diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 2b575792363e5..e4dba5461cb3e 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -102,6 +102,8 @@ config CRYPTO_AES_ARM_BS
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
+	select CRYPTO_AES
+	select CRYPTO_CBC
 	select CRYPTO_SIMD
 	help
 	  Use a faster and more secure NEON based implementation of AES in CBC,
diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S
index 946f74dd6fbaa..259383e1ad440 100644
--- a/arch/x86/crypto/chacha-avx512vl-x86_64.S
+++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S
@@ -172,7 +172,7 @@ SYM_FUNC_START(chacha_2block_xor_avx512vl)
 	# xor remaining bytes from partial register into output
 	mov		%rcx,%rax
 	and		$0xf,%rcx
-	jz		.Ldone8
+	jz		.Ldone2
 	mov		%rax,%r9
 	and		$~0xf,%r9
 
@@ -438,7 +438,7 @@ SYM_FUNC_START(chacha_4block_xor_avx512vl)
 	# xor remaining bytes from partial register into output
 	mov		%rcx,%rax
 	and		$0xf,%rcx
-	jz		.Ldone8
+	jz		.Ldone4
 	mov		%rax,%r9
 	and		$~0xf,%r9
 
diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
index 71fae5a09e56d..2077ce7a56479 100644
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
@@ -297,7 +297,7 @@ sub poly1305_iteration {
 $code.=<<___;
 	mov	\$1,%eax
 .Lno_key:
-	ret
+	RET
 ___
 &end_function("poly1305_init_x86_64");
 
@@ -373,7 +373,7 @@ sub poly1305_iteration {
 .cfi_adjust_cfa_offset	-48
 .Lno_data:
 .Lblocks_epilogue:
-	ret
+	RET
 .cfi_endproc
 ___
 &end_function("poly1305_blocks_x86_64");
@@ -399,7 +399,7 @@ sub poly1305_iteration {
 	mov	%rax,0($mac)	# write result
 	mov	%rcx,8($mac)
 
-	ret
+	RET
 ___
 &end_function("poly1305_emit_x86_64");
 if ($avx) {
@@ -429,7 +429,7 @@ sub poly1305_iteration {
 	&poly1305_iteration();
 $code.=<<___;
 	pop $ctx
-	ret
+	RET
 .size	__poly1305_block,.-__poly1305_block
 
 .type	__poly1305_init_avx,\@abi-omnipotent
@@ -594,7 +594,7 @@ sub poly1305_iteration {
 
 	lea	-48-64($ctx),$ctx	# size [de-]optimization
 	pop %rbp
-	ret
+	RET
 .size	__poly1305_init_avx,.-__poly1305_init_avx
 ___
 
@@ -747,7 +747,7 @@ sub poly1305_iteration {
 .cfi_restore	%rbp
 .Lno_data_avx:
 .Lblocks_avx_epilogue:
-	ret
+	RET
 .cfi_endproc
 
 .align	32
@@ -1452,7 +1452,7 @@ sub poly1305_iteration {
 ___
 $code.=<<___;
 	vzeroupper
-	ret
+	RET
 .cfi_endproc
 ___
 &end_function("poly1305_blocks_avx");
@@ -1508,7 +1508,7 @@ sub poly1305_iteration {
 	mov	%rax,0($mac)	# write result
 	mov	%rcx,8($mac)
 
-	ret
+	RET
 ___
 &end_function("poly1305_emit_avx");
 
@@ -1675,7 +1675,7 @@ sub poly1305_blocks_avxN {
 .cfi_restore 	%rbp
 .Lno_data_avx2$suffix:
 .Lblocks_avx2_epilogue$suffix:
-	ret
+	RET
 .cfi_endproc
 
