Adding upstream version 5.10.209.upstream/5.10.209

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

59 files changed, 8173 insertions, 0 deletions

diff --git a/arch/riscv/kernel/.gitignore b/arch/riscv/kernel/.gitignore
new file mode 100644
index 000000000..e052ed331
--- /dev/null
+++ b/arch/riscv/kernel/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+/vmlinux.lds
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
new file mode 100644
index 000000000..bc49d5f23
--- /dev/null
+++ b/arch/riscv/kernel/Makefile
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the RISC-V Linux kernel
+#
+
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
+endif
+
+extra-y += head.o
+extra-y += vmlinux.lds
+
+obj-y	+= soc.o
+obj-y	+= cpu.o
+obj-y	+= cpufeature.o
+obj-y	+= entry.o
+obj-y	+= irq.o
+obj-y	+= process.o
+obj-y	+= ptrace.o
+obj-y	+= reset.o
+obj-y	+= setup.o
+obj-y	+= signal.o
+obj-y	+= syscall_table.o
+obj-y	+= sys_riscv.o
+obj-y	+= time.o
+obj-y	+= traps.o
+obj-y	+= riscv_ksyms.o
+obj-y	+= stacktrace.o
+obj-y	+= cacheinfo.o
+obj-y	+= patch.o
+obj-$(CONFIG_MMU) += vdso.o vdso/
+
+obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
+obj-$(CONFIG_FPU)		+= fpu.o
+obj-$(CONFIG_SMP)		+= smpboot.o
+obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_SMP)		+= cpu_ops.o
+obj-$(CONFIG_SMP)		+= cpu_ops_spinwait.o
+obj-$(CONFIG_MODULES)		+= module.o
+obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
+
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
+
+obj-$(CONFIG_TRACE_IRQFLAGS)	+= trace_irq.o
+
+obj-$(CONFIG_RISCV_BASE_PMU)	+= perf_event.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
+obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
+obj-$(CONFIG_RISCV_SBI)		+= sbi.o
+ifeq ($(CONFIG_RISCV_SBI), y)
+obj-$(CONFIG_SMP) += cpu_ops_sbi.o
+endif
+obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
+obj-$(CONFIG_KGDB)		+= kgdb.o
+
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
+
+obj-$(CONFIG_EFI)		+= efi.o
+
+clean:
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
new file mode 100644
index 000000000..db203442c
--- /dev/null
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#define GENERATING_ASM_OFFSETS
+
+#include <linux/kbuild.h>
+#include <linux/sched.h>
+#include <asm/thread_info.h>
+#include <asm/ptrace.h>
+
+void asm_offsets(void)
+{
+	OFFSET(TASK_THREAD_RA, task_struct, thread.ra);
+	OFFSET(TASK_THREAD_SP, task_struct, thread.sp);
+	OFFSET(TASK_THREAD_S0, task_struct, thread.s[0]);
+	OFFSET(TASK_THREAD_S1, task_struct, thread.s[1]);
+	OFFSET(TASK_THREAD_S2, task_struct, thread.s[2]);
+	OFFSET(TASK_THREAD_S3, task_struct, thread.s[3]);
+	OFFSET(TASK_THREAD_S4, task_struct, thread.s[4]);
+	OFFSET(TASK_THREAD_S5, task_struct, thread.s[5]);
+	OFFSET(TASK_THREAD_S6, task_struct, thread.s[6]);
+	OFFSET(TASK_THREAD_S7, task_struct, thread.s[7]);
+	OFFSET(TASK_THREAD_S8, task_struct, thread.s[8]);
+	OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]);
+	OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]);
+	OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
+	OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
+	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
+	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
+	OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);
+
+	OFFSET(TASK_THREAD_F0,  task_struct, thread.fstate.f[0]);
+	OFFSET(TASK_THREAD_F1,  task_struct, thread.fstate.f[1]);
+	OFFSET(TASK_THREAD_F2,  task_struct, thread.fstate.f[2]);
+	OFFSET(TASK_THREAD_F3,  task_struct, thread.fstate.f[3]);
+	OFFSET(TASK_THREAD_F4,  task_struct, thread.fstate.f[4]);
+	OFFSET(TASK_THREAD_F5,  task_struct, thread.fstate.f[5]);
+	OFFSET(TASK_THREAD_F6,  task_struct, thread.fstate.f[6]);
+	OFFSET(TASK_THREAD_F7,  task_struct, thread.fstate.f[7]);
+	OFFSET(TASK_THREAD_F8,  task_struct, thread.fstate.f[8]);
+	OFFSET(TASK_THREAD_F9,  task_struct, thread.fstate.f[9]);
+	OFFSET(TASK_THREAD_F10, task_struct, thread.fstate.f[10]);
+	OFFSET(TASK_THREAD_F11, task_struct, thread.fstate.f[11]);
+	OFFSET(TASK_THREAD_F12, task_struct, thread.fstate.f[12]);
+	OFFSET(TASK_THREAD_F13, task_struct, thread.fstate.f[13]);
+	OFFSET(TASK_THREAD_F14, task_struct, thread.fstate.f[14]);
+	OFFSET(TASK_THREAD_F15, task_struct, thread.fstate.f[15]);
+	OFFSET(TASK_THREAD_F16, task_struct, thread.fstate.f[16]);
+	OFFSET(TASK_THREAD_F17, task_struct, thread.fstate.f[17]);
+	OFFSET(TASK_THREAD_F18, task_struct, thread.fstate.f[18]);
+	OFFSET(TASK_THREAD_F19, task_struct, thread.fstate.f[19]);
+	OFFSET(TASK_THREAD_F20, task_struct, thread.fstate.f[20]);
+	OFFSET(TASK_THREAD_F21, task_struct, thread.fstate.f[21]);
+	OFFSET(TASK_THREAD_F22, task_struct, thread.fstate.f[22]);
+	OFFSET(TASK_THREAD_F23, task_struct, thread.fstate.f[23]);
+	OFFSET(TASK_THREAD_F24, task_struct, thread.fstate.f[24]);
+	OFFSET(TASK_THREAD_F25, task_struct, thread.fstate.f[25]);
+	OFFSET(TASK_THREAD_F26, task_struct, thread.fstate.f[26]);
+	OFFSET(TASK_THREAD_F27, task_struct, thread.fstate.f[27]);
+	OFFSET(TASK_THREAD_F28, task_struct, thread.fstate.f[28]);
+	OFFSET(TASK_THREAD_F29, task_struct, thread.fstate.f[29]);
+	OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]);
+	OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]);
+	OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr);
+
+	DEFINE(PT_SIZE, sizeof(struct pt_regs));
+	OFFSET(PT_EPC, pt_regs, epc);
+	OFFSET(PT_RA, pt_regs, ra);
+	OFFSET(PT_FP, pt_regs, s0);
+	OFFSET(PT_S0, pt_regs, s0);
+	OFFSET(PT_S1, pt_regs, s1);
+	OFFSET(PT_S2, pt_regs, s2);
+	OFFSET(PT_S3, pt_regs, s3);
+	OFFSET(PT_S4, pt_regs, s4);
+	OFFSET(PT_S5, pt_regs, s5);
+	OFFSET(PT_S6, pt_regs, s6);
+	OFFSET(PT_S7, pt_regs, s7);
+	OFFSET(PT_S8, pt_regs, s8);
+	OFFSET(PT_S9, pt_regs, s9);
+	OFFSET(PT_S10, pt_regs, s10);
+	OFFSET(PT_S11, pt_regs, s11);
+	OFFSET(PT_SP, pt_regs, sp);
+	OFFSET(PT_TP, pt_regs, tp);
+	OFFSET(PT_A0, pt_regs, a0);
+	OFFSET(PT_A1, pt_regs, a1);
+	OFFSET(PT_A2, pt_regs, a2);
+	OFFSET(PT_A3, pt_regs, a3);
+	OFFSET(PT_A4, pt_regs, a4);
+	OFFSET(PT_A5, pt_regs, a5);
+	OFFSET(PT_A6, pt_regs, a6);
+	OFFSET(PT_A7, pt_regs, a7);
+	OFFSET(PT_T0, pt_regs, t0);
+	OFFSET(PT_T1, pt_regs, t1);
+	OFFSET(PT_T2, pt_regs, t2);
+	OFFSET(PT_T3, pt_regs, t3);
+	OFFSET(PT_T4, pt_regs, t4);
+	OFFSET(PT_T5, pt_regs, t5);
+	OFFSET(PT_T6, pt_regs, t6);
+	OFFSET(PT_GP, pt_regs, gp);
+	OFFSET(PT_ORIG_A0, pt_regs, orig_a0);
+	OFFSET(PT_STATUS, pt_regs, status);
+	OFFSET(PT_BADADDR, pt_regs, badaddr);
+	OFFSET(PT_CAUSE, pt_regs, cause);
+
+	/*
+	 * 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
+	 * to loading the long immediate every time.
+	 */
+	DEFINE(TASK_THREAD_RA_RA,
+		  offsetof(struct task_struct, thread.ra)
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_SP_RA,
+		  offsetof(struct task_struct, thread.sp)
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S0_RA,
+		  offsetof(struct task_struct, thread.s[0])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S1_RA,
+		  offsetof(struct task_struct, thread.s[1])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S2_RA,
+		  offsetof(struct task_struct, thread.s[2])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S3_RA,
+		  offsetof(struct task_struct, thread.s[3])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S4_RA,
+		  offsetof(struct task_struct, thread.s[4])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S5_RA,
+		  offsetof(struct task_struct, thread.s[5])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S6_RA,
+		  offsetof(struct task_struct, thread.s[6])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S7_RA,
+		  offsetof(struct task_struct, thread.s[7])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S8_RA,
+		  offsetof(struct task_struct, thread.s[8])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S9_RA,
+		  offsetof(struct task_struct, thread.s[9])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S10_RA,
+		  offsetof(struct task_struct, thread.s[10])
+		- offsetof(struct task_struct, thread.ra)
+	);
+	DEFINE(TASK_THREAD_S11_RA,
+		  offsetof(struct task_struct, thread.s[11])
+		- offsetof(struct task_struct, thread.ra)
+	);
+
+	DEFINE(TASK_THREAD_F0_F0,
+		  offsetof(struct task_struct, thread.fstate.f[0])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F1_F0,
+		  offsetof(struct task_struct, thread.fstate.f[1])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F2_F0,
+		  offsetof(struct task_struct, thread.fstate.f[2])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F3_F0,
+		  offsetof(struct task_struct, thread.fstate.f[3])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F4_F0,
+		  offsetof(struct task_struct, thread.fstate.f[4])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F5_F0,
+		  offsetof(struct task_struct, thread.fstate.f[5])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F6_F0,
+		  offsetof(struct task_struct, thread.fstate.f[6])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F7_F0,
+		  offsetof(struct task_struct, thread.fstate.f[7])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F8_F0,
+		  offsetof(struct task_struct, thread.fstate.f[8])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F9_F0,
+		  offsetof(struct task_struct, thread.fstate.f[9])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F10_F0,
+		  offsetof(struct task_struct, thread.fstate.f[10])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F11_F0,
+		  offsetof(struct task_struct, thread.fstate.f[11])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F12_F0,
+		  offsetof(struct task_struct, thread.fstate.f[12])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F13_F0,
+		  offsetof(struct task_struct, thread.fstate.f[13])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F14_F0,
+		  offsetof(struct task_struct, thread.fstate.f[14])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F15_F0,
+		  offsetof(struct task_struct, thread.fstate.f[15])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F16_F0,
+		  offsetof(struct task_struct, thread.fstate.f[16])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F17_F0,
+		  offsetof(struct task_struct, thread.fstate.f[17])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F18_F0,
+		  offsetof(struct task_struct, thread.fstate.f[18])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F19_F0,
+		  offsetof(struct task_struct, thread.fstate.f[19])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F20_F0,
+		  offsetof(struct task_struct, thread.fstate.f[20])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F21_F0,
+		  offsetof(struct task_struct, thread.fstate.f[21])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F22_F0,
+		  offsetof(struct task_struct, thread.fstate.f[22])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F23_F0,
+		  offsetof(struct task_struct, thread.fstate.f[23])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F24_F0,
+		  offsetof(struct task_struct, thread.fstate.f[24])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F25_F0,
+		  offsetof(struct task_struct, thread.fstate.f[25])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F26_F0,
+		  offsetof(struct task_struct, thread.fstate.f[26])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F27_F0,
+		  offsetof(struct task_struct, thread.fstate.f[27])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F28_F0,
+		  offsetof(struct task_struct, thread.fstate.f[28])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F29_F0,
+		  offsetof(struct task_struct, thread.fstate.f[29])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F30_F0,
+		  offsetof(struct task_struct, thread.fstate.f[30])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_F31_F0,
+		  offsetof(struct task_struct, thread.fstate.f[31])
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+	DEFINE(TASK_THREAD_FCSR_F0,
+		  offsetof(struct task_struct, thread.fstate.fcsr)
+		- offsetof(struct task_struct, thread.fstate.f[0])
+	);
+
+	/*
+	 * We allocate a pt_regs on the stack when entering the kernel.  This
+	 * ensures the alignment is sane.
+	 */
+	DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
+}
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
new file mode 100644
index 000000000..90deabfe6
--- /dev/null
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <asm/cacheinfo.h>
+
+static struct riscv_cacheinfo_ops *rv_cache_ops;
+
+void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops)
+{
+	rv_cache_ops = ops;
+}
+EXPORT_SYMBOL_GPL(riscv_set_cacheinfo_ops);
+
+const struct attribute_group *
+cache_get_priv_group(struct cacheinfo *this_leaf)
+{
+	if (rv_cache_ops && rv_cache_ops->get_priv_group)
+		return rv_cache_ops->get_priv_group(this_leaf);
+	return NULL;
+}
+
+static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type)
+{
+	/*
+	 * Using raw_smp_processor_id() elides a preemptability check, but this
+	 * is really indicative of a larger problem: the cacheinfo UABI assumes
+	 * that cores have a homonogenous view of the cache hierarchy.  That
+	 * happens to be the case for the current set of RISC-V systems, but
+	 * likely won't be true in general.  Since there's no way to provide
+	 * correct information for these systems via the current UABI we're
+	 * just eliding the check for now.
+	 */
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id());
+	struct cacheinfo *this_leaf;
+	int index;
+
+	for (index = 0; index < this_cpu_ci->num_leaves; index++) {
+		this_leaf = this_cpu_ci->info_list + index;
+		if (this_leaf->level == level && this_leaf->type == type)
+			return this_leaf;
+	}
+
+	return NULL;
+}
+
+uintptr_t get_cache_size(u32 level, enum cache_type type)
+{
+	struct cacheinfo *this_leaf = get_cacheinfo(level, type);
+
+	return this_leaf ? this_leaf->size : 0;
+}
+
+uintptr_t get_cache_geometry(u32 level, enum cache_type type)
+{
+	struct cacheinfo *this_leaf = get_cacheinfo(level, type);
+
+	return this_leaf ? (this_leaf->ways_of_associativity << 16 |
+			    this_leaf->coherency_line_size) :
+			   0;
+}
+
+static void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+			 unsigned int level, unsigned int size,
+			 unsigned int sets, unsigned int line_size)
+{
+	this_leaf->level = level;
+	this_leaf->type = type;
+	this_leaf->size = size;
+	this_leaf->number_of_sets = sets;
+	this_leaf->coherency_line_size = line_size;
+
+	/*
+	 * If the cache is fully associative, there is no need to
+	 * check the other properties.
+	 */
+	if (sets == 1)
+		return;
+
+	/*
+	 * Set the ways number for n-ways associative, make sure
+	 * all properties are big than zero.
+	 */
+	if (sets > 0 && size > 0 && line_size > 0)
+		this_leaf->ways_of_associativity = (size / sets) / line_size;
+}
+
+static void fill_cacheinfo(struct cacheinfo **this_leaf,
+			   struct device_node *node, unsigned int level)
+{
+	unsigned int size, sets, line_size;
+
+	if (!of_property_read_u32(node, "cache-size", &size) &&
+	    !of_property_read_u32(node, "cache-block-size", &line_size) &&
+	    !of_property_read_u32(node, "cache-sets", &sets)) {
+		ci_leaf_init((*this_leaf)++, CACHE_TYPE_UNIFIED, level, size, sets, line_size);
+	}
+
+	if (!of_property_read_u32(node, "i-cache-size", &size) &&
+	    !of_property_read_u32(node, "i-cache-sets", &sets) &&
+	    !of_property_read_u32(node, "i-cache-block-size", &line_size)) {
+		ci_leaf_init((*this_leaf)++, CACHE_TYPE_INST, level, size, sets, line_size);
+	}
+
+	if (!of_property_read_u32(node, "d-cache-size", &size) &&
+	    !of_property_read_u32(node, "d-cache-sets", &sets) &&
+	    !of_property_read_u32(node, "d-cache-block-size", &line_size)) {
+		ci_leaf_init((*this_leaf)++, CACHE_TYPE_DATA, level, size, sets, line_size);
+	}
+}
+
+int init_cache_level(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct device_node *np = of_cpu_device_node_get(cpu);
+	struct device_node *prev = NULL;
+	int levels = 0, leaves = 0, level;
+
+	if (of_property_read_bool(np, "cache-size"))
+		++leaves;
+	if (of_property_read_bool(np, "i-cache-size"))
+		++leaves;
+	if (of_property_read_bool(np, "d-cache-size"))
+		++leaves;
+	if (leaves > 0)
+		levels = 1;
+
+	prev = np;
+	while ((np = of_find_next_cache_node(np))) {
+		of_node_put(prev);
+		prev = np;
+		if (!of_device_is_compatible(np, "cache"))
+			break;
+		if (of_property_read_u32(np, "cache-level", &level))
+			break;
+		if (level <= levels)
+			break;
+		if (of_property_read_bool(np, "cache-size"))
+			++leaves;
+		if (of_property_read_bool(np, "i-cache-size"))
+			++leaves;
+		if (of_property_read_bool(np, "d-cache-size"))
+			++leaves;
+		levels = level;
+	}
+
+	of_node_put(np);
+	this_cpu_ci->num_levels = levels;
+	this_cpu_ci->num_leaves = leaves;
+
+	return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	struct device_node *np = of_cpu_device_node_get(cpu);
+	struct device_node *prev = NULL;
+	int levels = 1, level = 1;
+
+	/* Level 1 caches in cpu node */
+	fill_cacheinfo(&this_leaf, np, level);
+
+	/* Next level caches in cache nodes */
+	prev = np;
+	while ((np = of_find_next_cache_node(np))) {
+		of_node_put(prev);
+		prev = np;
+
+		if (!of_device_is_compatible(np, "cache"))
+			break;
+		if (of_property_read_u32(np, "cache-level", &level))
+			break;
+		if (level <= levels)
+			break;
+
+		fill_cacheinfo(&this_leaf, np, level);
+
+		levels = level;
+	}
+	of_node_put(np);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
new file mode 100644
index 000000000..df84e0c13
--- /dev/null
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/cpu.h>
+#include <linux/sched/hotplug.h>
+#include <asm/irq.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+
+void cpu_stop(void);
+void arch_cpu_idle_dead(void)
+{
+	cpu_stop();
+}
+
+bool cpu_has_hotplug(unsigned int cpu)
+{
+	if (cpu_ops[cpu]->cpu_stop)
+		return true;
+
+	return false;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+	int ret = 0;
+	unsigned int cpu = smp_processor_id();
+
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+		return -EOPNOTSUPP;
+
+	if (cpu_ops[cpu]->cpu_disable)
+		ret = cpu_ops[cpu]->cpu_disable(cpu);
+
+	if (ret)
+		return ret;
+
+	remove_cpu_topology(cpu);
+	set_cpu_online(cpu, false);
+	irq_migrate_all_off_this_cpu();
+
+	return ret;
+}
+
+/*
+ * Called on the thread which is asking for a CPU to be shutdown.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	int ret = 0;
+
+	if (!cpu_wait_death(cpu, 5)) {
+		pr_err("CPU %u: didn't die\n", cpu);
+		return;
+	}
+	pr_notice("CPU%u: off\n", cpu);
+
+	/* Verify from the firmware if the cpu is really stopped*/
+	if (cpu_ops[cpu]->cpu_is_stopped)
+		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (ret)
+		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ */
+void cpu_stop(void)
+{
+	idle_task_exit();
+
+	(void)cpu_report_death();
+
+	cpu_ops[smp_processor_id()]->cpu_stop();
+	/* It should never reach here */
+	BUG();
+}
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
new file mode 100644
index 000000000..6d59e6906
--- /dev/null
+++ b/arch/riscv/kernel/cpu.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+#include <asm/smp.h>
+
+/*
+ * Returns the hart ID of the given device tree node, or -ENODEV if the node
+ * isn't an enabled and valid RISC-V hart node.
+ */
+int riscv_of_processor_hartid(struct device_node *node)
+{
+	const char *isa;
+	u32 hart;
+
+	if (!of_device_is_compatible(node, "riscv")) {
+		pr_warn("Found incompatible CPU\n");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(node, "reg", &hart)) {
+		pr_warn("Found CPU without hart ID\n");
+		return -ENODEV;
+	}
+
+	if (!of_device_is_available(node)) {
+		pr_info("CPU with hartid=%d is not available\n", hart);
+		return -ENODEV;
+	}
+
+	if (of_property_read_string(node, "riscv,isa", &isa)) {
+		pr_warn("CPU with hartid=%d has no \"riscv,isa\" property\n", hart);
+		return -ENODEV;
+	}
+	if (isa[0] != 'r' || isa[1] != 'v') {
+		pr_warn("CPU with hartid=%d has an invalid ISA of \"%s\"\n", hart, isa);
+		return -ENODEV;
+	}
+
+	return hart;
+}
+
+/*
+ * Find hart ID of the CPU DT node under which given DT node falls.
+ *
+ * To achieve this, we walk up the DT tree until we find an active
+ * RISC-V core (HART) node and extract the cpuid from it.
+ */
+int riscv_of_parent_hartid(struct device_node *node)
+{
+	for (; node; node = node->parent) {
+		if (of_device_is_compatible(node, "riscv"))
+			return riscv_of_processor_hartid(node);
+	}
+
+	return -1;
+}
+
+#ifdef CONFIG_PROC_FS
+
+static void print_isa(struct seq_file *f, const char *isa)
+{
+	/* Print the entire ISA as it is */
+	seq_puts(f, "isa\t\t: ");
+	seq_write(f, isa, strlen(isa));
+	seq_puts(f, "\n");
+}
+
+static void print_mmu(struct seq_file *f, const char *mmu_type)
+{
+#if defined(CONFIG_32BIT)
+	if (strcmp(mmu_type, "riscv,sv32") != 0)
+		return;
+#elif defined(CONFIG_64BIT)
+	if (strcmp(mmu_type, "riscv,sv39") != 0 &&
+	    strcmp(mmu_type, "riscv,sv48") != 0)
+		return;
+#endif
+
+	seq_printf(f, "mmu\t\t: %s\n", mmu_type+6);
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	*pos = cpumask_next(*pos - 1, cpu_online_mask);
+	if ((*pos) < nr_cpu_ids)
+		return (void *)(uintptr_t)(1 + *pos);
+	return NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+static int c_show(struct seq_file *m, void *v)
+{
+	unsigned long cpu_id = (unsigned long)v - 1;
+	struct device_node *node = of_get_cpu_node(cpu_id, NULL);
+	const char *compat, *isa, *mmu;
+
+	seq_printf(m, "processor\t: %lu\n", cpu_id);
+	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
+	if (!of_property_read_string(node, "riscv,isa", &isa))
+		print_isa(m, isa);
+	if (!of_property_read_string(node, "mmu-type", &mmu))
+		print_mmu(m, mmu);
+	if (!of_property_read_string(node, "compatible", &compat)
+	    && strcmp(compat, "riscv"))
+		seq_printf(m, "uarch\t\t: %s\n", compat);
+	seq_puts(m, "\n");
+	of_node_put(node);
+
+	return 0;
+}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= c_show
+};
+
+#endif /* CONFIG_PROC_FS */
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
new file mode 100644
index 000000000..1985884fe
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+
+void *__cpu_up_stack_pointer[NR_CPUS] __section(".data");
+void *__cpu_up_task_pointer[NR_CPUS] __section(".data");
+
+extern const struct cpu_operations cpu_ops_sbi;
+extern const struct cpu_operations cpu_ops_spinwait;
+
+void cpu_update_secondary_bootdata(unsigned int cpuid,
+				   struct task_struct *tidle)
+{
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	/* Make sure tidle is updated */
+	smp_mb();
+	WRITE_ONCE(__cpu_up_stack_pointer[hartid],
+		   task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
+}
+
+void __init cpu_set_ops(int cpuid)
+{
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	if (sbi_probe_extension(SBI_EXT_HSM) > 0) {
+		if (!cpuid)
+			pr_info("SBI v0.2 HSM extension detected\n");
+		cpu_ops[cpuid] = &cpu_ops_sbi;
+	} else
+#endif
+		cpu_ops[cpuid] = &cpu_ops_spinwait;
+}
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
new file mode 100644
index 000000000..685fae72b
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HSM extension and cpu_ops implementation.
+ *
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+extern char secondary_start_sbi[];
+const struct cpu_operations cpu_ops_sbi;
+
+static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
+			      unsigned long priv)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_START,
+			hartid, saddr, priv, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_hsm_hart_stop(void)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STOP, 0, 0, 0, 0, 0, 0);
+
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return 0;
+}
+
+static int sbi_hsm_hart_get_status(unsigned long hartid)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STATUS,
+			hartid, 0, 0, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+	else
+		return ret.value;
+}
+#endif
+
+static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+	int rc;
+	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	cpu_update_secondary_bootdata(cpuid, tidle);
+	rc = sbi_hsm_hart_start(hartid, boot_addr, 0);
+
+	return rc;
+}
+
+static int sbi_cpu_prepare(unsigned int cpuid)
+{
+	if (!cpu_ops_sbi.cpu_start) {
+		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_cpu_disable(unsigned int cpuid)
+{
+	if (!cpu_ops_sbi.cpu_stop)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void sbi_cpu_stop(void)
+{
+	int ret;
+
+	ret = sbi_hsm_hart_stop();
+	pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret);
+}
+
+static int sbi_cpu_is_stopped(unsigned int cpuid)
+{
+	int rc;
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	rc = sbi_hsm_hart_get_status(hartid);
+
+	if (rc == SBI_HSM_HART_STATUS_STOPPED)
+		return 0;
+	return rc;
+}
+#endif
+
+const struct cpu_operations cpu_ops_sbi = {
+	.name		= "sbi",
+	.cpu_prepare	= sbi_cpu_prepare,
+	.cpu_start	= sbi_cpu_start,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= sbi_cpu_disable,
+	.cpu_stop	= sbi_cpu_stop,
+	.cpu_is_stopped	= sbi_cpu_is_stopped,
+#endif
+};
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
new file mode 100644
index 000000000..b2c957bb6
--- /dev/null
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+const struct cpu_operations cpu_ops_spinwait;
+
+static int spinwait_cpu_prepare(unsigned int cpuid)
+{
+	if (!cpu_ops_spinwait.cpu_start) {
+		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
+{
+	/*
+	 * In this protocol, all cpus boot on their own accord.  _start
+	 * selects the first cpu to boot the kernel and causes the remainder
+	 * of the cpus to spin in a loop waiting for their stack pointer to be
+	 * setup by that main cpu.  Writing to bootdata
+	 * (i.e __cpu_up_stack_pointer) signals to the spinning cpus that they
+	 * can continue the boot process.
