diff mbox

[v2,6/7] crypto: omap-aes: Add support for GCM mode

Message ID 1436283109-13318-7-git-send-email-lokeshvutla@ti.com (mailing list archive)
State New, archived
Headers show

Commit Message

Lokesh Vutla July 7, 2015, 3:31 p.m. UTC
OMAP AES hw supports AES-GCM mode.
Adding support for GCM mode in omap-aes driver.

Signed-off-by: Lokesh Vutla <lokeshvutla@ti.com>
---
 drivers/crypto/Kconfig        |   1 +
 drivers/crypto/Makefile       |   3 +-
 drivers/crypto/omap-aes-gcm.c | 376 ++++++++++++++++++++++++++++++++++++++++++
 drivers/crypto/omap-aes.c     | 300 ++++++++++++++-------------------
 drivers/crypto/omap-aes.h     | 212 ++++++++++++++++++++++++
 5 files changed, 718 insertions(+), 174 deletions(-)
 create mode 100644 drivers/crypto/omap-aes-gcm.c
 create mode 100644 drivers/crypto/omap-aes.h

Comments

Herbert Xu July 8, 2015, 4:18 a.m. UTC | #1
On Tue, Jul 07, 2015 at 09:01:48PM +0530, Lokesh Vutla wrote:
>
> +static int omap_aes_gcm_copy_buffers(struct omap_aes_dev *dd,
> +				     struct aead_request *req)
> +{
> +	void *buf_in;
> +	int pages, alen, clen, cryptlen, nsg;
> +	struct crypto_aead *aead = crypto_aead_reqtfm(req);
> +	unsigned int authlen = crypto_aead_authsize(aead);
> +	u32 dec = !(dd->flags & FLAGS_ENCRYPT);
> +	struct scatterlist *input, *assoc, tmp[2];
> +
> +	alen = ALIGN(req->assoclen, AES_BLOCK_SIZE);
> +	cryptlen = req->cryptlen - (dec * authlen);
> +	clen = ALIGN(cryptlen, AES_BLOCK_SIZE);
> +
> +	dd->sgs_copied = 0;
> +
> +	nsg = !!(req->assoclen && req->cryptlen);
> +
> +	assoc = &req->src[0];
> +	sg_init_table(dd->in_sgl, nsg + 1);
> +	if (req->assoclen) {
> +		if (omap_aes_check_aligned(assoc, req->assoclen)) {
> +			dd->sgs_copied |= AES_ASSOC_DATA_COPIED;
> +			pages = get_order(alen);
> +			buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
> +			if (!buf_in) {
> +				pr_err("Couldn't allocate for unaligncases.\n");
> +				return -1;
> +			}
> +
> +			scatterwalk_map_and_copy(buf_in, assoc, 0,
> +						 req->assoclen, 0);
> +			memset(buf_in + req->assoclen, 0, alen - req->assoclen);
> +		} else {
> +			buf_in = sg_virt(req->assoc);

req->assoc is now obsolete. Did you test this code?

> +static int do_encrypt_iv(struct aead_request *req, u32 *tag)
> +{
> +	struct scatterlist iv_sg;
> +	struct ablkcipher_request *ablk_req;
> +	struct crypto_ablkcipher *tfm;
> +	struct tcrypt_result result;
> +	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
> +	int ret = 0;
> +
> +	tfm = crypto_alloc_ablkcipher("ctr(aes)", 0, 0);

Ugh, you cannot allocate crypto transforms in the data path.  You
should allocate it in init instead.  Also using ctr(aes) is overkill.
Just use aes and do the xor by hand.

> +static int omap_aes_gcm_crypt(struct aead_request *req, unsigned long mode)
> +{
> +	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
> +	struct omap_aes_reqctx *rctx = aead_request_ctx(req);
> +	struct crypto_aead *aead = crypto_aead_reqtfm(req);
> +	unsigned int authlen = crypto_aead_authsize(aead);
> +	struct omap_aes_dev *dd;
> +	__be32 counter = cpu_to_be32(1);
> +	int err;
> +
> +	memset(ctx->auth_tag, 0, sizeof(ctx->auth_tag));

The ctx is shared memory and you must not write to it as multiple
requests can be called on the same tfm.  Use rctx instead.

> +	memcpy(req->iv + 12, &counter, 4);

The IV is only 12 bytes long so you're corrupting memory here.
You should use rctx here too.

> +	if (req->assoclen + req->cryptlen == 0) {
> +		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
> +					 1);
> +		return 0;
> +	}

How can this be right? Did you enable the selftest?

Cheers,
Lokesh Vutla July 8, 2015, 6:59 a.m. UTC | #2
On Wednesday 08 July 2015 09:48 AM, Herbert Xu wrote:
> On Tue, Jul 07, 2015 at 09:01:48PM +0530, Lokesh Vutla wrote:
>>
>> +static int omap_aes_gcm_copy_buffers(struct omap_aes_dev *dd,
>> +				     struct aead_request *req)
>> +{
>> +	void *buf_in;
>> +	int pages, alen, clen, cryptlen, nsg;
>> +	struct crypto_aead *aead = crypto_aead_reqtfm(req);
>> +	unsigned int authlen = crypto_aead_authsize(aead);
>> +	u32 dec = !(dd->flags & FLAGS_ENCRYPT);
>> +	struct scatterlist *input, *assoc, tmp[2];
>> +
>> +	alen = ALIGN(req->assoclen, AES_BLOCK_SIZE);
>> +	cryptlen = req->cryptlen - (dec * authlen);
>> +	clen = ALIGN(cryptlen, AES_BLOCK_SIZE);
>> +
>> +	dd->sgs_copied = 0;
>> +
>> +	nsg = !!(req->assoclen && req->cryptlen);
>> +
>> +	assoc = &req->src[0];
>> +	sg_init_table(dd->in_sgl, nsg + 1);
>> +	if (req->assoclen) {
>> +		if (omap_aes_check_aligned(assoc, req->assoclen)) {
>> +			dd->sgs_copied |= AES_ASSOC_DATA_COPIED;
>> +			pages = get_order(alen);
>> +			buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
>> +			if (!buf_in) {
>> +				pr_err("Couldn't allocate for unaligncases.\n");
>> +				return -1;
>> +			}
>> +
>> +			scatterwalk_map_and_copy(buf_in, assoc, 0,
>> +						 req->assoclen, 0);
>> +			memset(buf_in + req->assoclen, 0, alen - req->assoclen);
>> +		} else {
>> +			buf_in = sg_virt(req->assoc);
> 
> req->assoc is now obsolete. Did you test this code?
Sorry, I missed it. Ill update.

> 
>> +static int do_encrypt_iv(struct aead_request *req, u32 *tag)
>> +{
>> +	struct scatterlist iv_sg;
>> +	struct ablkcipher_request *ablk_req;
>> +	struct crypto_ablkcipher *tfm;
>> +	struct tcrypt_result result;
>> +	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
>> +	int ret = 0;
>> +
>> +	tfm = crypto_alloc_ablkcipher("ctr(aes)", 0, 0);
> 
> Ugh, you cannot allocate crypto transforms in the data path.  You
> should allocate it in init instead.  Also using ctr(aes) is overkill.
> Just use aes and do the xor by hand.
Ill take care of this.
> 
>> +static int omap_aes_gcm_crypt(struct aead_request *req, unsigned long mode)
>> +{
>> +	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
>> +	struct omap_aes_reqctx *rctx = aead_request_ctx(req);
>> +	struct crypto_aead *aead = crypto_aead_reqtfm(req);
>> +	unsigned int authlen = crypto_aead_authsize(aead);
>> +	struct omap_aes_dev *dd;
>> +	__be32 counter = cpu_to_be32(1);
>> +	int err;
>> +
>> +	memset(ctx->auth_tag, 0, sizeof(ctx->auth_tag));
> 
> The ctx is shared memory and you must not write to it as multiple
> requests can be called on the same tfm.  Use rctx instead.
> 
>> +	memcpy(req->iv + 12, &counter, 4);
> 
> The IV is only 12 bytes long so you're corrupting memory here.
> You should use rctx here too.
Ok, Ill use rctx. Thanks for pointing.

