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
  ...

19 files changed, 1598 insertions, 255 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 148865d..23d8acc 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -115,6 +115,9 @@ config ARCH_RV64I
 	select 64BIT
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 
 endchoice
 
@@ -132,6 +135,10 @@ choice
 		bool "medium any code model"
 endchoice
 
+config MODULE_SECTIONS
+	bool
+	select HAVE_MOD_ARCH_SPECIFIC
+
 choice
 	prompt "Maximum Physical Memory"
 	default MAXPHYSMEM_2GB if 32BIT
@@ -142,6 +149,7 @@ choice
 		bool "2GiB"
 	config MAXPHYSMEM_128GB
 		depends on 64BIT && CMODEL_MEDANY
+		select MODULE_SECTIONS if MODULES
 		bool "128GiB"
 endchoice
 
@@ -282,7 +290,7 @@ config CMDLINE_BOOL
 	  in CONFIG_CMDLINE.
 
 	  The built-in options will be concatenated to the default command
-	  line if CMDLINE_OVERRIDE is set to 'N'. Otherwise, the default
+	  line if CMDLINE_FORCE is set to 'N'. Otherwise, the default
 	  command line will be ignored and replaced by the built-in string.
 
 config CMDLINE
@@ -292,7 +300,7 @@ config CMDLINE
 	help
 	  Supply command-line options at build time by entering them here.
 
-config CMDLINE_OVERRIDE
+config CMDLINE_FORCE
 	bool "Built-in command line overrides bootloader arguments"
 	depends on CMDLINE_BOOL
 	help
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 6719dd3..76e958a 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -11,6 +11,9 @@
 LDFLAGS         :=
 OBJCOPYFLAGS    := -O binary
 LDFLAGS_vmlinux :=
+ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
+	LDFLAGS_vmlinux := --no-relax
+endif
 KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
 
@@ -56,6 +59,11 @@ endif
 ifeq ($(CONFIG_CMODEL_MEDANY),y)
 	KBUILD_CFLAGS += -mcmodel=medany
 endif
+ifeq ($(CONFIG_MODULE_SECTIONS),y)
+	KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/riscv/kernel/module.lds
+endif
+
+KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
 
 # GCC versions that support the "-mstrict-align" option default to allowing
 # unaligned accesses.  While unaligned accesses are explicitly allowed in the
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 47dacf0..bca0eee 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -73,3 +73,5 @@ CONFIG_NFS_V4_2=y
 CONFIG_ROOT_NFS=y
 # CONFIG_RCU_TRACE is not set
 CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index e65d1cd..855115a 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -24,6 +24,20 @@
 #include <asm/barrier.h>
 
 #define ATOMIC_INIT(i)	{ (i) }
+
+#define __atomic_op_acquire(op, args...)				\
+({									\
+	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
+	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory");	\
+	__ret;								\
+})
+
+#define __atomic_op_release(op, args...)				\
+({									\
+	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");	\
+	op##_relaxed(args);						\
+})
+
 static __always_inline int atomic_read(const atomic_t *v)
 {
 	return READ_ONCE(v->counter);
@@ -50,22 +64,23 @@ static __always_inline void atomic64_set(atomic64_t *v, long i)
  * have the AQ or RL bits set.  These don't return anything, so there's only
  * one version to worry about.
  */
-#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix)				\
-static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)	\
-{											\
-	__asm__ __volatile__ (								\
-		"amo" #asm_op "." #asm_type " zero, %1, %0"				\
-		: "+A" (v->counter)							\
-		: "r" (I)								\
-		: "memory");								\
-}
+#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix)		\
+static __always_inline							\
+void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
+{									\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type " zero, %1, %0"	\
+		: "+A" (v->counter)					\
+		: "r" (I)						\
+		: "memory");						\
+}									\
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, I)			\
+#define ATOMIC_OPS(op, asm_op, I)					\
         ATOMIC_OP (op, asm_op, I, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, I)			\
-        ATOMIC_OP (op, asm_op, I, w,  int,   )	\
+#define ATOMIC_OPS(op, asm_op, I)					\
+        ATOMIC_OP (op, asm_op, I, w,  int,   )				\
         ATOMIC_OP (op, asm_op, I, d, long, 64)
 #endif
 
@@ -79,75 +94,115 @@ ATOMIC_OPS(xor, xor,  i)
 #undef ATOMIC_OPS
 
 /*
- * Atomic ops that have ordered, relaxed, acquire, and relese variants.
+ * Atomic ops that have ordered, relaxed, acquire, and release variants.
  * There's two flavors of these: the arithmatic ops have both fetch and return
  * versions, while the logical ops only have fetch versions.
  */
-#define ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, asm_type, c_type, prefix)				\
-static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v)	\
-{													\
-	register c_type ret;										\
-	__asm__ __volatile__ (										\
-		"amo" #asm_op "." #asm_type #asm_or " %1, %2, %0"					\
-		: "+A" (v->counter), "=r" (ret)								\
-		: "r" (I)										\
-		: "memory");										\
-	return ret;											\
+#define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix)	\
+static __always_inline							\
+c_type atomic##prefix##_fetch_##op##_relaxed(c_type i,			\
+					     atomic##prefix##_t *v)	\
+{									\
+	register c_type ret;						\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type " %1, %2, %0"	\
+		: "+A" (v->counter), "=r" (ret)				\
+		: "r" (I)						\
+		: "memory");						\
+	return ret;							\
+}									\
+static __always_inline							\
+c_type atomic##prefix##_fetch_##op(c_type i, atomic##prefix##_t *v)	\
+{									\
+	register c_type ret;						\
+	__asm__ __volatile__ (						\
+		"	amo" #asm_op "." #asm_type ".aqrl  %1, %2, %0"	\
+		: "+A" (v->counter), "=r" (ret)				\
+		: "r" (I)						\
+		: "memory");						\
+	return ret;							\
 }
 
