Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - Add the ability to abort a skcipher walk.

  Algorithms:
   - Fix XTS to actually do the stealing.
   - Add library helpers for AES and DES for single-block users.
   - Add library helpers for SHA256.
   - Add new DES key verification helper.
   - Add surrounding bits for ESSIV generator.
   - Add accelerations for aegis128.
   - Add test vectors for lzo-rle.

  Drivers:
   - Add i.MX8MQ support to caam.
   - Add gcm/ccm/cfb/ofb aes support in inside-secure.
   - Add ofb/cfb aes support in media-tek.
   - Add HiSilicon ZIP accelerator support.

  Others:
   - Fix potential race condition in padata.
   - Use unbound workqueues in padata"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (311 commits)
  crypto: caam - Cast to long first before pointer conversion
  crypto: ccree - enable CTS support in AES-XTS
  crypto: inside-secure - Probe transform record cache RAM sizes
  crypto: inside-secure - Base RD fetchcount on actual RD FIFO size
  crypto: inside-secure - Base CD fetchcount on actual CD FIFO size
  crypto: inside-secure - Enable extended algorithms on newer HW
  crypto: inside-secure: Corrected configuration of EIP96_TOKEN_CTRL
  crypto: inside-secure - Add EIP97/EIP197 and endianness detection
  padata: remove cpu_index from the parallel_queue
  padata: unbind parallel jobs from specific CPUs
  padata: use separate workqueues for parallel and serial work
  padata, pcrypt: take CPU hotplug lock internally in padata_alloc_possible
  crypto: pcrypt - remove padata cpumask notifier
  padata: make padata_do_parallel find alternate callback CPU
  workqueue: require CPU hotplug read exclusion for apply_workqueue_attrs
  workqueue: unconfine alloc/apply/free_workqueue_attrs()
  padata: allocate workqueue internally
  arm64: dts: imx8mq: Add CAAM node
  random: Use wait_event_freezable() in add_hwgenerator_randomness()
  crypto: ux500 - Fix COMPILE_TEST warnings
  ...

11 files changed, 982 insertions, 395 deletions

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index a95322b59799..b24df84a1d7a 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -82,8 +82,8 @@ config CRYPTO_AES_ARM_BS
 	tristate "Bit sliced AES using NEON instructions"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
-	select CRYPTO_AES
 	help
 	  Use a faster and more secure NEON based implementation of AES in CBC,
 	  CTR and XTS modes
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
index caac519d6249..b978cdf133af 100644
--- a/arch/arm/crypto/aes-ce-core.S
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -44,63 +44,73 @@
 	veor		q0, q0, \key3
 	.endm
 
-	.macro		enc_dround_3x, key1, key2
+	.macro		enc_dround_4x, key1, key2
 	enc_round	q0, \key1
 	enc_round	q1, \key1
 	enc_round	q2, \key1
+	enc_round	q3, \key1
 	enc_round	q0, \key2
 	enc_round	q1, \key2
 	enc_round	q2, \key2
+	enc_round	q3, \key2
 	.endm
 
-	.macro		dec_dround_3x, key1, key2
+	.macro		dec_dround_4x, key1, key2
 	dec_round	q0, \key1
 	dec_round	q1, \key1
 	dec_round	q2, \key1
+	dec_round	q3, \key1
 	dec_round	q0, \key2
 	dec_round	q1, \key2
 	dec_round	q2, \key2
+	dec_round	q3, \key2
 	.endm
 
-	.macro		enc_fround_3x, key1, key2, key3
+	.macro		enc_fround_4x, key1, key2, key3
 	enc_round	q0, \key1
 	enc_round	q1, \key1
 	enc_round	q2, \key1
+	enc_round	q3, \key1
 	aese.8		q0, \key2
 	aese.8		q1, \key2
 	aese.8		q2, \key2
+	aese.8		q3, \key2
 	veor		q0, q0, \key3
 	veor		q1, q1, \key3
 	veor		q2, q2, \key3
+	veor		q3, q3, \key3
 	.endm
 
-	.macro		dec_fround_3x, key1, key2, key3
+	.macro		dec_fround_4x, key1, key2, key3
 	dec_round	q0, \key1
 	dec_round	q1, \key1
 	dec_round	q2, \key1
+	dec_round	q3, \key1
 	aesd.8		q0, \key2
 	aesd.8		q1, \key2
 	aesd.8		q2, \key2
+	aesd.8		q3, \key2
 	veor		q0, q0, \key3
 	veor		q1, q1, \key3
 	veor		q2, q2, \key3
+	veor		q3, q3, \key3
 	.endm
 
 	.macro		do_block, dround, fround
 	cmp		r3, #12			@ which key size?
-	vld1.8		{q10-q11}, [ip]!
+	vld1.32		{q10-q11}, [ip]!
 	\dround		q8, q9
-	vld1.8		{q12-q13}, [ip]!
+	vld1.32		{q12-q13}, [ip]!
 	\dround		q10, q11
-	vld1.8		{q10-q11}, [ip]!
+	vld1.32		{q10-q11}, [ip]!
 	\dround		q12, q13
-	vld1.8		{q12-q13}, [ip]!
+	vld1.32		{q12-q13}, [ip]!
 	\dround		q10, q11
 	blo		0f			@ AES-128: 10 rounds
-	vld1.8		{q10-q11}, [ip]!
+	vld1.32		{q10-q11}, [ip]!
 	\dround		q12, q13
 	beq		1f			@ AES-192: 12 rounds
-	vld1.8		{q12-q13}, [ip]
+	vld1.32		{q12-q13}, [ip]
 	\dround		q10, q11
 0:	\fround		q12, q13, q14
 	bx		lr
@@ -114,8 +124,9 @@
 	 * transforms. These should preserve all registers except q0 - q2 and ip
 	 * Arguments:
 	 *   q0        : first in/output block
-	 *   q1        : second in/output block (_3x version only)
-	 *   q2        : third in/output block (_3x version only)
+	 *   q1        : second in/output block (_4x version only)
+	 *   q2        : third in/output block (_4x version only)
+	 *   q3        : fourth in/output block (_4x version only)
 	 *   q8        : first round key
 	 *   q9        : secound round key
 	 *   q14       : final round key
@@ -136,44 +147,44 @@ aes_decrypt:
 ENDPROC(aes_decrypt)
 
 	.align		6
-aes_encrypt_3x:
+aes_encrypt_4x:
 	add		ip, r2, #32		@ 3rd round key
-	do_block	enc_dround_3x, enc_fround_3x
-ENDPROC(aes_encrypt_3x)
+	do_block	enc_dround_4x, enc_fround_4x
+ENDPROC(aes_encrypt_4x)
 
 	.align		6
-aes_decrypt_3x:
+aes_decrypt_4x:
 	add		ip, r2, #32		@ 3rd round key
-	do_block	dec_dround_3x, dec_fround_3x
-ENDPROC(aes_decrypt_3x)
+	do_block	dec_dround_4x, dec_fround_4x
+ENDPROC(aes_decrypt_4x)
 
 	.macro		prepare_key, rk, rounds
 	add		ip, \rk, \rounds, lsl #4
-	vld1.8		{q8-q9}, [\rk]		@ load first 2 round keys
-	vld1.8		{q14}, [ip]		@ load last round key
+	vld1.32		{q8-q9}, [\rk]		@ load first 2 round keys
+	vld1.32		{q14}, [ip]		@ load last round key
 	.endm
 
