[PATCH v12 01/17] riscv: Rename __switch_to_aux -> fpu

[PATCH v12 01/17] riscv: Rename __switch_to_aux -> fpu

[Chris Stillson]

From: Guo Ren <ren_guo@c-sky.com>

The name of __switch_to_aux is not clear and rename it with the
determine function: __switch_to_fpu. Next we could add other regs'
switch.

Signed-off-by: Guo Ren <ren_guo@c-sky.com>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/switch_to.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 11463489fec6..df1aa589b7fd 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -46,7 +46,7 @@ static inline void fstate_restore(struct task_struct *task,
 	}
 }
 
-static inline void __switch_to_aux(struct task_struct *prev,
+static inline void __switch_to_fpu(struct task_struct *prev,
 				   struct task_struct *next)
 {
 	struct pt_regs *regs;
@@ -65,7 +65,7 @@ static __always_inline bool has_fpu(void)
 static __always_inline bool has_fpu(void) { return false; }
 #define fstate_save(task, regs) do { } while (0)
 #define fstate_restore(task, regs) do { } while (0)
-#define __switch_to_aux(__prev, __next) do { } while (0)
+#define __switch_to_fpu(__prev, __next) do { } while (0)
 #endif
 
 extern struct task_struct *__switch_to(struct task_struct *,
@@ -76,7 +76,7 @@ do {							\
 	struct task_struct *__prev = (prev);		\
 	struct task_struct *__next = (next);		\
 	if (has_fpu())					\
-		__switch_to_aux(__prev, __next);	\
+		__switch_to_fpu(__prev, __next);	\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 
-- 
2.25.1

[PATCH v12 02/17] riscv: Extending cpufeature.c to detect V-extension

[Chris Stillson]

From: Guo Ren <ren_guo@c-sky.com>

Current cpufeature.c doesn't support detecting V-extension, because
"rv64" also contain a 'v' letter and we need to skip it.

Signed-off-by: Guo Ren <ren_guo@c-sky.com>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/uapi/asm/hwcap.h | 1 +
 arch/riscv/kernel/cpufeature.c      | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h
index 46dc3f5ee99f..c52bb7bbbabe 100644
--- a/arch/riscv/include/uapi/asm/hwcap.h
+++ b/arch/riscv/include/uapi/asm/hwcap.h
@@ -21,5 +21,6 @@
 #define COMPAT_HWCAP_ISA_F	(1 << ('F' - 'A'))
 #define COMPAT_HWCAP_ISA_D	(1 << ('D' - 'A'))
 #define COMPAT_HWCAP_ISA_C	(1 << ('C' - 'A'))
+#define COMPAT_HWCAP_ISA_V	(1 << ('V' - 'A'))
 
 #endif /* _UAPI_ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 553d755483ed..8d4448c2d4f4 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -83,6 +83,7 @@ void __init riscv_fill_hwcap(void)
 	isa2hwcap['f'] = isa2hwcap['F'] = COMPAT_HWCAP_ISA_F;
 	isa2hwcap['d'] = isa2hwcap['D'] = COMPAT_HWCAP_ISA_D;
 	isa2hwcap['c'] = isa2hwcap['C'] = COMPAT_HWCAP_ISA_C;
+	isa2hwcap['v'] = isa2hwcap['V'] = COMPAT_HWCAP_ISA_V;
 
 	elf_hwcap = 0;
 
-- 
2.25.1

[PATCH v12 03/17] riscv: Add new csr defines related to vector extension

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

Follow the riscv vector spec to add new csr numbers.

[guoren at linux.alibaba.com: first porting for new vector related csr]
Acked-by: Guo Ren <guoren@kernel.org>
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>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/csr.h | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 0e571f6483d9..78a68f29c3ba 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -24,6 +24,12 @@
 #define SR_FS_CLEAN	_AC(0x00004000, UL)
 #define SR_FS_DIRTY	_AC(0x00006000, UL)
 
+#define SR_VS           _AC(0x00000600, UL) /* Vector Status */
+#define SR_VS_OFF       _AC(0x00000000, UL)
+#define SR_VS_INITIAL   _AC(0x00000200, UL)
+#define SR_VS_CLEAN     _AC(0x00000400, UL)
+#define SR_VS_DIRTY     _AC(0x00000600, UL)
+
 #define SR_XS		_AC(0x00018000, UL) /* Extension Status */
 #define SR_XS_OFF	_AC(0x00000000, UL)
 #define SR_XS_INITIAL	_AC(0x00008000, UL)
@@ -31,9 +37,9 @@
 #define SR_XS_DIRTY	_AC(0x00018000, UL)
 
 #ifndef CONFIG_64BIT
-#define SR_SD		_AC(0x80000000, UL) /* FS/XS dirty */
+#define SR_SD		_AC(0x80000000, UL) /* FS/VS/XS dirty */
 #else
-#define SR_SD		_AC(0x8000000000000000, UL) /* FS/XS dirty */
+#define SR_SD		_AC(0x8000000000000000, UL) /* FS/VS/XS dirty */
 #endif
 
 #ifdef CONFIG_64BIT
@@ -297,6 +303,12 @@
 #define CSR_MIMPID		0xf13
 #define CSR_MHARTID		0xf14
 
+#define CSR_VSTART		0x8
+#define CSR_VCSR		0xf
+#define CSR_VL			0xc20
+#define CSR_VTYPE		0xc21
+#define CSR_VLENB		0xc22
+
 #ifdef CONFIG_RISCV_M_MODE
 # define CSR_STATUS	CSR_MSTATUS
 # define CSR_IE		CSR_MIE
-- 
2.25.1

[PATCH v12 03/17] riscv: Add new csr defines related to vector extension

[Heiko Stübner]

Am Mittwoch, 21. September 2022, 23:43:45 CET schrieb Chris Stillson:
> From: Greentime Hu <greentime.hu@sifive.com>
> 
> Follow the riscv vector spec to add new csr numbers.
> 
> [guoren at linux.alibaba.com: first porting for new vector related csr]
> Acked-by: Guo Ren <guoren@kernel.org>
> 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>
> Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>

Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>

[PATCH v12 04/17] riscv: Add vector feature to compile

[Chris Stillson]

From: Guo Ren <guoren@linux.alibaba.com>

This patch adds a new config option which could enable assembler's
vector feature.

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Co-developed-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
---
 arch/riscv/Kconfig  | 15 +++++++++++++--
 arch/riscv/Makefile |  1 +
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index ed66c31e4655..e294d85bfb7d 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -432,7 +432,17 @@ config FPU
 
 	  If you don't know what to do here, say Y.
 
-endmenu # "Platform type"
+config VECTOR
+	bool "VECTOR support"
+	depends on GCC_VERSION >= 120000 || CLANG_VERSION >= 130000
+	default n
+	help
+	  Say N here if you want to disable all vector related procedure
+	  in the kernel.
+
+	  If you don't know what to do here, say Y.
+
+endmenu
 
 menu "Kernel features"
 
@@ -556,6 +566,7 @@ config CMDLINE_EXTEND
 	  cases where the provided arguments are insufficient and
 	  you don't want to or cannot modify them.
 
+
 config CMDLINE_FORCE
 	bool "Always use the default kernel command string"
 	help
@@ -648,7 +659,7 @@ config XIP_PHYS_ADDR
 	  be linked for and stored to.  This address is dependent on your
 	  own flash usage.
 
-endmenu # "Boot options"
+endmenu
 
 config BUILTIN_DTB
 	bool
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 3fa8ef336822..1ec17f3d6d09 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -50,6 +50,7 @@ riscv-march-$(CONFIG_ARCH_RV32I)	:= rv32ima
 riscv-march-$(CONFIG_ARCH_RV64I)	:= rv64ima
 riscv-march-$(CONFIG_FPU)		:= $(riscv-march-y)fd
 riscv-march-$(CONFIG_RISCV_ISA_C)	:= $(riscv-march-y)c
+riscv-march-$(CONFIG_VECTOR)		:= $(riscv-march-y)v
 
 # Newer binutils versions default to ISA spec version 20191213 which moves some
 # instructions from the I extension to the Zicsr and Zifencei extensions.
-- 
2.25.1

[PATCH v12 04/17] riscv: Add vector feature to compile

[Atish Patra]

On Wed, Sep 21, 2022 at 2:47 PM Chris Stillson <stillson@rivosinc.com> wrote:
>
> From: Guo Ren <guoren@linux.alibaba.com>
>
> This patch adds a new config option which could enable assembler's
> vector feature.
>
> Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
> Co-developed-by: Greentime Hu <greentime.hu@sifive.com>
> Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
> ---
>  arch/riscv/Kconfig  | 15 +++++++++++++--
>  arch/riscv/Makefile |  1 +
>  2 files changed, 14 insertions(+), 2 deletions(-)
>
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index ed66c31e4655..e294d85bfb7d 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -432,7 +432,17 @@ config FPU
>
>           If you don't know what to do here, say Y.
>
> -endmenu # "Platform type"
> +config VECTOR
> +       bool "VECTOR support"
> +       depends on GCC_VERSION >= 120000 || CLANG_VERSION >= 130000
> +       default n
> +       help
> +         Say N here if you want to disable all vector related procedure
> +         in the kernel.
> +
> +         If you don't know what to do here, say Y.
> +
> +endmenu
>
>  menu "Kernel features"
>
> @@ -556,6 +566,7 @@ config CMDLINE_EXTEND
>           cases where the provided arguments are insufficient and
>           you don't want to or cannot modify them.
>
> +
>  config CMDLINE_FORCE
>         bool "Always use the default kernel command string"
>         help
> @@ -648,7 +659,7 @@ config XIP_PHYS_ADDR
>           be linked for and stored to.  This address is dependent on your
>           own flash usage.
>
> -endmenu # "Boot options"
> +endmenu
>
>  config BUILTIN_DTB
>         bool
> diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
> index 3fa8ef336822..1ec17f3d6d09 100644
> --- a/arch/riscv/Makefile
> +++ b/arch/riscv/Makefile
> @@ -50,6 +50,7 @@ riscv-march-$(CONFIG_ARCH_RV32I)      := rv32ima
>  riscv-march-$(CONFIG_ARCH_RV64I)       := rv64ima
>  riscv-march-$(CONFIG_FPU)              := $(riscv-march-y)fd
>  riscv-march-$(CONFIG_RISCV_ISA_C)      := $(riscv-march-y)c
> +riscv-march-$(CONFIG_VECTOR)           := $(riscv-march-y)v
>
>  # Newer binutils versions default to ISA spec version 20191213 which moves some
>  # instructions from the I extension to the Zicsr and Zifencei extensions.
> --
> 2.25.1
>

Kernel boot hangs if compiled LLVM and vector enabled. Because LLVM
enables auto vectorization by default and it inserts
random vector instructions.

