduce_final_16_bytes\@
+
+.Lhandle_partial_segment\@:
+ // Reduce the last '16 + len' bytes where 1 <= len <= 15 and the first
+ // 16 bytes are in q7 and the rest are the remaining data in 'buf'. To
+ // do this without needing a fold constant for each possible 'len',
+ // redivide the bytes into a first chunk of 'len' bytes and a second
+ // chunk of 16 bytes, then fold the first chunk into the second.
+
+ // q0 = last 16 original data bytes
+ add buf, buf, len
+ sub buf, buf, #16
+ vld1.64 {q0}, [buf]
+CPU_LE( vrev64.8 q0, q0 )
+ vswp q0l, q0h
+
+ // q1 = high order part of second chunk: q7 left-shifted by 'len' bytes.
+ mov_l r1, .Lbyteshift_table + 16
+ sub r1, r1, len
+ vld1.8 {q2}, [r1]
+ vtbl.8 q1l, {q7l-q7h}, q2l
+ vtbl.8 q1h, {q7l-q7h}, q2h
+
+ // q3 = first chunk: q7 right-shifted by '16-len' bytes.
+ vmov.i8 q3, #0x80
+ veor.8 q2, q2, q3
+ vtbl.8 q3l, {q7l-q7h}, q2l
+ vtbl.8 q3h, {q7l-q7h}, q2h
+
+ // Convert to 8-bit masks: 'len' 0x00 bytes, then '16-len' 0xff bytes.
+ vshr.s8 q2, q2, #7
+
+ // q2 = second chunk: 'len' bytes from q0 (low-order bytes),
+ // then '16-len' bytes from q1 (high-order bytes).
+ vbsl.8 q2, q1, q0
+
+ // Fold the first chunk into the second chunk, storing the result in q7.
+ pmull16x64_\p FOLD_CONST, q3
+ veor.8 q7, q3, q2
+ b .Lreduce_final_16_bytes\@
+
+.Lless_than_256_bytes\@:
+ // Checksumming a buffer of length 16...255 bytes
+
+ mov_l fold_consts_ptr, .Lfold_across_16_bytes_consts
+
+ // Load the first 16 data bytes.
+ vld1.64 {q7}, [buf]!
+CPU_LE( vrev64.8 q7, q7 )
+ vswp q7l, q7h
+
+ // XOR the first 16 data *bits* with the initial CRC value.
+ vmov.i8 q0h, #0
+ vmov.u16 q0h[3], init_crc
+ veor.8 q7h, q7h, q0h
+
+ // Load the fold-across-16-bytes constants.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+
+ cmp len, #16
+ beq .Lreduce_final_16_bytes\@ // len == 16
+ subs len, len, #32
+ addlt len, len, #16
+ blt .Lhandle_partial_segment\@ // 17 <= len <= 31
+ b .Lfold_16_bytes_loop\@ // 32 <= len <= 255
+
+.Lreduce_final_16_bytes\@:
+ .endm
+
+//
+// u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
+//
+// Assumes len >= 16.
+//
+ENTRY(crc_t10dif_pmull64)
+ crct10dif p64
+
+ // Reduce the 128-bit value M(x), stored in q7, to the final 16-bit CRC.
+
+ // Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+
+ // Fold the high 64 bits into the low 64 bits, while also multiplying by
+ // x^64. This produces a 128-bit value congruent to x^64 * M(x) and
+ // whose low 48 bits are 0.
+ vmull.p64 q0, q7h, FOLD_CONST_H // high bits * x^48 * (x^80 mod G(x))
+ veor.8 q0h, q0h, q7l // + low bits * x^64
+
+ // Fold the high 32 bits into the low 96 bits. This produces a 96-bit
+ // value congruent to x^64 * M(x) and whose low 48 bits are 0.
+ vmov.i8 q1, #0
+ vmov s4, s3 // extract high 32 bits
+ vmov s3, s5 // zero high 32 bits
+ vmull.p64 q1, q1l, FOLD_CONST_L // high 32 bits * x^48 * (x^48 mod G(x))
+ veor.8 q0, q0, q1 // + low bits
+
+ // Load G(x) and floor(x^48 / G(x)).
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]
+
+ // Use Barrett reduction to compute the final CRC value.
+ vmull.p64 q1, q0h, FOLD_CONST_H // high 32 bits * floor(x^48 / G(x))
+ vshr.u64 q1l, q1l, #32 // /= x^32
+ vmull.p64 q1, q1l, FOLD_CONST_L // *= G(x)
+ vshr.u64 q0l, q0l, #48
+ veor.8 q0l, q0l, q1l // + low 16 nonzero bits
+ // Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of q0.
+
+ vmov.u16 r0, q0l[0]
+ bx lr
+ENDPROC(crc_t10dif_pmull64)
+
+ENTRY(crc_t10dif_pmull8)
+ push {r4, lr}
+ mov_l r4, .L16x64perm
+
+ crct10dif p8
+
+CPU_LE( vrev64.8 q7, q7 )
+ vswp q7l, q7h
+ vst1.64 {q7}, [r3, :128]
+ pop {r4, pc}
+ENDPROC(crc_t10dif_pmull8)
+
+ .section ".rodata", "a"
+ .align 4
+
+// Fold constants precomputed from the polynomial 0x18bb7
+// G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+.Lfold_across_128_bytes_consts:
+ .quad 0x0000000000006123 // x^(8*128) mod G(x)
+ .quad 0x0000000000002295 // x^(8*128+64) mod G(x)
+// .Lfold_across_64_bytes_consts:
+ .quad 0x0000000000001069 // x^(4*128) mod G(x)
+ .quad 0x000000000000dd31 // x^(4*128+64) mod G(x)
+// .Lfold_across_32_bytes_consts:
+ .quad 0x000000000000857d // x^(2*128) mod G(x)
+ .quad 0x0000000000007acc // x^(2*128+64) mod G(x)
+.Lfold_across_16_bytes_consts:
+ .quad 0x000000000000a010 // x^(1*128) mod G(x)
+ .quad 0x0000000000001faa // x^(1*128+64) mod G(x)
+// .Lfinal_fold_consts:
+ .quad 0x1368000000000000 // x^48 * (x^48 mod G(x))
+ .quad 0x2d56000000000000 // x^48 * (x^80 mod G(x))
+// .Lbarrett_reduction_consts:
+ .quad 0x0000000000018bb7 // G(x)
+ .quad 0x00000001f65a57f8 // floor(x^48 / G(x))
+
+// For 1 <= len <= 15, the 16-byte vector beginning at &byteshift_table[16 -
+// len] is the index vector to shift left by 'len' bytes, and is also {0x80,
+// ..., 0x80} XOR the index vector to shift right by '16 - len' bytes.
