Message ID | 20220921214439.1491510-5-stillson@rivosinc.com (mailing list archive) |
---|---|
State | New |
Headers | show |
Series | [v12,01/17] riscv: Rename __switch_to_aux -> fpu | expand |
On 9/21/22 14:43, Chris Stillson wrote: > From: Greentime Hu <greentime.hu@sifive.com> > > This patch is used to detect vector support status of CPU and use > riscv_vsize to save the size of all the vector registers. It assumes > all harts has the same capabilities in SMP system. Patch title is horrible. The meat of patch is vector state save/restore, but no users of it yet. And then there are random unrelated snippets thrown in same patch. > > [guoren@linux.alibaba.com: add has_vector checking] > Co-developed-by: Guo Ren <guoren@linux.alibaba.com> > Signed-off-by: Guo Ren <guoren@linux.alibaba.com> > Co-developed-by: Vincent Chen <vincent.chen@sifive.com> > Signed-off-by: Vincent Chen <vincent.chen@sifive.com> > Signed-off-by: Greentime Hu <greentime.hu@sifive.com> > --- > arch/riscv/include/asm/vector.h | 14 +++++ > arch/riscv/kernel/cpufeature.c | 19 +++++++ > arch/riscv/kernel/riscv_ksyms.c | 6 +++ > arch/riscv/kernel/vector.S | 93 +++++++++++++++++++++++++++++++++ > 4 files changed, 132 insertions(+) > create mode 100644 arch/riscv/include/asm/vector.h > create mode 100644 arch/riscv/kernel/vector.S > > diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h > new file mode 100644 > index 000000000000..16304b0c6a6f > --- /dev/null > +++ b/arch/riscv/include/asm/vector.h > @@ -0,0 +1,14 @@ > +/* SPDX-License-Identifier: GPL-2.0-or-later */ > +/* > + * Copyright (C) 2020 SiFive > + */ > + > +#ifndef __ASM_RISCV_VECTOR_H > +#define __ASM_RISCV_VECTOR_H > + > +#include <linux/types.h> > + > +void rvv_enable(void); > +void rvv_disable(void); > + > +#endif /* ! __ASM_RISCV_VECTOR_H */ > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > index 8d4448c2d4f4..0487ab19b234 100644 > --- a/arch/riscv/kernel/cpufeature.c > +++ b/arch/riscv/kernel/cpufeature.c > @@ -30,6 +30,14 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; > > __ro_after_init DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX); > EXPORT_SYMBOL(riscv_isa_ext_keys); > +#ifdef CONFIG_FPU > +__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_fpu); > +#endif This needs to be broken out to a FPU patch which actually uses cpu_hwcap_fpu. > +#ifdef CONFIG_VECTOR > +#include <asm/vector.h> > +__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_vector); > +unsigned long riscv_vsize __read_mostly; > +#endif I would have moved all the detection code to patch 2/17 - including the static branch definition and enable below (except for vlen stuff) > > /** > * riscv_isa_extension_base() - Get base extension word > @@ -249,6 +257,16 @@ void __init riscv_fill_hwcap(void) > if (j >= 0) > static_branch_enable(&riscv_isa_ext_keys[j]); > } > + > +#ifdef CONFIG_VECTOR > + if (elf_hwcap & COMPAT_HWCAP_ISA_V) { > + static_branch_enable(&cpu_hwcap_vector); > + /* There are 32 vector registers with vlenb length. */ > + rvv_enable(); > + riscv_vsize = csr_read(CSR_VLENB) * 32; > + rvv_disable(); > + } > +#endif > } > > #ifdef CONFIG_RISCV_ALTERNATIVE > @@ -328,3 +346,4 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, > } > } > #endif > +} > diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c > index 5ab1c7e1a6ed..3489d2a20ca3 100644 > --- a/arch/riscv/kernel/riscv_ksyms.c > +++ b/arch/riscv/kernel/riscv_ksyms.c > @@ -15,3 +15,9 @@ EXPORT_SYMBOL(memmove); > EXPORT_SYMBOL(__memset); > EXPORT_SYMBOL(__memcpy); > EXPORT_SYMBOL(__memmove); > + > +#ifdef