diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index e4631027a62e6094bf469a1edad2a6be5c93509e..ecefaa8962654e1675fc0564aad5b484035dede5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -622,6 +622,28 @@ config RISCV_ISA_ZACAS
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_V_UCOPY_THRESHOLD
+	int "Threshold size for vectorized user copies"
+	depends on RISCV_ISA_V
+	default 768
+	help
+	  Prefer using vectorized copy_to_user()/copy_from_user() when the
+	  workload size exceeds this value.
+
+config RISCV_ISA_V_PREEMPTIVE
+	bool "Run kernel-mode Vector with kernel preemption"
+	depends on PREEMPTION
+	depends on RISCV_ISA_V
+	default y
+	help
+	  Usually, in-kernel SIMD routines are run with preemption disabled.
+	  Functions which envoke long running SIMD thus must yield core's
+	  vector unit to prevent blocking other tasks for too long.
+
+	  This config allows kernel to run SIMD without explicitly disable
+	  preemption. Enabling this config will result in higher memory
+	  consumption due to the allocation of per-task's kernel Vector context.
+
 config TOOLCHAIN_HAS_ZBB
 	bool
 	default y
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 36b955c762ba08e92ca0441ee8fbae9219c1f2fa..cd627ec289f163a630b73dd03dd52a6b28692997 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -9,6 +9,33 @@ long long __lshrti3(long long a, int b);
 long long __ashrti3(long long a, int b);
 long long __ashlti3(long long a, int b);
 
+#ifdef CONFIG_RISCV_ISA_V
+
+#ifdef CONFIG_MMU
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n);
+#endif /* CONFIG_MMU  */
+
+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);
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs);
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs);
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+#endif /* CONFIG_RISCV_ISA_V */
 
 #define DECLARE_DO_ERROR_INFO(name)	asmlinkage void name(struct pt_regs *regs)
 
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 6e4dee49d84b985a5ab1bb59b35ecc39a94ed0de..b75b39a4fc100764f0ef1f940872f75dd8bcaa28 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -4,6 +4,23 @@
 #define _ASM_RISCV_ENTRY_COMMON_H
 
 #include <asm/stacktrace.h>
+#include <asm/thread_info.h>
+#include <asm/vector.h>
+
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+	if (ti_work & _TIF_RISCV_V_DEFER_RESTORE) {
+		clear_thread_flag(TIF_RISCV_V_DEFER_RESTORE);
+		/*
+		 * We are already called with irq disabled, so go without
+		 * keeping track of riscv_v_flags.
+		 */
+		riscv_v_vstate_restore(&current->thread.vstate, regs);
+	}
+}
+
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
 
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index bbd4429d9aae0f1eba0f148e9caf3f0459f588a1..0d6b3df48fcc2bf0161850d6f31be72f62ec6a22 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -73,6 +73,43 @@
 struct task_struct;
 struct pt_regs;
 
+/*
+ * We use a flag to track in-kernel Vector context. Currently the flag has the
+ * following meaning:
+ *
+ *  - bit 0: indicates whether the in-kernel Vector context is active. The
+ *    activation of this state disables the preemption. On a non-RT kernel, it
+ *    also disable bh.
+ *  - bits 8: is used for tracking preemptible kernel-mode Vector, when
+ *    RISCV_ISA_V_PREEMPTIVE is enabled. Calling kernel_vector_begin() does not
+ *    disable the preemption if the thread's kernel_vstate.datap is allocated.
+ *    Instead, the kernel set this bit field. Then the trap entry/exit code
+ *    knows if we are entering/exiting the context that owns preempt_v.
+ *     - 0: the task is not using preempt_v
+ *     - 1: the task is actively using preempt_v. But whether does the task own
+ *          the preempt_v context is decided by bits in RISCV_V_CTX_DEPTH_MASK.
+ *  - bit 16-23 are RISCV_V_CTX_DEPTH_MASK, used by context tracking routine
+ *     when preempt_v starts:
+ *     - 0: the task is actively using, and own preempt_v context.
+ *     - non-zero: the task was using preempt_v, but then took a trap within.
+ *       Thus, the task does not own preempt_v. Any use of Vector will have to
+ *       save preempt_v, if dirty, and fallback to non-preemptible kernel-mode
+ *       Vector.
+ *  - bit 30: The in-kernel preempt_v context is saved, and requries to be
+ *    restored when returning to the context that owns the preempt_v.
+ *  - bit 31: The in-kernel preempt_v context is dirty, as signaled by the
+ *    trap entry code. Any context switches out-of current task need to save
+ *    it to the task's in-kernel V context. Also, any traps nesting on-top-of
+ *    preempt_v requesting to use V needs a save.
+ */
+#define RISCV_V_CTX_DEPTH_MASK		0x00ff0000
+
+#define RISCV_V_CTX_UNIT_DEPTH		0x00010000
+#define RISCV_KERNEL_MODE_V		0x00000001
+#define RISCV_PREEMPT_V			0x00000100
+#define RISCV_PREEMPT_V_DIRTY		0x80000000
+#define RISCV_PREEMPT_V_NEED_RESTORE	0x40000000
+
 /* CPU-specific state of a task */
 struct thread_struct {
 	/* Callee-saved registers */
@@ -82,8 +119,10 @@ struct thread_struct {
 	struct __riscv_d_ext_state fstate;
 	unsigned long bad_cause;
 	unsigned long envcfg;
-	unsigned long vstate_ctrl;
+	u32 riscv_v_flags;
+	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
+	struct __riscv_v_ext_state kernel_vstate;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
new file mode 100644
index 0000000000000000000000000000000000000000..54efbf523d49c67d75921c7f8454efc87ad0f257
--- /dev/null
+++ b/arch/riscv/include/asm/simd.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+#include <linux/thread_info.h>
+
+#include <asm/vector.h>
+
+#ifdef CONFIG_RISCV_ISA_V
+/*
+ * may_use_simd - 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_simd(void)
+{
+	/*
+	 * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled.
+	 */
+	if (in_hardirq() || in_nmi())
+		return false;
+
+	/*
+	 * Nesting is acheived in preempt_v by spreading the control for
+	 * preemptible and non-preemptible kernel-mode Vector into two fields.
+	 * Always try to match with prempt_v if kernel V-context exists. Then,
+	 * fallback to check non preempt_v if nesting happens, or if the config
+	 * is not set.
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_V_PREEMPTIVE) && current->thread.kernel_vstate.datap) {
+		if (!riscv_preempt_v_started(current))
+			return true;
+	}
+	/*
+	 * Non-preemptible kernel-mode Vector temporarily disables bh. So we
+	 * must not return true on irq_disabled(). Otherwise we would fail the
+	 * lockdep check calling local_bh_enable()
+	 */
+	return !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+}
+
+#else /* ! CONFIG_RISCV_ISA_V */
+
+static __must_check inline bool may_use_simd(void)
+{
+	return false;
+}
+
+#endif /* ! CONFIG_RISCV_ISA_V */
+
+#endif
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 8d19adc74938621b67e463f67e5278c50c7e34e9..4bec66f30f273786a4b670cd266e466381f08306 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -53,8 +53,7 @@ static inline void __switch_to_fpu(struct task_struct *prev,
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(prev);
-	if (unlikely(regs->status & SR_SD))
-		fstate_save(prev, regs);
+	fstate_save(prev, regs);
 	fstate_restore(next, task_pt_regs(next));
 }
 
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index ecb06186f90619b4551742561853f2c50eb94fb1..a9d93a4ee09b5db169050aa68f06573d95ad33a8 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -101,12 +101,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define TIF_NOTIFY_SIGNAL	9	/* signal notifications exist */
 #define TIF_UPROBE		10	/* uprobe breakpoint or singlestep */
 #define TIF_32BIT		11	/* compat-mode 32bit process */
+#define TIF_RISCV_V_DEFER_RESTORE	12 /* restore Vector before returing to user */
 
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_RISCV_V_DEFER_RESTORE	(1 << TIF_RISCV_V_DEFER_RESTORE)
 
