[PATCH v3 0/2] crypto: engine - support for parallel and batch requests

[PATCH v3 0/2] crypto: engine - support for parallel and batch requests

[Iuliana Prodan]

Added support for executing multiple, independent or not, requests
for crypto engine. This is based on a callback, can_enqueue_more, which
asks the driver if the hardware has free space, to enqueue a new request.
If hardware supports batch requests, crypto-engine can handle this use-case
through do_batch_requests callback.

Since, these new features, cannot be supported by all hardware,
the crypto-engine framework is backward compatible:
- by using the crypto_engine_alloc_init function, to initialize
crypto-engine, the new callbacks are NULL and the engine will work
as before these changes;
- to support only multiple requests, in parallel, the can_enqueue_more
callback must be implemented in driver. On crypto_pump_requests, if
can_enqueue_more callback returns true, a new request is send
to hardware, until there is no space and the callback returns false.
- to support batch requests, do_batch_requests callback must be
implemented in driver, to execute a batch of requests. The link
between the requests, is expected to be done in driver, in
do_one_request(). 

Signed-off-by: Iuliana Prodan <iuliana.prodan@nxp.com>

---
Changes since V2:
- readded cur_req in crypto-engine, to keep, the exact behavior as before
these changes, if can_enqueue_more is not implemented: send requests to hardware,
_one-by-one_, on crypto_pump_requests, and complete it, on
crypto_finalize_request, and so on.
- do_batch_requests is available only with can_enqueue_more.

Changes since V1:
- changed the name of can_enqueue_hardware callback to can_enqueue_more, and
the argument of this callback to crypto_engine structure (for cases when more
than ore crypto-engine is used).
- added a new patch with support for batch requests.

Changes since V0 (RFC):
- removed max_no_req and no_req, as the number of request that can be
processed in parallel;
- added a new callback, can_enqueue_more, to check whether the hardware
can process a new request.

Iuliana Prodan (2):
  crypto: engine - support for parallel requests
  crypto: engine - support for batch requests

 crypto/crypto_engine.c  | 132 +++++++++++++++++++++++++++++++++++++-----------
 include/crypto/engine.h |  14 +++--
 2 files changed, 113 insertions(+), 33 deletions(-)

-- 
2.1.0

[PATCH v3 1/2] crypto: engine - support for parallel requests

[Iuliana Prodan]

Added support for executing multiple requests, in parallel,
for crypto engine.
A new callback is added, can_enqueue_more, which asks the
driver if the hardware has free space, to enqueue a new request.
The new crypto_engine_alloc_init_and_set function, initialize
crypto-engine, sets the maximum size for crypto-engine software
queue (not hardcoded anymore) and the can_enqueue_more callback.
On crypto_pump_requests, if can_enqueue_more callback returns true,
a new request is send to hardware, until there is no space and the
callback returns false.

If the new callback, can_enqueue_more, is not implemented the
crypto-engine will work as before - will send requests to hardware,
one-by-one, on crypto_pump_requests, and complete it, on
crypto_finalize_request, and so on.

Signed-off-by: Iuliana Prodan <iuliana.prodan@nxp.com>
---
 crypto/crypto_engine.c  | 116 +++++++++++++++++++++++++++++++++++-------------
 include/crypto/engine.h |  11 +++--
 2 files changed, 94 insertions(+), 33 deletions(-)

diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
index eb029ff..dc33249 100644
--- a/crypto/crypto_engine.c
+++ b/crypto/crypto_engine.c
@@ -22,32 +22,33 @@
  * @err: error number
  */
 static void crypto_finalize_request(struct crypto_engine *engine,
-			     struct crypto_async_request *req, int err)
+				    struct crypto_async_request *req, int err)
 {
 	unsigned long flags;
-	bool finalize_cur_req = false;
+	bool finalize_req = false;
 	int ret;
 	struct crypto_engine_ctx *enginectx;
 
 	spin_lock_irqsave(&engine->queue_lock, flags);
-	if (engine->cur_req == req)
-		finalize_cur_req = true;
+	/*
+	 * If hardware cannot enqueue more requests,
+	 * make sure we are completing the current request
+	 */
+	if (engine->can_enqueue_more || engine->cur_req == req) {
+		finalize_req = true;
+		engine->cur_req = NULL;
+	}
 	spin_unlock_irqrestore(&engine->queue_lock, flags);
 