+.Lbyteshift_table:
+ .byte 0x0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87
+ .byte 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f
+ .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
+ .byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe , 0x0
+
+.L16x64perm:
+ .quad 0x808080800000000, 0x909090901010101
diff --git a/arch/arm/lib/crc-t10dif-glue.c b/arch/arm/lib/crc-t10dif-glue.c
new file mode 100644
index 000000000000..6efad3d78284
--- /dev/null
+++ b/arch/arm/lib/crc-t10dif-glue.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/crc-t10dif.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/simd.h>
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+static DEFINE_STATIC_KEY_FALSE(have_neon);
+static DEFINE_STATIC_KEY_FALSE(have_pmull);
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
+
+asmlinkage u16 crc_t10dif_pmull64(u16 init_crc, const u8 *buf, size_t len);
+asmlinkage void crc_t10dif_pmull8(u16 init_crc, const u8 *buf, size_t len,
+ u8 out[16]);
+
+u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
+{
+ if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) {
+ if (static_branch_likely(&have_pmull)) {
+ if (crypto_simd_usable()) {
+ kernel_neon_begin();
+ crc = crc_t10dif_pmull64(crc, data, length);
+ kernel_neon_end();
+ return crc;
+ }
+ } else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE &&
+ static_branch_likely(&have_neon) &&
+ crypto_simd_usable()) {
+ u8 buf[16] __aligned(16);
+
+ kernel_neon_begin();
+ crc_t10dif_pmull8(crc, data, length, buf);
+ kernel_neon_end();
+
+ return crc_t10dif_generic(0, buf, sizeof(buf));
+ }
+ }
+ return crc_t10dif_generic(crc, data, length);
+}
+EXPORT_SYMBOL(crc_t10dif_arch);
+
+static int __init crc_t10dif_arm_init(void)
+{
+ if (elf_hwcap & HWCAP_NEON) {
+ static_branch_enable(&have_neon);
+ if (elf_hwcap2 & HWCAP2_PMULL)
+ static_branch_enable(&have_pmull);
+ }
+ return 0;
+}
+arch_initcall(crc_t10dif_arm_init);
+
+static void __exit crc_t10dif_arm_exit(void)
+{
+}
+module_exit(crc_t10dif_arm_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_DESCRIPTION("Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/lib/crc32-core.S b/arch/arm/lib/crc32-core.S
new file mode 100644
index 000000000000..6f674f30c70b
--- /dev/null
+++ b/arch/arm/lib/crc32-core.S
@@ -0,0 +1,306 @@
+/*
+ * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 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.
+ */
+
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * 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 version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Using hardware provided PCLMULQDQ instruction to accelerate the CRC32
+ * calculation.
+ * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
+ * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
+ * at:
+ * https://www.intel.com/products/processor/manuals/
+ * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
+ * Volume 2B: Instruction Set Reference, N-Z
+ *
+ * Authors: Gregory Prestas <Gregory_Prestas@us.xyratex.com>
+ * Alexander Boyko <Alexander_Boyko@xyratex.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .align 6
+ .arch armv8-a
+ .arch_extension crc
+ .fpu crypto-neon-fp-armv8
+
+.Lcrc32_constants:
+ /*
+ * [x4*128+32 mod P(x) << 32)]' << 1 = 0x154442bd4
+ * #define CONSTANT_R1 0x154442bd4LL
+ *
+ * [(x4*128-32 mod P(x) << 32)]' << 1 = 0x1c6e41596
+ * #define CONSTANT_R2 0x1c6e41596LL
+ */
+ .quad 0x0000000154442bd4
+ .quad 0x00000001c6e41596
+
+ /*
+ * [(x128+32 mod P(x) << 32)]' << 1 = 0x1751997d0
+ * #define CONSTANT_R3 0x1751997d0LL
+ *
+ * [(x128-32 mod P(x) << 32)]' << 1 = 0x0ccaa009e
+ * #define CONSTANT_R4 0x0ccaa009eLL
+ */
+ .quad 0x00000001751997d0
+ .quad 0x00000000ccaa009e
+
+ /*
+ * [(x64 mod P(x) << 32)]' << 1 = 0x163cd6124
+ * #define CONSTANT_R5 0x163cd6124LL
+ */
+ .quad 0x0000000163cd6124
+ .quad 0x00000000FFFFFFFF
+
+ /*
+ * #define CRCPOLY_TRUE_LE_FULL 0x1DB710641LL
+ *
+ * Barrett Reduction constant (u64`) = u` = (x**64 / P(x))`
+ * = 0x1F7011641LL
+ * #define CONSTANT_RU 0x1F7011641LL
+ */
+ .quad 0x00000001DB710641
+ .quad 0x00000001F7011641
+
+.Lcrc32c_constants:
+ .quad 0x00000000740eef02
+ .quad 0x000000009e4addf8
+ .quad 0x00000000f20c0dfe
+ .quad 0x000000014cd00bd6
+ .quad 0x00000000dd45aab8
+ .quad 0x00000000FFFFFFFF
+ .quad 0x0000000105ec76f0
+ .quad 0x00000000dea713f1
+
+ dCONSTANTl .req d0
+ dCONSTANTh .req d1
+ qCONSTANT .req q0
+
+ BUF .req r0
+ LEN .req r1
+ CRC .req r2
+
+ qzr .req q9
+
+ /**
+ * Calculate crc32
+ * BUF - buffer
+ * LEN - sizeof buffer (multiple of 16 bytes), LEN should be > 63
+ * CRC - initial crc32
+ * return %eax crc32
+ * uint crc32_pmull_le(unsigned char const *buffer,
+ * size_t len, uint crc32)
+ */
+SYM_FUNC_START(crc32_pmull_le)
+ adr r3, .Lcrc32_constants
+ b 0f
+SYM_FUNC_END(crc32_pmull_le)
+
+SYM_FUNC_START(crc32c_pmull_le)
+ adr r3, .Lcrc32c_constants
+
+0: bic LEN, LEN, #15
+ vld1.8 {q1-q2}, [BUF, :128]!
+ vld1.8 {q3-q4}, [BUF, :128]!