We need to add "-mno-implicit-float" for llvm builds to disable auto
vectorization. Thanks Vineet and Saleem for the hint :).

-- 
Regards,
Atish

[PATCH v12 05/17] riscv: Add has_vector/riscv_vsize to save vector features.

[Chris Stillson]

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.

[guoren at 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
+#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)
-- 
2.25.1

[PATCH v12 06/17] riscv: Reset vector register

[Chris Stillson]

From: Guo Ren <guoren@linux.alibaba.com>

Reset vector registers at boot-time and disable vector instructions
execution for kernel mode.

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>
Co-developed-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Co-developed-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/entry.S |  6 +++---
 arch/riscv/kernel/head.S  | 35 +++++++++++++++++++++++++++++------
 2 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index b9eda3fcbd6d..1e9987376591 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -77,10 +77,10 @@ _save_context:
 	 * Disable user-mode memory access as it should only be set in the
 	 * actual user copy routines.
 	 *
-	 * Disable the FPU to detect illegal usage of floating point in kernel
-	 * space.
+	 * Disable the FPU/Vector to detect illegal usage of floating point
+	 * or vector in kernel space.
 	 */
-	li t0, SR_SUM | SR_FS
+	li t0, SR_SUM | SR_FS | SR_VS
 
 	REG_L s0, TASK_TI_USER_SP(tp)
 	csrrc s1, CSR_STATUS, t0
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index b865046e4dbb..2c81ca42ec4e 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -140,10 +140,10 @@ secondary_start_sbi:
 	.option pop
 
 	/*
-	 * Disable FPU to detect illegal usage of
-	 * floating point in kernel space
+	 * Disable FPU & VECTOR to detect illegal usage of
+	 * floating point or vector in kernel space
 	 */
-	li t0, SR_FS
+	li t0, SR_FS | SR_VS
 	csrc CSR_STATUS, t0
 
 	/* Set trap vector to spin forever to help debug */
@@ -234,10 +234,10 @@ pmp_done:
 .option pop
 
 	/*
-	 * Disable FPU to detect illegal usage of
-	 * floating point in kernel space
+	 * Disable FPU & VECTOR to detect illegal usage of
+	 * floating point or vector in kernel space
 	 */
-	li t0, SR_FS
+	li t0, SR_FS | SR_VS
 	csrc CSR_STATUS, t0
 
 #ifdef CONFIG_RISCV_BOOT_SPINWAIT
@@ -431,6 +431,29 @@ ENTRY(reset_regs)
 	csrw	fcsr, 0
 	/* note that the caller must clear SR_FS */
 #endif /* CONFIG_FPU */
+
+#ifdef CONFIG_VECTOR
+	csrr	t0, CSR_MISA
+	li	t1, COMPAT_HWCAP_ISA_V
+	and	t0, t0, t1
+	beqz	t0, .Lreset_regs_done
+
+	/*
+	 * Clear vector registers and reset vcsr
+	 * VLMAX has a defined value, VLEN is a constant,
+	 * and this form of vsetvli is defined to set vl to VLMAX.
+	 */
+	li	t1, SR_VS
+	csrs	CSR_STATUS, t1
+	csrs	CSR_VCSR, x0
+	vsetvli t1, x0, e8, m8, ta, ma
+	vmv.v.i v0, 0
+	vmv.v.i v8, 0
+	vmv.v.i v16, 0
+	vmv.v.i v24, 0
+	/* note that the caller must clear SR_VS */
+#endif /* CONFIG_VECTOR */
+
 .Lreset_regs_done:
 	ret
 END(reset_regs)
-- 
2.25.1

[PATCH v12 06/17] riscv: Reset vector register

[Heiko Stübner]

Am Mittwoch, 21. September 2022, 23:43:48 CET schrieb Chris Stillson:
> @@ -431,6 +431,29 @@ ENTRY(reset_regs)
>  	csrw	fcsr, 0
>  	/* note that the caller must clear SR_FS */
>  #endif /* CONFIG_FPU */
> +
> +#ifdef CONFIG_VECTOR
> +	csrr	t0, CSR_MISA
> +	li	t1, COMPAT_HWCAP_ISA_V
> +	and	t0, t0, t1
> +	beqz	t0, .Lreset_regs_done
> +
> +	/*
> +	 * Clear vector registers and reset vcsr
> +	 * VLMAX has a defined value, VLEN is a constant,
> +	 * and this form of vsetvli is defined to set vl to VLMAX.
> +	 */
> +	li	t1, SR_VS
> +	csrs	CSR_STATUS, t1
> +	csrs	CSR_VCSR, x0
> +	vsetvli t1, x0, e8, m8, ta, ma
> +	vmv.v.i v0, 0
> +	vmv.v.i v8, 0
> +	vmv.v.i v16, 0
> +	vmv.v.i v24, 0
> +	/* note that the caller must clear SR_VS */
> +#endif /* CONFIG_VECTOR */
> +
>  .Lreset_regs_done:

Not sure how much they go together, but the #ifdef CONFIG_FPU block above
your new VECTOR block also jumps to the same .Lreset_regs_done, so with
the patch as is the vector-reset block is never reached in the !FPU case.

So maybe making them independent of each other might prevent issues
down the roead.

[PATCH v12 07/17] riscv: Add vector struct and assembler definitions

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

Add vector state context struct in struct thread and asm-offsets.c
definitions.

The vector registers will be saved in datap pointer of __riscv_v_state. It
will be dynamically allocated in kernel space. It will be put right after
the __riscv_v_state data structure in user space.

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/processor.h   |  1 +
 arch/riscv/include/uapi/asm/ptrace.h | 17 +++++++++++++++++
 arch/riscv/kernel/asm-offsets.c      |  6 ++++++
 3 files changed, 24 insertions(+)

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 19eedd4af4cd..95917a2b24f9 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -39,6 +39,7 @@ struct thread_struct {
 	unsigned long s[12];	/* s[0]: frame pointer */
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
+	struct __riscv_v_state vstate;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 882547f6bd5c..6ee1ca2edfa7 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -77,6 +77,23 @@ union __riscv_fp_state {
 	struct __riscv_q_ext_state q;
 };
 
+struct __riscv_v_state {
+	unsigned long vstart;
+	unsigned long vl;
+	unsigned long vtype;
+	unsigned long vcsr;
+	void *datap;
+	/*
+	 * In signal handler, datap will be set a correct user stack offset
+	 * and vector registers will be copied to the address of datap
+	 * pointer.
+	 *
+	 * In ptrace syscall, datap will be set to zero and the vector
+	 * registers will be copied to the address right after this
+	 * structure.
+	 */
+};
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI_ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index df9444397908..37e3e6a8d877 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -75,6 +75,12 @@ void asm_offsets(void)
 	OFFSET(TSK_STACK_CANARY, task_struct, stack_canary);
 #endif
 
+	OFFSET(RISCV_V_STATE_VSTART, __riscv_v_state, vstart);
+	OFFSET(RISCV_V_STATE_VL, __riscv_v_state, vl);
+	OFFSET(RISCV_V_STATE_VTYPE, __riscv_v_state, vtype);
+	OFFSET(RISCV_V_STATE_VCSR, __riscv_v_state, vcsr);
+	OFFSET(RISCV_V_STATE_DATAP, __riscv_v_state, datap);
+
 	DEFINE(PT_SIZE, sizeof(struct pt_regs));
 	OFFSET(PT_EPC, pt_regs, epc);
 	OFFSET(PT_RA, pt_regs, ra);
-- 
2.25.1

[PATCH v12 08/17] riscv: Add task switch support for vector

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

This patch adds task switch support for vector. It supports partial lazy
save and restore mechanism. It also supports all lengths of vlen.

[guoren at linux.alibaba.com: First available porting to support vector
context switching]
[nick.knight at sifive.com: Rewrite vector.S to support dynamic vlen, xlen and
code refine]
[vincent.chen at sifive.com: Fix the might_sleep issue in vstate_save,
vstate_restore]
[andrew at sifive.com: Optimize task switch codes of vector]
[ruinland.tsai at sifive.com: Fix the arch_release_task_struct free wrong
datap issue]

Suggested-by: Andrew Waterman <andrew@sifive.com>
Co-developed-by: Nick Knight <nick.knight@sifive.com>
Signed-off-by: Nick Knight <nick.knight@sifive.com>
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>
Co-developed-by: Ruinland Tsai <ruinland.tsai@sifive.com>
Signed-off-by: Ruinland Tsai <ruinland.tsai@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
---
 arch/riscv/include/asm/switch_to.h | 66 ++++++++++++++++++++++++++++++
 arch/riscv/kernel/Makefile         |  1 +
 arch/riscv/kernel/process.c        | 43 +++++++++++++++++++
 3 files changed, 110 insertions(+)

diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index df1aa589b7fd..527951c033d4 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -7,11 +7,13 @@
 #define _ASM_RISCV_SWITCH_TO_H
 
 #include <linux/jump_label.h>
+#include <linux/slab.h>
 #include <linux/sched/task_stack.h>
 #include <asm/hwcap.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
+#include <asm/asm-offsets.h>
 
 #ifdef CONFIG_FPU
 extern void __fstate_save(struct task_struct *save_to);
@@ -68,6 +70,68 @@ static __always_inline bool has_fpu(void) { return false; }
 #define __switch_to_fpu(__prev, __next) do { } while (0)
 #endif
 
+#ifdef CONFIG_VECTOR
+extern struct static_key_false cpu_hwcap_vector;
+static __always_inline bool has_vector(void)
+{
+	return static_branch_likely(&cpu_hwcap_vector);
+}
+extern unsigned long riscv_vsize;
+extern void __vstate_save(struct __riscv_v_state *save_to, void *datap);
+extern void __vstate_restore(struct __riscv_v_state *restore_from, void *datap);
+
+static inline void __vstate_clean(struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~(SR_VS)) | SR_VS_CLEAN;
+}
+
+static inline void vstate_off(struct task_struct *task,
+			      struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~SR_VS) | SR_VS_OFF;
+}
+
+static inline void vstate_save(struct task_struct *task,
+			       struct pt_regs *regs)
+{
+	if ((regs->status & SR_VS) == SR_VS_DIRTY) {
+		struct __riscv_v_state *vstate = &(task->thread.vstate);
+
+		__vstate_save(vstate, vstate->datap);
+		__vstate_clean(regs);
+	}
+}
+
+static inline void vstate_restore(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	if ((regs->status & SR_VS) != SR_VS_OFF) {
+		struct __riscv_v_state *vstate = &(task->thread.vstate);
+
+		__vstate_restore(vstate, vstate->datap);
+		__vstate_clean(regs);
+	}
+}
+
+static inline void __switch_to_vector(struct task_struct *prev,
+				   struct task_struct *next)
+{
+	struct pt_regs *regs;
+
+	regs = task_pt_regs(prev);
+	if (unlikely(regs->status & SR_SD))
+		vstate_save(prev, regs);
+	vstate_restore(next, task_pt_regs(next));
+}
+
+#else
+static __always_inline bool has_vector(void) { return false; }
+#define riscv_vsize (0)
+#define vstate_save(task, regs) do { } while (0)
+#define vstate_restore(task, regs) do { } while (0)
+#define __switch_to_vector(__prev, __next) do { } while (0)
+#endif
+
 extern struct task_struct *__switch_to(struct task_struct *,
 				       struct task_struct *);
 