-	if (finalize_cur_req) {
+	if (finalize_req) {
 		enginectx = crypto_tfm_ctx(req->tfm);
-		if (engine->cur_req_prepared &&
+		if (enginectx->op.prepare_request &&
 		    enginectx->op.unprepare_request) {
 			ret = enginectx->op.unprepare_request(engine, req);
 			if (ret)
 				dev_err(engine->dev, "failed to unprepare request\n");
 		}
-		spin_lock_irqsave(&engine->queue_lock, flags);
-		engine->cur_req = NULL;
-		engine->cur_req_prepared = false;
-		spin_unlock_irqrestore(&engine->queue_lock, flags);
 	}
-
 	req->complete(req, err);
 
 	kthread_queue_work(engine->kworker, &engine->pump_requests);
@@ -73,10 +74,6 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 
 	spin_lock_irqsave(&engine->queue_lock, flags);
 
-	/* Make sure we are not already running a request */
-	if (engine->cur_req)
-		goto out;
-
 	/* If another context is idling then defer */
 	if (engine->idling) {
 		kthread_queue_work(engine->kworker, &engine->pump_requests);
@@ -108,13 +105,33 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 		goto out;
 	}
 
+start_request:
+	/* If hardware is busy, do not send any request */
+	if (engine->can_enqueue_more) {
+		if (!engine->can_enqueue_more(engine))
+			goto out;
+	} else if (engine->cur_req) {
+		/*
+		 * If hardware cannot enqueue more requests,
+		 * make sure we are not already running a request
+		 */
+		goto out;
+	}
+
 	/* Get the fist request from the engine queue to handle */
 	backlog = crypto_get_backlog(&engine->queue);
 	async_req = crypto_dequeue_request(&engine->queue);
 	if (!async_req)
 		goto out;
 
-	engine->cur_req = async_req;
+	/*
+	 * If hardware cannot enqueue more requests,
+	 * keep track of the request we are processing now.
+	 * We'll need it on completion (crypto_finalize_request).
+	 */
+	if (!engine->can_enqueue_more)
+		engine->cur_req = async_req;
+
 	if (backlog)
 		backlog->complete(backlog, -EINPROGRESS);
 
@@ -130,7 +147,7 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 		ret = engine->prepare_crypt_hardware(engine);
 		if (ret) {
 			dev_err(engine->dev, "failed to prepare crypt hardware\n");
-			goto req_err;
+			goto req_err_2;
 		}
 	}
 
@@ -141,26 +158,38 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 		if (ret) {
 			dev_err(engine->dev, "failed to prepare request: %d\n",
 				ret);
-			goto req_err;
+			goto req_err_2;
 		}
-		engine->cur_req_prepared = true;
 	}
 	if (!enginectx->op.do_one_request) {
 		dev_err(engine->dev, "failed to do request\n");
 		ret = -EINVAL;
-		goto req_err;
+		goto req_err_1;
 	}
+
 	ret = enginectx->op.do_one_request(engine, async_req);
 	if (ret) {
 		dev_err(engine->dev, "Failed to do one request from queue: %d\n", ret);
-		goto req_err;
+		goto req_err_1;
 	}
-	return;
 
-req_err:
-	crypto_finalize_request(engine, async_req, ret);
-	return;
+	goto retry;
 
+req_err_1:
+	if (enginectx->op.unprepare_request) {
+		ret = enginectx->op.unprepare_request(engine, async_req);
+		if (ret)
+			dev_err(engine->dev, "failed to unprepare request\n");
+	}
+req_err_2:
+	async_req->complete(async_req, ret);
+
+retry:
+	if (engine->can_enqueue_more) {
+		spin_lock_irqsave(&engine->queue_lock, flags);
+		goto start_request;
+	}
+	return;
 out:
 	spin_unlock_irqrestore(&engine->queue_lock, flags);
 }
@@ -386,15 +415,26 @@ int crypto_engine_stop(struct crypto_engine *engine)
 EXPORT_SYMBOL_GPL(crypto_engine_stop);
 