> 
>> +	if (req->assoclen + req->cryptlen == 0) {
>> +		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
>> +					 1);
>> +		return 0;
>> +	}
> 
> How can this be right? Did you enable the selftest?
Why not? Self tests are passed for this case.

As per the equation given in GCM spec[1], we can see that
if assoclen and cryptlen is 0, then output of GCM  is just E(K, Y0)
where Y0 = IV||(0^31)1
I have E(K, Y0) calculated in previous step. And copying it
to destination if assoclen and cryptlen is 0.

Correct me if I am wrong.

Thanks and regards,
Lokesh

[1] http://csrc.nist.gov/groups/ST/toolkit/BCM/documents/proposedmodes/gcm/gcm-revised-spec.pdf

> 
> Cheers,
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Herbert Xu July 8, 2015, 7:48 a.m. UTC | #3
On Wed, Jul 08, 2015 at 12:29:47PM +0530, Lokesh Vutla wrote:
>
> >> +	if (req->assoclen + req->cryptlen == 0) {
> >> +		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
> >> +					 1);
> >> +		return 0;
> >> +	}
> > 
> > How can this be right? Did you enable the selftest?
> Why not? Self tests are passed for this case.
> 
> As per the equation given in GCM spec[1], we can see that
> if assoclen and cryptlen is 0, then output of GCM  is just E(K, Y0)
> where Y0 = IV||(0^31)1
> I have E(K, Y0) calculated in previous step. And copying it
> to destination if assoclen and cryptlen is 0.
> 
> Correct me if I am wrong.

It should be E(K, Y0) ^ GHASH(0).  So unless GHASH(0) == 0, your
code doesn't work.

Cheers,
Herbert Xu July 8, 2015, 7:53 a.m. UTC | #4
On Wed, Jul 08, 2015 at 03:48:05PM +0800, Herbert Xu wrote:
> On Wed, Jul 08, 2015 at 12:29:47PM +0530, Lokesh Vutla wrote:
> >
> > >> +	if (req->assoclen + req->cryptlen == 0) {
> > >> +		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
> > >> +					 1);
> > >> +		return 0;
> > >> +	}
> > > 
> > > How can this be right? Did you enable the selftest?
> > Why not? Self tests are passed for this case.
> > 
> > As per the equation given in GCM spec[1], we can see that
> > if assoclen and cryptlen is 0, then output of GCM  is just E(K, Y0)
> > where Y0 = IV||(0^31)1
> > I have E(K, Y0) calculated in previous step. And copying it
> > to destination if assoclen and cryptlen is 0.
> > 
> > Correct me if I am wrong.
> 
> It should be E(K, Y0) ^ GHASH(0).  So unless GHASH(0) == 0, your
> code doesn't work.

OK, GHASH(0) is indeed zero so I guess your code does work after
all.

Cheers,
Lokesh Vutla July 8, 2015, 8:15 a.m. UTC | #5
On Wednesday 08 July 2015 01:18 PM, Herbert Xu wrote:
> On Wed, Jul 08, 2015 at 12:29:47PM +0530, Lokesh Vutla wrote:
>>
>>>> +	if (req->assoclen + req->cryptlen == 0) {
>>>> +		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
>>>> +					 1);
>>>> +		return 0;
>>>> +	}
>>>
>>> How can this be right? Did you enable the selftest?
>> Why not? Self tests are passed for this case.
>>
>> As per the equation given in GCM spec[1], we can see that
>> if assoclen and cryptlen is 0, then output of GCM  is just E(K, Y0)
>> where Y0 = IV||(0^31)1
>> I have E(K, Y0) calculated in previous step. And copying it
>> to destination if assoclen and cryptlen is 0.
>>
>> Correct me if I am wrong.
> 
> It should be E(K, Y0) ^ GHASH(0).  So unless GHASH(0) == 0, your
> code doesn't work.
Yes, thats right. I have considered that.
So, we need GHASH(H, {}, {}).
As per the spec, 
GHASH(H, A, C) = X(m + n + 1). 
					m = n = 0 in our case.

X0 = 0
X1 = (X(m  + n) ^ (len(A) || len(C)) . H
X1 = 0 . H		(GF(128) Multiplication)
X1 = 0	

The same thing is given in the Test case 1 of the spec. GHASH(H, {}, {}) = 0

Thanks and regards,
Lokesh

> 
> Cheers,
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Lokesh Vutla July 8, 2015, 8:30 a.m. UTC | #6
On Wednesday 08 July 2015 01:23 PM, Herbert Xu wrote:
> On Wed, Jul 08, 2015 at 03:48:05PM +0800, Herbert Xu wrote:
>> On Wed, Jul 08, 2015 at 12:29:47PM +0530, Lokesh Vutla wrote:
>>>
>>>>> +	if (req->assoclen + req->cryptlen == 0) {
>>>>> +		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
>>>>> +					 1);
>>>>> +		return 0;
>>>>> +	}
>>>>
>>>> How can this be right? Did you enable the selftest?
>>> Why not? Self tests are passed for this case.
>>>
>>> As per the equation given in GCM spec[1], we can see that
>>> if assoclen and cryptlen is 0, then output of GCM  is just E(K, Y0)
>>> where Y0 = IV||(0^31)1
>>> I have E(K, Y0) calculated in previous step. And copying it
>>> to destination if assoclen and cryptlen is 0.
>>>
>>> Correct me if I am wrong.
>>
>> It should be E(K, Y0) ^ GHASH(0).  So unless GHASH(0) == 0, your
>> code doesn't work.
> 
> OK, GHASH(0) is indeed zero so I guess your code does work after
> all.
Sorry. I did not see this message and replied on the other thread.

Thanks and regards,
Lokesh
> 
> Cheers,
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Lokesh Vutla July 10, 2015, 2:09 p.m. UTC | #7
Hi Herbert,
On Wednesday 08 July 2015 09:48 AM, Herbert Xu wrote:
> On Tue, Jul 07, 2015 at 09:01:48PM +0530, Lokesh Vutla wrote:
>>
>> +static int omap_aes_gcm_copy_buffers(struct omap_aes_dev *dd,
>> +				     struct aead_request *req)

[..snip..]

>> +static int do_encrypt_iv(struct aead_request *req, u32 *tag)
>> +{
>> +	struct scatterlist iv_sg;
>> +	struct ablkcipher_request *ablk_req;
>> +	struct crypto_ablkcipher *tfm;
>> +	struct tcrypt_result result;
>> +	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
>> +	int ret = 0;
>> +
>> +	tfm = crypto_alloc_ablkcipher("ctr(aes)", 0, 0);
> 
> Ugh, you cannot allocate crypto transforms in the data path.  You
> should allocate it in init instead.  Also using ctr(aes) is overkill.
> Just use aes and do the xor by hand.
> 
>> +static int omap_aes_gcm_crypt(struct aead_request *req, unsigned long mode)
>> +{
>> +	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
>> +	struct omap_aes_reqctx *rctx = aead_request_ctx(req);
>> +	struct crypto_aead *aead = crypto_aead_reqtfm(req);
>> +	unsigned int authlen = crypto_aead_authsize(aead);
>> +	struct omap_aes_dev *dd;
>> +	__be32 counter = cpu_to_be32(1);
>> +	int err;
>> +
>> +	memset(ctx->auth_tag, 0, sizeof(ctx->auth_tag));
> 
> The ctx is shared memory and you must not write to it as multiple
> requests can be called on the same tfm.  Use rctx instead.