+	 */
+	cpu_update_secondary_bootdata(cpuid, tidle);
+
+	return 0;
+}
+
+const struct cpu_operations cpu_ops_spinwait = {
+	.name		= "spinwait",
+	.cpu_prepare	= spinwait_cpu_prepare,
+	.cpu_start	= spinwait_cpu_start,
+};
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
new file mode 100644
index 000000000..ac202f44a
--- /dev/null
+++ b/arch/riscv/kernel/cpufeature.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copied from arch/arm64/kernel/cpufeature.c
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/bitmap.h>
+#include <linux/of.h>
+#include <asm/processor.h>
+#include <asm/hwcap.h>
+#include <asm/smp.h>
+#include <asm/switch_to.h>
+
+unsigned long elf_hwcap __read_mostly;
+
+/* Host ISA bitmap */
+static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
+
+#ifdef CONFIG_FPU
+bool has_fpu __read_mostly;
+#endif
+
+/**
+ * riscv_isa_extension_base() - Get base extension word
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * Return: base extension word as unsigned long value
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap)
+{
+	if (!isa_bitmap)
+		return riscv_isa[0];
+	return isa_bitmap[0];
+}
+EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
+
+/**
+ * __riscv_isa_extension_available() - Check whether given extension
+ * is available or not
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * @bit: bit position of the desired extension
+ * Return: true or false
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+{
+	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
+
+	if (bit >= RISCV_ISA_EXT_MAX)
+		return false;
+
+	return test_bit(bit, bmap) ? true : false;
+}
+EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
+
+void riscv_fill_hwcap(void)
+{
+	struct device_node *node;
+	const char *isa;
+	char print_str[BITS_PER_LONG + 1];
+	size_t i, j, isa_len;
+	static unsigned long isa2hwcap[256] = {0};
+
+	isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
+	isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M;
+	isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A;
+	isa2hwcap['f'] = isa2hwcap['F'] = COMPAT_HWCAP_ISA_F;
+	isa2hwcap['d'] = isa2hwcap['D'] = COMPAT_HWCAP_ISA_D;
+	isa2hwcap['c'] = isa2hwcap['C'] = COMPAT_HWCAP_ISA_C;
+
+	elf_hwcap = 0;
+
+	bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
+
+	for_each_of_cpu_node(node) {
+		unsigned long this_hwcap = 0;
+		unsigned long this_isa = 0;
+
+		if (riscv_of_processor_hartid(node) < 0)
+			continue;
+
+		if (of_property_read_string(node, "riscv,isa", &isa)) {
+			pr_warn("Unable to find \"riscv,isa\" devicetree entry\n");
+			continue;
+		}
+
+		i = 0;
+		isa_len = strlen(isa);
+#if IS_ENABLED(CONFIG_32BIT)
+		if (!strncmp(isa, "rv32", 4))
+			i += 4;
+#elif IS_ENABLED(CONFIG_64BIT)
+		if (!strncmp(isa, "rv64", 4))
+			i += 4;
+#endif
+		for (; i < isa_len; ++i) {
+			this_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+			/*
+			 * TODO: X, Y and Z extension parsing for Host ISA
+			 * bitmap will be added in-future.
+			 */
+			if ('a' <= isa[i] && isa[i] < 'x')
+				this_isa |= (1UL << (isa[i] - 'a'));
+		}
+
+		/*
+		 * All "okay" hart should have same isa. Set HWCAP based on
+		 * common capabilities of every "okay" hart, in case they don't
+		 * have.
+		 */
+		if (elf_hwcap)
+			elf_hwcap &= this_hwcap;
+		else
+			elf_hwcap = this_hwcap;
+
+		if (riscv_isa[0])
+			riscv_isa[0] &= this_isa;
+		else
+			riscv_isa[0] = this_isa;
+	}
+
+	/* We don't support systems with F but without D, so mask those out
+	 * here. */
+	if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) {
+		pr_info("This kernel does not support systems with F but not D\n");
+		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
+	}
+
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+		if (riscv_isa[0] & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: ISA extensions %s\n", print_str);
+
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+		if (elf_hwcap & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: ELF capabilities %s\n", print_str);
+
+#ifdef CONFIG_FPU
+	if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D))
+		has_fpu = true;
+#endif
+}
diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S
new file mode 100644
index 000000000..8e733aa48
--- /dev/null
+++ b/arch/riscv/kernel/efi-header.S
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Adapted from arch/arm64/kernel/efi-header.S
+ */
+
+#include <linux/pe.h>
+#include <linux/sizes.h>
+
+	.macro	__EFI_PE_HEADER
+	.long	PE_MAGIC
+coff_header:
+#ifdef CONFIG_64BIT
+	.short	IMAGE_FILE_MACHINE_RISCV64		// Machine
+#else
+	.short	IMAGE_FILE_MACHINE_RISCV32		// Machine
+#endif
+	.short	section_count				// NumberOfSections
+	.long	0 					// TimeDateStamp
+	.long	0					// PointerToSymbolTable
+	.long	0					// NumberOfSymbols
+	.short	section_table - optional_header		// SizeOfOptionalHeader
+	.short	IMAGE_FILE_DEBUG_STRIPPED | \
+		IMAGE_FILE_EXECUTABLE_IMAGE | \
+		IMAGE_FILE_LINE_NUMS_STRIPPED		// Characteristics
+
+optional_header:
+#ifdef CONFIG_64BIT
+	.short	PE_OPT_MAGIC_PE32PLUS			// PE32+ format
+#else
+	.short	PE_OPT_MAGIC_PE32			// PE32 format
+#endif
+	.byte	0x02					// MajorLinkerVersion
+	.byte	0x14					// MinorLinkerVersion
+	.long	__pecoff_text_end - efi_header_end	// SizeOfCode
+	.long	__pecoff_data_virt_size			// SizeOfInitializedData
+	.long	0					// SizeOfUninitializedData
+	.long	__efistub_efi_pe_entry - _start		// AddressOfEntryPoint
+	.long	efi_header_end - _start			// BaseOfCode
+#ifdef CONFIG_32BIT
+	.long  __pecoff_text_end - _start		// BaseOfData
+#endif
+
+extra_header_fields:
+	.quad	0					// ImageBase
+	.long	PECOFF_SECTION_ALIGNMENT		// SectionAlignment
+	.long	PECOFF_FILE_ALIGNMENT			// FileAlignment
+	.short	0					// MajorOperatingSystemVersion
+	.short	0					// MinorOperatingSystemVersion
+	.short	LINUX_EFISTUB_MAJOR_VERSION		// MajorImageVersion
+	.short	LINUX_EFISTUB_MINOR_VERSION		// MinorImageVersion
+	.short	0					// MajorSubsystemVersion
+	.short	0					// MinorSubsystemVersion
+	.long	0					// Win32VersionValue
+
+	.long	_end - _start				// SizeOfImage
+
+	// Everything before the kernel image is considered part of the header
+	.long	efi_header_end - _start			// SizeOfHeaders
+	.long	0					// CheckSum
+	.short	IMAGE_SUBSYSTEM_EFI_APPLICATION		// Subsystem
+	.short	0					// DllCharacteristics
+	.quad	0					// SizeOfStackReserve
+	.quad	0					// SizeOfStackCommit
+	.quad	0					// SizeOfHeapReserve
+	.quad	0					// SizeOfHeapCommit
+	.long	0					// LoaderFlags
+	.long	(section_table - .) / 8			// NumberOfRvaAndSizes
+
+	.quad	0					// ExportTable
+	.quad	0					// ImportTable
+	.quad	0					// ResourceTable
+	.quad	0					// ExceptionTable
+	.quad	0					// CertificationTable
+	.quad	0					// BaseRelocationTable
+
+	// Section table
+section_table:
+	.ascii	".text\0\0\0"
+	.long	__pecoff_text_end - efi_header_end	// VirtualSize
+	.long	efi_header_end - _start			// VirtualAddress
+	.long	__pecoff_text_end - efi_header_end	// SizeOfRawData
+	.long	efi_header_end - _start			// PointerToRawData
+
+	.long	0					// PointerToRelocations
+	.long	0					// PointerToLineNumbers
+	.short	0					// NumberOfRelocations
+	.short	0					// NumberOfLineNumbers
+	.long	IMAGE_SCN_CNT_CODE | \
+		IMAGE_SCN_MEM_READ | \
+		IMAGE_SCN_MEM_EXECUTE			// Characteristics
+
+	.ascii	".data\0\0\0"
+	.long	__pecoff_data_virt_size			// VirtualSize
+	.long	__pecoff_text_end - _start		// VirtualAddress
+	.long	__pecoff_data_raw_size			// SizeOfRawData
+	.long	__pecoff_text_end - _start		// PointerToRawData
+
+	.long	0					// PointerToRelocations
+	.long	0					// PointerToLineNumbers
+	.short	0					// NumberOfRelocations
+	.short	0					// NumberOfLineNumbers
+	.long	IMAGE_SCN_CNT_INITIALIZED_DATA | \
+		IMAGE_SCN_MEM_READ | \
+		IMAGE_SCN_MEM_WRITE			// Characteristics
+
+	.set	section_count, (. - section_table) / 40
+
+	.balign	0x1000
+efi_header_end:
+	.endm
diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c
new file mode 100644
index 000000000..1aa540350
--- /dev/null
+++ b/arch/riscv/kernel/efi.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Adapted from arch/arm64/kernel/efi.c
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+
+#include <asm/efi.h>
+#include <asm/pgtable.h>
+#include <asm/pgtable-bits.h>
+
+/*
+ * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
+ * executable, everything else can be mapped with the XN bits
+ * set. Also take the new (optional) RO/XP bits into account.
+ */
+static __init pgprot_t efimem_to_pgprot_map(efi_memory_desc_t *md)
+{
+	u64 attr = md->attribute;
+	u32 type = md->type;
+
+	if (type == EFI_MEMORY_MAPPED_IO)
+		return PAGE_KERNEL;
+
+	/* R-- */
+	if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) ==
+	    (EFI_MEMORY_XP | EFI_MEMORY_RO))
+		return PAGE_KERNEL_READ;
+
+	/* R-X */
+	if (attr & EFI_MEMORY_RO)
+		return PAGE_KERNEL_READ_EXEC;
+
+	/* RW- */
+	if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) ==
+	     EFI_MEMORY_XP) ||
+	    type != EFI_RUNTIME_SERVICES_CODE)
+		return PAGE_KERNEL;
+
+	/* RWX */
+	return PAGE_KERNEL_EXEC;
+}
+
+int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+	pgprot_t prot = __pgprot(pgprot_val(efimem_to_pgprot_map(md)) &
+				~(_PAGE_GLOBAL));
+	int i;
+
+	/* RISC-V maps one page at a time */
+	for (i = 0; i < md->num_pages; i++)
+		create_pgd_mapping(mm->pgd, md->virt_addr + i * PAGE_SIZE,
+				   md->phys_addr + i * PAGE_SIZE,
+				   PAGE_SIZE, prot);
+	return 0;
+}
+
+static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
+{
+	efi_memory_desc_t *md = data;
+	pte_t pte = READ_ONCE(*ptep);
+	unsigned long val;
+
+	if (md->attribute & EFI_MEMORY_RO) {
+		val = pte_val(pte) & ~_PAGE_WRITE;
+		val |= _PAGE_READ;
+		pte = __pte(val);
+	}
+	if (md->attribute & EFI_MEMORY_XP) {
+		val = pte_val(pte) & ~_PAGE_EXEC;
+		pte = __pte(val);
+	}
+	set_pte(ptep, pte);
+
+	return 0;
+}
+
+int __init efi_set_mapping_permissions(struct mm_struct *mm,
+				       efi_memory_desc_t *md)
+{
+	BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE &&
+	       md->type != EFI_RUNTIME_SERVICES_DATA);
+
+	/*
+	 * Calling apply_to_page_range() is only safe on regions that are
+	 * guaranteed to be mapped down to pages. Since we are only called
+	 * for regions that have been mapped using efi_create_mapping() above
+	 * (and this is checked by the generic Memory Attributes table parsing
+	 * routines), there is no need to check that again here.
+	 */
+	return apply_to_page_range(mm, md->virt_addr,
+				   md->num_pages << EFI_PAGE_SHIFT,
+				   set_permissions, md);
+}
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
new file mode 100644
index 000000000..5214c578a
--- /dev/null
+++ b/arch/riscv/kernel/entry.S
@@ -0,0 +1,477 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+
+#if !IS_ENABLED(CONFIG_PREEMPTION)
+.set resume_kernel, restore_all
+#endif
+
+ENTRY(handle_exception)
+	/*
+	 * If coming from userspace, preserve the user thread pointer and load
+	 * the kernel thread pointer.  If we came from the kernel, the scratch
+	 * register will contain 0, and we should continue on the current TP.
+	 */
+	csrrw tp, CSR_SCRATCH, tp
+	bnez tp, _save_context
+
+_restore_kernel_tpsp:
+	csrr tp, CSR_SCRATCH
+	REG_S sp, TASK_TI_KERNEL_SP(tp)
+_save_context:
+	REG_S sp, TASK_TI_USER_SP(tp)
+	REG_L sp, TASK_TI_KERNEL_SP(tp)
+	addi sp, sp, -(PT_SIZE_ON_STACK)
+	REG_S x1,  PT_RA(sp)
+	REG_S x3,  PT_GP(sp)
+	REG_S x5,  PT_T0(sp)
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+
+	/*
+	 * 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.
+	 */
+	li t0, SR_SUM | SR_FS
+
+	REG_L s0, TASK_TI_USER_SP(tp)
+	csrrc s1, CSR_STATUS, t0
+	csrr s2, CSR_EPC
+	csrr s3, CSR_TVAL
+	csrr s4, CSR_CAUSE
+	csrr s5, CSR_SCRATCH
+	REG_S s0, PT_SP(sp)
+	REG_S s1, PT_STATUS(sp)
+	REG_S s2, PT_EPC(sp)
+	REG_S s3, PT_BADADDR(sp)
+	REG_S s4, PT_CAUSE(sp)
+	REG_S s5, PT_TP(sp)
+
+	/*
+	 * Set the scratch register to 0, so that if a recursive exception
+	 * occurs, the exception vector knows it came from the kernel
+	 */
+	csrw CSR_SCRATCH, x0
+
+	/* Load the global pointer */
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call __trace_hardirqs_off
+#endif
+
+#ifdef CONFIG_CONTEXT_TRACKING
+	/* If previous state is in user mode, call context_tracking_user_exit. */
+	li   a0, SR_PP
+	and a0, s1, a0
+	bnez a0, skip_context_tracking
+	call context_tracking_user_exit
+skip_context_tracking:
+#endif
+
+	/*
+	 * MSB of cause differentiates between
+	 * interrupts and exceptions
+	 */
+	bge s4, zero, 1f
+
+	la ra, ret_from_exception
+
+	/* Handle interrupts */
+	move a0, sp /* pt_regs */
+	la a1, handle_arch_irq
+	REG_L a1, (a1)
+	jr a1
+1:
+	/*
+	 * Exceptions run with interrupts enabled or disabled depending on the
+	 * state of SR_PIE in m/sstatus.
+	 */
+	andi t0, s1, SR_PIE
+	beqz t0, 1f
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call __trace_hardirqs_on
+#endif
+	csrs CSR_STATUS, SR_IE
+
+1:
+	la ra, ret_from_exception
+	/* Handle syscalls */
+	li t0, EXC_SYSCALL
+	beq s4, t0, handle_syscall
+
+	/* Handle other exceptions */
+	slli t0, s4, RISCV_LGPTR
+	la t1, excp_vect_table
+	la t2, excp_vect_table_end
+	move a0, sp /* pt_regs */
+	add t0, t1, t0
+	/* Check if exception code lies within bounds */
+	bgeu t0, t2, 1f
+	REG_L t0, 0(t0)
+	jr t0
+1:
+	tail do_trap_unknown
+
+handle_syscall:
+#ifdef CONFIG_RISCV_M_MODE
+	/*
+	 * When running is M-Mode (no MMU config), MPIE does not get set.
+	 * As a result, we need to force enable interrupts here because
+	 * handle_exception did not do set SR_IE as it always sees SR_PIE
+	 * being cleared.
+	 */
+	csrs CSR_STATUS, SR_IE
+#endif
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
+	/* Recover a0 - a7 for system calls */
+	REG_L a0, PT_A0(sp)
+	REG_L a1, PT_A1(sp)
+	REG_L a2, PT_A2(sp)
+	REG_L a3, PT_A3(sp)
+	REG_L a4, PT_A4(sp)
+	REG_L a5, PT_A5(sp)
+	REG_L a6, PT_A6(sp)
+	REG_L a7, PT_A7(sp)
+#endif
+	 /* save the initial A0 value (needed in signal handlers) */
+	REG_S a0, PT_ORIG_A0(sp)
+	/*
+	 * Advance SEPC to avoid executing the original
+	 * scall instruction on sret
+	 */
+	addi s2, s2, 0x4
+	REG_S s2, PT_EPC(sp)
+	/* Trace syscalls, but only if requested by the user. */
+	REG_L t0, TASK_TI_FLAGS(tp)
+	andi t0, t0, _TIF_SYSCALL_WORK
+	bnez t0, handle_syscall_trace_enter
+check_syscall_nr:
+	/* Check to make sure we don't jump to a bogus syscall number. */
+	li t0, __NR_syscalls
+	la s0, sys_ni_syscall
+	/*
+	 * Syscall number held in a7.
+	 * If syscall number is above allowed value, redirect to ni_syscall.
+	 */
+	bgeu a7, t0, 1f
+	/* Call syscall */
+	la s0, sys_call_table
+	slli t0, a7, RISCV_LGPTR
+	add s0, s0, t0
+	REG_L s0, 0(s0)
+1:
+	jalr s0
+
+ret_from_syscall:
+	/* Set user a0 to kernel a0 */
+	REG_S a0, PT_A0(sp)
+	/*
+	 * We didn't execute the actual syscall.
+	 * Seccomp already set return value for the current task pt_regs.
+	 * (If it was configured with SECCOMP_RET_ERRNO/TRACE)
+	 */
+ret_from_syscall_rejected:
+	/* Trace syscalls, but only if requested by the user. */
+	REG_L t0, TASK_TI_FLAGS(tp)
+	andi t0, t0, _TIF_SYSCALL_WORK
+	bnez t0, handle_syscall_trace_exit
+
+ret_from_exception:
+	REG_L s0, PT_STATUS(sp)
+	csrc CSR_STATUS, SR_IE
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call __trace_hardirqs_off
+#endif
+#ifdef CONFIG_RISCV_M_MODE
+	/* the MPP value is too large to be used as an immediate arg for addi */
+	li t0, SR_MPP
+	and s0, s0, t0
+#else
+	andi s0, s0, SR_SPP
+#endif
+	bnez s0, resume_kernel
+
+resume_userspace:
+	/* Interrupts must be disabled here so flags are checked atomically */
+	REG_L s0, TASK_TI_FLAGS(tp) /* current_thread_info->flags */
+	andi s1, s0, _TIF_WORK_MASK
+	bnez s1, work_pending
+
+#ifdef CONFIG_CONTEXT_TRACKING
+	call context_tracking_user_enter
+#endif
+
+	/* Save unwound kernel stack pointer in thread_info */
+	addi s0, sp, PT_SIZE_ON_STACK
+	REG_S s0, TASK_TI_KERNEL_SP(tp)
+
+	/*
+	 * Save TP into the scratch register , so we can find the kernel data
+	 * structures again.
+	 */
+	csrw CSR_SCRATCH, tp
+
+restore_all:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	REG_L s1, PT_STATUS(sp)
+	andi t0, s1, SR_PIE
+	beqz t0, 1f
+	call __trace_hardirqs_on
+	j 2f
+1:
+	call __trace_hardirqs_off
+2:
+#endif
+	REG_L a0, PT_STATUS(sp)
+	/*
+	 * The current load reservation is effectively part of the processor's
+	 * state, in the sense that load reservations cannot be shared between
+	 * different hart contexts.  We can't actually save and restore a load
+	 * reservation, so instead here we clear any existing reservation --
+	 * it's always legal for implementations to clear load reservations at
+	 * any point (as long as the forward progress guarantee is kept, but
+	 * we'll ignore that here).
+	 *
+	 * Dangling load reservations can be the result of taking a trap in the
+	 * middle of an LR/SC sequence, but can also be the result of a taken
+	 * forward branch around an SC -- which is how we implement CAS.  As a
+	 * result we need to clear reservations between the last CAS and the
+	 * jump back to the new context.  While it is unlikely the store
+	 * completes, implementations are allowed to expand reservations to be
+	 * arbitrarily large.
+	 */
+	REG_L  a2, PT_EPC(sp)
+	REG_SC x0, a2, PT_EPC(sp)
+
+	csrw CSR_STATUS, a0
+	csrw CSR_EPC, a2
+
+	REG_L x1,  PT_RA(sp)
+	REG_L x3,  PT_GP(sp)
+	REG_L x4,  PT_TP(sp)
+	REG_L x5,  PT_T0(sp)
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
+
+	REG_L x2,  PT_SP(sp)
+
+#ifdef CONFIG_RISCV_M_MODE
+	mret
+#else
+	sret
+#endif
+
+#if IS_ENABLED(CONFIG_PREEMPTION)
+resume_kernel:
+	REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
+	bnez s0, restore_all
+	REG_L s0, TASK_TI_FLAGS(tp)
+	andi s0, s0, _TIF_NEED_RESCHED
+	beqz s0, restore_all
+	call preempt_schedule_irq
+	j restore_all
+#endif
+
+work_pending:
+	/* Enter slow path for supplementary processing */
+	la ra, ret_from_exception
+	andi s1, s0, _TIF_NEED_RESCHED
+	bnez s1, work_resched
+work_notifysig:
+	/* Handle pending signals and notify-resume requests */
+	csrs CSR_STATUS, SR_IE /* Enable interrupts for do_notify_resume() */
+	move a0, sp /* pt_regs */
+	move a1, s0 /* current_thread_info->flags */
+	tail do_notify_resume
+work_resched:
+	tail schedule
+
+/* Slow paths for ptrace. */
+handle_syscall_trace_enter:
+	move a0, sp
+	call do_syscall_trace_enter
+	move t0, a0
+	REG_L a0, PT_A0(sp)
+	REG_L a1, PT_A1(sp)
+	REG_L a2, PT_A2(sp)
+	REG_L a3, PT_A3(sp)
+	REG_L a4, PT_A4(sp)
+	REG_L a5, PT_A5(sp)
+	REG_L a6, PT_A6(sp)
+	REG_L a7, PT_A7(sp)
+	bnez t0, ret_from_syscall_rejected
+	j check_syscall_nr
+handle_syscall_trace_exit:
+	move a0, sp
+	call do_syscall_trace_exit
+	j ret_from_exception
+
+END(handle_exception)
+
+ENTRY(ret_from_fork)
+	la ra, ret_from_exception
+	tail schedule_tail
+ENDPROC(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+	call schedule_tail
+	/* Call fn(arg) */
+	la ra, ret_from_exception
+	move a0, s1
+	jr s0
+ENDPROC(ret_from_kernel_thread)
+
+
+/*
+ * Integer register context switch
+ * The callee-saved registers must be saved and restored.
+ *
+ *   a0: previous task_struct (must be preserved across the switch)
+ *   a1: next task_struct
+ *
+ * The value of a0 and a1 must be preserved by this function, as that's how
+ * arguments are passed to schedule_tail.
+ */
+ENTRY(__switch_to)
+	/* Save context into prev->thread */
+	li    a4,  TASK_THREAD_RA
+	add   a3, a0, a4
+	add   a4, a1, a4
+	REG_S ra,  TASK_THREAD_RA_RA(a3)
+	REG_S sp,  TASK_THREAD_SP_RA(a3)
+	REG_S s0,  TASK_THREAD_S0_RA(a3)
+	REG_S s1,  TASK_THREAD_S1_RA(a3)
+	REG_S s2,  TASK_THREAD_S2_RA(a3)
+	REG_S s3,  TASK_THREAD_S3_RA(a3)
+	REG_S s4,  TASK_THREAD_S4_RA(a3)
+	REG_S s5,  TASK_THREAD_S5_RA(a3)
+	REG_S s6,  TASK_THREAD_S6_RA(a3)
+	REG_S s7,  TASK_THREAD_S7_RA(a3)
+	REG_S s8,  TASK_THREAD_S8_RA(a3)
+	REG_S s9,  TASK_THREAD_S9_RA(a3)
+	REG_S s10, TASK_THREAD_S10_RA(a3)
+	REG_S s11, TASK_THREAD_S11_RA(a3)
+	/* Restore context from next->thread */
+	REG_L ra,  TASK_THREAD_RA_RA(a4)
+	REG_L sp,  TASK_THREAD_SP_RA(a4)
+	REG_L s0,  TASK_THREAD_S0_RA(a4)
+	REG_L s1,  TASK_THREAD_S1_RA(a4)
+	REG_L s2,  TASK_THREAD_S2_RA(a4)
+	REG_L s3,  TASK_THREAD_S3_RA(a4)
+	REG_L s4,  TASK_THREAD_S4_RA(a4)
+	REG_L s5,  TASK_THREAD_S5_RA(a4)
+	REG_L s6,  TASK_THREAD_S6_RA(a4)
+	REG_L s7,  TASK_THREAD_S7_RA(a4)
+	REG_L s8,  TASK_THREAD_S8_RA(a4)
+	REG_L s9,  TASK_THREAD_S9_RA(a4)
+	REG_L s10, TASK_THREAD_S10_RA(a4)
+	REG_L s11, TASK_THREAD_S11_RA(a4)
+	/* Swap the CPU entry around. */
+	lw a3, TASK_TI_CPU(a0)
+	lw a4, TASK_TI_CPU(a1)
+	sw a3, TASK_TI_CPU(a1)
+	sw a4, TASK_TI_CPU(a0)
+	/* The offset of thread_info in task_struct is zero. */
+	move tp, a1
+	ret
+ENDPROC(__switch_to)
+
+#ifndef CONFIG_MMU
+#define do_page_fault do_trap_unknown
+#endif
+
+	.section ".rodata"
+	.align LGREG
+	/* Exception vector table */
+ENTRY(excp_vect_table)
+	RISCV_PTR do_trap_insn_misaligned
+	RISCV_PTR do_trap_insn_fault
+	RISCV_PTR do_trap_insn_illegal
+	RISCV_PTR do_trap_break
+	RISCV_PTR do_trap_load_misaligned
+	RISCV_PTR do_trap_load_fault
+	RISCV_PTR do_trap_store_misaligned
+	RISCV_PTR do_trap_store_fault
+	RISCV_PTR do_trap_ecall_u /* system call, gets intercepted */
+	RISCV_PTR do_trap_ecall_s
+	RISCV_PTR do_trap_unknown
+	RISCV_PTR do_trap_ecall_m
+	RISCV_PTR do_page_fault   /* instruction page fault */
+	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:
+END(excp_vect_table)
+
+#ifndef CONFIG_MMU
+ENTRY(__user_rt_sigreturn)
+	li a7, __NR_rt_sigreturn
+	scall
+END(__user_rt_sigreturn)
+#endif
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
new file mode 100644
index 000000000..dd2205473
--- /dev/null
+++ b/arch/riscv/kernel/fpu.S
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ *
+ *   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>
+
+ENTRY(__fstate_save)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	csrs CSR_STATUS, t1
+	frcsr t0
+	fsd f0,  TASK_THREAD_F0_F0(a0)
+	fsd f1,  TASK_THREAD_F1_F0(a0)
+	fsd f2,  TASK_THREAD_F2_F0(a0)
+	fsd f3,  TASK_THREAD_F3_F0(a0)
+	fsd f4,  TASK_THREAD_F4_F0(a0)
+	fsd f5,  TASK_THREAD_F5_F0(a0)
+	fsd f6,  TASK_THREAD_F6_F0(a0)
+	fsd f7,  TASK_THREAD_F7_F0(a0)
+	fsd f8,  TASK_THREAD_F8_F0(a0)
+	fsd f9,  TASK_THREAD_F9_F0(a0)
+	fsd f10, TASK_THREAD_F10_F0(a0)
+	fsd f11, TASK_THREAD_F11_F0(a0)
+	fsd f12, TASK_THREAD_F12_F0(a0)
+	fsd f13, TASK_THREAD_F13_F0(a0)
+	fsd f14, TASK_THREAD_F14_F0(a0)
+	fsd f15, TASK_THREAD_F15_F0(a0)
+	fsd f16, TASK_THREAD_F16_F0(a0)
+	fsd f17, TASK_THREAD_F17_F0(a0)
+	fsd f18, TASK_THREAD_F18_F0(a0)
+	fsd f19, TASK_THREAD_F19_F0(a0)
+	fsd f20, TASK_THREAD_F20_F0(a0)
+	fsd f21, TASK_THREAD_F21_F0(a0)
+	fsd f22, TASK_THREAD_F22_F0(a0)
+	fsd f23, TASK_THREAD_F23_F0(a0)
+	fsd f24, TASK_THREAD_F24_F0(a0)
+	fsd f25, TASK_THREAD_F25_F0(a0)
+	fsd f26, TASK_THREAD_F26_F0(a0)
+	fsd f27, TASK_THREAD_F27_F0(a0)
+	fsd f28, TASK_THREAD_F28_F0(a0)
+	fsd f29, TASK_THREAD_F29_F0(a0)
+	fsd f30, TASK_THREAD_F30_F0(a0)
+	fsd f31, TASK_THREAD_F31_F0(a0)
+	sw t0, TASK_THREAD_FCSR_F0(a0)
+	csrc CSR_STATUS, t1
+	ret
+ENDPROC(__fstate_save)
+
+ENTRY(__fstate_restore)
+	li  a2,  TASK_THREAD_F0
+	add a0, a0, a2
+	li t1, SR_FS
+	lw t0, TASK_THREAD_FCSR_F0(a0)
+	csrs CSR_STATUS, t1
+	fld f0,  TASK_THREAD_F0_F0(a0)
+	fld f1,  TASK_THREAD_F1_F0(a0)
+	fld f2,  TASK_THREAD_F2_F0(a0)
+	fld f3,  TASK_THREAD_F3_F0(a0)
+	fld f4,  TASK_THREAD_F4_F0(a0)
+	fld f5,  TASK_THREAD_F5_F0(a0)
+	fld f6,  TASK_THREAD_F6_F0(a0)
+	fld f7,  TASK_THREAD_F7_F0(a0)
+	fld f8,  TASK_THREAD_F8_F0(a0)
+	fld f9,  TASK_THREAD_F9_F0(a0)
+	fld f10, TASK_THREAD_F10_F0(a0)
+	fld f11, TASK_THREAD_F11_F0(a0)
+	fld f12, TASK_THREAD_F12_F0(a0)
+	fld f13, TASK_THREAD_F13_F0(a0)
+	fld f14, TASK_THREAD_F14_F0(a0)
+	fld f15, TASK_THREAD_F15_F0(a0)
+	fld f16, TASK_THREAD_F16_F0(a0)
+	fld f17, TASK_THREAD_F17_F0(a0)
+	fld f18, TASK_THREAD_F18_F0(a0)
+	fld f19, TASK_THREAD_F19_F0(a0)
+	fld f20, TASK_THREAD_F20_F0(a0)
+	fld f21, TASK_THREAD_F21_F0(a0)
+	fld f22, TASK_THREAD_F22_F0(a0)
+	fld f23, TASK_THREAD_F23_F0(a0)
+	fld f24, TASK_THREAD_F24_F0(a0)
+	fld f25, TASK_THREAD_F25_F0(a0)
+	fld f26, TASK_THREAD_F26_F0(a0)
+	fld f27, TASK_THREAD_F27_F0(a0)
+	fld f28, TASK_THREAD_F28_F0(a0)
+	fld f29, TASK_THREAD_F29_F0(a0)
+	fld f30, TASK_THREAD_F30_F0(a0)
+	fld f31, TASK_THREAD_F31_F0(a0)
+	fscsr t0
+	csrc CSR_STATUS, t1
+	ret
+ENDPROC(__fstate_restore)
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
new file mode 100644
index 000000000..8693dfcff
--- /dev/null
+++ b/arch/riscv/kernel/ftrace.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ * Copyright (C) 2017 Andes Technology Corporation
+ */
+
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <linux/memory.h>
+#include <asm/cacheflush.h>
+#include <asm/patch.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
+{
+	mutex_lock(&text_mutex);
+
+	/*
+	 * The code sequences we use for ftrace can't be patched while the
+	 * kernel is running, so we need to use stop_machine() to modify them
+	 * for now.  This doesn't play nice with text_mutex, we use this flag
+	 * to elide the check.
+	 */
+	riscv_patch_in_stop_machine = true;
+
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
+{
+	riscv_patch_in_stop_machine = false;
+	mutex_unlock(&text_mutex);
+	return 0;
+}
+
+static int ftrace_check_current_call(unsigned long hook_pos,
+				     unsigned int *expected)
+{
+	unsigned int replaced[2];
+	unsigned int nops[2] = {NOP4, NOP4};
+
+	/* we expect nops at the hook position */
+	if (!expected)
+		expected = nops;
+
+	/*
+	 * Read the text we want to modify;
+	 * return must be -EFAULT on read error
+	 */
+	if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
+			MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/*
+	 * Make sure it is what we expect it to be;
+	 * return must be -EINVAL on failed comparison
+	 */
+	if (memcmp(expected, replaced, sizeof(replaced))) {
+		pr_err("%p: expected (%08x %08x) but got (%08x %08x)\n",
+		       (void *)hook_pos, expected[0], expected[1], replaced[0],
+		       replaced[1]);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
+				bool enable)
+{
+	unsigned int call[2];
+	unsigned int nops[2] = {NOP4, NOP4};
+
+	make_call(hook_pos, target, call);
+
+	/* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
+	if (patch_text_nosync
+	    ((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	int ret = ftrace_check_current_call(rec->ip, NULL);
+
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call(rec->ip, addr, true);
+}
+
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	unsigned int call[2];
+	int ret;
+
+	make_call(rec->ip, addr, call);
+	ret = ftrace_check_current_call(rec->ip, call);
+
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call(rec->ip, addr, false);
+}
+
+
+/*
+ * This is called early on, and isn't wrapped by
+ * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold
+ * text_mutex, which triggers a lockdep failure.  SMP isn't running so we could
+ * just directly poke the text, but it's simpler to just take the lock
+ * ourselves.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	int out;
+
+	mutex_lock(&text_mutex);
+	out = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+	mutex_unlock(&text_mutex);
+
+	return out;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	int ret = __ftrace_modify_call((unsigned long)&ftrace_call,
+				       (unsigned long)func, true);
+	if (!ret) {
+		ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call,
+					   (unsigned long)func, true);
+	}
+
+	return ret;
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	unsigned int call[2];
+	int ret;
+
+	make_call(rec->ip, old_addr, call);
+	ret = ftrace_check_current_call(rec->ip, call);
+
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call(rec->ip, addr, true);
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * Most of this function is copied from arm64.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * We don't suffer access faults, so no extra fault-recovery assembly
+	 * is needed here.
+	 */
+	old = *parent;
+
+	if (!function_graph_enter(old, self_addr, frame_pointer, parent))
+		*parent = return_hooker;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	unsigned int call[2];
+	static int init_graph = 1;
+	int ret;
+
+	make_call(&ftrace_graph_call, &ftrace_stub, call);
+
+	/*
+	 * When enabling graph tracer for the first time, ftrace_graph_call
+	 * should contains a call to ftrace_stub.  Once it has been disabled,
+	 * the 8-bytes at the position becomes NOPs.
+	 */
+	if (init_graph) {
+		ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call,
+						call);
+		init_graph = 0;
+	} else {
+		ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call,
+						NULL);
+	}
+
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+				    (unsigned long)&prepare_ftrace_return, true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	unsigned int call[2];
+	int ret;
+
+	make_call(&ftrace_graph_call, &prepare_ftrace_return, call);
+
+	/*
+	 * This is to make sure that ftrace_enable_ftrace_graph_caller
+	 * did the right thing.
+	 */
+	ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call,
+					call);
+
+	if (ret)
+		return ret;
+
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
+				    (unsigned long)&prepare_ftrace_return, false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
new file mode 100644
index 000000000..47d1411db
--- /dev/null
+++ b/arch/riscv/kernel/head.S
@@ -0,0 +1,396 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/image.h>
+#include "efi-header.S"
+
+__HEAD
+ENTRY(_start)
+	/*
+	 * Image header expected by Linux boot-loaders. The image header data
+	 * structure is described in asm/image.h.
+	 * Do not modify it without modifying the structure and all bootloaders
+	 * that expects this header format!!
+	 */
+#ifdef CONFIG_EFI
+	/*
+	 * This instruction decodes to "MZ" ASCII required by UEFI.
+	 */
+	c.li s4,-13
+	j _start_kernel
+#else
+	/* jump to start kernel */
+	j _start_kernel
+	/* reserved */
+	.word 0
+#endif
+	.balign 8
+#ifdef CONFIG_RISCV_M_MODE
+	/* Image load offset (0MB) from start of RAM for M-mode */
+	.dword 0
+#else
+#if __riscv_xlen == 64
+	/* Image load offset(2MB) from start of RAM */
+	.dword 0x200000
+#else
+	/* Image load offset(4MB) from start of RAM */
+	.dword 0x400000
+#endif
+#endif
+	/* Effective size of kernel image */
+	.dword _end - _start
+	.dword __HEAD_FLAGS
+	.word RISCV_HEADER_VERSION
+	.word 0
+	.dword 0
+	.ascii RISCV_IMAGE_MAGIC
+	.balign 4
+	.ascii RISCV_IMAGE_MAGIC2
+#ifdef CONFIG_EFI
+	.word pe_head_start - _start
+pe_head_start:
+
+	__EFI_PE_HEADER
+#else
+	.word 0
+#endif
+
+.align 2
+#ifdef CONFIG_MMU
+relocate:
+	/* Relocate return address */
+	li a1, PAGE_OFFSET
+	la a2, _start
+	sub a1, a1, a2
+	add ra, ra, a1
+
+	/* Point stvec to virtual address of intruction after satp write */
+	la a2, 1f
+	add a2, a2, a1
+	csrw CSR_TVEC, a2
+
+	/* Compute satp for kernel page tables, but don't load it yet */
+	srl a2, a0, PAGE_SHIFT
+	li a1, SATP_MODE
+	or a2, a2, a1
+
+	/*
+	 * Load trampoline page directory, which will cause us to trap to
+	 * stvec if VA != PA, or simply fall through if VA == PA.  We need a
+	 * full fence here because setup_vm() just wrote these PTEs and we need
+	 * to ensure the new translations are in use.
+	 */
+	la a0, trampoline_pg_dir
+	srl a0, a0, PAGE_SHIFT
+	or a0, a0, a1
+	sfence.vma
+	csrw CSR_SATP, a0
+.align 2
+1:
+	/* Set trap vector to spin forever to help debug */
+	la a0, .Lsecondary_park
+	csrw CSR_TVEC, a0
+
+	/* Reload the global pointer */
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+
+	/*
+	 * Switch to kernel page tables.  A full fence is necessary in order to
+	 * avoid using the trampoline translations, which are only correct for
+	 * the first superpage.  Fetching the fence is guarnteed to work
+	 * because that first superpage is translated the same way.
+	 */
+	csrw CSR_SATP, a2
+	sfence.vma
+
+	ret
+#endif /* CONFIG_MMU */
+#ifdef CONFIG_SMP
+	.global secondary_start_sbi
+secondary_start_sbi:
+	/* Mask all interrupts */
+	csrw CSR_IE, zero
+	csrw CSR_IP, zero
+
+	/* Load the global pointer */
+	.option push
+	.option norelax
+		la gp, __global_pointer$
+	.option pop
+
+	/*
+	 * Disable FPU to detect illegal usage of
+	 * floating point in kernel space
+	 */
+	li t0, SR_FS
+	csrc CSR_STATUS, t0
+
+	/* Set trap vector to spin forever to help debug */
+	la a3, .Lsecondary_park
+	csrw CSR_TVEC, a3
+
+	slli a3, a0, LGREG
+	la a4, __cpu_up_stack_pointer
+	la a5, __cpu_up_task_pointer
+	add a4, a3, a4
+	add a5, a3, a5
+	REG_L sp, (a4)
+	REG_L tp, (a5)
+
+	.global secondary_start_common
+secondary_start_common:
+
+#ifdef CONFIG_MMU
+	/* Enable virtual memory and relocate to virtual address */
+	la a0, swapper_pg_dir
+	call relocate
+#endif
+	call setup_trap_vector
+	tail smp_callin
+#endif /* CONFIG_SMP */
+
+.align 2
+setup_trap_vector:
+	/* Set trap vector to exception handler */
+	la a0, handle_exception
+	csrw CSR_TVEC, a0
+
+	/*
+	 * Set sup0 scratch register to 0, indicating to exception vector that
+	 * we are presently executing in kernel.
+	 */
+	csrw CSR_SCRATCH, zero
+	ret
+
+.align 2
+.Lsecondary_park:
+	/* We lack SMP support or have too many harts, so park this hart */
+	wfi
+	j .Lsecondary_park
+
+END(_start)
+
+	__INIT
+ENTRY(_start_kernel)
+	/* Mask all interrupts */
+	csrw CSR_IE, zero
+	csrw CSR_IP, zero
+
+#ifdef CONFIG_RISCV_M_MODE
+	/* flush the instruction cache */
+	fence.i
+
+	/* Reset all registers except ra, a0, a1 */
+	call reset_regs
+
+	/*
+	 * Setup a PMP to permit access to all of memory.  Some machines may
+	 * not implement PMPs, so we set up a quick trap handler to just skip
+	 * touching the PMPs on any trap.
+	 */
+	la a0, pmp_done
+	csrw CSR_TVEC, a0
+
+	li a0, -1
+	csrw CSR_PMPADDR0, a0
+	li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X)
+	csrw CSR_PMPCFG0, a0
+.align 2
+pmp_done:
+
+	/*
+	 * The hartid in a0 is expected later on, and we have no firmware
+	 * to hand it to us.
+	 */
+	csrr a0, CSR_MHARTID
+#endif /* CONFIG_RISCV_M_MODE */
+
+	/* Load the global pointer */
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+
+	/*
+	 * Disable FPU to detect illegal usage of
+	 * floating point in kernel space
+	 */
+	li t0, SR_FS
+	csrc CSR_STATUS, t0
+
+#ifdef CONFIG_SMP
+	li t0, CONFIG_NR_CPUS
+	blt a0, t0, .Lgood_cores
+	tail .Lsecondary_park
+.Lgood_cores:
+#endif
+
+	/* Pick one hart to run the main boot sequence */
+	la a3, hart_lottery
+	li a2, 1
+	amoadd.w a3, a2, (a3)
+	bnez a3, .Lsecondary_start
+
+	/* Clear BSS for flat non-ELF images */
+	la a3, __bss_start
+	la a4, __bss_stop
+	ble a4, a3, clear_bss_done
+clear_bss:
+	REG_S zero, (a3)
+	add a3, a3, RISCV_SZPTR
+	blt a3, a4, clear_bss
+clear_bss_done:
+
+	/* Save hart ID and DTB physical address */
+	mv s0, a0
+	mv s1, a1
+	la a2, boot_cpu_hartid
+	REG_S a0, (a2)
+
+	/* Initialize page tables and relocate to virtual addresses */
+	la tp, init_task
+	la sp, init_thread_union + THREAD_SIZE
+	mv a0, s1
+	call setup_vm
+#ifdef CONFIG_MMU
+	la a0, early_pg_dir
+	call relocate
+#endif /* CONFIG_MMU */
+
+	call setup_trap_vector
+	/* Restore C environment */
+	la tp, init_task
+	sw zero, TASK_TI_CPU(tp)
+	la sp, init_thread_union + THREAD_SIZE
+
+#ifdef CONFIG_KASAN
+	call kasan_early_init
+#endif
+	/* Start the kernel */
+	call soc_early_init
+	tail start_kernel
+
+.Lsecondary_start:
+#ifdef CONFIG_SMP
+	/* Set trap vector to spin forever to help debug */
+	la a3, .Lsecondary_park
+	csrw CSR_TVEC, a3
+
+	slli a3, a0, LGREG
+	la a1, __cpu_up_stack_pointer
+	la a2, __cpu_up_task_pointer
+	add a1, a3, a1
+	add a2, a3, a2
+
+	/*
+	 * This hart didn't win the lottery, so we wait for the winning hart to
+	 * get far enough along the boot process that it should continue.
+	 */
+.Lwait_for_cpu_up:
+	/* FIXME: We should WFI to save some energy here. */
+	REG_L sp, (a1)
+	REG_L tp, (a2)
+	beqz sp, .Lwait_for_cpu_up
+	beqz tp, .Lwait_for_cpu_up
+	fence
+
+	tail secondary_start_common
+#endif
+
+END(_start_kernel)
+
+#ifdef CONFIG_RISCV_M_MODE
+ENTRY(reset_regs)
+	li	sp, 0
+	li	gp, 0
+	li	tp, 0
+	li	t0, 0
+	li	t1, 0
+	li	t2, 0
+	li	s0, 0
+	li	s1, 0
+	li	a2, 0
+	li	a3, 0
+	li	a4, 0
+	li	a5, 0
+	li	a6, 0
+	li	a7, 0
+	li	s2, 0
+	li	s3, 0
+	li	s4, 0
+	li	s5, 0
+	li	s6, 0
+	li	s7, 0
+	li	s8, 0
+	li	s9, 0
+	li	s10, 0
+	li	s11, 0
+	li	t3, 0
+	li	t4, 0
+	li	t5, 0
+	li	t6, 0
+	csrw	CSR_SCRATCH, 0
+
+#ifdef CONFIG_FPU
+	csrr	t0, CSR_MISA
+	andi	t0, t0, (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)
+	beqz	t0, .Lreset_regs_done
+
+	li	t1, SR_FS
+	csrs	CSR_STATUS, t1
+	fmv.s.x	f0, zero
+	fmv.s.x	f1, zero
+	fmv.s.x	f2, zero
+	fmv.s.x	f3, zero
+	fmv.s.x	f4, zero
+	fmv.s.x	f5, zero
+	fmv.s.x	f6, zero
+	fmv.s.x	f7, zero
+	fmv.s.x	f8, zero
+	fmv.s.x	f9, zero
+	fmv.s.x	f10, zero
+	fmv.s.x	f11, zero
+	fmv.s.x	f12, zero
+	fmv.s.x	f13, zero
+	fmv.s.x	f14, zero
+	fmv.s.x	f15, zero
+	fmv.s.x	f16, zero
+	fmv.s.x	f17, zero
+	fmv.s.x	f18, zero
+	fmv.s.x	f19, zero
+	fmv.s.x	f20, zero
+	fmv.s.x	f21, zero
+	fmv.s.x	f22, zero
+	fmv.s.x	f23, zero
+	fmv.s.x	f24, zero
+	fmv.s.x	f25, zero
+	fmv.s.x	f26, zero
+	fmv.s.x	f27, zero
+	fmv.s.x	f28, zero
+	fmv.s.x	f29, zero
+	fmv.s.x	f30, zero
+	fmv.s.x	f31, zero
+	csrw	fcsr, 0
+	/* note that the caller must clear SR_FS */
+#endif /* CONFIG_FPU */
+.Lreset_regs_done:
+	ret
+END(reset_regs)
+#endif /* CONFIG_RISCV_M_MODE */
+
+__PAGE_ALIGNED_BSS
+	/* Empty zero page */
+	.balign PAGE_SIZE
diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h
new file mode 100644
index 000000000..b48dda3d0
--- /dev/null
+++ b/arch/riscv/kernel/head.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 SiFive, Inc.
+ */
+#ifndef __ASM_HEAD_H
+#define __ASM_HEAD_H
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+extern atomic_t hart_lottery;
+
+asmlinkage void do_page_fault(struct pt_regs *regs);
+asmlinkage void __init setup_vm(uintptr_t dtb_pa);
+
+extern void *__cpu_up_stack_pointer[];
+extern void *__cpu_up_task_pointer[];
+
+#endif /* __ASM_HEAD_H */
diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h
new file mode 100644
index 000000000..8c212efb3
--- /dev/null
+++ b/arch/riscv/kernel/image-vars.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ * Linker script variables to be set after section resolution, as
+ * ld.lld does not like variables assigned before SECTIONS is processed.
+ * Based on arch/arm64/kerne/image-vars.h
+ */
+#ifndef __RISCV_KERNEL_IMAGE_VARS_H
+#define __RISCV_KERNEL_IMAGE_VARS_H
+
+#ifndef LINKER_SCRIPT
+#error This file should only be included in vmlinux.lds.S
+#endif
+
+#ifdef CONFIG_EFI
+
+/*
+ * The EFI stub has its own symbol namespace prefixed by __efistub_, to
+ * isolate it from the kernel proper. The following symbols are legally
+ * accessed by the stub, so provide some aliases to make them accessible.
+ * Only include data symbols here, or text symbols of functions that are
+ * guaranteed to be safe when executed at another offset than they were
+ * linked at. The routines below are all implemented in assembler in a
+ * position independent manner
+ */
+__efistub_memcmp		= memcmp;
+__efistub_memchr		= memchr;
+__efistub_memcpy		= memcpy;
+__efistub_memmove		= memmove;
+__efistub_memset		= memset;
+__efistub_strlen		= strlen;
+__efistub_strnlen		= strnlen;
+__efistub_strcmp		= strcmp;
+__efistub_strncmp		= strncmp;
+__efistub_strrchr		= strrchr;
+
+#ifdef CONFIG_KASAN
+__efistub___memcpy		= memcpy;
+__efistub___memmove		= memmove;
+__efistub___memset		= memset;
+#endif
+
+__efistub__start		= _start;
+__efistub__start_kernel		= _start_kernel;
+__efistub__end			= _end;
+__efistub__edata		= _edata;
+__efistub_screen_info		= screen_info;
+
+#endif
+
+#endif /* __RISCV_KERNEL_IMAGE_VARS_H */
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
new file mode 100644
index 000000000..7207fa08d
--- /dev/null
+++ b/arch/riscv/kernel/irq.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2018 Christoph Hellwig
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <linux/seq_file.h>
+#include <asm/smp.h>
+
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+	show_ipi_stats(p, prec);
+	return 0;
+}
+
+void __init init_IRQ(void)
+{
+	irqchip_init();
+	if (!handle_arch_irq)
+		panic("No interrupt controller found.");
+}
diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c
new file mode 100644
index 000000000..20e09056d
--- /dev/null
+++ b/arch/riscv/kernel/jump_label.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Emil Renner Berthing
+ *
+ * Based on arch/arm64/kernel/jump_label.c
+ */
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mutex.h>
+#include <asm/bug.h>
+#include <asm/patch.h>
+
+#define RISCV_INSN_NOP 0x00000013U
+#define RISCV_INSN_JAL 0x0000006fU
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	void *addr = (void *)jump_entry_code(entry);
+	u32 insn;
+
+	if (type == JUMP_LABEL_JMP) {
+		long offset = jump_entry_target(entry) - jump_entry_code(entry);
+
+		if (WARN_ON(offset & 1 || offset < -524288 || offset >= 524288))
+			return;
+
+		insn = RISCV_INSN_JAL |
+			(((u32)offset & GENMASK(19, 12)) << (12 - 12)) |
+			(((u32)offset & GENMASK(11, 11)) << (20 - 11)) |
+			(((u32)offset & GENMASK(10,  1)) << (21 -  1)) |
+			(((u32)offset & GENMASK(20, 20)) << (31 - 20));
+	} else {
+		insn = RISCV_INSN_NOP;
+	}
+
+	mutex_lock(&text_mutex);
+	patch_text_nosync(addr, &insn, sizeof(insn));
+	mutex_unlock(&text_mutex);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	/*
+	 * We use the same instructions in the arch_static_branch and
+	 * arch_static_branch_jump inline functions, so there's no
+	 * need to patch them up here.
+	 * The core will call arch_jump_label_transform  when those
+	 * instructions need to be replaced.
+	 */
+}
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
new file mode 100644
index 000000000..963ed7edc
--- /dev/null
+++ b/arch/riscv/kernel/kgdb.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/ptrace.h>
+#include <linux/kdebug.h>
+#include <linux/bug.h>
+#include <linux/kgdb.h>
+#include <linux/irqflags.h>
+#include <linux/string.h>
+#include <asm/cacheflush.h>
+#include <asm/gdb_xml.h>
+#include <asm/parse_asm.h>
+
+enum {
+	NOT_KGDB_BREAK = 0,
+	KGDB_SW_BREAK,
+	KGDB_COMPILED_BREAK,
+	KGDB_SW_SINGLE_STEP
+};
+
+static unsigned long stepped_address;
+static unsigned int stepped_opcode;
+
+#if __riscv_xlen == 32
+/* C.JAL is an RV32C-only instruction */
+DECLARE_INSN(c_jal, MATCH_C_JAL, MASK_C_JAL)
+#else
+#define is_c_jal_insn(opcode) 0
+#endif
+DECLARE_INSN(jalr, MATCH_JALR, MASK_JALR)
+DECLARE_INSN(jal, MATCH_JAL, MASK_JAL)
+DECLARE_INSN(c_jr, MATCH_C_JR, MASK_C_JR)
+DECLARE_INSN(c_jalr, MATCH_C_JALR, MASK_C_JALR)
+DECLARE_INSN(c_j, MATCH_C_J, MASK_C_J)
+DECLARE_INSN(beq, MATCH_BEQ, MASK_BEQ)
+DECLARE_INSN(bne, MATCH_BNE, MASK_BNE)
+DECLARE_INSN(blt, MATCH_BLT, MASK_BLT)
+DECLARE_INSN(bge, MATCH_BGE, MASK_BGE)
+DECLARE_INSN(bltu, MATCH_BLTU, MASK_BLTU)
+DECLARE_INSN(bgeu, MATCH_BGEU, MASK_BGEU)
+DECLARE_INSN(c_beqz, MATCH_C_BEQZ, MASK_C_BEQZ)
+DECLARE_INSN(c_bnez, MATCH_C_BNEZ, MASK_C_BNEZ)
+DECLARE_INSN(sret, MATCH_SRET, MASK_SRET)
+
+static int decode_register_index(unsigned long opcode, int offset)
+{
+	return (opcode >> offset) & 0x1F;
+}
+
+static int decode_register_index_short(unsigned long opcode, int offset)
+{
+	return ((opcode >> offset) & 0x7) + 8;
+}
+
+/* Calculate the new address for after a step */
+static int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
+{
+	unsigned long pc = regs->epc;
+	unsigned long *regs_ptr = (unsigned long *)regs;
+	unsigned int rs1_num, rs2_num;
+	int op_code;
+
+	if (get_kernel_nofault(op_code, (void *)pc))
+		return -EINVAL;
+	if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) {
+		if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) {
+			rs1_num = decode_register_index(op_code, RVC_C2_RS1_OPOFF);
+			*next_addr = regs_ptr[rs1_num];
+		} else if (is_c_j_insn(op_code) || is_c_jal_insn(op_code)) {
+			*next_addr = EXTRACT_RVC_J_IMM(op_code) + pc;
+		} else if (is_c_beqz_insn(op_code)) {
+			rs1_num = decode_register_index_short(op_code,
+							      RVC_C1_RS1_OPOFF);
+			if (!rs1_num || regs_ptr[rs1_num] == 0)
+				*next_addr = EXTRACT_RVC_B_IMM(op_code) + pc;
+			else
+				*next_addr = pc + 2;
+		} else if (is_c_bnez_insn(op_code)) {
+			rs1_num =
+			    decode_register_index_short(op_code, RVC_C1_RS1_OPOFF);
+			if (rs1_num && regs_ptr[rs1_num] != 0)
+				*next_addr = EXTRACT_RVC_B_IMM(op_code) + pc;
+			else
+				*next_addr = pc + 2;
+		} else {
+			*next_addr = pc + 2;
+		}
+	} else {
+		if ((op_code & __INSN_OPCODE_MASK) == __INSN_BRANCH_OPCODE) {
+			bool result = false;
+			long imm = EXTRACT_BTYPE_IMM(op_code);
+			unsigned long rs1_val = 0, rs2_val = 0;
+
+			rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF);
+			rs2_num = decode_register_index(op_code, RVG_RS2_OPOFF);
+			if (rs1_num)
+				rs1_val = regs_ptr[rs1_num];
+			if (rs2_num)
+				rs2_val = regs_ptr[rs2_num];
+
+			if (is_beq_insn(op_code))
+				result = (rs1_val == rs2_val) ? true : false;
+			else if (is_bne_insn(op_code))
+				result = (rs1_val != rs2_val) ? true : false;
+			else if (is_blt_insn(op_code))
+				result =
+				    ((long)rs1_val <
+				     (long)rs2_val) ? true : false;
+			else if (is_bge_insn(op_code))
+				result =
+				    ((long)rs1_val >=
+				     (long)rs2_val) ? true : false;
+			else if (is_bltu_insn(op_code))
+				result = (rs1_val < rs2_val) ? true : false;
+			else if (is_bgeu_insn(op_code))
+				result = (rs1_val >= rs2_val) ? true : false;
+			if (result)
+				*next_addr = imm + pc;
+			else
+				*next_addr = pc + 4;
+		} else if (is_jal_insn(op_code)) {
+			*next_addr = EXTRACT_JTYPE_IMM(op_code) + pc;
+		} else if (is_jalr_insn(op_code)) {
+			rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF);
+			if (rs1_num)
+				*next_addr = ((unsigned long *)regs)[rs1_num];
+			*next_addr += EXTRACT_ITYPE_IMM(op_code);
+		} else if (is_sret_insn(op_code)) {
+			*next_addr = pc;
+		} else {
+			*next_addr = pc + 4;
+		}
+	}
+	return 0;
+}
+
+static int do_single_step(struct pt_regs *regs)
+{
+	/* Determine where the target instruction will send us to */
+	unsigned long addr = 0;
+	int error = get_step_address(regs, &addr);
+
+	if (error)
+		return error;
+
+	/* Store the op code in the stepped address */
+	error = get_kernel_nofault(stepped_opcode, (void *)addr);
+	if (error)
+		return error;
+
+	stepped_address = addr;
+
+	/* Replace the op code with the break instruction */
+	error = copy_to_kernel_nofault((void *)stepped_address,
+				   arch_kgdb_ops.gdb_bpt_instr,
+				   BREAK_INSTR_SIZE);
+	/* Flush and return */
+	if (!error) {
+		flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
+		kgdb_single_step = 1;
+		atomic_set(&kgdb_cpu_doing_single_step,
+			   raw_smp_processor_id());
+	} else {
+		stepped_address = 0;
+		stepped_opcode = 0;
+	}
+	return error;
+}
+
+/* Undo a single step */
+static void undo_single_step(struct pt_regs *regs)
+{
+	if (stepped_opcode != 0) {
+		copy_to_kernel_nofault((void *)stepped_address,
+				   (void *)&stepped_opcode, BREAK_INSTR_SIZE);
+		flush_icache_range(stepped_address,
+				   stepped_address + BREAK_INSTR_SIZE);
+	}
+	stepped_address = 0;
+	stepped_opcode = 0;
+	kgdb_single_step = 0;
+	atomic_set(&kgdb_cpu_doing_single_step, -1);
+}
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+	{DBG_REG_ZERO, GDB_SIZEOF_REG, -1},
+	{DBG_REG_RA, GDB_SIZEOF_REG, offsetof(struct pt_regs, ra)},
+	{DBG_REG_SP, GDB_SIZEOF_REG, offsetof(struct pt_regs, sp)},
+	{DBG_REG_GP, GDB_SIZEOF_REG, offsetof(struct pt_regs, gp)},
+	{DBG_REG_TP, GDB_SIZEOF_REG, offsetof(struct pt_regs, tp)},
+	{DBG_REG_T0, GDB_SIZEOF_REG, offsetof(struct pt_regs, t0)},
+	{DBG_REG_T1, GDB_SIZEOF_REG, offsetof(struct pt_regs, t1)},
+	{DBG_REG_T2, GDB_SIZEOF_REG, offsetof(struct pt_regs, t2)},
+	{DBG_REG_FP, GDB_SIZEOF_REG, offsetof(struct pt_regs, s0)},
+	{DBG_REG_S1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
+	{DBG_REG_A0, GDB_SIZEOF_REG, offsetof(struct pt_regs, a0)},
+	{DBG_REG_A1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
+	{DBG_REG_A2, GDB_SIZEOF_REG, offsetof(struct pt_regs, a2)},
+	{DBG_REG_A3, GDB_SIZEOF_REG, offsetof(struct pt_regs, a3)},
+	{DBG_REG_A4, GDB_SIZEOF_REG, offsetof(struct pt_regs, a4)},
+	{DBG_REG_A5, GDB_SIZEOF_REG, offsetof(struct pt_regs, a5)},
+	{DBG_REG_A6, GDB_SIZEOF_REG, offsetof(struct pt_regs, a6)},
+	{DBG_REG_A7, GDB_SIZEOF_REG, offsetof(struct pt_regs, a7)},
+	{DBG_REG_S2, GDB_SIZEOF_REG, offsetof(struct pt_regs, s2)},
+	{DBG_REG_S3, GDB_SIZEOF_REG, offsetof(struct pt_regs, s3)},
+	{DBG_REG_S4, GDB_SIZEOF_REG, offsetof(struct pt_regs, s4)},
+	{DBG_REG_S5, GDB_SIZEOF_REG, offsetof(struct pt_regs, s5)},
+	{DBG_REG_S6, GDB_SIZEOF_REG, offsetof(struct pt_regs, s6)},
+	{DBG_REG_S7, GDB_SIZEOF_REG, offsetof(struct pt_regs, s7)},
+	{DBG_REG_S8, GDB_SIZEOF_REG, offsetof(struct pt_regs, s8)},
+	{DBG_REG_S9, GDB_SIZEOF_REG, offsetof(struct pt_regs, s9)},
+	{DBG_REG_S10, GDB_SIZEOF_REG, offsetof(struct pt_regs, s10)},
+	{DBG_REG_S11, GDB_SIZEOF_REG, offsetof(struct pt_regs, s11)},
+	{DBG_REG_T3, GDB_SIZEOF_REG, offsetof(struct pt_regs, t3)},
+	{DBG_REG_T4, GDB_SIZEOF_REG, offsetof(struct pt_regs, t4)},
+	{DBG_REG_T5, GDB_SIZEOF_REG, offsetof(struct pt_regs, t5)},
+	{DBG_REG_T6, GDB_SIZEOF_REG, offsetof(struct pt_regs, t6)},
+	{DBG_REG_EPC, GDB_SIZEOF_REG, offsetof(struct pt_regs, epc)},
+	{DBG_REG_STATUS, GDB_SIZEOF_REG, offsetof(struct pt_regs, status)},
+	{DBG_REG_BADADDR, GDB_SIZEOF_REG, offsetof(struct pt_regs, badaddr)},
+	{DBG_REG_CAUSE, GDB_SIZEOF_REG, offsetof(struct pt_regs, cause)},
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return NULL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+		       dbg_reg_def[regno].size);
+	else
+		memset(mem, 0, dbg_reg_def[regno].size);
+	return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return -EINVAL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+		       dbg_reg_def[regno].size);
+	return 0;
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+	/* Initialize to zero */
+	memset((char *)gdb_regs, 0, NUMREGBYTES);
+
+	gdb_regs[DBG_REG_SP_OFF] = task->thread.sp;
+	gdb_regs[DBG_REG_FP_OFF] = task->thread.s[0];
+	gdb_regs[DBG_REG_S1_OFF] = task->thread.s[1];
+	gdb_regs[DBG_REG_S2_OFF] = task->thread.s[2];
+	gdb_regs[DBG_REG_S3_OFF] = task->thread.s[3];
+	gdb_regs[DBG_REG_S4_OFF] = task->thread.s[4];
+	gdb_regs[DBG_REG_S5_OFF] = task->thread.s[5];
+	gdb_regs[DBG_REG_S6_OFF] = task->thread.s[6];
+	gdb_regs[DBG_REG_S7_OFF] = task->thread.s[7];
+	gdb_regs[DBG_REG_S8_OFF] = task->thread.s[8];
+	gdb_regs[DBG_REG_S9_OFF] = task->thread.s[10];
+	gdb_regs[DBG_REG_S10_OFF] = task->thread.s[11];
+	gdb_regs[DBG_REG_EPC_OFF] = task->thread.ra;
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+	regs->epc = pc;
+}
+
+void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
+				char *remcom_out_buffer)
+{
+	if (!strncmp(remcom_in_buffer, gdb_xfer_read_target,
+		     sizeof(gdb_xfer_read_target)))
+		strcpy(remcom_out_buffer, riscv_gdb_stub_target_desc);
+	else if (!strncmp(remcom_in_buffer, gdb_xfer_read_cpuxml,
+			  sizeof(gdb_xfer_read_cpuxml)))
+		strcpy(remcom_out_buffer, riscv_gdb_stub_cpuxml);
+}
+
+static inline void kgdb_arch_update_addr(struct pt_regs *regs,
+					 char *remcom_in_buffer)
+{
+	unsigned long addr;
+	char *ptr;
+
+	ptr = &remcom_in_buffer[1];
+	if (kgdb_hex2long(&ptr, &addr))
+		regs->epc = addr;
+}
+
+int kgdb_arch_handle_exception(int vector, int signo, int err_code,
+			       char *remcom_in_buffer, char *remcom_out_buffer,
+			       struct pt_regs *regs)
+{
+	int err = 0;
+
+	undo_single_step(regs);
+
+	switch (remcom_in_buffer[0]) {
+	case 'c':
+	case 'D':
+	case 'k':
+		if (remcom_in_buffer[0] == 'c')
+			kgdb_arch_update_addr(regs, remcom_in_buffer);
+		break;
+	case 's':
+		kgdb_arch_update_addr(regs, remcom_in_buffer);
+		err = do_single_step(regs);
+		break;
+	default:
+		err = -1;
+	}
+	return err;
+}
+
+static int kgdb_riscv_kgdbbreak(unsigned long addr)
+{
+	if (stepped_address == addr)
+		return KGDB_SW_SINGLE_STEP;
+	if (atomic_read(&kgdb_setting_breakpoint))
+		if (addr == (unsigned long)&kgdb_compiled_break)
+			return KGDB_COMPILED_BREAK;
+
+	return kgdb_has_hit_break(addr);
+}
+
+static int kgdb_riscv_notify(struct notifier_block *self, unsigned long cmd,
+			     void *ptr)
+{
+	struct die_args *args = (struct die_args *)ptr;
+	struct pt_regs *regs = args->regs;
+	unsigned long flags;
+	int type;
+
+	if (user_mode(regs))
+		return NOTIFY_DONE;
+
+	type = kgdb_riscv_kgdbbreak(regs->epc);
+	if (type == NOT_KGDB_BREAK && cmd == DIE_TRAP)
+		return NOTIFY_DONE;
+
+	local_irq_save(flags);
+
+	if (kgdb_handle_exception(type == KGDB_SW_SINGLE_STEP ? 0 : 1,
+				  args->signr, cmd, regs))
+		return NOTIFY_DONE;
+
+	if (type == KGDB_COMPILED_BREAK)
+		regs->epc += 4;
+
+	local_irq_restore(flags);
+
+	return NOTIFY_STOP;
+}
+
+static struct notifier_block kgdb_notifier = {
+	.notifier_call = kgdb_riscv_notify,
+};
+
+int kgdb_arch_init(void)
+{
+	register_die_notifier(&kgdb_notifier);
+
+	return 0;
+}
+
+void kgdb_arch_exit(void)
+{
+	unregister_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * Global data
+ */
+#ifdef CONFIG_RISCV_ISA_C
+const struct kgdb_arch arch_kgdb_ops = {
+	.gdb_bpt_instr = {0x02, 0x90},	/* c.ebreak */
+};
+#else
+const struct kgdb_arch arch_kgdb_ops = {
+	.gdb_bpt_instr = {0x73, 0x00, 0x10, 0x00},	/* ebreak */
+};
+#endif
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
new file mode 100644
index 000000000..35a6ed76c
--- /dev/null
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -0,0 +1,239 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm-generic/export.h>
+#include <asm/ftrace.h>
+
+	.text
+
+	.macro SAVE_ABI_STATE
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	addi    sp, sp, -48
+	sd      s0, 32(sp)
+	sd      ra, 40(sp)
+	addi    s0, sp, 48
+	sd      t0, 24(sp)
+	sd      t1, 16(sp)
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	sd      t2, 8(sp)
+#endif
+#else
+	addi	sp, sp, -16
+	sd	s0, 0(sp)
+	sd	ra, 8(sp)
+	addi	s0, sp, 16
+#endif
+	.endm
+
+	.macro RESTORE_ABI_STATE
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	ld	s0, 32(sp)
+	ld	ra, 40(sp)
+	addi	sp, sp, 48
+#else
+	ld	ra, 8(sp)
+	ld	s0, 0(sp)
+	addi	sp, sp, 16
+#endif
+	.endm
+
+	.macro RESTORE_GRAPH_ARGS
+	ld	a0, 24(sp)
+	ld	a1, 16(sp)
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	ld	a2, 8(sp)
+#endif
+	.endm
+
+ENTRY(ftrace_graph_caller)
+	addi	sp, sp, -16
+	sd	s0, 0(sp)
+	sd	ra, 8(sp)
+	addi	s0, sp, 16
+ftrace_graph_call:
+	.global ftrace_graph_call
+	/*
+	 * Calling ftrace_enable/disable_ftrace_graph_caller would overwrite the
+	 * call below.  Check ftrace_modify_all_code for details.
+	 */
+	call	ftrace_stub
+	ld	ra, 8(sp)
+	ld	s0, 0(sp)
+	addi	sp, sp, 16
+	ret
+ENDPROC(ftrace_graph_caller)
+
+ENTRY(ftrace_caller)
+	/*
+	 * a0: the address in the caller when calling ftrace_caller
+	 * a1: the caller's return address
+	 * a2: the address of global variable function_trace_op
+	 */
+	ld	a1, -8(s0)
+	addi	a0, ra, -MCOUNT_INSN_SIZE
+	la	t5, function_trace_op
+	ld	a2, 0(t5)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/*
+	 * the graph tracer (specifically, prepare_ftrace_return) needs these
+	 * arguments but for now the function tracer occupies the regs, so we
+	 * save them in temporary regs to recover later.
+	 */
+	addi	t0, s0, -8
+	mv	t1, a0
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	ld	t2, -16(s0)
+#endif
+#endif
+
+	SAVE_ABI_STATE
+ftrace_call:
+	.global ftrace_call
+	/*
+	 * For the dynamic ftrace to work, here we should reserve at least
+	 * 8 bytes for a functional auipc-jalr pair.  The following call
+	 * serves this purpose.
+	 *
+	 * Calling ftrace_update_ftrace_func would overwrite the nops below.
+	 * Check ftrace_modify_all_code for details.
+	 */
+	call	ftrace_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	RESTORE_GRAPH_ARGS
+	call	ftrace_graph_caller
+#endif
+
+	RESTORE_ABI_STATE
+	ret
+ENDPROC(ftrace_caller)
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+	.macro SAVE_ALL
+	addi	sp, sp, -(PT_SIZE_ON_STACK+16)
+	sd	s0, (PT_SIZE_ON_STACK)(sp)
+	sd	ra, (PT_SIZE_ON_STACK+8)(sp)
+	addi	s0, sp, (PT_SIZE_ON_STACK+16)
+
+	sd x1,  PT_RA(sp)
+	sd x2,  PT_SP(sp)
+	sd x3,  PT_GP(sp)
+	sd x4,  PT_TP(sp)
+	sd x5,  PT_T0(sp)
+	sd x6,  PT_T1(sp)
+	sd x7,  PT_T2(sp)
+	sd x8,  PT_S0(sp)
+	sd x9,  PT_S1(sp)
+	sd x10, PT_A0(sp)
+	sd x11, PT_A1(sp)
+	sd x12, PT_A2(sp)
+	sd x13, PT_A3(sp)
+	sd x14, PT_A4(sp)
+	sd x15, PT_A5(sp)
+	sd x16, PT_A6(sp)
+	sd x17, PT_A7(sp)
+	sd x18, PT_S2(sp)
+	sd x19, PT_S3(sp)
+	sd x20, PT_S4(sp)
+	sd x21, PT_S5(sp)
+	sd x22, PT_S6(sp)
+	sd x23, PT_S7(sp)
+	sd x24, PT_S8(sp)
+	sd x25, PT_S9(sp)
+	sd x26, PT_S10(sp)
+	sd x27, PT_S11(sp)
+	sd x28, PT_T3(sp)
+	sd x29, PT_T4(sp)
+	sd x30, PT_T5(sp)
+	sd x31, PT_T6(sp)
+	.endm
+
+	.macro RESTORE_ALL
+	ld x1,  PT_RA(sp)
+	ld x2,  PT_SP(sp)
+	ld x3,  PT_GP(sp)
+	ld x4,  PT_TP(sp)
+	ld x5,  PT_T0(sp)
+	ld x6,  PT_T1(sp)
+	ld x7,  PT_T2(sp)
+	ld x8,  PT_S0(sp)
+	ld x9,  PT_S1(sp)
+	ld x10, PT_A0(sp)
+	ld x11, PT_A1(sp)
+	ld x12, PT_A2(sp)
+	ld x13, PT_A3(sp)
+	ld x14, PT_A4(sp)
+	ld x15, PT_A5(sp)
+	ld x16, PT_A6(sp)
+	ld x17, PT_A7(sp)
+	ld x18, PT_S2(sp)
+	ld x19, PT_S3(sp)
+	ld x20, PT_S4(sp)
+	ld x21, PT_S5(sp)
+	ld x22, PT_S6(sp)
+	ld x23, PT_S7(sp)
+	ld x24, PT_S8(sp)
+	ld x25, PT_S9(sp)
+	ld x26, PT_S10(sp)
+	ld x27, PT_S11(sp)
+	ld x28, PT_T3(sp)
+	ld x29, PT_T4(sp)
+	ld x30, PT_T5(sp)
+	ld x31, PT_T6(sp)
+
+	ld	s0, (PT_SIZE_ON_STACK)(sp)
+	ld	ra, (PT_SIZE_ON_STACK+8)(sp)
+	addi	sp, sp, (PT_SIZE_ON_STACK+16)
+	.endm
+
+	.macro RESTORE_GRAPH_REG_ARGS
+	ld	a0, PT_T0(sp)
+	ld	a1, PT_T1(sp)
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	ld	a2, PT_T2(sp)
+#endif
+	.endm
+
+/*
+ * Most of the contents are the same as ftrace_caller.
+ */
+ENTRY(ftrace_regs_caller)
+	/*
+	 * a3: the address of all registers in the stack
+	 */
+	ld	a1, -8(s0)
+	addi	a0, ra, -MCOUNT_INSN_SIZE
+	la	t5, function_trace_op
+	ld	a2, 0(t5)
+	addi	a3, sp, -(PT_SIZE_ON_STACK+16)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	addi	t0, s0, -8
+	mv	t1, a0
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	ld	t2, -16(s0)
+#endif
+#endif
+	SAVE_ALL
+
+ftrace_regs_call:
+	.global ftrace_regs_call
+	call	ftrace_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	RESTORE_GRAPH_REG_ARGS
+	call	ftrace_graph_caller
+#endif
+
+	RESTORE_ALL
+	ret
+ENDPROC(ftrace_regs_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
new file mode 100644
index 000000000..6d462681c
--- /dev/null
+++ b/arch/riscv/kernel/mcount.S
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm-generic/export.h>
+#include <asm/ftrace.h>
+
+	.text
+
+	.macro SAVE_ABI_STATE
+	addi	sp, sp, -16
+	sd	s0, 0(sp)
+	sd	ra, 8(sp)
+	addi	s0, sp, 16
+	.endm
+
+	/*
+	 * The call to ftrace_return_to_handler would overwrite the return
+	 * register if a0 was not saved.
+	 */
+	.macro SAVE_RET_ABI_STATE
+	addi	sp, sp, -32
+	sd	s0, 16(sp)
+	sd	ra, 24(sp)
+	sd	a0, 8(sp)
+	addi	s0, sp, 32
+	.endm
+
+	.macro RESTORE_ABI_STATE
+	ld	ra, 8(sp)
+	ld	s0, 0(sp)
+	addi	sp, sp, 16
+	.endm
+
+	.macro RESTORE_RET_ABI_STATE
+	ld	ra, 24(sp)
+	ld	s0, 16(sp)
+	ld	a0, 8(sp)
+	addi	sp, sp, 32
+	.endm
+
+ENTRY(ftrace_stub)
+#ifdef CONFIG_DYNAMIC_FTRACE
+       .global MCOUNT_NAME
+       .set    MCOUNT_NAME, ftrace_stub
+#endif
+	ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(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.
+ * However, the psABI of variable-length-argument functions does not allow this.
+ *
+ * So alternatively we check the *old* frame pointer position, that is, the
+ * value stored in -16(s0) on entry, and the s0 on return.
+ */
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	t6, s0
+#endif
+	SAVE_RET_ABI_STATE
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	a0, t6
+#endif
+	call	ftrace_return_to_handler
+	mv	a1, a0
+	RESTORE_RET_ABI_STATE
+	jalr	a1
+ENDPROC(return_to_handler)
+#endif
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+ENTRY(MCOUNT_NAME)
+	la	t4, ftrace_stub
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	la	t0, ftrace_graph_return
+	ld	t1, 0(t0)
+	bne	t1, t4, do_ftrace_graph_caller
+
+	la	t3, ftrace_graph_entry
+	ld	t2, 0(t3)
+	la	t6, ftrace_graph_entry_stub
+	bne	t2, t6, do_ftrace_graph_caller
+#endif
+	la	t3, ftrace_trace_function
+	ld	t5, 0(t3)
+	bne	t5, t4, do_trace
+	ret
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * A pseudo representation for the function graph tracer:
+ * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller)
+ */
+do_ftrace_graph_caller:
+	addi	a0, s0, -8
+	mv	a1, ra
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	ld	a2, -16(s0)
+#endif
+	SAVE_ABI_STATE
+	call	prepare_ftrace_return
+	RESTORE_ABI_STATE
+	ret
+#endif
+
+/*
+ * A pseudo representation for the function tracer:
+ * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller)
+ */
+do_trace:
+	ld	a1, -8(s0)
+	mv	a0, ra
+
+	SAVE_ABI_STATE
+	jalr	t5
+	RESTORE_ABI_STATE
+	ret
+ENDPROC(MCOUNT_NAME)
+#endif
+EXPORT_SYMBOL(MCOUNT_NAME)
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
new file mode 100644
index 000000000..e264e59e5
--- /dev/null
+++ b/arch/riscv/kernel/module-sections.c
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Copyright (C) 2018 Andes Technology Corporation <zong@andestech.com>
+ */
+
+#include <linux/elf.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleloader.h>
+
+unsigned long module_emit_got_entry(struct module *mod, unsigned long val)
+{
+	struct mod_section *got_sec = &mod->arch.got;
+	int i = got_sec->num_entries;
+	struct got_entry *got = get_got_entry(val, got_sec);
+
+	if (got)
+		return (unsigned long)got;
+
+	/* There is no duplicate entry, create a new one */
+	got = (struct got_entry *)got_sec->shdr->sh_addr;
+	got[i] = emit_got_entry(val);
+
+	got_sec->num_entries++;
+	BUG_ON(got_sec->num_entries > got_sec->max_entries);
+
+	return (unsigned long)&got[i];
+}
+
+unsigned long module_emit_plt_entry(struct module *mod, unsigned long val)
+{
+	struct mod_section *got_plt_sec = &mod->arch.got_plt;
+	struct got_entry *got_plt;
+	struct mod_section *plt_sec = &mod->arch.plt;
+	struct plt_entry *plt = get_plt_entry(val, plt_sec, got_plt_sec);
+	int i = plt_sec->num_entries;
+
+	if (plt)
+		return (unsigned long)plt;
+
+	/* There is no duplicate entry, create a new one */
+	got_plt = (struct got_entry *)got_plt_sec->shdr->sh_addr;
+	got_plt[i] = emit_got_entry(val);
+	plt = (struct plt_entry *)plt_sec->shdr->sh_addr;
+	plt[i] = emit_plt_entry(val,
+				(unsigned long)&plt[i],
+				(unsigned long)&got_plt[i]);
+
+	plt_sec->num_entries++;
+	got_plt_sec->num_entries++;
+	BUG_ON(plt_sec->num_entries > plt_sec->max_entries);
+
+	return (unsigned long)&plt[i];
+}
+
+static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
+{
+	return x->r_info == y->r_info && x->r_addend == y->r_addend;
+}
+
+static bool duplicate_rela(const Elf_Rela *rela, int idx)
+{
+	int i;
+	for (i = 0; i < idx; i++) {
+		if (is_rela_equal(&rela[i], &rela[idx]))
+			return true;
+	}
+	return false;
+}
+
+static void count_max_entries(Elf_Rela *relas, int num,
+			      unsigned int *plts, unsigned int *gots)
+{
+	unsigned int type, i;
+
+	for (i = 0; i < num; i++) {
+		type = ELF_RISCV_R_TYPE(relas[i].r_info);
+		if (type == R_RISCV_CALL_PLT) {
+			if (!duplicate_rela(relas, i))
+				(*plts)++;
+		} else if (type == R_RISCV_GOT_HI20) {
+			if (!duplicate_rela(relas, i))
+				(*gots)++;
+		}
+	}
+}
+
+int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+			      char *secstrings, struct module *mod)
+{
+	unsigned int num_plts = 0;
+	unsigned int num_gots = 0;
+	int i;
+
+	/*
+	 * Find the empty .got and .plt sections.
+	 */
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
+			mod->arch.plt.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got"))
+			mod->arch.got.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got.plt"))
+			mod->arch.got_plt.shdr = sechdrs + i;
+	}
+
+	if (!mod->arch.plt.shdr) {
+		pr_err("%s: module PLT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+	if (!mod->arch.got.shdr) {
+		pr_err("%s: module GOT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+	if (!mod->arch.got_plt.shdr) {
+		pr_err("%s: module GOT.PLT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+
+	/* Calculate the maxinum number of entries */
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset;
+		int num_rela = sechdrs[i].sh_size / sizeof(Elf_Rela);
+		Elf_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info;
+
+		if (sechdrs[i].sh_type != SHT_RELA)
+			continue;
+
+		/* ignore relocations that operate on non-exec sections */
+		if (!(dst_sec->sh_flags & SHF_EXECINSTR))
+			continue;
+
+		count_max_entries(relas, num_rela, &num_plts, &num_gots);
+	}
+
+	mod->arch.plt.shdr->sh_type = SHT_NOBITS;
+	mod->arch.plt.shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.plt.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.plt.shdr->sh_size = (num_plts + 1) * sizeof(struct plt_entry);
+	mod->arch.plt.num_entries = 0;
+	mod->arch.plt.max_entries = num_plts;
+
+	mod->arch.got.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got.shdr->sh_size = (num_gots + 1) * sizeof(struct got_entry);
+	mod->arch.got.num_entries = 0;
+	mod->arch.got.max_entries = num_gots;
+
+	mod->arch.got_plt.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got_plt.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got_plt.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got_plt.shdr->sh_size = (num_plts + 1) * sizeof(struct got_entry);
+	mod->arch.got_plt.num_entries = 0;
+	mod->arch.got_plt.max_entries = num_plts;
+	return 0;
+}
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
new file mode 100644
index 000000000..c3310a68a
--- /dev/null
+++ b/arch/riscv/kernel/module.c
@@ -0,0 +1,431 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ *  Copyright (C) 2017 Zihao Yu
+ */
+
+#include <linux/elf.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/moduleloader.h>
+#include <linux/vmalloc.h>
+#include <linux/sizes.h>
+#include <linux/pgtable.h>
+#include <asm/sections.h>
+
+/*
+ * The auipc+jalr instruction pair can reach any PC-relative offset
+ * in the range [-2^31 - 2^11, 2^31 - 2^11)
+ */
+static bool riscv_insn_valid_32bit_offset(ptrdiff_t val)
+{
+#ifdef CONFIG_32BIT
+	return true;
+#else
+	return (-(1L << 31) - (1L << 11)) <= val && val < ((1L << 31) - (1L << 11));
+#endif
+}
+
+static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+	if (v != (u32)v) {
+		pr_err("%s: value %016llx out of range for 32-bit field\n",
+		       me->name, (long long)v);
+		return -EINVAL;
+	}
+	*location = v;
+	return 0;
+}
+
+static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
+{
+	*(u64 *)location = v;
+	return 0;
+}
+
+static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
+				     Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 imm12 = (offset & 0x1000) << (31 - 12);
+	u32 imm11 = (offset & 0x800) >> (11 - 7);
+	u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
+	u32 imm4_1 = (offset & 0x1e) << (11 - 4);
+
+	*location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1;
+	return 0;
+}
+
+static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
+				  Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 imm20 = (offset & 0x100000) << (31 - 20);
+	u32 imm19_12 = (offset & 0xff000);
+	u32 imm11 = (offset & 0x800) << (20 - 11);
+	u32 imm10_1 = (offset & 0x7fe) << (30 - 10);
+
+	*location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1;
+	return 0;
+}
+
+static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
+					 Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u16 imm8 = (offset & 0x100) << (12 - 8);
+	u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
+	u16 imm5 = (offset & 0x20) >> (5 - 2);
+	u16 imm4_3 = (offset & 0x18) << (12 - 5);
+	u16 imm2_1 = (offset & 0x6) << (12 - 10);
+
+	*(u16 *)location = (*(u16 *)location & 0xe383) |
+		    imm8 | imm7_6 | imm5 | imm4_3 | imm2_1;
+	return 0;
+}
+
+static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
+				       Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u16 imm11 = (offset & 0x800) << (12 - 11);
+	u16 imm10 = (offset & 0x400) >> (10 - 8);
+	u16 imm9_8 = (offset & 0x300) << (12 - 11);
+	u16 imm7 = (offset & 0x80) >> (7 - 6);
+	u16 imm6 = (offset & 0x40) << (12 - 11);
+	u16 imm5 = (offset & 0x20) >> (5 - 2);
+	u16 imm4 = (offset & 0x10) << (12 - 5);
+	u16 imm3_1 = (offset & 0xe) << (12 - 10);
+
+	*(u16 *)location = (*(u16 *)location & 0xe003) |
+		    imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1;
+	return 0;
+}
+
+static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
+					 Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	s32 hi20;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		pr_err(
+		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	*location = (*location & 0xfff) | hi20;
+	return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location,
+					   Elf_Addr v)
+{
+	/*
+	 * v is the lo12 value to fill. It is calculated before calling this
+	 * handler.
