[-next,v17,10/20] riscv: Allocate user's vector context in the first-use trap

Commit Message

Andy Chiu March 27, 2023, 4:49 p.m. UTC

Vector unit is disabled by default for all user processes. Thus, a
process will take a trap (illegal instruction) into kernel at the first
time when it uses Vector. Only after then, the kernel allocates V
context and starts take care of the context for that user process.

Suggested-by: Richard Henderson <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Andy Chiu <[e-mail]>
---
 arch/riscv/include/asm/insn.h   | 29 +++++++++++
 arch/riscv/include/asm/vector.h |  2 +
 arch/riscv/kernel/traps.c       | 26 +++++++++-
 arch/riscv/kernel/vector.c      | 90 +++++++++++++++++++++++++++++++++
 4 files changed, 145 insertions(+), 2 deletions(-)

Comments

Conor Dooley March 28, 2023, 5:22 p.m. UTC | #1

On Mon, Mar 27, 2023 at 04:49:30PM +0000, Andy Chiu wrote:
> Vector unit is disabled by default for all user processes. Thus, a
> process will take a trap (illegal instruction) into kernel at the first
> time when it uses Vector. Only after then, the kernel allocates V
> context and starts take care of the context for that user process.
> 
> Suggested-by: Richard Henderson <[e-mail]>
> Link: https://lore.kernel.org/r/[e-mail]
> Signed-off-by: Andy Chiu <[e-mail]>

I see you dropped two R-b from this patch, what actually changed here?
It's not immediately obvious to me (sorry!) and the cover doesn't mention
why they were dropped.

Thanks Andy!
Conor.