+ vmov.i8 qzr, #0
+ vmov.i8 qCONSTANT, #0
+ vmov.32 dCONSTANTl[0], CRC
+ veor.8 d2, d2, dCONSTANTl
+ sub LEN, LEN, #0x40
+ cmp LEN, #0x40
+ blt less_64
+
+ vld1.64 {qCONSTANT}, [r3]
+
+loop_64: /* 64 bytes Full cache line folding */
+ sub LEN, LEN, #0x40
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q6, d5, dCONSTANTh
+ vmull.p64 q7, d7, dCONSTANTh
+ vmull.p64 q8, d9, dCONSTANTh
+
+ vmull.p64 q1, d2, dCONSTANTl
+ vmull.p64 q2, d4, dCONSTANTl
+ vmull.p64 q3, d6, dCONSTANTl
+ vmull.p64 q4, d8, dCONSTANTl
+
+ veor.8 q1, q1, q5
+ vld1.8 {q5}, [BUF, :128]!
+ veor.8 q2, q2, q6
+ vld1.8 {q6}, [BUF, :128]!
+ veor.8 q3, q3, q7
+ vld1.8 {q7}, [BUF, :128]!
+ veor.8 q4, q4, q8
+ vld1.8 {q8}, [BUF, :128]!
+
+ veor.8 q1, q1, q5
+ veor.8 q2, q2, q6
+ veor.8 q3, q3, q7
+ veor.8 q4, q4, q8
+
+ cmp LEN, #0x40
+ bge loop_64
+
+less_64: /* Folding cache line into 128bit */
+ vldr dCONSTANTl, [r3, #16]
+ vldr dCONSTANTh, [r3, #24]
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q2
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q3
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q4
+
+ teq LEN, #0
+ beq fold_64
+
+loop_16: /* Folding rest buffer into 128bit */
+ subs LEN, LEN, #0x10
+
+ vld1.8 {q2}, [BUF, :128]!
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q2
+
+ bne loop_16
+
+fold_64:
+ /* perform the last 64 bit fold, also adds 32 zeroes
+ * to the input stream */
+ vmull.p64 q2, d2, dCONSTANTh
+ vext.8 q1, q1, qzr, #8
+ veor.8 q1, q1, q2
+
+ /* final 32-bit fold */
+ vldr dCONSTANTl, [r3, #32]
+ vldr d6, [r3, #40]
+ vmov.i8 d7, #0
+
+ vext.8 q2, q1, qzr, #4
+ vand.8 d2, d2, d6
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q2
+
+ /* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
+ vldr dCONSTANTl, [r3, #48]
+ vldr dCONSTANTh, [r3, #56]
+
+ vand.8 q2, q1, q3
+ vext.8 q2, qzr, q2, #8
+ vmull.p64 q2, d5, dCONSTANTh
+ vand.8 q2, q2, q3
+ vmull.p64 q2, d4, dCONSTANTl
+ veor.8 q1, q1, q2
+ vmov r0, s5
+
+ bx lr
+SYM_FUNC_END(crc32c_pmull_le)
+
+ .macro __crc32, c
+ subs ip, r2, #8
+ bmi .Ltail\c
+
+ tst r1, #3
+ bne .Lunaligned\c
+
+ teq ip, #0
+.Laligned8\c:
+ ldrd r2, r3, [r1], #8
+ARM_BE8(rev r2, r2 )
+ARM_BE8(rev r3, r3 )
+ crc32\c\()w r0, r0, r2
+ crc32\c\()w r0, r0, r3
+ bxeq lr
+ subs ip, ip, #8
+ bpl .Laligned8\c
+
+.Ltail\c:
+ tst ip, #4
+ beq 2f
+ ldr r3, [r1], #4
+ARM_BE8(rev r3, r3 )
+ crc32\c\()w r0, r0, r3
+
+2: tst ip, #2
+ beq 1f
+ ldrh r3, [r1], #2
+ARM_BE8(rev16 r3, r3 )
+ crc32\c\()h r0, r0, r3
+
+1: tst ip, #1
+ bxeq lr
+ ldrb r3, [r1]
+ crc32\c\()b r0, r0, r3
+ bx lr
+
+.Lunaligned\c:
+ tst r1, #1
+ beq 2f
+ ldrb r3, [r1], #1
+ subs r2, r2, #1
+ crc32\c\()b r0, r0, r3
+
+ tst r1, #2
+ beq 0f
+2: ldrh r3, [r1], #2
+ subs r2, r2, #2
+ARM_BE8(rev16 r3, r3 )
+ crc32\c\()h r0, r0, r3
+
+0: subs ip, r2, #8
+ bpl .Laligned8\c
+ b .Ltail\c
+ .endm
+
+ .align 5
+SYM_FUNC_START(crc32_armv8_le)
+ __crc32
+SYM_FUNC_END(crc32_armv8_le)
+
+ .align 5
+SYM_FUNC_START(crc32c_armv8_le)
+ __crc32 c
+SYM_FUNC_END(crc32c_armv8_le)
diff --git a/arch/arm/lib/crc32-glue.c b/arch/arm/lib/crc32-glue.c
new file mode 100644
index 000000000000..4340351dbde8
--- /dev/null
+++ b/arch/arm/lib/crc32-glue.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/cpufeature.h>
+#include <linux/crc32.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/simd.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+static DEFINE_STATIC_KEY_FALSE(have_crc32);
+static DEFINE_STATIC_KEY_FALSE(have_pmull);
+
+#define PMULL_MIN_LEN 64 /* min size of buffer for pmull functions */
+
+asmlinkage u32 crc32_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+asmlinkage u32 crc32c_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+static u32 crc32_le_scalar(u32 crc, const u8 *p, size_t len)
+{
+ if (static_branch_likely(&have_crc32))
+ return crc32_armv8_le(crc, p, len);
+ return crc32_le_base(crc, p, len);
+}
+
+u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+ if (len >= PMULL_MIN_LEN + 15 &&
+ static_branch_likely(&have_pmull) && crypto_simd_usable()) {
+ size_t n = -(uintptr_t)p & 15;
+
+ /* align p to 16-byte boundary */
+ if (n) {
+ crc = crc32_le_scalar(crc, p, n);
+ p += n;
+ len -= n;
+ }
+ n = round_down(len, 16);
+ kernel_neon_begin();
+ crc = crc32_pmull_le(p, n, crc);
+ kernel_neon_end();
+ p += n;
+ len -= n;
+ }
+ return crc32_le_scalar(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_le_arch);
+
+static u32 crc32c_scalar(u32 crc, const u8 *p, size_t len)
+{
+ if (static_branch_likely(&have_crc32))
+ return crc32c_armv8_le(crc, p, len);
+ return crc32c_base(crc, p, len);
+}
+
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
+{
+ if (len >= PMULL_MIN_LEN + 15 &&
+ static_branch_likely(&have_pmull) && crypto_simd_usable()) {
+ size_t n = -(uintptr_t)p & 15;
