diff options
Diffstat (limited to 'arch/arm/lib')
58 files changed, 1296 insertions, 1641 deletions
diff --git a/arch/arm/lib/.gitignore b/arch/arm/lib/.gitignore new file mode 100644 index 000000000000..647d7a922e68 --- /dev/null +++ b/arch/arm/lib/.gitignore @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only + +# This now-removed directory used to contain generated files. +/crypto/ diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index af72969820b4..0ca5aae1bcc3 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -1,32 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 # # linux/arch/arm/lib/Makefile # # Copyright (C) 1995-2000 Russell King # -lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \ +lib-y := changebit.o csumipv6.o csumpartial.o \ csumpartialcopy.o csumpartialcopyuser.o clearbit.o \ delay.o delay-loop.o findbit.o memchr.o memcpy.o \ - memmove.o memset.o memzero.o setbit.o \ + memmove.o memset.o setbit.o \ strchr.o strrchr.o \ testchangebit.o testclearbit.o testsetbit.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 +mmu-y := clear_user.o copy_page.o getuser.o putuser.o \ + copy_from_user.o copy_to_user.o -# the code in uaccess.S is not preemption safe and -# probably faster on ARMv3 only -ifeq ($(CONFIG_PREEMPT),y) - mmu-y += copy_from_user.o copy_to_user.o +ifdef CONFIG_CC_IS_CLANG + lib-y += backtrace-clang.o else -ifneq ($(CONFIG_CPU_32v3),y) - mmu-y += copy_from_user.o copy_to_user.o -else - mmu-y += uaccess.o -endif + lib-y += backtrace.o endif # using lib_ here won't override already available weak symbols @@ -40,8 +36,12 @@ else lib-y += io-readsw-armv4.o io-writesw-armv4.o endif -lib-$(CONFIG_ARCH_RPC) += ecard.o io-acorn.o floppydma.o -lib-$(CONFIG_ARCH_SHARK) += io-shark.o - $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S $(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S + +ifeq ($(CONFIG_KERNEL_MODE_NEON),y) + CFLAGS_xor-neon.o += $(CC_FLAGS_FPU) + obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o +endif + +obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S index 638deb13da1c..b05e95840651 100644 --- a/arch/arm/lib/ashldi3.S +++ b/arch/arm/lib/ashldi3.S @@ -27,6 +27,7 @@ Boston, MA 02110-1301, USA. */ #include <linux/linkage.h> +#include <asm/assembler.h> #ifdef __ARMEB__ #define al r1 @@ -47,7 +48,7 @@ ENTRY(__aeabi_llsl) THUMB( lsrmi r3, al, ip ) THUMB( orrmi ah, ah, r3 ) mov al, al, lsl r2 - mov pc, lr + ret lr ENDPROC(__ashldi3) ENDPROC(__aeabi_llsl) diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S index 015e8aa5a1d1..275d7d2341a4 100644 --- a/arch/arm/lib/ashrdi3.S +++ b/arch/arm/lib/ashrdi3.S @@ -27,6 +27,7 @@ Boston, MA 02110-1301, USA. */ #include <linux/linkage.h> +#include <asm/assembler.h> #ifdef __ARMEB__ #define al r1 @@ -47,7 +48,7 @@ ENTRY(__aeabi_lasr) THUMB( lslmi r3, ah, ip ) THUMB( orrmi al, al, r3 ) mov ah, ah, asr r2 - mov pc, lr + ret lr ENDPROC(__ashrdi3) ENDPROC(__aeabi_lasr) diff --git a/arch/arm/lib/backtrace-clang.S b/arch/arm/lib/backtrace-clang.S new file mode 100644 index 000000000000..290c52a60fc6 --- /dev/null +++ b/arch/arm/lib/backtrace-clang.S @@ -0,0 +1,230 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/lib/backtrace-clang.S + * + * Copyright (C) 2019 Nathan Huckleberry + * + */ +#include <linux/kern_levels.h> +#include <linux/linkage.h> +#include <asm/assembler.h> + .text + +/* fp is 0 or stack frame */ + +#define frame r4 +#define sv_fp r5 +#define sv_pc r6 +#define mask r7 +#define sv_lr r8 +#define loglvl r9 + +ENTRY(c_backtrace) + +#if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK) + ret lr +ENDPROC(c_backtrace) +#else + + +/* + * Clang does not store pc or sp in function prologues so we don't know exactly + * where the function starts. + * + * We can treat the current frame's lr as the saved pc and the preceding + * frame's lr as the current frame's lr, but we can't trace the most recent + * call. Inserting a false stack frame allows us to reference the function + * called last in the stacktrace. + * + * If the call instruction was a bl we can look at the callers branch + * instruction to calculate the saved pc. We can recover the pc in most cases, + * but in cases such as calling function pointers we cannot. In this case, + * default to using the lr. This will be some address in the function, but will + * not be the function start. + * + * Unfortunately due to the stack frame layout we can't dump r0 - r3, but these + * are less frequently saved. + * + * Stack frame layout: + * <larger addresses> + * saved lr + * frame=> saved fp + * optionally saved caller registers (r4 - r10) + * optionally saved arguments (r0 - r3) + * <top of stack frame> + * <smaller addresses> + * + * Functions start with the following code sequence: + * corrected pc => stmfd sp!, {..., fp, lr} + * add fp, sp, #x + * stmfd sp!, {r0 - r3} (optional) + * + * + * + * + * + * + * The diagram below shows an example stack setup for dump_stack. + * + * The frame for c_backtrace has pointers to the code of dump_stack. This is + * why the frame of c_backtrace is used to for the pc calculation of + * dump_stack. This is why we must move back a frame to print dump_stack. + * + * The stored locals for dump_stack are in dump_stack's frame. This means that + * to fully print dump_stack's frame we need both the frame for dump_stack (for + * locals) and the frame that was called by dump_stack (for pc). + * + * To print locals we must know where the function start is. If we read the + * function prologue opcodes we can determine which variables are stored in the + * stack frame. + * + * To find the function start of dump_stack we can look at the stored LR of + * show_stack. It points at the instruction directly after the bl dump_stack. + * We can then read the offset from the bl opcode to determine where the branch + * takes us. The address calculated must be the start of dump_stack. + * + * c_backtrace frame dump_stack: + * {[LR] } ============| ... + * {[FP] } =======| | bl c_backtrace + * | |=> ... + * {[R4-R10]} | + * {[R0-R3] } | show_stack: + * dump_stack frame | ... + * {[LR] } =============| bl dump_stack + * {[FP] } <=======| |=> ... + * {[R4-R10]} + * {[R0-R3] } + */ + + stmfd sp!, {r4 - r9, fp, lr} @ Save an extra register + @ 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 + +/* + * Switches the current frame to be the frame for dump_stack. + */ + add frame, sp, #24 @ switch to false frame +for_each_frame: tst frame, mask @ Check for address exceptions + bne no_frame + +/* + * sv_fp is the stack frame with the locals for the current considered + * function. + * + * sv_pc is the saved lr frame the frame above. This is a pointer to a code + * address within the current considered function, but it is not the function + * start. This value gets updated to be the function start later if it is + * possible. + */ +1001: ldr sv_pc, [frame, #4] @ get saved 'pc' +1002: ldr sv_fp, [frame, #0] @ get saved fp + + teq sv_fp, mask @ make sure next frame exists + beq no_frame + +/* + * sv_lr is the lr from the function that called the current function. This is + * a pointer to a code address in the current function's caller. sv_lr-4 is + * the instruction used to call the current function. + * + * This sv_lr can be used to calculate the function start if the function was + * called using a bl instruction. If the function start can be recovered sv_pc + * is overwritten with the function start. + * + * If the current function was called using a function pointer we cannot + * recover the function start and instead continue with sv_pc as an arbitrary + * value within the current function. If this is the case we cannot print + * registers for the current function, but the stacktrace is still printed + * properly. + */ +1003: ldr sv_lr, [sv_fp, #4] @ get saved lr from next frame + +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 + bne finished_setup @ give up if it's not + and r0, #0xffffff @ get call offset 24-bit int + lsl r0, r0, #8 @ sign extend offset + asr r0, r0, #8 + ldr sv_pc, [sv_fp, #4] @ get lr address + add sv_pc, sv_pc, #-4 @ get call instruction address + add sv_pc, sv_pc, #8 @ take care of prefetch + add sv_pc, sv_pc, r0, lsl #2@ find function start + +finished_setup: + + bic sv_pc, sv_pc, mask @ mask PC/LR for the mode + +/* + * Print the function (sv_pc) and where it was called from (sv_lr). + */ + 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 + +/* + * Test if the function start is a stmfd instruction to determine which + * registers were stored in the function prologue. + * + * If we could not recover the sv_pc because we were called through a function + * pointer the comparison will fail and no registers will print. Unwinding will + * continue as if there had been no registers stored in this frame. + */ +1005: ldr r1, [sv_pc, #0] @ if stmfd sp!, {..., fp, lr} + ldr r3, .Lopcode @ instruction exists, + teq r3, r1, lsr #11 + ldr r0, [frame] @ locals are stored in + @ the preceding frame + subeq r0, r0, #4 + mov r2, loglvl + bleq dump_backtrace_stm @ dump saved registers + +/* + * If we are out of frames or if the next frame is invalid. + */ + teq sv_fp, #0 @ zero saved fp means + beq no_frame @ no further frames + + 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, loglvl + mov r2, frame + bl _printk +no_frame: ldmfd sp!, {r4 - r9, fp, pc} +ENDPROC(c_backtrace) + .pushsection __ex_table,"a" + .align 3 + .long 1001b, 1006b + .long 1002b, 1006b + .long 1003b, 1006b + .long 1004b, finished_setup + .long 1005b, 1006b + .popsection + +.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 + +#endif diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S index cd07b5814c23..293a2716bd20 100644 --- a/arch/arm/lib/backtrace.S +++ b/arch/arm/lib/backtrace.S @@ -1,15 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/backtrace.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. - * * 27/03/03 Ian Molton Clean up CONFIG_CPU - * */ +#include <linux/kern_levels.h> #include <linux/linkage.h> #include <asm/assembler.h> .text @@ -21,16 +18,18 @@ #define sv_pc r6 #define mask r7 #define offset r8 +#define loglvl r9 ENTRY(c_backtrace) #if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK) - mov pc, lr + 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 ) @@ -69,39 +68,51 @@ for_each_frame: tst frame, mask @ Check for address exceptions 1003: ldr r2, [sv_pc, #-4] @ if stmfd sp!, {args} exists, ldr r3, .Ldsi+4 @ adjust saved 'pc' back one - teq r3, r2, lsr #10 @ instruction + teq r3, r2, lsr #11 @ instruction subne r0, sv_pc, #4 @ allow for mov subeq r0, sv_pc, #8 @ allow for mov + stmia 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, 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 + 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 #10 + teq r3, r1, lsr #11 subeq r0, frame, #16 - bleq .Ldumpstm @ dump saved registers + mov r2, loglvl + bleq dump_backtrace_stm @ dump saved registers teq sv_fp, #0 @ zero saved fp means beq no_frame @ no further frames 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" @@ -112,41 +123,9 @@ ENDPROC(c_backtrace) .long 1004b, 1006b .popsection -#define instr r4 -#define reg r5 -#define stack r6 - -.Ldumpstm: stmfd sp!, {instr, reg, stack, r7, lr} - mov stack, r0 - mov instr, r1 - mov reg, #10 - mov r7, #0 -1: mov r3, #1 - ARM( tst instr, r3, lsl reg ) - THUMB( lsl r3, reg ) - THUMB( tst instr, r3 ) - beq 2f - add r7, r7, #1 - teq r7, #6 - moveq r7, #1 - moveq r1, #'\n' - movne r1, #' ' - ldr r3, [stack], #-4 - mov r2, reg - adr r0, .Lfp - bl printk -2: subs reg, reg, #1 - bpl 1b - teq r7, #0 - adrne r0, .Lcr - blne printk - ldmfd sp!, {instr, reg, stack, r7, pc} - -.Lfp: .asciz "%cr%d:%08x" -.Lcr: .asciz "\n" -.