Merge tag 'riscv-for-linus-4.17-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux

Pull RISC-V updates from Palmer Dabbelt:
 "This contains the new features we'd like to incorporate into the
  RISC-V port for 4.17. We might have a bit more stuff land later in the
  merge window, but I wanted to get this out earlier just so everyone
  can see where we currently stand.

  A short summary of the changes is:

   - We've added support for dynamic ftrace on RISC-V targets.

   - There have been a handful of cleanups to our atomic and locking
     routines. They now more closely match the released RISC-V memory
     model draft.

   - Our module loading support has been cleaned up and is now enabled
     by default, despite some limitations still existing.

   - A patch to define COMMANDLINE_FORCE instead of COMMANDLINE_OVERRIDE
     so the generic device tree code picks up handling all our command
     line stuff.

  There's more information in the merge commits for each patch set"

* tag 'riscv-for-linus-4.17-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux: (21 commits)
  RISC-V: Rename CONFIG_CMDLINE_OVERRIDE to CONFIG_CMDLINE_FORCE
  RISC-V: Add definition of relocation types
  RISC-V: Enable module support in defconfig
  RISC-V: Support SUB32 relocation type in kernel module
  RISC-V: Support ADD32 relocation type in kernel module
  RISC-V: Support ALIGN relocation type in kernel module
  RISC-V: Support RVC_BRANCH/JUMP relocation type in kernel modulewq
  RISC-V: Support HI20/LO12_I/LO12_S relocation type in kernel module
  RISC-V: Support CALL relocation type in kernel module
  RISC-V: Support GOT_HI20/CALL_PLT relocation type in kernel module
  RISC-V: Add section of GOT.PLT for kernel module
  RISC-V: Add sections of PLT and GOT for kernel module
  riscv/atomic: Strengthen implementations with fences
  riscv/spinlock: Strengthen implementations with fences
  riscv/barrier: Define __smp_{store_release,load_acquire}
  riscv/ftrace: Add HAVE_FUNCTION_GRAPH_RET_ADDR_PTR support
  riscv/ftrace: Add DYNAMIC_FTRACE_WITH_REGS support
  riscv/ftrace: Add ARCH_SUPPORTS_FTRACE_OPS support
  riscv/ftrace: Add dynamic function graph tracer support
  riscv/ftrace: Add dynamic function tracer support
  ...

8 files changed, 772 insertions, 19 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 196f62ffc428..8586dd96c2f0 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -34,7 +34,9 @@ CFLAGS_setup.o := -mcmodel=medany
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_MODULES)		+= module.o
-obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
+
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
 clean:
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index d0de68d144cb..1157b6b52d25 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -6,9 +6,126 @@
  */
 
 #include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+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 (probe_kernel_read(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 get (%08x %08x)",
+		       (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};
+	int ret = 0;
+
+	make_call(hook_pos, target, call);
+
+	/* replace the auipc-jalr pair at once */
+	ret = probe_kernel_write((void *)hook_pos, enable ? call : nops,
+				 MCOUNT_INSN_SIZE);
+	/* return must be -EPERM on write error */
+	if (ret)
+		return -EPERM;
+
+	smp_mb();
+	flush_icache_range((void *)hook_pos, (void *)hook_pos + MCOUNT_INSN_SIZE);
+
+	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);
+}
+
+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 file is copied from arm64.
+ * Most of this function is copied from arm64.
  */
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 			   unsigned long frame_pointer)
@@ -34,8 +151,62 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		return;
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
-				       frame_pointer, NULL);
+				       frame_pointer, parent);
 	if (err == -EBUSY)
 		return;
 	*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/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
new file mode 100644
index 000000000000..35a6ed76cb8b
--- /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
index c46a778627be..ce9bdc57a2a1 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -32,13 +32,13 @@
 	addi	s0, sp, 32
 	.endm
 
-	.macro STORE_ABI_STATE
+	.macro RESTORE_ABI_STATE
 	ld	ra, 8(sp)
 	ld	s0, 0(sp)
 	addi	sp, sp, 16
 	.endm
 
-	.macro STORE_RET_ABI_STATE
+	.macro RESTORE_RET_ABI_STATE
 	ld	ra, 24(sp)
 	ld	s0, 16(sp)
 	ld	a0, 8(sp)
@@ -46,6 +46,10 @@
 	.endm
 
 ENTRY(ftrace_stub)
+#ifdef CONFIG_DYNAMIC_FTRACE
+       .global _mcount
+       .set    _mcount, ftrace_stub
+#endif
 	ret
 ENDPROC(ftrace_stub)
 
@@ -66,15 +70,15 @@ ENTRY(return_to_handler)
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	mv	a0, t6
 #endif
-	la	t0, ftrace_return_to_handler
-	jalr	t0
+	call	ftrace_return_to_handler
 	mv	a1, a0
-	STORE_RET_ABI_STATE
+	RESTORE_RET_ABI_STATE
 	jalr	a1
 ENDPROC(return_to_handler)
 EXPORT_SYMBOL(return_to_handler)
 #endif
 