-#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix)			\
-static __always_inline c_type atomic##prefix##_##op##_return##c_or(c_type i, atomic##prefix##_t *v)	\
-{													\
-        return atomic##prefix##_fetch_##op##c_or(i, v) c_op I;						\
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_type, c_type, prefix)	\
+static __always_inline							\
+c_type atomic##prefix##_##op##_return_relaxed(c_type i,			\
+					      atomic##prefix##_t *v)	\
+{									\
+        return atomic##prefix##_fetch_##op##_relaxed(i, v) c_op I;	\
+}									\
+static __always_inline							\
+c_type atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v)	\
+{									\
+        return atomic##prefix##_fetch_##op(i, v) c_op I;		\
 }
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, c_op, I)					\
+        ATOMIC_FETCH_OP( op, asm_op,       I, w,  int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
-        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, d, long, 64)	\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, c_op, I)					\
+        ATOMIC_FETCH_OP( op, asm_op,       I, w,  int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w,  int,   )		\
+        ATOMIC_FETCH_OP( op, asm_op,       I, d, long, 64)		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, long, 64)
 #endif
 
-ATOMIC_OPS(add, add, +,  i,      , _relaxed)
-ATOMIC_OPS(add, add, +,  i, .aq  , _acquire)
-ATOMIC_OPS(add, add, +,  i, .rl  , _release)
-ATOMIC_OPS(add, add, +,  i, .aqrl,         )
+ATOMIC_OPS(add, add, +,  i)
+ATOMIC_OPS(sub, add, +, -i)
+
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_add_return		atomic_add_return
+#define atomic_sub_return		atomic_sub_return
 
-ATOMIC_OPS(sub, add, +, -i,      , _relaxed)
-ATOMIC_OPS(sub, add, +, -i, .aq  , _acquire)
-ATOMIC_OPS(sub, add, +, -i, .rl  , _release)
-ATOMIC_OPS(sub, add, +, -i, .aqrl,         )
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+#define atomic_fetch_add		atomic_fetch_add
+#define atomic_fetch_sub		atomic_fetch_sub
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_add_return		atomic64_add_return
+#define atomic64_sub_return		atomic64_sub_return
+
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+#define atomic64_fetch_add		atomic64_fetch_add
+#define atomic64_fetch_sub		atomic64_fetch_sub
+#endif
 
 #undef ATOMIC_OPS
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, I)					\
+        ATOMIC_FETCH_OP(op, asm_op, I, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )	\
-        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I)					\
+        ATOMIC_FETCH_OP(op, asm_op, I, w,  int,   )			\
+        ATOMIC_FETCH_OP(op, asm_op, I, d, long, 64)
 #endif
 
-ATOMIC_OPS(and, and, i,      , _relaxed)
-ATOMIC_OPS(and, and, i, .aq  , _acquire)
-ATOMIC_OPS(and, and, i, .rl  , _release)
-ATOMIC_OPS(and, and, i, .aqrl,         )
+ATOMIC_OPS(and, and, i)
+ATOMIC_OPS( or,  or, i)
+ATOMIC_OPS(xor, xor, i)
 
-ATOMIC_OPS( or,  or, i,      , _relaxed)
-ATOMIC_OPS( or,  or, i, .aq  , _acquire)
-ATOMIC_OPS( or,  or, i, .rl  , _release)
-ATOMIC_OPS( or,  or, i, .aqrl,         )
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
+#define atomic_fetch_and		atomic_fetch_and
+#define atomic_fetch_or			atomic_fetch_or
+#define atomic_fetch_xor		atomic_fetch_xor
 
-ATOMIC_OPS(xor, xor, i,      , _relaxed)
-ATOMIC_OPS(xor, xor, i, .aq  , _acquire)
-ATOMIC_OPS(xor, xor, i, .rl  , _release)
-ATOMIC_OPS(xor, xor, i, .aqrl,         )
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
+#define atomic64_fetch_and		atomic64_fetch_and
+#define atomic64_fetch_or		atomic64_fetch_or
+#define atomic64_fetch_xor		atomic64_fetch_xor
+#endif
 
