summaryrefslogtreecommitdiff
path: root/arch/sparc/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/sparc/lib')
-rw-r--r--arch/sparc/lib/M7memcpy.S20
-rw-r--r--arch/sparc/lib/Makefile2
-rw-r--r--arch/sparc/lib/Memcpy_utils.S9
-rw-r--r--arch/sparc/lib/NG4memcpy.S2
-rw-r--r--arch/sparc/lib/NGmemcpy.S29
-rw-r--r--arch/sparc/lib/U1memcpy.S19
-rw-r--r--arch/sparc/lib/U3memcpy.S2
7 files changed, 50 insertions, 33 deletions
diff --git a/arch/sparc/lib/M7memcpy.S b/arch/sparc/lib/M7memcpy.S
index cbd42ea7c3f7..99357bfa8e82 100644
--- a/arch/sparc/lib/M7memcpy.S
+++ b/arch/sparc/lib/M7memcpy.S
@@ -696,16 +696,16 @@ FUNC_NAME:
EX_LD_FP(LOAD(ldd, %o4+40, %f26), memcpy_retl_o2_plus_o5_plus_40)
faligndata %f24, %f26, %f10
EX_ST_FP(STORE(std, %f6, %o0+24), memcpy_retl_o2_plus_o5_plus_40)
- EX_LD_FP(LOAD(ldd, %o4+48, %f28), memcpy_retl_o2_plus_o5_plus_40)
+ EX_LD_FP(LOAD(ldd, %o4+48, %f28), memcpy_retl_o2_plus_o5_plus_32)
faligndata %f26, %f28, %f12
- EX_ST_FP(STORE(std, %f8, %o0+32), memcpy_retl_o2_plus_o5_plus_40)
+ EX_ST_FP(STORE(std, %f8, %o0+32), memcpy_retl_o2_plus_o5_plus_32)
add %o4, 64, %o4
- EX_LD_FP(LOAD(ldd, %o4-8, %f30), memcpy_retl_o2_plus_o5_plus_40)
+ EX_LD_FP(LOAD(ldd, %o4-8, %f30), memcpy_retl_o2_plus_o5_plus_24)
faligndata %f28, %f30, %f14
- EX_ST_FP(STORE(std, %f10, %o0+40), memcpy_retl_o2_plus_o5_plus_40)
- EX_ST_FP(STORE(std, %f12, %o0+48), memcpy_retl_o2_plus_o5_plus_40)
+ EX_ST_FP(STORE(std, %f10, %o0+40), memcpy_retl_o2_plus_o5_plus_24)
+ EX_ST_FP(STORE(std, %f12, %o0+48), memcpy_retl_o2_plus_o5_plus_16)
add %o0, 64, %o0
- EX_ST_FP(STORE(std, %f14, %o0-8), memcpy_retl_o2_plus_o5_plus_40)
+ EX_ST_FP(STORE(std, %f14, %o0-8), memcpy_retl_o2_plus_o5_plus_8)
fsrc2 %f30, %f14
bgu,pt %xcc, .Lunalign_sloop
prefetch [%o4 + (8 * BLOCK_SIZE)], 20
@@ -728,7 +728,7 @@ FUNC_NAME:
add %o4, 8, %o4
faligndata %f0, %f2, %f16
subcc %o5, 8, %o5
- EX_ST_FP(STORE(std, %f16, %o0), memcpy_retl_o2_plus_o5)
+ EX_ST_FP(STORE(std, %f16, %o0), memcpy_retl_o2_plus_o5_plus_8)
fsrc2 %f2, %f0
bgu,pt %xcc, .Lunalign_by8
add %o0, 8, %o0
@@ -772,7 +772,7 @@ FUNC_NAME:
subcc %o5, 0x20, %o5
EX_ST(STORE(stx, %o3, %o0 + 0x00), memcpy_retl_o2_plus_o5_plus_32)
EX_ST(STORE(stx, %g2, %o0 + 0x08), memcpy_retl_o2_plus_o5_plus_24)
- EX_ST(STORE(stx, %g7, %o0 + 0x10), memcpy_retl_o2_plus_o5_plus_24)
+ EX_ST(STORE(stx, %g7, %o0 + 0x10), memcpy_retl_o2_plus_o5_plus_16)
EX_ST(STORE(stx, %o4, %o0 + 0x18), memcpy_retl_o2_plus_o5_plus_8)
bne,pt %xcc, 1b
add %o0, 0x20, %o0
@@ -804,12 +804,12 @@ FUNC_NAME:
brz,pt %o3, 2f
sub %o2, %o3, %o2
-1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), memcpy_retl_o2_plus_g1)
+1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), memcpy_retl_o2_plus_o3)
add %o1, 1, %o1
subcc %o3, 1, %o3
add %o0, 1, %o0
bne,pt %xcc, 1b
- EX_ST(STORE(stb, %g2, %o0 - 0x01), memcpy_retl_o2_plus_g1_plus_1)
+ EX_ST(STORE(stb, %g2, %o0 - 0x01), memcpy_retl_o2_plus_o3_plus_1)