 /**
- * crypto_engine_alloc_init - allocate crypto hardware engine structure and
- * initialize it.
+ * crypto_engine_alloc_init_and_set - allocate crypto hardware engine structure
+ * and initialize it by setting the maximum number of entries in the software
+ * crypto-engine queue.
  * @dev: the device attached with one hardware engine
+ * @cbk_can_enq: pointer to a callback function to be invoked when pumping
+ *               requests to check whether the hardware can process a new
+ *               request.
+ *               This has the form:
+ *               callback(struct crypto_engine *engine)
+ *               where:
+ *               @engine: the crypto engine structure.
  * @rt: whether this queue is set to run as a realtime task
+ * @qlen: maximum size of the crypto-engine queue
  *
  * This must be called from context that can sleep.
  * Return: the crypto engine structure on success, else NULL.
  */
-struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
+struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
+						       bool (*cbk_can_enq)(struct crypto_engine *engine),
+						       bool rt, int qlen)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO / 2 };
 	struct crypto_engine *engine;
@@ -411,12 +451,12 @@ struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
 	engine->running = false;
 	engine->busy = false;
 	engine->idling = false;
-	engine->cur_req_prepared = false;
 	engine->priv_data = dev;
+	engine->can_enqueue_more = cbk_can_enq;
 	snprintf(engine->name, sizeof(engine->name),
 		 "%s-engine", dev_name(dev));
 
-	crypto_init_queue(&engine->queue, CRYPTO_ENGINE_MAX_QLEN);
+	crypto_init_queue(&engine->queue, qlen);
 	spin_lock_init(&engine->queue_lock);
 
 	engine->kworker = kthread_create_worker(0, "%s", engine->name);
@@ -433,6 +473,22 @@ struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
 
 	return engine;
 }
+EXPORT_SYMBOL_GPL(crypto_engine_alloc_init_and_set);
+
+/**
+ * crypto_engine_alloc_init - allocate crypto hardware engine structure and
+ * initialize it.
+ * @dev: the device attached with one hardware engine
+ * @rt: whether this queue is set to run as a realtime task
+ *
+ * This must be called from context that can sleep.
+ * Return: the crypto engine structure on success, else NULL.
+ */
+struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
+{
+	return crypto_engine_alloc_init_and_set(dev, NULL, rt,
+						CRYPTO_ENGINE_MAX_QLEN);
+}
 EXPORT_SYMBOL_GPL(crypto_engine_alloc_init);
 
 /**
diff --git a/include/crypto/engine.h b/include/crypto/engine.h
index e29cd67..00d35703 100644
--- a/include/crypto/engine.h
+++ b/include/crypto/engine.h
@@ -24,7 +24,6 @@
  * @idling: the engine is entering idle state
  * @busy: request pump is busy
  * @running: the engine is on working
- * @cur_req_prepared: current request is prepared
  * @list: link with the global crypto engine list
  * @queue_lock: spinlock to syncronise access to request queue
  * @queue: the crypto queue of the engine
@@ -35,17 +34,19 @@
  * @unprepare_crypt_hardware: there are currently no more requests on the
  * queue so the subsystem notifies the driver that it may relax the
  * hardware by issuing this call
+ * @can_enqueue_more: callback to check whether the hardware can process
+ * a new request
  * @kworker: kthread worker struct for request pump
  * @pump_requests: work struct for scheduling work to the request pump
  * @priv_data: the engine private data
- * @cur_req: the current request which is on processing
+ * @cur_req: the current request which is on processing, in case the hardware
+ * doesn't support multiple requests (can_enqueue_more is not used).
  */
 struct crypto_engine {
 	char			name[ENGINE_NAME_LEN];
 	bool			idling;
 	bool			busy;
 	bool			running;
-	bool			cur_req_prepared;
 