 	/*
-	 * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 * aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
 	 *		   int blocks)
-	 * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 * aes_ecb_decrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
 	 *		   int blocks)
 	 */
 ENTRY(ce_aes_ecb_encrypt)
 	push		{r4, lr}
 	ldr		r4, [sp, #8]
 	prepare_key	r2, r3
-.Lecbencloop3x:
-	subs		r4, r4, #3
+.Lecbencloop4x:
+	subs		r4, r4, #4
 	bmi		.Lecbenc1x
 	vld1.8		{q0-q1}, [r1]!
-	vld1.8		{q2}, [r1]!
-	bl		aes_encrypt_3x
+	vld1.8		{q2-q3}, [r1]!
+	bl		aes_encrypt_4x
 	vst1.8		{q0-q1}, [r0]!
-	vst1.8		{q2}, [r0]!
-	b		.Lecbencloop3x
+	vst1.8		{q2-q3}, [r0]!
+	b		.Lecbencloop4x
 .Lecbenc1x:
-	adds		r4, r4, #3
+	adds		r4, r4, #4
 	beq		.Lecbencout
 .Lecbencloop:
 	vld1.8		{q0}, [r1]!
@@ -189,17 +200,17 @@ ENTRY(ce_aes_ecb_decrypt)
 	push		{r4, lr}
 	ldr		r4, [sp, #8]
 	prepare_key	r2, r3
-.Lecbdecloop3x:
-	subs		r4, r4, #3
+.Lecbdecloop4x:
+	subs		r4, r4, #4
 	bmi		.Lecbdec1x
 	vld1.8		{q0-q1}, [r1]!
-	vld1.8		{q2}, [r1]!
-	bl		aes_decrypt_3x
+	vld1.8		{q2-q3}, [r1]!
+	bl		aes_decrypt_4x
 	vst1.8		{q0-q1}, [r0]!
-	vst1.8		{q2}, [r0]!
-	b		.Lecbdecloop3x
+	vst1.8		{q2-q3}, [r0]!
+	b		.Lecbdecloop4x
 .Lecbdec1x:
-	adds		r4, r4, #3
+	adds		r4, r4, #4
 	beq		.Lecbdecout
 .Lecbdecloop:
 	vld1.8		{q0}, [r1]!
@@ -212,9 +223,9 @@ ENTRY(ce_aes_ecb_decrypt)
 ENDPROC(ce_aes_ecb_decrypt)
 
 	/*
-	 * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 * aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
 	 *		   int blocks, u8 iv[])
-	 * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 * aes_cbc_decrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
 	 *		   int blocks, u8 iv[])
 	 */
 ENTRY(ce_aes_cbc_encrypt)
@@ -236,88 +247,181 @@ ENDPROC(ce_aes_cbc_encrypt)
 ENTRY(ce_aes_cbc_decrypt)
 	push		{r4-r6, lr}
 	ldrd		r4, r5, [sp, #16]
-	vld1.8		{q6}, [r5]		@ keep iv in q6
+	vld1.8		{q15}, [r5]		@ keep iv in q15
 	prepare_key	r2, r3
-.Lcbcdecloop3x:
-	subs		r4, r4, #3
+.Lcbcdecloop4x:
+	subs		r4, r4, #4
 	bmi		.Lcbcdec1x
 	vld1.8		{q0-q1}, [r1]!
-	vld1.8		{q2}, [r1]!
-	vmov		q3, q0
-	vmov		q4, q1
-	vmov		q5, q2
-	bl		aes_decrypt_3x
-	veor		q0, q0, q6
-	veor		q1, q1, q3
-	veor		q2, q2, q4
-	vmov		q6, q5
+	vld1.8		{q2-q3}, [r1]!
+	vmov		q4, q0
+	vmov		q5, q1
+	vmov		q6, q2
+	vmov		q7, q3
+	bl		aes_decrypt_4x
+	veor		q0, q0, q15
+	veor		q1, q1, q4
+	veor		q2, q2, q5
+	veor		q3, q3, q6
+	vmov		q15, q7
 	vst1.8		{q0-q1}, [r0]!
-	vst1.8		{q2}, [r0]!
-	b		.Lcbcdecloop3x
+	vst1.8		{q2-q3}, [r0]!
+	b		.Lcbcdecloop4x
 .Lcbcdec1x:
-	adds		r4, r4, #3
+	adds		r4, r4, #4
 	beq		.Lcbcdecout
-	vmov		q15, q14		@ preserve last round key
+	vmov		q6, q14			@ preserve last round key
 .Lcbcdecloop:
 	vld1.8		{q0}, [r1]!		@ get next ct block
 	veor		q14, q15, q6		@ combine prev ct with last key
-	vmov		q6, q0
+	vmov		q15, q0
 	bl		aes_decrypt
 	vst1.8		{q0}, [r0]!
 	subs		r4, r4, #1
 	bne		.Lcbcdecloop
 .Lcbcdecout:
-	vst1.8		{q6}, [r5]		@ keep iv in q6
+	vst1.8		{q15}, [r5]		@ keep iv in q15
 	pop		{r4-r6, pc}
 ENDPROC(ce_aes_cbc_decrypt)
 
+
 	/*
-	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 * ce_aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+	 *			  int rounds, int bytes, u8 const iv[])
+	 * ce_aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+	 *			  int rounds, int bytes, u8 const iv[])
+	 */
+
+ENTRY(ce_aes_cbc_cts_encrypt)
+	push		{r4-r6, lr}
+	ldrd		r4, r5, [sp, #16]
+
+	movw		ip, :lower16:.Lcts_permute_table
+	movt		ip, :upper16:.Lcts_permute_table
+	sub		r4, r4, #16
+	add		lr, ip, #32
+	add		ip, ip, r4
+	sub		lr, lr, r4
+	vld1.8		{q5}, [ip]
+	vld1.8		{q6}, [lr]
+
+	add		ip, r1, r4
+	vld1.8		{q0}, [r1]			@ overlapping loads
+	vld1.8		{q3}, [ip]
+
+	vld1.8		{q1}, [r5]			@ get iv
+	prepare_key	r2, r3
+
+	veor		q0, q0, q1			@ xor with iv
+	bl		aes_encrypt
+
+	vtbl.8		d4, {d0-d1}, d10
+	vtbl.8		d5, {d0-d1}, d11
+	vtbl.8		d2, {d6-d7}, d12
+	vtbl.8		d3, {d6-d7}, d13
+
+	veor		q0, q0, q1
+	bl		aes_encrypt
+
+	add		r4, r0, r4
+	vst1.8		{q2}, [r4]			@ overlapping stores
+	vst1.8		{q0}, [r0]
+
+	pop		{r4-r6, pc}
+ENDPROC(ce_aes_cbc_cts_encrypt)
+
+ENTRY(ce_aes_cbc_cts_decrypt)
+	push		{r4-r6, lr}
+	ldrd		r4, r5, [sp, #16]
+
+	movw		ip, :lower16:.Lcts_permute_table
+	movt		ip, :upper16:.Lcts_permute_table
+	sub		r4, r4, #16
+	add		lr, ip, #32
+	add		ip, ip, r4
+	sub		lr, lr, r4
+	vld1.8		{q5}, [ip]
+	vld1.8		{q6}, [lr]
+
+	add		ip, r1, r4
+	vld1.8		{q0}, [r1]			@ overlapping loads
+	vld1.8		{q1}, [ip]
+
+	vld1.8		{q3}, [r5]			@ get iv
+	prepare_key	r2, r3
+
+	bl		aes_decrypt
+
+	vtbl.8		d4, {d0-d1}, d10
+	vtbl.8		d5, {d0-d1}, d11
+	vtbx.8		d0, {d2-d3}, d12
+	vtbx.8		d1, {d2-d3}, d13
+
+	veor		q1, q1, q2
+	bl		aes_decrypt
+	veor		q0, q0, q3			@ xor with iv
+
+	add		r4, r0, r4
+	vst1.8		{q1}, [r4]			@ overlapping stores
+	vst1.8		{q0}, [r0]
+
+	pop		{r4-r6, pc}
+ENDPROC(ce_aes_cbc_cts_decrypt)
+
+
+	/*
+	 * aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
 	 *		   int blocks, u8 ctr[])
 	 */
 ENTRY(ce_aes_ctr_encrypt)
 	push		{r4-r6, lr}
 	ldrd		r4, r5, [sp, #16]
-	vld1.8		{q6}, [r5]		@ load ctr
+	vld1.8		{q7}, [r5]		@ load ctr
 	prepare_key	r2, r3
-	vmov		r6, s27			@ keep swabbed ctr in r6
+	vmov		r6, s31			@ keep swabbed ctr in r6
 	rev		r6, r6
 	cmn		r6, r4			@ 32 bit overflow?
 	bcs		.Lctrloop
-.Lctrloop3x:
-	subs		r4, r4, #3
+.Lctrloop4x:
+	subs		r4, r4, #4
 	bmi		.Lctr1x
 	add		r6, r6, #1
-	vmov		q0, q6
-	vmov		q1, q6
+	vmov		q0, q7
+	vmov		q1, q7
 	rev		ip, r6
 	add		r6, r6, #1
-	vmov		q2, q6
+	vmov		q2, q7
 	vmov		s7, ip
 	rev		ip, r6
 	add		r6, r6, #1
+	vmov		q3, q7
 	vmov		s11, ip
-	vld1.8		{q3-q4}, [r1]!
-	vld1.8		{q5}, [r1]!
-	bl		aes_encrypt_3x
-	veor		q0, q0, q3
-	veor		q1, q1, q4
-	veor		q2, q2, q5
+	rev		ip, r6
+	add		r6, r6, #1
+	vmov		s15, ip
+	vld1.8		{q4-q5}, [r1]!
+	vld1.8		{q6}, [r1]!
+	vld1.8		{q15}, [r1]!
+	bl		aes_encrypt_4x
+	veor		q0, q0, q4
+	veor		q1, q1, q5
+	veor		q2, q2, q6
+	veor		q3, q3, q15
 	rev		ip, r6
 	vst1.8		{q0-q1}, [r0]!
-	vst1.8		{q2}, [r0]!
-	vmov		s27, ip
-	b		.Lctrloop3x
+	vst1.8		{q2-q3}, [r0]!
+	vmov		s31, ip
+	b		.Lctrloop4x
 .Lctr1x:
-	adds		r4, r4, #3
+	adds		r4, r4, #4
 	beq		.Lctrout
 .Lctrloop:
-	vmov		q0, q6
+	vmov		q0, q7
 	bl		aes_encrypt
 