May be a dumb question. 
If you don't mind can you elaborate more on the usage of rctx and ctx
in the driver?

Thanks and regards,
Lokesh
> 
>> +	memcpy(req->iv + 12, &counter, 4);
> 
> The IV is only 12 bytes long so you're corrupting memory here.
> You should use rctx here too.
> 
>> +	if (req->assoclen + req->cryptlen == 0) {
>> +		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
>> +					 1);
>> +		return 0;
>> +	}
> 
> How can this be right? Did you enable the selftest?
> 
> Cheers,
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Herbert Xu July 11, 2015, 2:40 a.m. UTC | #8
On Fri, Jul 10, 2015 at 07:39:35PM +0530, Lokesh Vutla wrote:
>
> If you don't mind can you elaborate more on the usage of rctx and ctx
> in the driver?

The ctx is a property of the tfm and it's shared by all users
of that tfm.  So it must not be written to unless you use locking.

The reqeust context on the other hand is specific to a request
so it can be used to store information.

Cheers,
diff mbox

Patch

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 4044125..6e67271 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -293,6 +293,7 @@  config CRYPTO_DEV_OMAP_AES
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || ARCH_OMAP2PLUS
 	select CRYPTO_AES
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_AEAD
 	help
 	  OMAP processors have AES module accelerator. Select this if you
 	  want to use the OMAP module for AES algorithms.
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index e35c07a..73115bd 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -14,7 +14,8 @@  obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
 obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
 n2_crypto-y := n2_core.o n2_asm.o
 obj-$(CONFIG_CRYPTO_DEV_NX) += nx/
-obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes.o
+obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes-driver.o
+omap-aes-driver-objs := omap-aes.o omap-aes-gcm.o
 obj-$(CONFIG_CRYPTO_DEV_OMAP_DES) += omap-des.o
 obj-$(CONFIG_CRYPTO_DEV_OMAP_SHAM) += omap-sham.o
 obj-$(CONFIG_CRYPTO_DEV_PADLOCK_AES) += padlock-aes.o
diff --git a/drivers/crypto/omap-aes-gcm.c b/drivers/crypto/omap-aes-gcm.c
new file mode 100644
index 0000000..f0faa72
--- /dev/null
+++ b/drivers/crypto/omap-aes-gcm.c
@@ -0,0 +1,376 @@ 
+/*
+ * Cryptographic API.
+ *
+ * Support for OMAP AES GCM HW acceleration.
+ *
+ * Copyright (c) 2015 Texas Instruments Incorporated
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/omap-dma.h>
+#include <linux/interrupt.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/aes.h>
+#include <crypto/internal/aead.h>
+#include "omap-aes.h"
+
+static int omap_aes_gcm_handle_queue(struct omap_aes_dev *dd,
+				     struct aead_request *req);
+
+static void omap_aes_gcm_finish_req(struct omap_aes_dev *dd, int ret)
+{
+	struct aead_request *req = dd->aead_req;
+
+	dd->flags &= ~FLAGS_BUSY;
+	dd->in_sg = NULL;
+	dd->out_sg = NULL;
+
+	req->base.complete(&req->base, ret);
+}
+
+static void omap_aes_gcm_done_task(struct omap_aes_dev *dd)
+{
+	void *buf;
+	u8 *tag;
+	int pages, alen, clen, i, ret = 0, nsg;
+
+	alen = ALIGN(dd->assoc_len, AES_BLOCK_SIZE);
+	clen = ALIGN(dd->total, AES_BLOCK_SIZE);
+
+	nsg = !!(dd->assoc_len && dd->total);
+
+	dma_sync_sg_for_device(dd->dev, dd->out_sg, dd->out_sg_len,
+			       DMA_FROM_DEVICE);
+	dma_unmap_sg(dd->dev, dd->in_sg, dd->in_sg_len, DMA_TO_DEVICE);
+	dma_unmap_sg(dd->dev, dd->out_sg, dd->out_sg_len, DMA_FROM_DEVICE);
+	omap_aes_crypt_dma_stop(dd);
+
+	if (dd->sgs_copied & AES_OUT_DATA_COPIED) {
+		buf = sg_virt(&dd->out_sgl);
+		scatterwalk_map_and_copy(buf, dd->orig_out, dd->assoc_len,
+					 dd->total, 1);
+
+		pages = get_order(clen);
+		free_pages((unsigned long)buf, pages);
+	}
+
+	if (dd->flags & FLAGS_ENCRYPT)
+		scatterwalk_map_and_copy(dd->ctx->auth_tag,
+					 dd->aead_req->dst,
+					 dd->total + dd->assoc_len,
+					 dd->authsize, 1);
+
+	if (dd->sgs_copied & AES_ASSOC_DATA_COPIED) {
+		buf = sg_virt(&dd->in_sgl[0]);
+		pages = get_order(alen);
+		free_pages((unsigned long)buf, pages);
+	}
+	if (dd->sgs_copied & AES_IN_DATA_COPIED) {
+		buf = sg_virt(&dd->in_sgl[nsg]);
+		pages = get_order(clen);
+		free_pages((unsigned long)buf, pages);
+	}
+
+	if (!(dd->flags & FLAGS_ENCRYPT)) {
+		tag = (u8 *)dd->ctx->auth_tag;
+		for (i = 0; i < dd->authsize; i++) {
+			if (tag[i]) {
+				dev_err(dd->dev, "GCM decryption: Tag Message is wrong\n");
+				ret = -EBADMSG;
+			}
+		}
+	}
+
+	omap_aes_gcm_finish_req(dd, ret);
+	omap_aes_gcm_handle_queue(dd, NULL);
+}
+
+static int omap_aes_gcm_copy_buffers(struct omap_aes_dev *dd,
+				     struct aead_request *req)
+{
+	void *buf_in;
+	int pages, alen, clen, cryptlen, nsg;
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	unsigned int authlen = crypto_aead_authsize(aead);
+	u32 dec = !(dd->flags & FLAGS_ENCRYPT);
+	struct scatterlist *input, *assoc, tmp[2];
+
+	alen = ALIGN(req->assoclen, AES_BLOCK_SIZE);
+	cryptlen = req->cryptlen - (dec * authlen);
+	clen = ALIGN(cryptlen, AES_BLOCK_SIZE);
+
+	dd->sgs_copied = 0;
+
+	nsg = !!(req->assoclen && req->cryptlen);
+
+	assoc = &req->src[0];
+	sg_init_table(dd->in_sgl, nsg + 1);
+	if (req->assoclen) {
+		if (omap_aes_check_aligned(assoc, req->assoclen)) {
+			dd->sgs_copied |= AES_ASSOC_DATA_COPIED;
+			pages = get_order(alen);
