linux-sg2042/arch/sparc/lib/NGmemcpy.S

511 lines
13 KiB
ArmAsm
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
/* SPDX-License-Identifier: GPL-2.0 */
/* NGmemcpy.S: Niagara optimized memcpy.
*
* Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
*/
#ifdef __KERNEL__
#include <linux/linkage.h>
#include <asm/asi.h>
#include <asm/thread_info.h>
#define GLOBAL_SPARE %g7
#define RESTORE_ASI(TMP) \
ldub [%g6 + TI_CURRENT_DS], TMP; \
wr TMP, 0x0, %asi;
#else
#define GLOBAL_SPARE %g5
#define RESTORE_ASI(TMP) \
wr %g0, ASI_PNF, %asi
#endif
#ifdef __sparc_v9__
#define SAVE_AMOUNT 128
#else
#define SAVE_AMOUNT 64
#endif
#ifndef STORE_ASI
#define STORE_ASI ASI_BLK_INIT_QUAD_LDD_P
#endif
#ifndef EX_LD
#define EX_LD(x,y) x
#endif
#ifndef EX_ST
#define EX_ST(x,y) x
#endif
#ifndef LOAD
#ifndef MEMCPY_DEBUG
#define LOAD(type,addr,dest) type [addr], dest
#else
#define LOAD(type,addr,dest) type##a [addr] 0x80, dest
#endif
#endif
#ifndef LOAD_TWIN
#define LOAD_TWIN(addr_reg,dest0,dest1) \
ldda [addr_reg] ASI_BLK_INIT_QUAD_LDD_P, dest0
#endif
#ifndef STORE
#define STORE(type,src,addr) type src, [addr]
#endif
#ifndef STORE_INIT
#ifndef SIMULATE_NIAGARA_ON_NON_NIAGARA
#define STORE_INIT(src,addr) stxa src, [addr] %asi
#else
#define STORE_INIT(src,addr) stx src, [addr + 0x00]
#endif
#endif
#ifndef FUNC_NAME
#define FUNC_NAME NGmemcpy
#endif
#ifndef PREAMBLE
#define PREAMBLE
#endif
#ifndef XCC
#define XCC xcc
#endif
.register %g2,#scratch
.register %g3,#scratch
.text
#ifndef EX_RETVAL
#define EX_RETVAL(x) x
__restore_asi:
ret
wr %g0, ASI_AIUS, %asi
restore
ENTRY(NG_ret_i2_plus_i4_plus_1)
ba,pt %xcc, __restore_asi
add %i2, %i5, %i0
ENDPROC(NG_ret_i2_plus_i4_plus_1)
ENTRY(NG_ret_i2_plus_g1)
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1)
ENTRY(NG_ret_i2_plus_g1_minus_8)
sub %g1, 8, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_8)
ENTRY(NG_ret_i2_plus_g1_minus_16)
sub %g1, 16, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_16)
ENTRY(NG_ret_i2_plus_g1_minus_24)
sub %g1, 24, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_24)
ENTRY(NG_ret_i2_plus_g1_minus_32)
sub %g1, 32, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_32)
ENTRY(NG_ret_i2_plus_g1_minus_40)
sub %g1, 40, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_40)
ENTRY(NG_ret_i2_plus_g1_minus_48)
sub %g1, 48, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_48)
ENTRY(NG_ret_i2_plus_g1_minus_56)
sub %g1, 56, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_56)
ENTRY(NG_ret_i2_plus_i4)
ba,pt %xcc, __restore_asi
add %i2, %i4, %i0
ENDPROC(NG_ret_i2_plus_i4)
ENTRY(NG_ret_i2_plus_i4_minus_8)
sub %i4, 8, %i4
ba,pt %xcc, __restore_asi
add %i2, %i4, %i0
ENDPROC(NG_ret_i2_plus_i4_minus_8)
ENTRY(NG_ret_i2_plus_8)
ba,pt %xcc, __restore_asi
add %i2, 8, %i0
ENDPROC(NG_ret_i2_plus_8)
ENTRY(NG_ret_i2_plus_4)
ba,pt %xcc, __restore_asi
add %i2, 4, %i0
ENDPROC(NG_ret_i2_plus_4)
ENTRY(NG_ret_i2_plus_1)
ba,pt %xcc, __restore_asi
add %i2, 1, %i0
ENDPROC(NG_ret_i2_plus_1)
ENTRY(NG_ret_i2_plus_g1_plus_1)
add %g1, 1, %g1
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_plus_1)
ENTRY(NG_ret_i2)
ba,pt %xcc, __restore_asi
mov %i2, %i0
ENDPROC(NG_ret_i2)
ENTRY(NG_ret_i2_and_7_plus_i4)
and %i2, 7, %i2
ba,pt %xcc, __restore_asi
add %i2, %i4, %i0
ENDPROC(NG_ret_i2_and_7_plus_i4)
#endif
.align 64
.globl FUNC_NAME
.type FUNC_NAME,#function
FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
PREAMBLE
save %sp, -SAVE_AMOUNT, %sp
srlx %i2, 31, %g2
cmp %g2, 0
tne %xcc, 5
mov %i0, %o0
cmp %i2, 0
be,pn %XCC, 85f
or %o0, %i1, %i3
cmp %i2, 16
blu,a,pn %XCC, 80f
or %i3, %i2, %i3
/* 2 blocks (128 bytes) is the minimum we can do the block
* copy with. We need to ensure that we'll iterate at least
* once in the block copy loop. At worst we'll need to align
* the destination to a 64-byte boundary which can chew up
* to (64 - 1) bytes from the length before we perform the
* block copy loop.
