diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 16627fec80b2..c36b850fdc81 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -256,6 +256,37 @@ aad_shift_arr:
 	pxor      \TMP1, \GH            # result is in TMP1
 .endm
 
+# Reads DLEN bytes starting at DPTR and stores in XMMDst
+# where 0 < DLEN < 16
+# Clobbers %rax, DLEN and XMM1
+.macro READ_PARTIAL_BLOCK DPTR DLEN XMM1 XMMDst
+        cmp $8, \DLEN
+        jl _read_lt8_\@
+        mov (\DPTR), %rax
+        MOVQ_R64_XMM %rax, \XMMDst
+        sub $8, \DLEN
+        jz _done_read_partial_block_\@
+	xor %eax, %eax
+_read_next_byte_\@:
+        shl $8, %rax
+        mov 7(\DPTR, \DLEN, 1), %al
+        dec \DLEN
+        jnz _read_next_byte_\@
+        MOVQ_R64_XMM %rax, \XMM1
+	pslldq $8, \XMM1
+        por \XMM1, \XMMDst
+	jmp _done_read_partial_block_\@
+_read_lt8_\@:
+	xor %eax, %eax
+_read_next_byte_lt8_\@:
+        shl $8, %rax
+        mov -1(\DPTR, \DLEN, 1), %al
+        dec \DLEN
+        jnz _read_next_byte_lt8_\@
+        MOVQ_R64_XMM %rax, \XMMDst
+_done_read_partial_block_\@:
+.endm
+
 /*
 * if a = number of total plaintext bytes
 * b = floor(a/16)
@@ -1385,14 +1416,6 @@ _esb_loop_\@:
 *
 *                        AAD Format with 64-bit Extended Sequence Number
 *
-* aadLen:
-*       from the definition of the spec, aadLen can only be 8 or 12 bytes.
-*       The code supports 16 too but for other sizes, the code will fail.
-*
-* TLen:
-*       from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
-*       For other sizes, the code will fail.
-*
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 *
 *****************************************************************************/
@@ -1486,19 +1509,16 @@ _zero_cipher_left_decrypt:
 	PSHUFB_XMM %xmm10, %xmm0
 
 	ENCRYPT_SINGLE_BLOCK  %xmm0, %xmm1    # E(K, Yn)
-	sub $16, %r11
-	add %r13, %r11
-	movdqu (%arg3,%r11,1), %xmm1   # receive the last <16 byte block
-	lea SHIFT_MASK+16(%rip), %r12
-	sub %r13, %r12
-# adjust the shuffle mask pointer to be able to shift 16-%r13 bytes
-# (%r13 is the number of bytes in plaintext mod 16)
-	movdqu (%r12), %xmm2           # get the appropriate shuffle mask
-	PSHUFB_XMM %xmm2, %xmm1            # right shift 16-%r13 butes
 
+	lea (%arg3,%r11,1), %r10
+	mov %r13, %r12
+	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
+
+	lea ALL_F+16(%rip), %r12
+	sub %r13, %r12
 	movdqa  %xmm1, %xmm2
 	pxor %xmm1, %xmm0            # Ciphertext XOR E(K, Yn)
-	movdqu ALL_F-SHIFT_MASK(%r12), %xmm1
+	movdqu (%r12), %xmm1
 	# get the appropriate mask to mask out top 16-%r13 bytes of %xmm0
 	pand %xmm1, %xmm0            # mask out top 16-%r13 bytes of %xmm0
 	pand    %xmm1, %xmm2
@@ -1507,9 +1527,6 @@ _zero_cipher_left_decrypt:
 
 	pxor %xmm2, %xmm8
 	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
-	          # GHASH computation for the last <16 byte block
-	sub %r13, %r11
-	add $16, %r11
 
         # output %r13 bytes
 	MOVQ_R64_XMM	%xmm0, %rax
@@ -1663,14 +1680,6 @@ ENDPROC(aesni_gcm_dec)
 *
 *                         AAD Format with 64-bit Extended Sequence Number
 *
-* aadLen:
-*       from the definition of the spec, aadLen can only be 8 or 12 bytes.
-*       The code supports 16 too but for other sizes, the code will fail.
-*
-* TLen:
-*       from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
-*       For other sizes, the code will fail.
-*
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 ***************************************************************************/
 ENTRY(aesni_gcm_enc)
@@ -1763,19 +1772,16 @@ _zero_cipher_left_encrypt:
         movdqa SHUF_MASK(%rip), %xmm10
 	PSHUFB_XMM %xmm10, %xmm0
 
-
 	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm1        # Encrypt(K, Yn)
-	sub $16, %r11
-	add %r13, %r11
-	movdqu (%arg3,%r11,1), %xmm1     # receive the last <16 byte blocks
-	lea SHIFT_MASK+16(%rip), %r12
+
+	lea (%arg3,%r11,1), %r10
+	mov %r13, %r12
+	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
+
+	lea ALL_F+16(%rip), %r12
 	sub %r13, %r12
-	# adjust the shuffle mask pointer to be able to shift 16-r13 bytes
-	# (%r13 is the number of bytes in plaintext mod 16)
-	movdqu	(%r12), %xmm2           # get the appropriate shuffle mask
-	PSHUFB_XMM	%xmm2, %xmm1            # shift right 16-r13 byte
 	pxor	%xmm1, %xmm0            # Plaintext XOR Encrypt(K, Yn)
-	movdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
+	movdqu	(%r12), %xmm1
 	# get the appropriate mask to mask out top 16-r13 bytes of xmm0
 	pand	%xmm1, %xmm0            # mask out top 16-r13 bytes of xmm0
         movdqa SHUF_MASK(%rip), %xmm10
@@ -1784,9 +1790,6 @@ _zero_cipher_left_encrypt:
 	pxor	%xmm0, %xmm8
 	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
 	# GHASH computation for the last <16 byte block
-	sub	%r13, %r11
-	add	$16, %r11
-
 	movdqa SHUF_MASK(%rip), %xmm10
 	PSHUFB_XMM %xmm10, %xmm0