diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index b430edfb83f4..be8b68514417 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -12,6 +12,7 @@
 #include <linux/stop_machine.h>
 #include <asm/cacheflush.h>
 #include <asm/text-patching.h>
+#include <asm/insn.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 void ftrace_arch_code_modify_prepare(void)
@@ -63,7 +64,9 @@ static int __ftrace_modify_call(unsigned long source, unsigned long target, bool
 		if (copy_from_kernel_nofault(replaced, (void *)source, 2 * MCOUNT_INSN_SIZE))
 			return -EFAULT;
 
-		if (replaced[0] != call[0]) {
+		/* Bypass the check if the auipc insn is a kprobe breakpoint */
+		if (replaced[0] != call[0] &&
+		    !(riscv_insn_is_ebreak(replaced[0]) || riscv_insn_is_c_ebreak(replaced[0]))) {
 			pr_err("%p: expected (%08x) but got (%08x)\n",
 			       (void *)source, call[0], replaced[0]);
 			return -EINVAL;
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 5a5aa22124e7..36201613d2ca 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -411,4 +411,10 @@ static int __init check_unaligned_access_all_cpus(void)
 	return 0;
 }
 
-late_initcall(check_unaligned_access_all_cpus);
+/*
+ * Run after clocksource_done_booting() so measure_cycles() uses a stable
+ * clocksource, but before rootfs_initcall() enables usermode helpers. Those
+ * helpers can reach hwprobe and populate the vDSO cache, so async hwprobe
+ * probes must be registered first.
+ */
+fs_initcall_sync(check_unaligned_access_all_cpus);
diff --git a/arch/riscv/lib/strnlen.S b/arch/riscv/lib/strnlen.S
index 53afa7b5b314..a8911605c248 100644
--- a/arch/riscv/lib/strnlen.S
+++ b/arch/riscv/lib/strnlen.S
@@ -83,8 +83,13 @@ strnlen_zbb:
 	sub	t3, t3, t2
 	slli	t2, t2, 3
 
-	/* Aligned boundary. */
+	/*
+	 * Aligned boundary.  Use the address of the last valid byte
+	 * (s + count - 1) to avoid loading a word past the count
+	 * boundary in the loop below.  count == 0 is handled above.
+	 */
 	add	t4, a0, a1
+	addi	t4, t4, -1
 	andi	t4, t4, -SZREG
 
 	/* Get the first word.  */
@@ -120,6 +125,9 @@ strnlen_zbb:
 
 	bgtu	t3, a0, 2f
 
+	/* All remaining bytes are in the first word, no loop needed. */
+	bgeu	t0, t4, 2f
+
 	/* Prepare for the word comparison loop. */
 	addi	t2, t0, SZREG
 	li	t3, -1