+	 */
+	*location = (*location & 0xfffff) | ((v & 0xfff) << 20);
+	return 0;
+}
+
+static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
+					   Elf_Addr v)
+{
+	/*
+	 * v is the lo12 value to fill. It is calculated before calling this
+	 * handler.
+	 */
+	u32 imm11_5 = (v & 0xfe0) << (31 - 11);
+	u32 imm4_0 = (v & 0x1f) << (11 - 4);
+
+	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
+	return 0;
+}
+
+static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
+				   Elf_Addr v)
+{
+	s32 hi20;
+
+	if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) {
+		pr_err(
+		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = ((s32)v + 0x800) & 0xfffff000;
+	*location = (*location & 0xfff) | hi20;
+	return 0;
+}
+
+static int apply_r_riscv_lo12_i_rela(struct module *me, u32 *location,
+				     Elf_Addr v)
+{
+	/* Skip medlow checking because of filtering by HI20 already */
+	s32 hi20 = ((s32)v + 0x800) & 0xfffff000;
+	s32 lo12 = ((s32)v - hi20);
+	*location = (*location & 0xfffff) | ((lo12 & 0xfff) << 20);
+	return 0;
+}
+
+static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
+				     Elf_Addr v)
+{
+	/* Skip medlow checking because of filtering by HI20 already */
+	s32 hi20 = ((s32)v + 0x800) & 0xfffff000;
+	s32 lo12 = ((s32)v - hi20);
+	u32 imm11_5 = (lo12 & 0xfe0) << (31 - 11);
+	u32 imm4_0 = (lo12 & 0x1f) << (11 - 4);
+	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
+	return 0;
+}
+
+static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
+				       Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	s32 hi20;
+
+	/* Always emit the got entry */
+	if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
+		offset = module_emit_got_entry(me, v);
+		offset = (void *)offset - (void *)location;
+	} else {
+		pr_err(
+		  "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	*location = (*location & 0xfff) | hi20;
+	return 0;
+}
+
+static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
+				       Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 hi20, lo12;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		/* Only emit the plt entry if offset over 32-bit range */
+		if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
+			offset = module_emit_plt_entry(me, v);
+			offset = (void *)offset - (void *)location;
+		} else {
+			pr_err(
+			  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+			  me->name, (long long)v, location);
+			return -EINVAL;
+		}
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	lo12 = (offset - hi20) & 0xfff;
+	*location = (*location & 0xfff) | hi20;
+	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
+	return 0;
+}
+
+static int apply_r_riscv_call_rela(struct module *me, u32 *location,
+				   Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	u32 hi20, lo12;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		pr_err(
+		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+		  me->name, (long long)v, location);
+		return -EINVAL;
+	}
+
+	hi20 = (offset + 0x800) & 0xfffff000;
+	lo12 = (offset - hi20) & 0xfff;
+	*location = (*location & 0xfff) | hi20;
+	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
+	return 0;
+}
+
+static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	return 0;
+}
+
+static int apply_r_riscv_align_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	pr_err(
+	  "%s: The unexpected relocation type 'R_RISCV_ALIGN' from PC = %p\n",
+	  me->name, location);
+	return -EINVAL;
+}
+
+static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u32 *)location += (u32)v;
+	return 0;
+}
+
+static int apply_r_riscv_add64_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u64 *)location += (u64)v;
+	return 0;
+}
+
+static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u32 *)location -= (u32)v;
+	return 0;
+}
+
+static int apply_r_riscv_sub64_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u64 *)location -= (u64)v;
+	return 0;
+}
+
+static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
+				Elf_Addr v) = {
+	[R_RISCV_32]			= apply_r_riscv_32_rela,
+	[R_RISCV_64]			= apply_r_riscv_64_rela,
+	[R_RISCV_BRANCH]		= apply_r_riscv_branch_rela,
+	[R_RISCV_JAL]			= apply_r_riscv_jal_rela,
+	[R_RISCV_RVC_BRANCH]		= apply_r_riscv_rcv_branch_rela,
+	[R_RISCV_RVC_JUMP]		= apply_r_riscv_rvc_jump_rela,
+	[R_RISCV_PCREL_HI20]		= apply_r_riscv_pcrel_hi20_rela,
+	[R_RISCV_PCREL_LO12_I]		= apply_r_riscv_pcrel_lo12_i_rela,
+	[R_RISCV_PCREL_LO12_S]		= apply_r_riscv_pcrel_lo12_s_rela,
+	[R_RISCV_HI20]			= apply_r_riscv_hi20_rela,
+	[R_RISCV_LO12_I]		= apply_r_riscv_lo12_i_rela,
+	[R_RISCV_LO12_S]		= apply_r_riscv_lo12_s_rela,
+	[R_RISCV_GOT_HI20]		= apply_r_riscv_got_hi20_rela,
+	[R_RISCV_CALL_PLT]		= apply_r_riscv_call_plt_rela,
+	[R_RISCV_CALL]			= apply_r_riscv_call_rela,
+	[R_RISCV_RELAX]			= apply_r_riscv_relax_rela,
+	[R_RISCV_ALIGN]			= apply_r_riscv_align_rela,
+	[R_RISCV_ADD32]			= apply_r_riscv_add32_rela,
+	[R_RISCV_ADD64]			= apply_r_riscv_add64_rela,
+	[R_RISCV_SUB32]			= apply_r_riscv_sub32_rela,
+	[R_RISCV_SUB64]			= apply_r_riscv_sub64_rela,
+};
+
+int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+		       unsigned int symindex, unsigned int relsec,
+		       struct module *me)
+{
+	Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr;
+	int (*handler)(struct module *me, u32 *location, Elf_Addr v);
+	Elf_Sym *sym;
+	u32 *location;
+	unsigned int i, type;
+	Elf_Addr v;
+	int res;
+
+	pr_debug("Applying relocate section %u to %u\n", relsec,
+	       sechdrs[relsec].sh_info);
+
+	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+		/* This is where to make the change */
+		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+			+ rel[i].r_offset;
+		/* This is the symbol it is referring to */
+		sym = (Elf_Sym *)sechdrs[symindex].sh_addr
+			+ ELF_RISCV_R_SYM(rel[i].r_info);
+		if (IS_ERR_VALUE(sym->st_value)) {
+			/* Ignore unresolved weak symbol */
+			if (ELF_ST_BIND(sym->st_info) == STB_WEAK)
+				continue;
+			pr_warn("%s: Unknown symbol %s\n",
+				me->name, strtab + sym->st_name);
+			return -ENOENT;
+		}
+
+		type = ELF_RISCV_R_TYPE(rel[i].r_info);
+
+		if (type < ARRAY_SIZE(reloc_handlers_rela))
+			handler = reloc_handlers_rela[type];
+		else
+			handler = NULL;
+
+		if (!handler) {
+			pr_err("%s: Unknown relocation type %u\n",
+			       me->name, type);
+			return -EINVAL;
+		}
+
+		v = sym->st_value + rel[i].r_addend;
+
+		if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
+			unsigned int j;
+
+			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+				unsigned long hi20_loc =
+					sechdrs[sechdrs[relsec].sh_info].sh_addr
+					+ rel[j].r_offset;
+				u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info);
+
+				/* Find the corresponding HI20 relocation entry */
+				if (hi20_loc == sym->st_value
+				    && (hi20_type == R_RISCV_PCREL_HI20
+					|| hi20_type == R_RISCV_GOT_HI20)) {
+					s32 hi20, lo12;
+					Elf_Sym *hi20_sym =
+						(Elf_Sym *)sechdrs[symindex].sh_addr
+						+ ELF_RISCV_R_SYM(rel[j].r_info);
+					unsigned long hi20_sym_val =
+						hi20_sym->st_value
+						+ rel[j].r_addend;
+
+					/* Calculate lo12 */
+					size_t offset = hi20_sym_val - hi20_loc;
+					if (IS_ENABLED(CONFIG_MODULE_SECTIONS)
+					    && hi20_type == R_RISCV_GOT_HI20) {
+						offset = module_emit_got_entry(
+							 me, hi20_sym_val);
+						offset = offset - hi20_loc;
+					}
+					hi20 = (offset + 0x800) & 0xfffff000;
+					lo12 = offset - hi20;
+					v = lo12;
+
+					break;
+				}
+			}
+			if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+				pr_err(
+				  "%s: Can not find HI20 relocation information\n",
+				  me->name);
+				return -EINVAL;
+			}
+		}
+
+		res = handler(me, location, v);
+		if (res)
+			return res;
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
+#define VMALLOC_MODULE_START \
+	 max(PFN_ALIGN((unsigned long)&_end - SZ_2G), VMALLOC_START)
+void *module_alloc(unsigned long size)
+{
+	return __vmalloc_node_range(size, 1, VMALLOC_MODULE_START,
+				    VMALLOC_END, GFP_KERNEL,
+				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+#endif
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
new file mode 100644
index 000000000..c3fced410
--- /dev/null
+++ b/arch/riscv/kernel/patch.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <asm/kprobes.h>
+#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
+#include <asm/ftrace.h>
+#include <asm/patch.h>
+
+struct patch_insn {
+	void *addr;
+	u32 insn;
+	atomic_t cpu_count;
+};
+
+int riscv_patch_in_stop_machine = false;
+
+#ifdef CONFIG_MMU
+static void *patch_map(void *addr, int fixmap)
+{
+	uintptr_t uintaddr = (uintptr_t) addr;
+	struct page *page;
+
+	if (core_kernel_text(uintaddr))
+		page = phys_to_page(__pa_symbol(addr));
+	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		page = vmalloc_to_page(addr);
+	else
+		return addr;
+
+	BUG_ON(!page);
+
+	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
+					 (uintaddr & ~PAGE_MASK));
+}
+NOKPROBE_SYMBOL(patch_map);
+
+static void patch_unmap(int fixmap)
+{
+	clear_fixmap(fixmap);
+}
+NOKPROBE_SYMBOL(patch_unmap);
+
+static int patch_insn_write(void *addr, const void *insn, size_t len)
+{
+	void *waddr = addr;
+	bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE;
+	int ret;
+
+	/*
+	 * Before reaching here, it was expected to lock the text_mutex
+	 * already, so we don't need to give another lock here and could
+	 * ensure that it was safe between each cores.
+	 *
+	 * We're currently using stop_machine() for ftrace & kprobes, and while
+	 * that ensures text_mutex is held before installing the mappings it
+	 * does not ensure text_mutex is held by the calling thread.  That's
+	 * safe but triggers a lockdep failure, so just elide it for that
+	 * specific case.
+	 */
+	if (!riscv_patch_in_stop_machine)
+		lockdep_assert_held(&text_mutex);
+
+	if (across_pages)
+		patch_map(addr + len, FIX_TEXT_POKE1);
+
+	waddr = patch_map(addr, FIX_TEXT_POKE0);
+
+	ret = copy_to_kernel_nofault(waddr, insn, len);
+
+	patch_unmap(FIX_TEXT_POKE0);
+
+	if (across_pages)
+		patch_unmap(FIX_TEXT_POKE1);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_insn_write);
+#else
+static int patch_insn_write(void *addr, const void *insn, size_t len)
+{
+	return copy_to_kernel_nofault(addr, insn, len);
+}
+NOKPROBE_SYMBOL(patch_insn_write);
+#endif /* CONFIG_MMU */
+
+int patch_text_nosync(void *addr, const void *insns, size_t len)
+{
+	u32 *tp = addr;
+	int ret;
+
+	ret = patch_insn_write(tp, insns, len);
+
+	if (!ret)
+		flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_text_nosync);
+
+static int patch_text_cb(void *data)
+{
+	struct patch_insn *patch = data;
+	int ret = 0;
+
+	if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) {
+		ret =
+		    patch_text_nosync(patch->addr, &patch->insn,
+					    GET_INSN_LENGTH(patch->insn));
+		atomic_inc(&patch->cpu_count);
+	} else {
+		while (atomic_read(&patch->cpu_count) <= num_online_cpus())
+			cpu_relax();
+		smp_mb();
+	}
+
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_text_cb);
+
+int patch_text(void *addr, u32 insn)
+{
+	int ret;
+	struct patch_insn patch = {
+		.addr = addr,
+		.insn = insn,
+		.cpu_count = ATOMIC_INIT(0),
+	};
+
+	/*
+	 * kprobes takes text_mutex, before calling patch_text(), but as we call
+	 * calls stop_machine(), the lockdep assertion in patch_insn_write()
+	 * gets confused by the context in which the lock is taken.
+	 * Instead, ensure the lock is held before calling stop_machine(), and
+	 * set riscv_patch_in_stop_machine to skip the check in
+	 * patch_insn_write().
+	 */
+	lockdep_assert_held(&text_mutex);
+	riscv_patch_in_stop_machine = true;
+	ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask);
+	riscv_patch_in_stop_machine = false;
+	return ret;
+}
+NOKPROBE_SYMBOL(patch_text);
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
new file mode 100644
index 000000000..fb02811df
--- /dev/null
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+/* Kernel callchain */
+struct stackframe {
+	unsigned long fp;
+	unsigned long ra;
+};
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
+				    unsigned long fp, unsigned long reg_ra)
+{
+	struct stackframe buftail;
+	unsigned long ra = 0;
+	unsigned long __user *user_frame_tail =
+		(unsigned long __user *)(fp - sizeof(struct stackframe));
+
+	/* Check accessibility of one struct frame_tail beyond */
+	if (!access_ok(user_frame_tail, sizeof(buftail)))
+		return 0;
+	if (__copy_from_user_inatomic(&buftail, user_frame_tail,
+				      sizeof(buftail)))
+		return 0;
+
+	if (reg_ra != 0)
+		ra = reg_ra;
+	else
+		ra = buftail.ra;
+
+	fp = buftail.fp;
+	if (ra != 0)
+		perf_callchain_store(entry, ra);
+	else
+		return 0;
+
+	return fp;
+}
+
+/*
+ * This will be called when the target is in user mode
+ * This function will only be called when we use
+ * "PERF_SAMPLE_CALLCHAIN" in
+ * kernel/events/core.c:perf_prepare_sample()
+ *
+ * How to trigger perf_callchain_[user/kernel] :
+ * $ perf record -e cpu-clock --call-graph fp ./program
+ * $ perf report --call-graph
+ *
+ * On RISC-V platform, the program being sampled and the C library
+ * need to be compiled with -fno-omit-frame-pointer, otherwise
+ * the user stack will not contain function frame.
+ */
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
+{
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+	unsigned long fp = 0;
+
+	/* RISC-V does not support perf in guest mode. */
+	if (guest_cbs && guest_cbs->is_in_guest())
+		return;
+
+	fp = regs->s0;
+	perf_callchain_store(entry, regs->epc);
+
+	fp = user_backtrace(entry, fp, regs->ra);
+	while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
+		fp = user_backtrace(entry, fp, 0);
+}
+
+bool fill_callchain(unsigned long pc, void *entry)
+{
+	return perf_callchain_store(entry, pc) == 0;
+}
+
+void notrace walk_stackframe(struct task_struct *task,
+	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg);
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+
+	/* RISC-V does not support perf in guest mode. */
+	if (guest_cbs && guest_cbs->is_in_guest()) {
+		pr_warn("RISC-V does not support perf in guest mode!");
+		return;
+	}
+
+	walk_stackframe(NULL, regs, fill_callchain, entry);
+}
diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c
new file mode 100644
index 000000000..c835f0362
--- /dev/null
+++ b/arch/riscv/kernel/perf_event.c
@@ -0,0 +1,485 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
+ * Copyright (C) 2009 Jaswinder Singh Rajput
+ * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
+ * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
+ * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
+ * Copyright (C) 2009 Google, Inc., Stephane Eranian
+ * Copyright 2014 Tilera Corporation. All Rights Reserved.
+ * Copyright (C) 2018 Andes Technology Corporation
+ *
+ * Perf_events support for RISC-V platforms.
+ *
+ * Since the spec. (as of now, Priv-Spec 1.10) does not provide enough
+ * functionality for perf event to fully work, this file provides
+ * the very basic framework only.
+ *
+ * For platform portings, please check Documentations/riscv/pmu.txt.
+ *
+ * The Copyright line includes x86 and tile ones.
+ */
+
+#include <linux/kprobes.h>
+#include <linux/kernel.h>
+#include <linux/kdebug.h>
+#include <linux/mutex.h>
+#include <linux/bitmap.h>
+#include <linux/irq.h>
+#include <linux/perf_event.h>
+#include <linux/atomic.h>
+#include <linux/of.h>
+#include <asm/perf_event.h>
+
+static const struct riscv_pmu *riscv_pmu __read_mostly;
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+
+/*
+ * Hardware & cache maps and their methods
+ */
+
+static const int riscv_hw_event_map[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= RISCV_PMU_CYCLE,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= RISCV_PMU_INSTRET,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= RISCV_OP_UNSUPP,
+	[PERF_COUNT_HW_CACHE_MISSES]		= RISCV_OP_UNSUPP,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= RISCV_OP_UNSUPP,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= RISCV_OP_UNSUPP,
+	[PERF_COUNT_HW_BUS_CYCLES]		= RISCV_OP_UNSUPP,
+};
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+static const int riscv_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
+[PERF_COUNT_HW_CACHE_OP_MAX]
+[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] =  RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] =  RISCV_OP_UNSUPP,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
+			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
+		},
+	},
+};
+
+static int riscv_map_hw_event(u64 config)
+{
+	if (config >= riscv_pmu->max_events)
+		return -EINVAL;
+
+	return riscv_pmu->hw_events[config];
+}
+
+static int riscv_map_cache_decode(u64 config, unsigned int *type,
+			   unsigned int *op, unsigned int *result)
+{
+	return -ENOENT;
+}
+
+static int riscv_map_cache_event(u64 config)
+{
+	unsigned int type, op, result;
+	int err = -ENOENT;
+		int code;
+
+	err = riscv_map_cache_decode(config, &type, &op, &result);
+	if (!riscv_pmu->cache_events || err)
+		return err;
+
+	if (type >= PERF_COUNT_HW_CACHE_MAX ||
+	    op >= PERF_COUNT_HW_CACHE_OP_MAX ||
+	    result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return -EINVAL;
+
+	code = (*riscv_pmu->cache_events)[type][op][result];
+	if (code == RISCV_OP_UNSUPP)
+		return -EINVAL;
+
+	return code;
+}
+
+/*
+ * Low-level functions: reading/writing counters
+ */
+
+static inline u64 read_counter(int idx)
+{
+	u64 val = 0;
+
+	switch (idx) {
+	case RISCV_PMU_CYCLE:
+		val = csr_read(CSR_CYCLE);
+		break;
+	case RISCV_PMU_INSTRET:
+		val = csr_read(CSR_INSTRET);
+		break;
+	default:
+		WARN_ON_ONCE(idx < 0 ||	idx > RISCV_MAX_COUNTERS);
+		return -EINVAL;
+	}
+
+	return val;
+}
+
+static inline void write_counter(int idx, u64 value)
+{
+	/* currently not supported */
+	WARN_ON_ONCE(1);
+}
+
+/*
+ * pmu->read: read and update the counter
+ *
+ * Other architectures' implementation often have a xxx_perf_event_update
+ * routine, which can return counter values when called in the IRQ, but
+ * return void when being called by the pmu->read method.
+ */
+static void riscv_pmu_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev_raw_count, new_raw_count;
+	u64 oldval;
+	int idx = hwc->idx;
+	u64 delta;
+
+	do {
+		prev_raw_count = local64_read(&hwc->prev_count);
+		new_raw_count = read_counter(idx);
+
+		oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+					 new_raw_count);
+	} while (oldval != prev_raw_count);
+
+	/*
+	 * delta is the value to update the counter we maintain in the kernel.
+	 */
+	delta = (new_raw_count - prev_raw_count) &
+		((1ULL << riscv_pmu->counter_width) - 1);
+	local64_add(delta, &event->count);
+	/*
+	 * Something like local64_sub(delta, &hwc->period_left) here is
+	 * needed if there is an interrupt for perf.
+	 */
+}
+
+/*
+ * State transition functions:
+ *
+ * stop()/start() & add()/del()
+ */
+
+/*
+ * pmu->stop: stop the counter
+ */
+static void riscv_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+	hwc->state |= PERF_HES_STOPPED;
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		riscv_pmu->pmu->read(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+}
+
+/*
+ * pmu->start: start the event.
+ */
+static void riscv_pmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+		/*
+		 * Set the counter to the period to the next interrupt here,
+		 * if you have any.
+		 */
+	}
+
+	hwc->state = 0;
+	perf_event_update_userpage(event);
+
+	/*
+	 * Since we cannot write to counters, this serves as an initialization
+	 * to the delta-mechanism in pmu->read(); otherwise, the delta would be
+	 * wrong when pmu->read is called for the first time.
+	 */
+	local64_set(&hwc->prev_count, read_counter(hwc->idx));
+}
+
+/*
+ * pmu->add: add the event to PMU.
+ */
+static int riscv_pmu_add(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (cpuc->n_events == riscv_pmu->num_counters)
+		return -ENOSPC;
+
+	/*
+	 * We don't have general conunters, so no binding-event-to-counter
+	 * process here.
+	 *
+	 * Indexing using hwc->config generally not works, since config may
+	 * contain extra information, but here the only info we have in
+	 * hwc->config is the event index.
+	 */
+	hwc->idx = hwc->config;
+	cpuc->events[hwc->idx] = event;
+	cpuc->n_events++;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		riscv_pmu->pmu->start(event, PERF_EF_RELOAD);
+
+	return 0;
+}
+
+/*
+ * pmu->del: delete the event from PMU.
+ */
+static void riscv_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	cpuc->events[hwc->idx] = NULL;
+	cpuc->n_events--;
+	riscv_pmu->pmu->stop(event, PERF_EF_UPDATE);
+	perf_event_update_userpage(event);
+}
+
+/*
+ * Interrupt: a skeletion for reference.
+ */
+
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
+{
+	return IRQ_NONE;
+}
+
+static int reserve_pmc_hardware(void)
+{
+	int err = 0;
+
+	mutex_lock(&pmc_reserve_mutex);
+	if (riscv_pmu->irq >= 0 && riscv_pmu->handle_irq) {
+		err = request_irq(riscv_pmu->irq, riscv_pmu->handle_irq,
+				  IRQF_PERCPU, "riscv-base-perf", NULL);
+	}
+	mutex_unlock(&pmc_reserve_mutex);
+
+	return err;
+}
+
+static void release_pmc_hardware(void)
+{
+	mutex_lock(&pmc_reserve_mutex);
+	if (riscv_pmu->irq >= 0)
+		free_irq(riscv_pmu->irq, NULL);
+	mutex_unlock(&pmc_reserve_mutex);
+}
+
+/*
+ * Event Initialization/Finalization
+ */
+
+static atomic_t riscv_active_events = ATOMIC_INIT(0);
+
+static void riscv_event_destroy(struct perf_event *event)
+{
+	if (atomic_dec_return(&riscv_active_events) == 0)
+		release_pmc_hardware();
+}
+
+static int riscv_event_init(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	struct hw_perf_event *hwc = &event->hw;
+	int err;
+	int code;
+
+	if (atomic_inc_return(&riscv_active_events) == 1) {
+		err = reserve_pmc_hardware();
+
+		if (err) {
+			pr_warn("PMC hardware not available\n");
+			atomic_dec(&riscv_active_events);
+			return -EBUSY;
+		}
+	}
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		code = riscv_pmu->map_hw_event(attr->config);
+		break;
+	case PERF_TYPE_HW_CACHE:
+		code = riscv_pmu->map_cache_event(attr->config);
+		break;
+	case PERF_TYPE_RAW:
+		return -EOPNOTSUPP;
+	default:
+		return -ENOENT;
+	}
+
+	event->destroy = riscv_event_destroy;
+	if (code < 0) {
+		event->destroy(event);
+		return code;
+	}
+
+	/*
+	 * idx is set to -1 because the index of a general event should not be
+	 * decided until binding to some counter in pmu->add().
+	 *
+	 * But since we don't have such support, later in pmu->add(), we just
+	 * use hwc->config as the index instead.
