cryptodev: add enqueue and dequeue callbacks

This patch adds APIs to add/remove callback functions on crypto
enqueue/dequeue burst. The callback function will be called for
each burst of crypto ops received/sent on a given crypto device
queue pair.

Signed-off-by: Abhinandan Gujjar <abhinandan.gujjar@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Akhil Goyal <akhil.goyal@nxp.com>

config/rte_config.h

@@ -62,6 +62,7 @@
 /* cryptodev defines */
 #define RTE_CRYPTO_MAX_DEVS 64
 #define RTE_CRYPTODEV_NAME_LEN 64
+#define RTE_CRYPTO_CALLBACKS 1
 
 /* compressdev defines */
 #define RTE_COMPRESS_MAX_DEVS 64

devtools/libabigail.abignore

@@ -11,3 +11,8 @@
 ; Explicit ignore for driver-only ABI
 [suppress_type]
         name = eth_dev_ops
+
+; Ignore fields inserted in cacheline boundary of rte_cryptodev
+[suppress_type]
+        name = rte_cryptodev
+        has_data_member_inserted_between = {0, 1023}

doc/guides/prog_guide/cryptodev_lib.rst

@@ -338,6 +338,50 @@ start of private data information. The offset is counted from the start of the
 rte_crypto_op including other crypto information such as the IVs (since there can
 be an IV also for authentication).
 
+User callback APIs
+~~~~~~~~~~~~~~~~~~
+The add APIs configures a user callback function to be called for each burst of crypto
+ops received/sent on a given crypto device queue pair. The return value is a pointer
+that can be used later to remove the callback using remove API. Application is expected
+to register a callback function of type ``rte_cryptodev_callback_fn``. Multiple callback
+functions can be added for a given queue pair. API does not restrict on maximum number of
+callbacks.
+
+Callbacks registered by application would not survive ``rte_cryptodev_configure`` as it
+reinitializes the callback list. It is user responsibility to remove all installed
+callbacks before calling ``rte_cryptodev_configure`` to avoid possible memory leakage.
+
+So, the application is expected to add user callback after ``rte_cryptodev_configure``.
+The callbacks can also be added at the runtime. These callbacks get executed when
+``rte_cryptodev_enqueue_burst``/``rte_cryptodev_dequeue_burst`` is called.
+
+.. code-block:: c
+
+	struct rte_cryptodev_cb *
+		rte_cryptodev_add_enq_callback(uint8_t dev_id, uint16_t qp_id,
+					       rte_cryptodev_callback_fn cb_fn,
+					       void *cb_arg);
+
+	struct rte_cryptodev_cb *
+		rte_cryptodev_add_deq_callback(uint8_t dev_id, uint16_t qp_id,
+					       rte_cryptodev_callback_fn cb_fn,
+					       void *cb_arg);
+
+	uint16_t (* rte_cryptodev_callback_fn)(uint16_t dev_id, uint16_t qp_id,
+					       struct rte_crypto_op **ops,
+					       uint16_t nb_ops, void *user_param);
+
+The remove API removes a callback function added by
+``rte_cryptodev_add_enq_callback``/``rte_cryptodev_add_deq_callback``.
+
+.. code-block:: c
+
+	int rte_cryptodev_remove_enq_callback(uint8_t dev_id, uint16_t qp_id,
+					      struct rte_cryptodev_cb *cb);
+
+	int rte_cryptodev_remove_deq_callback(uint8_t dev_id, uint16_t qp_id,
+					      struct rte_cryptodev_cb *cb);
+
 
 Enqueue / Dequeue Burst APIs
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~

doc/guides/rel_notes/release_21_02.rst

@@ -76,6 +76,12 @@ New Features
 
   * Added inner UDP/IPv4 support for VXLAN IPv4 GSO.
 
+* **Added enqueue & dequeue callback APIs for cryptodev library.**
+
+  Cryptodev library is added with enqueue & dequeue callback APIs to
+  enable applications to add/remove user callbacks which gets called
+  for every enqueue/dequeue operation.
+
 * **Updated the OCTEON TX2 crypto PMD.**
 
   * Updated the OCTEON TX2 crypto PMD lookaside protocol offload for IPsec with
@@ -119,6 +125,9 @@ API Changes
    Also, make sure to start the actual text at the margin.
    =======================================================
 
+* cryptodev: The structure ``rte_cryptodev`` has been updated with pointers
+  for adding enqueue and dequeue callbacks.
+
 
 ABI Changes
 -----------

lib/librte_cryptodev/meson.build

@@ -9,4 +9,4 @@ headers = files('rte_cryptodev.h',
 	'rte_crypto.h',
 	'rte_crypto_sym.h',
 	'rte_crypto_asym.h')
-deps += ['kvargs', 'mbuf']
+deps += ['kvargs', 'mbuf', 'rcu']

lib/librte_cryptodev/rte_cryptodev.c

@@ -448,6 +448,122 @@ rte_cryptodev_asym_xform_capability_check_modlen(
 	return 0;
 }
 