 	adds		r6, r6, #1		@ increment BE ctr
 	rev		ip, r6
-	vmov		s27, ip
+	vmov		s31, ip
 	bcs		.Lctrcarry
 
 .Lctrcarrydone:
@@ -329,7 +433,7 @@ ENTRY(ce_aes_ctr_encrypt)
 	bne		.Lctrloop
 
 .Lctrout:
-	vst1.8		{q6}, [r5]		@ return next CTR value
+	vst1.8		{q7}, [r5]		@ return next CTR value
 	pop		{r4-r6, pc}
 
 .Lctrtailblock:
@@ -337,7 +441,7 @@ ENTRY(ce_aes_ctr_encrypt)
 	b		.Lctrout
 
 .Lctrcarry:
-	.irp		sreg, s26, s25, s24
+	.irp		sreg, s30, s29, s28
 	vmov		ip, \sreg		@ load next word of ctr
 	rev		ip, ip			@ ... to handle the carry
 	adds		ip, ip, #1
@@ -349,10 +453,10 @@ ENTRY(ce_aes_ctr_encrypt)
 ENDPROC(ce_aes_ctr_encrypt)
 
 	/*
-	 * aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
-	 *		   int blocks, u8 iv[], u8 const rk2[], int first)
-	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
-	 *		   int blocks, u8 iv[], u8 const rk2[], int first)
+	 * aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds,
+	 *		   int bytes, u8 iv[], u32 const rk2[], int first)
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds,
+	 *		   int bytes, u8 iv[], u32 const rk2[], int first)
 	 */
 
 	.macro		next_tweak, out, in, const, tmp
@@ -363,13 +467,10 @@ ENDPROC(ce_aes_ctr_encrypt)
 	veor		\out, \out, \tmp
 	.endm
 
-	.align		3
-.Lxts_mul_x:
-	.quad		1, 0x87
-
 ce_aes_xts_init:
-	vldr		d14, .Lxts_mul_x
-	vldr		d15, .Lxts_mul_x + 8
+	vmov.i32	d30, #0x87		@ compose tweak mask vector
+	vmovl.u32	q15, d30
+	vshr.u64	d30, d31, #7
 
 	ldrd		r4, r5, [sp, #16]	@ load args
 	ldr		r6, [sp, #28]
@@ -390,49 +491,86 @@ ENTRY(ce_aes_xts_encrypt)
 
 	bl		ce_aes_xts_init		@ run shared prologue
 	prepare_key	r2, r3
-	vmov		q3, q0
+	vmov		q4, q0
 
 	teq		r6, #0			@ start of a block?
-	bne		.Lxtsenc3x
+	bne		.Lxtsenc4x
 
-.Lxtsencloop3x:
-	next_tweak	q3, q3, q7, q6
-.Lxtsenc3x:
-	subs		r4, r4, #3
+.Lxtsencloop4x:
+	next_tweak	q4, q4, q15, q10
+.Lxtsenc4x:
+	subs		r4, r4, #64
 	bmi		.Lxtsenc1x
-	vld1.8		{q0-q1}, [r1]!		@ get 3 pt blocks
-	vld1.8		{q2}, [r1]!
-	next_tweak	q4, q3, q7, q6
-	veor		q0, q0, q3
-	next_tweak	q5, q4, q7, q6
-	veor		q1, q1, q4
-	veor		q2, q2, q5
-	bl		aes_encrypt_3x
-	veor		q0, q0, q3
-	veor		q1, q1, q4
-	veor		q2, q2, q5
-	vst1.8		{q0-q1}, [r0]!		@ write 3 ct blocks
-	vst1.8		{q2}, [r0]!
-	vmov		q3, q5
+	vld1.8		{q0-q1}, [r1]!		@ get 4 pt blocks
+	vld1.8		{q2-q3}, [r1]!
+	next_tweak	q5, q4, q15, q10
+	veor		q0, q0, q4
+	next_tweak	q6, q5, q15, q10
+	veor		q1, q1, q5
+	next_tweak	q7, q6, q15, q10
+	veor		q2, q2, q6
+	veor		q3, q3, q7
+	bl		aes_encrypt_4x
+	veor		q0, q0, q4
+	veor		q1, q1, q5
+	veor		q2, q2, q6
+	veor		q3, q3, q7
+	vst1.8		{q0-q1}, [r0]!		@ write 4 ct blocks
+	vst1.8		{q2-q3}, [r0]!
+	vmov		q4, q7
 	teq		r4, #0
-	beq		.Lxtsencout
-	b		.Lxtsencloop3x
+	beq		.Lxtsencret
+	b		.Lxtsencloop4x
 .Lxtsenc1x:
-	adds		r4, r4, #3
+	adds		r4, r4, #64
 	beq		.Lxtsencout
+	subs		r4, r4, #16
+	bmi		.LxtsencctsNx
 .Lxtsencloop:
 	vld1.8		{q0}, [r1]!
-	veor		q0, q0, q3
+.Lxtsencctsout:
+	veor		q0, q0, q4
 	bl		aes_encrypt
-	veor		q0, q0, q3
-	vst1.8		{q0}, [r0]!
-	subs		r4, r4, #1
+	veor		q0, q0, q4
+	teq		r4, #0
 	beq		.Lxtsencout
-	next_tweak	q3, q3, q7, q6
+	subs		r4, r4, #16
+	next_tweak	q4, q4, q15, q6
+	bmi		.Lxtsenccts
+	vst1.8		{q0}, [r0]!
 	b		.Lxtsencloop
 .Lxtsencout:
-	vst1.8		{q3}, [r5]
+	vst1.8		{q0}, [r0]
+.Lxtsencret:
+	vst1.8		{q4}, [r5]
 	pop		{r4-r6, pc}
+
+.LxtsencctsNx:
+	vmov		q0, q3
+	sub		r0, r0, #16
+.Lxtsenccts:
+	movw		ip, :lower16:.Lcts_permute_table
+	movt		ip, :upper16:.Lcts_permute_table
+
+	add		r1, r1, r4		@ rewind input pointer
+	add		r4, r4, #16		@ # bytes in final block
+	add		lr, ip, #32
+	add		ip, ip, r4
+	sub		lr, lr, r4
+	add		r4, r0, r4		@ output address of final block
+
+	vld1.8		{q1}, [r1]		@ load final partial block
+	vld1.8		{q2}, [ip]
+	vld1.8		{q3}, [lr]
+
+	vtbl.8		d4, {d0-d1}, d4
+	vtbl.8		d5, {d0-d1}, d5
+	vtbx.8		d0, {d2-d3}, d6
+	vtbx.8		d1, {d2-d3}, d7
+
+	vst1.8		{q2}, [r4]		@ overlapping stores
+	mov		r4, #0
+	b		.Lxtsencctsout
 ENDPROC(ce_aes_xts_encrypt)
 