+	 */
+	hwc->config = code;
+	hwc->idx = -1;
+
+	return 0;
+}
+
+/*
+ * Initialization
+ */
+
+static struct pmu min_pmu = {
+	.name		= "riscv-base",
+	.event_init	= riscv_event_init,
+	.add		= riscv_pmu_add,
+	.del		= riscv_pmu_del,
+	.start		= riscv_pmu_start,
+	.stop		= riscv_pmu_stop,
+	.read		= riscv_pmu_read,
+};
+
+static const struct riscv_pmu riscv_base_pmu = {
+	.pmu = &min_pmu,
+	.max_events = ARRAY_SIZE(riscv_hw_event_map),
+	.map_hw_event = riscv_map_hw_event,
+	.hw_events = riscv_hw_event_map,
+	.map_cache_event = riscv_map_cache_event,
+	.cache_events = &riscv_cache_event_map,
+	.counter_width = 63,
+	.num_counters = RISCV_BASE_COUNTERS + 0,
+	.handle_irq = &riscv_base_pmu_handle_irq,
+
+	/* This means this PMU has no IRQ. */
+	.irq = -1,
+};
+
+static const struct of_device_id riscv_pmu_of_ids[] = {
+	{.compatible = "riscv,base-pmu",	.data = &riscv_base_pmu},
+	{ /* sentinel value */ }
+};
+
+static int __init init_hw_perf_events(void)
+{
+	struct device_node *node = of_find_node_by_type(NULL, "pmu");
+	const struct of_device_id *of_id;
+
+	riscv_pmu = &riscv_base_pmu;
+
+	if (node) {
+		of_id = of_match_node(riscv_pmu_of_ids, node);
+
+		if (of_id)
+			riscv_pmu = of_id->data;
+		of_node_put(node);
+	}
+
+	perf_pmu_register(riscv_pmu->pmu, "cpu", PERF_TYPE_RAW);
+	return 0;
+}
+arch_initcall(init_hw_perf_events);
diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
new file mode 100644
index 000000000..fd304a248
--- /dev/null
+++ b/arch/riscv/kernel/perf_regs.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_RISCV_MAX))
+		return 0;
+
+	return ((unsigned long *)regs)[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_RISCV_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+#if __riscv_xlen == 64
+	return PERF_SAMPLE_REGS_ABI_64;
+#else
+	return PERF_SAMPLE_REGS_ABI_32;
+#endif
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
new file mode 100644
index 000000000..7868050ff
--- /dev/null
+++ b/arch/riscv/kernel/process.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/cpu.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tick.h>
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/unistd.h>
+#include <asm/processor.h>
+#include <asm/csr.h>
+#include <asm/string.h>
+#include <asm/switch_to.h>
+#include <asm/thread_info.h>
+
+register unsigned long gp_in_global __asm__("gp");
+
+#ifdef CONFIG_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
+extern asmlinkage void ret_from_fork(void);
+extern asmlinkage void ret_from_kernel_thread(void);
+
+void arch_cpu_idle(void)
+{
+	wait_for_interrupt();
+	raw_local_irq_enable();
+}
+
+void show_regs(struct pt_regs *regs)
+{
+	show_regs_print_info(KERN_DEFAULT);
+
+	pr_cont("epc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
+		regs->epc, regs->ra, regs->sp);
+	pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n",
+		regs->gp, regs->tp, regs->t0);
+	pr_cont(" t1 : " REG_FMT " t2 : " REG_FMT " s0 : " REG_FMT "\n",
+		regs->t1, regs->t2, regs->s0);
+	pr_cont(" s1 : " REG_FMT " a0 : " REG_FMT " a1 : " REG_FMT "\n",
+		regs->s1, regs->a0, regs->a1);
+	pr_cont(" a2 : " REG_FMT " a3 : " REG_FMT " a4 : " REG_FMT "\n",
+		regs->a2, regs->a3, regs->a4);
+	pr_cont(" a5 : " REG_FMT " a6 : " REG_FMT " a7 : " REG_FMT "\n",
+		regs->a5, regs->a6, regs->a7);
+	pr_cont(" s2 : " REG_FMT " s3 : " REG_FMT " s4 : " REG_FMT "\n",
+		regs->s2, regs->s3, regs->s4);
+	pr_cont(" s5 : " REG_FMT " s6 : " REG_FMT " s7 : " REG_FMT "\n",
+		regs->s5, regs->s6, regs->s7);
+	pr_cont(" s8 : " REG_FMT " s9 : " REG_FMT " s10: " REG_FMT "\n",
+		regs->s8, regs->s9, regs->s10);
+	pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n",
+		regs->s11, regs->t3, regs->t4);
+	pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT "\n",
+		regs->t5, regs->t6);
+
+	pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n",
+		regs->status, regs->badaddr, regs->cause);
+}
+
+void start_thread(struct pt_regs *regs, unsigned long pc,
+	unsigned long sp)
+{
+	regs->status = SR_PIE;
+	if (has_fpu) {
+		regs->status |= SR_FS_INITIAL;
+		/*
+		 * Restore the initial value to the FP register
+		 * before starting the user program.
+		 */
+		fstate_restore(current, regs);
+	}
+	regs->epc = pc;
+	regs->sp = sp;
+}
+
+void flush_thread(void)
+{
+#ifdef CONFIG_FPU
+	/*
+	 * Reset FPU state and context
+	 *	frm: round to nearest, ties to even (IEEE default)
+	 *	fflags: accrued exceptions cleared
+	 */
+	fstate_off(current, task_pt_regs(current));
+	memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
+#endif
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	fstate_save(src, task_pt_regs(src));
+	*dst = *src;
+	return 0;
+}
+
+int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
+{
+	struct pt_regs *childregs = task_pt_regs(p);
+
+	memset(&p->thread.s, 0, sizeof(p->thread.s));
+
+	/* p->thread holds context to be restored by __switch_to() */
+	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+		/* Kernel thread */
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->gp = gp_in_global;
+		/* Supervisor/Machine, irqs on: */
+		childregs->status = SR_PP | SR_PIE;
+
+		p->thread.ra = (unsigned long)ret_from_kernel_thread;
+		p->thread.s[0] = usp; /* fn */
+		p->thread.s[1] = arg;
+	} else {
+		*childregs = *(current_pt_regs());
+		if (usp) /* User fork */
+			childregs->sp = usp;
+		if (clone_flags & CLONE_SETTLS)
+			childregs->tp = tls;
+		childregs->a0 = 0; /* Return value of fork() */
+		p->thread.ra = (unsigned long)ret_from_fork;
+	}
+	p->thread.sp = (unsigned long)childregs; /* kernel sp */
+	return 0;
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
new file mode 100644
index 000000000..69678ab64
--- /dev/null
+++ b/arch/riscv/kernel/ptrace.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2015 Regents of the University of California
+ * Copyright 2017 SiFive
+ *
+ * Copied from arch/tile/kernel/ptrace.c
+ */
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+#include <asm/thread_info.h>
+#include <asm/switch_to.h>
+#include <linux/audit.h>
+#include <linux/ptrace.h>
+#include <linux/elf.h>
+#include <linux/regset.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/tracehook.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+enum riscv_regset {
+	REGSET_X,
+#ifdef CONFIG_FPU
+	REGSET_F,
+#endif
+};
+
+static int riscv_gpr_get(struct task_struct *target,
+			 const struct user_regset *regset,
+			 struct membuf to)
+{
+	return membuf_write(&to, task_pt_regs(target),
+			    sizeof(struct user_regs_struct));
+}
+
+static int riscv_gpr_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;
+	struct pt_regs *regs;
+
+	regs = task_pt_regs(target);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
+	return ret;
+}
+
+#ifdef CONFIG_FPU
+static int riscv_fpr_get(struct task_struct *target,
+			 const struct user_regset *regset,
+			 struct membuf to)
+{
+	struct __riscv_d_ext_state *fstate = &target->thread.fstate;
+
+	if (target == current)
+		fstate_save(current, task_pt_regs(current));
+
+	membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr));
+	membuf_store(&to, fstate->fcsr);
+	return membuf_zero(&to, 4);	// explicitly pad
+}
+
+static int riscv_fpr_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;
+	struct __riscv_d_ext_state *fstate = &target->thread.fstate;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
+				 offsetof(struct __riscv_d_ext_state, fcsr));
+	if (!ret) {
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
+					 offsetof(struct __riscv_d_ext_state, fcsr) +
+					 sizeof(fstate->fcsr));
+	}
+
+	return ret;
+}
+#endif
+
+static const struct user_regset riscv_user_regset[] = {
+	[REGSET_X] = {
+		.core_note_type = NT_PRSTATUS,
+		.n = ELF_NGREG,
+		.size = sizeof(elf_greg_t),
+		.align = sizeof(elf_greg_t),
+		.regset_get = riscv_gpr_get,
+		.set = riscv_gpr_set,
+	},
+#ifdef CONFIG_FPU
+	[REGSET_F] = {
+		.core_note_type = NT_PRFPREG,
+		.n = ELF_NFPREG,
+		.size = sizeof(elf_fpreg_t),
+		.align = sizeof(elf_fpreg_t),
+		.regset_get = riscv_fpr_get,
+		.set = riscv_fpr_set,
+	},
+#endif
+};
+
+static const struct user_regset_view riscv_user_native_view = {
+	.name = "riscv",
+	.e_machine = EM_RISCV,
+	.regsets = riscv_user_regset,
+	.n = ARRAY_SIZE(riscv_user_regset),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	return &riscv_user_native_view;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	long ret = -EIO;
+
+	switch (request) {
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Allows PTRACE_SYSCALL to work.  These are called from entry.S in
+ * {handle,ret_from}_syscall.
+ */
+__visible int do_syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		if (tracehook_report_syscall_entry(regs))
+			return -1;
+
+	/*
+	 * Do the secure computing after ptrace; failures should be fast.
+	 * If this fails we might have return value in a0 from seccomp
+	 * (via SECCOMP_RET_ERRNO/TRACE).
+	 */
+	if (secure_computing() == -1)
+		return -1;
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, syscall_get_nr(current, regs));
+#endif
+
+	audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
+	return 0;
+}
+
+__visible void do_syscall_trace_exit(struct pt_regs *regs)
+{
+	audit_syscall_exit(regs);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall_exit(regs, 0);
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, regs_return_value(regs));
+#endif
+}
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
new file mode 100644
index 000000000..9c842c416
--- /dev/null
+++ b/arch/riscv/kernel/reset.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/reboot.h>
+#include <linux/pm.h>
+
+static void default_power_off(void)
+{
+	while (1)
+		wait_for_interrupt();
+}
+
+void (*pm_power_off)(void) = NULL;
+EXPORT_SYMBOL(pm_power_off);
+
+void machine_restart(char *cmd)
+{
+	do_kernel_restart(cmd);
+	while (1);
+}
+
+void machine_halt(void)
+{
+	if (pm_power_off != NULL)
+		pm_power_off();
+	else
+		default_power_off();
+}
+
+void machine_power_off(void)
+{
+	if (pm_power_off != NULL)
+		pm_power_off();
+	else
+		default_power_off();
+}
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
new file mode 100644
index 000000000..450492e1c
--- /dev/null
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 Zihao Yu
+ */
+
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+/*
+ * Assembly functions that may be used (directly or indirectly) by modules
+ */
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(__memcpy);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
new file mode 100644
index 000000000..226ccce0f
--- /dev/null
+++ b/arch/riscv/kernel/sbi.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SBI initialilization and all extension implementation.
+ *
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+/* default SBI version is 0.1 */
+unsigned long sbi_spec_version = SBI_SPEC_VERSION_DEFAULT;
+EXPORT_SYMBOL(sbi_spec_version);
+
+static void (*__sbi_set_timer)(uint64_t stime);
+static int (*__sbi_send_ipi)(const unsigned long *hart_mask);
+static int (*__sbi_rfence)(int fid, const unsigned long *hart_mask,
+			   unsigned long start, unsigned long size,
+			   unsigned long arg4, unsigned long arg5);
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+			unsigned long arg1, unsigned long arg2,
+			unsigned long arg3, unsigned long arg4,
+			unsigned long arg5)
+{
+	struct sbiret ret;
+
+	register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+	register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+	register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+	register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+	register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+	register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+	register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+	register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+	asm volatile ("ecall"
+		      : "+r" (a0), "+r" (a1)
+		      : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+		      : "memory");
+	ret.error = a0;
+	ret.value = a1;
+
+	return ret;
+}
+EXPORT_SYMBOL(sbi_ecall);
+
+int sbi_err_map_linux_errno(int err)
+{
+	switch (err) {
+	case SBI_SUCCESS:
+		return 0;
+	case SBI_ERR_DENIED:
+		return -EPERM;
+	case SBI_ERR_INVALID_PARAM:
+		return -EINVAL;
+	case SBI_ERR_INVALID_ADDRESS:
+		return -EFAULT;
+	case SBI_ERR_NOT_SUPPORTED:
+	case SBI_ERR_FAILURE:
+	default:
+		return -ENOTSUPP;
+	};
+}
+EXPORT_SYMBOL(sbi_err_map_linux_errno);
+
+#ifdef CONFIG_RISCV_SBI_V01
+/**
+ * sbi_console_putchar() - Writes given character to the console device.
+ * @ch: The data to be written to the console.
+ *
+ * Return: None
+ */
+void sbi_console_putchar(int ch)
+{
+	sbi_ecall(SBI_EXT_0_1_CONSOLE_PUTCHAR, 0, ch, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_console_putchar);
+
+/**
+ * sbi_console_getchar() - Reads a byte from console device.
+ *
+ * Returns the value read from console.
+ */
+int sbi_console_getchar(void)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_0_1_CONSOLE_GETCHAR, 0, 0, 0, 0, 0, 0, 0);
+
+	return ret.error;
+}
+EXPORT_SYMBOL(sbi_console_getchar);
+
+/**
+ * sbi_shutdown() - Remove all the harts from executing supervisor code.
+ *
+ * Return: None
+ */
+void sbi_shutdown(void)
+{
+	sbi_ecall(SBI_EXT_0_1_SHUTDOWN, 0, 0, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_shutdown);
+
+/**
+ * sbi_clear_ipi() - Clear any pending IPIs for the calling hart.
+ *
+ * Return: None
+ */
+void sbi_clear_ipi(void)
+{
+	sbi_ecall(SBI_EXT_0_1_CLEAR_IPI, 0, 0, 0, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_clear_ipi);
+
+/**
+ * sbi_set_timer_v01() - Program the timer for next timer event.
+ * @stime_value: The value after which next timer event should fire.
+ *
+ * Return: None
+ */
+static void __sbi_set_timer_v01(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+	sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value,
+		  stime_value >> 32, 0, 0, 0, 0);
+#else
+	sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value, 0, 0, 0, 0, 0);
+#endif
+}
+
+static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+{
+	sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)hart_mask,
+		  0, 0, 0, 0, 0);
+	return 0;
+}
+
+static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+			    unsigned long start, unsigned long size,
+			    unsigned long arg4, unsigned long arg5)
+{
+	int result = 0;
+
+	/* v0.2 function IDs are equivalent to v0.1 extension IDs */
+	switch (fid) {
+	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+		sbi_ecall(SBI_EXT_0_1_REMOTE_FENCE_I, 0,
+			  (unsigned long)hart_mask, 0, 0, 0, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+		sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA, 0,
+			  (unsigned long)hart_mask, start, size,
+			  0, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+		sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID, 0,
+			  (unsigned long)hart_mask, start, size,
+			  arg4, 0, 0);
+		break;
+	default:
+		pr_err("SBI call [%d]not supported in SBI v0.1\n", fid);
+		result = -EINVAL;
+	}
+
+	return result;
+}
+
+static void sbi_set_power_off(void)
+{
+	pm_power_off = sbi_shutdown;
+}
+#else
+static void __sbi_set_timer_v01(uint64_t stime_value)
+{
+	pr_warn("Timer extension is not available in SBI v%lu.%lu\n",
+		sbi_major_version(), sbi_minor_version());
+}
+
+static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+{
+	pr_warn("IPI extension is not available in SBI v%lu.%lu\n",
+		sbi_major_version(), sbi_minor_version());
+
+	return 0;
+}
+
+static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+			    unsigned long start, unsigned long size,
+			    unsigned long arg4, unsigned long arg5)
+{
+	pr_warn("remote fence extension is not available in SBI v%lu.%lu\n",
+		sbi_major_version(), sbi_minor_version());
+
+	return 0;
+}
+
+static void sbi_set_power_off(void) {}
+#endif /* CONFIG_RISCV_SBI_V01 */
+
+static void __sbi_set_timer_v02(uint64_t stime_value)
+{
+#if __riscv_xlen == 32
+	sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value,
+		  stime_value >> 32, 0, 0, 0, 0);
+#else
+	sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value, 0,
+		  0, 0, 0, 0);
+#endif
+}
+
+static int __sbi_send_ipi_v02(const unsigned long *hart_mask)
+{
+	unsigned long hartid, hmask_val, hbase;
+	struct cpumask tmask;
+	struct sbiret ret = {0};
+	int result;
+
+	if (!hart_mask || !(*hart_mask)) {
+		riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
+		hart_mask = cpumask_bits(&tmask);
+	}
+
+	hmask_val = 0;
+	hbase = 0;
+	for_each_set_bit(hartid, hart_mask, NR_CPUS) {
+		if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
+			ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
+					hmask_val, hbase, 0, 0, 0, 0);
+			if (ret.error)
+				goto ecall_failed;
+			hmask_val = 0;
+			hbase = 0;
+		}
+		if (!hmask_val)
+			hbase = hartid;
+		hmask_val |= 1UL << (hartid - hbase);
+	}
+
+	if (hmask_val) {
+		ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
+				hmask_val, hbase, 0, 0, 0, 0);
+		if (ret.error)
+			goto ecall_failed;
+	}
+
+	return 0;
+
+ecall_failed:
+	result = sbi_err_map_linux_errno(ret.error);
+	pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
+	       __func__, hbase, hmask_val, result);
+	return result;
+}
+
+static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
+				 unsigned long hbase, unsigned long start,
+				 unsigned long size, unsigned long arg4,
+				 unsigned long arg5)
+{
+	struct sbiret ret = {0};
+	int ext = SBI_EXT_RFENCE;
+	int result = 0;
+
+	switch (fid) {
+	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
+		ret = sbi_ecall(ext, fid, hmask_val, hbase, 0, 0, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
+		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+				size, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
+		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+				size, arg4, 0);
+		break;
+
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
+		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+				size, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID:
+		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+				size, arg4, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA:
+		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+				size, 0, 0);
+		break;
+	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
+		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+				size, arg4, 0);
+		break;
+	default:
+		pr_err("unknown function ID [%lu] for SBI extension [%d]\n",
+		       fid, ext);
+		result = -EINVAL;
+	}
+
+	if (ret.error) {
+		result = sbi_err_map_linux_errno(ret.error);
+		pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
+		       __func__, hbase, hmask_val, result);
+	}
+
+	return result;
+}
+
+static int __sbi_rfence_v02(int fid, const unsigned long *hart_mask,
+			    unsigned long start, unsigned long size,
+			    unsigned long arg4, unsigned long arg5)
+{
+	unsigned long hmask_val, hartid, hbase;
+	struct cpumask tmask;
+	int result;
+
+	if (!hart_mask || !(*hart_mask)) {
+		riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
+		hart_mask = cpumask_bits(&tmask);
+	}
+
+	hmask_val = 0;
+	hbase = 0;
+	for_each_set_bit(hartid, hart_mask, NR_CPUS) {
+		if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
+			result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+						       start, size, arg4, arg5);
+			if (result)
+				return result;
+			hmask_val = 0;
+			hbase = 0;
+		}
+		if (!hmask_val)
+			hbase = hartid;
+		hmask_val |= 1UL << (hartid - hbase);
+	}
+
+	if (hmask_val) {
+		result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+					       start, size, arg4, arg5);
+		if (result)
+			return result;
+	}
+
+	return 0;
+}
+
+/**
+ * sbi_set_timer() - Program the timer for next timer event.
+ * @stime_value: The value after which next timer event should fire.
+ *
+ * Return: None
+ */
+void sbi_set_timer(uint64_t stime_value)
+{
+	__sbi_set_timer(stime_value);
+}
+
+/**
+ * sbi_send_ipi() - Send an IPI to any hart.
+ * @hart_mask: A cpu mask containing all the target harts.
+ *
+ * Return: None
+ */
+void sbi_send_ipi(const unsigned long *hart_mask)
+{
+	__sbi_send_ipi(hart_mask);
+}
+EXPORT_SYMBOL(sbi_send_ipi);
+
+/**
+ * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts.
+ * @hart_mask: A cpu mask containing all the target harts.
+ *
+ * Return: None
+ */
+void sbi_remote_fence_i(const unsigned long *hart_mask)
+{
+	__sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I,
+		     hart_mask, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_fence_i);
+
+/**
+ * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
+ *			     harts for the specified virtual address range.
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the virtual address
+ * @size: Total size of the virtual address range.
+ *
+ * Return: None
+ */
+void sbi_remote_sfence_vma(const unsigned long *hart_mask,
+			   unsigned long start,
+			   unsigned long size)
+{
+	__sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+		     hart_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_sfence_vma);
+
+/**
+ * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
+ * remote harts for a virtual address range belonging to a specific ASID.
+ *
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the virtual address
+ * @size: Total size of the virtual address range.
+ * @asid: The value of address space identifier (ASID).
+ *
+ * Return: None
+ */
+void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid)
+{
+	__sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+		     hart_mask, start, size, asid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
+
+/**
+ * sbi_remote_hfence_gvma() - Execute HFENCE.GVMA instructions on given remote
+ *			   harts for the specified guest physical address range.
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the guest physical address
+ * @size: Total size of the guest physical address range.
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_gvma(const unsigned long *hart_mask,
+			   unsigned long start,
+			   unsigned long size)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
+			    hart_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma);
+
+/**
+ * sbi_remote_hfence_gvma_vmid() - Execute HFENCE.GVMA instructions on given
+ * remote harts for a guest physical address range belonging to a specific VMID.
+ *
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the guest physical address
+ * @size: Total size of the guest physical address range.
+ * @vmid: The value of guest ID (VMID).
+ *
+ * Return: 0 if success, Error otherwise.
+ */
+int sbi_remote_hfence_gvma_vmid(const unsigned long *hart_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long vmid)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
+			    hart_mask, start, size, vmid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_gvma_vmid);
+
+/**
+ * sbi_remote_hfence_vvma() - Execute HFENCE.VVMA instructions on given remote
+ *			     harts for the current guest virtual address range.
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the current guest virtual address
+ * @size: Total size of the current guest virtual address range.
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_vvma(const unsigned long *hart_mask,
+			   unsigned long start,
+			   unsigned long size)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+			    hart_mask, start, size, 0, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_vvma);
+
+/**
+ * sbi_remote_hfence_vvma_asid() - Execute HFENCE.VVMA instructions on given
+ * remote harts for current guest virtual address range belonging to a specific
+ * ASID.
+ *
+ * @hart_mask: A cpu mask containing all the target harts.
+ * @start: Start of the current guest virtual address
+ * @size: Total size of the current guest virtual address range.
+ * @asid: The value of address space identifier (ASID).
+ *
+ * Return: None
+ */
+int sbi_remote_hfence_vvma_asid(const unsigned long *hart_mask,
+				unsigned long start,
+				unsigned long size,
+				unsigned long asid)
+{
+	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+			    hart_mask, start, size, asid, 0);
+}
+EXPORT_SYMBOL(sbi_remote_hfence_vvma_asid);
+
+/**
+ * sbi_probe_extension() - Check if an SBI extension ID is supported or not.
+ * @extid: The extension ID to be probed.
+ *
+ * Return: Extension specific nonzero value f yes, -ENOTSUPP otherwise.
+ */
+int sbi_probe_extension(int extid)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid,
+			0, 0, 0, 0, 0);
+	if (!ret.error)
+		if (ret.value)
+			return ret.value;
+
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(sbi_probe_extension);
+
+static long __sbi_base_ecall(int fid)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_BASE, fid, 0, 0, 0, 0, 0, 0);
+	if (!ret.error)
+		return ret.value;
+	else
+		return sbi_err_map_linux_errno(ret.error);
+}
+
+static inline long sbi_get_spec_version(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_SPEC_VERSION);
+}
+
+static inline long sbi_get_firmware_id(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_ID);
+}
+
+static inline long sbi_get_firmware_version(void)
+{
+	return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION);
+}
+
+static void sbi_send_cpumask_ipi(const struct cpumask *target)
+{
+	struct cpumask hartid_mask;
+
+	riscv_cpuid_to_hartid_mask(target, &hartid_mask);
+
+	sbi_send_ipi(cpumask_bits(&hartid_mask));
+}
+
+static struct riscv_ipi_ops sbi_ipi_ops = {
+	.ipi_inject = sbi_send_cpumask_ipi
+};
+
+int __init sbi_init(void)
+{
+	int ret;
+
+	sbi_set_power_off();
+	ret = sbi_get_spec_version();
+	if (ret > 0)
+		sbi_spec_version = ret;
+
+	pr_info("SBI specification v%lu.%lu detected\n",
+		sbi_major_version(), sbi_minor_version());
+
+	if (!sbi_spec_is_0_1()) {
+		pr_info("SBI implementation ID=0x%lx Version=0x%lx\n",
+			sbi_get_firmware_id(), sbi_get_firmware_version());
+		if (sbi_probe_extension(SBI_EXT_TIME) > 0) {
+			__sbi_set_timer = __sbi_set_timer_v02;
+			pr_info("SBI v0.2 TIME extension detected\n");
+		} else {
+			__sbi_set_timer = __sbi_set_timer_v01;
+		}
+		if (sbi_probe_extension(SBI_EXT_IPI) > 0) {
+			__sbi_send_ipi	= __sbi_send_ipi_v02;
+			pr_info("SBI v0.2 IPI extension detected\n");
+		} else {
+			__sbi_send_ipi	= __sbi_send_ipi_v01;
+		}
+		if (sbi_probe_extension(SBI_EXT_RFENCE) > 0) {
+			__sbi_rfence	= __sbi_rfence_v02;
+			pr_info("SBI v0.2 RFENCE extension detected\n");
+		} else {
+			__sbi_rfence	= __sbi_rfence_v01;
+		}
+	} else {
+		__sbi_set_timer = __sbi_set_timer_v01;
+		__sbi_send_ipi	= __sbi_send_ipi_v01;
+		__sbi_rfence	= __sbi_rfence_v01;
+	}
+
+	riscv_set_ipi_ops(&sbi_ipi_ops);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
new file mode 100644
index 000000000..8e78a8ab6
--- /dev/null
+++ b/arch/riscv/kernel/setup.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/sched.h>
+#include <linux/console.h>
+#include <linux/screen_info.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/sched/task.h>
+#include <linux/swiotlb.h>
+#include <linux/smp.h>
+#include <linux/efi.h>
+
+#include <asm/cpu_ops.h>
+#include <asm/early_ioremap.h>
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/thread_info.h>
+#include <asm/kasan.h>
+#include <asm/efi.h>
+
+#include "head.h"
+
+#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI)
+struct screen_info screen_info __section(".data") = {
+	.orig_video_lines	= 30,
+	.orig_video_cols	= 80,
+	.orig_video_mode	= 0,
+	.orig_video_ega_bx	= 0,
+	.orig_video_isVGA	= 1,
+	.orig_video_points	= 8
+};
+#endif
+
+/*
+ * The lucky hart to first increment this variable will boot the other cores.
+ * This is used before the kernel initializes the BSS so it can't be in the
+ * BSS.