 #define _TIF_WORK_MASK \
 	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index be77ae870829e964960ffe98d514995716f454ee..f371376f411cd703c71a997057b1d46c50afa664 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -22,6 +22,18 @@
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
 bool riscv_v_first_use_handler(struct pt_regs *regs);
+void kernel_vector_begin(void);
+void kernel_vector_end(void);
+void get_cpu_vector_context(void);
+void put_cpu_vector_context(void);
+void riscv_v_thread_free(struct task_struct *tsk);
+void __init riscv_v_setup_ctx_cache(void);
+void riscv_v_thread_alloc(struct task_struct *tsk);
+
+static inline u32 riscv_v_flags(void)
+{
+	return READ_ONCE(current->thread.riscv_v_flags);
+}
 
 static __always_inline bool has_vector(void)
 {
@@ -162,36 +174,89 @@ static inline void riscv_v_vstate_discard(struct pt_regs *regs)
 	__riscv_v_vstate_dirty(regs);
 }
 
-static inline void riscv_v_vstate_save(struct task_struct *task,
+static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
 				       struct pt_regs *regs)
 {
 	if ((regs->status & SR_VS) == SR_VS_DIRTY) {
-		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
 		__riscv_v_vstate_save(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
 }
 
-static inline void riscv_v_vstate_restore(struct task_struct *task,
+static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
 					  struct pt_regs *regs)
 {
 	if ((regs->status & SR_VS) != SR_VS_OFF) {
-		struct __riscv_v_ext_state *vstate = &task->thread.vstate;
-
 		__riscv_v_vstate_restore(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
 }
 
+static inline void riscv_v_vstate_set_restore(struct task_struct *task,
+					      struct pt_regs *regs)
+{
+	if ((regs->status & SR_VS) != SR_VS_OFF) {
+		set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
+		riscv_v_vstate_on(regs);
+	}
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static inline bool riscv_preempt_v_dirty(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_DIRTY);
+}
+
+static inline bool riscv_preempt_v_restore(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_preempt_v_clear_dirty(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_set_restore(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags |= RISCV_PREEMPT_V_NEED_RESTORE;
+}
+
+static inline bool riscv_preempt_v_started(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V);
+}
+
+#else /* !CONFIG_RISCV_ISA_V_PREEMPTIVE */
+static inline bool riscv_preempt_v_dirty(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_restore(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_started(struct task_struct *task) { return false; }
+#define riscv_preempt_v_clear_dirty(tsk)	do {} while (0)
+#define riscv_preempt_v_set_restore(tsk)	do {} while (0)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
 static inline void __switch_to_vector(struct task_struct *prev,
 				      struct task_struct *next)
 {
 	struct pt_regs *regs;
 
-	regs = task_pt_regs(prev);
-	riscv_v_vstate_save(prev, regs);
-	riscv_v_vstate_restore(next, task_pt_regs(next));
+	if (riscv_preempt_v_started(prev)) {
+		if (riscv_preempt_v_dirty(prev)) {
+			__riscv_v_vstate_save(&prev->thread.kernel_vstate,
+					      prev->thread.kernel_vstate.datap);
+			riscv_preempt_v_clear_dirty(prev);
+		}
+	} else {
+		regs = task_pt_regs(prev);
+		riscv_v_vstate_save(&prev->thread.vstate, regs);
+	}
+
+	if (riscv_preempt_v_started(next))
+		riscv_preempt_v_set_restore(next);
+	else
+		riscv_v_vstate_set_restore(next, task_pt_regs(next));
 }
 
 void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
@@ -208,11 +273,14 @@ static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
 #define riscv_v_vsize (0)
 #define riscv_v_vstate_discard(regs)		do {} while (0)
-#define riscv_v_vstate_save(task, regs)		do {} while (0)
-#define riscv_v_vstate_restore(task, regs)	do {} while (0)
+#define riscv_v_vstate_save(vstate, regs)	do {} while (0)
+#define riscv_v_vstate_restore(vstate, regs)	do {} while (0)
 #define __switch_to_vector(__prev, __next)	do {} while (0)
 #define riscv_v_vstate_off(regs)		do {} while (0)
 #define riscv_v_vstate_on(regs)			do {} while (0)
+#define riscv_v_thread_free(tsk)		do {} while (0)
+#define  riscv_v_setup_ctx_cache()		do {} while (0)
+#define riscv_v_thread_alloc(tsk)		do {} while (0)
 
 #endif /* CONFIG_RISCV_ISA_V */
 
diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 0000000000000000000000000000000000000000..96011861e46b4df24cb973a9066324283ad17b60
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#ifdef CONFIG_RISCV_ISA_V
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
+
+static void xor_vector_2(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2)
+{
+	kernel_vector_begin();
+	xor_regs_2_(bytes, p1, p2);
+	kernel_vector_end();
+}
+
+static void xor_vector_3(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3)
+{
+	kernel_vector_begin();
+	xor_regs_3_(bytes, p1, p2, p3);
+	kernel_vector_end();
+}
+
+static void xor_vector_4(unsigned long bytes, unsigned long *__restrict p1,
+			 const unsigned long *__restrict p2,
+			 const unsigned long *__restrict p3,
+			 const unsigned long *__restrict p4)
+{
+	kernel_vector_begin();
+	xor_regs_4_(bytes, p1, p2, p3, p4);
+	kernel_vector_end();
+}
+
+static void xor_vector_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_vector_begin();
+	xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+	kernel_vector_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+	.name = "rvv",
+	.do_2 = xor_vector_2,
+	.do_3 = xor_vector_3,
+	.do_4 = xor_vector_4,
+	.do_5 = xor_vector_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/kernel/Makefile b/arch/riscv/kernel/Makefile
index f18f9e4d1ef121484d431e99e61c515274bd2a50..2ffd9bf4d9115befe6e9fff495670008dcec160f 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
+obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S
index cfdecfbaad627153ead8cde6fe9ca7a298c1aa40..2b3d9398c113fbaea3f775b1439058e5a5178c7d 100644
--- a/arch/riscv/kernel/copy-unaligned.S
+++ b/arch/riscv/kernel/copy-unaligned.S
@@ -9,7 +9,7 @@
 /* void __riscv_copy_words_unaligned(void *, const void *, size_t) */
 /* Performs a memcpy without aligning buffers, using word loads and stores. */
 /* Note: The size is truncated to a multiple of 8 * SZREG */
-ENTRY(__riscv_copy_words_unaligned)
+SYM_FUNC_START(__riscv_copy_words_unaligned)
 	andi  a4, a2, ~((8*SZREG)-1)
 	beqz  a4, 2f
 	add   a3, a1, a4
@@ -36,12 +36,12 @@ ENTRY(__riscv_copy_words_unaligned)
 
 2:
 	ret
-END(__riscv_copy_words_unaligned)
+SYM_FUNC_END(__riscv_copy_words_unaligned)
 
 /* void __riscv_copy_bytes_unaligned(void *, const void *, size_t) */
 /* Performs a memcpy without aligning buffers, using only byte accesses. */
 /* Note: The size is truncated to a multiple of 8 */
-ENTRY(__riscv_copy_bytes_unaligned)
+SYM_FUNC_START(__riscv_copy_bytes_unaligned)
 	andi a4, a2, ~(8-1)
 	beqz a4, 2f
 	add  a3, a1, a4
@@ -68,4 +68,4 @@ ENTRY(__riscv_copy_bytes_unaligned)
 
 2:
 	ret
-END(__riscv_copy_bytes_unaligned)
+SYM_FUNC_END(__riscv_copy_bytes_unaligned)
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 1372b67dbd2828c029e6056c8f944a4d6c6fc2a6..7167ee40af4cc2a6f7ac9254482b9f4bff4b46b8 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -98,9 +98,9 @@ SYM_CODE_START(handle_exception)
 	 * register will contain 0, and we should continue on the current TP.
 	 */
 	csrrw tp, CSR_SCRATCH, tp
-	bnez tp, _save_context
+	bnez tp, .Lsave_context
 
-_restore_kernel_tpsp:
+.Lrestore_kernel_tpsp:
 	csrr tp, CSR_SCRATCH
 
 #ifdef CONFIG_64BIT
@@ -126,7 +126,7 @@ _restore_kernel_tpsp:
 	REG_L sp, TASK_TI_KERNEL_SP(tp)
 #endif
 