 	struct list_head	list;
 	spinlock_t		queue_lock;
@@ -56,6 +57,7 @@ struct crypto_engine {
 
 	int (*prepare_crypt_hardware)(struct crypto_engine *engine);
 	int (*unprepare_crypt_hardware)(struct crypto_engine *engine);
+	bool (*can_enqueue_more)(struct crypto_engine *engine);
 
 	struct kthread_worker           *kworker;
 	struct kthread_work             pump_requests;
@@ -102,6 +104,9 @@ void crypto_finalize_skcipher_request(struct crypto_engine *engine,
 int crypto_engine_start(struct crypto_engine *engine);
 int crypto_engine_stop(struct crypto_engine *engine);
 struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt);
+struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
+						       bool (*cbk_can_enq)(struct crypto_engine *engine),
+						       bool rt, int qlen);
 int crypto_engine_exit(struct crypto_engine *engine);
 
 #endif /* _CRYPTO_ENGINE_H */
-- 
2.1.0

Re: [PATCH v3 1/2] crypto: engine - support for parallel requests

[Herbert Xu]

On Fri, Feb 07, 2020 at 02:36:13PM +0200, Iuliana Prodan wrote:
>
> +start_request:
> +	/* If hardware is busy, do not send any request */
> +	if (engine->can_enqueue_more) {
> +		if (!engine->can_enqueue_more(engine))
> +			goto out;

Instead of a driver callback I'd rather the driver called into
the engine telling it to stop/start, similar to how net drivers
work.

Thanks,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

Re: [PATCH v3 1/2] crypto: engine - support for parallel requests

[Iuliana Prodan]

On 2/13/2020 8:18 AM, Herbert Xu wrote:
> On Fri, Feb 07, 2020 at 02:36:13PM +0200, Iuliana Prodan wrote:
>>
>> +start_request:
>> +	/* If hardware is busy, do not send any request */
>> +	if (engine->can_enqueue_more) {
>> +		if (!engine->can_enqueue_more(engine))
>> +			goto out;
> 
> Instead of a driver callback I'd rather the driver called into
> the engine telling it to stop/start, similar to how net drivers
> work.
> 

Given your suggestion, I’m thinking of implementing do_one_request, in 
the driver, to return -IN_PROGRESS if the hw can enqueue more and -EBUSY 
if otherwise (solution 1). But, this implies to update all the drivers 
that use crypto-engine (something I wouldn’t mind doing, but I don’t 
have the hw to test it).

My current proposal keeps the backward compatibility of crypto-engine, 
so no need to change the other drivers. If they want to use multiple 
requests or batch requests, they can implement can_enqueue_more, 
respective do_batch_requests (solution 2).

Please, let me know how do you want me to proceed?  Solution 1 or 
solution 2, or… maybe I’ve missed something?

Thanks,
Iulia

Re: [PATCH v3 1/2] crypto: engine - support for parallel requests

[Herbert Xu]

On Fri, Feb 14, 2020 at 01:25:50AM +0000, Iuliana Prodan wrote:
> 
> Given your suggestion, I’m thinking of implementing do_one_request, in 
> the driver, to return -IN_PROGRESS if the hw can enqueue more and -EBUSY 
> if otherwise (solution 1). But, this implies to update all the drivers 
> that use crypto-engine (something I wouldn’t mind doing, but I don’t 
> have the hw to test it).

We could always maintain a legacy interface for existing drivers
until they are all converted.

Thanks,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

[PATCH v3 2/2] crypto: engine - support for batch requests

[Iuliana Prodan]

Added support for batch requests, per crypto engine.
A new callback is added, do_batch_requests, which executes a
batch of requests. This has the crypto_engine structure as argument
(for cases when more than one crypto-engine is used).
The crypto_engine_alloc_init_and_set function, initializes
crypto-engine, but also, sets the do_batch_requests callback.
On crypto_pump_requests, if do_batch_requests callback is
implemented in a driver, this will be executed. The link between
the requests will be done in driver, if possible.
do_batch_requests is available only if the hardware has support
for multiple request (if can_enqueue_more callback is implemented).