2:
and %o1, 0x7, %o3
brz,pn %o3, .Lmedium_noprefetch_cp
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index ee5091dd67ed..783bdec0d7be 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -2,7 +2,7 @@
# Makefile for Sparc library files..
#
-asflags-y := -ansi -DST_DIV0=0x02
+asflags-y := -DST_DIV0=0x02
lib-$(CONFIG_SPARC32) += ashrdi3.o
lib-$(CONFIG_SPARC32) += memcpy.o memset.o
diff --git a/arch/sparc/lib/Memcpy_utils.S b/arch/sparc/lib/Memcpy_utils.S
index 64fbac28b3db..207343367bb2 100644
--- a/arch/sparc/lib/Memcpy_utils.S
+++ b/arch/sparc/lib/Memcpy_utils.S
@@ -137,6 +137,15 @@ ENTRY(memcpy_retl_o2_plus_63_8)
ba,pt %xcc, __restore_asi
add %o2, 8, %o0
ENDPROC(memcpy_retl_o2_plus_63_8)
+ENTRY(memcpy_retl_o2_plus_o3)
+ ba,pt %xcc, __restore_asi
+ add %o2, %o3, %o0
+ENDPROC(memcpy_retl_o2_plus_o3)
+ENTRY(memcpy_retl_o2_plus_o3_plus_1)
+ add %o3, 1, %o3
+ ba,pt %xcc, __restore_asi
+ add %o2, %o3, %o0
+ENDPROC(memcpy_retl_o2_plus_o3_plus_1)
ENTRY(memcpy_retl_o2_plus_o5)
ba,pt %xcc, __restore_asi
add %o2, %o5, %o0
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 7ad58ebe0d00..df0ec1bd1948 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -281,7 +281,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
subcc %o5, 0x20, %o5
EX_ST(STORE(stx, %g1, %o0 + 0x00), memcpy_retl_o2_plus_o5_plus_32)
EX_ST(STORE(stx, %g2, %o0 + 0x08), memcpy_retl_o2_plus_o5_plus_24)
- EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), memcpy_retl_o2_plus_o5_plus_24)
+ EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), memcpy_retl_o2_plus_o5_plus_16)
EX_ST(STORE(stx, %o4, %o0 + 0x18), memcpy_retl_o2_plus_o5_plus_8)
bne,pt %icc, 1b
add %o0, 0x20, %o0
diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index ee51c1230689..bbd3ea0a6482 100644
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -79,8 +79,8 @@
#ifndef EX_RETVAL
#define EX_RETVAL(x) x
__restore_asi:
- ret
wr %g0, ASI_AIUS, %asi
+ ret
restore
ENTRY(NG_ret_i2_plus_i4_plus_1)
ba,pt %xcc, __restore_asi
@@ -125,15 +125,16 @@ ENTRY(NG_ret_i2_plus_g1_minus_56)
ba,pt %xcc, __restore_asi
add %i2, %g1, %i0
ENDPROC(NG_ret_i2_plus_g1_minus_56)
-ENTRY(NG_ret_i2_plus_i4)
+ENTRY(NG_ret_i2_plus_i4_plus_16)
+ add %i4, 16, %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
+ENDPROC(NG_ret_i2_plus_i4_plus_16)
+ENTRY(NG_ret_i2_plus_i4_plus_8)
+ add %i4, 8, %i4
ba,pt %xcc, __restore_asi
add %i2, %i4, %i0
-ENDPROC(NG_ret_i2_plus_i4_minus_8)
+ENDPROC(NG_ret_i2_plus_i4_plus_8)
ENTRY(NG_ret_i2_plus_8)
ba,pt %xcc, __restore_asi
add %i2, 8, %i0
@@ -160,6 +161,12 @@ ENTRY(NG_ret_i2_and_7_plus_i4)
ba,pt %xcc, __restore_asi
add %i2, %i4, %i0
ENDPROC(NG_ret_i2_and_7_plus_i4)
+ENTRY(NG_ret_i2_and_7_plus_i4_plus_8)
+ and %i2, 7, %i2
+ add %i4, 8, %i4
+ ba,pt %xcc, __restore_asi
+ add %i2, %i4, %i0
+ENDPROC(NG_ret_i2_and_7_plus_i4)
#endif
.align 64
