android_bionic/libc/arch-arm/krait/bionic/memcpy_base.S

118 lines
4.2 KiB
ArmAsm
Raw Normal View History

Create optimized __strcpy_chk/__strcat_chk. This change pulls the memcpy code out into a new file so that the __strcpy_chk and __strcat_chk can use it with an include. The new versions of the two chk functions uses assembly versions of strlen and memcpy to implement this check. This allows near parity with the assembly versions of strcpy/strcat. It also means that as memcpy implementations get faster, so do the chk functions. Other included changes: - Change all of the assembly labels to local labels. The other labels confuse gdb and mess up backtracing. - Add .cfi_startproc and .cfi_endproc directives so that gdb is not confused when falling through from one function to another. - Change all functions to use cfi directives since they are more powerful. - Move the memcpy_chk fail code outside of the memcpy function definition so that backtraces work properly. - Preserve lr before the calls to __fortify_chk_fail so that the backtrace actually works. Testing: - Ran the bionic unit tests. Verified all error messages in logs are set correctly. - Ran libc_test, replacing strcpy with __strcpy_chk and replacing strcat with __strcat_chk. - Ran the debugger on nexus10, nexus4, and old nexus7. Verified that the backtrace is correct for all fortify check failures. Also verify that when falling through from __memcpy_chk to memcpy that the backtrace is still correct. Also verified the same for __memset_chk and bzero. Verified the two different paths in the cortex-a9 memset routine that save variables to the stack still show the backtrace properly. Bug: 9293744 (cherry-picked from 2be91915dcecc956d14ff281db0c7d216ca98af2) Change-Id: Ia407b74d3287d0b6af0139a90b6eb3bfaebf2155
2013-08-07 20:09:51 +00:00
/*
* Copyright (C) 2013 The Android Open Source Project
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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
* COPYRIGHT OWNER 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.
*/
/*
* This code assumes it is running on a processor that supports all arm v7
* instructions, that supports neon instructions, and that has a 32 byte
* cache line.
*/
// Assumes neon instructions and a cache line size of 32 bytes.
/* do we have at least 16-bytes to copy (needed for alignment below) */
cmp r2, #16
blo 5f
/* align destination to cache-line for the write-buffer */
rsb r3, r0, #0
ands r3, r3, #0xF
beq 2f
/* copy up to 15-bytes (count in r3) */
sub r2, r2, r3
movs ip, r3, lsl #31
itt mi
ldrbmi lr, [r1], #1
strbmi lr, [r0], #1
itttt cs
ldrbcs ip, [r1], #1
ldrbcs lr, [r1], #1
strbcs ip, [r0], #1
strbcs lr, [r0], #1
movs ip, r3, lsl #29
bge 1f
// copies 4 bytes, destination 32-bits aligned
vld4.8 {d0[0], d1[0], d2[0], d3[0]}, [r1]!
vst4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0, :32]!
1: bcc 2f
// copies 8 bytes, destination 64-bits aligned
vld1.8 {d0}, [r1]!
vst1.8 {d0}, [r0, :64]!
2: /* make sure we have at least 64 bytes to copy */
subs r2, r2, #64
blo 2f
1: /* The main loop copies 64 bytes at a time */
vld1.8 {d0 - d3}, [r1]!
vld1.8 {d4 - d7}, [r1]!
pld [r1, #(32*2)]
subs r2, r2, #64
vst1.8 {d0 - d3}, [r0, :128]!
vst1.8 {d4 - d7}, [r0, :128]!
bhs 1b
2: /* fix-up the remaining count and make sure we have >= 32 bytes left */
adds r2, r2, #32
blo 4f
/* Copy 32 bytes. These cache lines were already preloaded */
vld1.8 {d0 - d3}, [r1]!
sub r2, r2, #32
vst1.8 {d0 - d3}, [r0, :128]!
4: /* less than 32 left */
add r2, r2, #32
tst r2, #0x10
beq 5f
// copies 16 bytes, 128-bits aligned
vld1.8 {d0, d1}, [r1]!
vst1.8 {d0, d1}, [r0, :128]!
5: /* copy up to 15-bytes (count in r2) */
movs ip, r2, lsl #29
bcc 1f
vld1.8 {d0}, [r1]!
vst1.8 {d0}, [r0]!
1: bge 2f
vld4.8 {d0[0], d1[0], d2[0], d3[0]}, [r1]!
vst4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0]!
2: movs ip, r2, lsl #31
itt mi
ldrbmi r3, [r1], #1
strbmi r3, [r0], #1
itttt cs
ldrbcs ip, [r1], #1
ldrbcs lr, [r1], #1
strbcs ip, [r0], #1
strbcs lr, [r0], #1
ldmfd sp!, {r0, lr}
bx lr