 
@@ -441,50 +579,90 @@ ENTRY(ce_aes_xts_decrypt)
 
 	bl		ce_aes_xts_init		@ run shared prologue
 	prepare_key	r2, r3
-	vmov		q3, q0
+	vmov		q4, q0
+
+	/* subtract 16 bytes if we are doing CTS */
+	tst		r4, #0xf
+	subne		r4, r4, #0x10
 
 	teq		r6, #0			@ start of a block?
-	bne		.Lxtsdec3x
+	bne		.Lxtsdec4x
 
-.Lxtsdecloop3x:
-	next_tweak	q3, q3, q7, q6
-.Lxtsdec3x:
-	subs		r4, r4, #3
+.Lxtsdecloop4x:
+	next_tweak	q4, q4, q15, q10
+.Lxtsdec4x:
+	subs		r4, r4, #64
 	bmi		.Lxtsdec1x
-	vld1.8		{q0-q1}, [r1]!		@ get 3 ct blocks
-	vld1.8		{q2}, [r1]!
-	next_tweak	q4, q3, q7, q6
-	veor		q0, q0, q3
-	next_tweak	q5, q4, q7, q6
-	veor		q1, q1, q4
-	veor		q2, q2, q5
-	bl		aes_decrypt_3x
-	veor		q0, q0, q3
-	veor		q1, q1, q4
-	veor		q2, q2, q5
-	vst1.8		{q0-q1}, [r0]!		@ write 3 pt blocks
-	vst1.8		{q2}, [r0]!
-	vmov		q3, q5
+	vld1.8		{q0-q1}, [r1]!		@ get 4 ct blocks
+	vld1.8		{q2-q3}, [r1]!
+	next_tweak	q5, q4, q15, q10
+	veor		q0, q0, q4
+	next_tweak	q6, q5, q15, q10
+	veor		q1, q1, q5
+	next_tweak	q7, q6, q15, q10
+	veor		q2, q2, q6
+	veor		q3, q3, q7
+	bl		aes_decrypt_4x
+	veor		q0, q0, q4
+	veor		q1, q1, q5
+	veor		q2, q2, q6
+	veor		q3, q3, q7
+	vst1.8		{q0-q1}, [r0]!		@ write 4 pt blocks
+	vst1.8		{q2-q3}, [r0]!
+	vmov		q4, q7
 	teq		r4, #0
 	beq		.Lxtsdecout
-	b		.Lxtsdecloop3x
+	b		.Lxtsdecloop4x
 .Lxtsdec1x:
-	adds		r4, r4, #3
+	adds		r4, r4, #64
 	beq		.Lxtsdecout
+	subs		r4, r4, #16
 .Lxtsdecloop:
 	vld1.8		{q0}, [r1]!
-	veor		q0, q0, q3
-	add		ip, r2, #32		@ 3rd round key
+	bmi		.Lxtsdeccts
+.Lxtsdecctsout:
+	veor		q0, q0, q4
 	bl		aes_decrypt
-	veor		q0, q0, q3
+	veor		q0, q0, q4
 	vst1.8		{q0}, [r0]!
-	subs		r4, r4, #1
+	teq		r4, #0
 	beq		.Lxtsdecout
-	next_tweak	q3, q3, q7, q6
+	subs		r4, r4, #16
+	next_tweak	q4, q4, q15, q6
 	b		.Lxtsdecloop
 .Lxtsdecout:
-	vst1.8		{q3}, [r5]
+	vst1.8		{q4}, [r5]
 	pop		{r4-r6, pc}
+
+.Lxtsdeccts:
+	movw		ip, :lower16:.Lcts_permute_table
+	movt		ip, :upper16:.Lcts_permute_table
+
+	add		r1, r1, r4		@ rewind input pointer
+	add		r4, r4, #16		@ # bytes in final block
+	add		lr, ip, #32
+	add		ip, ip, r4
+	sub		lr, lr, r4
+	add		r4, r0, r4		@ output address of final block
+
+	next_tweak	q5, q4, q15, q6
+
+	vld1.8		{q1}, [r1]		@ load final partial block
+	vld1.8		{q2}, [ip]
+	vld1.8		{q3}, [lr]
+
+	veor		q0, q0, q5
+	bl		aes_decrypt
+	veor		q0, q0, q5
+
+	vtbl.8		d4, {d0-d1}, d4
+	vtbl.8		d5, {d0-d1}, d5
+	vtbx.8		d0, {d2-d3}, d6
+	vtbx.8		d1, {d2-d3}, d7
+
+	vst1.8		{q2}, [r4]		@ overlapping stores
+	mov		r4, #0
+	b		.Lxtsdecctsout
 ENDPROC(ce_aes_xts_decrypt)
 
 	/*
@@ -505,8 +683,18 @@ ENDPROC(ce_aes_sub)
 	 *                                        operation on round key *src
 	 */
 ENTRY(ce_aes_invert)
-	vld1.8		{q0}, [r1]
+	vld1.32		{q0}, [r1]
 	aesimc.8	q0, q0
-	vst1.8		{q0}, [r0]
+	vst1.32		{q0}, [r0]
 	bx		lr
 ENDPROC(ce_aes_invert)
+
+	.section	".rodata", "a"
+	.align		6
+.Lcts_permute_table:
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
+	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index 620aacf0d128..cdb1a07e7ad0 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -7,9 +7,13 @@
 
 #include <asm/hwcap.h>
 #include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
 #include <crypto/aes.h>
+#include <crypto/ctr.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
 #include <linux/cpufeature.h>
 #include <linux/module.h>
 #include <crypto/xts.h>
@@ -22,25 +26,29 @@ MODULE_LICENSE("GPL v2");
 asmlinkage u32 ce_aes_sub(u32 input);
 asmlinkage void ce_aes_invert(void *dst, void *src);
 
-asmlinkage void ce_aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void ce_aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
 				   int rounds, int blocks);
-asmlinkage void ce_aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void ce_aes_ecb_decrypt(u8 out[], u8 const in[], u32 const rk[],
 				   int rounds, int blocks);
 
-asmlinkage void ce_aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void ce_aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
 				   int rounds, int blocks, u8 iv[]);
-asmlinkage void ce_aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void ce_aes_cbc_decrypt(u8 out[], u8 const in[], u32 const rk[],
 				   int rounds, int blocks, u8 iv[]);
+asmlinkage void ce_aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				   int rounds, int bytes, u8 const iv[]);
+asmlinkage void ce_aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+				   int rounds, int bytes, u8 const iv[]);
 
-asmlinkage void ce_aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void ce_aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
 				   int rounds, int blocks, u8 ctr[]);
 
-asmlinkage void ce_aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
-				   int rounds, int blocks, u8 iv[],
-				   u8 const rk2[], int first);
-asmlinkage void ce_aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
-				   int rounds, int blocks, u8 iv[],
-				   u8 const rk2[], int first);
+asmlinkage void ce_aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[],
+				   int rounds, int bytes, u8 iv[],
+				   u32 const rk2[], int first);
+asmlinkage void ce_aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[],
+				   int rounds, int bytes, u8 iv[],
+				   u32 const rk2[], int first);
 
 struct aes_block {
 	u8 b[AES_BLOCK_SIZE];
@@ -77,21 +85,17 @@ static int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 	    key_len != AES_KEYSIZE_256)
 		return -EINVAL;
 
-	memcpy(ctx->key_enc, in_key, key_len);
 	ctx->key_length = key_len;
+	for (i = 0; i < kwords; i++)
+		ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32));
 
 	kernel_neon_begin();
 	for (i = 0; i < sizeof(rcon); i++) {
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
-#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(ce_aes_sub(rki[kwords - 1]), 8);
 		rko[0] = rko[0] ^ rki[0] ^ rcon[i];
-#else
-		rko[0] = rol32(ce_aes_sub(rki[kwords - 1]), 8);
-		rko[0] = rko[0] ^ rki[0] ^ (rcon[i] << 24);
-#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
@@ -178,15 +182,15 @@ static int ecb_encrypt(struct skcipher_request *req)
 	unsigned int blocks;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		ce_aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   (u8 *)ctx->key_enc, num_rounds(ctx), blocks);
+				   ctx->key_enc, num_rounds(ctx), blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -198,58 +202,192 @@ static int ecb_decrypt(struct skcipher_request *req)
 	unsigned int blocks;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		ce_aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   (u8 *)ctx->key_dec, num_rounds(ctx), blocks);
+				   ctx->key_dec, num_rounds(ctx), blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
-static int cbc_encrypt(struct skcipher_request *req)
+static int cbc_encrypt_walk(struct skcipher_request *req,
+			    struct skcipher_walk *walk)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
 	unsigned int blocks;
+	int err = 0;
+
+	while ((blocks = (walk->nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
+		ce_aes_cbc_encrypt(walk->dst.virt.addr, walk->src.virt.addr,
+				   ctx->key_enc, num_rounds(ctx), blocks,
+				   walk->iv);
+		kernel_neon_end();
+		err = skcipher_walk_done(walk, walk->nbytes % AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int cbc_encrypt(struct skcipher_request *req)
+{
+	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+	return cbc_encrypt_walk(req, &walk);
+}
 