 #undef ATOMIC_OPS
 
@@ -157,22 +212,24 @@ ATOMIC_OPS(xor, xor, i, .aqrl,         )
 /*
  * The extra atomic operations that are constructed from one of the core
  * AMO-based operations above (aside from sub, which is easier to fit above).
- * These are required to perform a barrier, but they're OK this way because
- * atomic_*_return is also required to perform a barrier.
+ * These are required to perform a full barrier, but they're OK this way
+ * because atomic_*_return is also required to perform a full barrier.
+ *
  */
-#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix)			\
-static __always_inline bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
-{										\
-	return atomic##prefix##_##func_op##_return(i, v) comp_op I;		\
+#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix)		\
+static __always_inline							\
+bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
+{									\
+	return atomic##prefix##_##func_op##_return(i, v) comp_op I;	\
 }
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, func_op, comp_op, I)			\
-        ATOMIC_OP (op, func_op, comp_op, I,  int,   )
+#define ATOMIC_OPS(op, func_op, comp_op, I)				\
+        ATOMIC_OP(op, func_op, comp_op, I,  int,   )
 #else
-#define ATOMIC_OPS(op, func_op, comp_op, I)			\
-        ATOMIC_OP (op, func_op, comp_op, I,  int,   )		\
-        ATOMIC_OP (op, func_op, comp_op, I, long, 64)
+#define ATOMIC_OPS(op, func_op, comp_op, I)				\
+        ATOMIC_OP(op, func_op, comp_op, I,  int,   )			\
+        ATOMIC_OP(op, func_op, comp_op, I, long, 64)
 #endif
 
 ATOMIC_OPS(add_and_test, add, ==, 0)
@@ -182,51 +239,87 @@ ATOMIC_OPS(add_negative, add,  <, 0)
 #undef ATOMIC_OP
 #undef ATOMIC_OPS
 
-#define ATOMIC_OP(op, func_op, I, c_type, prefix)				\
-static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v)	\
-{										\
-	atomic##prefix##_##func_op(I, v);					\
+#define ATOMIC_OP(op, func_op, I, c_type, prefix)			\
+static __always_inline							\
+void atomic##prefix##_##op(atomic##prefix##_t *v)			\
+{									\
+	atomic##prefix##_##func_op(I, v);				\
 }
 
-#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)					\
-static __always_inline c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)	\
-{											\
-	return atomic##prefix##_fetch_##func_op(I, v);					\
+#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)			\
+static __always_inline							\
+c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v)	\
+{									\
+	return atomic##prefix##_fetch_##func_op##_relaxed(I, v);	\
+}									\
+static __always_inline							\
+c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)		\
+{									\
+	return atomic##prefix##_fetch_##func_op(I, v);			\
 }
 
-#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix)				\
-static __always_inline c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v)	\
-{											\
-        return atomic##prefix##_fetch_##op(v) c_op I;					\
+#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix)		\
+static __always_inline							\
+c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v)	\
+{									\
+        return atomic##prefix##_fetch_##op##_relaxed(v) c_op I;		\
+}									\
+static __always_inline							\
+c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v)		\
+{									\
+        return atomic##prefix##_fetch_##op(v) c_op I;			\
 }
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
+#define ATOMIC_OPS(op, asm_op, c_op, I)					\
+        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
+        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_OP       (op, asm_op,       I, long, 64)				\
-        ATOMIC_FETCH_OP (op, asm_op,       I, long, 64)				\
+#define ATOMIC_OPS(op, asm_op, c_op, I)					\
+        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
+        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )			\
+        ATOMIC_OP(       op, asm_op,       I, long, 64)			\
+        ATOMIC_FETCH_OP( op, asm_op,       I, long, 64)			\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
 #endif
 
 ATOMIC_OPS(inc, add, +,  1)
 ATOMIC_OPS(dec, add, +, -1)
 
+#define atomic_inc_return_relaxed	atomic_inc_return_relaxed
+#define atomic_dec_return_relaxed	atomic_dec_return_relaxed
+#define atomic_inc_return		atomic_inc_return
+#define atomic_dec_return		atomic_dec_return
+
+#define atomic_fetch_inc_relaxed	atomic_fetch_inc_relaxed
+#define atomic_fetch_dec_relaxed	atomic_fetch_dec_relaxed
+#define atomic_fetch_inc		atomic_fetch_inc
+#define atomic_fetch_dec		atomic_fetch_dec
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+#define atomic64_inc_return_relaxed	atomic64_inc_return_relaxed
+#define atomic64_dec_return_relaxed	atomic64_dec_return_relaxed
+#define atomic64_inc_return		atomic64_inc_return
+#define atomic64_dec_return		atomic64_dec_return
+
+#define atomic64_fetch_inc_relaxed	atomic64_fetch_inc_relaxed
+#define atomic64_fetch_dec_relaxed	atomic64_fetch_dec_relaxed
+#define atomic64_fetch_inc		atomic64_fetch_inc
+#define atomic64_fetch_dec		atomic64_fetch_dec
+#endif
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
-#define ATOMIC_OP(op, func_op, comp_op, I, prefix)				\
-static __always_inline bool atomic##prefix##_##op(atomic##prefix##_t *v)	\
-{										\
-	return atomic##prefix##_##func_op##_return(v) comp_op I;		\
+#define ATOMIC_OP(op, func_op, comp_op, I, prefix)			\
+static __always_inline							\
+bool atomic##prefix##_##op(atomic##prefix##_t *v)			\
+{									\
+	return atomic##prefix##_##func_op##_return(v) comp_op I;	\
 }
 
 ATOMIC_OP(inc_and_test, inc, ==, 0,   )
@@ -238,19 +331,19 @@ ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
 