-_save_context:
+.Lsave_context:
 	REG_S sp, TASK_TI_USER_SP(tp)
 	REG_L sp, TASK_TI_KERNEL_SP(tp)
 	addi sp, sp, -(PT_SIZE_ON_STACK)
@@ -168,6 +168,10 @@ _save_context:
 .option norelax
 	la gp, __global_pointer$
 .option pop
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_start
+#endif
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 
@@ -221,6 +225,10 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	 */
 	csrw CSR_SCRATCH, tp
 1:
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_end
+#endif
 	REG_L a0, PT_STATUS(sp)
 	/*
 	 * The current load reservation is effectively part of the processor's
@@ -366,7 +374,7 @@ SYM_FUNC_END(__switch_to)
 	.section ".rodata"
 	.align LGREG
 	/* Exception vector table */
-SYM_CODE_START(excp_vect_table)
+SYM_DATA_START_LOCAL(excp_vect_table)
 	RISCV_PTR do_trap_insn_misaligned
 	ALT_INSN_FAULT(RISCV_PTR do_trap_insn_fault)
 	RISCV_PTR do_trap_insn_illegal
@@ -384,12 +392,11 @@ SYM_CODE_START(excp_vect_table)
 	RISCV_PTR do_page_fault   /* load page fault */
 	RISCV_PTR do_trap_unknown
 	RISCV_PTR do_page_fault   /* store page fault */
-excp_vect_table_end:
-SYM_CODE_END(excp_vect_table)
+SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end)
 
 #ifndef CONFIG_MMU
-SYM_CODE_START(__user_rt_sigreturn)
+SYM_DATA_START(__user_rt_sigreturn)
 	li a7, __NR_rt_sigreturn
 	ecall
-SYM_CODE_END(__user_rt_sigreturn)
+SYM_DATA_END(__user_rt_sigreturn)
 #endif
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
index dd2205473de78571a5a4a4b68bd4b33302a77b31..6201afcd6b45fc91de2a8bdf6db1df25423180ca 100644
--- a/arch/riscv/kernel/fpu.S
+++ b/arch/riscv/kernel/fpu.S
@@ -19,7 +19,7 @@
 #include <asm/csr.h>
 #include <asm/asm-offsets.h>
 
-ENTRY(__fstate_save)
+SYM_FUNC_START(__fstate_save)
 	li  a2,  TASK_THREAD_F0
 	add a0, a0, a2
 	li t1, SR_FS
@@ -60,9 +60,9 @@ ENTRY(__fstate_save)
 	sw t0, TASK_THREAD_FCSR_F0(a0)
 	csrc CSR_STATUS, t1
 	ret
-ENDPROC(__fstate_save)
+SYM_FUNC_END(__fstate_save)
 
-ENTRY(__fstate_restore)
+SYM_FUNC_START(__fstate_restore)
 	li  a2,  TASK_THREAD_F0
 	add a0, a0, a2
 	li t1, SR_FS
@@ -103,4 +103,4 @@ ENTRY(__fstate_restore)
 	fscsr t0
 	csrc CSR_STATUS, t1
 	ret
-ENDPROC(__fstate_restore)
+SYM_FUNC_END(__fstate_restore)
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 600a98f12ad91dd2003f111314cdabd0138c8c6b..ecf008b5b2a1514100a5ebcb3d24a0aecc40d6a0 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -18,7 +18,7 @@
 #include "efi-header.S"
 
 __HEAD
-ENTRY(_start)
+SYM_CODE_START(_start)
 	/*
 	 * Image header expected by Linux boot-loaders. The image header data
 	 * structure is described in asm/image.h.
@@ -169,7 +169,7 @@ secondary_start_sbi:
 	XIP_FIXUP_OFFSET a0
 	call relocate_enable_mmu
 #endif
-	call setup_trap_vector
+	call .Lsetup_trap_vector
 	call smp_callin
 #endif /* CONFIG_SMP */
 
@@ -185,7 +185,7 @@ secondary_start_sbi:
 	j .Lsecondary_park
 
 .align 2
-setup_trap_vector:
+.Lsetup_trap_vector:
 	/* Set trap vector to exception handler */
 	la a0, handle_exception
 	csrw CSR_TVEC, a0
@@ -197,9 +197,9 @@ setup_trap_vector:
 	csrw CSR_SCRATCH, zero
 	ret
 
-END(_start)
+SYM_CODE_END(_start)
 
-ENTRY(_start_kernel)
+SYM_CODE_START(_start_kernel)
 	/* Mask all interrupts */
 	csrw CSR_IE, zero
 	csrw CSR_IP, zero
@@ -216,7 +216,7 @@ ENTRY(_start_kernel)
 	 * not implement PMPs, so we set up a quick trap handler to just skip
 	 * touching the PMPs on any trap.
 	 */
-	la a0, pmp_done
+	la a0, .Lpmp_done
 	csrw CSR_TVEC, a0
 
 	li a0, -1
@@ -224,7 +224,7 @@ ENTRY(_start_kernel)
 	li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X)
 	csrw CSR_PMPCFG0, a0
 .align 2
-pmp_done:
+.Lpmp_done:
 
 	/*
 	 * The hartid in a0 is expected later on, and we have no firmware
@@ -288,12 +288,12 @@ pmp_done:
 	/* Clear BSS for flat non-ELF images */
 	la a3, __bss_start
 	la a4, __bss_stop
-	ble a4, a3, clear_bss_done
-clear_bss:
+	ble a4, a3, .Lclear_bss_done
+.Lclear_bss:
 	REG_S zero, (a3)
 	add a3, a3, RISCV_SZPTR
-	blt a3, a4, clear_bss
-clear_bss_done:
+	blt a3, a4, .Lclear_bss
+.Lclear_bss_done:
 #endif
 	la a2, boot_cpu_hartid
 	XIP_FIXUP_OFFSET a2
@@ -320,7 +320,7 @@ clear_bss_done:
 	call relocate_enable_mmu
 #endif /* CONFIG_MMU */
 
-	call setup_trap_vector
+	call .Lsetup_trap_vector
 	/* Restore C environment */
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
@@ -362,10 +362,10 @@ clear_bss_done:
 	tail .Lsecondary_start_common
 #endif /* CONFIG_RISCV_BOOT_SPINWAIT */
 
-END(_start_kernel)
+SYM_CODE_END(_start_kernel)
 
 #ifdef CONFIG_RISCV_M_MODE
-ENTRY(reset_regs)
+SYM_CODE_START_LOCAL(reset_regs)
 	li	sp, 0
 	li	gp, 0
 	li	tp, 0
@@ -463,5 +463,5 @@ ENTRY(reset_regs)
 .Lreset_regs_done_vector:
 #endif /* CONFIG_RISCV_ISA_V */
 	ret
-END(reset_regs)
+SYM_CODE_END(reset_regs)
 #endif /* CONFIG_RISCV_M_MODE */
diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S
index d698dd7df637ba8ad9263e2312f896c268a58b2d..d040dcf4add453dadaa328b85cd462ae43d6d31a 100644
--- a/arch/riscv/kernel/hibernate-asm.S
+++ b/arch/riscv/kernel/hibernate-asm.S
@@ -21,7 +21,7 @@
  *
  * Always returns 0
  */
-ENTRY(__hibernate_cpu_resume)
+SYM_FUNC_START(__hibernate_cpu_resume)
 	/* switch to hibernated image's page table. */
 	csrw CSR_SATP, s0
 	sfence.vma
@@ -34,7 +34,7 @@ ENTRY(__hibernate_cpu_resume)
 	mv	a0, zero
 
 	ret
-END(__hibernate_cpu_resume)
+SYM_FUNC_END(__hibernate_cpu_resume)
 