-	kernel_neon_begin();
-	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
-		ce_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   (u8 *)ctx->key_enc, num_rounds(ctx), blocks,
-				   walk.iv);
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+static int cbc_decrypt_walk(struct skcipher_request *req,
+			    struct skcipher_walk *walk)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	unsigned int blocks;
+	int err = 0;
+
+	while ((blocks = (walk->nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
+		ce_aes_cbc_decrypt(walk->dst.virt.addr, walk->src.virt.addr,
+				   ctx->key_dec, num_rounds(ctx), blocks,
+				   walk->iv);
+		kernel_neon_end();
+		err = skcipher_walk_done(walk, walk->nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+	return cbc_decrypt_walk(req, &walk);
+}
+
+static int cts_cbc_encrypt(struct skcipher_request *req)
+{
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
 	struct skcipher_walk walk;
-	unsigned int blocks;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
+	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = skcipher_walk_virt(&walk, &subreq, false) ?:
+		      cbc_encrypt_walk(&subreq, &walk);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
 
 	kernel_neon_begin();
-	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
-		ce_aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   (u8 *)ctx->key_dec, num_rounds(ctx), blocks,
-				   walk.iv);
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+	ce_aes_cbc_cts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			       ctx->key_enc, num_rounds(ctx), walk.nbytes,
+			       walk.iv);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static int cts_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+	int err;
+
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
 	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = skcipher_walk_virt(&walk, &subreq, false) ?:
+		      cbc_decrypt_walk(&subreq, &walk);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	ce_aes_cbc_cts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			       ctx->key_dec, num_rounds(ctx), walk.nbytes,
+			       walk.iv);
 	kernel_neon_end();
-	return err;
+
+	return skcipher_walk_done(&walk, 0);
 }
 
 static int ctr_encrypt(struct skcipher_request *req)
@@ -259,13 +397,14 @@ static int ctr_encrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	int err, blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		ce_aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   (u8 *)ctx->key_enc, num_rounds(ctx), blocks,
+				   ctx->key_enc, num_rounds(ctx), blocks,
 				   walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	if (walk.nbytes) {
@@ -279,36 +418,109 @@ static int ctr_encrypt(struct skcipher_request *req)
 		 */
 		blocks = -1;
 
-		ce_aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc,
-				   num_rounds(ctx), blocks, walk.iv);
+		kernel_neon_begin();
+		ce_aes_ctr_encrypt(tail, NULL, ctx->key_enc, num_rounds(ctx),
+				   blocks, walk.iv);
+		kernel_neon_end();
 		crypto_xor_cpy(tdst, tsrc, tail, nbytes);
 		err = skcipher_walk_done(&walk, 0);
 	}
-	kernel_neon_end();
-
 	return err;
 }
 
+static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+{
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	unsigned long flags;
+
+	/*
+	 * Temporarily disable interrupts to avoid races where
+	 * cachelines are evicted when the CPU is interrupted
+	 * to do something else.
+	 */
+	local_irq_save(flags);
+	aes_encrypt(ctx, dst, src);
+	local_irq_restore(flags);
+}
+
+static int ctr_encrypt_sync(struct skcipher_request *req)
+{
+	if (!crypto_simd_usable())
+		return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
+
+	return ctr_encrypt(req);
+}
+
 static int xts_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err, first, rounds = num_rounds(&ctx->key1);
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct scatterlist *src, *dst;
 	struct skcipher_walk walk;
-	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	err = skcipher_walk_virt(&walk, req, false);
+
+	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+		int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+					      AES_BLOCK_SIZE) - 2;
+
+		skcipher_walk_abort(&walk);
+
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   xts_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+		req = &subreq;
+		err = skcipher_walk_virt(&walk, req, false);
+	} else {
+		tail = 0;
+	}
+
+	for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+		int nbytes = walk.nbytes;
+
+		if (walk.nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
+
+		kernel_neon_begin();
 		ce_aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   (u8 *)ctx->key1.key_enc, rounds, blocks,
-				   walk.iv, (u8 *)ctx->key2.key_enc, first);
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+				   ctx->key1.key_enc, rounds, nbytes, walk.iv,
+				   ctx->key2.key_enc, first);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
+
+	if (err || likely(!tail))
+		return err;
+
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	ce_aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			   ctx->key1.key_enc, rounds, walk.nbytes, walk.iv,
+			   ctx->key2.key_enc, first);
 	kernel_neon_end();
 
-	return err;
+	return skcipher_walk_done(&walk, 0);
 }
 
 static int xts_decrypt(struct skcipher_request *req)
@@ -316,87 +528,165 @@ static int xts_decrypt(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err, first, rounds = num_rounds(&ctx->key1);
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct scatterlist *src, *dst;
 	struct skcipher_walk walk;
-	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+		int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+					      AES_BLOCK_SIZE) - 2;
+
+		skcipher_walk_abort(&walk);
+
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   xts_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+		req = &subreq;
+		err = skcipher_walk_virt(&walk, req, false);
+	} else {
+		tail = 0;
+	}
+
+	for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+		int nbytes = walk.nbytes;
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		if (walk.nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
+
+		kernel_neon_begin();
 		ce_aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   (u8 *)ctx->key1.key_dec, rounds, blocks,
-				   walk.iv, (u8 *)ctx->key2.key_enc, first);
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+				   ctx->key1.key_dec, rounds, nbytes, walk.iv,
+				   ctx->key2.key_enc, first);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
+
+	if (err || likely(!tail))
+		return err;
+
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	ce_aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			   ctx->key1.key_dec, rounds, walk.nbytes, walk.iv,
+			   ctx->key2.key_enc, first);
 	kernel_neon_end();
 
-	return err;
+	return skcipher_walk_done(&walk, 0);
 }
 
 static struct skcipher_alg aes_algs[] = { {
-	.base = {
-		.cra_name		= "__ecb(aes)",
-		.cra_driver_name	= "__ecb-aes-ce",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_INTERNAL,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-		.cra_module		= THIS_MODULE,
-	},
-	.min_keysize	= AES_MIN_KEY_SIZE,
-	.max_keysize	= AES_MAX_KEY_SIZE,
-	.setkey		= ce_aes_setkey,
-	.encrypt	= ecb_encrypt,
-	.decrypt	= ecb_decrypt,
+	.base.cra_name		= "__ecb(aes)",
+	.base.cra_driver_name	= "__ecb-aes-ce",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.setkey			= ce_aes_setkey,
+	.encrypt		= ecb_encrypt,
+	.decrypt		= ecb_decrypt,
 }, {
-	.base = {
-		.cra_name		= "__cbc(aes)",
-		.cra_driver_name	= "__cbc-aes-ce",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_INTERNAL,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-		.cra_module		= THIS_MODULE,
-	},
-	.min_keysize	= AES_MIN_KEY_SIZE,
-	.max_keysize	= AES_MAX_KEY_SIZE,
-	.ivsize		= AES_BLOCK_SIZE,
-	.setkey		= ce_aes_setkey,
-	.encrypt	= cbc_encrypt,
-	.decrypt	= cbc_decrypt,
+	.base.cra_name		= "__cbc(aes)",
+	.base.cra_driver_name	= "__cbc-aes-ce",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= ce_aes_setkey,
+	.encrypt		= cbc_encrypt,
+	.decrypt		= cbc_decrypt,
 }, {
-	.base = {
-		.cra_name		= "__ctr(aes)",
-		.cra_driver_name	= "__ctr-aes-ce",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_INTERNAL,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-		.cra_module		= THIS_MODULE,
-	},
-	.min_keysize	= AES_MIN_KEY_SIZE,
-	.max_keysize	= AES_MAX_KEY_SIZE,
-	.ivsize		= AES_BLOCK_SIZE,
-	.chunksize	= AES_BLOCK_SIZE,
-	.setkey		= ce_aes_setkey,
-	.encrypt	= ctr_encrypt,
-	.decrypt	= ctr_encrypt,
+	.base.cra_name		= "__cts(cbc(aes))",
+	.base.cra_driver_name	= "__cts-cbc-aes-ce",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.walksize		= 2 * AES_BLOCK_SIZE,
+	.setkey			= ce_aes_setkey,
+	.encrypt		= cts_cbc_encrypt,
+	.decrypt		= cts_cbc_decrypt,
 }, {
-	.base = {
-		.cra_name		= "__xts(aes)",
-		.cra_driver_name	= "__xts-aes-ce",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_INTERNAL,
-		.cra_blocksize		= AES_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct crypto_aes_xts_ctx),
-		.cra_module		= THIS_MODULE,
-	},
-	.min_keysize	= 2 * AES_MIN_KEY_SIZE,
-	.max_keysize	= 2 * AES_MAX_KEY_SIZE,
-	.ivsize		= AES_BLOCK_SIZE,
-	.setkey		= xts_set_key,
-	.encrypt	= xts_encrypt,
-	.decrypt	= xts_decrypt,
+	.base.cra_name		= "__ctr(aes)",
+	.base.cra_driver_name	= "__ctr-aes-ce",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.setkey			= ce_aes_setkey,
+	.encrypt		= ctr_encrypt,
+	.decrypt		= ctr_encrypt,
+}, {
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-ce-sync",
+	.base.cra_priority	= 300 - 1,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.setkey			= ce_aes_setkey,
+	.encrypt		= ctr_encrypt_sync,
+	.decrypt		= ctr_encrypt_sync,
+}, {
+	.base.cra_name		= "__xts(aes)",
+	.base.cra_driver_name	= "__xts-aes-ce",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct crypto_aes_xts_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
+	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.walksize		= 2 * AES_BLOCK_SIZE,
+	.setkey			= xts_set_key,
+	.encrypt		= xts_encrypt,
+	.decrypt		= xts_decrypt,
 } };
 