+ */
+atomic_t hart_lottery __section(".sdata");
+unsigned long boot_cpu_hartid;
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+static void __init parse_dtb(void)
+{
+	/* Early scan of device tree from init memory */
+	if (early_init_dt_scan(dtb_early_va)) {
+		const char *name = of_flat_dt_get_machine_name();
+
+		if (name) {
+			pr_info("Machine model: %s\n", name);
+			dump_stack_set_arch_desc("%s (DT)", name);
+		}
+	} else {
+		pr_err("No DTB passed to the kernel\n");
+	}
+
+#ifdef CONFIG_CMDLINE_FORCE
+	strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+	pr_info("Forcing kernel command line to: %s\n", boot_command_line);
+#endif
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	parse_dtb();
+	init_mm.start_code = (unsigned long) _stext;
+	init_mm.end_code   = (unsigned long) _etext;
+	init_mm.end_data   = (unsigned long) _edata;
+	init_mm.brk        = (unsigned long) _end;
+
+	*cmdline_p = boot_command_line;
+
+	early_ioremap_setup();
+	jump_label_init();
+	parse_early_param();
+
+	efi_init();
+	setup_bootmem();
+	paging_init();
+#if IS_ENABLED(CONFIG_BUILTIN_DTB)
+	unflatten_and_copy_device_tree();
+#else
+	if (early_init_dt_verify(__va(dtb_early_pa)))
+		unflatten_device_tree();
+	else
+		pr_err("No DTB found in kernel mappings\n");
+#endif
+	early_init_fdt_scan_reserved_mem();
+	misc_mem_init();
+
+#ifdef CONFIG_SWIOTLB
+	swiotlb_init(1);
+#endif
+
+#ifdef CONFIG_KASAN
+	kasan_init();
+#endif
+
+#if IS_ENABLED(CONFIG_RISCV_SBI)
+	sbi_init();
+#endif
+
+#ifdef CONFIG_SMP
+	setup_smp();
+#endif
+
+	riscv_fill_hwcap();
+}
+
+static int __init topology_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct cpu *cpu = &per_cpu(cpu_devices, i);
+
+		cpu->hotpluggable = cpu_has_hotplug(i);
+		register_cpu(cpu, i);
+	}
+
+	return 0;
+}
+subsys_initcall(topology_init);
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
new file mode 100644
index 000000000..dd63407e8
--- /dev/null
+++ b/arch/riscv/kernel/signal.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/tracehook.h>
+#include <linux/linkage.h>
+
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/switch_to.h>
+#include <asm/csr.h>
+#include <asm/cacheflush.h>
+
+extern u32 __user_rt_sigreturn[2];
+
+#define DEBUG_SIG 0
+
+struct rt_sigframe {
+	struct siginfo info;
+	struct ucontext uc;
+#ifndef CONFIG_MMU
+	u32 sigreturn_code[2];
+#endif
+};
+
+#ifdef CONFIG_FPU
+static long restore_fp_state(struct pt_regs *regs,
+			     union __riscv_fp_state __user *sc_fpregs)
+{
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
+	err = __copy_from_user(&current->thread.fstate, state, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	fstate_restore(current, regs);
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		u32 value;
+
+		err = __get_user(value, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+		if (value != 0)
+			return -EINVAL;
+	}
+
+	return err;
+}
+
+static long save_fp_state(struct pt_regs *regs,
+			  union __riscv_fp_state __user *sc_fpregs)
+{
+	long err;
+	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
+	size_t i;
+
+	fstate_save(current, regs);
+	err = __copy_to_user(state, &current->thread.fstate, sizeof(*state));
+	if (unlikely(err))
+		return err;
+
+	/* We support no other extension state at this time. */
+	for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) {
+		err = __put_user(0, &sc_fpregs->q.reserved[i]);
+		if (unlikely(err))
+			break;
+	}
+
+	return err;
+}
+#else
+#define save_fp_state(task, regs) (0)
+#define restore_fp_state(task, regs) (0)
+#endif
+
+static long restore_sigcontext(struct pt_regs *regs,
+	struct sigcontext __user *sc)
+{
+	long err;
+	/* 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);
+	return err;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+	struct pt_regs *regs = current_pt_regs();
+	struct rt_sigframe __user *frame;
+	struct task_struct *task;
+	sigset_t set;
+
+	/* 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)))
+		goto badframe;
+
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	set_current_blocked(&set);
+
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+		goto badframe;
+
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
+
+	regs->cause = -1UL;
+
+	return regs->a0;
+
+badframe:
+	task = current;
+	if (show_unhandled_signals) {
+		pr_info_ratelimited(
+			"%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n",
+			task->comm, task_pid_nr(task), __func__,
+			frame, (void *)regs->epc, (void *)regs->sp);
+	}
+	force_sig(SIGSEGV);
+	return 0;
+}
+
+static long setup_sigcontext(struct rt_sigframe __user *frame,
+	struct pt_regs *regs)
+{
+	struct sigcontext __user *sc = &frame->uc.uc_mcontext;
+	long err;
+	/* 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);
+	return err;
+}
+
+static inline void __user *get_sigframe(struct ksignal *ksig,
+	struct pt_regs *regs, size_t framesize)
+{
+	unsigned long sp;
+	/* Default to using normal stack */
+	sp = regs->sp;
+
+	/*
+	 * If we are on the alternate signal stack and would overflow it, don't.
+	 * Return an always-bogus address instead so we will die with SIGSEGV.
+	 */
+	if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize)))
+		return (void __user __force *)(-1UL);
+
+	/* This is the X/Open sanctioned signal stack switching. */
+	sp = sigsp(sp, ksig) - framesize;
+
+	/* Align the stack frame. */
+	sp &= ~0xfUL;
+
+	return (void __user *)sp;
+}
+
+static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+	struct pt_regs *regs)
+{
+	struct rt_sigframe __user *frame;
+	long err = 0;
+	unsigned long __maybe_unused addr;
+
+	frame = get_sigframe(ksig, regs, sizeof(*frame));
+	if (!access_ok(frame, sizeof(*frame)))
+		return -EFAULT;
+
+	err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+	/* Create the ucontext. */
+	err |= __put_user(0, &frame->uc.uc_flags);
+	err |= __put_user(NULL, &frame->uc.uc_link);
+	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+	err |= setup_sigcontext(frame, regs);
+	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+	if (err)
+		return -EFAULT;
+
+	/* Set up to return from userspace. */
+#ifdef CONFIG_MMU
+	regs->ra = (unsigned long)VDSO_SYMBOL(
+		current->mm->context.vdso, rt_sigreturn);
+#else
+	/*
+	 * For the nommu case we don't have a VDSO.  Instead we push two
+	 * instructions to call the rt_sigreturn syscall onto the user stack.
+	 */
+	if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn,
+			 sizeof(frame->sigreturn_code)))
+		return -EFAULT;
+
+	addr = (unsigned long)&frame->sigreturn_code;
+	/* Make sure the two instructions are pushed to icache. */
+	flush_icache_range(addr, addr + sizeof(frame->sigreturn_code));
+
+	regs->ra = addr;
+#endif /* CONFIG_MMU */
+
+	/*
+	 * Set up registers for signal handler.
+	 * Registers that we don't modify keep the value they had from
+	 * user-space at the time we took the signal.
+	 * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+	 * since some things rely on this (e.g. glibc's debug/segfault.c).
+	 */
+	regs->epc = (unsigned long)ksig->ka.sa.sa_handler;
+	regs->sp = (unsigned long)frame;
+	regs->a0 = ksig->sig;                     /* a0: signal number */
+	regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */
+	regs->a2 = (unsigned long)(&frame->uc);   /* a2: ucontext pointer */
+
+#if DEBUG_SIG
+	pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n",
+		current->comm, task_pid_nr(current), ksig->sig,
+		(void *)regs->epc, (void *)regs->ra, frame);
+#endif
+
+	return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int ret;
+
+	/* Are we from a system call? */
+	if (regs->cause == EXC_SYSCALL) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		regs->cause = -1UL;
+		/* If so, check system call restarting.. */
+		switch (regs->a0) {
+		case -ERESTART_RESTARTBLOCK:
+		case -ERESTARTNOHAND:
+			regs->a0 = -EINTR;
+			break;
+
+		case -ERESTARTSYS:
+			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+				regs->a0 = -EINTR;
+				break;
+			}
+			fallthrough;
+		case -ERESTARTNOINTR:
+                        regs->a0 = regs->orig_a0;
+			regs->epc -= 0x4;
+			break;
+		}
+	}
+
+	/* Set up the stack frame */
+	ret = setup_rt_frame(ksig, oldset, regs);
+
+	signal_setup_done(ret, ksig, 0);
+}
+
+static void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+
+	if (get_signal(&ksig)) {
+		/* Actually deliver the signal */
+		handle_signal(&ksig, regs);
+		return;
+	}
+
+	/* Did we come from a system call? */
+	if (regs->cause == EXC_SYSCALL) {
+		/* Avoid additional syscall restarting via ret_from_exception */
+		regs->cause = -1UL;
+
+		/* Restart the system call - no handlers present */
+		switch (regs->a0) {
+		case -ERESTARTNOHAND:
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+                        regs->a0 = regs->orig_a0;
+			regs->epc -= 0x4;
+			break;
+		case -ERESTART_RESTARTBLOCK:
+                        regs->a0 = regs->orig_a0;
+			regs->a7 = __NR_restart_syscall;
+			regs->epc -= 0x4;
+			break;
+		}
+	}
+
+	/*
+	 * If there is no signal to deliver, we just put the saved
+	 * sigmask back.
+	 */
+	restore_saved_sigmask();
+}
+
+/*
+ * notification of userspace execution resumption
+ * - triggered by the _TIF_WORK_MASK flags
+ */
+asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
+					   unsigned long thread_info_flags)
+{
+	/* Handle pending signal delivery */
+	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+		do_signal(regs);
+
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
+		tracehook_notify_resume(regs);
+}
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
new file mode 100644
index 000000000..d44567490
--- /dev/null
+++ b/arch/riscv/kernel/smp.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/cpu.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/delay.h>
+#include <linux/irq_work.h>
+
+#include <asm/sbi.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+
+enum ipi_message_type {
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNC,
+	IPI_CPU_STOP,
+	IPI_IRQ_WORK,
+	IPI_MAX
+};
+
+unsigned long __cpuid_to_hartid_map[NR_CPUS] = {
+	[0 ... NR_CPUS-1] = INVALID_HARTID
+};
+
+void __init smp_setup_processor_id(void)
+{
+	cpuid_to_hartid_map(0) = boot_cpu_hartid;
+}
+
+/* A collection of single bit ipi messages.  */
+static struct {
+	unsigned long stats[IPI_MAX] ____cacheline_aligned;
+	unsigned long bits ____cacheline_aligned;
+} ipi_data[NR_CPUS] __cacheline_aligned;
+
+int riscv_hartid_to_cpuid(int hartid)
+{
+	int i;
+
+	for (i = 0; i < NR_CPUS; i++)
+		if (cpuid_to_hartid_map(i) == hartid)
+			return i;
+
+	pr_err("Couldn't find cpu id for hartid [%d]\n", hartid);
+	return -ENOENT;
+}
+
+void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out)
+{
+	int cpu;
+
+	cpumask_clear(out);
+	for_each_cpu(cpu, in)
+		cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
+}
+EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask);
+
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == cpuid_to_hartid_map(cpu);
+}
+
+/* Unsupported */
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return -EINVAL;
+}
+
+static void ipi_stop(void)
+{
+	set_cpu_online(smp_processor_id(), false);
+	while (1)
+		wait_for_interrupt();
+}
+
+static struct riscv_ipi_ops *ipi_ops;
+
+void riscv_set_ipi_ops(struct riscv_ipi_ops *ops)
+{
+	ipi_ops = ops;
+}
+EXPORT_SYMBOL_GPL(riscv_set_ipi_ops);
+
+void riscv_clear_ipi(void)
+{
+	if (ipi_ops && ipi_ops->ipi_clear)
+		ipi_ops->ipi_clear();
+
+	csr_clear(CSR_IP, IE_SIE);
+}
+EXPORT_SYMBOL_GPL(riscv_clear_ipi);
+
+static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
+{
+	int cpu;
+
+	smp_mb__before_atomic();
+	for_each_cpu(cpu, mask)
+		set_bit(op, &ipi_data[cpu].bits);
+	smp_mb__after_atomic();
+
+	if (ipi_ops && ipi_ops->ipi_inject)
+		ipi_ops->ipi_inject(mask);
+	else
+		pr_warn("SMP: IPI inject method not available\n");
+}
+
+static void send_ipi_single(int cpu, enum ipi_message_type op)
+{
+	smp_mb__before_atomic();
+	set_bit(op, &ipi_data[cpu].bits);
+	smp_mb__after_atomic();
+
+	if (ipi_ops && ipi_ops->ipi_inject)
+		ipi_ops->ipi_inject(cpumask_of(cpu));
+	else
+		pr_warn("SMP: IPI inject method not available\n");
+}
+
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	send_ipi_single(smp_processor_id(), IPI_IRQ_WORK);
+}
+#endif
+
+void handle_IPI(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
+	unsigned long *stats = ipi_data[smp_processor_id()].stats;
+
+	irq_enter();
+
+	riscv_clear_ipi();
+
+	while (true) {
+		unsigned long ops;
+
+		/* Order bit clearing and data access. */
+		mb();
+
+		ops = xchg(pending_ipis, 0);
+		if (ops == 0)
+			goto done;
+
+		if (ops & (1 << IPI_RESCHEDULE)) {
+			stats[IPI_RESCHEDULE]++;
+			scheduler_ipi();
+		}
+
+		if (ops & (1 << IPI_CALL_FUNC)) {
+			stats[IPI_CALL_FUNC]++;
+			generic_smp_call_function_interrupt();
+		}
+
+		if (ops & (1 << IPI_CPU_STOP)) {
+			stats[IPI_CPU_STOP]++;
+			ipi_stop();
+		}
+
+		if (ops & (1 << IPI_IRQ_WORK)) {
+			stats[IPI_IRQ_WORK]++;
+			irq_work_run();
+		}
+
+		BUG_ON((ops >> IPI_MAX) != 0);
+
+		/* Order data access and bit testing. */
+		mb();
+	}
+
+done:
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+static const char * const ipi_names[] = {
+	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
+	[IPI_CALL_FUNC]		= "Function call interrupts",
+	[IPI_CPU_STOP]		= "CPU stop interrupts",
+	[IPI_IRQ_WORK]		= "IRQ work interrupts",
+};
+
+void show_ipi_stats(struct seq_file *p, int prec)
+{
+	unsigned int cpu, i;
+
+	for (i = 0; i < IPI_MAX; i++) {
+		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
+			   prec >= 4 ? " " : "");
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10lu ", ipi_data[cpu].stats[i]);
+		seq_printf(p, " %s\n", ipi_names[i]);
+	}
+}
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask)
+{
+	send_ipi_mask(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	send_ipi_single(cpu, IPI_CALL_FUNC);
+}
+
+void smp_send_stop(void)
+{
+	unsigned long timeout;
+
+	if (num_online_cpus() > 1) {
+		cpumask_t mask;
+
+		cpumask_copy(&mask, cpu_online_mask);
+		cpumask_clear_cpu(smp_processor_id(), &mask);
+
+		if (system_state <= SYSTEM_RUNNING)
+			pr_crit("SMP: stopping secondary CPUs\n");
+		send_ipi_mask(&mask, IPI_CPU_STOP);
+	}
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while (num_online_cpus() > 1 && timeout--)
+		udelay(1);
+
+	if (num_online_cpus() > 1)
+		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+			   cpumask_pr_args(cpu_online_mask));
+}
+
+void smp_send_reschedule(int cpu)
+{
+	send_ipi_single(cpu, IPI_RESCHEDULE);
+}
+EXPORT_SYMBOL_GPL(smp_send_reschedule);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
new file mode 100644
index 000000000..0e0aed380
--- /dev/null
+++ b/arch/riscv/kernel/smpboot.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SMP initialisation and IPI support
+ * Based on arch/arm64/kernel/smp.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/arch_topology.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/mm.h>
+#include <asm/cpu_ops.h>
+#include <asm/irq.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+
+#include "head.h"
+
+static DECLARE_COMPLETION(cpu_running);
+
+void __init smp_prepare_boot_cpu(void)
+{
+	init_cpu_topology();
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	int cpuid;
+	int ret;
+
+	store_cpu_topology(smp_processor_id());
+
+	/* This covers non-smp usecase mandated by "nosmp" option */
+	if (max_cpus == 0)
+		return;
+
+	for_each_possible_cpu(cpuid) {
+		if (cpuid == smp_processor_id())
+			continue;
+		if (cpu_ops[cpuid]->cpu_prepare) {
+			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
+			if (ret)
+				continue;
+		}
+		set_cpu_present(cpuid, true);
+	}
+}
+
+void __init setup_smp(void)
+{
+	struct device_node *dn;
+	int hart;
+	bool found_boot_cpu = false;
+	int cpuid = 1;
+
+	cpu_set_ops(0);
+
+	for_each_of_cpu_node(dn) {
+		hart = riscv_of_processor_hartid(dn);
+		if (hart < 0)
+			continue;
+
+		if (hart == cpuid_to_hartid_map(0)) {
+			BUG_ON(found_boot_cpu);
+			found_boot_cpu = 1;
+			continue;
+		}
+		if (cpuid >= NR_CPUS) {
+			pr_warn("Invalid cpuid [%d] for hartid [%d]\n",
+				cpuid, hart);
+			break;
+		}
+
+		cpuid_to_hartid_map(cpuid) = hart;
+		cpuid++;
+	}
+
+	BUG_ON(!found_boot_cpu);
+
+	if (cpuid > nr_cpu_ids)
+		pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n",
+			cpuid, nr_cpu_ids);
+
+	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
+			cpu_set_ops(cpuid);
+			set_cpu_possible(cpuid, true);
+		}
+	}
+}
+
+static int start_secondary_cpu(int cpu, struct task_struct *tidle)
+{
+	if (cpu_ops[cpu]->cpu_start)
+		return cpu_ops[cpu]->cpu_start(cpu, tidle);
+
+	return -EOPNOTSUPP;
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+	int ret = 0;
+	tidle->thread_info.cpu = cpu;
+
+	ret = start_secondary_cpu(cpu, tidle);
+	if (!ret) {
+		wait_for_completion_timeout(&cpu_running,
+					    msecs_to_jiffies(1000));
+
+		if (!cpu_online(cpu)) {
+			pr_crit("CPU%u: failed to come online\n", cpu);
+			ret = -EIO;
+		}
+	} else {
+		pr_crit("CPU%u: failed to start\n", cpu);
+	}
+
+	return ret;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+/*
+ * C entry point for a secondary processor.
+ */
+asmlinkage __visible void smp_callin(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int curr_cpuid = smp_processor_id();
+
+	riscv_clear_ipi();
+
+	/* All kernel threads share the same mm context.  */
+	mmgrab(mm);
+	current->active_mm = mm;
+
+	store_cpu_topology(curr_cpuid);
+	notify_cpu_starting(curr_cpuid);
+	set_cpu_online(curr_cpuid, 1);
+
+	/*
+	 * Remote TLB flushes are ignored while the CPU is offline, so emit
+	 * a local TLB flush right now just in case.
+	 */
+	local_flush_tlb_all();
+	complete(&cpu_running);
+	/*
+	 * Disable preemption before enabling interrupts, so we don't try to
+	 * schedule a CPU that hasn't actually started yet.
+	 */
+	local_irq_enable();
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c
new file mode 100644
index 000000000..c7b0a73e3
--- /dev/null
+++ b/arch/riscv/kernel/soc.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/init.h>
+#include <linux/libfdt.h>
+#include <linux/pgtable.h>
+#include <asm/soc.h>
+
+/*
+ * This is called extremly early, before parse_dtb(), to allow initializing
+ * SoC hardware before memory or any device driver initialization.
+ */
+void __init soc_early_init(void)
+{
+	void (*early_fn)(const void *fdt);
+	const struct of_device_id *s;
+	const void *fdt = dtb_early_va;
+
+	for (s = (void *)&__soc_early_init_table_start;
+	     (void *)s < (void *)&__soc_early_init_table_end; s++) {
+		if (!fdt_node_check_compatible(fdt, 0, s->compatible)) {
+			early_fn = s->data;
+			early_fn(fdt);
+			return;
+		}
+	}
+}
+
+static bool soc_builtin_dtb_match(unsigned long vendor_id,
+				unsigned long arch_id, unsigned long imp_id,
+				const struct soc_builtin_dtb *entry)
+{
+	return entry->vendor_id == vendor_id &&
+	       entry->arch_id == arch_id &&
+	       entry->imp_id == imp_id;
+}
+
+void * __init soc_lookup_builtin_dtb(void)
+{
+	unsigned long vendor_id, arch_id, imp_id;
+	const struct soc_builtin_dtb *s;
+
+	__asm__ ("csrr %0, mvendorid" : "=r"(vendor_id));
+	__asm__ ("csrr %0, marchid" : "=r"(arch_id));
+	__asm__ ("csrr %0, mimpid" : "=r"(imp_id));
+
+	for (s = (void *)&__soc_builtin_dtb_table_start;
+	     (void *)s < (void *)&__soc_builtin_dtb_table_end; s++) {
+		if (soc_builtin_dtb_match(vendor_id, arch_id, imp_id, s))
+			return s->dtb_func();
+	}
+
+	return NULL;
+}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
new file mode 100644
index 000000000..9c34735c1
--- /dev/null
+++ b/arch/riscv/kernel/stacktrace.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 ARM Limited
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#include <linux/export.h>
+#include <linux/kallsyms.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+#include <linux/ftrace.h>
+
+register unsigned long sp_in_global __asm__("sp");
+
+#ifdef CONFIG_FRAME_POINTER
+
+struct stackframe {
+	unsigned long fp;
+	unsigned long ra;
+};
+
+void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
+			     bool (*fn)(unsigned long, void *), void *arg)
+{
+	unsigned long fp, sp, pc;
+
+	if (regs) {
+		fp = frame_pointer(regs);
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		const register unsigned long current_sp = sp_in_global;
+		fp = (unsigned long)__builtin_frame_address(0);
+		sp = current_sp;
+		pc = (unsigned long)walk_stackframe;
+	} else {
+		/* task blocked in __switch_to */
+		fp = task->thread.s[0];
+		sp = task->thread.sp;
+		pc = task->thread.ra;
+	}
+
+	for (;;) {
+		unsigned long low, high;
+		struct stackframe *frame;
+
+		if (unlikely(!__kernel_text_address(pc) || fn(pc, arg)))
+			break;
+
+		/* Validate frame pointer */
+		low = sp + sizeof(struct stackframe);
+		high = ALIGN(sp, THREAD_SIZE);
+		if (unlikely(fp < low || fp > high || fp & 0x7))
+			break;
+		/* Unwind stack frame */
+		frame = (struct stackframe *)fp - 1;
+		sp = fp;
+		if (regs && (regs->epc == pc) && (frame->fp & 0x7)) {
+			fp = frame->ra;
+			pc = regs->ra;
+		} else {
+			fp = frame->fp;
+			pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+						   &frame->ra);
+		}
+
+	}
+}
+
+#else /* !CONFIG_FRAME_POINTER */
+
+void notrace walk_stackframe(struct task_struct *task,
+	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
+{
+	unsigned long sp, pc;
+	unsigned long *ksp;
+
+	if (regs) {
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		sp = sp_in_global;
+		pc = (unsigned long)walk_stackframe;
+	} else {
+		/* task blocked in __switch_to */
+		sp = task->thread.sp;
+		pc = task->thread.ra;
+	}
+
+	if (unlikely(sp & 0x7))
+		return;
+
+	ksp = (unsigned long *)sp;
+	while (!kstack_end(ksp)) {
+		if (__kernel_text_address(pc) && unlikely(fn(pc, arg)))
+			break;
+		pc = READ_ONCE_NOCHECK(*ksp++) - 0x4;
+	}
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+
+static bool print_trace_address(unsigned long pc, void *arg)
+{
+	const char *loglvl = arg;
+
+	print_ip_sym(loglvl, pc);
+	return false;
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
+{
+	pr_cont("Call Trace:\n");
+	walk_stackframe(task, NULL, print_trace_address, (void *)loglvl);
+}
+
+static bool save_wchan(unsigned long pc, void *arg)
+{
+	if (!in_sched_functions(pc)) {
+		unsigned long *p = arg;
+		*p = pc;
+		return true;
+	}
+	return false;
+}
+
+unsigned long get_wchan(struct task_struct *task)
+{
+	unsigned long pc = 0;
+
+	if (likely(task && task != current && task->state != TASK_RUNNING))
+		walk_stackframe(task, NULL, save_wchan, &pc);
+	return pc;
+}
+
+
+#ifdef CONFIG_STACKTRACE
+
+static bool __save_trace(unsigned long pc, void *arg, bool nosched)
+{
+	struct stack_trace *trace = arg;
+
+	if (unlikely(nosched && in_sched_functions(pc)))
+		return false;
+	if (unlikely(trace->skip > 0)) {
+		trace->skip--;
+		return false;
+	}
+
+	trace->entries[trace->nr_entries++] = pc;
+	return (trace->nr_entries >= trace->max_entries);
+}
+
+static bool save_trace(unsigned long pc, void *arg)
+{
+	return __save_trace(pc, arg, false);
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	walk_stackframe(tsk, NULL, save_trace, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	save_stack_trace_tsk(NULL, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+#endif /* CONFIG_STACKTRACE */
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
new file mode 100644
index 000000000..bb4026850
--- /dev/null
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2014 Darius Rad <darius@bluespec.com>
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/syscalls.h>
+#include <asm/unistd.h>
+#include <asm/cacheflush.h>
+#include <asm-generic/mman-common.h>
+
+static long riscv_sys_mmap(unsigned long addr, unsigned long len,
+			   unsigned long prot, unsigned long flags,
+			   unsigned long fd, off_t offset,
+			   unsigned long page_shift_offset)
+{
+	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
+		return -EINVAL;
+
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
+			       offset >> (PAGE_SHIFT - page_shift_offset));
+}
+
+#ifdef CONFIG_64BIT
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+	unsigned long, prot, unsigned long, flags,
+	unsigned long, fd, off_t, offset)
+{
+	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0);
+}
+#else
+SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
+	unsigned long, prot, unsigned long, flags,
+	unsigned long, fd, off_t, offset)
+{
+	/*
+	 * Note that the shift for mmap2 is constant (12),
+	 * regardless of PAGE_SIZE
+	 */
+	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
+}
+#endif /* !CONFIG_64BIT */
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * sys_riscv_flush_icache() is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
+	uintptr_t, flags)
+{
+	/* Check the reserved flags. */
+	if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL))
+		return -EINVAL;
+
+	flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
new file mode 100644
index 000000000..f1ead9df9
--- /dev/null
+++ b/arch/riscv/kernel/syscall_table.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2009 Arnd Bergmann <arnd@arndb.de>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/linkage.h>
+#include <linux/syscalls.h>
+#include <asm-generic/syscalls.h>
+#include <asm/vdso.h>
+#include <asm/syscall.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call)	[nr] = (call),
+
+void *sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
new file mode 100644
index 000000000..303ae47df
--- /dev/null
+++ b/arch/riscv/kernel/time.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/of_clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/delay.h>
+#include <asm/sbi.h>
+#include <asm/processor.h>
+
+unsigned long riscv_timebase;
+EXPORT_SYMBOL_GPL(riscv_timebase);
+
+void __init time_init(void)
+{
+	struct device_node *cpu;
+	u32 prop;
+
+	cpu = of_find_node_by_path("/cpus");
+	if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop))
+		panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n");
+	of_node_put(cpu);
+	riscv_timebase = prop;
+
+	lpj_fine = riscv_timebase / HZ;
+
+	of_clk_init(NULL);
+	timer_probe();
+
+	tick_setup_hrtimer_broadcast();
+}
+
+void clocksource_arch_init(struct clocksource *cs)
+{
+#ifdef CONFIG_GENERIC_GETTIMEOFDAY
+	cs->vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER;
+#else
+	cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
+#endif
+}
diff --git a/arch/riscv/kernel/trace_irq.c b/arch/riscv/kernel/trace_irq.c
new file mode 100644
index 000000000..095ac976d
--- /dev/null
+++ b/arch/riscv/kernel/trace_irq.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com>
+ */
+
+#include <linux/irqflags.h>
+#include <linux/kprobes.h>
+#include "trace_irq.h"
+
+/*
+ * trace_hardirqs_on/off require the caller to setup frame pointer properly.
+ * Otherwise, CALLER_ADDR1 might trigger an pagging exception in kernel.
+ * Here we add one extra level so they can be safely called by low
+ * level entry code which $fp is used for other purpose.
