summaryrefslogtreecommitdiff
path: root/arch/sparc/lib/checksum_32.S
diff options
context:
space:
mode:
Diffstat (limited to 'arch/sparc/lib/checksum_32.S')
-rw-r--r--arch/sparc/lib/checksum_32.S262
1 files changed, 65 insertions, 197 deletions
diff --git a/arch/sparc/lib/checksum_32.S b/arch/sparc/lib/checksum_32.S
index 0084c3361e15..66eda40fce36 100644
--- a/arch/sparc/lib/checksum_32.S
+++ b/arch/sparc/lib/checksum_32.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/* checksum.S: Sparc optimized checksum code.
*
* Copyright(C) 1995 Linus Torvalds
@@ -13,6 +14,7 @@
* BSD4.4 portable checksum routine
*/
+#include <linux/export.h>
#include <asm/errno.h>
#define CSUM_BIGCHUNK(buf, offset, sum, t0, t1, t2, t3, t4, t5) \
@@ -104,6 +106,7 @@ csum_partial_fix_alignment:
* buffer of size 0x20. Follow the code path for that case.
*/
.globl csum_partial
+ EXPORT_SYMBOL(csum_partial)
csum_partial: /* %o0=buf, %o1=len, %o2=sum */
andcc %o0, 0x7, %g0 ! alignment problems?
bne csum_partial_fix_alignment ! yep, handle it
@@ -141,44 +144,14 @@ cpte: bne csum_partial_end_cruft ! yep, handle it
cpout: retl ! get outta here
mov %o2, %o0 ! return computed csum
- .globl __csum_partial_copy_start, __csum_partial_copy_end
-__csum_partial_copy_start:
-
/* Work around cpp -rob */
#define ALLOC #alloc
#define EXECINSTR #execinstr
-#define EX(x,y,a,b) \
-98: x,y; \
- .section .fixup,ALLOC,EXECINSTR; \
- .align 4; \
-99: ba 30f; \
- a, b, %o3; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 99b; \
- .text; \
- .align 4
-
-#define EX2(x,y) \
-98: x,y; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 30f; \
- .text; \
- .align 4
-
-#define EX3(x,y) \
+#define EX(x,y) \
98: x,y; \
.section __ex_table,ALLOC; \
.align 4; \
- .word 98b, 96f; \
- .text; \
- .align 4
-
-#define EXT(start,end,handler) \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word start, 0, end, handler; \
+ .word 98b, cc_fault; \
.text; \
.align 4
@@ -189,20 +162,20 @@ __csum_partial_copy_start:
* please check the fixup code below as well.
*/
#define CSUMCOPY_BIGCHUNK_ALIGNED(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [src + off + 0x00], t0; \
- ldd [src + off + 0x08], t2; \
+ EX(ldd [src + off + 0x00], t0); \
+ EX(ldd [src + off + 0x08], t2); \
addxcc t0, sum, sum; \
- ldd [src + off + 0x10], t4; \
+ EX(ldd [src + off + 0x10], t4); \
addxcc t1, sum, sum; \
- ldd [src + off + 0x18], t6; \
+ EX(ldd [src + off + 0x18], t6); \
addxcc t2, sum, sum; \
- std t0, [dst + off + 0x00]; \
+ EX(std t0, [dst + off + 0x00]); \
addxcc t3, sum, sum; \
- std t2, [dst + off + 0x08]; \
+ EX(std t2, [dst + off + 0x08]); \
addxcc t4, sum, sum; \
- std t4, [dst + off + 0x10]; \
+ EX(std t4, [dst + off + 0x10]); \
addxcc t5, sum, sum; \
- std t6, [dst + off + 0x18]; \
+ EX(std t6, [dst + off + 0x18]); \
addxcc t6, sum, sum; \
addxcc t7, sum, sum;
@@ -211,59 +184,59 @@ __csum_partial_copy_start:
* Viking MXCC into streaming mode. Ho hum...