 static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
@@ -425,6 +715,9 @@ static int __init aes_init(void)
 		return err;
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
+			continue;
+
 		algname = aes_algs[i].base.cra_name + 2;
 		drvname = aes_algs[i].base.cra_driver_name + 2;
 		basename = aes_algs[i].base.cra_driver_name;
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
index 4460ed05d6ff..472e56d09eea 100644
--- a/arch/arm/crypto/aes-cipher-core.S
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -219,43 +219,5 @@ ENDPROC(__aes_arm_encrypt)
 
 	.align		5
 ENTRY(__aes_arm_decrypt)
-	do_crypt	iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
+	do_crypt	iround, crypto_it_tab, crypto_aes_inv_sbox, 0
 ENDPROC(__aes_arm_decrypt)
-
-	.section	".rodata", "a"
-	.align		L1_CACHE_SHIFT
-	.type		__aes_arm_inverse_sbox, %object
-__aes_arm_inverse_sbox:
-	.byte		0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
-	.byte		0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
-	.byte		0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
-	.byte		0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
-	.byte		0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
-	.byte		0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
-	.byte		0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
-	.byte		0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
-	.byte		0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
-	.byte		0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
-	.byte		0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
-	.byte		0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
-	.byte		0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
-	.byte		0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
-	.byte		0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
-	.byte		0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
-	.byte		0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
-	.byte		0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
-	.byte		0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
-	.byte		0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
-	.byte		0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
-	.byte		0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
-	.byte		0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
-	.byte		0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
-	.byte		0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
-	.byte		0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
-	.byte		0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
-	.byte		0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
-	.byte		0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
-	.byte		0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
-	.byte		0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
-	.byte		0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
-	.size		__aes_arm_inverse_sbox, . - __aes_arm_inverse_sbox
diff --git a/arch/arm/crypto/aes-cipher-glue.c b/arch/arm/crypto/aes-cipher-glue.c
index 128d0a1ac068..8cd00f56800e 100644
--- a/arch/arm/crypto/aes-cipher-glue.c
+++ b/arch/arm/crypto/aes-cipher-glue.c
@@ -11,12 +11,9 @@
 #include <linux/module.h>
 
 asmlinkage void __aes_arm_encrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
-EXPORT_SYMBOL(__aes_arm_encrypt);
-
 asmlinkage void __aes_arm_decrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
-EXPORT_SYMBOL(__aes_arm_decrypt);
 
-static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+static void aes_arm_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 	int rounds = 6 + ctx->key_length / 4;
@@ -24,7 +21,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 	__aes_arm_encrypt(ctx->key_enc, rounds, in, out);
 }
 
-static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+static void aes_arm_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 	int rounds = 6 + ctx->key_length / 4;
@@ -44,8 +41,8 @@ static struct crypto_alg aes_alg = {
 	.cra_cipher.cia_min_keysize	= AES_MIN_KEY_SIZE,
 	.cra_cipher.cia_max_keysize	= AES_MAX_KEY_SIZE,
 	.cra_cipher.cia_setkey		= crypto_aes_set_key,
-	.cra_cipher.cia_encrypt		= aes_encrypt,
-	.cra_cipher.cia_decrypt		= aes_decrypt,
+	.cra_cipher.cia_encrypt		= aes_arm_encrypt,
+	.cra_cipher.cia_decrypt		= aes_arm_decrypt,
 
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	.cra_alignmask			= 3,
diff --git a/arch/arm/crypto/aes-neonbs-core.S b/arch/arm/crypto/aes-neonbs-core.S
index d3eab76b6e1b..cfaed4e67535 100644
--- a/arch/arm/crypto/aes-neonbs-core.S
+++ b/arch/arm/crypto/aes-neonbs-core.S
@@ -887,19 +887,17 @@ ENDPROC(aesbs_ctr_encrypt)
 	veor		\out, \out, \tmp
 	.endm
 
-	.align		4
-.Lxts_mul_x:
-	.quad		1, 0x87
-
 	/*
 	 * aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		     int blocks, u8 iv[])
+	 *		     int blocks, u8 iv[], int reorder_last_tweak)
 	 * aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		     int blocks, u8 iv[])
+	 *		     int blocks, u8 iv[], int reorder_last_tweak)
 	 */
 __xts_prepare8:
 	vld1.8		{q14}, [r7]		// load iv
-	__ldr		q15, .Lxts_mul_x	// load tweak mask
+	vmov.i32	d30, #0x87		// compose tweak mask vector
+	vmovl.u32	q15, d30
+	vshr.u64	d30, d31, #7
 	vmov		q12, q14
 
 	__adr		ip, 0f
@@ -946,17 +944,25 @@ __xts_prepare8:
 
 	vld1.8		{q7}, [r1]!
 	next_tweak	q14, q12, q15, q13
-	veor		q7, q7, q12
+THUMB(	itt		le		)
+	W(cmple)	r8, #0
+	ble		1f
+0:	veor		q7, q7, q12
 	vst1.8		{q12}, [r4, :128]
 
-0:	vst1.8		{q14}, [r7]		// store next iv
+	vst1.8		{q14}, [r7]		// store next iv
 	bx		lr
+
+1:	vswp		q12, q14
+	b		0b
 ENDPROC(__xts_prepare8)
 
 	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
 	push		{r4-r8, lr}
 	mov		r5, sp			// preserve sp
 	ldrd		r6, r7, [sp, #24]	// get blocks and iv args
+	ldr		r8, [sp, #32]		// reorder final tweak?
+	rsb		r8, r8, #1
 	sub		ip, sp, #128		// make room for 8x tweak
 	bic		ip, ip, #0xf		// align sp to 16 bytes
 	mov		sp, ip
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index bd0bee9c8f7b..e85839a8aaeb 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -6,10 +6,13 @@
  */
 
 #include <asm/neon.h>
+#include <asm/simd.h>
 #include <crypto/aes.h>
 #include <crypto/cbc.h>
+#include <crypto/ctr.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
 #include <crypto/xts.h>
 #include <linux/module.h>
 
@@ -35,9 +38,9 @@ asmlinkage void aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 ctr[], u8 final[]);
 
 asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 iv[]);
+				  int rounds, int blocks, u8 iv[], int);
 asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 iv[]);
+				  int rounds, int blocks, u8 iv[], int);
 
 struct aesbs_ctx {
 	int	rounds;
@@ -51,9 +54,15 @@ struct aesbs_cbc_ctx {
 
 struct aesbs_xts_ctx {
 	struct aesbs_ctx	key;
+	struct crypto_cipher	*cts_tfm;
 	struct crypto_cipher	*tweak_tfm;
 };
 
