diff --git a/sys/arm64/arm64/memcpy.S b/sys/arm64/arm64/memcpy.S index d5fbfa64e0fa..b394d6c1d30a 100644 --- a/sys/arm64/arm64/memcpy.S +++ b/sys/arm64/arm64/memcpy.S @@ -1,242 +1,242 @@ /* * memcpy - copy memory area * * Copyright (c) 2012-2020, Arm Limited. * SPDX-License-Identifier: MIT */ /* Assumptions: * * ARMv8-a, AArch64, unaligned accesses. * */ #include #define L(l) .L ## l #define dstin x0 #define src x1 #define count x2 #define dst x3 #define srcend x4 #define dstend x5 #define A_l x6 #define A_lw w6 #define A_h x7 #define B_l x8 #define B_lw w8 #define B_h x9 #define C_l x10 #define C_lw w10 #define C_h x11 #define D_l x12 #define D_h x13 #define E_l x14 #define E_h x15 #define F_l x16 #define F_h x17 #define G_l count #define G_h dst #define H_l src #define H_h srcend #define tmp1 x14 /* This implementation handles overlaps and supports both memcpy and memmove from a single entry point. It uses unaligned accesses and branchless sequences to keep the code small, simple and improve performance. Copies are split into 3 main cases: small copies of up to 32 bytes, medium copies of up to 128 bytes, and large copies. The overhead of the overlap check is negligible since it is only required for large copies. Large copies use a software pipelined loop processing 64 bytes per iteration. The destination pointer is 16-byte aligned to minimize unaligned accesses. The loop tail is handled by always copying 64 bytes from the end. */ -ENTRY(memcpy) EENTRY(memmove) +ENTRY(memcpy) add srcend, src, count add dstend, dstin, count cmp count, 128 b.hi L(copy_long) cmp count, 32 b.hi L(copy32_128) /* Small copies: 0..32 bytes. */ cmp count, 16 b.lo L(copy16) ldp A_l, A_h, [src] ldp D_l, D_h, [srcend, -16] stp A_l, A_h, [dstin] stp D_l, D_h, [dstend, -16] ret /* Copy 8-15 bytes. */ L(copy16): tbz count, 3, L(copy8) ldr A_l, [src] ldr A_h, [srcend, -8] str A_l, [dstin] str A_h, [dstend, -8] ret .p2align 3 /* Copy 4-7 bytes. */ L(copy8): tbz count, 2, L(copy4) ldr A_lw, [src] ldr B_lw, [srcend, -4] str A_lw, [dstin] str B_lw, [dstend, -4] ret /* Copy 0..3 bytes using a branchless sequence. */ L(copy4): cbz count, L(copy0) lsr tmp1, count, 1 ldrb A_lw, [src] ldrb C_lw, [srcend, -1] ldrb B_lw, [src, tmp1] strb A_lw, [dstin] strb B_lw, [dstin, tmp1] strb C_lw, [dstend, -1] L(copy0): ret .p2align 4 /* Medium copies: 33..128 bytes. */ L(copy32_128): ldp A_l, A_h, [src] ldp B_l, B_h, [src, 16] ldp C_l, C_h, [srcend, -32] ldp D_l, D_h, [srcend, -16] cmp count, 64 b.hi L(copy128) stp A_l, A_h, [dstin] stp B_l, B_h, [dstin, 16] stp C_l, C_h, [dstend, -32] stp D_l, D_h, [dstend, -16] ret .p2align 4 /* Copy 65..128 bytes. */ L(copy128): ldp E_l, E_h, [src, 32] ldp F_l, F_h, [src, 48] cmp count, 96 b.ls L(copy96) ldp G_l, G_h, [srcend, -64] ldp H_l, H_h, [srcend, -48] stp G_l, G_h, [dstend, -64] stp H_l, H_h, [dstend, -48] L(copy96): stp A_l, A_h, [dstin] stp B_l, B_h, [dstin, 16] stp E_l, E_h, [dstin, 32] stp F_l, F_h, [dstin, 48] stp C_l, C_h, [dstend, -32] stp