*/
#define CSUMCOPY_BIGCHUNK(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [src + off + 0x00], t0; \
- ldd [src + off + 0x08], t2; \
- ldd [src + off + 0x10], t4; \
- ldd [src + off + 0x18], t6; \
- st t0, [dst + off + 0x00]; \
+ EX(ldd [src + off + 0x00], t0); \
+ EX(ldd [src + off + 0x08], t2); \
+ EX(ldd [src + off + 0x10], t4); \
+ EX(ldd [src + off + 0x18], t6); \
+ EX(st t0, [dst + off + 0x00]); \
addxcc t0, sum, sum; \
- st t1, [dst + off + 0x04]; \
+ EX(st t1, [dst + off + 0x04]); \
addxcc t1, sum, sum; \
- st t2, [dst + off + 0x08]; \
+ EX(st t2, [dst + off + 0x08]); \
addxcc t2, sum, sum; \
- st t3, [dst + off + 0x0c]; \
+ EX(st t3, [dst + off + 0x0c]); \
addxcc t3, sum, sum; \
- st t4, [dst + off + 0x10]; \
+ EX(st t4, [dst + off + 0x10]); \
addxcc t4, sum, sum; \
- st t5, [dst + off + 0x14]; \
+ EX(st t5, [dst + off + 0x14]); \
addxcc t5, sum, sum; \
- st t6, [dst + off + 0x18]; \
+ EX(st t6, [dst + off + 0x18]); \
addxcc t6, sum, sum; \
- st t7, [dst + off + 0x1c]; \
+ EX(st t7, [dst + off + 0x1c]); \
addxcc t7, sum, sum;
/* Yuck, 6 superscalar cycles... */
#define CSUMCOPY_LASTCHUNK(src, dst, sum, off, t0, t1, t2, t3) \
- ldd [src - off - 0x08], t0; \
- ldd [src - off - 0x00], t2; \
+ EX(ldd [src - off - 0x08], t0); \
+ EX(ldd [src - off - 0x00], t2); \
addxcc t0, sum, sum; \
- st t0, [dst - off - 0x08]; \
+ EX(st t0, [dst - off - 0x08]); \
addxcc t1, sum, sum; \
- st t1, [dst - off - 0x04]; \
+ EX(st t1, [dst - off - 0x04]); \
addxcc t2, sum, sum; \
- st t2, [dst - off - 0x00]; \
+ EX(st t2, [dst - off - 0x00]); \
addxcc t3, sum, sum; \
- st t3, [dst - off + 0x04];
+ EX(st t3, [dst - off + 0x04]);
/* Handle the end cruft code out of band for better cache patterns. */
cc_end_cruft:
be 1f
andcc %o3, 4, %g0
- EX(ldd [%o0 + 0x00], %g2, and %o3, 0xf)
+ EX(ldd [%o0 + 0x00], %g2)
add %o1, 8, %o1
addcc %g2, %g7, %g7
add %o0, 8, %o0
addxcc %g3, %g7, %g7
- EX2(st %g2, [%o1 - 0x08])
+ EX(st %g2, [%o1 - 0x08])
addx %g0, %g7, %g7
andcc %o3, 4, %g0
- EX2(st %g3, [%o1 - 0x04])
+ EX(st %g3, [%o1 - 0x04])
1: be 1f
andcc %o3, 3, %o3
- EX(ld [%o0 + 0x00], %g2, add %o3, 4)
+ EX(ld [%o0 + 0x00], %g2)
add %o1, 4, %o1
addcc %g2, %g7, %g7
- EX2(st %g2, [%o1 - 0x04])
+ EX(st %g2, [%o1 - 0x04])
addx %g0, %g7, %g7
andcc %o3, 3, %g0
add %o0, 4, %o0
@@ -273,14 +246,14 @@ cc_end_cruft:
subcc %o3, 2, %o3
b 4f
or %g0, %g0, %o4
-2: EX(lduh [%o0 + 0x00], %o4, add %o3, 2)
+2: EX(lduh [%o0 + 0x00], %o4)
add %o0, 2, %o0
- EX2(sth %o4, [%o1 + 0x00])
+ EX(sth %o4, [%o1 + 0x00])
be 6f
add %o1, 2, %o1
sll %o4, 16, %o4
-4: EX(ldub [%o0 + 0x00], %o5, add %g0, 1)
- EX2(stb %o5, [%o1 + 0x00])
+4: EX(ldub [%o0 + 0x00], %o5)
+ EX(stb %o5, [%o1 + 0x00])
sll %o5, 8, %o5
or %o5, %o4, %o4
6: addcc %o4, %g7, %g7
@@ -303,9 +276,9 @@ cc_dword_align:
andcc %o0, 0x2, %g0
be 1f
andcc %o0, 0x4, %g0
- EX(lduh [%o0 + 0x00], %g4, add %g1, 0)
+ EX(lduh [%o0 + 0x00], %g4)
sub %g1, 2, %g1
- EX2(sth %g4, [%o1 + 0x00])
+ EX(sth %g4, [%o1 + 0x00])
add %o0, 2, %o0
sll %g4, 16, %g4
addcc %g4, %g7, %g7
@@ -319,9 +292,9 @@ cc_dword_align:
or %g3, %g7, %g7
1: be 3f
andcc %g1, 0xffffff80, %g0
- EX(ld [%o0 + 0x00], %g4, add %g1, 0)
+ EX(ld [%o0 + 0x00], %g4)
sub %g1, 4, %g1
- EX2(st %g4, [%o1 + 0x00])
+ EX(st %g4, [%o1 + 0x00])
add %o0, 4, %o0
addcc %g4, %g7, %g7
add %o1, 4, %o1
@@ -335,6 +308,7 @@ cc_dword_align:
*/
.align 8
.globl __csum_partial_copy_sparc_generic
+ EXPORT_SYMBOL(__csum_partial_copy_sparc_generic)
__csum_partial_copy_sparc_generic:
/* %o0=src, %o1=dest, %g1=len, %g7=sum */
xor %o0, %o1, %o4 ! get changing bits
@@ -350,7 +324,6 @@ __csum_partial_copy_sparc_generic:
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-10: EXT(5b, 10b, 20f) ! note for exception handling
sub %g1, 128, %g1 ! detract from length
addx %g0, %g7, %g7 ! add in last carry bit
andcc %g1, 0xffffff80, %g0 ! more to csum?
@@ -375,8 +348,7 @@ cctbl: CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x68,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x28,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x18,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x08,%g2,%g3,%g4,%g5)
-12: EXT(cctbl, 12b, 22f) ! note for exception table handling
- addx %g0, %g7, %g7
+12: addx %g0, %g7, %g7
andcc %o3, 0xf, %g0 ! check for low bits set
ccte: bne cc_end_cruft ! something left, handle it out of band
andcc %o3, 8, %g0 ! begin checks for that code
@@ -386,7 +358,6 @@ ccdbl: CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x00,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-11: EXT(ccdbl, 11b, 21f) ! note for exception table handling
sub %g1, 128, %g1 ! detract from length
addx %g0, %g7, %g7 ! add in last carry bit
andcc %g1, 0xffffff80, %g0 ! more to csum?
@@ -403,9 +374,9 @@ ccslow: cmp %g1, 0
be,a 1f
srl %g1, 1, %g4
sub %g1, 1, %g1
- EX(ldub [%o0], %g5, add %g1, 1)
+ EX(ldub [%o0], %g5)
add %o0, 1, %o0
- EX2(stb %g5, [%o1])
+ EX(stb %g5, [%o1])
srl %g1, 1, %g4
add %o1, 1, %o1
1: cmp %g4, 0
@@ -414,34 +385,34 @@ ccslow: cmp %g1, 0
andcc %o0, 2, %g0
be,a 1f
srl %g4, 1, %g4
- EX(lduh [%o0], %o4, add %g1, 0)
+ EX(lduh [%o0], %o4)
sub %g1, 2, %g1
srl %o4, 8, %g2
sub %g4, 1, %g4
- EX2(stb %g2, [%o1])
+ EX(stb %g2, [%o1])
add %o4, %g5, %g5
- EX2(stb %o4, [%o1 + 1])
+ EX(stb %o4, [%o1 + 1])
add %o0, 2, %o0
srl %g4, 1, %g4
add %o1, 2, %o1
1: cmp %g4, 0
be,a 2f
andcc %g1, 2, %g0
- EX3(ld [%o0], %o4)
+ EX(ld [%o0], %o4)
5: srl %o4, 24, %g2
srl %o4, 16, %g3
- EX2(stb %g2, [%o1])
+ EX(stb %g2, [%o1])
srl %o4, 8, %g2
- EX2(stb %g3, [%o1 + 1])
+ EX(stb %g3, [%o1 + 1])
add %o0, 4, %o0
- EX2(stb %g2, [%o1 + 2])
+ EX(stb %g2, [%o1 + 2])
addcc %o4, %g5, %g5
- EX2(stb %o4, [%o1 + 3])
+ EX(stb %o4, [%o1 + 3])
addx %g5, %g0, %g5 ! I am now to lazy to optimize this (question it
add %o1, 4, %o1 ! is worthy). Maybe some day - with the sll/srl
subcc %g4, 1, %g4 ! tricks
bne,a 5b
- EX3(ld [%o0], %o4)
+ EX(ld [%o0], %o4)
sll %g5, 16, %g2
srl %g5, 16, %g5
srl %g2, 16, %g2
@@ -449,19 +420,19 @@ ccslow: cmp %g1, 0
add %g2, %g5, %g5
2: be,a 3f
andcc %g1, 1, %g0
- EX(lduh [%o0], %o4, and %g1, 3)
+ EX(lduh [%o0], %o4)
andcc %g1, 1, %g0
srl %o4, 8, %g2
add %o0, 2, %o0
- EX2(stb %g2, [%o1])
+ EX(stb %g2, [%o1])
add %g5, %o4, %g5
- EX2(stb %o4, [%o1 + 1])
+ EX(stb %o4, [%o1 + 1])
add %o1, 2, %o1
3: be,a 1f
sll %g5, 16, %o4
- EX(ldub [%o0], %g2, add %g0, 1)
+ EX(ldub [%o0], %g2)
sll %g2, 8, %o4
- EX2(stb %g2, [%o1])
+ EX(stb %g2, [%o1])
add %g5, %o4, %g5
sll %g5, 16, %o4
1: addcc %o4, %g5, %g5
@@ -477,113 +448,10 @@ ccslow: cmp %g1, 0
4: addcc %g7, %g5, %g7
retl
addx %g0, %g7, %o0
-__csum_partial_copy_end:
/* We do these strange calculations for the csum_*_from_user case only, ie.
