diff options
Diffstat (limited to 'arch/mips/include/asm/asmmacro.h')
| -rw-r--r-- | arch/mips/include/asm/asmmacro.h | 195 |
1 files changed, 109 insertions, 86 deletions
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 867f924b05c7..6741673c92ca 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -235,6 +235,7 @@ .macro ld_b wd, off, base .set push .set mips32r2 + .set fp=64 .set msa ld.b $w\wd, \off(\base) .set pop @@ -243,6 +244,7 @@ .macro ld_h wd, off, base .set push .set mips32r2 + .set fp=64 .set msa ld.h $w\wd, \off(\base) .set pop @@ -251,6 +253,7 @@ .macro ld_w wd, off, base .set push .set mips32r2 + .set fp=64 .set msa ld.w $w\wd, \off(\base) .set pop @@ -268,6 +271,7 @@ .macro st_b wd, off, base .set push .set mips32r2 + .set fp=64 .set msa st.b $w\wd, \off(\base) .set pop @@ -276,6 +280,7 @@ .macro st_h wd, off, base .set push .set mips32r2 + .set fp=64 .set msa st.h $w\wd, \off(\base) .set pop @@ -284,6 +289,7 @@ .macro st_w wd, off, base .set push .set mips32r2 + .set fp=64 .set msa st.w $w\wd, \off(\base) .set pop @@ -298,21 +304,21 @@ .set pop .endm - .macro copy_u_w ws, n + .macro copy_s_w ws, n .set push .set mips32r2 .set fp=64 .set msa - copy_u.w $1, $w\ws[\n] + copy_s.w $1, $w\ws[\n] .set pop .endm - .macro copy_u_d ws, n + .macro copy_s_d ws, n .set push .set mips64r2 .set fp=64 .set msa - copy_u.d $1, $w\ws[\n] + copy_s.d $1, $w\ws[\n] .set pop .endm @@ -346,8 +352,8 @@ #define STH_MSA_INSN 0x5800081f #define STW_MSA_INSN 0x5800082f #define STD_MSA_INSN 0x5800083f -#define COPY_UW_MSA_INSN 0x58f00056 -#define COPY_UD_MSA_INSN 0x58f80056 +#define COPY_SW_MSA_INSN 0x58b00056 +#define COPY_SD_MSA_INSN 0x58b80056 #define INSERT_W_MSA_INSN 0x59300816 #define INSERT_D_MSA_INSN 0x59380816 #else @@ -361,8 +367,8 @@ #define STH_MSA_INSN 0x78000825 #define STW_MSA_INSN 0x78000826 #define STD_MSA_INSN 0x78000827 -#define COPY_UW_MSA_INSN 0x78f00059 -#define COPY_UD_MSA_INSN 0x78f80059 +#define COPY_SW_MSA_INSN 0x78b00059 +#define COPY_SD_MSA_INSN 0x78b80059 #define INSERT_W_MSA_INSN 0x79300819 #define INSERT_D_MSA_INSN 0x79380819 #endif @@ -393,7 +399,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDB_MSA_INSN | (\wd << 6) .set pop .endm @@ -402,7 +408,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDH_MSA_INSN | (\wd << 6) .set pop .endm @@ -411,7 +417,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDW_MSA_INSN | (\wd << 6) .set pop .endm @@ -420,7 +426,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDD_MSA_INSN | (\wd << 6) .set pop .endm @@ -429,7 +435,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STB_MSA_INSN | (\wd << 6) .set pop .endm @@ -438,7 +444,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STH_MSA_INSN | (\wd << 6) .set pop .endm @@ -447,7 +453,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STW_MSA_INSN | (\wd << 6) .set pop .endm @@ -456,26 +462,26 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STD_MSA_INSN | (\wd << 6) .set pop .endm - .macro copy_u_w ws, n + .macro copy_s_w ws, n .set push .set noat SET_HARDFLOAT .insn - .word COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11) + .word