+struct aesbs_ctr_ctx {
+	struct aesbs_ctx	key;		/* must be first member */
+	struct crypto_aes_ctx	fallback;
+};
+
 static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			unsigned int key_len)
 {
@@ -61,7 +70,7 @@ static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 	struct crypto_aes_ctx rk;
 	int err;
 
-	err = crypto_aes_expand_key(&rk, in_key, key_len);
+	err = aes_expandkey(&rk, in_key, key_len);
 	if (err)
 		return err;
 
@@ -83,9 +92,8 @@ static int __ecb_crypt(struct skcipher_request *req,
 	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -93,12 +101,13 @@ static int __ecb_crypt(struct skcipher_request *req,
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
 		   ctx->rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -120,7 +129,7 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 	struct crypto_aes_ctx rk;
 	int err;
 
-	err = crypto_aes_expand_key(&rk, in_key, key_len);
+	err = aes_expandkey(&rk, in_key, key_len);
 	if (err)
 		return err;
 
@@ -152,9 +161,8 @@ static int cbc_decrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -162,13 +170,14 @@ static int cbc_decrypt(struct skcipher_request *req)
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				  ctx->key.rk, ctx->key.rounds, blocks,
 				  walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -189,6 +198,25 @@ static void cbc_exit(struct crypto_tfm *tfm)
 	crypto_free_cipher(ctx->enc_tfm);
 }
 
+static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key,
+				 unsigned int key_len)
+{
+	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = aes_expandkey(&ctx->fallback, in_key, key_len);
+	if (err)
+		return err;
+
+	ctx->key.rounds = 6 + key_len / 4;
+
+	kernel_neon_begin();
+	aesbs_convert_key(ctx->key.rk, ctx->fallback.key_enc, ctx->key.rounds);
+	kernel_neon_end();
+
+	return 0;
+}
+
 static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -197,9 +225,8 @@ static int ctr_encrypt(struct skcipher_request *req)
 	u8 buf[AES_BLOCK_SIZE];
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes > 0) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 		u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
@@ -210,8 +237,10 @@ static int ctr_encrypt(struct skcipher_request *req)
 			final = NULL;
 		}
 
+		kernel_neon_begin();
 		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				  ctx->rk, ctx->rounds, blocks, walk.iv, final);
+		kernel_neon_end();
 
 		if (final) {
 			u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
@@ -226,11 +255,33 @@ static int ctr_encrypt(struct skcipher_request *req)
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
 
+static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+{
+	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+	unsigned long flags;
+
+	/*
+	 * Temporarily disable interrupts to avoid races where
+	 * cachelines are evicted when the CPU is interrupted
+	 * to do something else.
+	 */
+	local_irq_save(flags);
+	aes_encrypt(&ctx->fallback, dst, src);
+	local_irq_restore(flags);
+}
+
+static int ctr_encrypt_sync(struct skcipher_request *req)
+{
+	if (!crypto_simd_usable())
+		return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
+
+	return ctr_encrypt(req);
+}
+
 static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
@@ -242,6 +293,9 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 		return err;
 
 	key_len /= 2;
+	err = crypto_cipher_setkey(ctx->cts_tfm, in_key, key_len);
+	if (err)
+		return err;
 	err = crypto_cipher_setkey(ctx->tweak_tfm, in_key + key_len, key_len);
 	if (err)
 		return err;
@@ -253,7 +307,13 @@ static int xts_init(struct crypto_tfm *tfm)
 {
 	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 
+	ctx->cts_tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(ctx->cts_tfm))
+		return PTR_ERR(ctx->cts_tfm);
+
 	ctx->tweak_tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(ctx->tweak_tfm))
+		crypto_free_cipher(ctx->cts_tfm);
 
 	return PTR_ERR_OR_ZERO(ctx->tweak_tfm);
 }
@@ -263,49 +323,89 @@ static void xts_exit(struct crypto_tfm *tfm)
 	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	crypto_free_cipher(ctx->tweak_tfm);
+	crypto_free_cipher(ctx->cts_tfm);
 }
 
-static int __xts_crypt(struct skcipher_request *req,
+static int __xts_crypt(struct skcipher_request *req, bool encrypt,
 		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 iv[]))
+				  int rounds, int blocks, u8 iv[], int))
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct skcipher_request subreq;
+	u8 buf[2 * AES_BLOCK_SIZE];
 	struct skcipher_walk walk;
 	int err;
 
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	if (unlikely(tail)) {
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   req->cryptlen - tail, req->iv);
+		req = &subreq;
+	}
+
 	err = skcipher_walk_virt(&walk, req, true);
 	if (err)
 		return err;
 
 	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+		int reorder_last_tweak = !encrypt && tail > 0;
 
-		if (walk.nbytes < walk.total)
+		if (walk.nbytes < walk.total) {
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
+			reorder_last_tweak = 0;
+		}
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk,
-		   ctx->key.rounds, blocks, walk.iv);
+		   ctx->key.rounds, blocks, walk.iv, reorder_last_tweak);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
-	return err;
+	if (err || likely(!tail))
+		return err;
+
+	/* handle ciphertext stealing */
+	scatterwalk_map_and_copy(buf, req->dst, req->cryptlen - AES_BLOCK_SIZE,
+				 AES_BLOCK_SIZE, 0);
+	memcpy(buf + AES_BLOCK_SIZE, buf, tail);
+	scatterwalk_map_and_copy(buf, req->src, req->cryptlen, tail, 0);
+
+	crypto_xor(buf, req->iv, AES_BLOCK_SIZE);
+
+	if (encrypt)
+		crypto_cipher_encrypt_one(ctx->cts_tfm, buf, buf);
+	else
+		crypto_cipher_decrypt_one(ctx->cts_tfm, buf, buf);
+
+	crypto_xor(buf, req->iv, AES_BLOCK_SIZE);
+
+	scatterwalk_map_and_copy(buf, req->dst, req->cryptlen - AES_BLOCK_SIZE,
+				 AES_BLOCK_SIZE + tail, 1);
+	return 0;
 }
 
 static int xts_encrypt(struct skcipher_request *req)
 {
-	return __xts_crypt(req, aesbs_xts_encrypt);
+	return __xts_crypt(req, true, aesbs_xts_encrypt);
 }
 
 static int xts_decrypt(struct skcipher_request *req)
 {
-	return __xts_crypt(req, aesbs_xts_decrypt);
+	return __xts_crypt(req, false, aesbs_xts_decrypt);
 }
 
 static struct skcipher_alg aes_algs[] = { {
@@ -359,6 +459,22 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= ctr_encrypt,
 	.decrypt		= ctr_encrypt,
 }, {
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-neonbs-sync",
+	.base.cra_priority	= 250 - 1,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct aesbs_ctr_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_ctr_setkey_sync,
+	.encrypt		= ctr_encrypt_sync,
+	.decrypt		= ctr_encrypt_sync,
+}, {
 	.base.cra_name		= "__xts(aes)",
 	.base.cra_driver_name	= "__xts-aes-neonbs",
 	.base.cra_priority	= 250,
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 52d472a050e6..c691077679a6 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -9,6 +9,7 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <asm/unaligned.h>
+#include <crypto/b128ops.h>
 #include <crypto/cryptd.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
@@ -17,7 +18,7 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
-MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
+MODULE_DESCRIPTION("GHASH hash function using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("ghash");
@@ -30,6 +31,8 @@ struct ghash_key {
 	u64	h2[2];
 	u64	h3[2];
 	u64	h4[2];
+
+	be128	k;
 };
 
 struct ghash_desc_ctx {
@@ -62,6 +65,36 @@ static int ghash_init(struct shash_desc *desc)
 	return 0;
 }
 
+static void ghash_do_update(int blocks, u64 dg[], const char *src,
+			    struct ghash_key *key, const char *head)
+{
+	if (likely(crypto_simd_usable())) {
+		kernel_neon_begin();
+		pmull_ghash_update(blocks, dg, src, key, head);
+		kernel_neon_end();
+	} else {
+		be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
+
+		do {
+			const u8 *in = src;
+
+			if (head) {
+				in = head;
+				blocks++;
+				head = NULL;
+			} else {
+				src += GHASH_BLOCK_SIZE;
+			}
+
+			crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
+			gf128mul_lle(&dst, &key->k);
+		} while (--blocks);
+
+		dg[0] = be64_to_cpu(dst.b);
+		dg[1] = be64_to_cpu(dst.a);
+	}
+}
+
 static int ghash_update(struct shash_desc *desc, const u8 *src,
 			unsigned int len)
 {
@@ -85,10 +118,8 @@ static int ghash_update(struct shash_desc *desc, const u8 *src,
 		blocks = len / GHASH_BLOCK_SIZE;
 		len %= GHASH_BLOCK_SIZE;
 