 #undef ATOMIC_OP
 
-/* This is required to provide a barrier on success. */
+/* This is required to provide a full barrier on success. */
 static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
        int prev, rc;
 
 	__asm__ __volatile__ (
-		"0:\n\t"
-		"lr.w.aqrl  %[p],  %[c]\n\t"
-		"beq        %[p],  %[u], 1f\n\t"
-		"add       %[rc],  %[p], %[a]\n\t"
-		"sc.w.aqrl %[rc], %[rc], %[c]\n\t"
-		"bnez      %[rc], 0b\n\t"
-		"1:"
+		"0:	lr.w     %[p],  %[c]\n"
+		"	beq      %[p],  %[u], 1f\n"
+		"	add      %[rc], %[p], %[a]\n"
+		"	sc.w.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
 		: [a]"r" (a), [u]"r" (u)
 		: "memory");
@@ -263,13 +356,13 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
        long prev, rc;
 
 	__asm__ __volatile__ (
-		"0:\n\t"
-		"lr.d.aqrl  %[p],  %[c]\n\t"
-		"beq        %[p],  %[u], 1f\n\t"
-		"add       %[rc],  %[p], %[a]\n\t"
-		"sc.d.aqrl %[rc], %[rc], %[c]\n\t"
-		"bnez      %[rc], 0b\n\t"
-		"1:"
+		"0:	lr.d     %[p],  %[c]\n"
+		"	beq      %[p],  %[u], 1f\n"
+		"	add      %[rc], %[p], %[a]\n"
+		"	sc.d.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
 		: [a]"r" (a), [u]"r" (u)
 		: "memory");
@@ -300,37 +393,63 @@ static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
 
 /*
  * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
- * {cmp,}xchg and the operations that return, so they need a barrier.
- */
-/*
- * FIXME: atomic_cmpxchg_{acquire,release,relaxed} are all implemented by
- * assigning the same barrier to both the LR and SC operations, but that might
- * not make any sense.  We're waiting on a memory model specification to
- * determine exactly what the right thing to do is here.
+ * {cmp,}xchg and the operations that return, so they need a full barrier.
  */
-#define ATOMIC_OP(c_t, prefix, c_or, size, asm_or)						\
-static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) 	\
-{												\
-	return __cmpxchg(&(v->counter), o, n, size, asm_or, asm_or);				\
-}												\
-static __always_inline c_t atomic##prefix##_xchg##c_or(atomic##prefix##_t *v, c_t n) 		\
-{												\
-	return __xchg(n, &(v->counter), size, asm_or);						\
+#define ATOMIC_OP(c_t, prefix, size)					\
+static __always_inline							\
+c_t atomic##prefix##_xchg_relaxed(atomic##prefix##_t *v, c_t n)		\
+{									\
+	return __xchg_relaxed(&(v->counter), n, size);			\
+}									\
+static __always_inline							\
+c_t atomic##prefix##_xchg_acquire(atomic##prefix##_t *v, c_t n)		\
+{									\
+	return __xchg_acquire(&(v->counter), n, size);			\
+}									\
+static __always_inline							\
+c_t atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n)		\
+{									\
+	return __xchg_release(&(v->counter), n, size);			\
+}									\
+static __always_inline							\
+c_t atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n)			\
+{									\
+	return __xchg(&(v->counter), n, size);				\
+}									\
+static __always_inline							\
+c_t atomic##prefix##_cmpxchg_relaxed(atomic##prefix##_t *v,		\
+				     c_t o, c_t n)			\
+{									\
+	return __cmpxchg_relaxed(&(v->counter), o, n, size);		\
+}									\
+static __always_inline							\
+c_t atomic##prefix##_cmpxchg_acquire(atomic##prefix##_t *v,		\
+				     c_t o, c_t n)			\
+{									\
+	return __cmpxchg_acquire(&(v->counter), o, n, size);		\
+}									\
+static __always_inline							\
+c_t atomic##prefix##_cmpxchg_release(atomic##prefix##_t *v,		\
+				     c_t o, c_t n)			\
+{									\
+	return __cmpxchg_release(&(v->counter), o, n, size);		\
+}									\
+static __always_inline							\
+c_t atomic##prefix##_cmpxchg(atomic##prefix##_t *v, c_t o, c_t n)	\
+{									\
+	return __cmpxchg(&(v->counter), o, n, size);			\
 }
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(c_or, asm_or)			\
-	ATOMIC_OP( int,   , c_or, 4, asm_or)
+#define ATOMIC_OPS()							\
+	ATOMIC_OP( int,   , 4)
 #else
-#define ATOMIC_OPS(c_or, asm_or)			\
-	ATOMIC_OP( int,   , c_or, 4, asm_or)		\
-	ATOMIC_OP(long, 64, c_or, 8, asm_or)
+#define ATOMIC_OPS()							\
+	ATOMIC_OP( int,   , 4)						\
+	ATOMIC_OP(long, 64, 8)
 #endif
 
-ATOMIC_OPS(        , .aqrl)
-ATOMIC_OPS(_acquire,   .aq)
-ATOMIC_OPS(_release,   .rl)
-ATOMIC_OPS(_relaxed,      )
+ATOMIC_OPS()
 