+			buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
+			if (!buf_in) {
+				pr_err("Couldn't allocate for unaligncases.\n");
+				return -1;
+			}
+
+			scatterwalk_map_and_copy(buf_in, assoc, 0,
+						 req->assoclen, 0);
+			memset(buf_in + req->assoclen, 0, alen - req->assoclen);
+		} else {
+			buf_in = sg_virt(req->assoc);
+		}
+		sg_set_buf(dd->in_sgl, buf_in, alen);
+	}
+
+	if (req->cryptlen) {
+		input = scatterwalk_ffwd(tmp, req->src, req->assoclen);
+
+		if (omap_aes_check_aligned(input, req->cryptlen)) {
+			dd->sgs_copied |= AES_IN_DATA_COPIED;
+			pages = get_order(clen);
+			buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
+			if (!buf_in) {
+				pr_err("Couldn't allocate for unaligncases.\n");
+				return -1;
+			}
+
+			scatterwalk_map_and_copy(buf_in, input, 0, cryptlen, 0);
+			memset(buf_in + cryptlen, 0, clen - cryptlen);
+		} else {
+			buf_in = sg_virt(input);
+		}
+		sg_set_buf(&dd->in_sgl[nsg], buf_in, clen);
+	}
+
+	dd->in_sg = dd->in_sgl;
+	dd->total = cryptlen;
+	dd->assoc_len = req->assoclen;
+	dd->authsize = authlen;
+
+	if (omap_aes_check_aligned(req->dst, cryptlen + req->assoclen)) {
+		pages = get_order(clen);
+
+		buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
+
+		if (!buf_in) {
+			pr_err("Couldn't allocate for unaligned cases.\n");
+			return -1;
+		}
+
+		sg_init_one(&dd->out_sgl, buf_in, clen);
+		dd->out_sg = &dd->out_sgl;
+		dd->orig_out = req->dst;
+		dd->sgs_copied |= AES_OUT_DATA_COPIED;
+	} else {
+		dd->out_sg = scatterwalk_ffwd(tmp, req->dst, req->assoclen);
+	}
+
+	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, alen + clen);
+	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, clen);
+
+	return 0;
+}
+
+static void tcrypt_complete(struct crypto_async_request *req, int err)
+{
+	struct tcrypt_result *res = req->data;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	res->err = err;
+	complete(&res->completion);
+}
+
+static int do_encrypt_iv(struct aead_request *req, u32 *tag)
+{
+	struct scatterlist iv_sg;
+	struct ablkcipher_request *ablk_req;
+	struct crypto_ablkcipher *tfm;
+	struct tcrypt_result result;
+	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	int ret = 0;
+
+	tfm = crypto_alloc_ablkcipher("ctr(aes)", 0, 0);
+	ablk_req = ablkcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!ablk_req) {
+		pr_err("skcipher: Failed to allocate request\n");
+		return -1;
+	}
+
+	init_completion(&result.completion);
+
+	sg_init_one(&iv_sg, tag, AES_BLOCK_SIZE);
+	ablkcipher_request_set_callback(ablk_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					tcrypt_complete, &result);
+	ret = crypto_ablkcipher_setkey(tfm, (u8 *)ctx->key, ctx->keylen);
+	ablkcipher_request_set_crypt(ablk_req, &iv_sg, &iv_sg, AES_BLOCK_SIZE,
+				     req->iv);
+	ret = crypto_ablkcipher_encrypt(ablk_req);
+	switch (ret) {
+	case 0:
+		break;
+	case -EINPROGRESS:
+	case -EBUSY:
+		ret = wait_for_completion_interruptible(&result.completion);
+		if (!ret) {
+			ret = result.err;
+			if (!ret) {
+				reinit_completion(&result.completion);
+				break;
+			}
+		}
+		/* fall through */
+	default:
+		pr_err("Encryptio of IV failed for GCM mode");
+		break;
+	}
+
+	ablkcipher_request_free(ablk_req);
+	crypto_free_ablkcipher(tfm);
+	return ret;
+}
+
+void omap_aes_gcm_dma_out_callback(void *data)
+{
+	struct omap_aes_dev *dd = data;
+	int i, val;
+	u32 *auth_tag, tag[4];
+
+	if (!(dd->flags & FLAGS_ENCRYPT))
+		scatterwalk_map_and_copy(tag, dd->aead_req->src,
+					 dd->total + dd->assoc_len,
+					 dd->authsize, 0);
+
+	auth_tag = dd->ctx->auth_tag;
+	for (i = 0; i < 4; i++) {
+		val = omap_aes_read(dd, AES_REG_TAG_N(dd, i));
+		auth_tag[i] = val ^ auth_tag[i];
+		if (!(dd->flags & FLAGS_ENCRYPT))
+			auth_tag[i] = auth_tag[i] ^ tag[i];
+	}
+
+	omap_aes_gcm_done_task(dd);
+}
+
+static int omap_aes_gcm_handle_queue(struct omap_aes_dev *dd,
+				     struct aead_request *req)
+{
+	struct omap_aes_ctx *ctx;
+	struct crypto_async_request *async_req, *backlog;
+	struct omap_aes_reqctx *rctx;
+	unsigned long flags;
+	int err, ret = 0;
+
+	spin_lock_irqsave(&dd->lock, flags);
+	if (req)
+		ret = crypto_enqueue_request(&dd->aead_queue, &req->base);
+	if (dd->flags & FLAGS_BUSY) {
+		spin_unlock_irqrestore(&dd->lock, flags);
+		return ret;
+	}
+	backlog = crypto_get_backlog(&dd->aead_queue);
+	async_req = crypto_dequeue_request(&dd->aead_queue);
+	if (async_req)
+		dd->flags |= FLAGS_BUSY;
+	spin_unlock_irqrestore(&dd->lock, flags);
+
+	if (!async_req)
+		return ret;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	req = aead_request_cast(async_req);
+
+	ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	rctx = aead_request_ctx(req);
+
+	dd->ctx = ctx;
+	ctx->dd = dd;
+	dd->aead_req = req;
+
+	rctx->mode &= FLAGS_MODE_MASK;
+	dd->flags = (dd->flags & ~FLAGS_MODE_MASK) | rctx->mode;
+
+	err = omap_aes_gcm_copy_buffers(dd, req);
+	if (err)
+		return err;
+
+	err = omap_aes_write_ctrl(dd);
+	if (!err)
+		err = omap_aes_crypt_dma_start(dd);
+
+	if (err) {
+		omap_aes_gcm_finish_req(dd, err);
+		omap_aes_gcm_handle_queue(dd, NULL);
+	}
+
+	return ret;
+}
+
+static int omap_aes_gcm_crypt(struct aead_request *req, unsigned long mode)
+{
+	struct omap_aes_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct omap_aes_reqctx *rctx = aead_request_ctx(req);