 /*
  * Prepare to restore the image.
@@ -42,7 +42,7 @@ END(__hibernate_cpu_resume)
  * a1: satp of temporary page tables.
  * a2: cpu_resume.
  */
-ENTRY(hibernate_restore_image)
+SYM_FUNC_START(hibernate_restore_image)
 	mv	s0, a0
 	mv	s1, a1
 	mv	s2, a2
@@ -50,7 +50,7 @@ ENTRY(hibernate_restore_image)
 	REG_L	a1, relocated_restore_code
 
 	jr	a1
-END(hibernate_restore_image)
+SYM_FUNC_END(hibernate_restore_image)
 
 /*
  * The below code will be executed from a 'safe' page.
@@ -58,7 +58,7 @@ END(hibernate_restore_image)
  * back to the original memory location. Finally, it jumps to __hibernate_cpu_resume()
  * to restore the CPU context.
  */
-ENTRY(hibernate_core_restore_code)
+SYM_FUNC_START(hibernate_core_restore_code)
 	/* switch to temp page table. */
 	csrw satp, s1
 	sfence.vma
@@ -73,4 +73,4 @@ ENTRY(hibernate_core_restore_code)
 	bnez	s4, .Lcopy
 
 	jr	s2
-END(hibernate_core_restore_code)
+SYM_FUNC_END(hibernate_core_restore_code)
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 0000000000000000000000000000000000000000..6afe80c7f03ab0c195ee43725d6dfd041dc0464b
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,247 @@
+// 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>
+#include <asm/simd.h>
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+#include <asm/asm-prototypes.h>
+#endif
+
+static inline void riscv_v_flags_set(u32 flags)
+{
+	WRITE_ONCE(current->thread.riscv_v_flags, flags);
+}
+
+static inline void riscv_v_start(u32 flags)
+{
+	int orig;
+
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) != 0);
+	riscv_v_flags_set(orig | flags);
+	barrier();
+}
+
+static inline void riscv_v_stop(u32 flags)
+{
+	int orig;
+
+	barrier();
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) == 0);
+	riscv_v_flags_set(orig & ~flags);
+}
+
+/*
+ * 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.
+ */
+void get_cpu_vector_context(void)
+{
+	/*
+	 * disable softirqs so it is impossible for softirqs to nest
+	 * get_cpu_vector_context() when kernel is actively using Vector.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
+
+	riscv_v_start(RISCV_KERNEL_MODE_V);
+}
+
+/*
+ * 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.
+ */
+void put_cpu_vector_context(void)
+{
+	riscv_v_stop(RISCV_KERNEL_MODE_V);
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static __always_inline u32 *riscv_v_flags_ptr(void)
+{
+	return &current->thread.riscv_v_flags;
+}
+
+static inline void riscv_preempt_v_set_dirty(void)
+{
+	*riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_reset_flags(void)
+{
+	*riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_v_ctx_depth_inc(void)
+{
+	*riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline void riscv_v_ctx_depth_dec(void)
+{
+	*riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline u32 riscv_v_ctx_get_depth(void)
+{
+	return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK;
+}
+
+static int riscv_v_stop_kernel_context(void)
+{
+	if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current))
+		return 1;
+
+	riscv_preempt_v_clear_dirty(current);
+	riscv_v_stop(RISCV_PREEMPT_V);
+	return 0;
+}
+
+static int riscv_v_start_kernel_context(bool *is_nested)
+{
+	struct __riscv_v_ext_state *kvstate, *uvstate;
+
+	kvstate = &current->thread.kernel_vstate;
+	if (!kvstate->datap)
+		return -ENOENT;
+
+	if (riscv_preempt_v_started(current)) {
+		WARN_ON(riscv_v_ctx_get_depth() == 0);
+		*is_nested = true;
+		get_cpu_vector_context();
+		if (riscv_preempt_v_dirty(current)) {
+			__riscv_v_vstate_save(kvstate, kvstate->datap);
+			riscv_preempt_v_clear_dirty(current);
+		}
+		riscv_preempt_v_set_restore(current);
+		return 0;
+	}
+
+	/* Transfer the ownership of V from user to kernel, then save */
+	riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
+	if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+		uvstate = &current->thread.vstate;
+		__riscv_v_vstate_save(uvstate, uvstate->datap);
+	}
+	riscv_preempt_v_clear_dirty(current);
+	return 0;
+}
+
+/* low-level V context handling code, called with irq disabled */
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
+{
+	int depth;
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+		riscv_preempt_v_set_dirty();
+
+	riscv_v_ctx_depth_inc();
+}
+
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs)
+{
+	struct __riscv_v_ext_state *vstate = &current->thread.kernel_vstate;
+	u32 depth;
+
+	WARN_ON(!irqs_disabled());
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	riscv_v_ctx_depth_dec();
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0) {
+		if (riscv_preempt_v_restore(current)) {
+			__riscv_v_vstate_restore(vstate, vstate->datap);
+			__riscv_v_vstate_clean(regs);
+			riscv_preempt_v_reset_flags();
+		}
+	}
+}
+#else
+#define riscv_v_start_kernel_context(nested)	(-ENOENT)
+#define riscv_v_stop_kernel_context()		(-ENOENT)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+/*
+ * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_vector_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_vector_end() is
+ * called.
+ */
+void kernel_vector_begin(void)
+{
+	bool nested = false;
+
+	if (WARN_ON(!has_vector()))
+		return;
+
+	BUG_ON(!may_use_simd());
+
+	if (riscv_v_start_kernel_context(&nested)) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+	}
+
+	if (!nested)
+		riscv_v_vstate_set_restore(current, task_pt_regs(current));
+
+	riscv_v_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_begin);
+
+/*
+ * kernel_vector_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_vector_begin() was previously
+ * called, with no call to kernel_vector_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_vector_begin() is called again in the meantime.
+ */
+void kernel_vector_end(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	riscv_v_disable();
+
+	if (riscv_v_stop_kernel_context())
+		put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 669b8697aa38a5ed792ead53d73ce3057c62ab51..58dd96a2a15340ee83c473436a1b2cf25d407c1f 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -82,7 +82,7 @@
 	.endm
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
-ENTRY(ftrace_caller)
+SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
 	addi	a0, t0, -FENTRY_RA_OFFSET
@@ -91,8 +91,7 @@ ENTRY(ftrace_caller)
 	mv	a1, ra
 	mv	a3, sp
 
-ftrace_call:
-	.global ftrace_call
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -102,16 +101,15 @@ ftrace_call:
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	mv	a2, s0
 #endif
-ftrace_graph_call:
-	.global ftrace_graph_call
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 	RESTORE_ABI
 	jr t0
-ENDPROC(ftrace_caller)
+SYM_FUNC_END(ftrace_caller)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-ENTRY(ftrace_regs_caller)
+SYM_FUNC_START(ftrace_regs_caller)
 	SAVE_ALL
 
 	addi	a0, t0, -FENTRY_RA_OFFSET
@@ -120,8 +118,7 @@ ENTRY(ftrace_regs_caller)
 	mv	a1, ra
 	mv	a3, sp
 
-ftrace_regs_call:
-	.global ftrace_regs_call
+SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -131,12 +128,11 @@ ftrace_regs_call:
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	mv	a2, s0
 #endif
-ftrace_graph_regs_call:
-	.global ftrace_graph_regs_call
+SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 
 	RESTORE_ALL
 	jr t0
-ENDPROC(ftrace_regs_caller)
+SYM_FUNC_END(ftrace_regs_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 8818a8fa9ff3af7b3427e2456f1650c5c6cb7168..b4dd9ed6849e30f13922a5ab4e398f87de984e9b 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -61,7 +61,7 @@ SYM_TYPED_FUNC_START(ftrace_stub_graph)
 	ret
 SYM_FUNC_END(ftrace_stub_graph)
 
-ENTRY(return_to_handler)
+SYM_FUNC_START(return_to_handler)
 /*
  * On implementing the frame point test, the ideal way is to compare the
  * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return.
@@ -76,25 +76,25 @@ ENTRY(return_to_handler)
 	mv	a2, a0
 	RESTORE_RET_ABI_STATE
 	jalr	a2
-ENDPROC(return_to_handler)
+SYM_FUNC_END(return_to_handler)
 #endif
 