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 >> 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 d6408d1ee543..f069d1b2318e 100644 --- a/arch/arm/lib/bitops.h +++ b/arch/arm/lib/bitops.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/assembler.h> #include <asm/unwind.h> #if __LINUX_ARM_ARCH__ >= 6 @@ -5,11 +7,16 @@ ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned mov r2, #1 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 @@ -21,36 +28,49 @@ UNWIND( .fnend ) ENDPROC(\name ) .endm - .macro testop, name, instr, store + .macro __testop, name, instr, store, barrier ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned mov r2, #1 and r3, r0, #31 @ Get bit offset 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]) + ALT_UP(W(nop)) +#endif 1: ldrex r2, [r1] ands r0, r2, r3 @ save old value of bit \instr r2, r2, r3 @ toggle bit 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 ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned and r2, r0, #31 mov r0, r0, lsr #5 mov r3, #1 @@ -60,7 +80,7 @@ UNWIND( .fnstart ) \instr r2, r2, r3 str r2, [r1, r0, lsl #2] restore_irqs ip - mov pc, lr + ret lr UNWIND( .fnend ) ENDPROC(\name ) .endm @@ -77,7 +97,7 @@ ENDPROC(\name ) ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned and r3, r0, #31 mov r0, r0, lsr #5 save_and_disable_irqs ip @@ -88,7 +108,7 @@ UNWIND( .fnstart ) \store r2, [r1] moveq r0, #0 restore_irqs ip - mov pc, lr + ret lr UNWIND( .fnend ) ENDPROC(\name ) .endm diff --git a/arch/arm/lib/bswapsdi2.S b/arch/arm/lib/bswapsdi2.S new file mode 100644 index 000000000000..591ba077e874 --- /dev/null +++ b/arch/arm/lib/bswapsdi2.S @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> +#include <asm/assembler.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 + ret 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 + ret lr +ENDPROC(__bswapdi2) +#endif diff --git a/arch/arm/lib/call_with_stack.S b/arch/arm/lib/call_with_stack.S index 916c80f13ae7..5030d4e8d126 100644 --- a/arch/arm/lib/call_with_stack.S +++ b/arch/arm/lib/call_with_stack.S @@ -1,44 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * arch/arm/lib/call_with_stack.S * * Copyright (C) 2011 ARM Ltd. * Written by Will Deacon <will.deacon@arm.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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #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 - adr lr, BSYM(1f) - mov pc, r2 + bl_r r2 -1: ldr lr, [sp] - ldr sp, [sp, #4] - mov pc, 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/changebit.S b/arch/arm/lib/changebit.S index f4027862172f..02424765e9e1 100644 --- a/arch/arm/lib/changebit.S +++ b/arch/arm/lib/changebit.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/changebit.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. */ #include <linux/linkage.h> #include <asm/assembler.h> diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S index 14a0d988c82c..8f2c4dbfc5f2 100644 --- a/arch/arm/lib/clear_user.S +++ b/arch/arm/lib/clear_user.S @@ -1,25 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/clear_user.S * * Copyright (C) 1995, 1996,1997,1998 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/unwind.h> .text -/* Prototype: int __clear_user(void *addr, size_t sz) +/* Prototype: unsigned long arm_clear_user(void *addr, size_t sz) * Purpose : clear some user memory * Params : addr - user memory address to clear * : sz - number of bytes to clear * Returns : number of bytes NOT cleared */ ENTRY(__clear_user_std) -WEAK(__clear_user) +WEAK(arm_clear_user) +UNWIND(.fnstart) +UNWIND(.save {r1, lr}) stmfd sp!, {r1, lr} mov r2, #0 cmp r1, #4 @@ -41,13 +41,14 @@ WEAK(__clear_user) strusr r2, r0, 1, ne, rept=2 tst r1, #1 @ x1 x0 x1 x0 x1 x0 x1 it ne @ explicit IT needed for the label -USER( strnebt r2, [r0]) +USER( strbtne r2, [r0]) mov r0, #0 ldmfd sp!, {r1, pc} -ENDPROC(__clear_user) +UNWIND(.fnend) +ENDPROC(arm_clear_user) ENDPROC(__clear_user_std) - .pushsection .fixup,"ax" + .pushsection .text.fixup,"ax" .align 0 9001: ldmfd sp!, {r0, pc} .popsection diff --git a/arch/arm/lib/clearbit.S b/arch/arm/lib/clearbit.S index f6b75fb64d30..4646dee8a339 100644 --- a/arch/arm/lib/clearbit.S +++ b/arch/arm/lib/clearbit.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/clearbit.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. */ #include <linux/linkage.h> #include <asm/assembler.h> diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 66a477a3e3cc..270de7debd0f 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -1,22 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/copy_from_user.S * * Author: Nicolas Pitre * Created: Sep 29, 2005 * Copyright: MontaVista Software, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/unwind.h> /* * Prototype: * - * size_t __copy_from_user(void *to, const void *from, size_t n) + * size_t arm_copy_from_user(void *to, const void *from, size_t n) * * Purpose: * @@ -33,12 +31,13 @@ * Number of bytes NOT copied. */ +#ifdef CONFIG_CPU_USE_DOMAINS + #ifndef CONFIG_THUMB2_KERNEL #define LDR1W_SHIFT 0 #else #define LDR1W_SHIFT 1 #endif -#define STR1W_SHIFT 0 .macro ldr1w ptr reg abort ldrusr \reg, \ptr, 4, abort=\abort @@ -56,10 +55,30 @@ ldr4w \ptr, \reg5, \reg6, \reg7, \reg8, \abort .endm +#else + +#define LDR1W_SHIFT 0 + + .macro ldr1w ptr reg abort + USERL(\abort, W(ldr) \reg, [\ptr], #4) + .endm + + .macro ldr4w ptr reg1 reg2 reg3 reg4 abort + USERL(\abort, ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4}) + .endm + + .macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + USERL(\abort, ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8}) + .endm + +#endif /* CONFIG_CPU_USE_DOMAINS */ + .macro ldr1b ptr reg cond=al abort ldrusr \reg, \ptr, 1, \cond, abort=\abort .endm +#define STR1W_SHIFT 0 + .macro str1w ptr reg abort W(str) \reg, [\ptr], #4 .endm @@ -69,36 +88,38 @@ .endm .macro str1b ptr reg cond=al abort - str\cond\()b \reg, [\ptr], #1 + 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 exit reg1 reg2 + .macro exit regs:vararg add sp, sp, #8 - ldmfd sp!, {r0, \reg1, \reg2} + ldmfd sp!, {r0, \regs} .endm .text -ENTRY(__copy_from_user) +ENTRY(arm_copy_from_user) +#ifdef CONFIG_CPU_SPECTRE + ldr r3, =TASK_SIZE + uaccess_mask_range_ptr r1, r2, r3, ip +#endif #include "copy_template.S" -ENDPROC(__copy_from_user) +ENDPROC(arm_copy_from_user) - .pushsection .fixup,"ax" + .pushsection .text.fixup,"ax" .align 0 copy_abort_preamble - ldmfd sp!, {r1, r2} - sub r3, r0, r1 - rsb r1, r3, r2 - str r1, [sp] - bl __memzero - ldr r0, [sp], #4 + ldmfd sp!, {r1, r2, r3} + sub r0, r0, r1 + rsb r0, r0, r2 copy_abort_end .popsection diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S index 6ee2f6706f86..5db1a8ee3d9f 100644 --- a/arch/arm/lib/copy_page.S +++ b/arch/arm/lib/copy_page.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/copypage.S * * Copyright (C) 1995-1999 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. - * * ASM optimised string functions */ #include <linux/linkage.h> @@ -39,9 +36,9 @@ ENTRY(copy_page) .endr subs r2, r2, #1 @ 1 stmia r0!, {r3, r4, ip, lr} @ 4 - ldmgtia r1!, {r3, r4, ip, lr} @ 4 + ldmiagt r1!, {r3, r4, ip, lr} @ 4 bgt 1b @ 1 - PLD( ldmeqia r1!, {r3, r4, ip, lr} ) + PLD( ldmiaeq r1!, {r3, r4, ip, lr} ) PLD( beq 2b ) ldmfd sp!, {r4, pc} @ 3 ENDPROC(copy_page) diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S index 805e3f8fb007..8fbafb074fe9 100644 --- a/arch/arm/lib/copy_template.S +++ b/arch/arm/lib/copy_template.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/copy_template.s * @@ -6,10 +7,6 @@ * Author: Nicolas Pitre * Created: Sep 28, 2005 * Copyright: MontaVista Software, Inc. - * - * 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. */ /* @@ -53,6 +50,12 @@ * data as needed by the implementation including this code. Called * upon code entry. * + * usave reg1 reg2 + * + * Unwind annotation macro is corresponding for 'enter' macro. + * It tell unwinder that preserved some provided registers on the stack + * and additional data by a prior 'enter' macro. + * * exit reg1 reg2 * * Restore registers with the values previously saved with the @@ -66,8 +69,10 @@ * than one 32bit instruction in Thumb-2) */ - - enter r4, lr + UNWIND( .fnstart ) + enter r4, UNWIND(fpreg,) lr + UNWIND( .setfp fpreg, sp ) + UNWIND( mov fpreg, sp ) subs r2, r2, #4 blt 8f @@ -78,12 +83,12 @@ bne 10f 1: subs r2, r2, #(28) - stmfd sp!, {r5 - r8} + stmfd sp!, {r5, r6, r8, r9} blt 5f CALGN( ands ip, r0, #31 ) CALGN( rsb r3, ip, #32 ) - CALGN( sbcnes r4, r3, r2 ) @ C is always set here + CALGN( sbcsne r4, r3, r2 ) @ C is always set here CALGN( bcs 2f ) CALGN( adr r4, 6f ) CALGN( subs r2, r2, r3 ) @ C gets set @@ -97,9 +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 ) @@ -119,8 +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 @@ -137,13 +142,13 @@ 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} +7: ldmfd sp!, {r5, r6, r8, r9} 8: movs r2, r2, lsl #31 ldr1b r1, r3, ne, abort=21f @@ -153,7 +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 @@ -182,11 +187,11 @@ CALGN( ands ip, r0, #31 ) CALGN( rsb ip, ip, #32 ) - CALGN( sbcnes r4, ip, r2 ) @ C is always set here + CALGN( sbcsne r4, ip, r2 ) @ C is always set here CALGN( subcc r2, r2, ip ) CALGN( bcc 15f ) -11: stmfd sp!, {r5 - r9} +11: stmfd sp!, {r5, r6, r8 - r10} PLD( pld [r1, #0] ) PLD( subs r2, r2, #96 ) @@ -196,39 +201,39 @@ PLD( pld [r1, #92] ) 12: PLD( pld [r1, #124] ) -13: ldr4w r1, r4, r5, r6, r7, abort=19f - mov r3, lr, pull #\pull +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 - 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 - str8w r0, r3, r4, r5, r6, r7, r8, r9, ip, , 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, r8, lspush #\push + mov r8, r8, lspull #\pull + orr r8, r8, r9, lspush #\push + mov r9, r9, lspull #\pull + 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, r8, r9, r10, ip, abort=19f bge 12b PLD( cmn r2, #96 ) PLD( bge 13b ) - ldmfd sp!, {r5 - r9} + ldmfd sp!, {r5, r6, r8 - r10} 