 #undef ATOMIC_OPS
 #undef ATOMIC_OP
@@ -340,13 +459,13 @@ static __always_inline int atomic_sub_if_positive(atomic_t *v, int offset)
        int prev, rc;
 
 	__asm__ __volatile__ (
-		"0:\n\t"
-		"lr.w.aqrl  %[p],  %[c]\n\t"
-		"sub       %[rc],  %[p], %[o]\n\t"
-		"bltz      %[rc],    1f\n\t"
-		"sc.w.aqrl %[rc], %[rc], %[c]\n\t"
-		"bnez      %[rc],    0b\n\t"
-		"1:"
+		"0:	lr.w     %[p],  %[c]\n"
+		"	sub      %[rc], %[p], %[o]\n"
+		"	bltz     %[rc], 1f\n"
+		"	sc.w.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
 		: [o]"r" (offset)
 		: "memory");
@@ -361,13 +480,13 @@ static __always_inline long atomic64_sub_if_positive(atomic64_t *v, int offset)
        long prev, rc;
 
 	__asm__ __volatile__ (
-		"0:\n\t"
-		"lr.d.aqrl  %[p],  %[c]\n\t"
-		"sub       %[rc],  %[p], %[o]\n\t"
-		"bltz      %[rc],    1f\n\t"
-		"sc.d.aqrl %[rc], %[rc], %[c]\n\t"
-		"bnez      %[rc],    0b\n\t"
-		"1:"
+		"0:	lr.d     %[p],  %[c]\n"
+		"	sub      %[rc], %[p], %[o]\n"
+		"	bltz     %[rc], 1f\n"
+		"	sc.d.rl  %[rc], %[rc], %[c]\n"
+		"	bnez     %[rc], 0b\n"
+		"	fence    rw, rw\n"
+		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
 		: [o]"r" (offset)
 		: "memory");
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 5510366..d4628e4 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -38,6 +38,21 @@
 #define __smp_rmb()	RISCV_FENCE(r,r)
 #define __smp_wmb()	RISCV_FENCE(w,w)
 
+#define __smp_store_release(p, v)					\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	RISCV_FENCE(rw,w);						\
+	WRITE_ONCE(*p, v);						\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	RISCV_FENCE(r,rw);						\
+	___p1;								\
+})
+
 /*
  * This is a very specific barrier: it's currently only used in two places in
  * the kernel, both in the scheduler.  See include/linux/spinlock.h for the two
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index db249db..c12833f 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -17,45 +17,153 @@
 #include <linux/bug.h>
 
 #include <asm/barrier.h>
+#include <asm/fence.h>
 
-#define __xchg(new, ptr, size, asm_or)				\
-({								\
-	__typeof__(ptr) __ptr = (ptr);				\
-	__typeof__(new) __new = (new);				\
-	__typeof__(*(ptr)) __ret;				\
-	switch (size) {						\
-	case 4:							\
-		__asm__ __volatile__ (				\
-			"amoswap.w" #asm_or " %0, %2, %1"	\
-			: "=r" (__ret), "+A" (*__ptr)		\
-			: "r" (__new)				\
-			: "memory");				\
-		break;						\
-	case 8:							\
-		__asm__ __volatile__ (				\
-			"amoswap.d" #asm_or " %0, %2, %1"	\
-			: "=r" (__ret), "+A" (*__ptr)		\
-			: "r" (__new)				\
-			: "memory");				\
-		break;						\
-	default:						\
-		BUILD_BUG();					\
-	}							\
-	__ret;							\
-})
-
-#define xchg(ptr, x)    (__xchg((x), (ptr), sizeof(*(ptr)), .aqrl))
-
-#define xchg32(ptr, x)				\
-({						\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 4);	\
-	xchg((ptr), (x));			\
-})
-
-#define xchg64(ptr, x)				\
-({						\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);	\
-	xchg((ptr), (x));			\
+#define __xchg_relaxed(ptr, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.w %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.d %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define xchg_relaxed(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
+					    _x_, sizeof(*(ptr)));	\
+})
+
+#define __xchg_acquire(ptr, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.w %0, %2, %1\n"			\
+			RISCV_ACQUIRE_BARRIER				\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.d %0, %2, %1\n"			\
+			RISCV_ACQUIRE_BARRIER				\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define xchg_acquire(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_acquire((ptr),			\
+					    _x_, sizeof(*(ptr)));	\
+})
+
+#define __xchg_release(ptr, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"	amoswap.w %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"	amoswap.d %0, %2, %1\n"			\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define xchg_release(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_release((ptr),			\
+					    _x_, sizeof(*(ptr)));	\
+})
+
+#define __xchg(ptr, new, size)						\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(new) __new = (new);					\
+	__typeof__(*(ptr)) __ret;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.w.aqrl %0, %2, %1\n"		\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"	amoswap.d.aqrl %0, %2, %1\n"		\
+			: "=r" (__ret), "+A" (*__ptr)			\
+			: "r" (__new)					\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define xchg(ptr, x)							\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg((ptr), _x_, sizeof(*(ptr)));	\
+})
+
+#define xchg32(ptr, x)							\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
+	xchg((ptr), (x));						\
+})
+
+#define xchg64(ptr, x)							\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	xchg((ptr), (x));						\
 })
 