 #ifndef CONFIG_DYNAMIC_FTRACE
-ENTRY(MCOUNT_NAME)
+SYM_FUNC_START(MCOUNT_NAME)
 	la	t4, ftrace_stub
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	la	t0, ftrace_graph_return
 	REG_L	t1, 0(t0)
-	bne	t1, t4, do_ftrace_graph_caller
+	bne	t1, t4, .Ldo_ftrace_graph_caller
 
 	la	t3, ftrace_graph_entry
 	REG_L	t2, 0(t3)
 	la	t6, ftrace_graph_entry_stub
-	bne	t2, t6, do_ftrace_graph_caller
+	bne	t2, t6, .Ldo_ftrace_graph_caller
 #endif
 	la	t3, ftrace_trace_function
 	REG_L	t5, 0(t3)
-	bne	t5, t4, do_trace
+	bne	t5, t4, .Ldo_trace
 	ret
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -102,7 +102,7 @@ ENTRY(MCOUNT_NAME)
  * A pseudo representation for the function graph tracer:
  * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller)
  */
-do_ftrace_graph_caller:
+.Ldo_ftrace_graph_caller:
 	addi	a0, s0, -SZREG
 	mv	a1, ra
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
@@ -118,7 +118,7 @@ do_ftrace_graph_caller:
  * A pseudo representation for the function tracer:
  * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller)
  */
-do_trace:
+.Ldo_trace:
 	REG_L	a1, -SZREG(s0)
 	mv	a0, ra
 
@@ -126,6 +126,6 @@ do_trace:
 	jalr	t5
 	RESTORE_ABI_STATE
 	ret
-ENDPROC(MCOUNT_NAME)
+SYM_FUNC_END(MCOUNT_NAME)
 #endif
 EXPORT_SYMBOL(MCOUNT_NAME)
diff --git a/arch/riscv/kernel/probes/rethook_trampoline.S b/arch/riscv/kernel/probes/rethook_trampoline.S
index 21bac92a170a9bd43be973f213cb8be3329175ef..f2cd83d9b0f004e0fe6ae64db9425d343a394bf9 100644
--- a/arch/riscv/kernel/probes/rethook_trampoline.S
+++ b/arch/riscv/kernel/probes/rethook_trampoline.S
@@ -75,7 +75,7 @@
 	REG_L x31, PT_T6(sp)
 	.endm
 
-ENTRY(arch_rethook_trampoline)
+SYM_CODE_START(arch_rethook_trampoline)
 	addi sp, sp, -(PT_SIZE_ON_STACK)
 	save_all_base_regs
 
@@ -90,4 +90,4 @@ ENTRY(arch_rethook_trampoline)
 	addi sp, sp, PT_SIZE_ON_STACK
 
 	ret
-ENDPROC(arch_rethook_trampoline)
+SYM_CODE_END(arch_rethook_trampoline)
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index ec158c7353a5929562be4f3a90507aabf985219e..4b76018b02a285721a4a913f39d0325638aa35ef 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -152,6 +152,7 @@ void flush_thread(void)
 	riscv_v_vstate_off(task_pt_regs(current));
 	kfree(current->thread.vstate.datap);
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
 #ifdef CONFIG_RISCV_ISA_SUPM
 	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
@@ -163,7 +164,7 @@ void arch_release_task_struct(struct task_struct *tsk)
 {
 	/* Free the vector context of datap. */
 	if (has_vector())
-		kfree(tsk->thread.vstate.datap);
+		riscv_v_thread_free(tsk);
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -172,6 +173,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	*dst = *src;
 	/* clear entire V context, including datap for a new task */
 	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
 
 	return 0;
 }
@@ -209,11 +212,19 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.s[0] = 0;
 	}
+	p->thread.riscv_v_flags = 0;
+	if (has_vector())
+		riscv_v_thread_alloc(p);
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }
 
+void __init arch_task_cache_init(void)
+{
+	riscv_v_setup_ctx_cache();
+}
+
 EXPORT_SYMBOL_GPL(__fstate_save);
 EXPORT_SYMBOL_GPL(__fstate_restore);
 
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index a81c944c2e695214c8bae30c2f4cd0f73fa3ab5b..6e3caafef03620225d2fa1b4d85e77507615c7ee 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -102,8 +102,11 @@ static int riscv_vr_get(struct task_struct *target,
 	 * Ensure the vector registers have been saved to the memory before
 	 * copying them to membuf.
 	 */
-	if (target == current)
-		riscv_v_vstate_save(current, task_pt_regs(current));
+	if (target == current) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+		put_cpu_vector_context();
+	}
 
 	ptrace_vstate.vstart = vstate->vstart;
 	ptrace_vstate.vl = vstate->vl;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 048b9b23d7543e65f529566a27c0e5e6cd2b3f56..0e3bdd520617ea52e06a2e9a68e4b24593d83d1b 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -86,7 +86,10 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	/* datap is designed to be 16 byte aligned for better performance */
 	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
 
-	riscv_v_vstate_save(current, regs);
+	get_cpu_vector_context();
+	riscv_v_vstate_save(&current->thread.vstate, regs);
+	put_cpu_vector_context();
+
 	/* Copy everything of vstate but datap. */
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
@@ -116,6 +119,13 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	struct __sc_riscv_v_state __user *state = sc_vec;
 	void __user *datap;
 
+	/*
+	 * Mark the vstate as clean prior performing the actual copy,
+	 * to avoid getting the vstate incorrectly clobbered by the
+	 *  discarded vector state.
+	 */
+	riscv_v_vstate_set_restore(current, regs);
+
 	/* Copy everything of __sc_riscv_v_state except datap. */
 	err = __copy_from_user(&current->thread.vstate, &state->v_state,
 			       offsetof(struct __riscv_v_ext_state, datap));
@@ -130,13 +140,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	 * Copy the whole vector content from user space datap. Use
 	 * copy_from_user to prevent information leak.
 	 */
-	err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
-	if (unlikely(err))
-		return err;
-
-	riscv_v_vstate_restore(current, regs);
-
-	return err;
+	return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
 }
 #else
 #define save_v_state(task, regs) (0)
diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S
index f7960c7c5f9e25081424f3edbe526896c1692303..a59c4c9036963c453f8842937af7c91124cea54e 100644
--- a/arch/riscv/kernel/suspend_entry.S
+++ b/arch/riscv/kernel/suspend_entry.S
@@ -16,7 +16,7 @@
 	.altmacro
 	.option norelax
 
-ENTRY(__cpu_suspend_enter)
+SYM_FUNC_START(__cpu_suspend_enter)
 	/* Save registers (except A0 and T0-T6) */
 	REG_S	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
 	REG_S	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
@@ -57,7 +57,7 @@ ENTRY(__cpu_suspend_enter)
 
 	/* Return to C code */
 	ret
-END(__cpu_suspend_enter)
+SYM_FUNC_END(__cpu_suspend_enter)
 
 SYM_TYPED_FUNC_START(__cpu_resume_enter)
 	/* Load the global pointer */
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
index 82f97d67c23e9bdde94b0d2f655f52d32c8fd6d1..8f884227e8bca7fd3634217e71d4ee4ed122559a 100644
--- a/arch/riscv/kernel/vdso/flush_icache.S
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -8,7 +8,7 @@
 
 	.text
 /* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
-ENTRY(__vdso_flush_icache)
+SYM_FUNC_START(__vdso_flush_icache)
 	.cfi_startproc
 #ifdef CONFIG_SMP
 	li a7, __NR_riscv_flush_icache
@@ -19,4 +19,4 @@ ENTRY(__vdso_flush_icache)
 #endif
 	ret
 	.cfi_endproc
-ENDPROC(__vdso_flush_icache)
+SYM_FUNC_END(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
index bb0c05e2ffbae3d6aa3609fc5b5de84630aaa37d..9c1bd531907f2fefda1d0778191073ca6b70df1a 100644
--- a/arch/riscv/kernel/vdso/getcpu.S
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -8,11 +8,11 @@
 