@@ -77,6 +141,8 @@ do {							\
 	struct task_struct *__next = (next);		\
 	if (has_fpu())					\
 		__switch_to_fpu(__prev, __next);	\
+	if (has_vector())					\
+		__switch_to_vector(__prev, __next);	\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 33bb60a354cd..35752fb6d145 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
+obj-$(CONFIG_VECTOR)		+= vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index ceb9ebab6558..e88a37fc77ed 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -124,6 +124,25 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 		 */
 		fstate_restore(current, regs);
 	}
+
+	if (has_vector()) {
+		struct __riscv_v_state *vstate = &(current->thread.vstate);
+
+		/* Enable vector and allocate memory for vector registers. */
+		if (!vstate->datap) {
+			vstate->datap = kzalloc(riscv_vsize, GFP_KERNEL);
+			if (WARN_ON(!vstate->datap))
+				return;
+		}
+		regs->status |= SR_VS_INITIAL;
+
+		/*
+		 * Restore the initial value to the vector register
+		 * before starting the user program.
+		 */
+		vstate_restore(current, regs);
+	}
+
 	regs->epc = pc;
 	regs->sp = sp;
 
@@ -148,15 +167,29 @@ void flush_thread(void)
 	fstate_off(current, task_pt_regs(current));
 	memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
 #endif
+#ifdef CONFIG_VECTOR
+	/* Reset vector state */
+	vstate_off(current, task_pt_regs(current));
+	memset(&current->thread.vstate, 0, RISCV_V_STATE_DATAP);
+#endif
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	fstate_save(src, task_pt_regs(src));
 	*dst = *src;
+	dst->thread.vstate.datap = NULL;
+
 	return 0;
 }
 
+void arch_release_task_struct(struct task_struct *tsk)
+{
+	/* Free the vector context of datap. */
+	if (has_vector() && tsk->thread.vstate.datap)
+		kfree(tsk->thread.vstate.datap);
+}
+
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
@@ -175,7 +208,17 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		p->thread.ra = (unsigned long)ret_from_kernel_thread;
 		p->thread.s[0] = (unsigned long)args->fn;
 		p->thread.s[1] = (unsigned long)args->fn_arg;
+		p->thread.vstate.datap = NULL;
 	} else {
+		/* Allocate the datap for the user process if datap is NULL */
+		if (has_vector() && !p->thread.vstate.datap) {
+			void *datap = kzalloc(riscv_vsize, GFP_KERNEL);
+			/* Failed to allocate memory. */
+			if (!datap)
+				return -ENOMEM;
+			p->thread.vstate.datap = datap;
+			memset(&p->thread.vstate, 0, RISCV_V_STATE_DATAP);
+		}
 		*childregs = *(current_pt_regs());
 		if (usp) /* User fork */
 			childregs->sp = usp;
-- 
2.25.1

[PATCH v12 09/17] riscv: Add ptrace vector support

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

This patch adds ptrace support for riscv vector. The vector registers will
be saved in datap pointer of __riscv_v_state. This pointer will be set
right after the __riscv_v_state data structure then it will be put in ubuf
for ptrace system call to get or set. It will check if the datap got from
ubuf is set to the correct address or not when the ptrace system call is
trying to set the vector registers.

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/uapi/asm/ptrace.h |  6 +++
 arch/riscv/kernel/ptrace.c           | 71 ++++++++++++++++++++++++++++
 include/uapi/linux/elf.h             |  1 +
 3 files changed, 78 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 6ee1ca2edfa7..2491875be80d 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -94,6 +94,12 @@ struct __riscv_v_state {
 	 */
 };
 
+/*
+ * According to spec: The number of bits in a single vector register,
+ * VLEN >= ELEN, which must be a power of 2, and must be no greater than
+ * 2^16 = 65536bits = 8192bytes
+ */
+#define RISCV_MAX_VLENB (8192)
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI_ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2ae8280ae475..cce459ff551d 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -27,6 +27,9 @@ enum riscv_regset {
 #ifdef CONFIG_FPU
 	REGSET_F,
 #endif
+#ifdef CONFIG_VECTOR
+	REGSET_V,
+#endif
 };
 
 static int riscv_gpr_get(struct task_struct *target,
@@ -83,6 +86,64 @@ static int riscv_fpr_set(struct task_struct *target,
 }
 #endif
 
+#ifdef CONFIG_VECTOR
+static int riscv_vr_get(struct task_struct *target,
+			const struct user_regset *regset,
+			struct membuf to)
+{
+	struct __riscv_v_state *vstate = &target->thread.vstate;
+
+	/*
+	 * Ensure the vector registers have been saved to the memory before
+	 * copying them to membuf.
+	 */
+	if (target == current)
+		vstate_save(current, task_pt_regs(current));
+
+	/* Copy vector header from vstate. */
+	membuf_write(&to, vstate, RISCV_V_STATE_DATAP);
+	membuf_zero(&to, sizeof(void *));
+#if __riscv_xlen == 32
+	membuf_zero(&to, sizeof(__u32));
+#endif
+
+	/* Copy all the vector registers from vstate. */
+	return membuf_write(&to, vstate->datap, riscv_vsize);
+}
+
+static int riscv_vr_set(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf)
+{
+	int ret, size;
+	struct __riscv_v_state *vstate = &target->thread.vstate;
+
+	/* Copy rest of the vstate except datap and __padding. */
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate, 0,
+				 RISCV_V_STATE_DATAP);
+	if (unlikely(ret))
+		return ret;
+
+	/* Skip copy datap. */
+	size = sizeof(vstate->datap);
+	count -= size;
+	ubuf += size;
+#if __riscv_xlen == 32
+	/* Skip copy _padding. */
+	size = sizeof(vstate->__padding);
+	count -= size;
+	ubuf += size;
+#endif
+
+	/* Copy all the vector registers. */
+	pos = 0;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap,
+				 0, riscv_vsize);
+	return ret;
+}
+#endif
+
 static const struct user_regset riscv_user_regset[] = {
 	[REGSET_X] = {
 		.core_note_type = NT_PRSTATUS,
@@ -102,6 +163,16 @@ static const struct user_regset riscv_user_regset[] = {
 		.set = riscv_fpr_set,
 	},
 #endif
+#ifdef CONFIG_VECTOR
+	[REGSET_V] = {
+		.core_note_type = NT_RISCV_VECTOR,
+		.align = 16,
+		.n = (32 * RISCV_MAX_VLENB)/sizeof(__u32),
+		.size = sizeof(__u32),
+		.regset_get = riscv_vr_get,
+		.set = riscv_vr_set,
+	},
+#endif
 };
 
 static const struct user_regset_view riscv_user_native_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index c7b056af9ef0..5a5056c6a2a1 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -439,6 +439,7 @@ typedef struct elf64_shdr {
 #define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
 #define NT_MIPS_FP_MODE	0x801		/* MIPS floating-point mode */
 #define NT_MIPS_MSA	0x802		/* MIPS SIMD registers */
+#define NT_RISCV_VECTOR	0x900		/* RISC-V vector registers */
 #define NT_LOONGARCH_CPUCFG	0xa00	/* LoongArch CPU config registers */
 #define NT_LOONGARCH_CSR	0xa01	/* LoongArch control and status registers */
 #define NT_LOONGARCH_LSX	0xa02	/* LoongArch Loongson SIMD Extension registers */
-- 
2.25.1

[PATCH v12 10/17] riscv: Add sigcontext save/restore for vector

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

This patch adds sigcontext save/restore for vector. The vector registers
will be saved in datap pointer. The datap pointer will be allocated
dynamically when the task needs in kernel space. The datap pointer will
be set right after the __riscv_v_state data structure to save all the
vector registers in the signal handler stack.

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/uapi/asm/sigcontext.h |  24 ++++
 arch/riscv/kernel/asm-offsets.c          |   2 +
 arch/riscv/kernel/signal.c               | 165 ++++++++++++++++++++++-
 3 files changed, 187 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h
index 84f2dfcfdbce..b8a0fd7d7cfc 100644
--- a/arch/riscv/include/uapi/asm/sigcontext.h
+++ b/arch/riscv/include/uapi/asm/sigcontext.h
@@ -8,6 +8,23 @@
 
 #include <asm/ptrace.h>
 
+/* The Magic number for signal context frame header. */
+#define RVV_MAGIC	0x53465457
+#define END_MAGIC	0x0
+
+/* The size of END signal context header. */
+#define END_HDR_SIZE	0x0
+
+struct __riscv_ctx_hdr {
+	__u32 magic;
+	__u32 size;
+};
+
+struct __sc_riscv_v_state {
+	struct __riscv_ctx_hdr head;
+	struct __riscv_v_state v_state;
+} __attribute__((aligned(16)));
+
 /*
  * Signal context structure
  *
@@ -17,6 +34,13 @@
 struct sigcontext {
 	struct user_regs_struct sc_regs;
 	union __riscv_fp_state sc_fpregs;
+	/*
+	 * 4K + 128 reserved for vector state and future expansion.
+	 * This space is enough to store the vector context whose VLENB
+	 * is less or equal to 128.
+	 * (The size of the vector context is 4144 byte as VLENB is 128)
+	 */
+	__u8 __reserved[4224] __attribute__((__aligned__(16)));
 };
 
 #endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 37e3e6a8d877..80316ef7bb78 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -75,6 +75,8 @@ void asm_offsets(void)
 	OFFSET(TSK_STACK_CANARY, task_struct, stack_canary);
 #endif
 
+	OFFSET(RISCV_V_STATE_MAGIC, __riscv_ctx_hdr, magic);
+	OFFSET(RISCV_V_STATE_SIZE, __riscv_ctx_hdr, size);
 	OFFSET(RISCV_V_STATE_VSTART, __riscv_v_state, vstart);
 	OFFSET(RISCV_V_STATE_VL, __riscv_v_state, vl);
 	OFFSET(RISCV_V_STATE_VTYPE, __riscv_v_state, vtype);
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 38b05ca6fe66..41d9a02c7098 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -20,15 +20,16 @@
 #include <asm/csr.h>
 
 extern u32 __user_rt_sigreturn[2];
+static size_t rvv_sc_size;
 