+
+ /* align p to 16-byte boundary */
+ if (n) {
+ crc = crc32c_scalar(crc, p, n);
+ p += n;
+ len -= n;
+ }
+ n = round_down(len, 16);
+ kernel_neon_begin();
+ crc = crc32c_pmull_le(p, n, crc);
+ kernel_neon_end();
+ p += n;
+ len -= n;
+ }
+ return crc32c_scalar(crc, p, len);
+}
+EXPORT_SYMBOL(crc32c_arch);
+
+u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
+{
+ return crc32_be_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_be_arch);
+
+static int __init crc32_arm_init(void)
+{
+ if (elf_hwcap2 & HWCAP2_CRC32)
+ static_branch_enable(&have_crc32);
+ if (elf_hwcap2 & HWCAP2_PMULL)
+ static_branch_enable(&have_pmull);
+ return 0;
+}
+arch_initcall(crc32_arm_init);
+
+static void __exit crc32_arm_exit(void)
+{
+}
+module_exit(crc32_arm_exit);
+
+u32 crc32_optimizations(void)
+{
+ if (elf_hwcap2 & (HWCAP2_CRC32 | HWCAP2_PMULL))
+ return CRC32_LE_OPTIMIZATION | CRC32C_OPTIMIZATION;
+ return 0;
+}
+EXPORT_SYMBOL(crc32_optimizations);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_DESCRIPTION("Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S
index 184d97254a7a..1ca6aadd649c 100644
--- a/arch/arm/lib/csumpartialcopy.S
+++ b/arch/arm/lib/csumpartialcopy.S
@@ -9,8 +9,8 @@
.text
-/* Function: __u32 csum_partial_copy_nocheck(const char *src, char *dst, int len, __u32 sum)
- * Params : r0 = src, r1 = dst, r2 = len, r3 = checksum
+/* Function: __u32 csum_partial_copy_nocheck(const char *src, char *dst, int len)
+ * Params : r0 = src, r1 = dst, r2 = len
* Returns : r0 = new checksum
*/
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index 0b706a39a677..0fd5c10e90a7 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -86,6 +86,7 @@ sum .req r3
FN_ENTRY
save_regs
+ mov sum, #-1
cmp len, #8 @ Ensure that we have at least
blo .Lless8 @ 8 bytes to copy.
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 6bd3a93eaa3c..c289bde04743 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -13,7 +13,8 @@
.text
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+#if defined(CONFIG_CPU_SW_DOMAIN_PAN)
+
.macro save_regs
mrc p15, 0, ip, c3, c0, 0
stmfd sp!, {r1, r2, r4 - r8, ip, lr}
@@ -25,7 +26,23 @@
mcr p15, 0, ip, c3, c0, 0
ret lr
.endm
+
+#elif defined(CONFIG_CPU_TTBR0_PAN)
+
+ .macro save_regs
+ mrc p15, 0, ip, c2, c0, 2 @ read TTBCR
+ stmfd sp!, {r1, r2, r4 - r8, ip, lr}
+ uaccess_enable ip
+ .endm
+
+ .macro load_regs
+ ldmfd sp!, {r1, r2, r4 - r8, ip, lr}
+ mcr p15, 0, ip, c2, c0, 2 @ restore TTBCR
+ ret lr
+ .endm
+
#else
+
.macro save_regs
stmfd sp!, {r1, r2, r4 - r8, lr}
.endm
@@ -33,6 +50,7 @@
.macro load_regs
ldmfd sp!, {r1, r2, r4 - r8, pc}
.endm
+
#endif
.macro load1b, reg1
@@ -62,9 +80,9 @@
/*
* unsigned int
- * csum_partial_copy_from_user(const char *src, char *dst, int len, int sum, int *err_ptr)
- * r0 = src, r1 = dst, r2 = len, r3 = sum, [sp] = *err_ptr
- * Returns : r0 = checksum, [[sp, #0], #0] = 0 or -EFAULT
+ * csum_partial_copy_from_user(const char *src, char *dst, int len)
+ * r0 = src, r1 = dst, r2 = len
+ * Returns : r0 = checksum or 0
*/
#define FN_ENTRY ENTRY(csum_partial_copy_from_user)
@@ -73,25 +91,11 @@
#include "csumpartialcopygeneric.S"
/*
- * FIXME: minor buglet here
- * We don't return the checksum for the data present in the buffer. To do
- * so properly, we would have to add in whatever registers were loaded before
- * the fault, which, with the current asm above is not predictable.
+ * We report fault by returning 0 csum - impossible in normal case, since
+ * we start with 0xffffffff for initial sum.
*/
.pushsection .text.fixup,"ax"
.align 4
-9001: mov r4, #-EFAULT
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
- ldr r5, [sp, #9*4] @ *err_ptr
-#else
- ldr r5, [sp, #8*4] @ *err_ptr
-#endif
- str r4, [r5]
- ldmia sp, {r1, r2} @ retrieve dst, len
- add r2, r2, r1
- mov r0, #0 @ zero the buffer
-9002: teq r2, r1
- strbne r0, [r1], #1
- bne 9002b
+9001: mov r0, #0
load_regs
.popsection
diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
index 3ccade0f8130..33b08ca1c242 100644
--- a/arch/arm/lib/delay-loop.S
+++ b/arch/arm/lib/delay-loop.S
@@ -5,9 +5,14 @@
* Copyright (C) 1995, 1996 Russell King
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include <asm/delay.h>
+#ifdef CONFIG_ARCH_RPC
+ .arch armv4
+#endif
+
.text
.LC0: .word loops_per_jiffy
@@ -20,21 +25,26 @@
* HZ <= 1000
*/
-ENTRY(__loop_udelay)
+SYM_TYPED_FUNC_START(__loop_udelay)
ldr r2, .LC1
mul r0, r2, r0 @ r0 = delay_us * UDELAY_MULT
-ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0xfffffaf0
+ b __loop_const_udelay
+SYM_FUNC_END(__loop_udelay)
+
+SYM_TYPED_FUNC_START(__loop_const_udelay) @ 0 <= r0 <= 0xfffffaf0
ldr r2, .LC0
ldr r2, [r2]
umull r1, r0, r2, r0 @ r0-r1 = r0 * loops_per_jiffy
adds r1, r1, #0xffffffff @ rounding up ...