> ---
>  arch/riscv/include/asm/insn.h   | 29 +++++++++++
>  arch/riscv/include/asm/vector.h |  2 +
>  arch/riscv/kernel/traps.c       | 26 +++++++++-
>  arch/riscv/kernel/vector.c      | 90 +++++++++++++++++++++++++++++++++
>  4 files changed, 145 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h
> index 8d5c84f2d5ef..4e1505cef8aa 100644
> --- a/arch/riscv/include/asm/insn.h
> +++ b/arch/riscv/include/asm/insn.h
> @@ -137,6 +137,26 @@
>  #define RVG_OPCODE_JALR		0x67
>  #define RVG_OPCODE_JAL		0x6f
>  #define RVG_OPCODE_SYSTEM	0x73
> +#define RVG_SYSTEM_CSR_OFF	20
> +#define RVG_SYSTEM_CSR_MASK	GENMASK(12, 0)
> +
> +/* parts of opcode for RVF, RVD and RVQ */
> +#define RVFDQ_FL_FS_WIDTH_OFF	12
> +#define RVFDQ_FL_FS_WIDTH_MASK	GENMASK(3, 0)
> +#define RVFDQ_FL_FS_WIDTH_W	2
> +#define RVFDQ_FL_FS_WIDTH_D	3
> +#define RVFDQ_LS_FS_WIDTH_Q	4
> +#define RVFDQ_OPCODE_FL		0x07
> +#define RVFDQ_OPCODE_FS		0x27
> +
> +/* parts of opcode for RVV */
> +#define RVV_OPCODE_VECTOR	0x57
> +#define RVV_VL_VS_WIDTH_8	0
> +#define RVV_VL_VS_WIDTH_16	5
> +#define RVV_VL_VS_WIDTH_32	6
> +#define RVV_VL_VS_WIDTH_64	7
> +#define RVV_OPCODE_VL		RVFDQ_OPCODE_FL
> +#define RVV_OPCODE_VS		RVFDQ_OPCODE_FS
>  
>  /* parts of opcode for RVC*/
>  #define RVC_OPCODE_C0		0x0
> @@ -304,6 +324,15 @@ static __always_inline bool riscv_insn_is_branch(u32 code)
>  	(RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \
>  	(RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); })
>  
> +#define RVG_EXTRACT_SYSTEM_CSR(x) \
> +	({typeof(x) x_ = (x); RV_X(x_, RVG_SYSTEM_CSR_OFF, RVG_SYSTEM_CSR_MASK); })
> +
> +#define RVFDQ_EXTRACT_FL_FS_WIDTH(x) \
> +	({typeof(x) x_ = (x); RV_X(x_, RVFDQ_FL_FS_WIDTH_OFF, \
> +				   RVFDQ_FL_FS_WIDTH_MASK); })
> +
> +#define RVV_EXRACT_VL_VS_WIDTH(x) RVFDQ_EXTRACT_FL_FS_WIDTH(x)
> +
>  /*
>   * Get the immediate from a J-type instruction.
>   *
> diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
> index 4161352d6ea8..70a5e696c1de 100644
> --- a/arch/riscv/include/asm/vector.h
> +++ b/arch/riscv/include/asm/vector.h
> @@ -20,6 +20,7 @@
>  
>  extern unsigned long riscv_v_vsize;
>  void riscv_v_setup_vsize(void);
> +bool riscv_v_first_use_handler(struct pt_regs *regs);
>  
>  static __always_inline bool has_vector(void)
>  {
> @@ -163,6 +164,7 @@ static inline void __switch_to_vector(struct task_struct *prev,
>  struct pt_regs;
>  
>  static __always_inline bool has_vector(void) { return false; }
> +static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; }
>  static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
>  #define riscv_v_vsize (0)
>  #define riscv_v_setup_vsize()			do {} while (0)
> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
> index 1f4e37be7eb3..f543e5ebfd29 100644
> --- a/arch/riscv/kernel/traps.c
> +++ b/arch/riscv/kernel/traps.c
> @@ -26,6 +26,7 @@
>  #include <asm/ptrace.h>
>  #include <asm/syscall.h>
>  #include <asm/thread_info.h>
> +#include <asm/vector.h>
>  
>  int show_unhandled_signals = 1;
>  
> @@ -145,8 +146,29 @@ DO_ERROR_INFO(do_trap_insn_misaligned,
>  	SIGBUS, BUS_ADRALN, "instruction address misaligned");
>  DO_ERROR_INFO(do_trap_insn_fault,
>  	SIGSEGV, SEGV_ACCERR, "instruction access fault");
> -DO_ERROR_INFO(do_trap_insn_illegal,
> -	SIGILL, ILL_ILLOPC, "illegal instruction");
> +
> +asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *regs)
> +{
> +	if (user_mode(regs)) {
> +		irqentry_enter_from_user_mode(regs);
> +
> +		local_irq_enable();
> +
> +		if (!has_vector() || !riscv_v_first_use_handler(regs))
> +			do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
> +				      "Oops - illegal instruction");
> +
> +		irqentry_exit_to_user_mode(regs);
> +	} else {
> +		irqentry_state_t state = irqentry_nmi_enter(regs);
> +
> +		do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
> +			      "Oops - illegal instruction");
> +
> +		irqentry_nmi_exit(regs, state);
> +	}
> +}
> +
>  DO_ERROR_INFO(do_trap_load_fault,
>  	SIGSEGV, SEGV_ACCERR, "load access fault");
>  #ifndef CONFIG_RISCV_M_MODE
> diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
> index 03582e2ade83..ea59f32adf46 100644
> --- a/arch/riscv/kernel/vector.c
> +++ b/arch/riscv/kernel/vector.c
> @@ -4,9 +4,19 @@
>   * Author: Andy Chiu <[e-mail]>
>   */
>  #include <linux/export.h>
> +#include <linux/sched/signal.h>
> +#include <linux/types.h>
> +#include <linux/slab.h>
> +#include <linux/sched.h>
> +#include <linux/uaccess.h>
>  
> +#include <asm/thread_info.h>
> +#include <asm/processor.h>
> +#include <asm/insn.h>
>  #include <asm/vector.h>
>  #include <asm/csr.h>
> +#include <asm/ptrace.h>
> +#include <asm/bug.h>
>  
>  unsigned long riscv_v_vsize __read_mostly;
>  EXPORT_SYMBOL_GPL(riscv_v_vsize);
> @@ -18,3 +28,83 @@ void riscv_v_setup_vsize(void)
>  	riscv_v_vsize = csr_read(CSR_VLENB) * 32;
>  	riscv_v_disable();
>  }
> +
> +static bool insn_is_vector(u32 insn_buf)
> +{
> +	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
> +	bool is_vector = false;
> +	u32 width, csr;
> +
> +	/*
> +	 * All V-related instructions, including CSR operations are 4-Byte. So,
> +	 * do not handle if the instruction length is not 4-Byte.
> +	 */
> +	if (unlikely(GET_INSN_LENGTH(insn_buf) != 4))
> +		return false;
> +
> +	switch (opcode) {
> +	case RVV_OPCODE_VECTOR:
> +		is_vector = true;
> +		break;
> +	case RVV_OPCODE_VL:
> +	case RVV_OPCODE_VS:
> +		width = RVV_EXRACT_VL_VS_WIDTH(insn_buf);
> +		if (width == RVV_VL_VS_WIDTH_8 || width == RVV_VL_VS_WIDTH_16 ||
> +		    width == RVV_VL_VS_WIDTH_32 || width == RVV_VL_VS_WIDTH_64)
> +			is_vector = true;
> +		break;
> +	case RVG_OPCODE_SYSTEM:
> +		csr = RVG_EXTRACT_SYSTEM_CSR(insn_buf);
> +		if ((csr >= CSR_VSTART && csr <= CSR_VCSR) ||
> +		    (csr >= CSR_VL && csr <= CSR_VLENB))
> +			is_vector = true;
> +		break;
> +	}
> +	return is_vector;
> +}
> +
> +static int riscv_v_thread_zalloc(void)
> +{
> +	void *datap;
> +
> +	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
> +	if (!datap)
> +		return -ENOMEM;
> +	current->thread.vstate.datap = datap;
> +	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
> +						    datap));
> +	return 0;
> +}
> +
> +bool riscv_v_first_use_handler(struct pt_regs *regs)
> +{
> +	u32 __user *epc = (u32 __user *)regs->epc;
> +	u32 insn = (u32)regs->badaddr;
> +
> +	/* If V has been enabled then it is not the first-use trap */
> +	if (riscv_v_vstate_query(regs))
> +		return false;
> +
> +	/* Get the instruction */
> +	if (!insn) {
> +		if (__get_user(insn, epc))
> +			return false;
> +	}
> +	/* Filter out non-V instructions */
> +	if (!insn_is_vector(insn))
> +		return false;
> +
> +	/* Sanity check. datap should be null by the time of the first-use trap */
> +	WARN_ON(current->thread.vstate.datap);
> +	/*
> +	 * Now we sure that this is a V instruction. And it executes in the
> +	 * context where VS has been off. So, try to allocate the user's V
> +	 * context and resume execution.
> +	 */
> +	if (riscv_v_thread_zalloc()) {
> +		force_sig(SIGKILL);
> +		return true;
> +	}
> +	riscv_v_vstate_on(regs);
> +	return true;
> +}
> -- 
> 2.17.1
>