 /*
@@ -63,7 +171,51 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
-#define __cmpxchg(ptr, old, new, size, lrb, scb)			\
+#define __cmpxchg_relaxed(ptr, old, new, size)				\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __ret;					\
+	register unsigned int __rc;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define cmpxchg_relaxed(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_relaxed((ptr),			\
+					_o_, _n_, sizeof(*(ptr)));	\
+})
+
+#define __cmpxchg_acquire(ptr, old, new, size)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(ptr)) __old = (old);				\
@@ -73,24 +225,24 @@
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__ (					\
-		"0:"							\
-			"lr.w" #scb " %0, %2\n"				\
-			"bne         %0, %z3, 1f\n"			\
-			"sc.w" #lrb " %1, %z4, %2\n"			\
-			"bnez        %1, 0b\n"				\
-		"1:"							\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			RISCV_ACQUIRE_BARRIER				\
+			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" (__old), "rJ" (__new)			\
 			: "memory");					\
 		break;							\
 	case 8:								\
 		__asm__ __volatile__ (					\
-		"0:"							\
-			"lr.d" #scb " %0, %2\n"				\
-			"bne         %0, %z3, 1f\n"			\
-			"sc.d" #lrb " %1, %z4, %2\n"			\
-			"bnez        %1, 0b\n"				\
-		"1:"							\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			RISCV_ACQUIRE_BARRIER				\
+			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" (__old), "rJ" (__new)			\
 			: "memory");					\
@@ -101,34 +253,131 @@
 	__ret;								\
 })
 
-#define cmpxchg(ptr, o, n) \
-	(__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), .aqrl, .aqrl))
+#define cmpxchg_acquire(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_acquire((ptr),			\
+					_o_, _n_, sizeof(*(ptr)));	\
+})
 
-#define cmpxchg_local(ptr, o, n) \
-	(__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), , ))
+#define __cmpxchg_release(ptr, old, new, size)				\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __ret;					\
+	register unsigned int __rc;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			RISCV_RELEASE_BARRIER				\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
+
+#define cmpxchg_release(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_release((ptr),			\
+					_o_, _n_, sizeof(*(ptr)));	\
+})
+
+#define __cmpxchg(ptr, old, new, size)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __ret;					\
+	register unsigned int __rc;					\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.w %0, %2\n"				\
+			"	bne  %0, %z3, 1f\n"			\
+			"	sc.w.rl %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"	fence rw, rw\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__ (					\
+			"0:	lr.d %0, %2\n"				\
+			"	bne %0, %z3, 1f\n"			\
+			"	sc.d.rl %1, %z4, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			"	fence rw, rw\n"				\
+			"1:\n"						\
+			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
+			: "rJ" (__old), "rJ" (__new)			\
+			: "memory");					\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+	__ret;								\
+})
 
-#define cmpxchg32(ptr, o, n)			\
-({						\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 4);	\
-	cmpxchg((ptr), (o), (n));		\
+#define cmpxchg(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg((ptr),				\
+				       _o_, _n_, sizeof(*(ptr)));	\
 })
 
-#define cmpxchg32_local(ptr, o, n)		\
-({						\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 4);	\
-	cmpxchg_local((ptr), (o), (n));		\
+#define cmpxchg_local(ptr, o, n)					\
+	(__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
+
+#define cmpxchg32(ptr, o, n)						\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
+	cmpxchg((ptr), (o), (n));					\
 })
 
-#define cmpxchg64(ptr, o, n)			\
-({						\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);	\
-	cmpxchg((ptr), (o), (n));		\
+#define cmpxchg32_local(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
+	cmpxchg_relaxed((ptr), (o), (n))				\
 })
 
-#define cmpxchg64_local(ptr, o, n)		\
-({						\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);	\
-	cmpxchg_local((ptr), (o), (n));		\
+#define cmpxchg64(ptr, o, n)						\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg((ptr), (o), (n));					\
+})
+
+#define cmpxchg64_local(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_relaxed((ptr), (o), (n));				\
 })
 