 .align	32
@@ -2201,7 +2201,7 @@ sub poly1305_blocks_avxN {
 ___
 $code.=<<___;
 	vzeroupper
-	ret
+	RET
 .cfi_endproc
 ___
 if($avx > 2 && $avx512) {
@@ -2792,7 +2792,7 @@ sub poly1305_blocks_avxN {
 .cfi_def_cfa_register	%rsp
 ___
 $code.=<<___;
-	ret
+	RET
 .cfi_endproc
 ___
 
@@ -2893,7 +2893,7 @@ sub poly1305_blocks_avxN {
 ___
 $code.=<<___;
 	mov	\$1,%eax
-	ret
+	RET
 .size	poly1305_init_base2_44,.-poly1305_init_base2_44
 ___
 {
@@ -3010,7 +3010,7 @@ sub poly1305_blocks_avxN {
 	jnz		.Lblocks_vpmadd52_4x
 
 .Lno_data_vpmadd52:
-	ret
+	RET
 .size	poly1305_blocks_vpmadd52,.-poly1305_blocks_vpmadd52
 ___
 }
@@ -3451,7 +3451,7 @@ sub poly1305_blocks_avxN {
 	vzeroall
 
 .Lno_data_vpmadd52_4x:
-	ret
+	RET
 .size	poly1305_blocks_vpmadd52_4x,.-poly1305_blocks_vpmadd52_4x
 ___
 }
@@ -3824,7 +3824,7 @@ sub poly1305_blocks_avxN {
 	vzeroall
 
 .Lno_data_vpmadd52_8x:
-	ret
+	RET
 .size	poly1305_blocks_vpmadd52_8x,.-poly1305_blocks_vpmadd52_8x
 ___
 }
@@ -3861,7 +3861,7 @@ sub poly1305_blocks_avxN {
 	mov	%rax,0($mac)	# write result
 	mov	%rcx,8($mac)
 
-	ret
+	RET
 .size	poly1305_emit_base2_44,.-poly1305_emit_base2_44
 ___
 }	}	}
@@ -3916,7 +3916,7 @@ sub poly1305_blocks_avxN {
 
 .Ldone_enc:
 	mov	$otp,%rax
-	ret
+	RET
 .size	xor128_encrypt_n_pad,.-xor128_encrypt_n_pad
 
 .globl	xor128_decrypt_n_pad
@@ -3967,7 +3967,7 @@ sub poly1305_blocks_avxN {
 
 .Ldone_dec:
 	mov	$otp,%rax
-	ret
+	RET
 .size	xor128_decrypt_n_pad,.-xor128_decrypt_n_pad
 ___
 }
@@ -4109,7 +4109,7 @@ sub poly1305_blocks_avxN {
 	pop	%rbx
 	pop	%rdi
 	pop	%rsi
-	ret
+	RET
 .size	avx_handler,.-avx_handler
 
 .section	.pdata
diff --git a/arch/x86/crypto/sm3-avx-asm_64.S b/arch/x86/crypto/sm3-avx-asm_64.S
index 71e6aae23e17c..b12b9efb5ec51 100644
--- a/arch/x86/crypto/sm3-avx-asm_64.S
+++ b/arch/x86/crypto/sm3-avx-asm_64.S
@@ -513,5 +513,5 @@ SYM_FUNC_START(sm3_transform_avx)
 
 	movq %rbp, %rsp;
 	popq %rbp;
-	ret;
+	RET;
 SYM_FUNC_END(sm3_transform_avx)
diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c
index be1bf39a317de..90a920e7f6642 100644
--- a/drivers/crypto/stm32/stm32-crc32.c
+++ b/drivers/crypto/stm32/stm32-crc32.c
@@ -384,8 +384,10 @@ static int stm32_crc_remove(struct platform_device *pdev)
 	struct stm32_crc *crc = platform_get_drvdata(pdev);
 	int ret = pm_runtime_get_sync(crc->dev);
 
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(crc->dev);
 		return ret;
+	}
 
 	spin_lock(&crc_list.lock);
 	list_del(&crc->list);