*/
cmp %i2, (2 * 64)
blu,pt %XCC, 70f
andcc %i3, 0x7, %g0
/* %o0: dst
* %i1: src
* %i2: len (known to be >= 128)
*
* The block copy loops will use %i4/%i5,%g2/%g3 as
* temporaries while copying the data.
*/
LOAD(prefetch, %i1, #one_read)
wr %g0, STORE_ASI, %asi
/* Align destination on 64-byte boundary. */
andcc %o0, (64 - 1), %i4
be,pt %XCC, 2f
sub %i4, 64, %i4
sub %g0, %i4, %i4 ! bytes to align dst
sub %i2, %i4, %i2
1: subcc %i4, 1, %i4
EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1)
EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1)
add %i1, 1, %i1
bne,pt %XCC, 1b
add %o0, 1, %o0
/* If the source is on a 16-byte boundary we can do
* the direct block copy loop. If it is 8-byte aligned
* we can do the 16-byte loads offset by -8 bytes and the
* init stores offset by one register.
*
* If the source is not even 8-byte aligned, we need to do
* shifting and masking (basically integer faligndata).
*
* The careful bit with init stores is that if we store
* to any part of the cache line we have to store the whole
* cacheline else we can end up with corrupt L2 cache line
* contents. Since the loop works on 64-bytes of 64-byte
* aligned store data at a time, this is easy to ensure.
*/
2:
andcc %i1, (16 - 1), %i4
andn %i2, (64 - 1), %g1 ! block copy loop iterator
be,pt %XCC, 50f
sub %i2, %g1, %i2 ! final sub-block copy bytes
cmp %i4, 8
be,pt %XCC, 10f
sub %i1, %i4, %i1
/* Neither 8-byte nor 16-byte aligned, shift and mask. */
and %i4, 0x7, GLOBAL_SPARE
sll GLOBAL_SPARE, 3, GLOBAL_SPARE
mov 64, %i5
EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1)
sub %i5, GLOBAL_SPARE, %i5
mov 16, %o4
mov 32, %o5
mov 48, %o7
mov 64, %i3
bg,pn %XCC, 9f
nop
#define MIX_THREE_WORDS(WORD1, WORD2, WORD3, PRE_SHIFT, POST_SHIFT, TMP) \
sllx WORD1, POST_SHIFT, WORD1; \
srlx WORD2, PRE_SHIFT, TMP; \
sllx WORD2, POST_SHIFT, WORD2; \
or WORD1, TMP, WORD1; \
srlx WORD3, PRE_SHIFT, TMP; \
or WORD2, TMP, WORD2;
8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
LOAD(prefetch, %i1 + %i3, #one_read)
EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1)
EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 8b
add %o0, 64, %o0
ba,pt %XCC, 60f
add %i1, %i4, %i1
9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
LOAD(prefetch, %i1 + %i3, #one_read)
EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1)
EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 9b
add %o0, 64, %o0
ba,pt %XCC, 60f
add %i1, %i4, %i1
10: /* Destination is 64-byte aligned, source was only 8-byte
* aligned but it has been subtracted by 8 and we perform
* one twin load ahead, then add 8 back into source when
* we finish the loop.
*/
EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1)
mov 16, %o7
mov 32, %g2
mov 48, %g3
mov 64, %o1
1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
LOAD(prefetch, %i1 + %o1, #one_read)
EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line
EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 1b
add %o0, 64, %o0
ba,pt %XCC, 60f
add %i1, 0x8, %i1
50: /* Destination is 64-byte aligned, and source is 16-byte
* aligned.
*/
mov 16, %o7
mov 32, %g2
mov 48, %g3
mov 64, %o1
1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1)
EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
LOAD(prefetch, %i1 + %o1, #one_read)
EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line
EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
add %i1, 64, %i1
EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 1b
add %o0, 64, %o0
/* fall through */
60:
membar #Sync
/* %i2 contains any final bytes still needed to be copied
* over. If anything is left, we copy it one byte at a time.
*/
RESTORE_ASI(%i3)
brz,pt %i2, 85f
sub %o0, %i1, %i3
ba,a,pt %XCC, 90f
arch/sparc: Avoid DCTI Couples Avoid un-intended DCTI Couples. Use of DCTI couples is deprecated. Also address the "Programming Note" for optimal performance. Here is the complete text from Oracle SPARC Architecture Specs. 6.3.4.7 DCTI Couples "A delayed control transfer instruction (DCTI) in the delay slot of another DCTI is referred to as a “DCTI couple”. The use of DCTI couples is deprecated in the Oracle SPARC Architecture; no new software should place a DCTI in the delay slot of another DCTI, because on future Oracle SPARC Architecture implementations DCTI couples may execute either slowly or differently than the programmer assumes it will. SPARC V8 and SPARC V9 Compatibility Note The SPARC V8 architecture left behavior undefined for a DCTI couple. The SPARC V9 architecture defined behavior in that case, but as of UltraSPARC Architecture 2005, use of DCTI couples was deprecated. Software should not expect high performance from DCTI couples, and performance of DCTI couples should be expected to decline further in future processors. Programming Note As noted in TABLE 6-5 on page 115, an annulled branch-always (branch-always with a = 1) instruction is not architecturally a DCTI. However, since not all implementations make that distinction, for optimal performance, a DCTI should not be placed in the instruction word immediately following an annulled branch-always instruction (BA,A or BPA,A)." Signed-off-by: Babu Moger <babu.moger@oracle.com> Reviewed-by: Rob Gardner <rob.gardner@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-18 04:52:21 +08:00
nop
.align 64
70: /* 16 < len <= 64 */
bne,pn %XCC, 75f
sub %o0, %i1, %i3
72:
andn %i2, 0xf, %i4
and %i2, 0xf, %i2
1: subcc %i4, 0x10, %i4
EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4)
add %i1, 0x08, %i1
EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4)
sub %i1, 0x08, %i1
EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4)
add %i1, 0x8, %i1
EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8)
bgu,pt %XCC, 1b
add %i1, 0x8, %i1
73: andcc %i2, 0x8, %g0
be,pt %XCC, 1f
nop
sub %i2, 0x8, %i2
EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8)
EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8)
add %i1, 0x8, %i1
1: andcc %i2, 0x4, %g0
be,pt %XCC, 1f
nop
sub %i2, 0x4, %i2
EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4)
EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4)
add %i1, 0x4, %i1
1: cmp %i2, 0
be,pt %XCC, 85f
nop
ba,pt %xcc, 90f
nop
75:
andcc %o0, 0x7, %g1
sub %g1, 0x8, %g1
be,pn %icc, 2f
sub %g0, %g1, %g1
sub %i2, %g1, %i2
1: subcc %g1, 1, %g1
EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1)
EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1)
bgu,pt %icc, 1b
add %i1, 1, %i1
2: add %i1, %i3, %o0
andcc %i1, 0x7, %g1
bne,pt %icc, 8f
sll %g1, 3, %g1
cmp %i2, 16
bgeu,pt %icc, 72b
nop
ba,a,pt %xcc, 73b
8: mov 64, %i3
andn %i1, 0x7, %i1
EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2)
sub %i3, %g1, %i3
andn %i2, 0x7, %i4
sllx %g2, %g1, %g2
1: add %i1, 0x8, %i1
EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4)
subcc %i4, 0x8, %i4
srlx %g3, %i3, %i5
or %i5, %g2, %i5
EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
srl %g1, 3, %g1
andcc %i2, 0x7, %i2
be,pn %icc, 85f
add %i1, %g1, %i1
ba,pt %xcc, 90f
sub %o0, %i1, %i3
.align 64
80: /* 0 < len <= 16 */
andcc %i3, 0x3, %g0
bne,pn %XCC, 90f
sub %o0, %i1, %i3
1:
subcc %i2, 4, %i2
EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4)
EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4)
bgu,pt %XCC, 1b
add %i1, 4, %i1
85: ret
restore EX_RETVAL(%i0), %g0, %o0
.align 32
90:
subcc %i2, 1, %i2
EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1)
EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1)
bgu,pt %XCC, 90b
add %i1, 1, %i1
ret
restore EX_RETVAL(%i0), %g0, %o0
.size FUNC_NAME, .-FUNC_NAME