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	unsigned int authlen = crypto_aead_authsize(aead);
+	struct omap_aes_dev *dd;
+	__be32 counter = cpu_to_be32(1);
+	int err;
+
+	memset(ctx->auth_tag, 0, sizeof(ctx->auth_tag));
+	memcpy(req->iv + 12, &counter, 4);
+
+	err = do_encrypt_iv(req, ctx->auth_tag);
+	if (err)
+		return err;
+
+	if (req->assoclen + req->cryptlen == 0) {
+		scatterwalk_map_and_copy(ctx->auth_tag, req->dst, 0, authlen,
+					 1);
+		return 0;
+	}
+
+	dd = omap_aes_find_dev(ctx);
+	if (!dd)
+		return -ENODEV;
+	rctx->mode = mode;
+
+	return omap_aes_gcm_handle_queue(dd, req);
+}
+
+int omap_aes_gcm_encrypt(struct aead_request *req)
+{
+	return omap_aes_gcm_crypt(req, FLAGS_ENCRYPT | FLAGS_GCM);
+}
+
+int omap_aes_gcm_decrypt(struct aead_request *req)
+{
+	return omap_aes_gcm_crypt(req, FLAGS_GCM);
+}
+
+int omap_aes_gcm_setkey(struct crypto_aead *tfm, const u8 *key,
+			unsigned int keylen)
+{
+	struct omap_aes_ctx *ctx = crypto_aead_ctx(tfm);
+
+	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
+	    keylen != AES_KEYSIZE_256)
+		return -EINVAL;
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index eba2314..d1b4813 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -36,157 +36,8 @@ 
 #include <linux/interrupt.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/aes.h>
-
-#define DST_MAXBURST			4
-#define DMA_MIN				(DST_MAXBURST * sizeof(u32))
-
-#define _calc_walked(inout) (dd->inout##_walk.offset - dd->inout##_sg->offset)
-
-/* OMAP TRM gives bitfields as start:end, where start is the higher bit
-   number. For example 7:0 */
-#define FLD_MASK(start, end)	(((1 << ((start) - (end) + 1)) - 1) << (end))
-#define FLD_VAL(val, start, end) (((val) << (end)) & FLD_MASK(start, end))
-
-#define AES_REG_KEY(dd, x)		((dd)->pdata->key_ofs - \
-						((x ^ 0x01) * 0x04))
-#define AES_REG_IV(dd, x)		((dd)->pdata->iv_ofs + ((x) * 0x04))
-
-#define AES_REG_CTRL(dd)		((dd)->pdata->ctrl_ofs)
-#define AES_REG_CTRL_CTR_WIDTH_MASK	GENMASK(8, 7)
-#define AES_REG_CTRL_CTR_WIDTH_32	0
-#define AES_REG_CTRL_CTR_WIDTH_64	BIT(7)
-#define AES_REG_CTRL_CTR_WIDTH_96	BIT(8)
-#define AES_REG_CTRL_CTR_WIDTH_128	GENMASK(8, 7)
-#define AES_REG_CTRL_CTR		BIT(6)
-#define AES_REG_CTRL_CBC		BIT(5)
-#define AES_REG_CTRL_KEY_SIZE		GENMASK(4, 3)
-#define AES_REG_CTRL_DIRECTION		BIT(2)
-#define AES_REG_CTRL_INPUT_READY	BIT(1)
-#define AES_REG_CTRL_OUTPUT_READY	BIT(0)
-#define AES_REG_CTRL_MASK		GENMASK(24, 2)
-
-#define AES_REG_DATA_N(dd, x)		((dd)->pdata->data_ofs + ((x) * 0x04))
-
-#define AES_REG_REV(dd)			((dd)->pdata->rev_ofs)
-
-#define AES_REG_MASK(dd)		((dd)->pdata->mask_ofs)
-#define AES_REG_MASK_SIDLE		BIT(6)
-#define AES_REG_MASK_START		BIT(5)
-#define AES_REG_MASK_DMA_OUT_EN		BIT(3)
-#define AES_REG_MASK_DMA_IN_EN		BIT(2)
-#define AES_REG_MASK_SOFTRESET		BIT(1)
-#define AES_REG_AUTOIDLE		BIT(0)
-
-#define AES_REG_LENGTH_N(x)		(0x54 + ((x) * 0x04))
-
-#define AES_REG_IRQ_STATUS(dd)         ((dd)->pdata->irq_status_ofs)
-#define AES_REG_IRQ_ENABLE(dd)         ((dd)->pdata->irq_enable_ofs)
-#define AES_REG_IRQ_DATA_IN            BIT(1)
-#define AES_REG_IRQ_DATA_OUT           BIT(2)
-#define DEFAULT_TIMEOUT		(5*HZ)
-
-#define FLAGS_MODE_MASK		0x000f
-#define FLAGS_ENCRYPT		BIT(0)
-#define FLAGS_CBC		BIT(1)
-#define FLAGS_GIV		BIT(2)
-#define FLAGS_CTR		BIT(3)
-
-#define FLAGS_INIT		BIT(4)
-#define FLAGS_FAST		BIT(5)
-#define FLAGS_BUSY		BIT(6)
-
-#define AES_BLOCK_WORDS		(AES_BLOCK_SIZE >> 2)
-
-struct omap_aes_ctx {
-	struct omap_aes_dev *dd;
-
-	int		keylen;
-	u32		key[AES_KEYSIZE_256 / sizeof(u32)];
-	unsigned long	flags;
-};
-
-struct omap_aes_reqctx {
-	unsigned long mode;
-};
-
-#define OMAP_AES_QUEUE_LENGTH	1
-#define OMAP_AES_CACHE_SIZE	0
-
-struct omap_aes_algs_info {
-	struct crypto_alg	*algs_list;
-	unsigned int		size;
-	unsigned int		registered;
-};
-
-struct omap_aes_pdata {
-	struct omap_aes_algs_info	*algs_info;
-	unsigned int	algs_info_size;
-
-	void		(*trigger)(struct omap_aes_dev *dd, int length);
-
-	u32		key_ofs;
-	u32		iv_ofs;
-	u32		ctrl_ofs;
-	u32		data_ofs;
-	u32		rev_ofs;
-	u32		mask_ofs;
-	u32             irq_enable_ofs;
-	u32             irq_status_ofs;
-
-	u32		dma_enable_in;
-	u32		dma_enable_out;
-	u32		dma_start;
-
-	u32		major_mask;
-	u32		major_shift;
-	u32		minor_mask;
-	u32		minor_shift;
-};
-
-struct omap_aes_dev {
-	struct list_head	list;
-	unsigned long		phys_base;
-	void __iomem		*io_base;
-	struct omap_aes_ctx	*ctx;
-	struct device		*dev;
-	unsigned long		flags;
-	int			err;
-
-	spinlock_t		lock;
-	struct crypto_queue	queue;
-
-	struct tasklet_struct	done_task;
-	struct tasklet_struct	queue_task;
-
-	struct ablkcipher_request	*req;
-
-	/*
-	 * total is used by PIO mode for book keeping so introduce
-	 * variable total_save as need it to calc page_order
-	 */
-	size_t				total;
-	size_t				total_save;
-
-	struct scatterlist		*in_sg;
-	struct scatterlist		*out_sg;
-
-	/* Buffers for copying for unaligned cases */
-	struct scatterlist		in_sgl;
-	struct scatterlist		out_sgl;
-	struct scatterlist		*orig_out;
-	int				sgs_copied;
-
-	struct scatter_walk		in_walk;
-	struct scatter_walk		out_walk;
-	int			dma_in;
-	struct dma_chan		*dma_lch_in;
-	int			dma_out;
-	struct dma_chan		*dma_lch_out;
-	int			in_sg_len;
-	int			out_sg_len;
-	int			pio_only;
-	const struct omap_aes_pdata	*pdata;
-};
+#include <crypto/internal/aead.h>
+#include "omap-aes.h"
 