+ */
+
+void __trace_hardirqs_on(void)
+{
+	trace_hardirqs_on();
+}
+NOKPROBE_SYMBOL(__trace_hardirqs_on);
+
+void __trace_hardirqs_off(void)
+{
+	trace_hardirqs_off();
+}
+NOKPROBE_SYMBOL(__trace_hardirqs_off);
diff --git a/arch/riscv/kernel/trace_irq.h b/arch/riscv/kernel/trace_irq.h
new file mode 100644
index 000000000..99fe67377
--- /dev/null
+++ b/arch/riscv/kernel/trace_irq.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com>
+ */
+#ifndef __TRACE_IRQ_H
+#define __TRACE_IRQ_H
+
+void __trace_hardirqs_on(void);
+void __trace_hardirqs_off(void);
+
+#endif /* __TRACE_IRQ_H */
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
new file mode 100644
index 000000000..227253fde
--- /dev/null
+++ b/arch/riscv/kernel/traps.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+#include <linux/cpu.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <linux/signal.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/kexec.h>
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+int show_unhandled_signals = 1;
+
+extern asmlinkage void handle_exception(void);
+
+static DEFINE_SPINLOCK(die_lock);
+
+void die(struct pt_regs *regs, const char *str)
+{
+	static int die_counter;
+	int ret;
+	long cause;
+	unsigned long flags;
+
+	oops_enter();
+
+	spin_lock_irqsave(&die_lock, flags);
+	console_verbose();
+	bust_spinlocks(1);
+
+	pr_emerg("%s [#%d]\n", str, ++die_counter);
+	print_modules();
+	if (regs)
+		show_regs(regs);
+
+	cause = regs ? regs->cause : -1;
+	ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV);
+
+	if (kexec_should_crash(current))
+		crash_kexec(regs);
+
+	bust_spinlocks(0);
+	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+	spin_unlock_irqrestore(&die_lock, flags);
+	oops_exit();
+
+	if (in_interrupt())
+		panic("Fatal exception in interrupt");
+	if (panic_on_oops)
+		panic("Fatal exception");
+	if (ret != NOTIFY_STOP)
+		make_task_dead(SIGSEGV);
+}
+
+void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
+{
+	struct task_struct *tsk = current;
+
+	if (show_unhandled_signals && unhandled_signal(tsk, signo)
+	    && printk_ratelimit()) {
+		pr_info("%s[%d]: unhandled signal %d code 0x%x at 0x" REG_FMT,
+			tsk->comm, task_pid_nr(tsk), signo, code, addr);
+		print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
+		pr_cont("\n");
+		show_regs(regs);
+	}
+
+	force_sig_fault(signo, code, (void __user *)addr);
+}
+
+static void do_trap_error(struct pt_regs *regs, int signo, int code,
+	unsigned long addr, const char *str)
+{
+	if (user_mode(regs)) {
+		do_trap(regs, signo, code, addr);
+	} else {
+		if (!fixup_exception(regs))
+			die(regs, str);
+	}
+}
+
+#define DO_ERROR_INFO(name, signo, code, str)				\
+asmlinkage __visible void name(struct pt_regs *regs)			\
+{									\
+	do_trap_error(regs, signo, code, regs->epc, "Oops - " str);	\
+}
+
+DO_ERROR_INFO(do_trap_unknown,
+	SIGILL, ILL_ILLTRP, "unknown exception");
+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");
+DO_ERROR_INFO(do_trap_load_fault,
+	SIGSEGV, SEGV_ACCERR, "load access fault");
+#ifndef CONFIG_RISCV_M_MODE
+DO_ERROR_INFO(do_trap_load_misaligned,
+	SIGBUS, BUS_ADRALN, "Oops - load address misaligned");
+DO_ERROR_INFO(do_trap_store_misaligned,
+	SIGBUS, BUS_ADRALN, "Oops - store (or AMO) address misaligned");
+#else
+int handle_misaligned_load(struct pt_regs *regs);
+int handle_misaligned_store(struct pt_regs *regs);
+
+asmlinkage void do_trap_load_misaligned(struct pt_regs *regs)
+{
+	if (!handle_misaligned_load(regs))
+		return;
+	do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+		      "Oops - load address misaligned");
+}
+
+asmlinkage void do_trap_store_misaligned(struct pt_regs *regs)
+{
+	if (!handle_misaligned_store(regs))
+		return;
+	do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+		      "Oops - store (or AMO) address misaligned");
+}
+#endif
+DO_ERROR_INFO(do_trap_store_fault,
+	SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
+DO_ERROR_INFO(do_trap_ecall_u,
+	SIGILL, ILL_ILLTRP, "environment call from U-mode");
+DO_ERROR_INFO(do_trap_ecall_s,
+	SIGILL, ILL_ILLTRP, "environment call from S-mode");
+DO_ERROR_INFO(do_trap_ecall_m,
+	SIGILL, ILL_ILLTRP, "environment call from M-mode");
+
+static inline unsigned long get_break_insn_length(unsigned long pc)
+{
+	bug_insn_t insn;
+
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
+		return 0;
+
+	return GET_INSN_LENGTH(insn);
+}
+
+asmlinkage __visible void do_trap_break(struct pt_regs *regs)
+{
+	if (user_mode(regs))
+		force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->epc);
+#ifdef CONFIG_KGDB
+	else if (notify_die(DIE_TRAP, "EBREAK", regs, 0, regs->cause, SIGTRAP)
+								== NOTIFY_STOP)
+		return;
+#endif
+	else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN)
+		regs->epc += get_break_insn_length(regs->epc);
+	else
+		die(regs, "Kernel BUG");
+}
+
+#ifdef CONFIG_GENERIC_BUG
+int is_valid_bugaddr(unsigned long pc)
+{
+	bug_insn_t insn;
+
+	if (pc < VMALLOC_START)
+		return 0;
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
+		return 0;
+	if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
+		return (insn == __BUG_INSN_32);
+	else
+		return ((insn & __COMPRESSED_INSN_MASK) == __BUG_INSN_16);
+}
+#endif /* CONFIG_GENERIC_BUG */
+
+/* stvec & scratch is already set from head.S */
+void trap_init(void)
+{
+}
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
new file mode 100644
index 000000000..b246c3dc6
--- /dev/null
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/csr.h>
+
+#define INSN_MATCH_LB			0x3
+#define INSN_MASK_LB			0x707f
+#define INSN_MATCH_LH			0x1003
+#define INSN_MASK_LH			0x707f
+#define INSN_MATCH_LW			0x2003
+#define INSN_MASK_LW			0x707f
+#define INSN_MATCH_LD			0x3003
+#define INSN_MASK_LD			0x707f
+#define INSN_MATCH_LBU			0x4003
+#define INSN_MASK_LBU			0x707f
+#define INSN_MATCH_LHU			0x5003
+#define INSN_MASK_LHU			0x707f
+#define INSN_MATCH_LWU			0x6003
+#define INSN_MASK_LWU			0x707f
+#define INSN_MATCH_SB			0x23
+#define INSN_MASK_SB			0x707f
+#define INSN_MATCH_SH			0x1023
+#define INSN_MASK_SH			0x707f
+#define INSN_MATCH_SW			0x2023
+#define INSN_MASK_SW			0x707f
+#define INSN_MATCH_SD			0x3023
+#define INSN_MASK_SD			0x707f
+
+#define INSN_MATCH_FLW			0x2007
+#define INSN_MASK_FLW			0x707f
+#define INSN_MATCH_FLD			0x3007
+#define INSN_MASK_FLD			0x707f
+#define INSN_MATCH_FLQ			0x4007
+#define INSN_MASK_FLQ			0x707f
+#define INSN_MATCH_FSW			0x2027
+#define INSN_MASK_FSW			0x707f
+#define INSN_MATCH_FSD			0x3027
+#define INSN_MASK_FSD			0x707f
+#define INSN_MATCH_FSQ			0x4027
+#define INSN_MASK_FSQ			0x707f
+
+#define INSN_MATCH_C_LD			0x6000
+#define INSN_MASK_C_LD			0xe003
+#define INSN_MATCH_C_SD			0xe000
+#define INSN_MASK_C_SD			0xe003
+#define INSN_MATCH_C_LW			0x4000
+#define INSN_MASK_C_LW			0xe003
+#define INSN_MATCH_C_SW			0xc000
+#define INSN_MASK_C_SW			0xe003
+#define INSN_MATCH_C_LDSP		0x6002
+#define INSN_MASK_C_LDSP		0xe003
+#define INSN_MATCH_C_SDSP		0xe002
+#define INSN_MASK_C_SDSP		0xe003
+#define INSN_MATCH_C_LWSP		0x4002
+#define INSN_MASK_C_LWSP		0xe003
+#define INSN_MATCH_C_SWSP		0xc002
+#define INSN_MASK_C_SWSP		0xe003
+
+#define INSN_MATCH_C_FLD		0x2000
+#define INSN_MASK_C_FLD			0xe003
+#define INSN_MATCH_C_FLW		0x6000
+#define INSN_MASK_C_FLW			0xe003
+#define INSN_MATCH_C_FSD		0xa000
+#define INSN_MASK_C_FSD			0xe003
+#define INSN_MATCH_C_FSW		0xe000
+#define INSN_MASK_C_FSW			0xe003
+#define INSN_MATCH_C_FLDSP		0x2002
+#define INSN_MASK_C_FLDSP		0xe003
+#define INSN_MATCH_C_FSDSP		0xa002
+#define INSN_MASK_C_FSDSP		0xe003
+#define INSN_MATCH_C_FLWSP		0x6002
+#define INSN_MASK_C_FLWSP		0xe003
+#define INSN_MATCH_C_FSWSP		0xe002
+#define INSN_MASK_C_FSWSP		0xe003
+
+#define INSN_LEN(insn)			((((insn) & 0x3) < 0x3) ? 2 : 4)
+
+#if defined(CONFIG_64BIT)
+#define LOG_REGBYTES			3
+#define XLEN				64
+#else
+#define LOG_REGBYTES			2
+#define XLEN				32
+#endif
+#define REGBYTES			(1 << LOG_REGBYTES)
+#define XLEN_MINUS_16			((XLEN) - 16)
+
+#define SH_RD				7
+#define SH_RS1				15
+#define SH_RS2				20
+#define SH_RS2C				2
+
+#define RV_X(x, s, n)			(((x) >> (s)) & ((1 << (n)) - 1))
+#define RVC_LW_IMM(x)			((RV_X(x, 6, 1) << 2) | \
+					 (RV_X(x, 10, 3) << 3) | \
+					 (RV_X(x, 5, 1) << 6))
+#define RVC_LD_IMM(x)			((RV_X(x, 10, 3) << 3) | \
+					 (RV_X(x, 5, 2) << 6))
+#define RVC_LWSP_IMM(x)			((RV_X(x, 4, 3) << 2) | \
+					 (RV_X(x, 12, 1) << 5) | \
+					 (RV_X(x, 2, 2) << 6))
+#define RVC_LDSP_IMM(x)			((RV_X(x, 5, 2) << 3) | \
+					 (RV_X(x, 12, 1) << 5) | \
+					 (RV_X(x, 2, 3) << 6))
+#define RVC_SWSP_IMM(x)			((RV_X(x, 9, 4) << 2) | \
+					 (RV_X(x, 7, 2) << 6))
+#define RVC_SDSP_IMM(x)			((RV_X(x, 10, 3) << 3) | \
+					 (RV_X(x, 7, 3) << 6))
+#define RVC_RS1S(insn)			(8 + RV_X(insn, SH_RD, 3))
+#define RVC_RS2S(insn)			(8 + RV_X(insn, SH_RS2C, 3))
+#define RVC_RS2(insn)			RV_X(insn, SH_RS2C, 5)
+
+#define SHIFT_RIGHT(x, y)		\
+	((y) < 0 ? ((x) << -(y)) : ((x) >> (y)))
+
+#define REG_MASK			\
+	((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES))
+
+#define REG_OFFSET(insn, pos)		\
+	(SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK)
+
+#define REG_PTR(insn, pos, regs)	\
+	(ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))
+
+#define GET_RM(insn)			(((insn) >> 12) & 7)
+
+#define GET_RS1(insn, regs)		(*REG_PTR(insn, SH_RS1, regs))
+#define GET_RS2(insn, regs)		(*REG_PTR(insn, SH_RS2, regs))
+#define GET_RS1S(insn, regs)		(*REG_PTR(RVC_RS1S(insn), 0, regs))
+#define GET_RS2S(insn, regs)		(*REG_PTR(RVC_RS2S(insn), 0, regs))
+#define GET_RS2C(insn, regs)		(*REG_PTR(insn, SH_RS2C, regs))
+#define GET_SP(regs)			(*REG_PTR(2, 0, regs))
+#define SET_RD(insn, regs, val)		(*REG_PTR(insn, SH_RD, regs) = (val))
+#define IMM_I(insn)			((s32)(insn) >> 20)
+#define IMM_S(insn)			(((s32)(insn) >> 25 << 5) | \
+					 (s32)(((insn) >> 7) & 0x1f))
+#define MASK_FUNCT3			0x7000
+
+#define GET_PRECISION(insn) (((insn) >> 25) & 3)
+#define GET_RM(insn) (((insn) >> 12) & 7)
+#define PRECISION_S 0
+#define PRECISION_D 1
+
+#define STR(x) XSTR(x)
+#define XSTR(x) #x
+
+#define DECLARE_UNPRIVILEGED_LOAD_FUNCTION(type, insn)			\
+static inline type load_##type(const type *addr)			\
+{									\
+	type val;							\
+	asm (#insn " %0, %1"						\
+	: "=&r" (val) : "m" (*addr));					\
+	return val;							\
+}
+
+#define DECLARE_UNPRIVILEGED_STORE_FUNCTION(type, insn)			\
+static inline void store_##type(type *addr, type val)			\
+{									\
+	asm volatile (#insn " %0, %1\n"					\
+	: : "r" (val), "m" (*addr));					\
+}
+
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u8, lbu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u16, lhu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s8, lb)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s16, lh)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s32, lw)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u8, sb)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u16, sh)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u32, sw)
+#if defined(CONFIG_64BIT)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lwu)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u64, ld)
+DECLARE_UNPRIVILEGED_STORE_FUNCTION(u64, sd)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, ld)
+#else
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lw)
+DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, lw)
+
+static inline u64 load_u64(const u64 *addr)
+{
+	return load_u32((u32 *)addr)
+		+ ((u64)load_u32((u32 *)addr + 1) << 32);
+}
+
+static inline void store_u64(u64 *addr, u64 val)
+{
+	store_u32((u32 *)addr, val);
+	store_u32((u32 *)addr + 1, val >> 32);
+}
+#endif
+
+static inline ulong get_insn(ulong mepc)
+{
+	register ulong __mepc asm ("a2") = mepc;
+	ulong val, rvc_mask = 3, tmp;
+
+	asm ("and %[tmp], %[addr], 2\n"
+		"bnez %[tmp], 1f\n"
+#if defined(CONFIG_64BIT)
+		STR(LWU) " %[insn], (%[addr])\n"
+#else
+		STR(LW) " %[insn], (%[addr])\n"
+#endif
+		"and %[tmp], %[insn], %[rvc_mask]\n"
+		"beq %[tmp], %[rvc_mask], 2f\n"
+		"sll %[insn], %[insn], %[xlen_minus_16]\n"
+		"srl %[insn], %[insn], %[xlen_minus_16]\n"
+		"j 2f\n"
+		"1:\n"
+		"lhu %[insn], (%[addr])\n"
+		"and %[tmp], %[insn], %[rvc_mask]\n"
+		"bne %[tmp], %[rvc_mask], 2f\n"
+		"lhu %[tmp], 2(%[addr])\n"
+		"sll %[tmp], %[tmp], 16\n"
+		"add %[insn], %[insn], %[tmp]\n"
+		"2:"
+	: [insn] "=&r" (val), [tmp] "=&r" (tmp)
+	: [addr] "r" (__mepc), [rvc_mask] "r" (rvc_mask),
+	  [xlen_minus_16] "i" (XLEN_MINUS_16));
+
+	return val;
+}
+
+union reg_data {
+	u8 data_bytes[8];
+	ulong data_ulong;
+	u64 data_u64;
+};
+
+int handle_misaligned_load(struct pt_regs *regs)
+{
+	union reg_data val;
+	unsigned long epc = regs->epc;
+	unsigned long insn = get_insn(epc);
+	unsigned long addr = csr_read(mtval);
+	int i, fp = 0, shift = 0, len = 0;
+
+	regs->epc = 0;
+
+	if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) {
+		len = 4;
+		shift = 8 * (sizeof(unsigned long) - len);
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) {
+		len = 8;
+		shift = 8 * (sizeof(unsigned long) - len);
+	} else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) {
+		len = 4;
+#endif
+	} else if ((insn & INSN_MASK_FLD) == INSN_MATCH_FLD) {
+		fp = 1;
+		len = 8;
+	} else if ((insn & INSN_MASK_FLW) == INSN_MATCH_FLW) {
+		fp = 1;
+		len = 4;
+	} else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) {
+		len = 2;
+		shift = 8 * (sizeof(unsigned long) - len);
+	} else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) {
+		len = 2;
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) {
+		len = 8;
+		shift = 8 * (sizeof(unsigned long) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 8;
+		shift = 8 * (sizeof(unsigned long) - len);
+#endif
+	} else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) {
+		len = 4;
+		shift = 8 * (sizeof(unsigned long) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP &&
+		   ((insn >> SH_RD) & 0x1f)) {
+		len = 4;
+		shift = 8 * (sizeof(unsigned long) - len);
+	} else if ((insn & INSN_MASK_C_FLD) == INSN_MATCH_C_FLD) {
+		fp = 1;
+		len = 8;
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_FLDSP) == INSN_MATCH_C_FLDSP) {
+		fp = 1;
+		len = 8;
+#if defined(CONFIG_32BIT)
+	} else if ((insn & INSN_MASK_C_FLW) == INSN_MATCH_C_FLW) {
+		fp = 1;
+		len = 4;
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_FLWSP) == INSN_MATCH_C_FLWSP) {
+		fp = 1;
+		len = 4;
+#endif
+	} else {
+		regs->epc = epc;
+		return -1;
+	}
+
+	val.data_u64 = 0;
+	for (i = 0; i < len; i++)
+		val.data_bytes[i] = load_u8((void *)(addr + i));
+
+	if (fp)
+		return -1;
+	SET_RD(insn, regs, val.data_ulong << shift >> shift);
+
+	regs->epc = epc + INSN_LEN(insn);
+
+	return 0;
+}
+
+int handle_misaligned_store(struct pt_regs *regs)
+{
+	union reg_data val;
+	unsigned long epc = regs->epc;
+	unsigned long insn = get_insn(epc);
+	unsigned long addr = csr_read(mtval);
+	int i, len = 0;
+
+	regs->epc = 0;
+
+	val.data_ulong = GET_RS2(insn, regs);
+
+	if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) {
+		len = 4;
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) {
+		len = 8;
+#endif
+	} else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) {
+		len = 2;
+#if defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) {
+		len = 8;
+		val.data_ulong = GET_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) {
+		len = 8;
+		val.data_ulong = GET_RS2C(insn, regs);
+#endif
+	} else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) {
+		len = 4;
+		val.data_ulong = GET_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) {
+		len = 4;
+		val.data_ulong = GET_RS2C(insn, regs);
+	} else {
+		regs->epc = epc;
+		return -1;
+	}
+
+	for (i = 0; i < len; i++)
+		store_u8((void *)(addr + i), val.data_bytes[i]);
+
+	regs->epc = epc + INSN_LEN(insn);
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
new file mode 100644
index 000000000..73d45931a
--- /dev/null
+++ b/arch/riscv/kernel/vdso.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#include <linux/elf.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/binfmts.h>
+#include <linux/err.h>
+#include <asm/page.h>
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
+#include <vdso/datapage.h>
+#else
+#include <asm/vdso.h>
+#endif
+
+extern char vdso_start[], vdso_end[];
+
+static unsigned int vdso_pages;
+static struct page **vdso_pagelist;
+
+/*
+ * The vDSO data page.
+ */
+static union {
+	struct vdso_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+static int __init vdso_init(void)
+{
+	unsigned int i;
+
+	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+	vdso_pagelist =
+		kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+	if (unlikely(vdso_pagelist == NULL)) {
+		pr_err("vdso: pagelist allocation failed\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < vdso_pages; i++) {
+		struct page *pg;
+
+		pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
+		vdso_pagelist[i] = pg;
+	}
+	vdso_pagelist[i] = virt_to_page(vdso_data);
+
+	return 0;
+}
+arch_initcall(vdso_init);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+	int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long vdso_base, vdso_len;
+	int ret;
+
+	vdso_len = (vdso_pages + 1) << PAGE_SHIFT;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		ret = vdso_base;
+		goto end;
+	}
+
+	/*
+	 * Put vDSO base into mm struct. We need to do this before calling
+	 * install_special_mapping or the perf counter mmap tracking code
+	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
+	 */
+	mm->context.vdso = (void *)vdso_base;
+
+	ret =
+	   install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+		vdso_pagelist);
+
+	if (unlikely(ret)) {
+		mm->context.vdso = NULL;
+		goto end;
+	}
+
+	vdso_base += (vdso_pages << PAGE_SHIFT);
+	ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
+		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
+
+	if (unlikely(ret))
+		mm->context.vdso = NULL;
+end:
+	mmap_write_unlock(mm);
+	return ret;
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso))
+		return "[vdso]";
+	if (vma->vm_mm && (vma->vm_start ==
+			   (long)vma->vm_mm->context.vdso + PAGE_SIZE))
+		return "[vdso_data]";
+	return NULL;
+}
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
new file mode 100644
index 000000000..3a19def86
--- /dev/null
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vdso.lds
+*.tmp
+vdso-syms.S
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
new file mode 100644
index 000000000..f4ac7ff56
--- /dev/null
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -0,0 +1,85 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copied from arch/tile/kernel/vdso/Makefile
+
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_RISCV_32|R_RISCV_64|R_RISCV_JUMP_SLOT
+include $(srctree)/lib/vdso/Makefile
+# Symbols present in the vdso
+vdso-syms  = rt_sigreturn
+ifdef CONFIG_64BIT
+vdso-syms += vgettimeofday
+endif
+vdso-syms += getcpu
+vdso-syms += flush_icache
+
+# Files to link into the vdso
+obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
+
+ccflags-y := -fno-stack-protector
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+
+ifneq ($(c-gettimeofday-y),)
+  CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
+endif
+
+# Build rules
+targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-syms.S
+obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+
+obj-y += vdso.o vdso-syms.o
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+ifneq ($(filter vgettimeofday, $(vdso-syms)),)
+CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY
+endif
+
+# Disable -pg to prevent insert call site
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+
+# Disable profiling and instrumentation for VDSO code
+GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
+KASAN_SANITIZE := n
+
+# Force dependency
+$(obj)/vdso.o: $(obj)/vdso.so
+
+# link rule for the .so file, .lds has to be first
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,vdsold)
+LDFLAGS_vdso.so.dbg = -shared -s -soname=linux-vdso.so.1 \
+	--build-id=sha1 --hash-style=both --eh-frame-hdr
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO. With ld --just-symbols we can then
+# refer to these symbols in the kernel code rather than hand-coded addresses.
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
+	$(call if_changed,so2s)
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# actual build commands
+# The DSO images are built using a special linker script
+# Make sure only to export the intended __vdso_xxx symbol offsets.
+quiet_cmd_vdsold = VDSOLD  $@
+      cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \
+                   $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
+                   rm $@.tmp
+
+# Extracts symbol offsets from the VDSO, converting them into an assembly file
+# that contains the same symbols at the same offsets.
+quiet_cmd_so2s = SO2S    $@
+      cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso.so: $(obj)/vdso.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso.so
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
new file mode 100644
index 000000000..82f97d67c
--- /dev/null
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
+ENTRY(__vdso_flush_icache)
+	.cfi_startproc
+#ifdef CONFIG_SMP
+	li a7, __NR_riscv_flush_icache
+	ecall
+#else
+	fence.i
+	li a0, 0
+#endif
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
new file mode 100644
index 000000000..bb0c05e2f
--- /dev/null
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
+ENTRY(__vdso_getcpu)
+	.cfi_startproc
+	/* For now, just do the syscall. */
+	li a7, __NR_getcpu
+	ecall
+	ret
+	.cfi_endproc
+ENDPROC(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S
new file mode 100644
index 000000000..2a956c942
--- /dev/null
+++ b/arch/riscv/kernel/vdso/note.S
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/elfnote.h>
+#include <linux/version.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S
new file mode 100644
index 000000000..0573705ea
--- /dev/null
+++ b/arch/riscv/kernel/vdso/rt_sigreturn.S
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd.h>
+
+	.text
+ENTRY(__vdso_rt_sigreturn)
+	.cfi_startproc
+	.cfi_signal_frame
+	li a7, __NR_rt_sigreturn
+	scall
+	.cfi_endproc
+ENDPROC(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh
new file mode 100755
index 000000000..e64cb6d94
--- /dev/null
+++ b/arch/riscv/kernel/vdso/so2s.sh
@@ -0,0 +1,6 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com>
+
+sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \
+| grep '^\.'
diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S
new file mode 100644
index 000000000..df222245b
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.S
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Regents of the University of California
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+	__PAGE_ALIGNED_DATA
+
+	.globl vdso_start, vdso_end
+	.balign PAGE_SIZE
+vdso_start:
+	.incbin "arch/riscv/kernel/vdso/vdso.so"
+	.balign PAGE_SIZE
+vdso_end:
+
+	.previous
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
new file mode 100644
index 000000000..b3e58402c
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ */
+#include <asm/page.h>
+
+OUTPUT_ARCH(riscv)
+
+SECTIONS
+{
+	PROVIDE(_vdso_data = . + PAGE_SIZE);
+	. = SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+
+	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+
+	/*
+	 * This linker script is used both with -r and with -shared.
+	 * For the layouts to match, we need to skip more than enough
+	 * space for the dynamic symbol table, etc. If this amount is
+	 * insufficient, ld -shared will error; simply increase it here.
+	 */
+	. = 0x800;
+	.text		: { *(.text .text.*) }		:text
+
+	.data		: {
+		*(.got.plt) *(.got)
+		*(.data .data.* .gnu.linkonce.d.*)
+		*(.dynbss)
+		*(.bss .bss.* .gnu.linkonce.b.*)
+	}
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
+	note		PT_NOTE		FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+	LINUX_4.15 {
+	global:
+		__vdso_rt_sigreturn;
+#ifdef HAS_VGETTIMEOFDAY
+		__vdso_gettimeofday;
+		__vdso_clock_gettime;
+		__vdso_clock_getres;
+#endif
+		__vdso_getcpu;
+		__vdso_flush_icache;
+	local: *;
+	};
+}
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
new file mode 100644
index 000000000..cc0d80699
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copied from arch/arm64/kernel/vdso/vgettimeofday.c
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/time.h>
+#include <linux/types.h>
+
+extern
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+extern
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+extern
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
+{
+	return __cvdso_clock_getres(clock_id, res);
+}
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
new file mode 100644
index 000000000..3ffbd6cbd
--- /dev/null
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#define LOAD_OFFSET PAGE_OFFSET
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/set_memory.h>
+#include "image-vars.h"
+
+#include <linux/sizes.h>
+OUTPUT_ARCH(riscv)
+ENTRY(_start)
+
+jiffies = jiffies_64;
+
+PECOFF_SECTION_ALIGNMENT = 0x1000;
+PECOFF_FILE_ALIGNMENT = 0x200;
+
+SECTIONS
+{
+	/* Beginning of code and text segment */
+	. = LOAD_OFFSET;
+	_start = .;
+	HEAD_TEXT_SECTION
+	. = ALIGN(PAGE_SIZE);
+
+	__init_begin = .;
+	INIT_TEXT_SECTION(PAGE_SIZE)
+	. = ALIGN(8);
+	__soc_early_init_table : {
+		__soc_early_init_table_start = .;
+		KEEP(*(__soc_early_init_table))
+		__soc_early_init_table_end = .;
+	}
+	__soc_builtin_dtb_table : {
+		__soc_builtin_dtb_table_start = .;
+		KEEP(*(__soc_builtin_dtb_table))
+		__soc_builtin_dtb_table_end = .;
+	}
+	/* we have to discard exit text and such at runtime, not link time */
+	.exit.text :
+	{
+		EXIT_TEXT
+	}
+	.exit.data :
+	{
+		EXIT_DATA
+	}
+	PERCPU_SECTION(L1_CACHE_BYTES)
+	__init_end = .;
+
+	. = ALIGN(SECTION_ALIGN);
+	.text : {
+		_text = .;
+		_stext = .;
+		TEXT_TEXT
+		SCHED_TEXT
+		CPUIDLE_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		ENTRY_TEXT
+		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
+		*(.fixup)
+		_etext = .;
+	}
+
+#ifdef CONFIG_EFI
+	. = ALIGN(PECOFF_SECTION_ALIGNMENT);
+	__pecoff_text_end = .;
+#endif
+
+	INIT_DATA_SECTION(16)
+
+	/* Start of data section */
+	_sdata = .;
+	RO_DATA(SECTION_ALIGN)
+	.srodata : {
+		*(.srodata*)
+	}
+
+	EXCEPTION_TABLE(0x10)
+
+	. = ALIGN(SECTION_ALIGN);
+	_data = .;
+
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	.sdata : {
+		__global_pointer$ = . + 0x800;
+		*(.sdata*)
+	}
+
+#ifdef CONFIG_EFI
+	.pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); }
+	__pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end);
+#endif
+
+	/* End of data section */
+	_edata = .;
+
+	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
+
+	.rel.dyn : {
+		*(.rel.dyn*)
+	}
+
+#ifdef CONFIG_EFI
+	. = ALIGN(PECOFF_SECTION_ALIGNMENT);
+	__pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end);
+#endif
+	_end = .;
+
+	STABS_DEBUG
+	DWARF_DEBUG
+	ELF_DETAILS
+
+	DISCARDS
+}