 #define DEBUG_SIG 0
 
 struct rt_sigframe {
 	struct siginfo info;
-	struct ucontext uc;
 #ifndef CONFIG_MMU
 	u32 sigreturn_code[2];
 #endif
+	struct ucontext uc;
 };
 
 #ifdef CONFIG_FPU
@@ -85,16 +86,155 @@ static long save_fp_state(struct pt_regs *regs,
 #define restore_fp_state(task, regs) (0)
 #endif
 
+#ifdef CONFIG_VECTOR
+static long restore_v_state(struct pt_regs *regs, void **sc_reserved_ptr)
+{
+	long err;
+	struct __sc_riscv_v_state __user *state = (struct __sc_riscv_v_state *)(*sc_reserved_ptr);
+	void *datap;
+	__u32 magic;
+	__u32 size;
+
+	/* Get magic number and check it. */
+	err = __get_user(magic, &state->head.magic);
+	err = __get_user(size, &state->head.size);
+	if (unlikely(err))
+		return err;
+
+	if (magic != RVV_MAGIC || size != rvv_sc_size)
+		return -EINVAL;
+
+	/* Copy everything of __sc_riscv_v_state except datap. */
+	err = __copy_from_user(&current->thread.vstate, &state->v_state,
+			       RISCV_V_STATE_DATAP);
+	if (unlikely(err))
+		return err;
+
+	/* Copy the pointer datap itself. */
+	err = __get_user(datap, &state->v_state.datap);
+	if (unlikely(err))
+		return err;
+
+
+	/* Copy the whole vector content from user space datap. */
+	err = __copy_from_user(current->thread.vstate.datap, datap, riscv_vsize);
+	if (unlikely(err))
+		return err;
+
+	vstate_restore(current, regs);
+
+	/* Move sc_reserved_ptr to point the next signal context frame. */
+	*sc_reserved_ptr += size;
+
+	return err;
+}
+
+static long save_v_state(struct pt_regs *regs, void **sc_reserved_free_ptr)
+{
+	/*
+	 * Put __sc_riscv_v_state to the user's signal context space pointed
+	 * by sc_reserved_free_ptr and the datap point the address right
+	 * after __sc_riscv_v_state.
+	 */
+	struct __sc_riscv_v_state __user *state = (struct __sc_riscv_v_state *)
+		(*sc_reserved_free_ptr);
+	void *datap = state + 1;
+	long err;
+
+	*sc_reserved_free_ptr += rvv_sc_size;
+
+	err = __put_user(RVV_MAGIC, &state->head.magic);
+	err = __put_user(rvv_sc_size, &state->head.size);
+
+	vstate_save(current, regs);
+	/* Copy everything of vstate but datap. */
+	err = __copy_to_user(&state->v_state, &current->thread.vstate,
+			     RISCV_V_STATE_DATAP);
+	if (unlikely(err))
+		return err;
+
+	/* Copy the pointer datap itself. */
+	err = __put_user(datap, &state->v_state.datap);
+	if (unlikely(err))
+		return err;
+
+	/* Copy the whole vector content to user space datap. */
+	err = __copy_to_user(datap, current->thread.vstate.datap, riscv_vsize);
+
+	return err;
+}
+#else
+#define save_v_state(task, regs) (0)
+#define restore_v_state(task, regs) (0)
+#endif
+
 static long restore_sigcontext(struct pt_regs *regs,
 	struct sigcontext __user *sc)
 {
 	long err;
+	void *sc_reserved_ptr = sc->__reserved;
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs));
 	/* Restore the floating-point state. */
 	if (has_fpu())
 		err |= restore_fp_state(regs, &sc->sc_fpregs);
+
+	while (1 && !err) {
+		__u32 magic, size;
+		struct __riscv_ctx_hdr *head = (struct __riscv_ctx_hdr *)sc_reserved_ptr;
+
+		err |= __get_user(magic, &head->magic);
+		err |= __get_user(size, &head->size);
+		if (err)
+			goto done;
+
+		switch (magic) {
+		case 0:
+			if (size)
+				goto invalid;
+			goto done;
+		case RVV_MAGIC:
+			if (!has_vector())
+				goto invalid;
+			if (size != rvv_sc_size)
+				goto invalid;
+			err |= restore_v_state(regs, &sc_reserved_ptr);
+			break;
+		default:
+			goto invalid;
+		}
+	}
+done:
 	return err;
+
+invalid:
+	return -EINVAL;
+}
+
+static size_t cal_rt_frame_size(void)
+{
+	struct rt_sigframe __user *frame;
+	static size_t frame_size;
+	size_t total_context_size = 0;
+	size_t sc_reserved_size = sizeof(frame->uc.uc_mcontext.__reserved);
+
+	if (frame_size)
+		goto done;
+
+	frame_size = sizeof(*frame);
+
+	if (has_vector())
+		total_context_size += rvv_sc_size;
+	/* Preserved a __riscv_ctx_hdr for END signal context header. */
+	total_context_size += sizeof(struct __riscv_ctx_hdr);
+
+	if (total_context_size > sc_reserved_size)
+		frame_size += (total_context_size - sc_reserved_size);
+
+	frame_size = round_up(frame_size, 16);
+done:
+	return frame_size;
+
 }
 
 SYSCALL_DEFINE0(rt_sigreturn)
@@ -103,13 +243,14 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	struct rt_sigframe __user *frame;
 	struct task_struct *task;
 	sigset_t set;
+	size_t frame_size = cal_rt_frame_size();
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *)regs->sp;
 
-	if (!access_ok(frame, sizeof(*frame)))
+	if (!access_ok(frame, frame_size))
 		goto badframe;
 
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
@@ -142,11 +283,20 @@ static long setup_sigcontext(struct rt_sigframe __user *frame,
 {
 	struct sigcontext __user *sc = &frame->uc.uc_mcontext;
 	long err;
+	void *sc_reserved_free_ptr = sc->__reserved;
+
 	/* sc_regs is structured the same as the start of pt_regs */
 	err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs));
 	/* Save the floating-point state. */
 	if (has_fpu())
 		err |= save_fp_state(regs, &sc->sc_fpregs);
+	/* Save the vector state. */
+	if (has_vector())
+		err |= save_v_state(regs, &sc_reserved_free_ptr);
+
+	/* Put END __riscv_ctx_hdr at the end. */
+	err = __put_user(END_MAGIC, &((struct __riscv_ctx_hdr *)sc_reserved_free_ptr)->magic);
+	err = __put_user(END_HDR_SIZE, &((struct __riscv_ctx_hdr *)sc_reserved_free_ptr)->size);
 	return err;
 }
 
@@ -178,9 +328,10 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 {
 	struct rt_sigframe __user *frame;
 	long err = 0;
+	size_t frame_size = cal_rt_frame_size();
 
-	frame = get_sigframe(ksig, regs, sizeof(*frame));
-	if (!access_ok(frame, sizeof(*frame)))
+	frame = get_sigframe(ksig, regs, frame_size);
+	if (!access_ok(frame, frame_size))
 		return -EFAULT;
 
 	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
@@ -326,3 +477,9 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
 	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		resume_user_mode_work(regs);
 }
+
+void init_rt_signal_env(void);
+void __init init_rt_signal_env(void)
+{
+	rvv_sc_size = sizeof(struct __sc_riscv_v_state) + riscv_vsize;
+}
-- 
2.25.1

[PATCH v12 11/17] riscv: signal: Report signal frame size to userspace via auxv

[Chris Stillson]

From: Vincent Chen <vincent.chen@sifive.com>

The vector register belongs to the signal context. They need to be stored
and restored as entering and leaving the signal handler. According to the
V-extension specification, the maximum length of the vector registers can
be 2^(XLEN-1). Hence, if userspace refers to the MINSIGSTKSZ to create a
sigframe, it may not be enough. To resolve this problem, this patch refers
to the commit 94b07c1f8c39c
("arm64: signal: Report signal frame size to userspace via auxv") to enable
userspace to know the minimum required sigframe size through the auxiliary
vector and use it to allocate enough memory for signal context.

Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
---
 arch/riscv/include/asm/elf.h         | 47 +++++++++++++++-------------
 arch/riscv/include/asm/processor.h   |  2 ++
 arch/riscv/include/uapi/asm/auxvec.h |  1 +
 arch/riscv/kernel/signal.c           |  8 +++++
 4 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index 14fc7342490b..df9047b619e8 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -77,28 +77,31 @@ extern unsigned long elf_hwcap;
 #define COMPAT_ELF_PLATFORM	(NULL)
 
 #ifdef CONFIG_MMU
-#define ARCH_DLINFO						\
-do {								\
-	/*							\
-	 * Note that we add ulong after elf_addr_t because	\
-	 * casting current->mm->context.vdso triggers a cast	\
-	 * warning of cast from pointer to integer for		\
-	 * COMPAT ELFCLASS32.					\
-	 */							\
-	NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
-		(elf_addr_t)(ulong)current->mm->context.vdso);	\
-	NEW_AUX_ENT(AT_L1I_CACHESIZE,				\
-		get_cache_size(1, CACHE_TYPE_INST));		\
-	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY,			\
-		get_cache_geometry(1, CACHE_TYPE_INST));	\
-	NEW_AUX_ENT(AT_L1D_CACHESIZE,				\
-		get_cache_size(1, CACHE_TYPE_DATA));		\
-	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY,			\
-		get_cache_geometry(1, CACHE_TYPE_DATA));	\
-	NEW_AUX_ENT(AT_L2_CACHESIZE,				\
-		get_cache_size(2, CACHE_TYPE_UNIFIED));		\
-	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY,			\
-		get_cache_geometry(2, CACHE_TYPE_UNIFIED));	\
+#define ARCH_DLINFO						 \
+do {								 \
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,				 \
+		(elf_addr_t)current->mm->context.vdso);		 \
+	NEW_AUX_ENT(AT_L1I_CACHESIZE,				 \
+		get_cache_size(1, CACHE_TYPE_INST));		 \
+	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY,			 \
+		get_cache_geometry(1, CACHE_TYPE_INST));	 \
+	NEW_AUX_ENT(AT_L1D_CACHESIZE,				 \
+		get_cache_size(1, CACHE_TYPE_DATA));		 \
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY,			 \
+		get_cache_geometry(1, CACHE_TYPE_DATA));	 \
+	NEW_AUX_ENT(AT_L2_CACHESIZE,				 \
+		get_cache_size(2, CACHE_TYPE_UNIFIED));		 \
+	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY,			 \
+		get_cache_geometry(2, CACHE_TYPE_UNIFIED));	 \
+	/*							 \
+	 * Should always be nonzero unless there's a kernel bug. \
+	 * If we haven't determined a sensible value to give to	 \
+	 * userspace, omit the entry:				 \
+	 */							 \
+	if (likely(signal_minsigstksz))				 \
+		NEW_AUX_ENT(AT_MINSIGSTKSZ, signal_minsigstksz); \
+	else							 \
+		NEW_AUX_ENT(AT_IGNORE, 0);			 \
 } while (0)
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 95917a2b24f9..a09141ecf6aa 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -7,6 +7,7 @@
 #define _ASM_RISCV_PROCESSOR_H
 
 #include <linux/const.h>
+#include <linux/cache.h>
 
 #include <vdso/processor.h>
 
@@ -86,6 +87,7 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid);
 extern void riscv_fill_hwcap(void);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
+extern unsigned long signal_minsigstksz __ro_after_init;
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
index 32c73ba1d531..6610d24e6662 100644
--- a/arch/riscv/include/uapi/asm/auxvec.h
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -33,5 +33,6 @@
 
 /* entries in ARCH_DLINFO */
 #define AT_VECTOR_SIZE_ARCH	7
+#define AT_MINSIGSTKSZ 51
 
 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 41d9a02c7098..fb1f5012416e 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -478,8 +478,16 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
 		resume_user_mode_work(regs);
 }
 
+unsigned long __ro_after_init signal_minsigstksz;
+
 void init_rt_signal_env(void);
 void __init init_rt_signal_env(void)
 {
 	rvv_sc_size = sizeof(struct __sc_riscv_v_state) + riscv_vsize;
+	/*
+	 * Determine the stack space required for guaranteed signal delivery.
+	 * The signal_minsigstksz will be populated into the AT_MINSIGSTKSZ entry
+	 * in the auxiliary array at process startup.
+	 */
+	signal_minsigstksz = cal_rt_frame_size();
 }
-- 
2.25.1

[PATCH v12 12/17] riscv: Add support for kernel mode vector

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

Add kernel_rvv_begin() and kernel_rvv_end() function declarations
and corresponding definitions in kernel_mode_vector.c

These are needed to wrap uses of vector in kernel mode.

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        |   3 +
 arch/riscv/kernel/Makefile             |   1 +
 arch/riscv/kernel/kernel_mode_vector.c | 132 +++++++++++++++++++++++++
 arch/riscv/kernel/vector.S             |   9 ++
 4 files changed, 145 insertions(+)
 create mode 100644 arch/riscv/kernel/kernel_mode_vector.c

diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 16304b0c6a6f..a59841cc81fb 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -10,5 +10,8 @@
 
 void rvv_enable(void);
 void rvv_disable(void);
+void kernel_rvv_begin(void);
+void kernel_rvv_end(void);
+void vector_flush_cpu_state(void);
 
 #endif /* ! __ASM_RISCV_VECTOR_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 35752fb6d145..8c238415f800 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_VECTOR)		+= vector.o
+obj-$(CONFIG_VECTOR)		+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 000000000000..0277168af0c5
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+
+DECLARE_PER_CPU(bool, vector_context_busy);
+DEFINE_PER_CPU(bool, vector_context_busy);
+
+/*
+ * may_use_vector - whether it is allowable at this time to issue vector
+ *                instructions or access the vector register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_vector(void)
+{
+	/*
+	 * vector_context_busy is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled. Since
+	 * this_cpu_read() is atomic w.r.t. preemption, vector_context_busy
+	 * cannot change under our feet -- if it's set we cannot be
+	 * migrated, and if it's clear we cannot be migrated to a CPU
+	 * where it is set.
+	 */
+	return !in_irq() && !irqs_disabled() && !in_nmi() &&
+	       !this_cpu_read(vector_context_busy);
+}
+
+/*
+ * Claim ownership of the CPU vector context for use by the calling context.
+ *
+ * The caller may freely manipulate the vector context metadata until
+ * put_cpu_vector_context() is called.
+ */
+static void get_cpu_vector_context(void)
+{
+	bool busy;
+
+	preempt_disable();
+	busy = __this_cpu_xchg(vector_context_busy, true);
+
+	WARN_ON(busy);
+}
+
+/*
+ * Release the CPU vector context.
+ *
+ * Must be called from a context in which get_cpu_vector_context() was
+ * previously called, with no call to put_cpu_vector_context() in the
+ * meantime.
+ */
+static void put_cpu_vector_context(void)
+{
+	bool busy = __this_cpu_xchg(vector_context_busy, false);
+
+	WARN_ON(!busy);
+	preempt_enable();
+}
+
+/*
+ * kernel_rvv_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_vector() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_rvv_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_rvv_end() is
+ * called.
+ */
+void kernel_rvv_begin(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	WARN_ON(!may_use_vector());
+
+	/* Acquire kernel mode vector */
+	get_cpu_vector_context();
+
+	/* Save vector state, if any */
+	vstate_save(current, task_pt_regs(current));
+
+	/* Enable vector */
+	rvv_enable();
+
+	/* Invalidate vector regs */
+	vector_flush_cpu_state();
+}
+EXPORT_SYMBOL_GPL(kernel_rvv_begin);
+
+/*
+ * kernel_rvv_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_rvv_begin() was previously
+ * called, with no call to kernel_rvv_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_rvv_begin() is called again in the meantime.
+ */
+void kernel_rvv_end(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	/* Invalidate vector regs */
+	vector_flush_cpu_state();
+
+	/* Restore vector state, if any */
+	vstate_restore(current, task_pt_regs(current));
+
+	/* disable vector */
+	rvv_disable();
+
+	/* release kernel mode vector */
+	put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_rvv_end);
diff --git a/arch/riscv/kernel/vector.S b/arch/riscv/kernel/vector.S
index 9f7dc70c4443..9c2de823c0d9 100644
--- a/arch/riscv/kernel/vector.S
+++ b/arch/riscv/kernel/vector.S
@@ -91,3 +91,12 @@ ENTRY(rvv_disable)
 	csrc	CSR_STATUS, status
 	ret
 ENDPROC(rvv_disable)
+
+ENTRY(vector_flush_cpu_state)
+	vsetvli t0, x0, e8, m8, ta, ma
+	vmv.v.i v0, 0
+	vmv.v.i v8, 0
+	vmv.v.i v16, 0
+	vmv.v.i v24, 0
+	ret
+ENDPROC(vector_flush_cpu_state)
-- 
2.25.1

[PATCH v12 13/17] riscv: Add vector extension XOR implementation

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

This patch adds support for vector optimized XOR and it is tested in
qemu.

Co-developed-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
---
 arch/riscv/include/asm/xor.h | 82 ++++++++++++++++++++++++++++++++++++
 arch/riscv/lib/Makefile      |  1 +
 arch/riscv/lib/xor.S         | 81 +++++++++++++++++++++++++++++++++++
 3 files changed, 164 insertions(+)
 create mode 100644 arch/riscv/include/asm/xor.h
 create mode 100644 arch/riscv/lib/xor.S

diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 000000000000..d1f2eeb14afb
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#ifdef CONFIG_VECTOR
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+
+void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2);
+void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3);
+void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4);
+void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4,
+		 const unsigned long *__restrict p5);
+
+static void xor_rvv_2(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2)
+{
+	kernel_rvv_begin();
+	xor_regs_2_(bytes, p1, p2);
+	kernel_rvv_end();
+}
+
+static void xor_rvv_3(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2,
+		      const unsigned long *__restrict p3)
+{
+	kernel_rvv_begin();
+	xor_regs_3_(bytes, p1, p2, p3);
+	kernel_rvv_end();
+}
+
+static void xor_rvv_4(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2,
+		      const unsigned long *__restrict p3,
+		      const unsigned long *__restrict p4)
+{
+	kernel_rvv_begin();
+	xor_regs_4_(bytes, p1, p2, p3, p4);
+	kernel_rvv_end();
+}
+
+static void xor_rvv_5(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2,
+		      const unsigned long *__restrict p3,
+		      const unsigned long *__restrict p4,
+		      const unsigned long *__restrict p5)
+{
+	kernel_rvv_begin();
+	xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+	kernel_rvv_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+	.name = "rvv",
+	.do_2 = xor_rvv_2,
+	.do_3 = xor_rvv_3,
+	.do_4 = xor_rvv_4,
+	.do_5 = xor_rvv_5
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES           \
+	do {        \
+		xor_speed(&xor_block_8regs);    \
+		xor_speed(&xor_block_32regs);    \
+		if (has_vector()) { \
+			xor_speed(&xor_block_rvv);\
+		} \
+	} while (0)
+#endif
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 25d5c9664e57..acd87ac86d24 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -7,3 +7,4 @@ lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+lib-$(CONFIG_VECTOR)	+= xor.o
diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S
new file mode 100644
index 000000000000..3bc059e18171
--- /dev/null
+++ b/arch/riscv/lib/xor.S
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+
+ENTRY(xor_regs_2_)
+	vsetvli a3, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a3
+	vxor.vv v16, v0, v8
+	add a2, a2, a3
+	vse8.v v16, (a1)
+	add a1, a1, a3
+	bnez a0, xor_regs_2_
+	ret
+END(xor_regs_2_)
+EXPORT_SYMBOL(xor_regs_2_)
+
+ENTRY(xor_regs_3_)
+	vsetvli a4, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a4
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a4
+	vxor.vv v16, v0, v16
+	add a3, a3, a4
+	vse8.v v16, (a1)
+	add a1, a1, a4
+	bnez a0, xor_regs_3_
+	ret
+END(xor_regs_3_)
+EXPORT_SYMBOL(xor_regs_3_)
+
+ENTRY(xor_regs_4_)
+	vsetvli a5, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a5
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a5
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a5
+	vxor.vv v16, v0, v24
+	add a4, a4, a5
+	vse8.v v16, (a1)
+	add a1, a1, a5
+	bnez a0, xor_regs_4_
+	ret
+END(xor_regs_4_)
+EXPORT_SYMBOL(xor_regs_4_)
+
+ENTRY(xor_regs_5_)
+	vsetvli a6, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a6
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a6
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a6
+	vxor.vv v0, v0, v24
+	vle8.v v8, (a5)
+	add a4, a4, a6
+	vxor.vv v16, v0, v8
+	add a5, a5, a6
+	vse8.v v16, (a1)
+	add a1, a1, a6
+	bnez a0, xor_regs_5_
+	ret
+END(xor_regs_5_)
+EXPORT_SYMBOL(xor_regs_5_)
-- 
2.25.1

[PATCH v12 14/17] riscv: Fix a kernel panic issue if $s2 is set to a specific value before entering Linux

[Chris Stillson]