 /* keep registered devices data here */
 static LIST_HEAD(dev_list);
@@ -202,7 +53,7 @@  static DEFINE_SPINLOCK(list_lock);
 	_read_ret;						\
 })
 #else
-static inline u32 omap_aes_read(struct omap_aes_dev *dd, u32 offset)
+inline u32 omap_aes_read(struct omap_aes_dev *dd, u32 offset)
 {
 	return __raw_readl(dd->io_base + offset);
 }
@@ -216,7 +67,7 @@  static inline u32 omap_aes_read(struct omap_aes_dev *dd, u32 offset)
 		__raw_writel(value, dd->io_base + offset);		\
 	} while (0)
 #else
-static inline void omap_aes_write(struct omap_aes_dev *dd, u32 offset,
+inline void omap_aes_write(struct omap_aes_dev *dd, u32 offset,
 				  u32 value)
 {
 	__raw_writel(value, dd->io_base + offset);
@@ -251,7 +102,7 @@  static int omap_aes_hw_init(struct omap_aes_dev *dd)
 	return 0;
 }
 
-static int omap_aes_write_ctrl(struct omap_aes_dev *dd)
+int omap_aes_write_ctrl(struct omap_aes_dev *dd)
 {
 	unsigned int key32;
 	int i, err;
@@ -263,7 +114,11 @@  static int omap_aes_write_ctrl(struct omap_aes_dev *dd)
 
 	key32 = dd->ctx->keylen / sizeof(u32);
 
-	/* it seems a key should always be set even if it has not changed */
+	/* RESET the key as previous HASH keys should not get affected*/
+	if (dd->flags & FLAGS_GCM)
+		for (i = 0; i < 0x40; i = i + 4)
+			omap_aes_write(dd, i, 0x0);
+
 	for (i = 0; i < key32; i++) {
 		omap_aes_write(dd, AES_REG_KEY(dd, i),
 			__le32_to_cpu(dd->ctx->key[i]));
@@ -272,12 +127,20 @@  static int omap_aes_write_ctrl(struct omap_aes_dev *dd)
 	if ((dd->flags & (FLAGS_CBC | FLAGS_CTR)) && dd->req->info)
 		omap_aes_write_n(dd, AES_REG_IV(dd, 0), dd->req->info, 4);
 
+	if ((dd->flags & (FLAGS_GCM)) && dd->aead_req->iv)
+		omap_aes_write_n(dd, AES_REG_IV(dd, 0),
+				 (u32 *)dd->aead_req->iv, 4);
+
 	val = FLD_VAL(((dd->ctx->keylen >> 3) - 1), 4, 3);
 	if (dd->flags & FLAGS_CBC)
 		val |= AES_REG_CTRL_CBC;
-	if (dd->flags & FLAGS_CTR)
+
+	if (dd->flags & (FLAGS_CTR | FLAGS_GCM))
 		val |= AES_REG_CTRL_CTR | AES_REG_CTRL_CTR_WIDTH_128;
 
+	if (dd->flags & FLAGS_GCM)
+		val |= AES_REG_CTRL_GCM;
+
 	if (dd->flags & FLAGS_ENCRYPT)
 		val |= AES_REG_CTRL_DIRECTION;
 
@@ -308,6 +171,8 @@  static void omap_aes_dma_trigger_omap4(struct omap_aes_dev *dd, int length)
 {
 	omap_aes_write(dd, AES_REG_LENGTH_N(0), length);
 	omap_aes_write(dd, AES_REG_LENGTH_N(1), 0);
+	if (dd->flags & FLAGS_GCM)
+		omap_aes_write(dd, AES_REG_A_LEN, dd->assoc_len);
 
 	omap_aes_dma_trigger_omap2(dd, length);
 }
@@ -322,7 +187,7 @@  static void omap_aes_dma_stop(struct omap_aes_dev *dd)
 	omap_aes_write_mask(dd, AES_REG_MASK(dd), 0, mask);
 }
 
-static struct omap_aes_dev *omap_aes_find_dev(struct omap_aes_ctx *ctx)
+struct omap_aes_dev *omap_aes_find_dev(struct omap_aes_ctx *ctx)
 {
 	struct omap_aes_dev *dd = NULL, *tmp;
 
@@ -410,12 +275,11 @@  static void sg_copy_buf(void *buf, struct scatterlist *sg,
 	scatterwalk_done(&walk, out, 0);
 }
 
-static int omap_aes_crypt_dma(struct crypto_tfm *tfm,
-		struct scatterlist *in_sg, struct scatterlist *out_sg,
-		int in_sg_len, int out_sg_len)
+static int omap_aes_crypt_dma(struct omap_aes_dev *dd,
+			      struct scatterlist *in_sg,
+			      struct scatterlist *out_sg,
+			      int in_sg_len, int out_sg_len)
 {
-	struct omap_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct omap_aes_dev *dd = ctx->dd;
 	struct dma_async_tx_descriptor *tx_in, *tx_out;
 	struct dma_slave_config cfg;
 	int ret;
@@ -476,7 +340,10 @@  static int omap_aes_crypt_dma(struct crypto_tfm *tfm,
 		return -EINVAL;
 	}
 
-	tx_out->callback = omap_aes_dma_out_callback;
+	if (dd->flags & FLAGS_GCM)
+		tx_out->callback = omap_aes_gcm_dma_out_callback;
+	else
+		tx_out->callback = omap_aes_dma_out_callback;
 	tx_out->callback_param = dd;
 
 	dmaengine_submit(tx_in);
@@ -491,10 +358,8 @@  static int omap_aes_crypt_dma(struct crypto_tfm *tfm,
 	return 0;
 }
 
-static int omap_aes_crypt_dma_start(struct omap_aes_dev *dd)
+int omap_aes_crypt_dma_start(struct omap_aes_dev *dd)
 {
-	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(
-					crypto_ablkcipher_reqtfm(dd->req));
 	int err;
 
 	pr_debug("total: %d\n", dd->total);
@@ -515,7 +380,7 @@  static int omap_aes_crypt_dma_start(struct omap_aes_dev *dd)
 		}
 	}
 
-	err = omap_aes_crypt_dma(tfm, dd->in_sg, dd->out_sg, dd->in_sg_len,
+	err = omap_aes_crypt_dma(dd, dd->in_sg, dd->out_sg, dd->in_sg_len,
 				 dd->out_sg_len);
 	if (err && !dd->pio_only) {
 		dma_unmap_sg(dd->dev, dd->in_sg, dd->in_sg_len, DMA_TO_DEVICE);
@@ -537,7 +402,7 @@  static void omap_aes_finish_req(struct omap_aes_dev *dd, int err)
 	req->base.complete(&req->base, err);
 }
 
-static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
+int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 {
 	int err = 0;
 
@@ -551,7 +416,7 @@  static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 	return err;
 }
 
-static int omap_aes_check_aligned(struct scatterlist *sg, int total)
+int omap_aes_check_aligned(struct scatterlist *sg, int total)
 {
 	int len = 0;
 
@@ -566,6 +431,9 @@  static int omap_aes_check_aligned(struct scatterlist *sg, int total)
 
 		len += sg->length;
 		sg = sg_next(sg);
+
+		if (len >= total)
+			break;
 	}
 
 	if (len != total)
@@ -594,9 +462,9 @@  static int omap_aes_copy_sgs(struct omap_aes_dev *dd)
 
 	sg_copy_buf(buf_in, dd->in_sg, 0, dd->total, 0);
 