 	.text
 /* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
-ENTRY(__vdso_getcpu)
+SYM_FUNC_START(__vdso_getcpu)
 	.cfi_startproc
 	/* For now, just do the syscall. */
 	li a7, __NR_getcpu
 	ecall
 	ret
 	.cfi_endproc
-ENDPROC(__vdso_getcpu)
+SYM_FUNC_END(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S
index 10438c7c626acc8034fa22d6765422fbc7b67f0b..3dc022aa8931ad3b3798f4cc492ce795dd7b7bf5 100644
--- a/arch/riscv/kernel/vdso/rt_sigreturn.S
+++ b/arch/riscv/kernel/vdso/rt_sigreturn.S
@@ -7,10 +7,10 @@
 #include <asm/unistd.h>
 
 	.text
-ENTRY(__vdso_rt_sigreturn)
+SYM_FUNC_START(__vdso_rt_sigreturn)
 	.cfi_startproc
 	.cfi_signal_frame
 	li a7, __NR_rt_sigreturn
 	ecall
 	.cfi_endproc
-ENDPROC(__vdso_rt_sigreturn)
+SYM_FUNC_END(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S
index 4e704146c77a092e481b8b532c19b11e3efa82e4..77e57f8305216c466f51979c91899754b4a7b382 100644
--- a/arch/riscv/kernel/vdso/sys_hwprobe.S
+++ b/arch/riscv/kernel/vdso/sys_hwprobe.S
@@ -5,11 +5,11 @@
 #include <asm/unistd.h>
 
 .text
-ENTRY(riscv_hwprobe)
+SYM_FUNC_START(riscv_hwprobe)
 	.cfi_startproc
 	li a7, __NR_riscv_hwprobe
 	ecall
 	ret
 
 	.cfi_endproc
-ENDPROC(riscv_hwprobe)
+SYM_FUNC_END(riscv_hwprobe)
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 21ca4fea681fb7c8a9420ec958677c042fa71fac..82795ab6242b59660afa48a5d4ea036e01fc37d9 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -21,6 +21,10 @@
 #include <asm/bug.h>
 
 static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
+static struct kmem_cache *riscv_v_user_cachep;
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static struct kmem_cache *riscv_v_kernel_cachep;
+#endif
 
 unsigned long riscv_v_vsize __read_mostly;
 EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -47,6 +51,21 @@ int riscv_v_setup_vsize(void)
 	return 0;
 }
 
+void __init riscv_v_setup_ctx_cache(void)
+{
+	if (!has_vector())
+		return;
+
+	riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
+							 riscv_v_vsize, 16, SLAB_PANIC,
+							 0, riscv_v_vsize, NULL);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx",
+						  riscv_v_vsize, 16,
+						  SLAB_PANIC, NULL);
+#endif
+}
+
 static bool insn_is_vector(u32 insn_buf)
 {
 	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
@@ -80,20 +99,37 @@ static bool insn_is_vector(u32 insn_buf)
 	return false;
 }
 
-static int riscv_v_thread_zalloc(void)
+static int riscv_v_thread_zalloc(struct kmem_cache *cache,
+				 struct __riscv_v_ext_state *ctx)
 {
 	void *datap;
 
-	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	datap = kmem_cache_zalloc(cache, GFP_KERNEL);
 	if (!datap)
 		return -ENOMEM;
 
-	current->thread.vstate.datap = datap;
-	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
-						    datap));
+	ctx->datap = datap;
+	memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap));
 	return 0;
 }
 
+void riscv_v_thread_alloc(struct task_struct *tsk)
+{
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
+#endif
+}
+
+void riscv_v_thread_free(struct task_struct *tsk)
+{
+	if (tsk->thread.vstate.datap)
+		kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	if (tsk->thread.kernel_vstate.datap)
+		kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap);
+#endif
+}
+
 #define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
 #define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2)
 #define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK)
@@ -122,7 +158,8 @@ static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt,
 	ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt);
 	if (inherit)
 		ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
-	tsk->thread.vstate_ctrl = ctrl;
+	tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK;
+	tsk->thread.vstate_ctrl |= ctrl;
 }
 
 bool riscv_v_vstate_ctrl_user_allowed(void)
@@ -165,12 +202,12 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 	 * context where VS has been off. So, try to allocate the user's V
 	 * context and resume execution.
 	 */
-	if (riscv_v_thread_zalloc()) {
+	if (riscv_v_thread_zalloc(riscv_v_user_cachep, &current->thread.vstate)) {
 		force_sig(SIGBUS);
 		return true;
 	}
 	riscv_v_vstate_on(regs);
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 	return true;
 }
 
diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
index d74df8eb4d71a56faed0f4a7f4303bef88e6e399..0c26189aa01cf5b0ca5c6ef6ddbaa70153f3132c 100644
--- a/arch/riscv/kvm/vcpu_switch.S
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -15,7 +15,7 @@
 	.altmacro
 	.option norelax
 
-ENTRY(__kvm_riscv_switch_to)
+SYM_FUNC_START(__kvm_riscv_switch_to)
 	/* Save Host GPRs (except A0 and T0-T6) */
 	REG_S	ra, (KVM_ARCH_HOST_RA)(a0)
 	REG_S	sp, (KVM_ARCH_HOST_SP)(a0)
@@ -45,7 +45,7 @@ ENTRY(__kvm_riscv_switch_to)
 	REG_L	t0, (KVM_ARCH_GUEST_SSTATUS)(a0)
 	REG_L	t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
 	REG_L	t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
-	la	t4, __kvm_switch_return
+	la	t4, .Lkvm_switch_return
 	REG_L	t5, (KVM_ARCH_GUEST_SEPC)(a0)
 
 	/* Save Host and Restore Guest SSTATUS */
@@ -113,7 +113,7 @@ ENTRY(__kvm_riscv_switch_to)
 
 	/* Back to Host */
 	.align 2
-__kvm_switch_return:
+.Lkvm_switch_return:
 	/* Swap Guest A0 with SSCRATCH */
 	csrrw	a0, CSR_SSCRATCH, a0
 
@@ -208,9 +208,9 @@ __kvm_switch_return:
 
 	/* Return to C code */
 	ret
-ENDPROC(__kvm_riscv_switch_to)
+SYM_FUNC_END(__kvm_riscv_switch_to)
 
-ENTRY(__kvm_riscv_unpriv_trap)
+SYM_CODE_START(__kvm_riscv_unpriv_trap)
 	/*
 	 * We assume that faulting unpriv load/store instruction is
 	 * 4-byte long and blindly increment SEPC by 4.
@@ -231,12 +231,10 @@ ENTRY(__kvm_riscv_unpriv_trap)
 	csrr	a1, CSR_HTINST
 	REG_S	a1, (KVM_ARCH_TRAP_HTINST)(a0)
 	sret
-ENDPROC(__kvm_riscv_unpriv_trap)
+SYM_CODE_END(__kvm_riscv_unpriv_trap)
 
 #ifdef	CONFIG_FPU
-	.align 3
-	.global __kvm_riscv_fp_f_save
-__kvm_riscv_fp_f_save:
+SYM_FUNC_START(__kvm_riscv_fp_f_save)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	csrs CSR_SSTATUS, t1
@@ -276,10 +274,9 @@ __kvm_riscv_fp_f_save:
 	sw t0, KVM_ARCH_FP_F_FCSR(a0)
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_f_save)
 
-	.align 3
-	.global __kvm_riscv_fp_d_save
-__kvm_riscv_fp_d_save:
+SYM_FUNC_START(__kvm_riscv_fp_d_save)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	csrs CSR_SSTATUS, t1
@@ -319,10 +316,9 @@ __kvm_riscv_fp_d_save:
 	sw t0, KVM_ARCH_FP_D_FCSR(a0)
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_d_save)
 
-	.align 3
-	.global __kvm_riscv_fp_f_restore
-__kvm_riscv_fp_f_restore:
+SYM_FUNC_START(__kvm_riscv_fp_f_restore)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	lw t0, KVM_ARCH_FP_F_FCSR(a0)
@@ -362,10 +358,9 @@ __kvm_riscv_fp_f_restore:
 	fscsr t0
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_f_restore)
 
-	.align 3
-	.global __kvm_riscv_fp_d_restore
-__kvm_riscv_fp_d_restore:
+SYM_FUNC_START(__kvm_riscv_fp_d_restore)
 	csrr t2, CSR_SSTATUS
 	li t1, SR_FS
 	lw t0, KVM_ARCH_FP_D_FCSR(a0)
@@ -405,4 +400,5 @@ __kvm_riscv_fp_d_restore:
 	fscsr t0
 	csrw CSR_SSTATUS, t2
 	ret
+SYM_FUNC_END(__kvm_riscv_fp_d_restore)
 #endif
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 183bf2097d57a9ee554970c8b7549edfd797a1ac..983623e53b2b47bd49973d15f9dd17254f8bc8be 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -6,9 +6,14 @@ lib-y			+= memmove.o
 lib-y			+= strcmp.o
 lib-y			+= strlen.o
 lib-y			+= strncmp.o
-lib-$(CONFIG_MMU)	+= uaccess.o
+ifeq ($(CONFIG_MMU), y)
+lib-y				+= uaccess.o
+lib-$(CONFIG_RISCV_ISA_V)	+= uaccess_vector.o
+endif
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 lib-$(CONFIG_RISCV_ISA_ZBC)	+= crc32.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
+lib-$(CONFIG_RISCV_ISA_V)	+= riscv_v_helpers.o
\ No newline at end of file
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
index 1a40d01a95439e1592b673ad76e5f5b964bbbed3..44e009ec5fef683a3290d57f31239661a5352f9e 100644
--- a/arch/riscv/lib/memcpy.S
+++ b/arch/riscv/lib/memcpy.S
@@ -7,8 +7,7 @@
 #include <asm/asm.h>
 
 /* void *memcpy(void *, const void *, size_t) */
-ENTRY(__memcpy)
-WEAK(memcpy)
+SYM_FUNC_START(__memcpy)
 	move t6, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented copy for small sizes */
@@ -105,6 +104,7 @@ WEAK(memcpy)
 	bltu a1, a3, 5b
 6:
 	ret
-END(__memcpy)
+SYM_FUNC_END(__memcpy)
+SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy)
 SYM_FUNC_ALIAS(__pi_memcpy, __memcpy)
 SYM_FUNC_ALIAS(__pi___memcpy, __memcpy)
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
index 838ff2022fe32d8e16769ef0e5962d9c294b0ed3..cb3e2e7ef0baa248d906717523a6f848f591eaf9 100644
--- a/arch/riscv/lib/memmove.S
+++ b/arch/riscv/lib/memmove.S
@@ -7,7 +7,6 @@
 #include <asm/asm.h>
 
 SYM_FUNC_START(__memmove)
-SYM_FUNC_START_WEAK(memmove)
 	/*
 	 * Returns
 	 *   a0 - dest
@@ -26,8 +25,8 @@ SYM_FUNC_START_WEAK(memmove)
 	 */
 
 	/* Return if nothing to do */
-	beq a0, a1, return_from_memmove
-	beqz a2, return_from_memmove
+	beq a0, a1, .Lreturn_from_memmove
+	beqz a2, .Lreturn_from_memmove
 
 	/*
 	 * Register Uses
@@ -60,7 +59,7 @@ SYM_FUNC_START_WEAK(memmove)
 	 * small enough not to bother.
 	 */
 	andi t0, a2, -(2 * SZREG)
-	beqz t0, byte_copy
+	beqz t0, .Lbyte_copy
 
 	/*
 	 * Now solve for t5 and t6.
@@ -87,14 +86,14 @@ SYM_FUNC_START_WEAK(memmove)
 	 */
 	xor  t0, a0, a1
 	andi t1, t0, (SZREG - 1)
-	beqz t1, coaligned_copy
+	beqz t1, .Lcoaligned_copy
 	/* Fall through to misaligned fixup copy */
 
-misaligned_fixup_copy:
-	bltu a1, a0, misaligned_fixup_copy_reverse
+.Lmisaligned_fixup_copy:
+	bltu a1, a0, .Lmisaligned_fixup_copy_reverse
 
-misaligned_fixup_copy_forward:
-	jal  t0, byte_copy_until_aligned_forward
+.Lmisaligned_fixup_copy_forward:
+	jal  t0, .Lbyte_copy_until_aligned_forward
 
 	andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */
 	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
@@ -153,10 +152,10 @@ misaligned_fixup_copy_forward:
 	mv    t3, t6 /* Fix the dest pointer in case the loop was broken */
 
 	add  a1, t3, a5 /* Restore the src pointer */
-	j byte_copy_forward /* Copy any remaining bytes */
+	j .Lbyte_copy_forward /* Copy any remaining bytes */
 
-misaligned_fixup_copy_reverse:
-	jal  t0, byte_copy_until_aligned_reverse
+.Lmisaligned_fixup_copy_reverse:
+	jal  t0, .Lbyte_copy_until_aligned_reverse
 
 	andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */
 	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
@@ -215,18 +214,18 @@ misaligned_fixup_copy_reverse:
 	mv    t4, t5 /* Fix the dest pointer in case the loop was broken */
 
 	add  a4, t4, a5 /* Restore the src pointer */
-	j byte_copy_reverse /* Copy any remaining bytes */
+	j .Lbyte_copy_reverse /* Copy any remaining bytes */
 
 /*
  * Simple copy loops for SZREG co-aligned memory locations.
  * These also make calls to do byte copies for any unaligned
  * data at their terminations.
  */
-coaligned_copy:
-	bltu a1, a0, coaligned_copy_reverse
+.Lcoaligned_copy:
+	bltu a1, a0, .Lcoaligned_copy_reverse
 
-coaligned_copy_forward:
-	jal t0, byte_copy_until_aligned_forward
+.Lcoaligned_copy_forward:
+	jal t0, .Lbyte_copy_until_aligned_forward
 
 	1:
 	REG_L t1, ( 0 * SZREG)(a1)
@@ -235,10 +234,10 @@ coaligned_copy_forward:
 	REG_S t1, (-1 * SZREG)(t3)
 	bne   t3, t6, 1b
 
-	j byte_copy_forward /* Copy any remaining bytes */
+	j .Lbyte_copy_forward /* Copy any remaining bytes */
 
-coaligned_copy_reverse:
-	jal t0, byte_copy_until_aligned_reverse
+.Lcoaligned_copy_reverse:
+	jal t0, .Lbyte_copy_until_aligned_reverse
 
 	1:
 	REG_L t1, (-1 * SZREG)(a4)
@@ -247,7 +246,7 @@ coaligned_copy_reverse:
 	REG_S t1, ( 0 * SZREG)(t4)
 	bne   t4, t5, 1b
 
-	j byte_copy_reverse /* Copy any remaining bytes */
+	j .Lbyte_copy_reverse /* Copy any remaining bytes */
 
 /*
  * These are basically sub-functions within the function.  They
@@ -258,7 +257,7 @@ coaligned_copy_reverse:
  * up from where they were left and we avoid code duplication
  * without any overhead except the call in and return jumps.
  */
-byte_copy_until_aligned_forward:
+.Lbyte_copy_until_aligned_forward:
 	beq  t3, t5, 2f
 	1:
 	lb   t1,  0(a1)
@@ -269,7 +268,7 @@ byte_copy_until_aligned_forward:
 	2:
 	jalr zero, 0x0(t0) /* Return to multibyte copy loop */
 
-byte_copy_until_aligned_reverse:
+.Lbyte_copy_until_aligned_reverse:
 	beq  t4, t6, 2f
 	1:
 	lb   t1, -1(a4)
@@ -285,10 +284,10 @@ byte_copy_until_aligned_reverse:
  * These will byte copy until they reach the end of data to copy.
  * At that point, they will call to return from memmove.
  */
-byte_copy:
-	bltu a1, a0, byte_copy_reverse
+.Lbyte_copy:
+	bltu a1, a0, .Lbyte_copy_reverse
 
-byte_copy_forward:
+.Lbyte_copy_forward:
 	beq  t3, t4, 2f
 	1:
 	lb   t1,  0(a1)
@@ -299,7 +298,7 @@ byte_copy_forward:
 	2:
 	ret
 