@@ -405,13 +412,13 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
andn %i2, 0xf, %i4
and %i2, 0xf, %i2
1: subcc %i4, 0x10, %i4
- EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4)
+ EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4_plus_16)
add %i1, 0x08, %i1
- EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4)
+ EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4_plus_16)
sub %i1, 0x08, %i1
- EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4)
+ EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4_plus_16)
add %i1, 0x8, %i1
- EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8)
+ EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_plus_8)
bgu,pt %XCC, 1b
add %i1, 0x8, %i1
73: andcc %i2, 0x8, %g0
@@ -468,7 +475,7 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */
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)
+ EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4_plus_8)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index 635398ec7540..154fbd35400c 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -164,17 +164,18 @@ ENTRY(U1_gs_40_fp)
retl
add %o0, %o2, %o0
ENDPROC(U1_gs_40_fp)
-ENTRY(U1_g3_0_fp)
- VISExitHalf
- retl
- add %g3, %o2, %o0
-ENDPROC(U1_g3_0_fp)
ENTRY(U1_g3_8_fp)
VISExitHalf
add %g3, 8, %g3
retl
add %g3, %o2, %o0
ENDPROC(U1_g3_8_fp)
+ENTRY(U1_g3_16_fp)
+ VISExitHalf
+ add %g3, 16, %g3
+ retl
+ add %g3, %o2, %o0
+ENDPROC(U1_g3_16_fp)
ENTRY(U1_o2_0_fp)
VISExitHalf
retl
@@ -547,18 +548,18 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
62: FINISH_VISCHUNK(o0, f44, f46)
63: UNEVEN_VISCHUNK_LAST(o0, f46, f0)
-93: EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp)
+93: EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_8_fp)
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f0, %f2, %f8
- EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
+ EX_ST_FP(STORE(std, %f8, %o0), U1_g3_16_fp)
bl,pn %xcc, 95f
add %o0, 8, %o0
- EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp)
+ EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_8_fp)
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f2, %f0, %f8
- EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
+ EX_ST_FP(STORE(std, %f8, %o0), U1_g3_16_fp)
bge,pt %xcc, 93b
add %o0, 8, %o0
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 9248d59c734c..bace3a18f836 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -267,6 +267,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
faligndata %f10, %f12, %f26
EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2)
+ and %o2, 0x3f, %o2
subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE
add %o1, 0x40, %o1
bgu,pt %XCC, 1f
@@ -336,7 +337,6 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
* Also notice how this code is careful not to perform a
* load past the end of the src buffer.
*/
- and %o2, 0x3f, %o2
andcc %o2, 0x38, %g2
be,pn %XCC, 2f
subcc %g2, 0x8, %g2