COPY_SW_MSA_INSN | (\n << 16) | (\ws << 11) .set pop .endm - .macro copy_u_d ws, n + .macro copy_s_d ws, n .set push .set noat SET_HARDFLOAT .insn - .word COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11) + .word COPY_SD_MSA_INSN | (\n << 16) | (\ws << 11) .set pop .endm @@ -496,41 +502,52 @@ .endm #endif +#ifdef TOOLCHAIN_SUPPORTS_MSA +#define FPR_BASE_OFFS THREAD_FPR0 +#define FPR_BASE $1 +#else +#define FPR_BASE_OFFS 0 +#define FPR_BASE \thread +#endif + .macro msa_save_all thread - st_d 0, THREAD_FPR0, \thread - st_d 1, THREAD_FPR1, \thread - st_d 2, THREAD_FPR2, \thread - st_d 3, THREAD_FPR3, \thread - st_d 4, THREAD_FPR4, \thread - st_d 5, THREAD_FPR5, \thread - st_d 6, THREAD_FPR6, \thread - st_d 7, THREAD_FPR7, \thread - st_d 8, THREAD_FPR8, \thread - st_d 9, THREAD_FPR9, \thread - st_d 10, THREAD_FPR10, \thread - st_d 11, THREAD_FPR11, \thread - st_d 12, THREAD_FPR12, \thread - st_d 13, THREAD_FPR13, \thread - st_d 14, THREAD_FPR14, \thread - st_d 15, THREAD_FPR15, \thread - st_d 16, THREAD_FPR16, \thread - st_d 17, THREAD_FPR17, \thread - st_d 18, THREAD_FPR18, \thread - st_d 19, THREAD_FPR19, \thread - st_d 20, THREAD_FPR20, \thread - st_d 21, THREAD_FPR21, \thread - st_d 22, THREAD_FPR22, \thread - st_d 23, THREAD_FPR23, \thread - st_d 24, THREAD_FPR24, \thread - st_d 25, THREAD_FPR25, \thread - st_d 26, THREAD_FPR26, \thread - st_d 27, THREAD_FPR27, \thread - st_d 28, THREAD_FPR28, \thread - st_d 29, THREAD_FPR29, \thread - st_d 30, THREAD_FPR30, \thread - st_d 31, THREAD_FPR31, \thread .set push .set noat +#ifdef TOOLCHAIN_SUPPORTS_MSA + PTR_ADDU FPR_BASE, \thread, FPR_BASE_OFFS +#endif + st_d 0, THREAD_FPR0 - FPR_BASE_OFFS, FPR_BASE + st_d 1, THREAD_FPR1 - FPR_BASE_OFFS, FPR_BASE + st_d 2, THREAD_FPR2 - FPR_BASE_OFFS, FPR_BASE + st_d 3, THREAD_FPR3 - FPR_BASE_OFFS, FPR_BASE + st_d 4, THREAD_FPR4 - FPR_BASE_OFFS, FPR_BASE + st_d 5, THREAD_FPR5 - FPR_BASE_OFFS, FPR_BASE + st_d 6, THREAD_FPR6 - FPR_BASE_OFFS, FPR_BASE + st_d 7, THREAD_FPR7 - FPR_BASE_OFFS, FPR_BASE + st_d 8, THREAD_FPR8 - FPR_BASE_OFFS, FPR_BASE + st_d 9, THREAD_FPR9 - FPR_BASE_OFFS, FPR_BASE + st_d 10, THREAD_FPR10 - FPR_BASE_OFFS, FPR_BASE + st_d 11, THREAD_FPR11 - FPR_BASE_OFFS, FPR_BASE + st_d 12, THREAD_FPR12 - FPR_BASE_OFFS, FPR_BASE + st_d 13, THREAD_FPR13 - FPR_BASE_OFFS, FPR_BASE + st_d 14, THREAD_FPR14 - FPR_BASE_OFFS, FPR_BASE + st_d 15, THREAD_FPR15 - FPR_BASE_OFFS, FPR_BASE + st_d 16, THREAD_FPR16 - FPR_BASE_OFFS, FPR_BASE + st_d 17, THREAD_FPR17 - FPR_BASE_OFFS, FPR_BASE + st_d 18, THREAD_FPR18 - FPR_BASE_OFFS, FPR_BASE + st_d 19, THREAD_FPR19 - FPR_BASE_OFFS, FPR_BASE + st_d 20, THREAD_FPR20 - FPR_BASE_OFFS, FPR_BASE + st_d 21, THREAD_FPR21 - FPR_BASE_OFFS, FPR_BASE + st_d 22, THREAD_FPR22 - FPR_BASE_OFFS, FPR_BASE + st_d 23, THREAD_FPR23 - FPR_BASE_OFFS, FPR_BASE + st_d 24, THREAD_FPR24 - FPR_BASE_OFFS, FPR_BASE + st_d 25, THREAD_FPR25 - FPR_BASE_OFFS, FPR_BASE + st_d 26, THREAD_FPR26 - FPR_BASE_OFFS, FPR_BASE + st_d 27, THREAD_FPR27 - FPR_BASE_OFFS, FPR_BASE + st_d 28, THREAD_FPR28 - FPR_BASE_OFFS, FPR_BASE + st_d 29, THREAD_FPR29 - FPR_BASE_OFFS, FPR_BASE + st_d 30, THREAD_FPR30 - FPR_BASE_OFFS, FPR_BASE + st_d 31, THREAD_FPR31 - FPR_BASE_OFFS, FPR_BASE SET_HARDFLOAT _cfcmsa $1, MSA_CSR sw $1, THREAD_MSA_CSR(\thread) @@ -543,40 +560,46 @@ SET_HARDFLOAT lw $1, THREAD_MSA_CSR(\thread) _ctcmsa MSA_CSR, $1 - .set pop - ld_d 0, THREAD_FPR0, \thread - ld_d 1, THREAD_FPR1, \thread - ld_d 2, THREAD_FPR2, \thread - ld_d 3, THREAD_FPR3, \thread - ld_d 4, THREAD_FPR4, \thread - ld_d 5, THREAD_FPR5, \thread - ld_d 6, THREAD_FPR6, \thread - ld_d 7, THREAD_FPR7, \thread - ld_d 8, THREAD_FPR8, \thread - ld_d 9, THREAD_FPR9, \thread - ld_d 10, THREAD_FPR10, \thread - ld_d 11, THREAD_FPR11, \thread - ld_d 12, THREAD_FPR12, \thread - ld_d 13, THREAD_FPR13, \thread - ld_d 14, THREAD_FPR14, \thread - ld_d 15, THREAD_FPR15, \thread - ld_d 16, THREAD_FPR16, \thread - ld_d 17, THREAD_FPR17, \thread - ld_d 18, THREAD_FPR18, \thread - ld_d 19, THREAD_FPR19, \thread - ld_d 20, THREAD_FPR20, \thread - ld_d 21, THREAD_FPR21, \thread - ld_d 22, THREAD_FPR22, \thread - ld_d 23, THREAD_FPR23, \thread - ld_d 24, THREAD_FPR24, \thread - ld_d 25, THREAD_FPR25, \thread - ld_d 26, THREAD_FPR26, \thread - ld_d 27, THREAD_FPR27, \thread - ld_d 28, THREAD_FPR28, \thread - ld_d 29, THREAD_FPR29, \thread - ld_d 30, THREAD_FPR30, \thread - ld_d 31, THREAD_FPR31, \thread - .endm +#ifdef TOOLCHAIN_SUPPORTS_MSA + PTR_ADDU FPR_BASE, \thread, FPR_BASE_OFFS +#endif + ld_d 0, THREAD_FPR0 - FPR_BASE_OFFS, FPR_BASE + ld_d 1, THREAD_FPR1 - FPR_BASE_OFFS, FPR_BASE + ld_d 2, THREAD_FPR2 - FPR_BASE_OFFS, FPR_BASE + ld_d 3, THREAD_FPR3 - FPR_BASE_OFFS, FPR_BASE + ld_d 4, THREAD_FPR4 - FPR_BASE_OFFS, FPR_BASE + ld_d 5, THREAD_FPR5 - FPR_BASE_OFFS, FPR_BASE + ld_d 6, THREAD_FPR6 - FPR_BASE_OFFS, FPR_BASE + ld_d 7, THREAD_FPR7 - FPR_BASE_OFFS, FPR_BASE + ld_d 8, THREAD_FPR8 - FPR_BASE_OFFS, FPR_BASE + ld_d 9, THREAD_FPR9 - FPR_BASE_OFFS, FPR_BASE + ld_d 10, THREAD_FPR10 - FPR_BASE_OFFS, FPR_BASE + ld_d 11, THREAD_FPR11 - FPR_BASE_OFFS, FPR_BASE + ld_d 12, THREAD_FPR12 - FPR_BASE_OFFS, FPR_BASE + ld_d 13, THREAD_FPR13 - FPR_BASE_OFFS, FPR_BASE + ld_d 14, THREAD_FPR14 - FPR_BASE_OFFS, FPR_BASE + ld_d 15, THREAD_FPR15 - FPR_BASE_OFFS, FPR_BASE + ld_d 16, THREAD_FPR16 - FPR_BASE_OFFS, FPR_BASE + ld_d 17, THREAD_FPR17 - FPR_BASE_OFFS, FPR_BASE + ld_d 18, THREAD_FPR18 - FPR_BASE_OFFS, FPR_BASE + ld_d 19, THREAD_FPR19 - FPR_BASE_OFFS, FPR_BASE + ld_d 20, THREAD_FPR20 - FPR_BASE_OFFS, FPR_BASE + ld_d 21, THREAD_FPR21 - FPR_BASE_OFFS, FPR_BASE + ld_d 22, THREAD_FPR22 - FPR_BASE_OFFS, FPR_BASE + ld_d 23, THREAD_FPR23 - FPR_BASE_OFFS, FPR_BASE + ld_d 24, THREAD_FPR24 - FPR_BASE_OFFS, FPR_BASE + ld_d 25, THREAD_FPR25 - FPR_BASE_OFFS, FPR_BASE + ld_d 26, THREAD_FPR26 - FPR_BASE_OFFS, FPR_BASE + ld_d 27, THREAD_FPR27 - FPR_BASE_OFFS, FPR_BASE + ld_d 28, THREAD_FPR28 - FPR_BASE_OFFS, FPR_BASE + ld_d 29, THREAD_FPR29 - FPR_BASE_OFFS, FPR_BASE + ld_d 30, THREAD_FPR30 - FPR_BASE_OFFS, FPR_BASE + ld_d 31, THREAD_FPR31 - FPR_BASE_OFFS, FPR_BASE + .set pop + .endm + +#undef FPR_BASE_OFFS +#undef FPR_BASE .macro msa_init_upper wd #ifdef CONFIG_64BIT |