adcs r0, r0, r0 @ and right shift by 31
reteq lr
+ b __loop_delay
+SYM_FUNC_END(__loop_const_udelay)
.align 3
@ Delay routine
-ENTRY(__loop_delay)
+SYM_TYPED_FUNC_START(__loop_delay)
subs r0, r0, #1
#if 0
retls lr
@@ -54,6 +64,4 @@ ENTRY(__loop_delay)
#endif
bhi __loop_delay
ret lr
-ENDPROC(__loop_udelay)
-ENDPROC(__loop_const_udelay)
-ENDPROC(__loop_delay)
+SYM_FUNC_END(__loop_delay)
diff --git a/arch/arm/lib/error-inject.c b/arch/arm/lib/error-inject.c
new file mode 100644
index 000000000000..5a5b405792ba
--- /dev/null
+++ b/arch/arm/lib/error-inject.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+ instruction_pointer_set(regs, regs->ARM_lr);
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index b5e8b9ae4c7d..b7ac2d3c0748 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -12,182 +12,128 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/unwind.h>
.text
-/*
- * Purpose : Find a 'zero' bit
- * Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
- */
-ENTRY(_find_first_zero_bit_le)
- teq r1, #0
- beq 3f
- mov r2, #0
-1:
- ARM( ldrb r3, [r0, r2, lsr #3] )
- THUMB( lsr r3, r2, #3 )
- THUMB( ldrb r3, [r0, r3] )
- eors r3, r3, #0xff @ invert bits
- bne .L_found @ any now set - found zero bit
- add r2, r2, #8 @ next bit pointer
-2: cmp r2, r1 @ any more?
- blo 1b
-3: mov r0, r1 @ no free bits
- ret lr
-ENDPROC(_find_first_zero_bit_le)
+#ifdef __ARMEB__
+#define SWAB_ENDIAN le
+#else
+#define SWAB_ENDIAN be
+#endif
-/*
- * Purpose : Find next 'zero' bit
- * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
- */
-ENTRY(_find_next_zero_bit_le)
+ .macro find_first, endian, set, name
+ENTRY(_find_first_\name\()bit_\endian)
+ UNWIND( .fnstart)
teq r1, #0
- beq 3b
- ands ip, r2, #7
- beq 1b @ If new byte, goto old routine
- ARM( ldrb r3, [r0, r2, lsr #3] )
- THUMB( lsr r3, r2, #3 )
- THUMB( ldrb r3, [r0, r3] )
- eor r3, r3, #0xff @ now looking for a 1 bit
- movs r3, r3, lsr ip @ shift off unused bits
- bne .L_found
- orr r2, r2, #7 @ if zero, then no bits here
- add r2, r2, #1 @ align bit pointer
- b 2b @ loop for next bit
-ENDPROC(_find_next_zero_bit_le)
-
-/*
- * Purpose : Find a 'one' bit
- * Prototype: int find_first_bit(const unsigned long *addr, unsigned int maxbit);
- */
-ENTRY(_find_first_bit_le)
- teq r1, #0
beq 3f
mov r2, #0
-1:
- ARM( ldrb r3, [r0, r2, lsr #3] )
- THUMB( lsr r3, r2, #3 )
- THUMB( ldrb r3, [r0, r3] )
- movs r3, r3
- bne .L_found @ any now set - found zero bit
- add r2, r2, #8 @ next bit pointer
+1: ldr r3, [r0], #4
+ .ifeq \set
+ mvns r3, r3 @ invert/test bits
+ .else
+ movs r3, r3 @ test bits
+ .endif
+ .ifc \endian, SWAB_ENDIAN
+ bne .L_found_swab
+ .else
+ bne .L_found @ found the bit?
+ .endif
+ add r2, r2, #32 @ next index
2: cmp r2, r1 @ any more?
blo 1b
-3: mov r0, r1 @ no free bits
+3: mov r0, r1 @ no more bits
ret lr
-ENDPROC(_find_first_bit_le)
+ UNWIND( .fnend)
+ENDPROC(_find_first_\name\()bit_\endian)
+ .endm
-/*
- * Purpose : Find next 'one' bit
- * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
- */
-ENTRY(_find_next_bit_le)
- teq r1, #0
- beq 3b
- ands ip, r2, #7
- beq 1b @ If new byte, goto old routine
- ARM( ldrb r3, [r0, r2, lsr #3] )
- THUMB( lsr r3, r2, #3 )
- THUMB( ldrb r3, [r0, r3] )
+ .macro find_next, endian, set, name
+ENTRY(_find_next_\name\()bit_\endian)
+ UNWIND( .fnstart)
+ cmp r2, r1
+ bhs 3b
+ mov ip, r2, lsr #5 @ word index
+ add r0, r0, ip, lsl #2
+ ands ip, r2, #31 @ bit position
+ beq 1b
+ ldr r3, [r0], #4
+ .ifeq \set
+ mvn r3, r3 @ invert bits
+ .endif
+ .ifc \endian, SWAB_ENDIAN
+ rev_l r3, ip
+ .if .Lrev_l_uses_tmp
+ @ we need to recompute ip because rev_l will have overwritten
+ @ it.
+ and ip, r2, #31 @ bit position
+ .endif
+ .endif
movs r3, r3, lsr ip @ shift off unused bits
bne .L_found
- orr r2, r2, #7 @ if zero, then no bits here
+ orr r2, r2, #31 @ no zero bits
add r2, r2, #1 @ align bit pointer
b 2b @ loop for next bit
-ENDPROC(_find_next_bit_le)
+ UNWIND( .fnend)
+ENDPROC(_find_next_\name\()bit_\endian)
+ .endm
-#ifdef __ARMEB__
+ .macro find_bit, endian, set, name
+ find_first \endian, \set, \name
+ find_next \endian, \set, \name
+ .endm
-ENTRY(_find_first_zero_bit_be)
- teq r1, #0
- beq 3f
- mov r2, #0
-1: eor r3, r2, #0x18 @ big endian byte ordering
- ARM( ldrb r3, [r0, r3, lsr #3] )
- THUMB( lsr r3, #3 )
- THUMB( ldrb r3, [r0, r3] )
- eors r3, r3, #0xff @ invert bits
- bne .L_found @ any now set - found zero bit
- add r2, r2, #8 @ next bit pointer
-2: cmp r2, r1 @ any more?
