diff --git a/Documentation/arch/riscv/uabi.rst b/Documentation/arch/riscv/uabi.rst
index 54d199dce78bf50525b0430dcfc5a6a71429bf68..2b420bab0527a75f09d76c0d7fe9904262830e16 100644
--- a/Documentation/arch/riscv/uabi.rst
+++ b/Documentation/arch/riscv/uabi.rst
@@ -65,4 +65,6 @@ the extension, or may have deliberately removed it from the listing.
 Misaligned accesses
 -------------------
 
-Misaligned accesses are supported in userspace, but they may perform poorly.
+Misaligned scalar accesses are supported in userspace, but they may perform
+poorly.  Misaligned vector accesses are only supported if the Zicclsm extension
+is supported.
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index b94176e25be1810e749cb94686b9c536fd9a2bb0..0525ee2d63c716bc7551b2bedc519cd47b5d4262 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -106,7 +106,7 @@ config RISCV
 	select HAS_IOPORT if MMU
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
-	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT && !XIP_KERNEL
+	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
 	select HAVE_ARCH_KASAN if MMU && 64BIT
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index ddb002ed89dea0dbf4956a5161a0f426bcba557f..808b4c78462e5aa363fc55d7871497efa23d57b4 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -10,7 +10,7 @@
 
 #include <asm/fence.h>
 
-#define __arch_xchg_masked(prepend, append, r, p, n)			\
+#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)		\
 ({									\
 	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
 	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
@@ -25,7 +25,7 @@
 	       "0:	lr.w %0, %2\n"					\
 	       "	and  %1, %0, %z4\n"				\
 	       "	or   %1, %1, %z3\n"				\
-	       "	sc.w %1, %1, %2\n"				\
+	       "	sc.w" sc_sfx " %1, %1, %2\n"			\
 	       "	bnez %1, 0b\n"					\
 	       append							\
 	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
@@ -46,7 +46,8 @@
 		: "memory");						\
 })
 
-#define _arch_xchg(ptr, new, sfx, prepend, append)			\
+#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend,			\
+		   sc_append, swap_append)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __new = (new);				\
@@ -55,15 +56,15 @@
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
 	case 2:								\
-		__arch_xchg_masked(prepend, append,			\
+		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
-		__arch_xchg(".w" sfx, prepend, append,			\
+		__arch_xchg(".w" swap_sfx, prepend, swap_append,	\
 			      __ret, __ptr, __new);			\
 		break;							\
 	case 8:								\
-		__arch_xchg(".d" sfx, prepend, append,			\
+		__arch_xchg(".d" swap_sfx, prepend, swap_append,	\
 			      __ret, __ptr, __new);			\
 		break;							\
 	default:							\
@@ -73,16 +74,17 @@
 })
 
 #define arch_xchg_relaxed(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", "")
+	_arch_xchg(ptr, x, "", "", "", "", "")
 
 #define arch_xchg_acquire(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", RISCV_ACQUIRE_BARRIER)
+	_arch_xchg(ptr, x, "", "", "",					\
+		   RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER)
 
 #define arch_xchg_release(ptr, x)					\
-	_arch_xchg(ptr, x, "", RISCV_RELEASE_BARRIER, "")
+	_arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "")
 
 #define arch_xchg(ptr, x)						\
-	_arch_xchg(ptr, x, ".aqrl", "", "")
+	_arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
 
 #define xchg32(ptr, x)							\
 ({									\
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index 1cc7df740eddc9a2977fde8c428e19fd90ec9126..e6fbaaf549562d6e9ca63a66371441fe8b230cb3 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -72,7 +72,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	/* Make sure tidle is updated */
 	smp_mb();
 	bdata->task_ptr = tidle;
-	bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
+	bdata->stack_ptr = task_pt_regs(tidle);
 	/* Make sure boot data is updated */
 	smp_mb();
 	hsm_data = __pa(bdata);
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
index 613872b0a21acb2a708f194d22f186f376f8a748..24869eb889085e4ae40881230707b54024bad975 100644
--- a/arch/riscv/kernel/cpu_ops_spinwait.c
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -34,8 +34,7 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
 
 	/* Make sure tidle is updated */
 	smp_mb();
-	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid],
-		   task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle));
 	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
 }