Heiko Stuebner March 31, 2023, 1:08 p.m. UTC | #2

Am Montag, 27. März 2023, 18:49:30 CEST schrieb Andy Chiu:
> Vector unit is disabled by default for all user processes. Thus, a
> process will take a trap (illegal instruction) into kernel at the first
> time when it uses Vector. Only after then, the kernel allocates V
> context and starts take care of the context for that user process.
> 
> Suggested-by: Richard Henderson <[e-mail]>
> Link: https://lore.kernel.org/r/[e-mail]
> Signed-off-by: Andy Chiu <[e-mail]>
> ---
>  arch/riscv/include/asm/insn.h   | 29 +++++++++++
>  arch/riscv/include/asm/vector.h |  2 +
>  arch/riscv/kernel/traps.c       | 26 +++++++++-
>  arch/riscv/kernel/vector.c      | 90 +++++++++++++++++++++++++++++++++
>  4 files changed, 145 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h
> index 8d5c84f2d5ef..4e1505cef8aa 100644
> --- a/arch/riscv/include/asm/insn.h
> +++ b/arch/riscv/include/asm/insn.h
> @@ -137,6 +137,26 @@
>  #define RVG_OPCODE_JALR		0x67
>  #define RVG_OPCODE_JAL		0x6f
>  #define RVG_OPCODE_SYSTEM	0x73
> +#define RVG_SYSTEM_CSR_OFF	20
> +#define RVG_SYSTEM_CSR_MASK	GENMASK(12, 0)

The CSR instructions are all I-type instructions it seems, but I do
understand where this is coming from, as for CSRs this is not an IMM
but an unsigned value

> +/* parts of opcode for RVF, RVD and RVQ */
> +#define RVFDQ_FL_FS_WIDTH_OFF	12
> +#define RVFDQ_FL_FS_WIDTH_MASK	GENMASK(3, 0)
> +#define RVFDQ_FL_FS_WIDTH_W	2
> +#define RVFDQ_FL_FS_WIDTH_D	3
> +#define RVFDQ_LS_FS_WIDTH_Q	4
> +#define RVFDQ_OPCODE_FL		0x07
> +#define RVFDQ_OPCODE_FS		0x27


> +/* parts of opcode for RVV */
> +#define RVV_OPCODE_VECTOR	0x57
> +#define RVV_VL_VS_WIDTH_8	0
> +#define RVV_VL_VS_WIDTH_16	5
> +#define RVV_VL_VS_WIDTH_32	6
> +#define RVV_VL_VS_WIDTH_64	7
> +#define RVV_OPCODE_VL		RVFDQ_OPCODE_FL
> +#define RVV_OPCODE_VS		RVFDQ_OPCODE_FS

Same issue for those (FL_FS + VL_VS), but those even don't declare
being part of any *-type scheme in the spec.

So all of them mix content-definitions (RV*_OPCODE_*) with structure-
definitions and right now I don't know how to feel about that ;-) .

On the one hand I like the original separation, but on the other hand it
doesn't feel useful to put these single-use definitions somewhere above.


>  /* parts of opcode for RVC*/
>  #define RVC_OPCODE_C0		0x0
> @@ -304,6 +324,15 @@ static __always_inline bool riscv_insn_is_branch(u32 code)
>  	(RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \
>  	(RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); })
>  
> +#define RVG_EXTRACT_SYSTEM_CSR(x) \
> +	({typeof(x) x_ = (x); RV_X(x_, RVG_SYSTEM_CSR_OFF, RVG_SYSTEM_CSR_MASK); })
> +
> +#define RVFDQ_EXTRACT_FL_FS_WIDTH(x) \
> +	({typeof(x) x_ = (x); RV_X(x_, RVFDQ_FL_FS_WIDTH_OFF, \
> +				   RVFDQ_FL_FS_WIDTH_MASK); })
> +
> +#define RVV_EXRACT_VL_VS_WIDTH(x) RVFDQ_EXTRACT_FL_FS_WIDTH(x)
> +
>  /*
>   * Get the immediate from a J-type instruction.
>   *


> diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
> index 03582e2ade83..ea59f32adf46 100644
> --- a/arch/riscv/kernel/vector.c
> +++ b/arch/riscv/kernel/vector.c
> @@ -4,9 +4,19 @@
>   * Author: Andy Chiu <[e-mail]>
>   */
>  #include <linux/export.h>
> +#include <linux/sched/signal.h>
> +#include <linux/types.h>
> +#include <linux/slab.h>
> +#include <linux/sched.h>
> +#include <linux/uaccess.h>
>  
> +#include <asm/thread_info.h>
> +#include <asm/processor.h>
> +#include <asm/insn.h>
>  #include <asm/vector.h>
>  #include <asm/csr.h>
> +#include <asm/ptrace.h>
> +#include <asm/bug.h>
>  
>  unsigned long riscv_v_vsize __read_mostly;
>  EXPORT_SYMBOL_GPL(riscv_v_vsize);
> @@ -18,3 +28,83 @@ void riscv_v_setup_vsize(void)
>  	riscv_v_vsize = csr_read(CSR_VLENB) * 32;
>  	riscv_v_disable();
>  }
> +
> +static bool insn_is_vector(u32 insn_buf)
> +{
> +	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
> +	bool is_vector = false;
> +	u32 width, csr;
> +
> +	/*
> +	 * All V-related instructions, including CSR operations are 4-Byte. So,
> +	 * do not handle if the instruction length is not 4-Byte.
> +	 */
> +	if (unlikely(GET_INSN_LENGTH(insn_buf) != 4))
> +		return false;
> +
> +	switch (opcode) {
> +	case RVV_OPCODE_VECTOR:
> +		is_vector = true;
> +		break;
> +	case RVV_OPCODE_VL:
> +	case RVV_OPCODE_VS:
> +		width = RVV_EXRACT_VL_VS_WIDTH(insn_buf);
> +		if (width == RVV_VL_VS_WIDTH_8 || width == RVV_VL_VS_WIDTH_16 ||
> +		    width == RVV_VL_VS_WIDTH_32 || width == RVV_VL_VS_WIDTH_64)
> +			is_vector = true;
> +		break;
> +	case RVG_OPCODE_SYSTEM:
> +		csr = RVG_EXTRACT_SYSTEM_CSR(insn_buf);
> +		if ((csr >= CSR_VSTART && csr <= CSR_VCSR) ||
> +		    (csr >= CSR_VL && csr <= CSR_VLENB))
> +			is_vector = true;
> +		break;
> +	}

blank line?

> +	return is_vector;

I guess a matter of style-preference, but the other option would be to
just return true from inside the case elements, and simply false here.


> +}
> +
> +static int riscv_v_thread_zalloc(void)
> +{
> +	void *datap;
> +
> +	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
> +	if (!datap)
> +		return -ENOMEM;

blank line?

> +	current->thread.vstate.datap = datap;
> +	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
> +						    datap));
> +	return 0;
> +}
> +
> +bool riscv_v_first_use_handler(struct pt_regs *regs)
> +{
> +	u32 __user *epc = (u32 __user *)regs->epc;
> +	u32 insn = (u32)regs->badaddr;
> +
> +	/* If V has been enabled then it is not the first-use trap */
> +	if (riscv_v_vstate_query(regs))
> +		return false;
> +
> +	/* Get the instruction */
> +	if (!insn) {
> +		if (__get_user(insn, epc))
> +			return false;
> +	}

blank?

> +	/* Filter out non-V instructions */
> +	if (!insn_is_vector(insn))
> +		return false;
> +
> +	/* Sanity check. datap should be null by the time of the first-use trap */
> +	WARN_ON(current->thread.vstate.datap);

blank?

> +	/*
> +	 * Now we sure that this is a V instruction. And it executes in the
> +	 * context where VS has been off. So, try to allocate the user's V
> +	 * context and resume execution.
> +	 */
> +	if (riscv_v_thread_zalloc()) {
> +		force_sig(SIGKILL);
> +		return true;
> +	}
> +	riscv_v_vstate_on(regs);
> +	return true;
> +}
> 

in any case,

Acked-by: Heiko Stuebner <[e-mail]>
Tested-by: Heiko Stuebner <[e-mail]>


Heiko

Andy Chiu March 31, 2023, 2:38 p.m. UTC | #3

On Wed, Mar 29, 2023 at 1:22 AM Conor Dooley <[e-mail]> wrote:
>
> On Mon, Mar 27, 2023 at 04:49:30PM +0000, Andy Chiu wrote:
> > Vector unit is disabled by default for all user processes. Thus, a
> > process will take a trap (illegal instruction) into kernel at the first
> > time when it uses Vector. Only after then, the kernel allocates V
> > context and starts take care of the context for that user process.
> >
> > Suggested-by: Richard Henderson <[e-mail]>
> > Link: https://lore.kernel.org/r/[e-mail]
> > Signed-off-by: Andy Chiu <[e-mail]>
>
> I see you dropped two R-b from this patch, what actually changed here?
> It's not immediately obvious to me (sorry!) and the cover doesn't mention
> why they were dropped.