Signed-off-by: Iuliana Prodan <iuliana.prodan@nxp.com>
---
 crypto/crypto_engine.c  | 20 ++++++++++++++++++--
 include/crypto/engine.h |  3 +++
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
index dc33249..05f2895 100644
--- a/crypto/crypto_engine.c
+++ b/crypto/crypto_engine.c
@@ -192,6 +192,12 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 	return;
 out:
 	spin_unlock_irqrestore(&engine->queue_lock, flags);
+	if (engine->do_batch_requests) {
+		ret = engine->do_batch_requests(engine);
+		if (ret)
+			dev_err(engine->dev, "failed to do batch requests: %d\n",
+				ret);
+	}
 }
 
 static void crypto_pump_work(struct kthread_work *work)
@@ -426,6 +432,12 @@ EXPORT_SYMBOL_GPL(crypto_engine_stop);
  *               callback(struct crypto_engine *engine)
  *               where:
  *               @engine: the crypto engine structure.
+ * @cbk_do_batch: pointer to a callback function to be invoked when executing a
+ *                a batch of requests.
+ *                This has the form:
+ *                callback(struct crypto_engine *engine)
+ *                where:
+ *                @engine: the crypto engine structure.
  * @rt: whether this queue is set to run as a realtime task
  * @qlen: maximum size of the crypto-engine queue
  *
@@ -434,6 +446,7 @@ EXPORT_SYMBOL_GPL(crypto_engine_stop);
  */
 struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
 						       bool (*cbk_can_enq)(struct crypto_engine *engine),
+						       int (*cbk_do_batch)(struct crypto_engine *engine),
 						       bool rt, int qlen)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO / 2 };
@@ -452,7 +465,10 @@ struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
 	engine->busy = false;
 	engine->idling = false;
 	engine->priv_data = dev;
-	engine->can_enqueue_more = cbk_can_enq;
+	if (cbk_can_enq) {
+		engine->can_enqueue_more = cbk_can_enq;
+		engine->do_batch_requests = cbk_do_batch;
+	}
 	snprintf(engine->name, sizeof(engine->name),
 		 "%s-engine", dev_name(dev));
 
@@ -486,7 +502,7 @@ EXPORT_SYMBOL_GPL(crypto_engine_alloc_init_and_set);
  */
 struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
 {
-	return crypto_engine_alloc_init_and_set(dev, NULL, rt,
+	return crypto_engine_alloc_init_and_set(dev, NULL, NULL, rt,
 						CRYPTO_ENGINE_MAX_QLEN);
 }
 EXPORT_SYMBOL_GPL(crypto_engine_alloc_init);
diff --git a/include/crypto/engine.h b/include/crypto/engine.h
index 00d35703..019f884 100644
--- a/include/crypto/engine.h
+++ b/include/crypto/engine.h
@@ -34,6 +34,7 @@
  * @unprepare_crypt_hardware: there are currently no more requests on the
  * queue so the subsystem notifies the driver that it may relax the
  * hardware by issuing this call
+ * @do_batch_requests: execute a batch of requests
  * @can_enqueue_more: callback to check whether the hardware can process
  * a new request
  * @kworker: kthread worker struct for request pump
@@ -57,6 +58,7 @@ struct crypto_engine {
 
 	int (*prepare_crypt_hardware)(struct crypto_engine *engine);
 	int (*unprepare_crypt_hardware)(struct crypto_engine *engine);
+	int (*do_batch_requests)(struct crypto_engine *engine);
 	bool (*can_enqueue_more)(struct crypto_engine *engine);
 
 	struct kthread_worker           *kworker;
@@ -106,6 +108,7 @@ int crypto_engine_stop(struct crypto_engine *engine);
 struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt);
 struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
 						       bool (*cbk_can_enq)(struct crypto_engine *engine),
+						       int (*cbk_do_batch)(struct crypto_engine *engine),
 						       bool rt, int qlen);
 int crypto_engine_exit(struct crypto_engine *engine);
 
-- 
2.1.0