- blo 1b
-3: mov r0, r1 @ no free bits
- ret lr
-ENDPROC(_find_first_zero_bit_be)
+/* _find_first_zero_bit_le and _find_next_zero_bit_le */
+ find_bit le, 0, zero_
-ENTRY(_find_next_zero_bit_be)
- teq r1, #0
- beq 3b
- ands ip, r2, #7
- beq 1b @ If new byte, goto old routine
- eor r3, r2, #0x18 @ big endian byte ordering
- ARM( ldrb r3, [r0, r3, lsr #3] )
- THUMB( lsr r3, #3 )
- THUMB( ldrb r3, [r0, r3] )
- eor r3, r3, #0xff @ now looking for a 1 bit
- movs r3, r3, lsr ip @ shift off unused bits
- bne .L_found
- orr r2, r2, #7 @ if zero, then no bits here
- add r2, r2, #1 @ align bit pointer
- b 2b @ loop for next bit
-ENDPROC(_find_next_zero_bit_be)
+/* _find_first_bit_le and _find_next_bit_le */
+ find_bit le, 1
-ENTRY(_find_first_bit_be)
- teq r1, #0
- beq 3f
- mov r2, #0
-1: eor r3, r2, #0x18 @ big endian byte ordering
- ARM( ldrb r3, [r0, r3, lsr #3] )
- THUMB( lsr r3, #3 )
- THUMB( ldrb r3, [r0, r3] )
- movs r3, r3
- bne .L_found @ any now set - found zero bit
- add r2, r2, #8 @ next bit pointer
-2: cmp r2, r1 @ any more?
- blo 1b
-3: mov r0, r1 @ no free bits
- ret lr
-ENDPROC(_find_first_bit_be)
+#ifdef __ARMEB__
-ENTRY(_find_next_bit_be)
- teq r1, #0
- beq 3b
- ands ip, r2, #7
- beq 1b @ If new byte, goto old routine
- eor r3, r2, #0x18 @ big endian byte ordering
- ARM( ldrb r3, [r0, r3, lsr #3] )
- THUMB( lsr r3, #3 )
- THUMB( ldrb r3, [r0, r3] )
- movs r3, r3, lsr ip @ shift off unused bits
- bne .L_found
- orr r2, r2, #7 @ if zero, then no bits here
- add r2, r2, #1 @ align bit pointer
- b 2b @ loop for next bit
-ENDPROC(_find_next_bit_be)
+/* _find_first_zero_bit_be and _find_next_zero_bit_be */
+ find_bit be, 0, zero_
+
+/* _find_first_bit_be and _find_next_bit_be */
+ find_bit be, 1
#endif
/*
* One or more bits in the LSB of r3 are assumed to be set.
*/
+.L_found_swab:
+ UNWIND( .fnstart)
+ rev_l r3, ip
.L_found:
-#if __LINUX_ARM_ARCH__ >= 5
+#if __LINUX_ARM_ARCH__ >= 7
+ rbit r3, r3 @ reverse bits
+ clz r3, r3 @ count high zero bits
+ add r0, r2, r3 @ add offset of first set bit
+#elif __LINUX_ARM_ARCH__ >= 5
rsb r0, r3, #0
- and r3, r3, r0
- clz r3, r3
- rsb r3, r3, #31
- add r0, r2, r3
+ and r3, r3, r0 @ mask out lowest bit set
+ clz r3, r3 @ count high zero bits
+ rsb r3, r3, #31 @ offset of first set bit
+ add r0, r2, r3 @ add offset of first set bit
#else
- tst r3, #0x0f
+ mov ip, #~0
+ tst r3, ip, lsr #16 @ test bits 0-15
+ addeq r2, r2, #16
+ moveq r3, r3, lsr #16
+ tst r3, #0x00ff
+ addeq r2, r2, #8
+ moveq r3, r3, lsr #8
+ tst r3, #0x000f
addeq r2, r2, #4
- movne r3, r3, lsl #4
- tst r3, #0x30
+ moveq r3, r3, lsr #4
+ tst r3, #0x0003
addeq r2, r2, #2
- movne r3, r3, lsl #2
- tst r3, #0x40
+ moveq r3, r3, lsr #2
+ tst r3, #0x0001
addeq r2, r2, #1
mov r0, r2
#endif
cmp r1, r0 @ Clamp to maxbit
movlo r0, r1
ret lr
-
+ UNWIND( .fnend)
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 09a333153dc6..90f2b645aa0d 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -42,26 +42,25 @@
strb\cond \reg, [\ptr], #1
.endm
- .macro enter reg1 reg2
- stmdb sp!, {r0, \reg1, \reg2}
+ .macro enter regs:vararg
+UNWIND( .save {r0, \regs} )
+ stmdb sp!, {r0, \regs}
.endm
- .macro usave reg1 reg2
- UNWIND( .save {r0, \reg1, \reg2} )
- .endm
-
- .macro exit reg1 reg2
- ldmfd sp!, {r0, \reg1, \reg2}
+ .macro exit regs:vararg
+ ldmfd sp!, {r0, \regs}
.endm
.text
/* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
+ENTRY(__memcpy)
ENTRY(mmiocpy)
-ENTRY(memcpy)
+WEAK(memcpy)
#include "copy_template.S"
ENDPROC(memcpy)
ENDPROC(mmiocpy)
+ENDPROC(__memcpy)
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index b50e5770fb44..6410554039fd 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -24,18 +24,20 @@
* occurring in the opposite direction.
*/
-ENTRY(memmove)
+ENTRY(__memmove)
+WEAK(memmove)
UNWIND( .fnstart )
subs ip, r0, r1
cmphi r2, ip
- bls memcpy
-
- stmfd sp!, {r0, r4, lr}
+ bls __memcpy
UNWIND( .fnend )
UNWIND( .fnstart )
- UNWIND( .save {r0, r4, lr} ) @ in first stmfd block
+ UNWIND( .save {r0, r4, fpreg, lr} )
+ stmfd sp!, {r0, r4, UNWIND(fpreg,) lr}
+ UNWIND( .setfp fpreg, sp )
+ UNWIND( mov fpreg, sp )
add r1, r1, r2
add r0, r0, r2
subs r2, r2, #4
@@ -47,12 +49,7 @@ ENTRY(memmove)
bne 10f
1: subs r2, r2, #(28)
- stmfd sp!, {r5 - r8}
- UNWIND( .fnend )
-
- UNWIND( .fnstart )
- UNWIND( .save {r0, r4, lr} )
- UNWIND( .save {r5 - r8} ) @ in second stmfd block
+ stmfd sp!, {r5, r6, r8, r9}
blt 5f
CALGN( ands ip, r0, #31 )
@@ -71,9 +68,9 @@ ENTRY(memmove)
PLD( pld [r1, #-96] )
3: PLD( pld [r1, #-128] )
-4: ldmdb r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
+4: ldmdb r1!, {r3, r4, r5, r6, r8, r9, ip, lr}
subs r2, r2, #32
- stmdb r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
+ stmdb r0!, {r3, r4, r5, r6, r8, r9, ip, lr}
bge 3b
PLD( cmn r2, #96 )
PLD( bge 4b )
@@ -87,8 +84,8 @@ ENTRY(memmove)
W(ldr) r4, [r1, #-4]!