Hi, the reason why I dropped R-b here is that there is a conflict in
trap.c because the API has changed after converting to generic entry.
And that change does not make v16's way work out of the box, so it
(trap.c @ v17) requires some more reviewing I suppose.

Thanks for asking! I should get better at describing these in the cover letter.

Andy

Patch

diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h
index 8d5c84f2d5ef..4e1505cef8aa 100644
--- a/arch/riscv/include/asm/insn.h
+++ b/arch/riscv/include/asm/insn.h
@@ -137,6 +137,26 @@ 
 #define RVG_OPCODE_JALR		0x67
 #define RVG_OPCODE_JAL		0x6f
 #define RVG_OPCODE_SYSTEM	0x73
+#define RVG_SYSTEM_CSR_OFF	20
+#define RVG_SYSTEM_CSR_MASK	GENMASK(12, 0)
+
+/* parts of opcode for RVF, RVD and RVQ */
+#define RVFDQ_FL_FS_WIDTH_OFF	12
+#define RVFDQ_FL_FS_WIDTH_MASK	GENMASK(3, 0)
+#define RVFDQ_FL_FS_WIDTH_W	2
+#define RVFDQ_FL_FS_WIDTH_D	3
+#define RVFDQ_LS_FS_WIDTH_Q	4
+#define RVFDQ_OPCODE_FL		0x07
+#define RVFDQ_OPCODE_FS		0x27
+
+/* parts of opcode for RVV */
+#define RVV_OPCODE_VECTOR	0x57
+#define RVV_VL_VS_WIDTH_8	0
+#define RVV_VL_VS_WIDTH_16	5
+#define RVV_VL_VS_WIDTH_32	6
+#define RVV_VL_VS_WIDTH_64	7
+#define RVV_OPCODE_VL		RVFDQ_OPCODE_FL
+#define RVV_OPCODE_VS		RVFDQ_OPCODE_FS
 
 /* parts of opcode for RVC*/
 #define RVC_OPCODE_C0		0x0
@@ -304,6 +324,15 @@  static __always_inline bool riscv_insn_is_branch(u32 code)
 	(RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \
 	(RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); })
 
+#define RVG_EXTRACT_SYSTEM_CSR(x) \
+	({typeof(x) x_ = (x); RV_X(x_, RVG_SYSTEM_CSR_OFF, RVG_SYSTEM_CSR_MASK); })
+
+#define RVFDQ_EXTRACT_FL_FS_WIDTH(x) \
+	({typeof(x) x_ = (x); RV_X(x_, RVFDQ_FL_FS_WIDTH_OFF, \
+				   RVFDQ_FL_FS_WIDTH_MASK); })
+
+#define RVV_EXRACT_VL_VS_WIDTH(x) RVFDQ_EXTRACT_FL_FS_WIDTH(x)
+
 /*
  * Get the immediate from a J-type instruction.
  *
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 4161352d6ea8..70a5e696c1de 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -20,6 +20,7 @@ 
 
 extern unsigned long riscv_v_vsize;
 void riscv_v_setup_vsize(void);
+bool riscv_v_first_use_handler(struct pt_regs *regs);
 
 static __always_inline bool has_vector(void)
 {
@@ -163,6 +164,7 @@  static inline void __switch_to_vector(struct task_struct *prev,
 struct pt_regs;
 
 static __always_inline bool has_vector(void) { return false; }
+static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 #define riscv_v_vsize (0)
 #define riscv_v_setup_vsize()			do {} while (0)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 1f4e37be7eb3..f543e5ebfd29 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -26,6 +26,7 @@ 
 #include <asm/ptrace.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
+#include <asm/vector.h>
 
 int show_unhandled_signals = 1;
 