CONFIG_VECTOR > +#include <asm/vector.h> > +EXPORT_SYMBOL(rvv_enable); > +EXPORT_SYMBOL(rvv_disable); > +#endif > diff --git a/arch/riscv/kernel/vector.S b/arch/riscv/kernel/vector.S > new file mode 100644 > index 000000000000..9f7dc70c4443 > --- /dev/null > +++ b/arch/riscv/kernel/vector.S > @@ -0,0 +1,93 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +/* > + * Copyright (C) 2012 Regents of the University of California > + * Copyright (C) 2017 SiFive > + * Copyright (C) 2019 Alibaba Group Holding Limited > + * > + * This program is free software; you can redistribute it and/or > + * modify it under the terms of the GNU General Public License > + * as published by the Free Software Foundation, version 2. > + * > + * This program is distributed in the hope that it will be useful, > + * but WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > + * GNU General Public License for more details. > + */ > + > +#include <linux/linkage.h> > + > +#include <asm/asm.h> > +#include <asm/csr.h> > +#include <asm/asm-offsets.h> > + > +#define vstatep a0 > +#define datap a1 > +#define x_vstart t0 > +#define x_vtype t1 > +#define x_vl t2 > +#define x_vcsr t3 > +#define incr t4 > +#define status t5 > + A few words here as to when is this save/restore done. Best to do this in the patch which actually uses this code. > +ENTRY(__vstate_save) > + li status, SR_VS > + csrs CSR_STATUS, status > + > + csrr x_vstart, CSR_VSTART > + csrr x_vtype, CSR_VTYPE > + csrr x_vl, CSR_VL > + csrr x_vcsr, CSR_VCSR > + vsetvli incr, x0, e8, m8, ta, ma > + vse8.v v0, (datap) > + add datap, datap, incr > + vse8.v v8, (datap) > + add datap, datap, incr > + vse8.v v16, (datap) > + add datap, datap, incr > + vse8.v v24, (datap) > + > + REG_S x_vstart, RISCV_V_STATE_VSTART(vstatep) > + REG_S x_vtype, RISCV_V_STATE_VTYPE(vstatep) > + REG_S x_vl, RISCV_V_STATE_VL(vstatep) > + REG_S x_vcsr, RISCV_V_STATE_VCSR(vstatep) > + > + csrc CSR_STATUS, status > + ret > +ENDPROC(__vstate_save) > + > +ENTRY(__vstate_restore) > + li status, SR_VS > + csrs CSR_STATUS, status > + > + vsetvli incr, x0, e8, m8, ta, ma > + vle8.v v0, (datap) > + add datap, datap, incr > + vle8.v v8, (datap) > + add datap, datap, incr > + vle8.v v16, (datap) > + add datap, datap, incr > + vle8.v v24, (datap) > + > + REG_L x_vstart, RISCV_V_STATE_VSTART(vstatep) > + REG_L x_vtype, RISCV_V_STATE_VTYPE(vstatep) > + REG_L x_vl, RISCV_V_STATE_VL(vstatep) > + REG_L x_vcsr, RISCV_V_STATE_VCSR(vstatep) > + vsetvl x0, x_vl, x_vtype > + csrw CSR_VSTART, x_vstart > + csrw CSR_VCSR, x_vcsr > + > + csrc CSR_STATUS, status > + ret > +ENDPROC(__vstate_restore) > + > +ENTRY(rvv_enable) > + li status, SR_VS > + csrs CSR_STATUS, status > + ret > +ENDPROC(rvv_enable) > + > +ENTRY(rvv_disable) > + li status, SR_VS > + csrc CSR_STATUS, status > + ret > +ENDPROC(rvv_disable)
On 9/21/22 14:43, Chris Stillson wrote: > From: Greentime Hu <greentime.hu@sifive.com> > > This patch is used to detect vector support status of CPU and use > riscv_vsize to save the size of all the vector registers. It assumes > all harts has the same capabilities in SMP system. Patch title is horrible. The meat of patch is vector state save/restore, but no users of it yet. And then there are random unrelated snippets thrown in same patch. > +#ifdef CONFIG_FPU > +__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_fpu); > +#endif This needs to be broken out to a FPU patch which actually uses cpu_hwcap_fpu. > +#ifdef CONFIG_VECTOR > +#include <asm/vector.h> > +__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_vector); > +unsigned