diff options
Diffstat (limited to 'arch/arm64/include/asm/fpsimdmacros.h')
| -rw-r--r-- | arch/arm64/include/asm/fpsimdmacros.h | 119 |
1 files changed, 112 insertions, 7 deletions
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 059204477ce6..cda81d009c9b 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -93,7 +93,14 @@ .endif .endm +.macro _sme_check_wv v + .if (\v) < 12 || (\v) > 15 + .error "Bad vector select register \v." + .endif +.endm + /* SVE instruction encodings for non-SVE-capable assemblers */ +/* (pre binutils 2.28, all kernel capable clang versions support SVE) */ /* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */ .macro _sve_str_v nz, nxbase, offset=0 @@ -173,6 +180,68 @@ | (\np) .endm +/* SME instruction encodings for non-SME-capable assemblers */ +/* (pre binutils 2.38/LLVM 13) */ + +/* RDSVL X\nx, #\imm */ +.macro _sme_rdsvl nx, imm + _check_general_reg \nx + _check_num (\imm), -0x20, 0x1f + .inst 0x04bf5800 \ + | (\nx) \ + | (((\imm) & 0x3f) << 5) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_str_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_ldr_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * LDR (ZT0) + * + * LDR ZT0, nx + */ +.macro _ldr_zt nx + _check_general_reg \nx + .inst 0xe11f8000 \ + | (\nx << 5) +.endm + +/* + * STR (ZT0) + * + * STR ZT0, nx + */ +.macro _str_zt nx + _check_general_reg \nx + .inst 0xe13f8000 \ + | (\nx << 5) +.endm + .macro __for from:req, to:req .if (\from) == (\to) _for__body %\from @@ -207,6 +276,17 @@ 921: .endm +/* Update SMCR_EL1.LEN with the new VQ */ +.macro sme_load_vq xvqminus1, xtmp, xtmp2 + mrs_s \xtmp, SYS_SMCR_EL1 + bic \xtmp2, \xtmp, SMCR_ELx_LEN_MASK + orr \xtmp2, \xtmp2, \xvqminus1 + cmp \xtmp2, \xtmp + b.eq 921f + msr_s SYS_SMCR_EL1, \xtmp2 //self-synchronising +921: +.endm + /* Preserve the first 128-bits of Znz and zero the rest. */ .macro _sve_flush_z nz _sve_check_zreg \nz @@ -216,28 +296,36 @@ .macro sve_flush_z _for n, 0, 31, _sve_flush_z \n .endm -.macro sve_flush_p_ffr +.macro sve_flush_p _for n, 0, 15, _sve_pfalse \n +.endm +.macro sve_flush_ffr _sve_wrffr 0 .endm -.macro sve_save nxbase, xpfpsr, nxtmp +.macro sve_save nxbase, xpfpsr, save_ffr, nxtmp _for n, 0, 31, _sve_str_v \n, \nxbase, \n - 34 _for n, 0, 15, _sve_str_p \n, \nxbase, \n - 16 + cbz \save_ffr, 921f _sve_rdffr 0 + b 922f +921: + _sve_pfalse 0 // Zero out FFR +922: _sve_str_p 0, \nxbase _sve_ldr_p 0, \nxbase, -16 - mrs x\nxtmp, fpsr str w\nxtmp, [\xpfpsr] mrs x\nxtmp, fpcr str w\nxtmp, [\xpfpsr, #4] .endm -.macro __sve_load nxbase, xpfpsr, nxtmp +.macro sve_load nxbase, xpfpsr, restore_ffr, nxtmp _for n, 0, 31, _sve_ldr_v \n, \nxbase, \n - 34 + cbz \restore_ffr, 921f _sve_ldr_p 0, \nxbase _sve_wrffr 0 +921: _for n, 0, 15, _sve_ldr_p \n, \nxbase, \n - 16 ldr w\nxtmp, [\xpfpsr] @@ -246,7 +334,24 @@ msr fpcr, x\nxtmp .endm -.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp, xtmp2 - sve_load_vq \xvqminus1, x\nxtmp, \xtmp2 - __sve_load \nxbase, \xpfpsr, \nxtmp +.macro sme_save_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_str_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm + +.macro sme_load_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_ldr_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b .endm |