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 ) @@ -246,6 +251,7 @@ 18: forward_copy_shift pull=24 push=8 + UNWIND( .fnend ) /* * Abort preamble and completion macros. @@ -255,13 +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 d066df686e17..fac49e57cc0b 100644 --- a/arch/arm/lib/copy_to_user.S +++ b/arch/arm/lib/copy_to_user.S @@ -1,22 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/copy_to_user.S * * Author: Nicolas Pitre * Created: Sep 29, 2005 * Copyright: MontaVista Software, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/unwind.h> /* * Prototype: * - * size_t __copy_to_user(void *to, const void *from, size_t n) + * size_t arm_copy_to_user(void *to, const void *from, size_t n) * * Purpose: * @@ -34,11 +32,6 @@ */ #define LDR1W_SHIFT 0 -#ifndef CONFIG_THUMB2_KERNEL -#define STR1W_SHIFT 0 -#else -#define STR1W_SHIFT 1 -#endif .macro ldr1w ptr reg abort W(ldr) \reg, [\ptr], #4 @@ -53,9 +46,17 @@ .endm .macro ldr1b ptr reg cond=al abort - ldr\cond\()b \reg, [\ptr], #1 + ldrb\cond \reg, [\ptr], #1 .endm +#ifdef CONFIG_CPU_USE_DOMAINS + +#ifndef CONFIG_THUMB2_KERNEL +#define STR1W_SHIFT 0 +#else +#define STR1W_SHIFT 1 +#endif + .macro str1w ptr reg abort strusr \reg, \ptr, 4, abort=\abort .endm @@ -71,31 +72,50 @@ str1w \ptr, \reg8, \abort .endm +#else + +#define STR1W_SHIFT 0 + + .macro str1w ptr reg abort + USERL(\abort, W(str) \reg, [\ptr], #4) + .endm + + .macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + USERL(\abort, stmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8}) + .endm + +#endif /* CONFIG_CPU_USE_DOMAINS */ + .macro str1b ptr reg cond=al abort strusr \reg, \ptr, 1, \cond, abort=\abort .endm - .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 exit reg1 reg2 + .macro exit regs:vararg add sp, sp, #8 - ldmfd sp!, {r0, \reg1, \reg2} + ldmfd sp!, {r0, \regs} .endm .text ENTRY(__copy_to_user_std) -WEAK(__copy_to_user) +WEAK(arm_copy_to_user) +#ifdef CONFIG_CPU_SPECTRE + ldr r3, =TASK_SIZE + uaccess_mask_range_ptr r0, r2, r3, ip +#endif #include "copy_template.S" -ENDPROC(__copy_to_user) +ENDPROC(arm_copy_to_user) ENDPROC(__copy_to_user_std) - .pushsection .fixup,"ax" + .pushsection .text.fixup,"ax" .align 0 copy_abort_preamble ldmfd sp!, {r1, r2, r3} @@ -103,4 +123,3 @@ ENDPROC(__copy_to_user_std) rsb r0, r0, r2 copy_abort_end .popsection - diff --git a/arch/arm/lib/csumipv6.S b/arch/arm/lib/csumipv6.S index 3ac6ef01bc43..3559d515144c 100644 --- a/arch/arm/lib/csumipv6.S +++ b/arch/arm/lib/csumipv6.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/csumipv6.S * * Copyright (C) 1995-1998 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S index 31d3cb34740d..87c9471be8b6 100644 --- a/arch/arm/lib/csumpartial.S +++ b/arch/arm/lib/csumpartial.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/csumpartial.S * * Copyright (C) 1995-1998 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -40,9 +37,9 @@ td3 .req lr /* we must have at least one byte. */ tst buf, #1 @ odd address? movne sum, sum, ror #8 - ldrneb td0, [buf], #1 + ldrbne td0, [buf], #1 subne len, len, #1 - adcnes sum, sum, td0, put_byte_1 + adcsne sum, sum, td0, put_byte_1 .Lless4: tst len, #6 beq .Lless8_byte @@ -68,8 +65,8 @@ td3 .req lr bne .Lless8_wordlp .Lless8_byte: tst len, #1 @ odd number of bytes - ldrneb td0, [buf], #1 @ include last byte - adcnes sum, sum, td0, put_byte_0 @ update checksum + ldrbne td0, [buf], #1 @ include last byte + adcsne sum, sum, td0, put_byte_0 @ update checksum .Ldone: adc r0, sum, #0 @ collect up the last carry ldr td0, [sp], #4 @@ -78,17 +75,17 @@ td3 .req lr ldr pc, [sp], #4 @ return .Lnot_aligned: tst buf, #1 @ odd address - ldrneb td0, [buf], #1 @ make even + ldrbne td0, [buf], #1 @ make even subne len, len, #1 - adcnes sum, sum, td0, put_byte_1 @ update checksum + adcsne sum, sum, td0, put_byte_1 @ update checksum tst buf, #2 @ 32-bit aligned? #if __LINUX_ARM_ARCH__ >= 4 - ldrneh td0, [buf], #2 @ make 32-bit aligned + ldrhne td0, [buf], #2 @ make 32-bit aligned subne len, len, #2 #else - ldrneb td0, [buf], #1 - ldrneb ip, [buf], #1 + ldrbne td0, [buf], #1 + ldrbne ip, [buf], #1 subne len, len, #2 #ifndef __ARMEB__ orrne td0, td0, ip, lsl #8 @@ -96,8 +93,8 @@ td3 .req lr orrne td0, ip, td0, lsl #8 #endif #endif - adcnes sum, sum, td0 @ update checksum - mov pc, lr + adcsne sum, sum, td0 @ update checksum + ret lr ENTRY(csum_partial) stmfd sp!, {buf, lr} diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S index d03fc71fc88c..1ca6aadd649c 100644 --- a/arch/arm/lib/csumpartialcopy.S +++ b/arch/arm/lib/csumpartialcopy.S @@ -1,19 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/csumpartialcopy.S * * Copyright (C) 1995-1998 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> .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 d620a5f22a09..0fd5c10e90a7 100644 --- a/arch/arm/lib/csumpartialcopygeneric.S +++ b/arch/arm/lib/csumpartialcopygeneric.S @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/csumpartialcopygeneric.S * * Copyright (C) 1995-2001 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ +#include <asm/assembler.h> /* * unsigned int @@ -40,7 +38,7 @@ sum .req r3 adcs sum, sum, ip, put_byte_1 @ update checksum strb ip, [dst], #1 tst dst, #2 - moveq pc, lr @ dst is now 32bit aligned + reteq lr @ dst is now 32bit aligned .Ldst_16bit: load2b r8, ip sub len, len, #2 @@ -48,7 +46,7 @@ sum .req r3 strb r8, [dst], #1 adcs sum, sum, ip, put_byte_1 strb ip, [dst], #1 - mov pc, lr @ dst is now 32bit aligned + ret lr @ dst is now 32bit aligned /* * Handle 0 to 7 bytes, with any alignment of source and @@ -88,6 +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. @@ -141,15 +140,15 @@ 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 mov r5, r4, get_byte_2 .Lexit: tst len, #1 - strneb r5, [dst], #1 + strbne r5, [dst], #1 andne r5, r5, #255 - adcnes sum, sum, r5, put_byte_0 + adcsne sum, sum, r5, put_byte_0 /* * If the dst pointer was not 16-bit aligned, we @@ -171,23 +170,23 @@ 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 +195,50 @@ 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 +247,20 @@ 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 +275,24 @@ 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 +301,20 @@ 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 +325,7 @@ 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/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S index 7d08b43d2c0e..c289bde04743 100644 --- a/arch/arm/lib/csumpartialcopyuser.S +++ b/arch/arm/lib/csumpartialcopyuser.S @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/csumpartialcopyuser.S * * Copyright (C) 1995-1998 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * 27/03/03 Ian Molton Clean up CONFIG_CPU - * */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -17,6 +13,36 @@ .text +#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} + uaccess_enable ip + .endm + + .macro load_regs + ldmfd sp!, {r1, r2, r4 - r8, ip, lr} + 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 @@ -25,6 +51,8 @@ ldmfd sp!, {r1, r2, r4 - r8, pc} .endm +#endif + .macro load1b, reg1 ldrusr \reg1, r0, 1 .endm @@ -52,9 +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) @@ -63,21 +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 .fixup,"ax" + .pushsection .text.fixup,"ax" .align 4 -9001: mov r4, #-EFAULT - ldr r5, [sp, #8*4] @ *err_ptr - str r4, [r5] - ldmia sp, {r1, r2} @ retrieve dst, len - add r2, r2, r1 - mov r0, #0 @ zero the buffer -9002: teq r2, r1 - strneb 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 36b668d8e121..33b08ca1c242 100644 --- a/arch/arm/lib/delay-loop.S +++ b/arch/arm/lib/delay-loop.S @@ -1,67 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/delay.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. */ #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 .LC1: .word UDELAY_MULT /* + * loops = r0 * HZ * loops_per_jiffy / 1000000 + * * r0 <= 2000 - * lpj <= 0x01ffffff (max. 3355 bogomips) * HZ <= 1000 */ -ENTRY(__loop_udelay) +SYM_TYPED_FUNC_START(__loop_udelay) ldr r2, .LC1 - mul r0, r2, r0 -ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0x7fffff06 - mov r1, #-1 + mul r0, r2, r0 @ r0 = delay_us * UDELAY_MULT + 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] @ max = 0x01ffffff - add r0, r0, r1, lsr #32-14 - mov r0, r0, lsr #14 @ max = 0x0001ffff - add r2, r2, r1, lsr #32-10 - mov r2, r2, lsr #10 @ max = 0x00007fff - mul r0, r2, r0 @ max = 2^32-1 - add r0, r0, r1, lsr #32-6 - movs r0, r0, lsr #6 - moveq pc, lr + 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) -/* - * loops = r0 * HZ * loops_per_jiffy / 1000000 - */ + .align 3 @ Delay routine -ENTRY(__loop_delay) +SYM_TYPED_FUNC_START(__loop_delay) subs r0, r0, #1 #if 0 - movls pc, lr + retls lr subs r0, r0, #1 - movls pc, lr + retls lr subs r0, r0, #1 - movls pc, lr + retls lr subs r0, r0, #1 - movls pc, lr + retls lr subs r0, r0, #1 - movls pc, lr + retls lr subs r0, r0, #1 - movls pc, lr + retls lr subs r0, r0, #1 - movls pc, lr + retls lr subs r0, r0, #1 #endif bhi __loop_delay - mov pc, lr -ENDPROC(__loop_udelay) -ENDPROC(__loop_const_udelay) -ENDPROC(__loop_delay) + ret lr +SYM_FUNC_END(__loop_delay) diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c index 64dbfa57204a..b7fe84f68bf1 100644 --- a/arch/arm/lib/delay.c +++ b/arch/arm/lib/delay.c @@ -1,24 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Delay loops based on the OpenRISC implementation. * * Copyright (C) 2012 ARM Limited * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * Author: Will Deacon <will.deacon@arm.com> */ +#include <linux/clocksource.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/kernel.h> @@ -28,7 +17,7 @@ /* * Default to the loop-based delay implementation. */ -struct arm_delay_ops arm_delay_ops = { +struct arm_delay_ops arm_delay_ops __ro_after_init = { .delay = __loop_delay, .const_udelay = __loop_const_udelay, .udelay = __loop_udelay, @@ -36,6 +25,7 @@ struct arm_delay_ops arm_delay_ops = { static const struct delay_timer *delay_timer; static bool delay_calibrated; +static u64 delay_res; int read_current_timer(unsigned long *timer_val) { @@ -47,6 +37,11 @@ int read_current_timer(unsigned long *timer_val) } EXPORT_SYMBOL_GPL(read_current_timer); +static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) +{ + return (cyc * mult) >> shift; +} + static void __timer_delay(unsigned long cycles) { cycles_t start = get_cycles(); @@ -69,25 +64,42 @@ static void __timer_udelay(unsigned long usecs) void __init register_current_timer_delay(const struct delay_timer *timer) { - if (!delay_calibrated) { - pr_info("Switching to timer-based delay loop\n"); + u32 new_mult, new_shift; + u64 res; + + clocks_calc_mult_shift(&new_mult, &new_shift, timer->freq, + NSEC_PER_SEC, 3600); + res = cyc_to_ns(1ULL, new_mult, new_shift); + + if (res > 1000) { + pr_err("Ignoring delay timer %ps, which has insufficient resolution of %lluns\n", + timer, res); + return; + } + + if (!delay_calibrated && (!delay_res || (res < delay_res))) { + pr_info("Switching to timer-based delay loop, resolution %lluns\n", res); delay_timer = timer; lpj_fine = timer->freq / HZ; + delay_res = res; /* 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; } + +void calibration_delay_done(void) +{ + delay_calibrated = true; +} diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S index e55c4842c290..a87c02925ffa 100644 --- a/arch/arm/lib/div64.S +++ b/arch/arm/lib/div64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/div64.S * @@ -6,13 +7,10 @@ * Author: Nicolas Pitre * Created: Oct 5, 2003 * Copyright: Monta Vista Software, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> +#include <asm/assembler.h> #include <asm/unwind.h> #ifdef __ARMEB__ @@ -87,8 +85,8 @@ UNWIND(.fnstart) @ Break out early if dividend reaches 0. 