D_l, D_h, [dstend, -16] ret .p2align 4 /* Copy more than 128 bytes. */ L(copy_long): /* Use backwards copy if there is an overlap. */ sub tmp1, dstin, src cbz tmp1, L(copy0) cmp tmp1, count b.lo L(copy_long_backwards) /* Copy 16 bytes and then align dst to 16-byte alignment. */ ldp D_l, D_h, [src] and tmp1, dstin, 15 bic dst, dstin, 15 sub src, src, tmp1 add count, count, tmp1 /* Count is now 16 too large. */ ldp A_l, A_h, [src, 16] stp D_l, D_h, [dstin] ldp B_l, B_h, [src, 32] ldp C_l, C_h, [src, 48] ldp D_l, D_h, [src, 64]! subs count, count, 128 + 16 /* Test and readjust count. */ b.ls L(copy64_from_end) L(loop64): stp A_l, A_h, [dst, 16] ldp A_l, A_h, [src, 16] stp B_l, B_h, [dst, 32] ldp B_l, B_h, [src, 32] stp C_l, C_h, [dst, 48] ldp C_l, C_h, [src, 48] stp D_l, D_h, [dst, 64]! ldp D_l, D_h, [src, 64]! subs count, count, 64 b.hi L(loop64) /* Write the last iteration and copy 64 bytes from the end. */ L(copy64_from_end): ldp E_l, E_h, [srcend, -64] stp A_l, A_h, [dst, 16] ldp A_l, A_h, [srcend, -48] stp B_l, B_h, [dst, 32] ldp B_l, B_h, [srcend, -32] stp C_l, C_h, [dst, 48] ldp C_l, C_h, [srcend, -16] stp D_l, D_h, [dst, 64] stp E_l, E_h, [dstend, -64] stp A_l, A_h, [dstend, -48] stp B_l, B_h, [dstend, -32] stp C_l, C_h, [dstend, -16] ret .p2align 4 /* Large backwards copy for overlapping copies. Copy 16 bytes and then align dst to 16-byte alignment. */ L(copy_long_backwards): ldp D_l, D_h, [srcend, -16] and tmp1, dstend, 15 sub srcend, srcend, tmp1 sub count, count, tmp1 ldp A_l, A_h, [srcend, -16] stp D_l, D_h, [dstend, -16] ldp B_l, B_h, [srcend, -32] ldp C_l, C_h, [srcend, -48] ldp D_l, D_h, [srcend, -64]! sub dstend, dstend, tmp1 subs count, count, 128 b.ls L(copy64_from_start) L(loop64_backwards): stp A_l, A_h, [dstend, -16] ldp A_l, A_h, [srcend, -16] stp B_l, B_h, [dstend, -32] ldp B_l, B_h, [srcend, -32] stp C_l, C_h, [dstend, -48] ldp C_l, C_h, [srcend, -48] stp D_l, D_h, [dstend, -64]! ldp D_l, D_h, [srcend, -64]! subs count, count, 64 b.hi L(loop64_backwards) /* Write the last iteration and copy 64 bytes from the start. */ L(copy64_from_start): ldp G_l, G_h, [src, 48] stp A_l, A_h, [dstend, -16] ldp A_l, A_h, [src, 32] stp B_l, B_h, [dstend, -32] ldp B_l, B_h, [src, 16] stp C_l, C_h, [dstend, -48] ldp C_l, C_h, [src] stp D_l, D_h, [dstend, -64] stp G_l, G_h, [dstin, 48] stp A_l, A_h, [dstin, 32] stp B_l, B_h, [dstin, 16] stp C_l, C_h, [dstin] ret -EEND(memmove) END(memcpy) +EEND(memmove) diff --git a/sys/arm64/arm64/support.S b/sys/arm64/arm64/support.S index 885af5676159..28ac1d553fbc 100644 --- a/sys/arm64/arm64/support.S +++ b/sys/arm64/arm64/support.S @@ -1,299 +1,299 @@ /*- * Copyright (c) 2014 Andrew Turner * Copyright (c) 2014-2015 The FreeBSD Foundation * All rights reserved. * * Portions of this software were developed by Andrew Turner * under sponsorship from the FreeBSD Foundation * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * */ #include __FBSDID("$FreeBSD$"); #include #include #include #include "assym.inc" .macro