+#ifndef CONFIG_DYNAMIC_FTRACE
 ENTRY(_mcount)
 	la	t4, ftrace_stub
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -104,9 +108,8 @@ do_ftrace_graph_caller:
 	ld	a2, -16(s0)
 #endif
 	SAVE_ABI_STATE
-	la	t0, prepare_ftrace_return
-	jalr	t0
-	STORE_ABI_STATE
+	call	prepare_ftrace_return
+	RESTORE_ABI_STATE
 	ret
 #endif
 
@@ -120,7 +123,8 @@ do_trace:
 
 	SAVE_ABI_STATE
 	jalr	t5
-	STORE_ABI_STATE
+	RESTORE_ABI_STATE
 	ret
 ENDPROC(_mcount)
 EXPORT_SYMBOL(_mcount)
+#endif
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
new file mode 100644
index 000000000000..bbbd26e19bfd
--- /dev/null
+++ b/arch/riscv/kernel/module-sections.c
@@ -0,0 +1,156 @@
+/* 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>
+
+u64 module_emit_got_entry(struct module *mod, u64 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 (u64)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 (u64)&got[i];
+}
+
+u64 module_emit_plt_entry(struct module *mod, u64 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 (u64)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, (u64)&plt[i], (u64)&got_plt[i]);
+
+	plt_sec->num_entries++;
+	got_plt_sec->num_entries++;
+	BUG_ON(plt_sec->num_entries > plt_sec->max_entries);
+
+	return (u64)&plt[i];
+}
+
+static int is_rela_equal(const Elf64_Rela *x, const Elf64_Rela *y)
+{
+	return x->r_info == y->r_info && x->r_addend == y->r_addend;
+}
+
+static bool duplicate_rela(const Elf64_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(Elf64_Rela *relas, int num,
+			      unsigned int *plts, unsigned int *gots)
+{
+	unsigned int type, i;
+
+	for (i = 0; i < num; i++) {
+		type = ELF64_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++) {
+		Elf64_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset;
+		int num_rela = sechdrs[i].sh_size / sizeof(Elf64_Rela);
+		Elf64_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
index e0f05034fc21..5dddba301d0a 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -49,6 +49,39 @@ static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
 	return 0;
 }
 
+static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
+					 Elf_Addr v)
+{
+	s64 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)
+{
+	s64 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)
 {
@@ -92,6 +125,67 @@ static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
 	return 0;
 }
 
+static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
+				   Elf_Addr v)
+{
+	s32 hi20;
+
+	if (IS_ENABLED(CMODEL_MEDLOW)) {
+		pr_err(
+		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+		  me->name, 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)
+{
+	s64 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, 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)
 {
@@ -100,6 +194,33 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 	u32 hi20, lo12;
 
 	if (offset != fill_v) {
+		/* 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, 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)
+{
+	s64 offset = (void *)v - (void *)location;
+	s32 fill_v = offset;
+	u32 hi20, lo12;
+
+	if (offset != fill_v) {
 		pr_err(
 		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
 		  me->name, v, location);
@@ -119,16 +240,49 @@ static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
 	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_sub32_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u32 *)location -= (*(u32 *)v);
+	return 0;
+}
+
 static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
 				Elf_Addr v) = {
 	[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_SUB32]			= apply_r_riscv_sub32_rela,
 };
 
 int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
@@ -184,25 +338,38 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 				u64 hi20_loc =
 					sechdrs[sechdrs[relsec].sh_info].sh_addr
 					+ rel[j].r_offset;
-				/* Find the corresponding HI20 PC-relative relocation entry */
-				if (hi20_loc == sym->st_value) {
+				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);
 					u64 hi20_sym_val =
 						hi20_sym->st_value
 						+ rel[j].r_addend;
+
 					/* Calculate lo12 */
-					s64 offset = hi20_sym_val - hi20_loc;
-					s32 hi20 = (offset + 0x800) & 0xfffff000;
-					s32 lo12 = offset - hi20;
+					u64 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 PC-relative relocation information\n",
+				  "%s: Can not find HI20 relocation information\n",
 				  me->name);
 				return -EINVAL;
 			}
diff --git a/arch/riscv/kernel/module.lds b/arch/riscv/kernel/module.lds
new file mode 100644
index 000000000000..295ecfb341a2
--- /dev/null
+++ b/arch/riscv/kernel/module.lds
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+SECTIONS {
+	.plt (NOLOAD) : { BYTE(0) }
+	.got (NOLOAD) : { BYTE(0) }
+	.got.plt (NOLOAD) : { BYTE(0) }
+}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 559aae781154..a4b1d94371a0 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -18,6 +18,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
+#include <linux/ftrace.h>
 
 #ifdef CONFIG_FRAME_POINTER
 
@@ -63,7 +64,12 @@ static void notrace walk_stackframe(struct task_struct *task,
 		frame = (struct stackframe *)fp - 1;
 		sp = fp;
 		fp = frame->fp;
+#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+		pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+					   (unsigned long *)(fp - 8));
+#else
 		pc = frame->ra - 0x4;
+#endif
 	}
 }