2: cmp xh, yl orrcs yh, yh, ip - subcss xh, xh, yl - movnes ip, ip, lsr #1 + subscs xh, xh, yl + movsne ip, ip, lsr #1 mov yl, yl, lsr #1 bne 2b @@ -97,7 +95,7 @@ UNWIND(.fnstart) mov yl, #0 cmpeq xl, r4 movlo xh, xl - movlo pc, lr + retlo lr @ The division loop for lower bit positions. @ Here we shift remainer bits leftwards rather than moving the @@ -111,14 +109,14 @@ UNWIND(.fnstart) subcs xh, xh, r4 movs ip, ip, lsr #1 bne 4b - mov pc, lr + ret lr @ The top part of remainder became zero. If carry is set @ (the 33th bit) this is a false positive so resume the loop. @ Otherwise, if lower part is also null then we are done. 6: bcs 5b cmp xl, #0 - moveq pc, lr + reteq lr @ We still have remainer bits in the low part. Bring them up. @@ -144,7 +142,7 @@ UNWIND(.fnstart) movs ip, ip, lsr #1 mov xh, #1 bne 4b - mov pc, lr + ret lr 8: @ Division by a power of 2: determine what that divisor order is @ then simply shift values around @@ -184,13 +182,13 @@ UNWIND(.fnstart) THUMB( orr yl, yl, xh ) mov xh, xl, lsl ip mov xh, xh, lsr ip - mov pc, lr + ret lr @ eq -> division by 1: obvious enough... 9: moveq yl, xl moveq yh, xh moveq xh, #0 - moveq pc, lr + reteq lr UNWIND(.fnend) UNWIND(.fnstart) diff --git a/arch/arm/lib/ecard.S b/arch/arm/lib/ecard.S deleted file mode 100644 index e6057fa851bb..000000000000 --- a/arch/arm/lib/ecard.S +++ /dev/null @@ -1,44 +0,0 @@ -/* - * linux/arch/arm/lib/ecard.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. - * - * 27/03/03 Ian Molton Clean up CONFIG_CPU - * - */ -#include <linux/linkage.h> -#include <asm/assembler.h> - -#define CPSR2SPSR(rt) \ - mrs rt, cpsr; \ - msr spsr_cxsf, rt - -@ Purpose: call an expansion card loader to read bytes. -@ Proto : char read_loader(int offset, char *card_base, char *loader); -@ Returns: byte read - -ENTRY(ecard_loader_read) - stmfd sp!, {r4 - r12, lr} - mov r11, r1 - mov r1, r0 - CPSR2SPSR(r0) - mov lr, pc - mov pc, r2 - ldmfd sp!, {r4 - r12, pc} - -@ Purpose: call an expansion card loader to reset the card -@ Proto : void read_loader(int card_base, char *loader); -@ Returns: byte read - -ENTRY(ecard_loader_reset) - stmfd sp!, {r4 - r12, lr} - mov r11, r0 - CPSR2SPSR(r0) - mov lr, pc - add pc, r1, #8 - ldmfd sp!, {r4 - r12, pc} - 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 64f6bc1a9132..b7ac2d3c0748 100644 --- a/arch/arm/lib/findbit.S +++ b/arch/arm/lib/findbit.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/findbit.S * * Copyright (C) 1995-2000 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * 16th March 2001 - John Ripley <jripley@sonicblue.com> * Fixed so that "size" is an exclusive not an inclusive quantity. * All users of these functions expect exclusive sizes, and may @@ -15,182 +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 - mov pc, 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 - mov pc, lr -ENDPROC(_find_first_bit_le) +3: mov r0, r1 @ no more bits + ret lr + 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 - mov pc, 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 - mov pc, 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 - mov pc, lr - + ret lr + UNWIND( .fnend) diff --git a/arch/arm/lib/floppydma.S b/arch/arm/lib/floppydma.S deleted file mode 100644 index 617150b1baef..000000000000 --- a/arch/arm/lib/floppydma.S +++ /dev/null @@ -1,32 +0,0 @@ -/* - * linux/arch/arm/lib/floppydma.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. - */ -#include <linux/linkage.h> -#include <asm/assembler.h> - .text - - .global floppy_fiqin_end -ENTRY(floppy_fiqin_start) - subs r9, r9, #1 - ldrgtb r12, [r11, #-4] - ldrleb r12, [r11], #0 - strb r12, [r10], #1 - subs pc, lr, #4 -floppy_fiqin_end: - - .global floppy_fiqout_end -ENTRY(floppy_fiqout_start) - subs r9, r9, #1 - ldrgeb r12, [r10], #1 - movlt r12, #0 - strleb r12, [r11], #0 - subles pc, lr, #4 - strb r12, [r11, #-4] - subs pc, lr, #4 -floppy_fiqout_end: diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 9b06bb41fca6..c5e420750c48 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/getuser.S * * Copyright (C) 2001 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. - * * Idea from x86 version, (C) Copyright 1998 Linus Torvalds * * These functions have a non-standard call interface to make them more @@ -18,7 +15,7 @@ * Inputs: r0 contains the address * r1 contains the address limit, which must be preserved * Outputs: r0 is the error code - * r2 contains the zero-extended value + * r2, r3 contains the zero-extended value * lr corrupted * * No other registers must be altered. (see <asm/uaccess.h> @@ -36,11 +33,18 @@ ENTRY(__get_user_1) check_uaccess r0, 1, r1, r2, __get_user_bad 1: TUSER(ldrb) r2, [r0] mov r0, #0 - mov pc, lr + ret lr ENDPROC(__get_user_1) +_ASM_NOKPROBE(__get_user_1) ENTRY(__get_user_2) check_uaccess r0, 2, r1, r2, __get_user_bad +#if __LINUX_ARM_ARCH__ >= 6 + +2: TUSER(ldrh) r2, [r0] + +#else + #ifdef CONFIG_CPU_USE_DOMAINS rb .req ip 2: ldrbt r2, [r0], #1 @@ -55,26 +59,109 @@ rb .req r0 #else orr r2, rb, r2, lsl #8 #endif + +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + mov r0, #0 - mov pc, lr + ret lr ENDPROC(__get_user_2) +_ASM_NOKPROBE(__get_user_2) ENTRY(__get_user_4) check_uaccess r0, 4, r1, r2, __get_user_bad 4: TUSER(ldr) r2, [r0] mov r0, #0 - mov pc, lr + ret lr ENDPROC(__get_user_4) +_ASM_NOKPROBE(__get_user_4) + +ENTRY(__get_user_8) + check_uaccess r0, 8, r1, r2, __get_user_bad8 +#ifdef CONFIG_THUMB2_KERNEL +5: TUSER(ldr) r2, [r0] +6: TUSER(ldr) r3, [r0, #4] +#else +5: TUSER(ldr) r2, [r0], #4 +6: TUSER(ldr) r3, [r0] +#endif + mov r0, #0 + ret lr +ENDPROC(__get_user_8) +_ASM_NOKPROBE(__get_user_8) + +#ifdef __ARMEB__ +ENTRY(__get_user_32t_8) + check_uaccess r0, 8, r1, r2, __get_user_bad +#ifdef CONFIG_CPU_USE_DOMAINS + add r0, r0, #4 +7: ldrt r2, [r0] +#else +7: ldr r2, [r0, #4] +#endif + mov r0, #0 + ret lr +ENDPROC(__get_user_32t_8) +_ASM_NOKPROBE(__get_user_32t_8) + +ENTRY(__get_user_64t_1) + check_uaccess r0, 1, r1, r2, __get_user_bad8 +8: TUSER(ldrb) r3, [r0] + mov r0, #0 + ret lr +ENDPROC(__get_user_64t_1) +_ASM_NOKPROBE(__get_user_64t_1) +ENTRY(__get_user_64t_2) + check_uaccess r0, 2, r1, r2, __get_user_bad8 +#ifdef CONFIG_CPU_USE_DOMAINS +rb .req ip +9: ldrbt r3, [r0], #1 +10: ldrbt rb, [r0], #0 +#else +rb .req r0 +9: ldrb r3, [r0] +10: ldrb rb, [r0, #1] +#endif + orr r3, rb, r3, lsl #8 + mov r0, #0 + ret lr +ENDPROC(__get_user_64t_2) +_ASM_NOKPROBE(__get_user_64t_2) + +ENTRY(__get_user_64t_4) + check_uaccess r0, 4, r1, r2, __get_user_bad8 +11: TUSER(ldr) r3, [r0] + mov r0, #0 + ret lr +ENDPROC(__get_user_64t_4) +_ASM_NOKPROBE(__get_user_64t_4) +#endif + +__get_user_bad8: + mov r3, #0 __get_user_bad: mov r2, #0 mov r0, #-EFAULT - mov pc, lr + ret lr ENDPROC(__get_user_bad) +ENDPROC(__get_user_bad8) +_ASM_NOKPROBE(__get_user_bad) +_ASM_NOKPROBE(__get_user_bad8) .pushsection __ex_table, "a" .long 1b, __get_user_bad .long 2b, __get_user_bad +#if __LINUX_ARM_ARCH__ < 6 .long 3b, __get_user_bad +#endif .long 4b, __get_user_bad + .long 5b, __get_user_bad8 + .long 6b, __get_user_bad8 +#ifdef __ARMEB__ + .long 7b, __get_user_bad + .long 8b, __get_user_bad8 + .long 9b, __get_user_bad8 + .long 10b, __get_user_bad8 + .long 11b, __get_user_bad8 +#endif .popsection diff --git a/arch/arm/lib/io-acorn.S b/arch/arm/lib/io-acorn.S deleted file mode 100644 index 69719bad674d..000000000000 --- a/arch/arm/lib/io-acorn.S +++ /dev/null @@ -1,32 +0,0 @@ -/* - * linux/arch/arm/lib/io-acorn.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. - * - * 27/03/03 Ian Molton Clean up CONFIG_CPU - * - */ -#include <linux/linkage.h> -#include <linux/kern_levels.h> -#include <asm/assembler.h> - - .text - .align - -.Liosl_warning: - .ascii KERN_WARNING "insl/outsl not implemented, called from %08lX\0" - .align - -/* - * These make no sense on Acorn machines. - * Print a warning message. - */ -ENTRY(insl) -ENTRY(outsl) - adr r0, .Liosl_warning - mov r1, lr - b printk diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S index 9f4238987fe9..0def9388fb15 100644 --- a/arch/arm/lib/io-readsb.S +++ b/arch/arm/lib/io-readsb.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-readsb.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -16,16 +13,16 @@ cmp ip, #2 ldrb r3, [r0] strb r3, [r1], #1 - ldrgeb r3, [r0] - strgeb r3, [r1], #1 - ldrgtb r3, [r0] - strgtb r3, [r1], #1 + ldrbge r3, [r0] + strbge r3, [r1], #1 + ldrbgt r3, [r0] + strbgt r3, [r1], #1 subs r2, r2, ip bne .Linsb_aligned ENTRY(__raw_readsb) teq r2, #0 @ do we have to check for the zero len? - moveq pc, lr + reteq lr ands ip, r1, #3 bne .Linsb_align @@ -72,7 +69,7 @@ ENTRY(__raw_readsb) bpl .Linsb_16_lp tst r2, #15 - ldmeqfd sp!, {r4 - r6, pc} + ldmfdeq sp!, {r4 - r6, pc} .Linsb_no_16: tst r2, #8 beq .Linsb_no_8 @@ -109,15 +106,15 @@ ENTRY(__raw_readsb) str r3, [r1], #4 .Linsb_no_4: ands r2, r2, #3 - ldmeqfd sp!, {r4 - r6, pc} + ldmfdeq sp!, {r4 - r6, pc} cmp r2, #2 ldrb r3, [r0] strb r3, [r1], #1 - ldrgeb r3, [r0] - strgeb r3, [r1], #1 - ldrgtb r3, [r0] - strgtb r3, [r1] + ldrbge r3, [r0] + strbge r3, [r1], #1 + ldrbgt r3, [r0] + strbgt r3, [r1] ldmfd sp!, {r4 - r6, pc} ENDPROC(__raw_readsb) diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S index 5fb97e7f9f4b..d9f6b372b058 100644 --- a/arch/arm/lib/io-readsl.S +++ b/arch/arm/lib/io-readsl.S @@ -1,18 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-readsl.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> ENTRY(__raw_readsl) teq r2, #0 @ do we have to check for the zero len? - moveq pc, lr + reteq lr ands ip, r1, #3 bne 3f @@ -30,10 +27,10 @@ ENTRY(__raw_readsl) 2: movs r2, r2, lsl #31 ldrcs r3, [r0, #0] ldrcs ip, [r0, #0] - stmcsia r1!, {r3, ip} + stmiacs r1!, {r3, ip} ldrne r3, [r0, #0] strne r3, [r1, #0] - mov pc, lr + ret lr 3: ldr r3, [r0] cmp ip, #2 @@ -47,25 +44,25 @@ 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 @@ -75,5 +72,5 @@ ENTRY(__raw_readsl) strb r3, [r1, #1] 8: mov r3, ip, get_byte_0 strb r3, [r1, #0] - mov pc, lr + ret lr ENDPROC(__raw_readsl) diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S index 88487c8c4f23..266043610c0c 100644 --- a/arch/arm/lib/io-readsw-armv3.S +++ b/arch/arm/lib/io-readsw-armv3.