From: Greentime Hu <greentime.hu@sifive.com>

Panic log:
[    0.018707] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[    0.023060] Oops [#1]
[    0.023214] Modules linked in:
[    0.023725] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.14.0 #33
[    0.023955] Hardware name: SiFive,FU800 (DT)
[    0.024150] epc : __vstate_save+0x1c/0x48
[    0.024654]  ra : arch_dup_task_struct+0x70/0x108
[    0.024815] epc : ffffffff80005ad8 ra : ffffffff800035a8 sp : ffffffff81203d50
[    0.025020]  gp : ffffffff812e8290 tp : ffffffff8120bdc0 t0 : 0000000000000000
[    0.025216]  t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81203d80
[    0.025424]  s1 : ffffffff8120bdc0 a0 : ffffffff8120c820 a1 : 0000000000000000
[    0.025659]  a2 : 0000000000001000 a3 : 0000000000000000 a4 : 0000000000000600
[    0.025869]  a5 : ffffffff8120cdc0 a6 : ffffffe00160b400 a7 : ffffffff80a1fe60
[    0.026069]  s2 : ffffffe0016b8000 s3 : ffffffff81204000 s4 : 0000000000004000
[    0.026267]  s5 : 0000000000000000 s6 : ffffffe0016b8000 s7 : ffffffe0016b9000
[    0.026475]  s8 : ffffffff81203ee0 s9 : 0000000000800300 s10: ffffffff812e9088
[    0.026689]  s11: ffffffd004008000 t3 : 0000000000000000 t4 : 0000000000000100
[    0.026900]  t5 : 0000000000000600 t6 : ffffffe00167bcc4
[    0.027057] status: 8000000000000720 badaddr: 0000000000000000 cause: 000000000000000f
[    0.027344] [<ffffffff80005ad8>] __vstate_save+0x1c/0x48
[    0.027567] [<ffffffff8000abe8>] copy_process+0x266/0x11a0
[    0.027739] [<ffffffff8000bc98>] kernel_clone+0x90/0x2aa
[    0.027915] [<ffffffff8000c062>] kernel_thread+0x76/0x92
[    0.028075] [<ffffffff8072e34c>] rest_init+0x26/0xfc
[    0.028242] [<ffffffff80800638>] arch_call_rest_init+0x10/0x18
[    0.028423] [<ffffffff80800c4a>] start_kernel+0x5ce/0x5fe
[    0.029188] ---[ end trace 9a59af33f7ba3df4 ]---
[    0.029479] Kernel panic - not syncing: Attempted to kill the idle task!
[    0.029907] ---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]---

The NULL pointer accessing caused the kernel panic. There is a NULL
pointer is because in vstate_save() function it will check
(regs->status & SR_VS) == SR_VS_DIRTY and this is true, but it shouldn't
be true because vector is not used here. Since vector is not used, datap
won't be allocated so it is NULL. The reason why regs->status is set to
a wrong value is because pt_regs->status is put in stack and it is polluted
after setup_vm() called.

In prologue of setup_vm(), we can observe it will save s2 to stack however
s2 is meaningless here because the caller is assembly code and s2 is just
some value from previous stage. The compiler will base on calling
convention to save the register to stack. Then 0x80008638 in s2 is saved
to stack. It might be any value. In this failure case it is 0x80008638 and
it will accidentally cause SR_VS_DIRTY to call the vstate_save() function.

(gdb) info addr setup_vm
Symbol "setup_vm" is a function at address 0xffffffff80802c8a.
(gdb) va2pa 0xffffffff80802c8a
$64 = 0x80a02c8a
(gdb) x/10i 0x80a02c8a
   0x80a02c8a:  addi    sp,sp,-48
   0x80a02c8c:  li      a3,-1
   0x80a02c8e:  auipc   a5,0xff7fd
   0x80a02c92:  addi    a5,a5,882
   0x80a02c96:  sd      s0,32(sp)
   0x80a02c98:  sd      s2,16(sp) <-- store to stack

After returning from setup_vm()
(gdb) x/20i  0x0000000080201138
   0x80201138:  mv      a0,s1
   0x8020113a:  auipc   ra,0x802
   0x8020113e:  jalr    -1200(ra)    <-- jump to setup_vm()
   0x80201142:  auipc   a0,0xa03
(gdb) p/x $sp
$70 = 0x81404000
(gdb) p/x *(struct pt_regs*)($sp-0x120)
$71 = {
  epc = 0x0,
  ra = 0x0,
  sp = 0x0,
  gp = 0x0,
  tp = 0x0,
  t0 = 0x0,
  t1 = 0x0,
  t2 = 0x0,
  s0 = 0x0,
  s1 = 0x0,
  a0 = 0x0,
  a1 = 0x0,
  a2 = 0x0,
  a3 = 0x81403f90,
  a4 = 0x80c04000,
  a5 = 0x1,
  a6 = 0xffffffff81337000,
  a7 = 0x81096700,
  s2 = 0x81400000,
  s3 = 0xffffffff81200000,
  s4 = 0x81403fd0,
  s5 = 0x80a02c6c,
  s6 = 0x8000000000006800,
  s7 = 0x0,
  s8 = 0xfffffffffffffff3,
  s9 = 0x80c01000,
  s10 = 0x81096700,
  s11 = 0x82200000,
  t3 = 0x81404000,
  t4 = 0x80a02dea,
  t5 = 0x0,
  t6 = 0x82200000,
  status = 0x80008638, <- Wrong value in stack!!!
  badaddr = 0x82200000,
  cause = 0x0,
  orig_a0 = 0x80201142
}
(gdb) p/x $pc
$72 = 0x80201142
(gdb) p/x sizeof(struct pt_regs)
$73 = 0x120

Co-developed-by: ShihPo Hung <shihpo.hung@sifive.com>
Signed-off-by: ShihPo Hung <shihpo.hung@sifive.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/kernel/head.S | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 2c81ca42ec4e..c7effef23f41 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -301,6 +301,7 @@ clear_bss_done:
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
 	XIP_FIXUP_OFFSET sp
+	addi sp, sp, -PT_SIZE
 #ifdef CONFIG_BUILTIN_DTB
 	la a0, __dtb_start
 	XIP_FIXUP_OFFSET a0
@@ -318,6 +319,7 @@ clear_bss_done:
 	/* Restore C environment */
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
+	addi sp, sp, -PT_SIZE
 
 #ifdef CONFIG_KASAN
 	call kasan_early_init
-- 
2.25.1

[PATCH v12 15/17] riscv: Add V extension to KVM ISA allow list

[Chris Stillson]

From: Vincent Chen <vincent.chen@sifive.com>

Add V extension to KVM_RISCV_ISA_ALLOWED list to enable VCPU
to support V extension.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
---
 arch/riscv/include/asm/hwcap.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 6f59ec64175e..b242ed155262 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -35,6 +35,7 @@ extern unsigned long elf_hwcap;
 #define RISCV_ISA_EXT_m		('m' - 'a')
 #define RISCV_ISA_EXT_s		('s' - 'a')
 #define RISCV_ISA_EXT_u		('u' - 'a')
+#define RISCV_ISA_EXT_v		('v' - 'a')
 
 /*
  * Increse this to higher value as kernel support more ISA extensions.
-- 
2.25.1

[PATCH v12 16/17] riscv: KVM: Add vector lazy save/restore support

[Chris Stillson]

From: Vincent Chen <vincent.chen@sifive.com>

This patch adds vector context save/restore for guest VCPUs. To reduce the
impact on KVM performance, the implementation imitates the FP context
switch mechanism to lazily store and restore the vector context only when
the kernel enters/exits the in-kernel run loop and not during the KVM
world switch.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
---
 arch/riscv/include/asm/kvm_host.h        |   2 +
 arch/riscv/include/asm/kvm_vcpu_vector.h |  65 +++++++++
 arch/riscv/include/uapi/asm/kvm.h        |   7 +
 arch/riscv/kernel/asm-offsets.c          |   7 +
 arch/riscv/kvm/Makefile                  |   1 +
 arch/riscv/kvm/vcpu.c                    |  32 +++++
 arch/riscv/kvm/vcpu_switch.S             |  69 +++++++++
 arch/riscv/kvm/vcpu_vector.c             | 173 +++++++++++++++++++++++
 8 files changed, 356 insertions(+)
 create mode 100644 arch/riscv/include/asm/kvm_vcpu_vector.h
 create mode 100644 arch/riscv/kvm/vcpu_vector.c

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 60c517e4d576..665ddb4cec62 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -17,6 +17,7 @@
 #include <asm/hwcap.h>
 #include <asm/kvm_vcpu_fp.h>
 #include <asm/kvm_vcpu_insn.h>
+#include <asm/kvm_vcpu_vector.h>
 #include <asm/kvm_vcpu_timer.h>
 
 #define KVM_MAX_VCPUS			1024
@@ -143,6 +144,7 @@ struct kvm_cpu_context {
 	unsigned long sstatus;
 	unsigned long hstatus;
 	union __riscv_fp_state fp;
+	struct __riscv_v_state vector;
 };
 
 struct kvm_vcpu_csr {
diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h
new file mode 100644
index 000000000000..1dcc1b2e05bb
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_vector.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2022 SiFive
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ *     Anup Patel <anup.patel@wdc.com>
+ *     Vincent Chen <vincent.chen@sifive.com>
+ *     Greentime Hu <greentime.hu@sifive.com>
+ */
+
+#ifndef __KVM_VCPU_RISCV_VECTOR_H
+#define __KVM_VCPU_RISCV_VECTOR_H
+
+#include <linux/types.h>
+
+struct kvm_cpu_context;
+
+#ifdef CONFIG_VECTOR
+void __kvm_riscv_vector_save(struct kvm_cpu_context *context);
+void __kvm_riscv_vector_restore(struct kvm_cpu_context *context);
+void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
+				      unsigned long isa);
+void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
+					 unsigned long isa);
+void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx);
+void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx);
+void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu);
+#else
+static inline void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
+						    unsigned long isa)
+{
+}
+
+static inline void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
+						       unsigned long isa)
+{
+}
+
+static inline void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx)
+{
+}
+
+static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx)
+{
+}
+
+static inline void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu)
+{
+}
+#endif
+
+int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg,
+				  unsigned long rtype);
+int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg,
+				  unsigned long rtype);
+#endif
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 7351417afd62..f4ba57b235a3 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -96,6 +96,7 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_H,
 	KVM_RISCV_ISA_EXT_I,
 	KVM_RISCV_ISA_EXT_M,
+	KVM_RISCV_ISA_EXT_V,
 	KVM_RISCV_ISA_EXT_SVPBMT,
 	KVM_RISCV_ISA_EXT_SSTC,
 	KVM_RISCV_ISA_EXT_MAX,
@@ -145,6 +146,12 @@ enum KVM_RISCV_ISA_EXT_ID {
 /* ISA Extension registers are mapped as type 7 */
 #define KVM_REG_RISCV_ISA_EXT		(0x07 << KVM_REG_RISCV_TYPE_SHIFT)
 