 #endif /* _ASM_RISCV_CMPXCHG_H */
diff --git a/arch/riscv/include/asm/fence.h b/arch/riscv/include/asm/fence.h
new file mode 100644
index 0000000..2b443a3
--- /dev/null
+++ b/arch/riscv/include/asm/fence.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_RISCV_FENCE_H
+#define _ASM_RISCV_FENCE_H
+
+#ifdef CONFIG_SMP
+#define RISCV_ACQUIRE_BARRIER		"\tfence r , rw\n"
+#define RISCV_RELEASE_BARRIER		"\tfence rw,  w\n"
+#else
+#define RISCV_ACQUIRE_BARRIER
+#define RISCV_RELEASE_BARRIER
+#endif
+
+#endif	/* _ASM_RISCV_FENCE_H */
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 66d4175..c6dcc52 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -8,3 +8,59 @@
 #if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_FRAME_POINTER)
 #define HAVE_FUNCTION_GRAPH_FP_TEST
 #endif
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#ifndef __ASSEMBLY__
+void _mcount(void);
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+struct dyn_arch_ftrace {
+};
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * A general call in RISC-V is a pair of insts:
+ * 1) auipc: setting high-20 pc-related bits to ra register
+ * 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to
+ *          return address (original pc + 4)
+ *
+ * Dynamic ftrace generates probes to call sites, so we must deal with
+ * both auipc and jalr at the same time.
+ */
+
+#define MCOUNT_ADDR		((unsigned long)_mcount)
+#define JALR_SIGN_MASK		(0x00000800)
+#define JALR_OFFSET_MASK	(0x00000fff)
+#define AUIPC_OFFSET_MASK	(0xfffff000)
+#define AUIPC_PAD		(0x00001000)
+#define JALR_SHIFT		20
+#define JALR_BASIC		(0x000080e7)
+#define AUIPC_BASIC		(0x00000097)
+#define NOP4			(0x00000013)
+
+#define make_call(caller, callee, call)					\
+do {									\
+	call[0] = to_auipc_insn((unsigned int)((unsigned long)callee -	\
+				(unsigned long)caller));		\
+	call[1] = to_jalr_insn((unsigned int)((unsigned long)callee -	\
+			       (unsigned long)caller));			\
+} while (0)
+
+#define to_jalr_insn(offset)						\
+	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_BASIC)
+
+#define to_auipc_insn(offset)						\
+	((offset & JALR_SIGN_MASK) ?					\
+	(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_BASIC) :	\
+	((offset & AUIPC_OFFSET_MASK) | AUIPC_BASIC))
+
+/*
+ * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.
+ */
+#define MCOUNT_INSN_SIZE 8
+#endif
diff --git a/arch/riscv/include/asm/module.h b/arch/riscv/include/asm/module.h
new file mode 100644
index 0000000..349df33
--- /dev/null
+++ b/arch/riscv/include/asm/module.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#ifndef _ASM_RISCV_MODULE_H
+#define _ASM_RISCV_MODULE_H
+
+#include <asm-generic/module.h>
+
+#define MODULE_ARCH_VERMAGIC    "riscv"
+
+u64 module_emit_got_entry(struct module *mod, u64 val);
+u64 module_emit_plt_entry(struct module *mod, u64 val);
+
+#ifdef CONFIG_MODULE_SECTIONS
+struct mod_section {
+	struct elf64_shdr *shdr;
+	int num_entries;
+	int max_entries;
+};
+
+struct mod_arch_specific {
+	struct mod_section got;
+	struct mod_section plt;
+	struct mod_section got_plt;
+};
+
+struct got_entry {
+	u64 symbol_addr;	/* the real variable address */
+};
+
+static inline struct got_entry emit_got_entry(u64 val)
+{
+	return (struct got_entry) {val};
+}
+
+static inline struct got_entry *get_got_entry(u64 val,
+					      const struct mod_section *sec)
+{
+	struct got_entry *got = (struct got_entry *)sec->shdr->sh_addr;
+	int i;
+	for (i = 0; i < sec->num_entries; i++) {
+		if (got[i].symbol_addr == val)
+			return &got[i];
+	}
+	return NULL;
+}
+
+struct plt_entry {
+	/*
+	 * Trampoline code to real target address. The return address
+	 * should be the original (pc+4) before entring plt entry.
+	 */
+	u32 insn_auipc;		/* auipc t0, 0x0                       */
+	u32 insn_ld;		/* ld    t1, 0x10(t0)                  */
+	u32 insn_jr;		/* jr    t1                            */
+};
+
+#define OPC_AUIPC  0x0017
+#define OPC_LD     0x3003
+#define OPC_JALR   0x0067
+#define REG_T0     0x5
+#define REG_T1     0x6
+
+static inline struct plt_entry emit_plt_entry(u64 val, u64 plt, u64 got_plt)
+{
+	/*
+	 * U-Type encoding:
+	 * +------------+----------+----------+
+	 * | imm[31:12] | rd[11:7] | opc[6:0] |
+	 * +------------+----------+----------+
+	 *
+	 * I-Type encoding:
+	 * +------------+------------+--------+----------+----------+
+	 * | imm[31:20] | rs1[19:15] | funct3 | rd[11:7] | opc[6:0] |
+	 * +------------+------------+--------+----------+----------+
+	 *
+	 */
+	u64 offset = got_plt - plt;
+	u32 hi20 = (offset + 0x800) & 0xfffff000;
+	u32 lo12 = (offset - hi20);
+	return (struct plt_entry) {
+		OPC_AUIPC | (REG_T0 << 7) | hi20,
+		OPC_LD | (lo12 << 20) | (REG_T0 << 15) | (REG_T1 << 7),
+		OPC_JALR | (REG_T1 << 15)
+	};
+}
+
+static inline int get_got_plt_idx(u64 val, const struct mod_section *sec)
+{
+	struct got_entry *got_plt = (struct got_entry *)sec->shdr->sh_addr;
+	int i;
+	for (i = 0; i < sec->num_entries; i++) {
+		if (got_plt[i].symbol_addr == val)
+			return i;
+	}
+	return -1;
+}
+
+static inline struct plt_entry *get_plt_entry(u64 val,
+				      const struct mod_section *sec_plt,
+				      const struct mod_section *sec_got_plt)
+{
+	struct plt_entry *plt = (struct plt_entry *)sec_plt->shdr->sh_addr;
+	int got_plt_idx = get_got_plt_idx(val, sec_got_plt);
+	if (got_plt_idx >= 0)
+		return plt + got_plt_idx;
+	else
+		return NULL;
+}
+
+#endif /* CONFIG_MODULE_SECTIONS */
+
+#endif /* _ASM_RISCV_MODULE_H */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
index 2fd27e8..8eb26d1 100644
--- a/arch/riscv/include/asm/spinlock.h
+++ b/arch/riscv/include/asm/spinlock.h
@@ -17,6 +17,7 @@
 