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-readsw-armv3.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -27,11 +24,11 @@ strb r3, [r1], #1 subs r2, r2, #1 - moveq pc, lr + reteq lr ENTRY(__raw_readsw) teq r2, #0 @ do we have to check for the zero len? - moveq pc, lr + reteq lr tst r1, #3 bne .Linsw_align @@ -68,7 +65,7 @@ ENTRY(__raw_readsw) bpl .Linsw_8_lp tst r2, #7 - ldmeqfd sp!, {r4, r5, r6, pc} + ldmfdeq sp!, {r4, r5, r6, pc} .Lno_insw_8: tst r2, #4 beq .Lno_insw_4 @@ -97,9 +94,9 @@ ENTRY(__raw_readsw) .Lno_insw_2: tst r2, #1 ldrne r3, [r0] - strneb r3, [r1], #1 + strbne r3, [r1], #1 movne r3, r3, lsr #8 - strneb r3, [r1] + strbne r3, [r1] ldmfd sp!, {r4, r5, r6, pc} diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S index 1f393d42593d..228c176a94d1 100644 --- a/arch/arm/lib/io-readsw-armv4.S +++ b/arch/arm/lib/io-readsw-armv4.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-readsw-armv4.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -26,7 +23,7 @@ ENTRY(__raw_readsw) teq r2, #0 - moveq pc, lr + reteq lr tst r1, #3 bne .Linsw_align @@ -76,8 +73,8 @@ ENTRY(__raw_readsw) pack r3, r3, ip str r3, [r1], #4 -.Lno_insw_2: ldrneh r3, [r0] - strneh r3, [r1] +.Lno_insw_2: ldrhne r3, [r0] + strhne r3, [r1] ldmfd sp!, {r4, r5, pc} @@ -94,7 +91,7 @@ ENTRY(__raw_readsw) #endif .Linsw_noalign: stmfd sp!, {r4, lr} - ldrccb ip, [r1, #-1]! + ldrbcc ip, [r1, #-1]! bcc 1f ldrh ip, [r0] @@ -121,11 +118,11 @@ ENTRY(__raw_readsw) 3: tst r2, #1 strb ip, [r1], #1 - ldrneh ip, [r0] + ldrhne ip, [r0] _BE_ONLY_( movne ip, ip, ror #8 ) - strneb ip, [r1], #1 + strbne ip, [r1], #1 _LE_ONLY_( movne ip, ip, lsr #8 ) _BE_ONLY_( movne ip, ip, lsr #24 ) - strneb ip, [r1] + strbne ip, [r1] ldmfd sp!, {r4, pc} ENDPROC(__raw_readsw) diff --git a/arch/arm/lib/io-shark.c b/arch/arm/lib/io-shark.c deleted file mode 100644 index 824253948f51..000000000000 --- 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-writesb.S b/arch/arm/lib/io-writesb.S index 68b92f4acaeb..e2ae312f0b69 100644 --- a/arch/arm/lib/io-writesb.S +++ b/arch/arm/lib/io-writesb.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-writesb.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -36,16 +33,16 @@ cmp ip, #2 ldrb r3, [r1], #1 strb r3, [r0] - ldrgeb r3, [r1], #1 - strgeb r3, [r0] - ldrgtb r3, [r1], #1 - strgtb r3, [r0] + ldrbge r3, [r1], #1 + strbge r3, [r0] + ldrbgt r3, [r1], #1 + strbgt r3, [r0] subs r2, r2, ip bne .Loutsb_aligned ENTRY(__raw_writesb) teq r2, #0 @ do we have to check for the zero len? - moveq pc, lr + reteq lr ands ip, r1, #3 bne .Loutsb_align @@ -64,7 +61,7 @@ ENTRY(__raw_writesb) bpl .Loutsb_16_lp tst r2, #15 - ldmeqfd sp!, {r4, r5, pc} + ldmfdeq sp!, {r4, r5, pc} .Loutsb_no_16: tst r2, #8 beq .Loutsb_no_8 @@ -80,15 +77,15 @@ ENTRY(__raw_writesb) outword r3 .Loutsb_no_4: ands r2, r2, #3 - ldmeqfd sp!, {r4, r5, pc} + ldmfdeq sp!, {r4, r5, pc} cmp r2, #2 ldrb r3, [r1], #1 strb r3, [r0] - ldrgeb r3, [r1], #1 - strgeb r3, [r0] - ldrgtb r3, [r1] - strgtb r3, [r0] + ldrbge r3, [r1], #1 + strbge r3, [r0] + ldrbgt r3, [r1] + strbgt r3, [r0] ldmfd sp!, {r4, r5, pc} ENDPROC(__raw_writesb) diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S index 8d3b7813725c..89ef7be61421 100644 --- a/arch/arm/lib/io-writesl.S +++ b/arch/arm/lib/io-writesl.S @@ -1,18 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-writesl.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> ENTRY(__raw_writesl) teq r2, #0 @ do we have to check for the zero len? - moveq pc, lr + reteq lr ands ip, r1, #3 bne 3f @@ -28,12 +25,12 @@ ENTRY(__raw_writesl) bpl 1b ldmfd sp!, {r4, lr} 2: movs r2, r2, lsl #31 - ldmcsia r1!, {r3, ip} + ldmiacs r1!, {r3, ip} strcs r3, [r0, #0] ldrne r3, [r1, #0] strcs ip, [r0, #0] strne r3, [r0, #0] - mov pc, lr + ret lr 3: bic r1, r1, #3 ldr r3, [r1], #4 @@ -41,27 +38,27 @@ 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 + ret 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 + ret 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 + ret lr ENDPROC(__raw_writesl) diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S index 49b800419e32..4cabbee7f3b8 100644 --- a/arch/arm/lib/io-writesw-armv3.S +++ b/arch/arm/lib/io-writesw-armv3.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-writesw-armv3.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -28,11 +25,11 @@ orr r3, r3, r3, lsl #16 str r3, [r0] subs r2, r2, #1 - moveq pc, lr + reteq lr ENTRY(__raw_writesw) teq r2, #0 @ do we have to check for the zero len? - moveq pc, lr + reteq lr tst r1, #3 bne .Loutsw_align @@ -79,7 +76,7 @@ ENTRY(__raw_writesw) bpl .Loutsw_8_lp tst r2, #7 - ldmeqfd sp!, {r4, r5, r6, pc} + ldmfdeq sp!, {r4, r5, r6, pc} .Lno_outsw_8: tst r2, #4 beq .Lno_outsw_4 diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S index ff4f71b579ee..12eec53266c7 100644 --- a/arch/arm/lib/io-writesw-armv4.S +++ b/arch/arm/lib/io-writesw-armv4.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/io-writesw-armv4.S * * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -31,7 +28,7 @@ ENTRY(__raw_writesw) teq r2, #0 - moveq pc, lr + reteq lr ands r3, r1, #3 bne .Loutsw_align @@ -61,8 +58,8 @@ ENTRY(__raw_writesw) ldr r3, [r1], #4 outword r3 -.Lno_outsw_2: ldrneh r3, [r1] - strneh r3, [r0] +.Lno_outsw_2: ldrhne r3, [r1] + strhne r3, [r0] ldmfd sp!, {r4, r5, pc} @@ -95,6 +92,6 @@ ENTRY(__raw_writesw) tst r2, #1 3: movne ip, r3, lsr #8 - strneh ip, [r0] - mov pc, lr + strhne ip, [r0] + ret lr ENDPROC(__raw_writesw) diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S index c562f649734c..c23f9d9e2970 100644 --- a/arch/arm/lib/lib1funcs.S +++ b/arch/arm/lib/lib1funcs.S @@ -96,7 +96,7 @@ Boston, MA 02111-1307, USA. */ subhs \dividend, \dividend, \divisor, lsr #3 orrhs \result, \result, \curbit, lsr #3 cmp \dividend, #0 @ Early termination? - movnes \curbit, \curbit, lsr #4 @ No, any more bits to do? + movsne \curbit, \curbit, lsr #4 @ No, any more bits to do? movne \divisor, \divisor, lsr #4 bne 1b @@ -167,7 +167,7 @@ Boston, MA 02111-1307, USA. */ #endif - @ Perform all needed substractions to keep only the reminder. + @ Perform all needed subtractions to keep only the reminder. @ Do comparisons in batch of 4 first. subs \order, \order, #3 @ yes, 3 is intended here blt 2f @@ -182,14 +182,14 @@ Boston, MA 02111-1307, USA. */ subhs \dividend, \dividend, \divisor, lsr #3 cmp \dividend, #1 mov \divisor, \divisor, lsr #4 - subges \order, \order, #4 + subsge \order, \order, #4 bge 1b tst \order, #3 teqne \dividend, #0 beq 5f - @ Either 1, 2 or 3 comparison/substractions are left. + @ Either 1, 2 or 3 comparison/subtractions are left. 2: cmn \order, #2 blt 4f beq 3f @@ -205,12 +205,16 @@ Boston, MA 02111-1307, USA. */ .endm +#ifdef CONFIG_ARM_PATCH_IDIV + .align 3 +#endif + ENTRY(__udivsi3) ENTRY(__aeabi_uidiv) UNWIND(.fnstart) subs r2, r1, #1 - moveq pc, lr + reteq lr bcc Ldiv0 cmp r0, r1 bls 11f @@ -220,16 +224,16 @@ UNWIND(.fnstart) ARM_DIV_BODY r0, r1, r2, r3 mov r0, r2 - mov pc, lr + ret lr 11: moveq r0, #1 movne r0, #0 - mov pc, lr + ret lr 12: ARM_DIV2_ORDER r1, r2 mov r0, r0, lsr r2 - mov pc, lr + ret lr UNWIND(.fnend) ENDPROC(__udivsi3) @@ -244,15 +248,19 @@ UNWIND(.fnstart) moveq r0, #0 tsthi r1, r2 @ see if divisor is power of 2 andeq r0, r0, r2 - movls pc, lr + retls lr ARM_MOD_BODY r0, r1, r2, r3 - mov pc, lr + ret lr UNWIND(.fnend) ENDPROC(__umodsi3) +#ifdef CONFIG_ARM_PATCH_IDIV + .align 3 +#endif + ENTRY(__divsi3) ENTRY(__aeabi_idiv) UNWIND(.fnstart) @@ -274,23 +282,23 @@ UNWIND(.fnstart) cmp ip, #0 rsbmi r0, r0, #0 - mov pc, lr + ret lr 10: teq ip, r0 @ same sign ? rsbmi r0, r0, #0 - mov pc, lr + ret lr 11: movlo r0, #0 moveq r0, ip, asr #31 orreq r0, r0, #1 - mov pc, lr + ret lr 12: ARM_DIV2_ORDER r1, r2 cmp ip, #0 mov r0, r3, lsr r2 rsbmi r0, r0, #0 - mov pc, lr + ret lr UNWIND(.fnend) ENDPROC(__divsi3) @@ -315,7 +323,7 @@ UNWIND(.fnstart) 10: cmp ip, #0 rsbmi r0, r0, #0 - mov pc, lr + ret lr UNWIND(.fnend) ENDPROC(__modsi3) @@ -331,7 +339,7 @@ UNWIND(.save {r0, r1, ip, lr} ) ldmfd sp!, {r1, r2, ip, lr} mul r3, r0, r2 sub r1, r1, r3 - mov pc, lr + ret lr UNWIND(.fnend) ENDPROC(__aeabi_uidivmod) @@ -344,7 +352,7 @@ UNWIND(.save {r0, r1, ip, lr} ) ldmfd sp!, {r1, r2, ip, lr} mul r3, r0, r2 sub r1, r1, r3 - mov pc, lr + ret lr UNWIND(.fnend) ENDPROC(__aeabi_idivmod) diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S index f83d449141f7..922dcd88b02b 100644 --- a/arch/arm/lib/lshrdi3.S +++ b/arch/arm/lib/lshrdi3.S @@ -27,6 +27,7 @@ Boston, MA 02110-1301, USA. */ #include <linux/linkage.h> +#include <asm/assembler.h> #ifdef __ARMEB__ #define al r1 @@ -47,7 +48,7 @@ ENTRY(__aeabi_llsr) THUMB( lslmi r3, ah, ip ) THUMB( orrmi al, al, r3 ) mov ah, ah, lsr r2 - mov pc, lr + ret lr ENDPROC(__lshrdi3) ENDPROC(__aeabi_llsr) diff --git a/arch/arm/lib/memchr.S b/arch/arm/lib/memchr.S index 1da86991d700..95bedafd0330 100644 --- a/arch/arm/lib/memchr.S +++ b/arch/arm/lib/memchr.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/memchr.S * * Copyright (C) 1995-2000 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * ASM optimised string functions */ #include <linux/linkage.h> @@ -22,5 +19,5 @@ ENTRY(memchr) bne 1b sub r0, r0, #1 2: movne r0, #0 - mov pc, lr + ret lr ENDPROC(memchr) diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index a9b9e2287a09..90f2b645aa0d 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -1,17 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/memcpy.S * * Author: Nicolas Pitre * Created: Sep 28, 2005 * Copyright: MontaVista Software, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/unwind.h> #define LDR1W_SHIFT 0 #define STR1W_SHIFT 0 @@ -29,7 +27,7 @@ .endm .macro ldr1b ptr reg cond=al abort - ldr\cond\()b \reg, [\ptr], #1 + ldrb\cond \reg, [\ptr], #1 .endm .macro str1w ptr reg abort @@ -41,23 +39,28 @@ .endm .macro str1b ptr reg cond=al abort - str\cond\()b \reg, [\ptr], #1 + 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 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(__memcpy) +ENTRY(mmiocpy) +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 938fc14f962d..6410554039fd 100644 --- a/arch/arm/lib/memmove.S +++ b/arch/arm/lib/memmove.S @@ -1,17 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/memmove.S * * Author: Nicolas Pitre * Created: Sep 28, 2005 * Copyright: (C) MontaVista Software Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/unwind.h> .text @@ -26,13 +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, 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 @@ -44,11 +49,11 @@ ENTRY(memmove) bne 10f 1: subs r2, r2, #(28) - stmfd sp!, {r5 - r8} + stmfd