* we only bother with faults on loads... */
-/* o2 = ((g2%20)&3)*8
- * o3 = g1 - (g2/20)*32 - o2 */
-20:
- cmp %g2, 20
- blu,a 1f
- and %g2, 3, %o2
- sub %g1, 32, %g1
- b 20b
- sub %g2, 20, %g2
-1:
- sll %o2, 3, %o2
- b 31f
- sub %g1, %o2, %o3
-
-/* o2 = (!(g2 & 15) ? 0 : (((g2 & 15) + 1) & ~1)*8)
- * o3 = g1 - (g2/16)*32 - o2 */
-21:
- andcc %g2, 15, %o3
- srl %g2, 4, %g2
- be,a 1f
- clr %o2
- add %o3, 1, %o3
- and %o3, 14, %o3
- sll %o3, 3, %o2
-1:
- sll %g2, 5, %g2
- sub %g1, %g2, %o3
- b 31f
- sub %o3, %o2, %o3
-
-/* o0 += (g2/10)*16 - 0x70
- * 01 += (g2/10)*16 - 0x70
- * o2 = (g2 % 10) ? 8 : 0
- * o3 += 0x70 - (g2/10)*16 - o2 */
-22:
- cmp %g2, 10
- blu,a 1f
- sub %o0, 0x70, %o0
- add %o0, 16, %o0
- add %o1, 16, %o1
- sub %o3, 16, %o3
- b 22b
- sub %g2, 10, %g2
-1:
- sub %o1, 0x70, %o1
- add %o3, 0x70, %o3
- clr %o2
- tst %g2
- bne,a 1f
- mov 8, %o2
-1:
- b 31f
- sub %o3, %o2, %o3
-96:
- and %g1, 3, %g1
- sll %g4, 2, %g4
- add %g1, %g4, %o3
-30:
-/* %o1 is dst
- * %o3 is # bytes to zero out
- * %o4 is faulting address
- * %o5 is %pc where fault occurred */
- clr %o2
-31:
-/* %o0 is src
- * %o1 is dst
- * %o2 is # of bytes to copy from src to dst
- * %o3 is # bytes to zero out
- * %o4 is faulting address
- * %o5 is %pc where fault occurred */
- save %sp, -104, %sp
- mov %i5, %o0
- mov %i7, %o1
- mov %i4, %o2
- call lookup_fault
- mov %g7, %i4
- cmp %o0, 2
- bne 1f
- add %g0, -EFAULT, %i5
- tst %i2
- be 2f
- mov %i0, %o1
- mov %i1, %o0
-5:
- call memcpy
- mov %i2, %o2
- tst %o0
- bne,a 2f
- add %i3, %i2, %i3
- add %i1, %i2, %i1
-2:
- mov %i1, %o0
-6:
- call __bzero
- mov %i3, %o1
-1:
- ld [%sp + 168], %o2 ! struct_ptr of parent
- st %i5, [%o2]
- ret
- restore
-
- .section __ex_table,#alloc
- .align 4
- .word 5b,2
- .word 6b,2
+cc_fault:
+ retl
+ clr %o0
generated by cgit (git 2.34.1) at 2025-12-27 07:01:21 +0000