+/* V extension registers are mapped as type 7 */
+#define KVM_REG_RISCV_VECTOR		(0x07 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_VECTOR_CSR_REG(name)	\
+		(offsetof(struct __riscv_v_state, name) / sizeof(unsigned long))
+#define KVM_REG_RISCV_VECTOR_REG(n)	\
+		((n) + sizeof(struct __riscv_v_state) / sizeof(unsigned long))
 #endif
 
 #endif /* __LINUX_KVM_RISCV_H */
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 80316ef7bb78..2540b9146072 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -278,6 +278,13 @@ void asm_offsets(void)
 	OFFSET(KVM_ARCH_FP_D_F31, kvm_cpu_context, fp.d.f[31]);
 	OFFSET(KVM_ARCH_FP_D_FCSR, kvm_cpu_context, fp.d.fcsr);
 
+	/* V extension */
+
+	OFFSET(KVM_ARCH_VECTOR_VSTART, kvm_cpu_context, vector.vstart);
+	OFFSET(KVM_ARCH_VECTOR_VL, kvm_cpu_context, vector.vl);
+	OFFSET(KVM_ARCH_VECTOR_VTYPE, kvm_cpu_context, vector.vtype);
+	OFFSET(KVM_ARCH_VECTOR_VCSR, kvm_cpu_context, vector.vcsr);
+	OFFSET(KVM_ARCH_VECTOR_DATAP, kvm_cpu_context, vector.datap);
 	/*
 	 * THREAD_{F,X}* might be larger than a S-type offset can handle, but
 	 * these are used in performance-sensitive assembly so we can't resort
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index 019df9208bdd..b26bc605a267 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -17,6 +17,7 @@ kvm-y += mmu.o
 kvm-y += vcpu.o
 kvm-y += vcpu_exit.o
 kvm-y += vcpu_fp.o
+kvm-y += vcpu_vector.o
 kvm-y += vcpu_insn.o
 kvm-y += vcpu_switch.o
 kvm-y += vcpu_sbi.o
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index d0f08d5b4282..76941937e745 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -19,6 +19,7 @@
 #include <linux/kvm_host.h>
 #include <asm/csr.h>
 #include <asm/hwcap.h>
+#include <asm/switch_to.h>
 
 const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
@@ -51,6 +52,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	RISCV_ISA_EXT_h,
 	RISCV_ISA_EXT_i,
 	RISCV_ISA_EXT_m,
+	RISCV_ISA_EXT_v,
 	RISCV_ISA_EXT_SVPBMT,
 	RISCV_ISA_EXT_SSTC,
 };
@@ -79,6 +81,7 @@ static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext)
 	return true;
 }
 
+//CMS FIXME
 static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 {
 	switch (ext) {
@@ -121,6 +124,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	kvm_riscv_vcpu_fp_reset(vcpu);
 
+	kvm_riscv_vcpu_vector_reset(vcpu);
+
 	kvm_riscv_vcpu_timer_reset(vcpu);
 
 	WRITE_ONCE(vcpu->arch.irqs_pending, 0);
@@ -171,6 +176,15 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	cntx->hstatus |= HSTATUS_SPVP;
 	cntx->hstatus |= HSTATUS_SPV;
 
+	if (has_vector()) {
+		cntx->vector.datap = kmalloc(riscv_vsize, GFP_KERNEL);
+		if (!cntx->vector.datap)
+			return -ENOMEM;
+		vcpu->arch.host_context.vector.datap = kzalloc(riscv_vsize, GFP_KERNEL);
+		if (!vcpu->arch.host_context.vector.datap)
+			return -ENOMEM;
+	}
+
 	/* By default, make CY, TM, and IR counters accessible in VU mode */
 	reset_csr->scounteren = 0x7;
 
@@ -201,6 +215,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 	/* Free unused pages pre-allocated for G-stage page table mappings */
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+
+	/* Free vector context space for host and guest kernel */
+	kvm_riscv_vcpu_free_vector_context(vcpu);
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -539,6 +556,9 @@ static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 						 KVM_REG_RISCV_FP_D);
 	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
 		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_VECTOR)
+		return kvm_riscv_vcpu_set_reg_vector(vcpu, reg,
+						 KVM_REG_RISCV_VECTOR);
 
 	return -EINVAL;
 }
@@ -562,6 +582,9 @@ static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 						 KVM_REG_RISCV_FP_D);
 	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
 		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_VECTOR)
+		return kvm_riscv_vcpu_get_reg_vector(vcpu, reg,
+						 KVM_REG_RISCV_VECTOR);
 
 	return -EINVAL;
 }
@@ -818,6 +841,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_riscv_vcpu_host_fp_save(&vcpu->arch.host_context);
 	kvm_riscv_vcpu_guest_fp_restore(&vcpu->arch.guest_context,
 					vcpu->arch.isa);
+	kvm_riscv_vcpu_host_vector_save(&vcpu->arch.host_context);
+	kvm_riscv_vcpu_guest_vector_restore(&vcpu->arch.guest_context,
+					    vcpu->arch.isa);
 
 	vcpu->cpu = cpu;
 }
@@ -834,6 +860,12 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 	kvm_riscv_vcpu_timer_save(vcpu);
 
+	kvm_riscv_vcpu_guest_vector_save(&vcpu->arch.guest_context,
+					 vcpu->arch.isa);
+	kvm_riscv_vcpu_host_vector_restore(&vcpu->arch.host_context);
+
+	csr_write(CSR_HGATP, 0);
+
 	csr->vsstatus = csr_read(CSR_VSSTATUS);
 	csr->vsie = csr_read(CSR_VSIE);
 	csr->vstvec = csr_read(CSR_VSTVEC);
diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
index d74df8eb4d71..730dc9b8c644 100644
--- a/arch/riscv/kvm/vcpu_switch.S
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -406,3 +406,72 @@ __kvm_riscv_fp_d_restore:
 	csrw CSR_SSTATUS, t2
 	ret
 #endif
+
+#ifdef CONFIG_VECTOR
+
+#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(__kvm_riscv_vector_save)
+	li      status, SR_VS
+	csrs    CSR_STATUS, status
+
+	li	a2, KVM_ARCH_VECTOR_DATAP
+	add	datap, a0, a2
+	ld	datap, (datap)
+	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, KVM_ARCH_VECTOR_VSTART(vstatep)
+	REG_S   x_vtype, KVM_ARCH_VECTOR_VTYPE(vstatep)
+	REG_S   x_vl, KVM_ARCH_VECTOR_VL(vstatep)
+	REG_S   x_vcsr, KVM_ARCH_VECTOR_VCSR(vstatep)
+
+	csrc	CSR_STATUS, status
+	ret
+ENDPROC(__kvm_riscv_vector_save)
+
+ENTRY(__kvm_riscv_vector_restore)
+	li      status, SR_VS
+	csrs    CSR_STATUS, status
+
+	li	a2, KVM_ARCH_VECTOR_DATAP
+	add	datap, a0, a2
+	ld	datap, (datap)
+	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, KVM_ARCH_VECTOR_VSTART(vstatep)
+	REG_L   x_vtype, KVM_ARCH_VECTOR_VTYPE(vstatep)
+	REG_L   x_vl, KVM_ARCH_VECTOR_VL(vstatep)
+	REG_L   x_vcsr, KVM_ARCH_VECTOR_VCSR(vstatep)
+	vsetvl  x0, x_vl, x_vtype
+	csrw    CSR_VSTART, x_vstart
+	csrw    CSR_VCSR, x_vcsr
+
+	csrc	CSR_STATUS, status
+	ret
+ENDPROC(__kvm_riscv_vector_restore)
+#endif
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
new file mode 100644
index 000000000000..37bf4ffd47dd
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2022 SiFive
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ *     Anup Patel <anup.patel@wdc.com>
+ *     Vincent Chen <vincent.chen@sifive.com>
+ *     Greentime Hu <greentime.hu@sifive.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/uaccess.h>
+#include <asm/hwcap.h>
+
+#ifdef CONFIG_VECTOR
+extern unsigned long riscv_vsize;
+void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu)
+{
+	unsigned long isa = vcpu->arch.isa;
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+
+	cntx->sstatus &= ~SR_VS;
+	if (riscv_isa_extension_available(&isa, v))
+		cntx->sstatus |= SR_VS_INITIAL;
+	else
+		cntx->sstatus |= SR_VS_OFF;
+
+	memset(cntx->vector.datap, 0, riscv_vsize);
+}
+
+static void kvm_riscv_vcpu_vector_clean(struct kvm_cpu_context *cntx)
+{
+	cntx->sstatus &= ~SR_VS;
+	cntx->sstatus |= SR_VS_CLEAN;
+}
+
+void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
+				      unsigned long isa)
+{
+	if ((cntx->sstatus & SR_VS) == SR_VS_DIRTY) {
+		if (riscv_isa_extension_available(&isa, v))
+			__kvm_riscv_vector_save(cntx);
+		kvm_riscv_vcpu_vector_clean(cntx);
+	}
+}
+
+void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
+					 unsigned long isa)
+{
+	if ((cntx->sstatus & SR_VS) != SR_VS_OFF) {
+		if (riscv_isa_extension_available(&isa, v))
+			__kvm_riscv_vector_restore(cntx);
+		kvm_riscv_vcpu_vector_clean(cntx);
+	}
+}
+
+void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx)
+{
+	/* No need to check host sstatus as it can be modified outside */
+	__kvm_riscv_vector_save(cntx);
+}
+
+void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx)
+{
+	__kvm_riscv_vector_restore(cntx);
+}
+
+void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu)
+{
+	kfree(vcpu->arch.guest_reset_context.vector.datap);
+	kfree(vcpu->arch.host_context.vector.datap);
+}
+#else
+#define riscv_vsize (0)
+#endif
+
+static void *kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu,
+				      unsigned long reg_num,
+				      size_t reg_size)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	void *reg_val;
+	size_t vlenb = riscv_vsize / 32;
+
+	if (reg_num < KVM_REG_RISCV_VECTOR_REG(0)) {
+		if (reg_size != sizeof(unsigned long))
+			return NULL;
+		switch (reg_num) {
+		case KVM_REG_RISCV_VECTOR_CSR_REG(vstart):
+			reg_val = &cntx->vector.vstart;
+			break;
+		case KVM_REG_RISCV_VECTOR_CSR_REG(vl):
+			reg_val = &cntx->vector.vl;
+			break;
+		case KVM_REG_RISCV_VECTOR_CSR_REG(vtype):
+			reg_val = &cntx->vector.vtype;
+			break;
+		case KVM_REG_RISCV_VECTOR_CSR_REG(vcsr):
+			reg_val = &cntx->vector.vcsr;
+			break;
+		case KVM_REG_RISCV_VECTOR_CSR_REG(datap):
+		default:
+			return NULL;
+		}
+	} else if (reg_num <= KVM_REG_RISCV_VECTOR_REG(31)) {
+		if (reg_size != vlenb)
+			return NULL;
+		reg_val = cntx->vector.datap
+			  + (reg_num - KVM_REG_RISCV_VECTOR_REG(0)) * vlenb;
+	} else {
+		return NULL;
+	}
+
+	return reg_val;
+}
+
+int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg,
+				  unsigned long rtype)
+{
+	unsigned long isa = vcpu->arch.isa;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    rtype);
+	void *reg_val;
+	size_t reg_size = KVM_REG_SIZE(reg->id);
+
+	if ((rtype == KVM_REG_RISCV_VECTOR) &&
+	    riscv_isa_extension_available(&isa, v)) {
+		reg_val = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size);
+	}
+
+	if (!reg_val)
+		return -EINVAL;
+
+	if (copy_to_user(uaddr, reg_val, reg_size))
+		return -EFAULT;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg,
+				  unsigned long rtype)
+{
+	unsigned long isa = vcpu->arch.isa;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    rtype);
+	void *reg_val = NULL;
+	size_t reg_size = KVM_REG_SIZE(reg->id);
+
+	if ((rtype == KVM_REG_RISCV_VECTOR) &&
+	    riscv_isa_extension_available(&isa, v)) {
+		reg_val = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size);
+	}
+
+	if (!reg_val)
+		return -EINVAL;
+
+	if (copy_from_user(reg_val, uaddr, reg_size))
+		return -EFAULT;
+
+	return 0;
+}
-- 
2.25.1