sp!, {r5, r6, r8, r9} blt 5f CALGN( ands ip, r0, #31 ) - CALGN( sbcnes r4, ip, r2 ) @ C is always set here + CALGN( sbcsne r4, ip, r2 ) @ C is always set here CALGN( bcs 2f ) CALGN( adr r4, 6f ) CALGN( subs r2, r2, ip ) @ C is set here @@ -63,9 +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 ) @@ -79,8 +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 @@ -90,29 +95,29 @@ 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} +7: ldmfd sp!, {r5, r6, r8, r9} 8: movs r2, r2, lsl #31 - ldrneb r3, [r1, #-1]! - ldrcsb r4, [r1, #-1]! - ldrcsb ip, [r1, #-1] - strneb r3, [r0, #-1]! - strcsb r4, [r0, #-1]! - strcsb ip, [r0, #-1] - ldmfd sp!, {r0, r4, pc} + ldrbne r3, [r1, #-1]! + ldrbcs r4, [r1, #-1]! + ldrbcs ip, [r1, #-1] + strbne r3, [r0, #-1]! + strbcs r4, [r0, #-1]! + strbcs ip, [r0, #-1] + ldmfd sp!, {r0, r4, UNWIND(fpreg,) pc} 9: cmp ip, #2 - ldrgtb r3, [r1, #-1]! - ldrgeb r4, [r1, #-1]! + ldrbgt r3, [r1, #-1]! + ldrbge r4, [r1, #-1]! ldrb lr, [r1, #-1]! - strgtb r3, [r0, #-1]! - strgeb r4, [r0, #-1]! + strbgt r3, [r0, #-1]! + strbge r4, [r0, #-1]! subs r2, r2, ip strb lr, [r0, #-1]! blt 8b @@ -132,11 +137,11 @@ ENTRY(memmove) blt 14f CALGN( ands ip, r0, #31 ) - CALGN( sbcnes r4, ip, r2 ) @ C is always set here + CALGN( sbcsne r4, ip, r2 ) @ C is always set here CALGN( subcc r2, r2, ip ) CALGN( bcc 15f ) -11: stmfd sp!, {r5 - r9} +11: stmfd sp!, {r5, r6, r8 - r10} PLD( pld [r1, #-4] ) PLD( subs r2, r2, #96 ) @@ -146,39 +151,39 @@ ENTRY(memmove) PLD( pld [r1, #-96] ) 12: PLD( pld [r1, #-128] ) -13: ldmdb r1!, {r7, r8, r9, ip} - mov lr, r3, push #\push +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, 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 - stmdb r0!, {r4 - r9, ip, lr} + orr lr, lr, ip, lspull #\pull + mov ip, ip, lspush #\push + 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, 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 - r6, r8 - r10, ip, lr} bge 12b PLD( cmn r2, #96 ) PLD( bge 13b ) - ldmfd sp!, {r5 - r9} + ldmfd sp!, {r5, r6, r8 - r10} 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 ) @@ -196,4 +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 94b0650ea98f..de75ae4d5ab4 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -1,21 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/memset.S * * Copyright (C) 1995-2000 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * ASM optimised string functions */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/unwind.h> .text .align 5 -ENTRY(memset) +ENTRY(__memset) +ENTRY(mmioset) +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 @@ -25,34 +27,38 @@ ENTRY(memset) 1: orr r1, r1, r1, lsl #8 orr r1, r1, r1, lsl #16 mov r3, r1 - cmp r2, #16 +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 */ +UNWIND( .fnstart ) +UNWIND( .save {r8, lr} ) stmfd sp!, {r8, lr} mov r8, r1 - mov lr, r1 + mov lr, r3 2: subs r2, r2, #64 - 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} + stmiage ip!, {r1, r3, r8, lr} @ 64 bytes at a time. + stmiage ip!, {r1, r3, r8, lr} + stmiage ip!, {r1, r3, r8, lr} + stmiage ip!, {r1, r3, r8, lr} bgt 2b - ldmeqfd sp!, {r8, pc} @ Now <64 bytes to go. + ldmfdeq 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 ip!, {r1, r3, r8, lr} - stmneia ip!, {r1, r3, r8, lr} + stmiane ip!, {r1, r3, r8, lr} + stmiane ip!, {r1, r3, r8, lr} tst r2, #16 - stmneia ip!, {r1, r3, r8, lr} + stmiane ip!, {r1, r3, r8, lr} ldmfd sp!, {r8, lr} +UNWIND( .fnend ) #else @@ -61,13 +67,15 @@ ENTRY(memset) * whole cache lines at once. */ +UNWIND( .fnstart ) +UNWIND( .save {r4-r8, lr} ) stmfd sp!, {r4-r8, lr} mov r4, r1 - mov r5, r1 + mov r5, r3 mov r6, r1 - mov r7, r1 + mov r7, r3 mov r8, r1 - mov lr, r1 + mov lr, r3 cmp r2, #96 tstgt ip, #31 @@ -77,47 +85,64 @@ ENTRY(memset) rsb r8, r8, #32 sub r2, r2, r8 movs r8, r8, lsl #(32 - 4) - stmcsia ip!, {r4, r5, r6, r7} - stmmiia ip!, {r4, r5} + stmiacs ip!, {r4, r5, r6, r7} + stmiami ip!, {r4, r5} tst r8, #(1 << 30) mov r8, r1 strne r1, [ip], #4 3: subs r2, r2, #64 - stmgeia ip!, {r1, r3-r8, lr} - stmgeia ip!, {r1, r3-r8, lr} + stmiage ip!, {r1, r3-r8, lr} + stmiage ip!, {r1, r3-r8, lr} bgt 3b - ldmeqfd sp!, {r4-r8, pc} + ldmfdeq sp!, {r4-r8, pc} tst r2, #32 - stmneia ip!, {r1, r3-r8, lr} + stmiane ip!, {r1, r3-r8, lr} tst r2, #16 - stmneia ip!, {r4-r7} + stmiane ip!, {r4-r7} ldmfd sp!, {r4-r8, lr} +UNWIND( .fnend ) #endif +UNWIND( .fnstart ) 4: tst r2, #8 - stmneia ip!, {r1, r3} + stmiane ip!, {r1, r3} tst r2, #4 strne r1, [ip], #4 /* - * When we get here, we've got less than 4 bytes to zero. We + * When we get here, we've got less than 4 bytes to set. We * may have an unaligned pointer as well. */ 5: tst r2, #2 - strneb r1, [ip], #1 - strneb r1, [ip], #1 + strbne r1, [ip], #1 + strbne r1, [ip], #1 tst r2, #1 - strneb r1, [ip], #1 - mov pc, lr + strbne r1, [ip], #1 + ret 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 + strblt r1, [ip], #1 @ 1 + strble r1, [ip], #1 @ 1 strb r1, [ip], #1 @ 1 add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) b 1b +UNWIND( .fnend ) ENDPROC(memset) +ENDPROC(mmioset) +ENDPROC(__memset) + +ENTRY(__memset32) +UNWIND( .fnstart ) + mov r3, r1 @ copy r1 to r3 and fall into memset64 +UNWIND( .fnend ) +ENDPROC(__memset32) +ENTRY(__memset64) +UNWIND( .fnstart ) + mov ip, r0 @ preserve r0 as return value + b 7b @ jump into the middle of memset +UNWIND( .fnend ) +ENDPROC(__memset64) diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S deleted file mode 100644 index 3fbdef5f802a..000000000000 --- a/arch/arm/lib/memzero.S +++ /dev/null @@ -1,125 +0,0 @@ -/* - * linux/arch/arm/lib/memzero.S - * - * Copyright (C) 1995-2000 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/linkage.h> -#include <asm/assembler.h> - - .text - .align 5 - .word 0 -/* - * Align the pointer in r0. r3 contains the number of bytes that we are - * mis-aligned by, and r1 is the number of bytes. If r1 < 4, then we - * don't bother; we use byte stores instead. - */ -1: subs r1, r1, #4 @ 1 do we have enough - blt 5f @ 1 bytes to align with? - cmp r3, #2 @ 1 - strltb r2, [r0], #1 @ 1 - strleb r2, [r0], #1 @ 1 - strb r2, [r0], #1 @ 1 - add r1, r1, r3 @ 1 (r1 = r1 - (4 - r3)) -/* - * The pointer is now aligned and the length is adjusted. Try doing the - * memzero again. - */ - -ENTRY(__memzero) - mov r2, #0 @ 1 - ands r3, r0, #3 @ 1 unaligned? - bne 1b @ 1 -/* - * r3 = 0, and we know that the pointer in r0 is aligned to a word boundary. - */ - cmp r1, #16 @ 1 we can skip this chunk if we - blt 4f @ 1 have < 16 bytes - -#if ! CALGN(1)+0 - -/* - * We need an extra register for this loop - save the return address and - * use the LR - */ - str lr, [sp, #-4]! @ 1 - mov ip, r2 @ 1 - mov lr, r2 @ 1 - -3: subs r1, r1, #64 @ 1 write 32 bytes out per loop - stmgeia r0!, {r2, r3, ip, lr} @ 4 - stmgeia r0!, {r2, r3, ip, lr} @ 4 - stmgeia r0!, {r2, r3, ip, lr} @ 4 - stmgeia r0!, {r2, r3, ip, lr} @ 4 - bgt 3b @ 1 - ldmeqfd sp!, {pc} @ 1/2 quick exit -/* - * No need to correct the count; we're only testing bits from now on - */ - tst r1, #32 @ 1 - stmneia r0!, {r2, r3, ip, lr} @ 4 - stmneia r0!, {r2, r3, ip, lr} @ 4 - tst r1, #16 @ 1 16 bytes or more? - stmneia r0!, {r2, r3, ip, lr} @ 4 - ldr lr, [sp], #4 @ 1 - -#else - -/* - * This version aligns the destination pointer in order to write - * whole cache lines at once. - */ - - stmfd sp!, {r4-r7, lr} - mov r4, r2 - mov r5, r2 - mov r6, r2 - mov r7, r2 - mov ip, r2 - mov lr, r2 - - cmp r1, #96 - andgts ip, r0, #31 - ble 3f - - rsb ip, ip, #32 - sub r1, r1, ip - movs ip, ip, lsl #(32 - 4) - stmcsia r0!, {r4, r5, r6, r7} - stmmiia r0!, {r4, r5} - movs ip, ip, lsl #2 - strcs r2, [r0], #4 - -3: subs r1, r1, #64 - stmgeia r0!, {r2-r7, ip, lr} - stmgeia r0!, {r2-r7, ip, lr} - bgt 3b - ldmeqfd sp!, {r4-r7, pc} - - tst r1, #32 - stmneia r0!, {r2-r7, ip, lr} - tst r1, #16 - stmneia r0!, {r4-r7} - ldmfd sp!, {r4-r7, lr} - -#endif - -4: tst r1, #8 @ 1 8 bytes or more? - stmneia r0!, {r2, r3} @ 2 - tst r1, #4 @ 1 4 bytes or more? - strne r2, [r0], #4 @ 1 -/* - * When we get here, we've got less than 4 bytes to zero. We - * may have an unaligned pointer as well. - */ -5: tst r1, #2 @ 1 2 bytes or more? - strneb r2, [r0], #1 @ 1 - strneb r2, [r0], #1 @ 1 - tst r1, #1 @ 1 a byte left over - strneb r2, [r0], #1 @ 1 - mov pc, lr @ 1 -ENDPROC(__memzero) diff --git a/arch/arm/lib/muldi3.S b/arch/arm/lib/muldi3.S index 36c91b4957e2..8362fe6c0de9 100644 --- a/arch/arm/lib/muldi3.S +++ b/arch/arm/lib/muldi3.S @@ -1,16 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/muldi3.S * * Author: Nicolas Pitre * Created: Oct 19, 2005 * Copyright: Monta Vista Software, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> +#include <asm/assembler.h> #ifdef __ARMEB__ #define xh r0 @@ -41,7 +39,7 @@ ENTRY(__aeabi_lmul) adc xh, xh, yh, lsr #16 adds xl, xl, ip, lsl #16 adc xh, xh, ip, lsr #16 - mov pc, lr + ret lr ENDPROC(__muldi3) ENDPROC(__aeabi_lmul) diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S index 3d73dcb959b0..bdd8836dc5c2 100644 --- a/arch/arm/lib/putuser.S +++ b/arch/arm/lib/putuser.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/putuser.S * * Copyright (C) 2001 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. - * * Idea from x86 version, (C) Copyright 1998 Linus Torvalds * * These functions have a non-standard call interface to make @@ -36,21 +33,18 @@ ENTRY(__put_user_1) check_uaccess r0, 1, r1, ip, __put_user_bad 1: TUSER(strb) r2, [r0] mov r0, #0 - mov pc, lr + ret lr ENDPROC(__put_user_1) ENTRY(__put_user_2) check_uaccess r0, 2, r1, ip, __put_user_bad - mov ip, r2, lsr #8 -#ifdef CONFIG_THUMB2_KERNEL -#ifndef __ARMEB__ -2: TUSER(strb) r2, [r0] -3: TUSER(strb) ip, [r0, #1] +#if __LINUX_ARM_ARCH__ >= 6 + +2: TUSER(strh) r2, [r0] + #else -2: TUSER(strb) ip, [r0] -3: TUSER(strb) r2, [r0, #1] -#endif -#else /* !CONFIG_THUMB2_KERNEL */ + + mov ip, r2, lsr #8 #ifndef __ARMEB__ 2: TUSER(strb) r2, [r0], #1 3: TUSER(strb) ip, [r0] @@ -58,16 +52,17 @@ ENTRY(__put_user_2) 2: TUSER(strb) ip, [r0], #1 3: TUSER(strb) r2, [r0] #endif -#endif /* CONFIG_THUMB2_KERNEL */ + +#endif /* __LINUX_ARM_ARCH__ >= 6 */ mov r0, #0 - mov pc, lr + ret lr ENDPROC(__put_user_2) ENTRY(__put_user_4) check_uaccess r0, 4, r1, ip, __put_user_bad 4: TUSER(str) r2, [r0] mov r0, #0 - mov pc, lr + ret lr ENDPROC(__put_user_4) ENTRY(__put_user_8) @@ -80,18 +75,20 @@ ENTRY(__put_user_8) 6: TUSER(str) r3, [r0] #endif mov r0, #0 - mov pc, lr + ret lr ENDPROC(__put_user_8) __put_user_bad: mov r0, #-EFAULT - mov pc, lr + ret lr ENDPROC(__put_user_bad) .pushsection __ex_table, "a" .long 1b, __put_user_bad .long 2b, __put_user_bad +#if __LINUX_ARM_ARCH__ < 6 .long 3b, __put_user_bad +#endif .long 4b, __put_user_bad .long 5b, __put_user_bad .long 6b, __put_user_bad diff --git a/arch/arm/lib/setbit.S b/arch/arm/lib/setbit.S index 618fedae4b37..19a96f43f4bb 100644 --- a/arch/arm/lib/setbit.S +++ b/arch/arm/lib/setbit.