long riscv_vsize __read_mostly; > +#endif I'd move this patch v2/17 as part of detection etc. > +#ifdef CONFIG_VECTOR > + if (elf_hwcap & COMPAT_HWCAP_ISA_V) { > + static_branch_enable(&cpu_hwcap_vector); Ditto. > + /* There are 32 vector registers with vlenb length. */ > + rvv_enable(); > + riscv_vsize = csr_read(CSR_VLENB) * 32; Ditto. > + rvv_disable(); But guess these needs to be added first as well, see below. > +#ifdef CONFIG_VECTOR > +#include <asm/vector.h> > +EXPORT_SYMBOL(rvv_enable); > +EXPORT_SYMBOL(rvv_disable); As suggested in prior review comment, we don't need to EXPORT these, for now at least. > diff --git a/arch/riscv/kernel/vector.S b/arch/riscv/kernel/vector.S > new file mode 100644 > index 000000000000..9f7dc70c4443 > --- /dev/null > +++ b/arch/riscv/kernel/vector.S > @@ -0,0 +1,93 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +/* > + * Copyright (C) 2012 Regents of the University of California > + * Copyright (C) 2017 SiFive > + * Copyright (C) 2019 Alibaba Group Holding Limited > + * > + * This program is free software; you can redistribute it and/or > + * modify it under the terms of the GNU General Public License > + * as published by the Free Software Foundation, version 2. > + * > + * This program is distributed in the hope that it will be useful, > + * but WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > + * GNU General Public License for more details. > + */ SPDX hdr ... > + > +#include <linux/linkage.h> > + > +#include <asm/asm.h> > +#include <asm/csr.h> > +#include <asm/asm-offsets.h> > + > +#define vstatep a0 > +#define datap a1 > +#define x_vstart t0 > +#define x_vtype t1 > +#define x_vl t2 > +#define x_vcsr t3 > +#define incr t4 > +#define status t5 > + A few words here as to when is this save/restore done. Perhaps best to add this code in the patch which actually uses these. > +ENTRY(__vstate_save) > + li status, SR_VS > + csrs CSR_STATUS, status > + > + csrr x_vstart, CSR_VSTART > + csrr x_vtype, CSR_VTYPE > + csrr x_vl, CSR_VL > + csrr x_vcsr, CSR_VCSR > + vsetvli incr, x0, e8, m8, ta, ma > + vse8.v v0, (datap) > + add datap, datap, incr > + vse8.v v8, (datap) > + add datap, datap, incr > + vse8.v v16, (datap) > + add datap, datap, incr > + vse8.v v24, (datap) > + > + REG_S x_vstart, RISCV_V_STATE_VSTART(vstatep) > + REG_S x_vtype, RISCV_V_STATE_VTYPE(vstatep) > + REG_S x_vl, RISCV_V_STATE_VL(vstatep) > + REG_S x_vcsr, RISCV_V_STATE_VCSR(vstatep) > + > + csrc CSR_STATUS, status > + ret > +ENDPROC(__vstate_save) > + > +ENTRY(__vstate_restore) > + li status, SR_VS > + csrs CSR_STATUS, status This is rvv_enable code duplicated inline. > + > + vsetvli incr, x0, e8, m8, ta, ma > + vle8.v v0, (datap) > + add datap, datap, incr > + vle8.v v8, (datap) > + add datap, datap, incr > + vle8.v v16, (datap) > + add datap, datap, incr > + vle8.v v24, (datap) > + > + REG_L x_vstart, RISCV_V_STATE_VSTART(vstatep) > + REG_L x_vtype, RISCV_V_STATE_VTYPE(vstatep) > + REG_L x_vl, RISCV_V_STATE_VL(vstatep) > + REG_L x_vcsr, RISCV_V_STATE_VCSR(vstatep) > + vsetvl x0, x_vl, x_vtype > + csrw CSR_VSTART, x_vstart > + csrw CSR_VCSR, x_vcsr > + > + csrc CSR_STATUS, status > + ret > +ENDPROC(__vstate_restore) > + > +ENTRY(rvv_enable) > + li status, SR_VS > + csrs CSR_STATUS, status > + ret > +ENDPROC(rvv_enable) > + > +ENTRY(rvv_disable) > + li status, SR_VS > + csrc CSR_STATUS, status > + ret > +ENDPROC(rvv_disable) I'd suggest these be made asm macros, to avoid function call overhead and duplication as in save/restore above.
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h new file mode 100644 index 000000000000..16304b0c6a6f --- /dev/null +++ b/arch/riscv/include/asm/vector.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 SiFive + */ + +#ifndef __ASM_RISCV_VECTOR_H +#define __ASM_RISCV_VECTOR_H + +#include <linux/types.h> + +void rvv_enable(void); +void rvv_disable(void); + +#endif /* ! __ASM_RISCV_VECTOR_H */ diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 8d4448c2d4f4..0487ab19b234 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -30,6 +30,14 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; __ro_after_init DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX); EXPORT_SYMBOL(riscv_isa_ext_keys); +#ifdef CONFIG_FPU +__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_fpu); +#endif +#ifdef CONFIG_VECTOR +#include <asm/vector.h> +__ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_vector); +unsigned long riscv_vsize __read_mostly; +#endif /** * riscv_isa_extension_base() - Get base extension word @@ -249,6 +257,16 @@ void __init riscv_fill_hwcap(void) if (j >= 0) static_branch_enable(&riscv_isa_ext_keys[j]); } + +#ifdef CONFIG_VECTOR + if (elf_hwcap & COMPAT_HWCAP_ISA_V) { + static_branch_enable(&cpu_hwcap_vector); + /* There are 32 vector registers with vlenb length. */ + rvv_enable(); + riscv_vsize = csr_read(CSR_VLENB) * 32; + rvv_disable(); + } +#endif } #ifdef CONFIG_RISCV_ALTERNATIVE @@ -328,3 +346,4 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, } } #endif +} diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c index 5ab1c7e1a6ed..3489d2a20ca3 100644 --- a/arch/riscv/kernel/riscv_ksyms.c +++ b/arch/riscv/kernel/riscv_ksyms.c @@ -15,3 +15,9 @@ EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(__memset); EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(__memmove); + +#ifdef CONFIG_VECTOR +#include <asm/vector.h> +EXPORT_SYMBOL(rvv_enable); +EXPORT_SYMBOL(rvv_disable); +#endif diff --git a/arch/riscv/kernel/vector.S b/arch/riscv/kernel/vector.S new file mode 100644 index 000000000000..9f7dc70c4443 --- /dev/null +++ b/arch/riscv/kernel/vector.S @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + * Copyright (C) 2019 Alibaba Group Holding Limited + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/linkage.h> + +#include <asm/asm.h> +#include <asm/csr.h> +#include <asm/asm-offsets.h> + +#define vstatep a0 +#define datap a1 +#define x_vstart t0 +#define x_vtype t1 +#define x_vl t2 +#define x_vcsr t3 +#define incr t4 +#define status t5 + +ENTRY(__vstate_save) + li status, SR_VS + csrs CSR_STATUS, status + + csrr x_vstart, CSR_VSTART + csrr x_vtype, CSR_VTYPE + csrr x_vl, CSR_VL + csrr x_vcsr, CSR_VCSR + vsetvli incr, x0, e8, m8, ta, ma + vse8.v v0, (datap) + add datap, datap, incr + vse8.v v8, (datap) + add datap, datap, incr + vse8.v v16, (datap) + add datap, datap, incr + vse8.v v24, (datap) + + REG_S x_vstart, RISCV_V_STATE_VSTART(vstatep) + REG_S x_vtype, RISCV_V_STATE_VTYPE(vstatep) + REG_S x_vl, RISCV_V_STATE_VL(vstatep) + REG_S x_vcsr, RISCV_V_STATE_VCSR(vstatep) + + csrc CSR_STATUS, status + ret +ENDPROC(__vstate_save) + +ENTRY(__vstate_restore) + li status, SR_VS + csrs CSR_STATUS, status + + vsetvli incr, x0, e8, m8, ta, ma + vle8.v v0, (datap) + add datap, datap, incr + vle8.v v8, (datap) + add datap, datap, incr + vle8.v v16, (datap) + add datap, datap, incr + vle8.v v24, (datap) + + REG_L x_vstart, RISCV_V_STATE_VSTART(vstatep) + REG_L x_vtype, RISCV_V_STATE_VTYPE(vstatep) + REG_L x_vl, RISCV_V_STATE_VL(vstatep) + REG_L x_vcsr, RISCV_V_STATE_VCSR(vstatep) + vsetvl x0, x_vl, x_vtype + csrw CSR_VSTART, x_vstart + csrw CSR_VCSR, x_vcsr + + csrc CSR_STATUS, status + ret +ENDPROC(__vstate_restore) + +ENTRY(rvv_enable) + li status, SR_VS + csrs CSR_STATUS, status + ret +ENDPROC(rvv_enable) + +ENTRY(rvv_disable) + li status, SR_VS + csrc CSR_STATUS, status + ret +ENDPROC(rvv_disable)