-	sg_init_table(&dd->in_sgl, 1);
-	sg_set_buf(&dd->in_sgl, buf_in, total);
-	dd->in_sg = &dd->in_sgl;
+	sg_init_table(dd->in_sgl, 1);
+	sg_set_buf(dd->in_sgl, buf_in, total);
+	dd->in_sg = dd->in_sgl;
 
 	sg_init_table(&dd->out_sgl, 1);
 	sg_set_buf(&dd->out_sgl, buf_out, total);
@@ -665,6 +533,7 @@  static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 	ctx->dd = dd;
 
 	err = omap_aes_write_ctrl(dd);
+
 	if (!err)
 		err = omap_aes_crypt_dma_start(dd);
 	if (err) {
@@ -694,7 +563,7 @@  static void omap_aes_done_task(unsigned long data)
 	}
 
 	if (dd->sgs_copied) {
-		buf_in = sg_virt(&dd->in_sgl);
+		buf_in = sg_virt(dd->in_sgl);
 		buf_out = sg_virt(&dd->out_sgl);
 
 		sg_copy_buf(buf_out, dd->orig_out, 0, dd->total_save, 1);
@@ -811,6 +680,30 @@  static int omap_aes_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
+static int omap_aes_gcm_cra_init(struct crypto_aead *tfm)
+{
+	struct omap_aes_dev *dd = NULL;
+	int err;
+
+	/* Find AES device, currently picks the first device */
+	spin_lock_bh(&list_lock);
+	list_for_each_entry(dd, &dev_list, list) {
+		break;
+	}
+	spin_unlock_bh(&list_lock);
+
+	err = pm_runtime_get_sync(dd->dev);
+	if (err < 0) {
+		dev_err(dd->dev, "%s: failed to get_sync(%d)\n",
+			__func__, err);
+		return err;
+	}
+
+	tfm->reqsize = sizeof(struct omap_aes_reqctx);
+
+	return 0;
+}
+
 static void omap_aes_cra_exit(struct crypto_tfm *tfm)
 {
 	struct omap_aes_dev *dd = NULL;
@@ -825,6 +718,11 @@  static void omap_aes_cra_exit(struct crypto_tfm *tfm)
 	pm_runtime_put_sync(dd->dev);
 }
 
+static void omap_aes_gcm_cra_exit(struct crypto_aead *tfm)
+{
+	omap_aes_cra_exit(crypto_aead_tfm(tfm));
+}
+
 /* ********************** ALGS ************************************ */
 
 static struct crypto_alg algs_ecb_cbc[] = {
@@ -909,6 +807,34 @@  static struct omap_aes_algs_info omap_aes_algs_info_ecb_cbc[] = {
 	},
 };
 
+static struct aead_alg algs_aead_gcm[] = {
+{
+	.base = {
+		.cra_name		= "gcm(aes)",
+		.cra_driver_name	= "gcm-aes-omap",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_KERN_DRIVER_ONLY,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct omap_aes_ctx),
+		.cra_alignmask		= 0xf,
+		.cra_module		= THIS_MODULE,
+	},
+	.init		= omap_aes_gcm_cra_init,
+	.exit		= omap_aes_gcm_cra_exit,
+	.ivsize		= 12,
+	.maxauthsize	= AES_BLOCK_SIZE,
+	.setkey		= omap_aes_gcm_setkey,
+	.encrypt	= omap_aes_gcm_encrypt,
+	.decrypt	= omap_aes_gcm_decrypt,
+},
+};
+
+static struct omap_aes_aead_algs omap_aes_aead_info = {
+	.algs_list	=	algs_aead_gcm,
+	.size		=	ARRAY_SIZE(algs_aead_gcm),
+};
+
 static const struct omap_aes_pdata omap_aes_pdata_omap2 = {
 	.algs_info	= omap_aes_algs_info_ecb_cbc,
 	.algs_info_size	= ARRAY_SIZE(omap_aes_algs_info_ecb_cbc),
@@ -962,6 +888,7 @@  static const struct omap_aes_pdata omap_aes_pdata_omap3 = {
 static const struct omap_aes_pdata omap_aes_pdata_omap4 = {
 	.algs_info	= omap_aes_algs_info_ecb_cbc_ctr,
 	.algs_info_size	= ARRAY_SIZE(omap_aes_algs_info_ecb_cbc_ctr),
+	.aead_algs_info	= &omap_aes_aead_info,
 	.trigger	= omap_aes_dma_trigger_omap4,
 	.key_ofs	= 0x3c,
 	.iv_ofs		= 0x40,
@@ -1165,6 +1092,7 @@  static int omap_aes_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct omap_aes_dev *dd;
 	struct crypto_alg *algp;
+	struct aead_alg *aalg;
 	struct resource res;
 	int err = -ENOMEM, i, j, irq = -1;
 	u32 reg;
@@ -1179,6 +1107,7 @@  static int omap_aes_probe(struct platform_device *pdev)
 
 	spin_lock_init(&dd->lock);
 	crypto_init_queue(&dd->queue, OMAP_AES_QUEUE_LENGTH);
+	crypto_init_queue(&dd->aead_queue, OMAP_AES_QUEUE_LENGTH);
 
 	err = (dev->of_node) ? omap_aes_get_res_of(dd, dev, &res) :
 			       omap_aes_get_res_pdev(dd, pdev, &res);
@@ -1252,7 +1181,26 @@  static int omap_aes_probe(struct platform_device *pdev)
 		}
 	}
 
+	for (i = 0; i < dd->pdata->aead_algs_info->size; i++) {
+		aalg = &dd->pdata->aead_algs_info->algs_list[i];
+		algp = &aalg->base;
+
+		pr_debug("reg alg: %s\n", algp->cra_name);
+		INIT_LIST_HEAD(&algp->cra_list);
+
+		err = crypto_register_aead(aalg);
+		if (err)
+			goto err_aead_algs;
+
+		dd->pdata->aead_algs_info->registered++;
+	}
+
 	return 0;
+err_aead_algs:
+	for (i = dd->pdata->aead_algs_info->registered - 1; i >= 0; i--) {
+		aalg = &dd->pdata->aead_algs_info->algs_list[i];
+		crypto_unregister_aead(aalg);
+	}
 err_algs:
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
@@ -1274,6 +1222,7 @@  err_data:
 static int omap_aes_remove(struct platform_device *pdev)
 {
 	struct omap_aes_dev *dd = platform_get_drvdata(pdev);
+	struct aead_alg *aalg;
 	int i, j;
 
 	if (!dd)
@@ -1288,6 +1237,11 @@  static int omap_aes_remove(struct platform_device *pdev)
 			crypto_unregister_alg(
 					&dd->pdata->algs_info[i].algs_list[j]);
 