W(ldr) r5, [r1, #-4]!
W(ldr) r6, [r1, #-4]!
- W(ldr) r7, [r1, #-4]!
W(ldr) r8, [r1, #-4]!
+ W(ldr) r9, [r1, #-4]!
W(ldr) lr, [r1, #-4]!
add pc, pc, ip
@@ -98,17 +95,13 @@ ENTRY(memmove)
W(str) r4, [r0, #-4]!
W(str) r5, [r0, #-4]!
W(str) r6, [r0, #-4]!
- W(str) r7, [r0, #-4]!
W(str) r8, [r0, #-4]!
+ W(str) r9, [r0, #-4]!
W(str) lr, [r0, #-4]!
CALGN( bcs 2b )
-7: ldmfd sp!, {r5 - r8}
- UNWIND( .fnend ) @ end of second stmfd block
-
- UNWIND( .fnstart )
- UNWIND( .save {r0, r4, lr} ) @ still in first stmfd block
+7: ldmfd sp!, {r5, r6, r8, r9}
8: movs r2, r2, lsl #31
ldrbne r3, [r1, #-1]!
@@ -117,7 +110,7 @@ ENTRY(memmove)
strbne r3, [r0, #-1]!
strbcs r4, [r0, #-1]!
strbcs ip, [r0, #-1]
- ldmfd sp!, {r0, r4, pc}
+ ldmfd sp!, {r0, r4, UNWIND(fpreg,) pc}
9: cmp ip, #2
ldrbgt r3, [r1, #-1]!
@@ -136,13 +129,10 @@ ENTRY(memmove)
ldr r3, [r1, #0]
beq 17f
blt 18f
- UNWIND( .fnend )
.macro backward_copy_shift push pull
- UNWIND( .fnstart )
- UNWIND( .save {r0, r4, lr} ) @ still in first stmfd block
subs r2, r2, #28
blt 14f
@@ -151,12 +141,7 @@ ENTRY(memmove)
CALGN( subcc r2, r2, ip )
CALGN( bcc 15f )
-11: stmfd sp!, {r5 - r9}
- UNWIND( .fnend )
-
- UNWIND( .fnstart )
- UNWIND( .save {r0, r4, lr} )
- UNWIND( .save {r5 - r9} ) @ in new second stmfd block
+11: stmfd sp!, {r5, r6, r8 - r10}
PLD( pld [r1, #-4] )
PLD( subs r2, r2, #96 )
@@ -166,35 +151,31 @@ ENTRY(memmove)
PLD( pld [r1, #-96] )
12: PLD( pld [r1, #-128] )
-13: ldmdb r1!, {r7, r8, r9, ip}
+13: ldmdb r1!, {r8, r9, r10, ip}
mov lr, r3, lspush #\push
subs r2, r2, #32
ldmdb r1!, {r3, r4, r5, r6}
orr lr, lr, ip, lspull #\pull
mov ip, ip, lspush #\push
- orr ip, ip, r9, lspull #\pull
+ orr ip, ip, r10, lspull #\pull
+ mov r10, r10, lspush #\push
+ orr r10, r10, 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
+ orr r8, r8, 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}
+ stmdb r0!, {r4 - r6, r8 - r10, ip, lr}
bge 12b
PLD( cmn r2, #96 )
PLD( bge 13b )
- ldmfd sp!, {r5 - r9}
- UNWIND( .fnend ) @ end of the second stmfd block
-
- UNWIND( .fnstart )
- UNWIND( .save {r0, r4, lr} ) @ still in first stmfd block
+ ldmfd sp!, {r5, r6, r8 - r10}
14: ands ip, r2, #28
beq 16f
@@ -210,7 +191,6 @@ ENTRY(memmove)
16: add r1, r1, #(\pull / 8)
b 8b
- UNWIND( .fnend )
.endm
@@ -221,4 +201,6 @@ ENTRY(memmove)
18: backward_copy_shift push=24 pull=8
+ UNWIND( .fnend )
ENDPROC(memmove)
+ENDPROC(__memmove)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 6ca4535c47fb..de75ae4d5ab4 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -13,9 +13,11 @@
.text
.align 5
+ENTRY(__memset)
ENTRY(mmioset)
-ENTRY(memset)
+WEAK(memset)
UNWIND( .fnstart )
+ and r1, r1, #255 @ cast to unsigned char
ands r3, r0, #3 @ 1 unaligned?
mov ip, r0 @ preserve r0 as return value
bne 6f @ 1
@@ -27,16 +29,16 @@ UNWIND( .fnstart )
mov r3, r1
7: cmp r2, #16
blt 4f
+UNWIND( .fnend )
#if ! CALGN(1)+0
/*
* We need 2 extra registers for this loop - use r8 and the LR
*/
- stmfd sp!, {r8, lr}
-UNWIND( .fnend )
UNWIND( .fnstart )
UNWIND( .save {r8, lr} )
+ stmfd sp!, {r8, lr}
mov r8, r1
mov lr, r3
@@ -65,10 +67,9 @@ UNWIND( .fnend )
* whole cache lines at once.