@@ -145,8 +146,29 @@  DO_ERROR_INFO(do_trap_insn_misaligned,
 	SIGBUS, BUS_ADRALN, "instruction address misaligned");
 DO_ERROR_INFO(do_trap_insn_fault,
 	SIGSEGV, SEGV_ACCERR, "instruction access fault");
-DO_ERROR_INFO(do_trap_insn_illegal,
-	SIGILL, ILL_ILLOPC, "illegal instruction");
+
+asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		irqentry_enter_from_user_mode(regs);
+
+		local_irq_enable();
+
+		if (!has_vector() || !riscv_v_first_use_handler(regs))
+			do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
+				      "Oops - illegal instruction");
+
+		irqentry_exit_to_user_mode(regs);
+	} else {
+		irqentry_state_t state = irqentry_nmi_enter(regs);
+
+		do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
+			      "Oops - illegal instruction");
+
+		irqentry_nmi_exit(regs, state);
+	}
+}
+
 DO_ERROR_INFO(do_trap_load_fault,
 	SIGSEGV, SEGV_ACCERR, "load access fault");
 #ifndef CONFIG_RISCV_M_MODE
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 03582e2ade83..ea59f32adf46 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -4,9 +4,19 @@ 
  * Author: Andy Chiu <[e-mail]>
  */
 #include <linux/export.h>
+#include <linux/sched/signal.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
 
+#include <asm/thread_info.h>
+#include <asm/processor.h>
+#include <asm/insn.h>
 #include <asm/vector.h>
 #include <asm/csr.h>
+#include <asm/ptrace.h>
+#include <asm/bug.h>
 
 unsigned long riscv_v_vsize __read_mostly;
 EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -18,3 +28,83 @@  void riscv_v_setup_vsize(void)
 	riscv_v_vsize = csr_read(CSR_VLENB) * 32;
 	riscv_v_disable();
 }
+
+static bool insn_is_vector(u32 insn_buf)
+{
+	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
+	bool is_vector = false;
+	u32 width, csr;
+
+	/*
+	 * All V-related instructions, including CSR operations are 4-Byte. So,
+	 * do not handle if the instruction length is not 4-Byte.
+	 */
+	if (unlikely(GET_INSN_LENGTH(insn_buf) != 4))
+		return false;
+
+	switch (opcode) {
+	case RVV_OPCODE_VECTOR:
+		is_vector = true;
+		break;
+	case RVV_OPCODE_VL:
+	case RVV_OPCODE_VS:
+		width = RVV_EXRACT_VL_VS_WIDTH(insn_buf);
+		if (width == RVV_VL_VS_WIDTH_8 || width == RVV_VL_VS_WIDTH_16 ||
+		    width == RVV_VL_VS_WIDTH_32 || width == RVV_VL_VS_WIDTH_64)
+			is_vector = true;
+		break;
+	case RVG_OPCODE_SYSTEM:
+		csr = RVG_EXTRACT_SYSTEM_CSR(insn_buf);
+		if ((csr >= CSR_VSTART && csr <= CSR_VCSR) ||
+		    (csr >= CSR_VL && csr <= CSR_VLENB))
+			is_vector = true;
+		break;
+	}
+	return is_vector;
+}
+
+static int riscv_v_thread_zalloc(void)
+{
+	void *datap;
+
+	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	if (!datap)
+		return -ENOMEM;
+	current->thread.vstate.datap = datap;
+	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
+						    datap));
+	return 0;
+}
+
+bool riscv_v_first_use_handler(struct pt_regs *regs)
+{
+	u32 __user *epc = (u32 __user *)regs->epc;
+	u32 insn = (u32)regs->badaddr;
+
+	/* If V has been enabled then it is not the first-use trap */
+	if (riscv_v_vstate_query(regs))
+		return false;
+
+	/* Get the instruction */
+	if (!insn) {
+		if (__get_user(insn, epc))
+			return false;
+	}
+	/* Filter out non-V instructions */
+	if (!insn_is_vector(insn))
+		return false;
+
+	/* Sanity check. datap should be null by the time of the first-use trap */
+	WARN_ON(current->thread.vstate.datap);
+	/*
+	 * Now we sure that this is a V instruction. And it executes in the
+	 * context where VS has been off. So, try to allocate the user's V
+	 * context and resume execution.
+	 */
+	if (riscv_v_thread_zalloc()) {
+		force_sig(SIGKILL);
+		return true;
+	}
+	riscv_v_vstate_on(regs);
+	return true;
+}