diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d19d14ba9ae401558e6e387bed2ef0b45aa211ce..b1fdc486aed8239c681acdcab1d98550bbdf60d9 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -184,9 +184,17 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+	/*
+	 * We already refuse to boot CPUs that don't support our configured
+	 * page size, so we can only detect mismatches for a page size other
+	 * than the one we're currently using. Unfortunately, SoCs like this
+	 * exist in the wild so, even though we don't like it, we'll have to go
+	 * along with it and treat them as non-strict.
+	 */
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
 	/* Linux shouldn't care about secure memory */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 1285c7b2947fa74cf50e66b83ec163b2d7a21027..17177325797420cea45062f349f5dde71b72119b 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -73,7 +73,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
-		struct plt_entry trampoline;
+		struct plt_entry trampoline, *dst;
 		struct module *mod;
 
 		/*
@@ -106,23 +106,27 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * to check if the actual opcodes are in fact identical,
 		 * regardless of the offset in memory so use memcmp() instead.
 		 */
-		trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
-		if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
-			   sizeof(trampoline))) {
-			if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
+		dst = mod->arch.ftrace_trampoline;
+		trampoline = get_plt_entry(addr, dst);
+		if (memcmp(dst, &trampoline, sizeof(trampoline))) {
+			if (plt_entry_is_initialized(dst)) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;
 			}
 
 			/* point the trampoline to our ftrace entry point */
 			module_disable_ro(mod);
-			*mod->arch.ftrace_trampoline = trampoline;
+			*dst = trampoline;
 			module_enable_ro(mod, true);
 
-			/* update trampoline before patching in the branch */
-			smp_wmb();
+			/*
+			 * Ensure updated trampoline is visible to instruction
+			 * fetch before we patch in the branch.
+			 */
+			__flush_icache_range((unsigned long)&dst[0],
+					     (unsigned long)&dst[1]);
 		}
-		addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
+		addr = (unsigned long)dst;
 #else /* CONFIG_ARM64_MODULE_PLTS */
 		return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */