crypto: aesni_intel - fix accessing of unaligned memory

The new XTS code for aesni_intel uses input buffers directly as memory operands
for pxor instructions, which causes crash if those buffers are not aligned to
16 bytes.

Patch changes XTS code to handle unaligned memory correctly, by loading memory
with movdqu instead.
Reported-by: Dave Jones <davej@redhat.com>
Tested-by: Dave Jones <davej@redhat.com>
Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/aesni-intel_asm.S

@@ -2681,56 +2681,68 @@ ENTRY(aesni_xts_crypt8)
 	addq %rcx, KEYP
 
 	movdqa IV, STATE1
-	pxor 0x00(INP), STATE1
+	movdqu 0x00(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x10(INP), STATE2
+	movdqu 0x10(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x20(INP), STATE3
+	movdqu 0x20(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x30(INP), STATE4
+	movdqu 0x30(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
 	call *%r11
 
-	pxor 0x00(OUTP), STATE1
+	movdqu 0x00(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE1
-	pxor 0x40(INP), STATE1
+	movdqu 0x40(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x40(OUTP)
 
-	pxor 0x10(OUTP), STATE2
+	movdqu 0x10(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x50(INP), STATE2
+	movdqu 0x50(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x50(OUTP)
 
-	pxor 0x20(OUTP), STATE3
+	movdqu 0x20(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x60(INP), STATE3
+	movdqu 0x60(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x60(OUTP)
 
-	pxor 0x30(OUTP), STATE4
+	movdqu 0x30(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x30(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x70(INP), STATE4
+	movdqu 0x70(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x70(OUTP)
 
 	_aesni_gf128mul_x_ble()
@@ -2738,16 +2750,20 @@ ENTRY(aesni_xts_crypt8)
 
 	call *%r11
 
-	pxor 0x40(OUTP), STATE1
+	movdqu 0x40(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x40(OUTP)
 
-	pxor 0x50(OUTP), STATE2
+	movdqu 0x50(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x50(OUTP)
 
-	pxor 0x60(OUTP), STATE3
+	movdqu 0x60(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x60(OUTP)
 
-	pxor 0x70(OUTP), STATE4
+	movdqu 0x70(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x70(OUTP)
 
 	ret