check_user_access user_arg, limit, bad_addr_func ldr x7, =(\limit) cmp x\user_arg, x7 b.cs \bad_addr_func .endm /* * One of the fu* or su* functions failed, return -1. */ ENTRY(fsu_fault) SET_FAULT_HANDLER(xzr, x1) /* Reset the handler function */ EXIT_USER_ACCESS_CHECK(w0, x1) fsu_fault_nopcb: mov x0, #-1 ret END(fsu_fault) /* * int casueword32_llsc(volatile uint32_t *, uint32_t, uint32_t *, uint32_t) */ ENTRY(casueword32_llsc) check_user_access 0, (VM_MAXUSER_ADDRESS-3), fsu_fault_nopcb adr x6, fsu_fault /* Load the fault handler */ mov w5, #1 SET_FAULT_HANDLER(x6, x4) /* And set it */ ENTER_USER_ACCESS(w6, x4) ldxr w4, [x0] /* Load-exclusive the data */ cmp w4, w1 /* Compare */ b.ne 1f /* Not equal, exit */ stxr w5, w3, [x0] /* Store the new data */ 1: EXIT_USER_ACCESS(w6) SET_FAULT_HANDLER(xzr, x6) /* Reset the fault handler */ str w4, [x2] /* Store the read data */ mov w0, w5 /* Result same as store status */ ret /* Return */ END(casueword32_llsc) /* * int casueword32_lse(volatile uint32_t *, uint32_t, uint32_t *, uint32_t) */ ENTRY(casueword32_lse) check_user_access 0, (VM_MAXUSER_ADDRESS-3), fsu_fault_nopcb adr x6, fsu_fault /* Load the fault handler */ SET_FAULT_HANDLER(x6, x4) /* And set it */ ENTER_USER_ACCESS(w6, x4) mov w7, w1 /* Back up the compare value */ .arch_extension lse cas w1, w3, [x0] /* Compare and Swap */ .arch_extension nolse cmp w1, w7 /* Check if successful */ cset w0, ne /* Return 0 on success, 1 on failure */ EXIT_USER_ACCESS(w6) SET_FAULT_HANDLER(xzr, x6) /* Reset the fault handler */ str w1, [x2] /* Store the read data */ ret /* Return */ END(casueword32_lse) /* * int casueword_llsc(volatile u_long *, u_long, u_long *, u_long) */ ENTRY(casueword_llsc) check_user_access 0, (VM_MAXUSER_ADDRESS-7), fsu_fault_nopcb adr x6, fsu_fault /* Load the fault handler */ mov w5, #1 SET_FAULT_HANDLER(x6, x4) /* And set it */ ENTER_USER_ACCESS(w6, x4) ldxr x4, [x0] /* Load-exclusive the data */ cmp x4, x1 /* Compare */ b.ne 1f /* Not equal, exit */ stxr w5, x3, [x0] /* Store the new data */ 1: EXIT_USER_ACCESS(w6) SET_FAULT_HANDLER(xzr, x6) /* Reset the fault handler */ str x4, [x2] /* Store the read data */ mov w0, w5 /* Result same as store status */ ret /* Return */ END(casueword_llsc) /* * int casueword_lse(volatile u_long *, u_long, u_long *, u_long) */ ENTRY(casueword_lse) check_user_access 0, (VM_MAXUSER_ADDRESS-3), fsu_fault_nopcb adr x6, fsu_fault /* Load the fault handler */ SET_FAULT_HANDLER(x6, x4) /* And set it */ ENTER_USER_ACCESS(w6, x4) mov x7, x1 /* Back up the compare value */ .arch_extension lse cas x1, x3, [x0] /* Compare and Swap */ .arch_extension nolse cmp x1, x7 /* Check if successful */ cset w0, ne /* Return 0 on success, 1 on failure */ EXIT_USER_ACCESS(w6) SET_FAULT_HANDLER(xzr, x6) /* Reset the fault handler */ str x1, [x2] /* Store the read data */ ret /* Return */ END(casueword_lse) .macro fsudata insn, ret_reg, user_arg adr x7, fsu_fault /* Load the fault handler */ SET_FAULT_HANDLER(x7, x6) /* And set it */ \insn \ret_reg, [x\user_arg] /* Try accessing the data */ SET_FAULT_HANDLER(xzr, x6) /* Reset the fault handler */ .endm /* * int fubyte(volatile const void *) */ ENTRY(fubyte) check_user_access 0, (VM_MAXUSER_ADDRESS), fsu_fault_nopcb fsudata ldtrb, w0, 0 ret /* Return */ END(fubyte) /* * int fuword(volatile const void *) */ ENTRY(fuword16) check_user_access 0, (VM_MAXUSER_ADDRESS-1), fsu_fault_nopcb fsudata ldtrh, w0, 0 ret /* Return */ END(fuword16) /* * int32_t fueword32(volatile const void *, int32_t *) */ ENTRY(fueword32) check_user_access 0, (VM_MAXUSER_ADDRESS-3), fsu_fault_nopcb fsudata ldtr, w0, 0 str w0, [x1] /* Save the data in kernel space */ mov w0, #0 /* Success */ ret /* Return */ END(fueword32) /* * long fueword(volatile const void *, int64_t *) * int64_t fueword64(volatile const void *, int64_t *) */ -ENTRY(fueword) EENTRY(fueword64) +ENTRY(fueword) check_user_access 0, (VM_MAXUSER_ADDRESS-7), fsu_fault_nopcb fsudata ldtr, x0, 0 str x0, [x1] /* Save the data in kernel space */ mov x0, #0 /* Success */ ret /* Return */ -EEND(fueword64) END(fueword) +EEND(fueword64) /* * int subyte(volatile void *, int) */ ENTRY(subyte) check_user_access 0, (VM_MAXUSER_ADDRESS), fsu_fault_nopcb fsudata sttrb, w1, 0 mov x0, #0 /* Success */ ret /* Return */ END(subyte) /* * int suword16(volatile void *, int) */ ENTRY(suword16) check_user_access 0, (VM_MAXUSER_ADDRESS-1), fsu_fault_nopcb fsudata sttrh, w1, 0 mov x0, #0 /* Success */ ret /* Return */ END(suword16) /* * int suword32(volatile void *, int) */ ENTRY(suword32) check_user_access 0, (VM_MAXUSER_ADDRESS-3), fsu_fault_nopcb fsudata sttr, w1, 0 mov x0, #0 /* Success */ ret /* Return */ END(suword32) /* * int suword(volatile void *, long) */ -ENTRY(suword) EENTRY(suword64) +ENTRY(suword) check_user_access 0, (VM_MAXUSER_ADDRESS-7), fsu_fault_nopcb fsudata sttr, x1, 0 mov x0, #0 /* Success */ ret /* Return */ -EEND(suword64) END(suword) +EEND(suword64) ENTRY(setjmp) /* Store the stack pointer */ mov x8, sp str x8, [x0], #8 /* Store the general purpose registers and lr */ stp x19, x20, [x0], #16 stp x21, x22, [x0], #16 stp x23, x24, [x0], #16 stp x25, x26, [x0], #16 stp x27, x28, [x0], #16 stp x29, lr, [x0], #16 /* Return value */ mov x0, #0 ret END(setjmp) ENTRY(longjmp) /* Restore the stack pointer */ ldr x8, [x0], #8 mov sp, x8 /* Restore the general purpose registers and lr */ ldp x19, x20, [x0], #16 ldp x21, x22, [x0], #16 ldp x23, x24, [x0], #16 ldp x25, x26, [x0], #16 ldp x27, x28, [x0], #16 ldp x29, lr, [x0], #16 /* Load the return value */ mov x0, x1 ret END(longjmp) /* * pagezero, simple implementation */ ENTRY(pagezero_simple) add x1, x0, #PAGE_SIZE 1: stp xzr, xzr, [x0], #0x10 stp xzr, xzr, [x0], #0x10 stp xzr, xzr, [x0], #0x10 stp xzr, xzr, [x0], #0x10 cmp x0, x1 b.ne 1b ret END(pagezero_simple) /* * pagezero, cache assisted */ ENTRY(pagezero_cache) add x1, x0, #PAGE_SIZE ldr x2, =dczva_line_size ldr x2, [x2] 1: dc zva, x0 add x0, x0, x2 cmp x0, x1 b.ne 1b ret END(pagezero_cache)