-		kernel_neon_begin();
-		pmull_ghash_update(blocks, ctx->digest, src, key,
-				   partial ? ctx->buf : NULL);
-		kernel_neon_end();
+		ghash_do_update(blocks, ctx->digest, src, key,
+				partial ? ctx->buf : NULL);
 		src += blocks * GHASH_BLOCK_SIZE;
 		partial = 0;
 	}
@@ -106,9 +137,7 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
 		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
 
 		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
-		kernel_neon_begin();
-		pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
-		kernel_neon_end();
+		ghash_do_update(1, ctx->digest, ctx->buf, key, NULL);
 	}
 	put_unaligned_be64(ctx->digest[1], dst);
 	put_unaligned_be64(ctx->digest[0], dst + 8);
@@ -132,24 +161,25 @@ static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *inkey, unsigned int keylen)
 {
 	struct ghash_key *key = crypto_shash_ctx(tfm);
-	be128 h, k;
+	be128 h;
 
 	if (keylen != GHASH_BLOCK_SIZE) {
 		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	memcpy(&k, inkey, GHASH_BLOCK_SIZE);
-	ghash_reflect(key->h, &k);
+	/* needed for the fallback */
+	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
+	ghash_reflect(key->h, &key->k);
 
-	h = k;
-	gf128mul_lle(&h, &k);
+	h = key->k;
+	gf128mul_lle(&h, &key->k);
 	ghash_reflect(key->h2, &h);
 
-	gf128mul_lle(&h, &k);
+	gf128mul_lle(&h, &key->k);
 	ghash_reflect(key->h3, &h);
 
-	gf128mul_lle(&h, &k);
+	gf128mul_lle(&h, &key->k);
 	ghash_reflect(key->h4, &h);
 
 	return 0;
@@ -162,15 +192,13 @@ static struct shash_alg ghash_alg = {
 	.final			= ghash_final,
 	.setkey			= ghash_setkey,
 	.descsize		= sizeof(struct ghash_desc_ctx),
-	.base			= {
-		.cra_name	= "__ghash",
-		.cra_driver_name = "__driver-ghash-ce",
-		.cra_priority	= 0,
-		.cra_flags	= CRYPTO_ALG_INTERNAL,
-		.cra_blocksize	= GHASH_BLOCK_SIZE,
-		.cra_ctxsize	= sizeof(struct ghash_key),
-		.cra_module	= THIS_MODULE,
-	},
+
+	.base.cra_name		= "ghash",
+	.base.cra_driver_name	= "ghash-ce-sync",
+	.base.cra_priority	= 300 - 1,
+	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct ghash_key),
+	.base.cra_module	= THIS_MODULE,
 };
 
 static int ghash_async_init(struct ahash_request *req)
@@ -285,9 +313,7 @@ static int ghash_async_init_tfm(struct crypto_tfm *tfm)
 	struct cryptd_ahash *cryptd_tfm;
 	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	cryptd_tfm = cryptd_alloc_ahash("__driver-ghash-ce",
-					CRYPTO_ALG_INTERNAL,
-					CRYPTO_ALG_INTERNAL);
+	cryptd_tfm = cryptd_alloc_ahash("ghash-ce-sync", 0, 0);
 	if (IS_ERR(cryptd_tfm))
 		return PTR_ERR(cryptd_tfm);
 	ctx->cryptd_tfm = cryptd_tfm;
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
index 70efa9656bff..215497f011f2 100644
--- a/arch/arm/crypto/sha256_glue.c
+++ b/arch/arm/crypto/sha256_glue.c
@@ -39,7 +39,7 @@ int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data,
 }
 EXPORT_SYMBOL(crypto_sha256_arm_update);
 
-static int sha256_final(struct shash_desc *desc, u8 *out)
+static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out)
 {
 	sha256_base_do_finalize(desc,
 				(sha256_block_fn *)sha256_block_data_order);
@@ -51,7 +51,7 @@ int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data,
 {
 	sha256_base_do_update(desc, data, len,
 			      (sha256_block_fn *)sha256_block_data_order);
-	return sha256_final(desc, out);
+	return crypto_sha256_arm_final(desc, out);
 }
 EXPORT_SYMBOL(crypto_sha256_arm_finup);
 
@@ -59,7 +59,7 @@ static struct shash_alg algs[] = { {
 	.digestsize	=	SHA256_DIGEST_SIZE,
 	.init		=	sha256_base_init,
 	.update		=	crypto_sha256_arm_update,
-	.final		=	sha256_final,
+	.final		=	crypto_sha256_arm_final,
 	.finup		=	crypto_sha256_arm_finup,
 	.descsize	=	sizeof(struct sha256_state),
 	.base		=	{
@@ -73,7 +73,7 @@ static struct shash_alg algs[] = { {
 	.digestsize	=	SHA224_DIGEST_SIZE,
 	.init		=	sha224_base_init,
 	.update		=	crypto_sha256_arm_update,
-	.final		=	sha256_final,
+	.final		=	crypto_sha256_arm_final,
 	.finup		=	crypto_sha256_arm_finup,
 	.descsize	=	sizeof(struct sha256_state),
 	.base		=	{
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
index a7ce38a36006..38645e415196 100644
--- a/arch/arm/crypto/sha256_neon_glue.c
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -25,8 +25,8 @@
 asmlinkage void sha256_block_data_order_neon(u32 *digest, const void *data,
 					     unsigned int num_blks);
 
-static int sha256_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
+static int crypto_sha256_neon_update(struct shash_desc *desc, const u8 *data,
+				     unsigned int len)
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
@@ -42,8 +42,8 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 	return 0;
 }
 
-static int sha256_finup(struct shash_desc *desc, const u8 *data,
-			unsigned int len, u8 *out)
+static int crypto_sha256_neon_finup(struct shash_desc *desc, const u8 *data,
+				    unsigned int len, u8 *out)
 {
 	if (!crypto_simd_usable())
 		return crypto_sha256_arm_finup(desc, data, len, out);
@@ -59,17 +59,17 @@ static int sha256_finup(struct shash_desc *desc, const u8 *data,
 	return sha256_base_finish(desc, out);
 }
 
-static int sha256_final(struct shash_desc *desc, u8 *out)
+static int crypto_sha256_neon_final(struct shash_desc *desc, u8 *out)
 {
-	return sha256_finup(desc, NULL, 0, out);
+	return crypto_sha256_neon_finup(desc, NULL, 0, out);
 }
 
 struct shash_alg sha256_neon_algs[] = { {
 	.digestsize	=	SHA256_DIGEST_SIZE,
 	.init		=	sha256_base_init,
-	.update		=	sha256_update,
-	.final		=	sha256_final,
-	.finup		=	sha256_finup,
+	.update		=	crypto_sha256_neon_update,
+	.final		=	crypto_sha256_neon_final,
+	.finup		=	crypto_sha256_neon_finup,
 	.descsize	=	sizeof(struct sha256_state),
 	.base		=	{
 		.cra_name	=	"sha256",
@@ -81,9 +81,9 @@ struct shash_alg sha256_neon_algs[] = { {
 }, {
 	.digestsize	=	SHA224_DIGEST_SIZE,
 	.init		=	sha224_base_init,
-	.update		=	sha256_update,
-	.final		=	sha256_final,
-	.finup		=	sha256_finup,
+	.update		=	crypto_sha256_neon_update,
+	.final		=	crypto_sha256_neon_final,
+	.finup		=	crypto_sha256_neon_finup,
 	.descsize	=	sizeof(struct sha256_state),
 	.base		=	{
 		.cra_name	=	"sha224",
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 6b2dc15b6dff..68ca86f85eb7 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -17,7 +17,6 @@ generic-y += parport.h
 generic-y += preempt.h
 generic-y += seccomp.h
 generic-y += serial.h
-generic-y += simd.h
 generic-y += trace_clock.h
 
 generated-y += mach-types.h