[PATCH v12 17/17] riscv: prctl to enable vector commands

[Chris Stillson]

This code makes enabling the vector extension on a riscv manchine
optional by adding an option to prctl() to allow a process to enable,
disable or query its vector context state.

-added prctl to enable/disable/query current vector state
-added actual function in riscv specific code to change/query the process
state
- Fixed problem with initial set of patches
	(missing some EXPORT_SYMBOL() macro calls)
- rebased to 6.0-rc1
---
 arch/riscv/configs/defconfig             |  6 ++++++
 arch/riscv/include/asm/kvm_vcpu_vector.h |  8 ++++----
 arch/riscv/include/asm/processor.h       |  6 ++++++
 arch/riscv/include/asm/switch_to.h       | 11 +++++++++++
 arch/riscv/kernel/cpufeature.c           |  3 ++-
 arch/riscv/kernel/process.c              | 20 +++++++++++++++++++-
 arch/riscv/kvm/vcpu_vector.c             | 14 +++++++-------
 include/uapi/linux/prctl.h               |  6 ++++++
 kernel/sys.c                             |  7 +++++++
 9 files changed, 68 insertions(+), 13 deletions(-)

diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index aed332a9d4ea..fce054286b1f 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -209,3 +209,9 @@ CONFIG_RCU_EQS_DEBUG=y
 # CONFIG_FTRACE is not set
 # CONFIG_RUNTIME_TESTING_MENU is not set
 CONFIG_MEMTEST=y
+CONFIG_ARCH_RV64I=y
+CONFIG_64BIT=y
+CONFIG_VECTOR=y
+CONFIG_ARCH_RV64I=y
+CONFIG_64BIT=y
+CONFIG_VECTOR=y
diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h
index 1dcc1b2e05bb..c7101ff943a0 100644
--- a/arch/riscv/include/asm/kvm_vcpu_vector.h
+++ b/arch/riscv/include/asm/kvm_vcpu_vector.h
@@ -22,9 +22,9 @@ void __kvm_riscv_vector_save(struct kvm_cpu_context *context);
 void __kvm_riscv_vector_restore(struct kvm_cpu_context *context);
 void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
-				      unsigned long isa);
+				      unsigned long *isa);
 void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
-					 unsigned long isa);
+					 unsigned long *isa);
 void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx);
 void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx);
 void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu);
@@ -34,12 +34,12 @@ static inline void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu)
 }
 
 static inline void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
-						    unsigned long isa)
+						    unsigned long *isa)
 {
 }
 
 static inline void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
-						       unsigned long isa)
+						       unsigned long *isa)
 {
 }
 
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index a09141ecf6aa..f2d0a91ce174 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -88,6 +88,12 @@ extern void riscv_fill_hwcap(void);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
 extern unsigned long signal_minsigstksz __ro_after_init;
+
+#ifdef CONFIG_VECTOR
+extern int rvv_proc_enable(unsigned long x);
+#define RVV_PROC_ENABLE(x) rvv_proc_enable(x)
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 527951c033d4..d9747450311c 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -80,6 +80,17 @@ extern unsigned long riscv_vsize;
 extern void __vstate_save(struct __riscv_v_state *save_to, void *datap);
 extern void __vstate_restore(struct __riscv_v_state *restore_from, void *datap);
 
+static inline bool vstate_query(struct pt_regs *regs)
+{
+	return (regs->status & SR_VS) != 0;
+}
+
+static inline void vstate_on(struct task_struct *task,
+				struct pt_regs *regs)
+{
+	regs->status = (regs->status & ~(SR_VS)) | SR_VS_INITIAL;
+}
+
 static inline void __vstate_clean(struct pt_regs *regs)
 {
 	regs->status = (regs->status & ~(SR_VS)) | SR_VS_CLEAN;
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 0487ab19b234..3be469cb9266 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -37,6 +37,8 @@ __ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_fpu);
 #include <asm/vector.h>
 __ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_vector);
 unsigned long riscv_vsize __read_mostly;
+EXPORT_SYMBOL(cpu_hwcap_vector);
+EXPORT_SYMBOL(riscv_vsize);
 #endif
 
 /**
@@ -346,4 +348,3 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
 	}
 }
 #endif
-}
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index e88a37fc77ed..a5a76d1374ec 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/tick.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
+#include <linux/prctl.h>
 
 #include <asm/unistd.h>
 #include <asm/processor.h>
@@ -134,7 +135,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 			if (WARN_ON(!vstate->datap))
 				return;
 		}
-		regs->status |= SR_VS_INITIAL;
 
 		/*
 		 * Restore the initial value to the vector register
@@ -230,3 +229,22 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }
+
+#ifdef CONFIG_VECTOR
+int rvv_proc_enable(unsigned long x)
+{
+	switch (x) {
+	case PR_RVV_DISABLE:
+		vstate_off(current, task_pt_regs(current));
+		return 0;
+	case PR_RVV_ENABLE:
+		vstate_on(current, task_pt_regs(current));
+		return 0;
+	case PR_RVV_QUERY:
+		return vstate_query(task_pt_regs(current));
+	default:
+		return -(EINVAL);
+
+	}
+}
+#endif
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index 37bf4ffd47dd..9d1613da561a 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -20,7 +20,7 @@
 extern unsigned long riscv_vsize;
 void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu)
 {
-	unsigned long isa = vcpu->arch.isa;
+	unsigned long isa = *vcpu->arch.isa;
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
 
 	cntx->sstatus &= ~SR_VS;
@@ -39,20 +39,20 @@ static void kvm_riscv_vcpu_vector_clean(struct kvm_cpu_context *cntx)
 }
 
 void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
-				      unsigned long isa)
+				      unsigned long *isa)
 {
 	if ((cntx->sstatus & SR_VS) == SR_VS_DIRTY) {
-		if (riscv_isa_extension_available(&isa, v))
+		if (riscv_isa_extension_available(isa, v))
 			__kvm_riscv_vector_save(cntx);
 		kvm_riscv_vcpu_vector_clean(cntx);
 	}
 }
 
 void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
-					 unsigned long isa)
+					 unsigned long *isa)
 {
 	if ((cntx->sstatus & SR_VS) != SR_VS_OFF) {
-		if (riscv_isa_extension_available(&isa, v))
+		if (riscv_isa_extension_available(isa, v))
 			__kvm_riscv_vector_restore(cntx);
 		kvm_riscv_vcpu_vector_clean(cntx);
 	}
@@ -122,7 +122,7 @@ int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
 				  const struct kvm_one_reg *reg,
 				  unsigned long rtype)
 {
-	unsigned long isa = vcpu->arch.isa;
+	unsigned long isa = *vcpu->arch.isa;
 	unsigned long __user *uaddr =
 			(unsigned long __user *)(unsigned long)reg->addr;
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
@@ -149,7 +149,7 @@ int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
 				  const struct kvm_one_reg *reg,
 				  unsigned long rtype)
 {
-	unsigned long isa = vcpu->arch.isa;
+	unsigned long isa = *vcpu->arch.isa;
 	unsigned long __user *uaddr =
 			(unsigned long __user *)(unsigned long)reg->addr;
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index a5e06dcbba13..8ea56e4c48f8 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -281,6 +281,12 @@ struct prctl_mm_map {
 # define PR_SME_VL_LEN_MASK		0xffff
 # define PR_SME_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* RISC-V V vector extension */
+#define PR_RVV_STATE			65
+# define PR_RVV_DISABLE			0
+# define PR_RVV_ENABLE			1
+# define PR_RVV_QUERY			2
+
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
diff --git a/kernel/sys.c b/kernel/sys.c
index b911fa6d81ab..3049b1823273 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -138,6 +138,9 @@
 #ifndef GET_TAGGED_ADDR_CTRL
 # define GET_TAGGED_ADDR_CTRL()		(-EINVAL)
 #endif
+#ifndef RVV_PROC_ENABLE
+# define RVV_PROC_ENABLE(x)			(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -2620,6 +2623,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		error = sched_core_share_pid(arg2, arg3, arg4, arg5);
 		break;
 #endif
+	case PR_RVV_STATE:
+		error = RVV_PROC_ENABLE(arg2);
+		break;
+
 	case PR_SET_VMA:
 		error = prctl_set_vma(arg2, arg3, arg4, arg5);
 		break;
-- 
2.25.1

[PATCH v12 01/17] riscv: Rename __switch_to_aux -> fpu

[Heiko Stübner]

Am Mittwoch, 21. September 2022, 23:43:43 CET schrieb Chris Stillson:
> From: Guo Ren <ren_guo@c-sky.com>
> 
> The name of __switch_to_aux is not clear and rename it with the
> determine function: __switch_to_fpu. Next we could add other regs'
> switch.
> 
> Signed-off-by: Guo Ren <ren_guo@c-sky.com>
> Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
> Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
> Reviewed-by: Anup Patel <anup@brainfault.org>
> Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>

Tested-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>