+	for (i = dd->pdata->aead_algs_info->size - 1; i >= 0; i--) {
+		aalg = &dd->pdata->aead_algs_info->algs_list[i];
+		crypto_unregister_aead(aalg);
+	}
+
 	tasklet_kill(&dd->done_task);
 	tasklet_kill(&dd->queue_task);
 	omap_aes_dma_cleanup(dd);
diff --git a/drivers/crypto/omap-aes.h b/drivers/crypto/omap-aes.h
new file mode 100644
index 0000000..f9f8c5f
--- /dev/null
+++ b/drivers/crypto/omap-aes.h
@@ -0,0 +1,212 @@ 
+/*
+ * Cryptographic API.
+ *
+ * Support for OMAP AES HW ACCELERATOR defines
+ *
+ * Copyright (c) 2015 Texas Instruments Incorporated
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ */
+#ifndef __OMAP_AES_REGS_H__
+#define __OMAP_AES_REGS_H__
+
+#define DST_MAXBURST			4
+#define DMA_MIN				(DST_MAXBURST * sizeof(u32))
+
+#define _calc_walked(inout) (dd->inout##_walk.offset - dd->inout##_sg->offset)
+
+/* OMAP TRM gives bitfields as start:end, where start is the higher bit
+   number. For example 7:0 */
+#define FLD_MASK(start, end)	(((1 << ((start) - (end) + 1)) - 1) << (end))
+#define FLD_VAL(val, start, end) (((val) << (end)) & FLD_MASK(start, end))
+
+#define AES_REG_KEY(dd, x)		((dd)->pdata->key_ofs - \
+						((x ^ 0x01) * 0x04))
+#define AES_REG_IV(dd, x)		((dd)->pdata->iv_ofs + ((x) * 0x04))
+
+#define AES_REG_CTRL(dd)		((dd)->pdata->ctrl_ofs)
+#define AES_REG_CTRL_CONTEXT_READY	BIT(31)
+#define AES_REG_CTRL_CTR_WIDTH_MASK	GENMASK(8, 7)
+#define AES_REG_CTRL_CTR_WIDTH_32	0
+#define AES_REG_CTRL_CTR_WIDTH_64	BIT(7)
+#define AES_REG_CTRL_CTR_WIDTH_96	BIT(8)
+#define AES_REG_CTRL_CTR_WIDTH_128	GENMASK(8, 7)
+#define AES_REG_CTRL_GCM		GENMASK(17, 16)
+#define AES_REG_CTRL_CTR		BIT(6)
+#define AES_REG_CTRL_CBC		BIT(5)
+#define AES_REG_CTRL_KEY_SIZE		GENMASK(4, 3)
+#define AES_REG_CTRL_DIRECTION		BIT(2)
+#define AES_REG_CTRL_INPUT_READY	BIT(1)
+#define AES_REG_CTRL_OUTPUT_READY	BIT(0)
+#define AES_REG_CTRL_MASK		GENMASK(24, 2)
+
+#define AES_REG_C_LEN_0			0x54
+#define AES_REG_C_LEN_1			0x58
+#define AES_REG_A_LEN			0x5C
+
+#define AES_REG_DATA_N(dd, x)		((dd)->pdata->data_ofs + ((x) * 0x04))
+#define AES_REG_TAG_N(dd, x)		(0x70 + ((x) * 0x04))
+
+#define AES_REG_REV(dd)			((dd)->pdata->rev_ofs)
+
+#define AES_REG_MASK(dd)		((dd)->pdata->mask_ofs)
+#define AES_REG_MASK_SIDLE		BIT(6)
+#define AES_REG_MASK_START		BIT(5)
+#define AES_REG_MASK_DMA_OUT_EN		BIT(3)
+#define AES_REG_MASK_DMA_IN_EN		BIT(2)
+#define AES_REG_MASK_SOFTRESET		BIT(1)
+#define AES_REG_AUTOIDLE		BIT(0)
+
+#define AES_REG_LENGTH_N(x)		(0x54 + ((x) * 0x04))
+
+#define AES_REG_IRQ_STATUS(dd)         ((dd)->pdata->irq_status_ofs)
+#define AES_REG_IRQ_ENABLE(dd)         ((dd)->pdata->irq_enable_ofs)
+#define AES_REG_IRQ_DATA_IN            BIT(1)
+#define AES_REG_IRQ_DATA_OUT           BIT(2)
+#define DEFAULT_TIMEOUT		(5 * HZ)
+
+#define FLAGS_MODE_MASK		0x001f
+#define FLAGS_ENCRYPT		BIT(0)
+#define FLAGS_CBC		BIT(1)
+#define FLAGS_GIV		BIT(2)
+#define FLAGS_CTR		BIT(3)
+#define FLAGS_GCM		BIT(4)
+
+#define FLAGS_INIT		BIT(5)
+#define FLAGS_FAST		BIT(6)
+#define FLAGS_BUSY		BIT(7)
+
+#define AES_ASSOC_DATA_COPIED	BIT(0)
+#define AES_IN_DATA_COPIED	BIT(1)
+#define AES_OUT_DATA_COPIED	BIT(2)
+
+#define AES_BLOCK_WORDS		(AES_BLOCK_SIZE >> 2)
+
+struct tcrypt_result {
+	struct completion completion;
+	int err;
+};
+
+struct omap_aes_ctx {
+	struct omap_aes_dev *dd;
+
+	int		keylen;
+	u32		key[AES_KEYSIZE_256 / sizeof(u32)];
+	u32		auth_tag[AES_BLOCK_SIZE / sizeof(u32)];
+	unsigned long	flags;
+};
+
+struct omap_aes_reqctx {
+	unsigned long mode;
+};
+
+#define OMAP_AES_QUEUE_LENGTH	1
+#define OMAP_AES_CACHE_SIZE	0
+
+struct omap_aes_algs_info {
+	struct crypto_alg	*algs_list;
+	unsigned int		size;
+	unsigned int		registered;
+};
+
+struct omap_aes_aead_algs {
+	struct aead_alg	*algs_list;
+	unsigned int	size;
+	unsigned int	registered;
+};
+
+struct omap_aes_pdata {
+	struct omap_aes_algs_info	*algs_info;
+	unsigned int	algs_info_size;
+	struct omap_aes_aead_algs	*aead_algs_info;
+
+	void (*trigger)(struct omap_aes_dev *dd, int length);
+
+	u32		key_ofs;
+	u32		iv_ofs;
+	u32		ctrl_ofs;
+	u32		data_ofs;
+	u32		rev_ofs;
+	u32		mask_ofs;
+	u32             irq_enable_ofs;
+	u32             irq_status_ofs;
+
+	u32		dma_enable_in;
+	u32		dma_enable_out;
+	u32		dma_start;
+
+	u32		major_mask;
+	u32		major_shift;
+	u32		minor_mask;
+	u32		minor_shift;
+};
+
+struct omap_aes_dev {
+	struct list_head	list;
+	unsigned long		phys_base;
+	void __iomem		*io_base;
+	struct omap_aes_ctx	*ctx;
+	struct device		*dev;
+	unsigned long		flags;
+	int			err;
+
+	/* Lock to acquire omap_aes_dd */
+	spinlock_t		lock;
+	struct crypto_queue	queue;
+	struct crypto_queue	aead_queue;
+
+	struct tasklet_struct	done_task;
+	struct tasklet_struct	queue_task;
+
+	struct ablkcipher_request	*req;
+	struct aead_request		*aead_req;
+
+	/*
+	 * total is used by PIO mode for book keeping so introduce
+	 * variable total_save as need it to calc page_order
+	 */
+	size_t				total;
+	size_t				total_save;
+	size_t				assoc_len;
+	size_t				authsize;
+
+	struct scatterlist		*in_sg;
+	struct scatterlist		*assoc_sg;
+	struct scatterlist		*out_sg;
+
+	/* Buffers for copying for unaligned cases */
+	struct scatterlist		in_sgl[2];
+	struct scatterlist		out_sgl;
+	struct scatterlist		aead_sgl[2];
+	struct scatterlist		*orig_out;
+	int				sgs_copied;
+
+	struct scatter_walk		in_walk;
+	struct scatter_walk		out_walk;
+	int			dma_in;
+	struct dma_chan		*dma_lch_in;
+	int			dma_out;
+	struct dma_chan		*dma_lch_out;
+	int			in_sg_len;
+	int			out_sg_len;
+	int			pio_only;
+	const struct omap_aes_pdata	*pdata;
+};
+
+u32 omap_aes_read(struct omap_aes_dev *dd, u32 offset);
+void omap_aes_write(struct omap_aes_dev *dd, u32 offset, u32 value);
+struct omap_aes_dev *omap_aes_find_dev(struct omap_aes_ctx *ctx);
+int omap_aes_gcm_setkey(struct crypto_aead *tfm, const u8 *key,
+			unsigned int keylen);
+int omap_aes_gcm_encrypt(struct aead_request *req);
+int omap_aes_gcm_decrypt(struct aead_request *req);
+int omap_aes_write_ctrl(struct omap_aes_dev *dd);
+int omap_aes_check_aligned(struct scatterlist *sg, int total);
+int omap_aes_crypt_dma_start(struct omap_aes_dev *dd);
+void omap_aes_gcm_dma_out_callback(void *data);
+int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd);
+
+#endif