-byte_copy_reverse:
+.Lbyte_copy_reverse:
 	beq  t4, t3, 2f
 	1:
 	lb   t1, -1(a4)
@@ -309,10 +308,10 @@ byte_copy_reverse:
 	bne  t4, t3, 1b
 	2:
 
-return_from_memmove:
+.Lreturn_from_memmove:
 	ret
 
-SYM_FUNC_END(memmove)
 SYM_FUNC_END(__memmove)
+SYM_FUNC_ALIAS_WEAK(memmove, __memmove)
 SYM_FUNC_ALIAS(__pi_memmove, __memmove)
 SYM_FUNC_ALIAS(__pi___memmove, __memmove)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
index 34c5360c6705c56466cf9890f1a7261e6383a5e3..35f358e70bdb6bf79bda0f366e34c98c6ef5bbc3 100644
--- a/arch/riscv/lib/memset.S
+++ b/arch/riscv/lib/memset.S
@@ -8,8 +8,7 @@
 #include <asm/asm.h>
 
 /* void *memset(void *, int, size_t) */
-ENTRY(__memset)
-WEAK(memset)
+SYM_FUNC_START(__memset)
 	move t0, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented fill for small sizes */
@@ -110,4 +109,5 @@ WEAK(memset)
 	bltu t0, a3, 5b
 6:
 	ret
-END(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_ALIAS_WEAK(memset, __memset)
diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c
new file mode 100644
index 0000000000000000000000000000000000000000..be38a93cedaec5dafcd15d2f855df11474d2f383
--- /dev/null
+++ b/arch/riscv/lib/riscv_v_helpers.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 SiFive
+ * Author: Andy Chiu <andy.chiu@sifive.com>
+ */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#include <asm/vector.h>
+#include <asm/simd.h>
+
+#ifdef CONFIG_MMU
+#include <asm/asm-prototypes.h>
+#endif
+
+#ifdef CONFIG_MMU
+size_t riscv_v_usercopy_threshold = CONFIG_RISCV_ISA_V_UCOPY_THRESHOLD;
+int __asm_vector_usercopy(void *dst, void *src, size_t n);
+int fallback_scalar_usercopy(void *dst, void *src, size_t n);
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n)
+{
+	size_t remain, copied;
+
+	/* skip has_vector() check because it has been done by the asm  */
+	if (!may_use_simd())
+		goto fallback;
+
+	kernel_vector_begin();
+	remain = __asm_vector_usercopy(dst, src, n);
+	kernel_vector_end();
+
+	if (remain) {
+		copied = n - remain;
+		dst += copied;
+		src += copied;
+		n = remain;
+		goto fallback;
+	}
+
+	return remain;
+
+fallback:
+	return fallback_scalar_usercopy(dst, src, n);
+}
+#endif
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 09b47ebacf2e8743bc1cf77be0693b4499748afb..a1e4a3c4292549bfd509cd9ce18b509af50b76ae 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -3,6 +3,8 @@
 #include <asm/asm.h>
 #include <asm/asm-extable.h>
 #include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
 
 	.macro fixup op reg addr lbl
 100:
@@ -10,8 +12,14 @@
 	_asm_extable	100b, \lbl
 	.endm
 
-ENTRY(__asm_copy_to_user)
-ENTRY(__asm_copy_from_user)
+SYM_FUNC_START(__asm_copy_to_user)
+#ifdef CONFIG_RISCV_ISA_V
+	ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_v, CONFIG_RISCV_ISA_V)
+	REG_L	t0, riscv_v_usercopy_threshold
+	bltu	a2, t0, fallback_scalar_usercopy
+	tail enter_vector_usercopy
+#endif
+SYM_FUNC_START(fallback_scalar_usercopy)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -181,13 +189,14 @@ ENTRY(__asm_copy_from_user)
 	csrc CSR_STATUS, t6
 	sub a0, t5, a0
 	ret
-ENDPROC(__asm_copy_to_user)
-ENDPROC(__asm_copy_from_user)
+SYM_FUNC_END(__asm_copy_to_user)
+SYM_FUNC_END(fallback_scalar_usercopy)
 EXPORT_SYMBOL(__asm_copy_to_user)
+SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_from_user)
 
 
-ENTRY(__clear_user)
+SYM_FUNC_START(__clear_user)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -233,5 +242,5 @@ ENTRY(__clear_user)
 	csrc CSR_STATUS, t6
 	sub a0, a3, a0
 	ret
-ENDPROC(__clear_user)
+SYM_FUNC_END(__clear_user)
 EXPORT_SYMBOL(__clear_user)
diff --git a/arch/riscv/lib/uaccess_vector.S b/arch/riscv/lib/uaccess_vector.S
new file mode 100644
index 0000000000000000000000000000000000000000..51ab5588e9ff36b8b7dc80096be587d09da2881f
--- /dev/null
+++ b/arch/riscv/lib/uaccess_vector.S
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+#include <asm/asm-extable.h>
+#include <asm/csr.h>
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+	.macro fixup op reg addr lbl
+100:
+	\op \reg, \addr
+	_asm_extable	100b, \lbl
+	.endm
+
+SYM_FUNC_START(__asm_vector_usercopy)
+	/* Enable access to user memory */
+	li	t6, SR_SUM
+	csrs	CSR_STATUS, t6
+
+loop:
+	vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+	fixup vle8.v vData, (pSrc), 10f
+	sub iNum, iNum, iVL
+	add pSrc, pSrc, iVL
+	fixup vse8.v vData, (pDst), 11f
+	add pDst, pDst, iVL
+	bnez iNum, loop
+
+	/* Exception fixup for vector load is shared with normal exit */
+10:
+	/* Disable access to user memory */
+	csrc	CSR_STATUS, t6
+	mv	a0, iNum
+	ret
+
+	/* Exception fixup code for vector store. */
+11:
+	/* Undo the subtraction after vle8.v */
+	add	iNum, iNum, iVL
+	/* Make sure the scalar fallback skip already processed bytes */
+	csrr	t2, CSR_VSTART
+	sub	iNum, iNum, t2
+	j	10b
+SYM_FUNC_END(__asm_vector_usercopy)
diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S
new file mode 100644
index 0000000000000000000000000000000000000000..b28f2430e52fa50c199cd80153647fde33088e4c
--- /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 <linux/export.h>
+#include <asm/asm.h>
+
+SYM_FUNC_START(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
+SYM_FUNC_END(xor_regs_2_)
+EXPORT_SYMBOL(xor_regs_2_)
+
+SYM_FUNC_START(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
+SYM_FUNC_END(xor_regs_3_)
+EXPORT_SYMBOL(xor_regs_3_)
+
+SYM_FUNC_START(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
+SYM_FUNC_END(xor_regs_4_)
+EXPORT_SYMBOL(xor_regs_4_)
+
+SYM_FUNC_START(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
+SYM_FUNC_END(xor_regs_5_)
+EXPORT_SYMBOL(xor_regs_5_)
diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S
index a4ede42bc15107570e350e26f72b3fe80ad2ea31..609f0cc224ef7c3762b7a932b8b6957d53447e7d 100644
--- a/arch/riscv/purgatory/entry.S
+++ b/arch/riscv/purgatory/entry.S
@@ -8,16 +8,12 @@
  *
  */
 
-.macro	size, sym:req
-	.size \sym, . - \sym
-.endm
 #include <asm/asm.h>
 #include <linux/linkage.h>
 
 .text
 
-.globl purgatory_start
-purgatory_start:
+SYM_CODE_START(purgatory_start)
 
 	lla	sp, .Lstack
 	mv	s0, a0	/* The hartid of the current hart */
@@ -30,8 +26,7 @@ purgatory_start:
 	mv	a1, s1
 	ld	a2, riscv_kernel_entry
 	jr	a2
-
-size purgatory_start
+SYM_CODE_END(purgatory_start)
 
 .align 4
 	.rept	256
@@ -42,9 +37,6 @@ size purgatory_start
 .data
 
 .align LGREG
-.globl riscv_kernel_entry
-riscv_kernel_entry:
-	.quad	0
-size riscv_kernel_entry
+SYM_DATA(riscv_kernel_entry, .quad 0)
 
 .end