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/setbit.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. */ #include <linux/linkage.h> #include <asm/assembler.h> diff --git a/arch/arm/lib/strchr.S b/arch/arm/lib/strchr.S index d8f2a1c1aea4..09e2cc8a8950 100644 --- a/arch/arm/lib/strchr.S +++ b/arch/arm/lib/strchr.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/strchr.S * * Copyright (C) 1995-2000 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * ASM optimised string functions */ #include <linux/linkage.h> @@ -23,5 +20,5 @@ ENTRY(strchr) teq r2, r1 movne r0, #0 subeq r0, r0, #1 - mov pc, lr + ret lr ENDPROC(strchr) diff --git a/arch/arm/lib/strrchr.S b/arch/arm/lib/strrchr.S index 302f20cd2423..5e87247d1e8b 100644 --- a/arch/arm/lib/strrchr.S +++ b/arch/arm/lib/strrchr.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/strrchr.S * * Copyright (C) 1995-2000 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * ASM optimised string functions */ #include <linux/linkage.h> @@ -22,5 +19,5 @@ ENTRY(strrchr) teq r2, #0 bne 1b mov r0, r3 - mov pc, lr + ret lr ENDPROC(strrchr) diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S index 4becdc3a59cb..f13fe9bc2399 100644 --- a/arch/arm/lib/testchangebit.S +++ b/arch/arm/lib/testchangebit.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/testchangebit.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. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -13,3 +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 918841dcce7a..4d2c5ca620eb 100644 --- a/arch/arm/lib/testclearbit.S +++ b/arch/arm/lib/testclearbit.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/testclearbit.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. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -13,3 +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 8d1b2fe9e487..649dbab65d8d 100644 --- a/arch/arm/lib/testsetbit.S +++ b/arch/arm/lib/testsetbit.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/testsetbit.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. */ #include <linux/linkage.h> #include <asm/assembler.h> @@ -13,3 +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.S b/arch/arm/lib/uaccess.S deleted file mode 100644 index 5c908b1cb8ed..000000000000 --- a/arch/arm/lib/uaccess.S +++ /dev/null @@ -1,564 +0,0 @@ -/* - * linux/arch/arm/lib/uaccess.S - * - * Copyright (C) 1995, 1996,1997,1998 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Routines to block copy data to/from user memory - * These are highly optimised both for the 4k page size - * and for various alignments. - */ -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/errno.h> -#include <asm/domain.h> - - .text - -#define PAGE_SHIFT 12 - -/* Prototype: int __copy_to_user(void *to, const char *from, size_t n) - * Purpose : copy a block to user memory from kernel memory - * Params : to - user memory - * : from - kernel memory - * : n - number of bytes to copy - * Returns : Number of bytes NOT copied. - */ - -.Lc2u_dest_not_aligned: - rsb ip, ip, #4 - cmp ip, #2 - ldrb r3, [r1], #1 -USER( TUSER( strb) r3, [r0], #1) @ May fault - ldrgeb r3, [r1], #1 -USER( TUSER( strgeb) r3, [r0], #1) @ May fault - ldrgtb r3, [r1], #1 -USER( TUSER( strgtb) r3, [r0], #1) @ May fault - sub r2, r2, ip - b .Lc2u_dest_aligned - -ENTRY(__copy_to_user) - stmfd sp!, {r2, r4 - r7, lr} - cmp r2, #4 - blt .Lc2u_not_enough - ands ip, r0, #3 - bne .Lc2u_dest_not_aligned -.Lc2u_dest_aligned: - - ands ip, r1, #3 - bne .Lc2u_src_not_aligned -/* - * Seeing as there has to be at least 8 bytes to copy, we can - * copy one word, and force a user-mode page fault... - */ - -.Lc2u_0fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lc2u_0nowords - ldr r3, [r1], #4 -USER( TUSER( str) r3, [r0], #4) @ May fault - mov ip, r0, lsl #32 - PAGE_SHIFT @ On each page, use a ld/st??t instruction - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lc2u_0fupi -/* - * ip = max no. of bytes to copy before needing another "strt" insn - */ - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #32 - blt .Lc2u_0rem8lp - -.Lc2u_0cpy8lp: ldmia r1!, {r3 - r6} - stmia r0!, {r3 - r6} @ Shouldnt fault - ldmia r1!, {r3 - r6} - subs ip, ip, #32 - stmia r0!, {r3 - r6} @ Shouldnt fault - bpl .Lc2u_0cpy8lp - -.Lc2u_0rem8lp: cmn ip, #16 - ldmgeia r1!, {r3 - r6} - stmgeia r0!, {r3 - r6} @ Shouldnt fault - tst ip, #8 - ldmneia r1!, {r3 - r4} - stmneia r0!, {r3 - r4} @ Shouldnt fault - tst ip, #4 - ldrne r3, [r1], #4 - TUSER( strne) r3, [r0], #4 @ Shouldnt fault - ands ip, ip, #3 - beq .Lc2u_0fupi -.Lc2u_0nowords: teq ip, #0 - beq .Lc2u_finished -.Lc2u_nowords: cmp ip, #2 - ldrb r3, [r1], #1 -USER( TUSER( strb) r3, [r0], #1) @ May fault - ldrgeb r3, [r1], #1 -USER( TUSER( strgeb) r3, [r0], #1) @ May fault - ldrgtb r3, [r1], #1 -USER( TUSER( strgtb) r3, [r0], #1) @ May fault - b .Lc2u_finished - -.Lc2u_not_enough: - movs ip, r2 - bne .Lc2u_nowords -.Lc2u_finished: mov r0, #0 - ldmfd sp!, {r2, r4 - r7, pc} - -.Lc2u_src_not_aligned: - bic r1, r1, #3 - ldr r7, [r1], #4 - cmp ip, #2 - bgt .Lc2u_3fupi - beq .Lc2u_2fupi -.Lc2u_1fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lc2u_1nowords - mov r3, r7, pull #8 - ldr r7, [r1], #4 - orr r3, r3, r7, push #24 -USER( TUSER( str) r3, [r0], #4) @ May fault - mov ip, r0, lsl #32 - PAGE_SHIFT - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lc2u_1fupi - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #16 - blt .Lc2u_1rem8lp - -.Lc2u_1cpy8lp: mov r3, r7, pull #8 - ldmia r1!, {r4 - r7} - subs ip, ip, #16 - orr r3, r3, r4, push #24 - mov r4, r4, pull #8 - orr r4, r4, r5, push #24 - mov r5, r5, pull #8 - orr r5, r5, r6, push #24 - mov r6, r6, pull #8 - orr r6, r6, r7, push #24 - stmia r0!, {r3 - r6} @ Shouldnt fault - bpl .Lc2u_1cpy8lp - -.Lc2u_1rem8lp: tst ip, #8 - movne r3, r7, pull #8 - ldmneia r1!, {r4, r7} - orrne r3, r3, r4, push #24 - movne r4, r4, pull #8 - orrne r4, r4, r7, push #24 - stmneia r0!, {r3 - r4} @ Shouldnt fault - tst ip, #4 - movne r3, r7, pull #8 - ldrne r7, [r1], #4 - orrne r3, r3, r7, push #24 - TUSER( strne) r3, [r0], #4 @ Shouldnt fault - ands ip, ip, #3 - beq .Lc2u_1fupi -.Lc2u_1nowords: mov r3, r7, get_byte_1 - teq ip, #0 - beq .Lc2u_finished - cmp ip, #2 -USER( TUSER( strb) r3, [r0], #1) @ May fault - movge r3, r7, get_byte_2 -USER( TUSER( strgeb) r3, [r0], #1) @ May fault - movgt r3, r7, get_byte_3 -USER( TUSER( strgtb) r3, [r0], #1) @ May fault - b .Lc2u_finished - -.Lc2u_2fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lc2u_2nowords - mov r3, r7, pull #16 - ldr r7, [r1], #4 - orr r3, r3, r7, push #16 -USER( TUSER( str) r3, [r0], #4) @ May fault - mov ip, r0, lsl #32 - PAGE_SHIFT - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lc2u_2fupi - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #16 - blt .Lc2u_2rem8lp - -.Lc2u_2cpy8lp: mov r3, r7, pull #16 - ldmia r1!, {r4 - r7} - subs ip, ip, #16 - orr r3, r3, r4, push #16 - mov r4, r4, pull #16 - orr r4, r4, r5, push #16 - mov r5, r5, pull #16 - orr r5, r5, r6, push #16 - mov r6, r6, pull #16 - orr r6, r6, r7, push #16 - stmia r0!, {r3 - r6} @ Shouldnt fault - bpl .Lc2u_2cpy8lp - -.Lc2u_2rem8lp: tst ip, #8 - movne r3, r7, pull #16 - ldmneia r1!, {r4, r7} - orrne r3, r3, r4, push #16 - movne r4, r4, pull #16 - orrne r4, r4, r7, push #16 - stmneia r0!, {r3 - r4} @ Shouldnt fault - tst ip, #4 - movne r3, r7, pull #16 - ldrne r7, [r1], #4 - orrne r3, r3, r7, push #16 - TUSER( strne) r3, [r0], #4 @ Shouldnt fault - ands ip, ip, #3 - beq .Lc2u_2fupi -.Lc2u_2nowords: mov r3, r7, get_byte_2 - teq ip, #0 - beq .Lc2u_finished - cmp ip, #2 -USER( TUSER( strb) r3, [r0], #1) @ May fault - movge r3, r7, get_byte_3 -USER( TUSER( strgeb) r3, [r0], #1) @ May fault - ldrgtb r3, [r1], #0 -USER( TUSER( strgtb) r3, [r0], #1) @ May fault - b .Lc2u_finished - -.Lc2u_3fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lc2u_3nowords - mov r3, r7, pull #24 - ldr r7, [r1], #4 - orr r3, r3, r7, push #8 -USER( TUSER( str) r3, [r0], #4) @ May fault - mov ip, r0, lsl #32 - PAGE_SHIFT - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lc2u_3fupi - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #16 - blt .Lc2u_3rem8lp - -.Lc2u_3cpy8lp: mov r3, r7, pull #24 - ldmia r1!, {r4 - r7} - subs ip, ip, #16 - orr r3, r3, r4, push #8 - mov r4, r4, pull #24 - orr r4, r4, r5, push #8 - mov r5, r5, pull #24 - orr r5, r5, r6, push #8 - mov r6, r6, pull #24 - orr r6, r6, r7, push #8 - stmia r0!, {r3 - r6} @ Shouldnt fault - bpl .Lc2u_3cpy8lp - -.Lc2u_3rem8lp: tst ip, #8 - movne r3, r7, pull #24 - ldmneia r1!, {r4, r7} - orrne r3, r3, r4, push #8 - movne r4, r4, pull #24 - orrne r4, r4, r7, push #8 - stmneia r0!, {r3 - r4} @ Shouldnt fault - tst ip, #4 - movne r3, r7, pull #24 - ldrne r7, [r1], #4 - orrne r3, r3, r7, push #8 - TUSER( strne) r3, [r0], #4 @ Shouldnt fault - ands ip, ip, #3 - beq .Lc2u_3fupi -.Lc2u_3nowords: mov r3, r7, get_byte_3 - teq ip, #0 - beq .Lc2u_finished - cmp ip, #2 -USER( TUSER( strb) r3, [r0], #1) @ May fault - ldrgeb r3, [r1], #1 -USER( TUSER( strgeb) r3, [r0], #1) @ May fault - ldrgtb r3, [r1], #0 -USER( TUSER( strgtb) r3, [r0], #1) @ May fault - b .Lc2u_finished -ENDPROC(__copy_to_user) - - .pushsection .fixup,"ax" - .align 0 -9001: ldmfd sp!, {r0, r4 - r7, pc} - .popsection - -/* Prototype: unsigned long __copy_from_user(void *to,const void *from,unsigned long n); - * Purpose : copy a block from user memory to kernel memory - * Params : to - kernel memory - * : from - user memory - * : n - number of bytes to copy - * Returns : Number of bytes NOT copied. - */ -.Lcfu_dest_not_aligned: - rsb ip, ip, #4 - cmp ip, #2 -USER( TUSER( ldrb) r3, [r1], #1) @ May fault - strb r3, [r0], #1 -USER( TUSER( ldrgeb) r3, [r1], #1) @ May fault - strgeb r3, [r0], #1 -USER( TUSER( ldrgtb) r3, [r1], #1) @ May fault - strgtb r3, [r0], #1 - sub r2, r2, ip - b .Lcfu_dest_aligned - -ENTRY(__copy_from_user) - stmfd sp!, {r0, r2, r4 - r7, lr} - cmp r2, #4 - blt .Lcfu_not_enough - ands ip, r0, #3 - bne .Lcfu_dest_not_aligned -.Lcfu_dest_aligned: - ands ip, r1, #3 - bne .Lcfu_src_not_aligned - -/* - * Seeing as there has to be at least 8 bytes to copy, we can - * copy one word, and force a user-mode page fault... - */ - -.Lcfu_0fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lcfu_0nowords -USER( TUSER( ldr) r3, [r1], #4) - str r3, [r0], #4 - mov ip, r1, lsl #32 - PAGE_SHIFT @ On each page, use a ld/st??t instruction - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lcfu_0fupi -/* - * ip = max no. of bytes to copy before needing another "strt" insn - */ - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #32 - blt .Lcfu_0rem8lp - -.Lcfu_0cpy8lp: ldmia r1!, {r3 - r6} @ Shouldnt fault - stmia r0!, {r3 - r6} - ldmia r1!, {r3 - r6} @ Shouldnt fault - subs ip, ip, #32 - stmia r0!, {r3 - r6} - bpl .Lcfu_0cpy8lp - -.Lcfu_0rem8lp: cmn ip, #16 - ldmgeia r1!, {r3 - r6} @ Shouldnt fault - stmgeia r0!, {r3 - r6} - tst ip, #8 - ldmneia r1!, {r3 - r4} @ Shouldnt fault - stmneia r0!, {r3 - r4} - tst ip, #4 - TUSER( ldrne) r3, [r1], #4 @ Shouldnt fault - strne r3, [r0], #4 - ands ip, ip, #3 - beq .Lcfu_0fupi -.Lcfu_0nowords: teq ip, #0 - beq .Lcfu_finished -.Lcfu_nowords: cmp ip, #2 -USER( TUSER( ldrb) r3, [r1], #1) @ May fault - strb r3, [r0], #1 -USER( TUSER( ldrgeb) r3, [r1], #1) @ May fault - strgeb r3, [r0], #1 -USER( TUSER( ldrgtb) r3, [r1], #1) @ May fault - strgtb r3, [r0], #1 - b .Lcfu_finished - -.Lcfu_not_enough: - movs ip, r2 - bne .Lcfu_nowords -.Lcfu_finished: mov r0, #0 - add sp, sp, #8 - ldmfd sp!, {r4 - r7, pc} - -.Lcfu_src_not_aligned: - bic r1, r1, #3 -USER( TUSER( ldr) r7, [r1], #4) @ May fault - cmp ip, #2 - bgt .Lcfu_3fupi - beq .Lcfu_2fupi -.Lcfu_1fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lcfu_1nowords - mov r3, r7, pull #8 -USER( TUSER( ldr) r7, [r1], #4) @ May fault - orr r3, r3, r7, push #24 - str r3, [r0], #4 - mov ip, r1, lsl #32 - PAGE_SHIFT - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lcfu_1fupi - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #16 - blt .Lcfu_1rem8lp - -.Lcfu_1cpy8lp: mov r3, r7, pull #8 - ldmia r1!, {r4 - r7} @ Shouldnt fault - subs ip, ip, #16 - orr r3, r3, r4, push #24 - mov r4, r4, pull #8 - orr r4, r4, r5, push #24 - mov r5, r5, pull #8 - orr r5, r5, r6, push #24 - mov r6, r6, pull #8 - orr r6, r6, r7, push #24 - stmia r0!, {r3 - r6} - bpl .Lcfu_1cpy8lp - -.Lcfu_1rem8lp: tst ip, #8 - movne r3, r7, pull #8 - ldmneia r1!, {r4, r7} @ Shouldnt fault - orrne r3, r3, r4, push #24 - movne r4, r4, pull #8 - orrne r4, r4, r7, push #24 - stmneia r0!, {r3 - r4} - tst ip, #4 - movne r3, r7, pull #8 -USER( TUSER( ldrne) r7, [r1], #4) @ May fault - orrne r3, r3, r7, push #24 - strne r3, [r0], #4 - ands ip, ip, #3 - beq .Lcfu_1fupi -.Lcfu_1nowords: mov r3, r7, get_byte_1 - teq ip, #0 - beq .Lcfu_finished - cmp ip, #2 - strb r3, [r0], #1 - movge r3, r7, get_byte_2 - strgeb r3, [r0], #1 - movgt r3, r7, get_byte_3 - strgtb r3, [r0], #1 - b .Lcfu_finished - -.Lcfu_2fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lcfu_2nowords - mov r3, r7, pull #16 -USER( TUSER( ldr) r7, [r1], #4) @ May fault - orr r3, r3, r7, push #16 - str r3, [r0], #4 - mov ip, r1, lsl #32 - PAGE_SHIFT - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lcfu_2fupi - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #16 - blt .Lcfu_2rem8lp - - -.Lcfu_2cpy8lp: mov r3, r7, pull #16 - ldmia r1!, {r4 - r7} @ Shouldnt fault - subs ip, ip, #16 - orr r3, r3, r4, push #16 - mov r4, r4, pull #16 - orr r4, r4, r5, push #16 - mov r5, r5, pull #16 - orr r5, r5, r6, push #16 - mov r6, r6, pull #16 - orr r6, r6, r7, push #16 - stmia r0!, {r3 - r6} - bpl .Lcfu_2cpy8lp - -.Lcfu_2rem8lp: tst ip, #8 - movne r3, r7, pull #16 - ldmneia r1!, {r4, r7} @ Shouldnt fault - orrne r3, r3, r4, push #16 - movne r4, r4, pull #16 - orrne r4, r4, r7, push #16 - stmneia r0!, {r3 - r4} - tst ip, #4 - movne r3, r7, pull #16 -USER( TUSER( ldrne) r7, [r1], #4) @ May fault - orrne r3, r3, r7, push #16 - strne r3, [r0], #4 - ands ip, ip, #3 - beq .Lcfu_2fupi -.Lcfu_2nowords: mov r3, r7, get_byte_2 - teq ip, #0 - beq .Lcfu_finished - cmp ip, #2 - strb r3, [r0], #1 - movge r3, r7, get_byte_3 - strgeb r3, [r0], #1 -USER( TUSER( ldrgtb) r3, [r1], #0) @ May fault - strgtb r3, [r0], #1 - b .Lcfu_finished - -.Lcfu_3fupi: subs r2, r2, #4 - addmi ip, r2, #4 - bmi .Lcfu_3nowords - mov r3, r7, pull #24 -USER( TUSER( ldr) r7, [r1], #4) @ May fault - orr r3, r3, r7, push #8 - str r3, [r0], #4 - mov ip, r1, lsl #32 - PAGE_SHIFT - rsb ip, ip, #0 - movs ip, ip, lsr #32 - PAGE_SHIFT - beq .Lcfu_3fupi - cmp r2, ip - movlt ip, r2 - sub r2, r2, ip - subs ip, ip, #16 - blt .Lcfu_3rem8lp - -.Lcfu_3cpy8lp: mov r3, r7, pull #24 - ldmia r1!, {r4 - r7} @ Shouldnt fault - orr r3, r3, r4, push #8 - mov r4, r4, pull #24 - orr r4, r4, r5, push #8 - mov r5, r5, pull #24 - orr r5, r5, r6, push #8 - mov r6, r6, pull #24 - orr r6, r6, r7, push #8 - stmia r0!, {r3 - r6} - subs ip, ip, #16 - bpl .Lcfu_3cpy8lp - -.Lcfu_3rem8lp: tst ip, #8 - movne r3, r7, pull #24 - ldmneia r1!, {r4, r7} @ Shouldnt fault - orrne r3, r3, r4, push #8 - movne r4, r4, pull #24 - orrne r4, r4, r7, push #8 - stmneia r0!, {r3 - r4} - tst ip, #4 - movne r3, r7, pull #24 -USER( TUSER( ldrne) r7, [r1], #4) @ May fault - orrne r3, r3, r7, push #8 - strne r3, [r0], #4 - ands ip, ip, #3 - beq .Lcfu_3fupi -.Lcfu_3nowords: mov r3, r7, get_byte_3 - teq ip, #0 - beq .Lcfu_finished - cmp ip, #2 - strb r3, [r0], #1 -USER( TUSER( ldrgeb) r3, [r1], #1) @ May fault - strgeb r3, [r0], #1 -USER( TUSER( ldrgtb) r3, [r1], #1) @ May fault - strgtb r3, [r0], #1 - b .Lcfu_finished -ENDPROC(__copy_from_user) - - .pushsection .fixup,"ax" - .align 0 - /* - * We took an exception. r0 contains a pointer to - * the byte not copied. - */ -9001: ldr r2, [sp], #4 @ void *to - sub r2, r0, r2 @ bytes copied - ldr r1, [sp], #4 @ unsigned long count - subs r4, r1, r2 @ bytes left to copy - movne r1, r4 - blne __memzero - mov r0, r4 - ldmfd sp!, {r4 - r7, pc} - .popsection - diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 025f742dd4df..c0ac7796d775 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/arch/arm/lib/uaccess_with_memcpy.c * * Written by: Lennert Buytenhek and Nicolas Pitre * Copyright (C) 2009 Marvell Semiconductor - * - * 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/kernel.h> @@ -18,6 +15,7 @@ #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> @@ -26,6 +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; @@ -35,15 +34,49 @@ 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; 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. + */ + if (unlikely(pmd_leaf(*pmd))) { + ptl = ¤t->mm->page_table_lock; + spin_lock(ptl); + if (unlikely(!pmd_leaf(*pmd) + || pmd_hugewillfault(*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); + if (unlikely(!pte)) + return 0; + if (unlikely(!pte_present(*pte) || !pte_young(*pte) || !pte_write(*pte) || !pte_dirty(*pte))) { pte_unmap_unlock(pte, ptl); @@ -59,18 +92,14 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) static unsigned long noinline __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) { + unsigned long ua_flags; int atomic; - if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { - memcpy((void *)to, from, n); - return 0; - } - /* the mmap semaphore is taken only if not in an atomic context */ - atomic = in_atomic(); + atomic = faulthandler_disabled(); if (!atomic) - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); while (n) { pte_t *pte; spinlock_t *ptl; @@ -78,33 +107,38 @@ __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(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (__put_user(0, (char __user *)to)) goto out; if (!atomic) - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); } tocopy = (~(unsigned long)to & ~PAGE_MASK) + 1; if (tocopy > n) tocopy = n; - memcpy((void *)to, from, tocopy); + ua_flags = uaccess_save_and_enable(); + __memcpy((void *)to, from, tocopy); + uaccess_restore(ua_flags); to += tocopy; from += tocopy; n -= tocopy; - pte_unmap_unlock(pte, ptl); + if (pte) + pte_unmap_unlock(pte, ptl); + else + spin_unlock(ptl); } if (!atomic) - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); out: return n; } unsigned long -__copy_to_user(void __user *to, const void *from, unsigned long n) +arm_copy_to_user(void __user *to, const void *from, unsigned long n) { /* * This test is stubbed out of the main function above to keep @@ -113,54 +147,67 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) * With frame pointer disabled, tail call optimization kicks in * as well making this test almost invisible. */ - if (n < 64) - return __copy_to_user_std(to, from, n); - return __copy_to_user_memcpy(to, from, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __copy_to_user_std(to, from, n); + uaccess_restore(ua_flags); + } else { + n = __copy_to_user_memcpy(uaccess_mask_range_ptr(to, n), + from, n); + } + return n; } static unsigned long noinline __clear_user_memset(void __user *addr, unsigned long n) { - if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { - memset((void *)addr, 0, n); - return 0; - } + unsigned long ua_flags; - down_read(¤t->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(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (__put_user(0, (char __user *)addr)) goto out; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); } tocopy = (~(unsigned long)addr & ~PAGE_MASK) + 1; if (tocopy > n) tocopy = n; - memset((void *)addr, 0, tocopy); + ua_flags = uaccess_save_and_enable(); + __memset((void *)addr, 0, tocopy); + uaccess_restore(ua_flags); addr += tocopy; n -= tocopy; - pte_unmap_unlock(pte, ptl); + if (pte) + pte_unmap_unlock(pte, ptl); + else + spin_unlock(ptl); } - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); out: return n; } -unsigned long __clear_user(void __user *addr, unsigned long n) +unsigned long arm_clear_user(void __user *addr, unsigned long n) { /* See rational for this in __copy_to_user() above. */ - if (n < 64) - return __clear_user_std(addr, n); - return __clear_user_memset(addr, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __clear_user_std(addr, n); + uaccess_restore(ua_flags); + } else { + n = __clear_user_memset(addr, n); + } + return n; } #if 0 @@ -193,7 +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/ucmpdi2.S b/arch/arm/lib/ucmpdi2.S index f0df6a91db04..679e16a210ae 100644 --- a/arch/arm/lib/ucmpdi2.S +++ b/arch/arm/lib/ucmpdi2.S @@ -1,16 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/lib/ucmpdi2.S * * Author: Nicolas Pitre * Created: Oct 19, 2005 * Copyright: Monta Vista Software, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/linkage.h> +#include <asm/assembler.h> #ifdef __ARMEB__ #define xh r0 @@ -31,7 +29,7 @@ ENTRY(__ucmpdi2) movlo r0, #0 moveq r0, #1 movhi r0, #2 - mov pc, lr + ret lr ENDPROC(__ucmpdi2) @@ -44,7 +42,7 @@ ENTRY(__aeabi_ulcmp) movlo r0, #-1 moveq r0, #0 movhi r0, #1 - mov pc, lr + ret lr ENDPROC(__aeabi_ulcmp) diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c new file mode 100644 index 000000000000..cf57fca97908 --- /dev/null +++ b/arch/arm/lib/xor-neon.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/lib/xor-neon.c + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + */ + +#include <linux/raid/xor.h> +#include <linux/module.h> + +MODULE_DESCRIPTION("NEON accelerated XOR implementation"); +MODULE_LICENSE("GPL"); + +#ifndef __ARM_NEON__ +#error You should compile this file with '-march=armv7-a -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. Clang does this by default at O2 so no pragma is + * needed. + */ +#ifdef CONFIG_CC_IS_GCC +#pragma GCC optimize "tree-vectorize" +#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); |