 #include <linux/kernel.h>
 #include <asm/current.h>
+#include <asm/fence.h>
 
 /*
  * Simple spin lock operations.  These provide no fairness guarantees.
@@ -28,10 +29,7 @@
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	__asm__ __volatile__ (
-		"amoswap.w.rl x0, x0, %0"
-		: "=A" (lock->lock)
-		:: "memory");
+	smp_store_release(&lock->lock, 0);
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
@@ -39,7 +37,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 	int tmp = 1, busy;
 
 	__asm__ __volatile__ (
-		"amoswap.w.aq %0, %2, %1"
+		"	amoswap.w %0, %2, %1\n"
+		RISCV_ACQUIRE_BARRIER
 		: "=r" (busy), "+A" (lock->lock)
 		: "r" (tmp)
 		: "memory");
@@ -68,8 +67,9 @@ static inline void arch_read_lock(arch_rwlock_t *lock)
 		"1:	lr.w	%1, %0\n"
 		"	bltz	%1, 1b\n"
 		"	addi	%1, %1, 1\n"
-		"	sc.w.aq	%1, %1, %0\n"
+		"	sc.w	%1, %1, %0\n"
 		"	bnez	%1, 1b\n"
+		RISCV_ACQUIRE_BARRIER
 		: "+A" (lock->lock), "=&r" (tmp)
 		:: "memory");
 }
@@ -82,8 +82,9 @@ static inline void arch_write_lock(arch_rwlock_t *lock)
 		"1:	lr.w	%1, %0\n"
 		"	bnez	%1, 1b\n"
 		"	li	%1, -1\n"
-		"	sc.w.aq	%1, %1, %0\n"
+		"	sc.w	%1, %1, %0\n"
 		"	bnez	%1, 1b\n"
+		RISCV_ACQUIRE_BARRIER
 		: "+A" (lock->lock), "=&r" (tmp)
 		:: "memory");
 }
@@ -96,8 +97,9 @@ static inline int arch_read_trylock(arch_rwlock_t *lock)
 		"1:	lr.w	%1, %0\n"
 		"	bltz	%1, 1f\n"
 		"	addi	%1, %1, 1\n"
-		"	sc.w.aq	%1, %1, %0\n"
+		"	sc.w	%1, %1, %0\n"
 		"	bnez	%1, 1b\n"
+		RISCV_ACQUIRE_BARRIER
 		"1:\n"
 		: "+A" (lock->lock), "=&r" (busy)
 		:: "memory");
@@ -113,8 +115,9 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
 		"1:	lr.w	%1, %0\n"
 		"	bnez	%1, 1f\n"
 		"	li	%1, -1\n"
-		"	sc.w.aq	%1, %1, %0\n"
+		"	sc.w	%1, %1, %0\n"
 		"	bnez	%1, 1b\n"
+		RISCV_ACQUIRE_BARRIER
 		"1:\n"
 		: "+A" (lock->lock), "=&r" (busy)
 		:: "memory");
@@ -125,7 +128,8 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
 static inline void arch_read_unlock(arch_rwlock_t *lock)
 {
 	__asm__ __volatile__(
-		"amoadd.w.rl x0, %1, %0"
+		RISCV_RELEASE_BARRIER
+		"	amoadd.w x0, %1, %0\n"
 		: "+A" (lock->lock)
 		: "r" (-1)
 		: "memory");
@@ -133,10 +137,7 @@ static inline void arch_read_unlock(arch_rwlock_t *lock)
 
 static inline void arch_write_unlock(arch_rwlock_t *lock)
 {
-	__asm__ __volatile__ (
-		"amoswap.w.rl x0, x0, %0"
-		: "=A" (lock->lock)
-		:: "memory");
+	smp_store_release(&lock->lock, 0);
 }
 
 #endif /* _ASM_RISCV_SPINLOCK_H */
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
index a510edfa..5cae4c3 100644
--- a/arch/riscv/include/uapi/asm/elf.h
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -79,5 +79,12 @@ typedef union __riscv_fp_state elf_fpregset_t;
 #define R_RISCV_TPREL_I		49
 #define R_RISCV_TPREL_S		50
 #define R_RISCV_RELAX		51
+#define R_RISCV_SUB6		52
+#define R_RISCV_SET6		53
+#define R_RISCV_SET8		54
+#define R_RISCV_SET16		55
+#define R_RISCV_SET32		56
+#define R_RISCV_32_PCREL	57
+
 
 #endif /* _UAPI_ASM_ELF_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 196f62f..8586dd9 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 d0de68d..1157b6b 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 0000000..35a6ed7
--- /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 c46a778..ce9bdc5 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 0000000..bbbd26e
--- /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 e0f0503..5dddba3 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 0000000..295ecfb
--- /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 559aae7..a4b1d94 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
 	}
 }