*/
- stmfd sp!, {r4-r8, lr}
-UNWIND( .fnend )
UNWIND( .fnstart )
UNWIND( .save {r4-r8, lr} )
+ stmfd sp!, {r4-r8, lr}
mov r4, r1
mov r5, r3
mov r6, r1
@@ -132,6 +133,7 @@ UNWIND( .fnstart )
UNWIND( .fnend )
ENDPROC(memset)
ENDPROC(mmioset)
+ENDPROC(__memset)
ENTRY(__memset32)
UNWIND( .fnstart )
diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S
index 4ebecc67e6e0..f13fe9bc2399 100644
--- a/arch/arm/lib/testchangebit.S
+++ b/arch/arm/lib/testchangebit.S
@@ -10,3 +10,7 @@
.text
testop _test_and_change_bit, eor, str
+
+#if __LINUX_ARM_ARCH__ >= 6
+sync_testop _sync_test_and_change_bit, eor, str
+#endif
diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S
index 009afa0f5b4a..4d2c5ca620eb 100644
--- a/arch/arm/lib/testclearbit.S
+++ b/arch/arm/lib/testclearbit.S
@@ -10,3 +10,7 @@
.text
testop _test_and_clear_bit, bicne, strne
+
+#if __LINUX_ARM_ARCH__ >= 6
+sync_testop _sync_test_and_clear_bit, bicne, strne
+#endif
diff --git a/arch/arm/lib/testsetbit.S b/arch/arm/lib/testsetbit.S
index f3192e55acc8..649dbab65d8d 100644
--- a/arch/arm/lib/testsetbit.S
+++ b/arch/arm/lib/testsetbit.S
@@ -10,3 +10,7 @@
.text
testop _test_and_set_bit, orreq, streq
+
+#if __LINUX_ARM_ARCH__ >= 6
+sync_testop _sync_test_and_set_bit, orreq, streq
+#endif
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index c9450982a155..c0ac7796d775 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -24,6 +24,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
{
unsigned long addr = (unsigned long)_addr;
pgd_t *pgd;
+ p4d_t *p4d;
pmd_t *pmd;
pte_t *pte;
pud_t *pud;
@@ -33,7 +34,11 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
if (unlikely(pgd_none(*pgd) || pgd_bad(*pgd)))
return 0;
- pud = pud_offset(pgd, addr);
+ p4d = p4d_offset(pgd, addr);
+ if (unlikely(p4d_none(*p4d) || p4d_bad(*p4d)))
+ return 0;
+
+ pud = pud_offset(p4d, addr);
if (unlikely(pud_none(*pud) || pud_bad(*pud)))
return 0;
@@ -51,10 +56,10 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
* to see that it's still huge and whether or not we will
* need to fault on write.
*/
- if (unlikely(pmd_thp_or_huge(*pmd))) {
+ if (unlikely(pmd_leaf(*pmd))) {
ptl = &current->mm->page_table_lock;
spin_lock(ptl);
- if (unlikely(!pmd_thp_or_huge(*pmd)
+ if (unlikely(!pmd_leaf(*pmd)
|| pmd_hugewillfault(*pmd))) {
spin_unlock(ptl);
return 0;
@@ -69,6 +74,9 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
return 0;
pte = pte_offset_map_lock(current->mm, pmd, addr, &ptl);
+ if (unlikely(!pte))
+ return 0;
+
if (unlikely(!pte_present(*pte) || !pte_young(*pte) ||
!pte_write(*pte) || !pte_dirty(*pte))) {
pte_unmap_unlock(pte, ptl);
@@ -87,16 +95,11 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
unsigned long ua_flags;
int atomic;
- if (uaccess_kernel()) {
- memcpy((void *)to, from, n);
- return 0;
- }
-
/* the mmap semaphore is taken only if not in an atomic context */
atomic = faulthandler_disabled();
if (!atomic)
- down_read(&current->mm->mmap_sem);
+ mmap_read_lock(current->mm);
while (n) {
pte_t *pte;
spinlock_t *ptl;
@@ -104,11 +107,11 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
while (!pin_page_for_write(to, &pte, &ptl)) {
if (!atomic)
- up_read(&current->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
if (__put_user(0, (char __user *)to))
goto out;
if (!atomic)
- down_read(&current->mm->mmap_sem);
+ mmap_read_lock(current->mm);
}
tocopy = (~(unsigned long)to & ~PAGE_MASK) + 1;
@@ -116,7 +119,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
tocopy = n;
ua_flags = uaccess_save_and_enable();
- memcpy((void *)to, from, tocopy);
+ __memcpy((void *)to, from, tocopy);
uaccess_restore(ua_flags);
to += tocopy;
from += tocopy;
@@ -128,7 +131,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
spin_unlock(ptl);
}
if (!atomic)
- up_read(&current->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
out:
return n;
@@ -160,22 +163,17 @@ __clear_user_memset(void __user *addr, unsigned long n)
{
unsigned long ua_flags;
- if (uaccess_kernel()) {
- memset((void *)addr, 0, n);
- return 0;
- }
-
- down_read(&current->mm->mmap_sem);
+ mmap_read_lock(current->mm);
while (n) {
pte_t *pte;
spinlock_t *ptl;
int tocopy;
while (!pin_page_for_write(addr, &pte, &ptl)) {
- up_read(&current->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
if (__put_user(0, (char __user *)addr))
goto out;
- down_read(&current->mm->mmap_sem);
+ mmap_read_lock(current->mm);
}
tocopy = (~(unsigned long)addr & ~PAGE_MASK) + 1;
@@ -183,7 +181,7 @@ __clear_user_memset(void __user *addr, unsigned long n)
tocopy = n;
ua_flags = uaccess_save_and_enable();
- memset((void *)addr, 0, tocopy);
+ __memset((void *)addr, 0, tocopy);
uaccess_restore(ua_flags);
addr += tocopy;
n -= tocopy;
@@ -193,7 +191,7 @@ __clear_user_memset(void __user *addr, unsigned long n)
else
spin_unlock(ptl);
}
- up_read(&current->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
out:
return n;
@@ -242,7 +240,7 @@ static int __init test_size_treshold(void)
if (!dst_page)
goto no_dst;
kernel_ptr = page_address(src_page);
- user_ptr = vmap(&dst_page, 1, VM_IOREMAP, __pgprot(__P010));
+ user_ptr = vmap(&dst_page, 1, VM_IOREMAP, __pgprot(__PAGE_COPY));
if (!user_ptr)
goto no_vmap;
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index b99dd8e1c93f..cf57fca97908 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -8,6 +8,7 @@
#include <linux/raid/xor.h>
#include <linux/module.h>
+MODULE_DESCRIPTION("NEON accelerated XOR implementation");
MODULE_LICENSE("GPL");
#ifndef __ARM_NEON__
@@ -17,17 +18,11 @@ MODULE_LICENSE("GPL");
/*
* Pull in the reference implementations while instructing GCC (through
* -ftree-vectorize) to attempt to exploit implicit parallelism and emit
- * NEON instructions.
+ * NEON instructions. Clang does this by default at O2 so no pragma is
+ * needed.
*/
-#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#ifdef CONFIG_CC_IS_GCC
#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"