+/* spinlock for crypto device enq callbacks */
+static rte_spinlock_t rte_cryptodev_callback_lock = RTE_SPINLOCK_INITIALIZER;
+
+static void
+cryptodev_cb_cleanup(struct rte_cryptodev *dev)
+{
+	struct rte_cryptodev_cb_rcu *list;
+	struct rte_cryptodev_cb *cb, *next;
+	uint16_t qp_id;
+
+	if (dev->enq_cbs == NULL && dev->deq_cbs == NULL)
+		return;
+
+	for (qp_id = 0; qp_id < dev->data->nb_queue_pairs; qp_id++) {
+		list = &dev->enq_cbs[qp_id];
+		cb = list->next;
+		while (cb != NULL) {
+			next = cb->next;
+			rte_free(cb);
+			cb = next;
+		}
+
+		rte_free(list->qsbr);
+	}
+
+	for (qp_id = 0; qp_id < dev->data->nb_queue_pairs; qp_id++) {
+		list = &dev->deq_cbs[qp_id];
+		cb = list->next;
+		while (cb != NULL) {
+			next = cb->next;
+			rte_free(cb);
+			cb = next;
+		}
+
+		rte_free(list->qsbr);
+	}
+
+	rte_free(dev->enq_cbs);
+	dev->enq_cbs = NULL;
+	rte_free(dev->deq_cbs);
+	dev->deq_cbs = NULL;
+}
+
+static int
+cryptodev_cb_init(struct rte_cryptodev *dev)
+{
+	struct rte_cryptodev_cb_rcu *list;
+	struct rte_rcu_qsbr *qsbr;
+	uint16_t qp_id;
+	size_t size;
+
+	/* Max thread set to 1, as one DP thread accessing a queue-pair */
+	const uint32_t max_threads = 1;
+
+	dev->enq_cbs = rte_zmalloc(NULL,
+				   sizeof(struct rte_cryptodev_cb_rcu) *
+				   dev->data->nb_queue_pairs, 0);
+	if (dev->enq_cbs == NULL) {
+		CDEV_LOG_ERR("Failed to allocate memory for enq callbacks");
+		return -ENOMEM;
+	}
+
+	dev->deq_cbs = rte_zmalloc(NULL,
+				   sizeof(struct rte_cryptodev_cb_rcu) *
+				   dev->data->nb_queue_pairs, 0);
+	if (dev->deq_cbs == NULL) {
+		CDEV_LOG_ERR("Failed to allocate memory for deq callbacks");
+		rte_free(dev->enq_cbs);
+		return -ENOMEM;
+	}
+
+	/* Create RCU QSBR variable */
+	size = rte_rcu_qsbr_get_memsize(max_threads);
+
+	for (qp_id = 0; qp_id < dev->data->nb_queue_pairs; qp_id++) {
+		list = &dev->enq_cbs[qp_id];
+		qsbr = rte_zmalloc(NULL, size, RTE_CACHE_LINE_SIZE);
+		if (qsbr == NULL) {
+			CDEV_LOG_ERR("Failed to allocate memory for RCU on "
+				"queue_pair_id=%d", qp_id);
+			goto cb_init_err;
+		}
+
+		if (rte_rcu_qsbr_init(qsbr, max_threads)) {
+			CDEV_LOG_ERR("Failed to initialize for RCU on "
+				"queue_pair_id=%d", qp_id);
+			goto cb_init_err;
+		}
+
+		list->qsbr = qsbr;
+	}
+
+	for (qp_id = 0; qp_id < dev->data->nb_queue_pairs; qp_id++) {
+		list = &dev->deq_cbs[qp_id];
+		qsbr = rte_zmalloc(NULL, size, RTE_CACHE_LINE_SIZE);
+		if (qsbr == NULL) {
+			CDEV_LOG_ERR("Failed to allocate memory for RCU on "
+				"queue_pair_id=%d", qp_id);
+			goto cb_init_err;
+		}
+
+		if (rte_rcu_qsbr_init(qsbr, max_threads)) {
+			CDEV_LOG_ERR("Failed to initialize for RCU on "
+				"queue_pair_id=%d", qp_id);
+			goto cb_init_err;
+		}
+
+		list->qsbr = qsbr;
+	}
+
+	return 0;
+
+cb_init_err:
+	cryptodev_cb_cleanup(dev);
+	return -ENOMEM;
+}
 
 const char *
 rte_cryptodev_get_feature_name(uint64_t flag)
@@ -927,6 +1043,10 @@ rte_cryptodev_configure(uint8_t dev_id, struct rte_cryptodev_config *config)
 
 	RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_configure, -ENOTSUP);
 
+	rte_spinlock_lock(&rte_cryptodev_callback_lock);
+	cryptodev_cb_cleanup(dev);
+	rte_spinlock_unlock(&rte_cryptodev_callback_lock);
+
 	/* Setup new number of queue pairs and reconfigure device. */
 	diag = rte_cryptodev_queue_pairs_config(dev, config->nb_queue_pairs,
 			config->socket_id);
@@ -936,11 +1056,18 @@ rte_cryptodev_configure(uint8_t dev_id, struct rte_cryptodev_config *config)
 		return diag;
 	}
 
+	rte_spinlock_lock(&rte_cryptodev_callback_lock);
+	diag = cryptodev_cb_init(dev);
+	rte_spinlock_unlock(&rte_cryptodev_callback_lock);
+	if (diag) {
+		CDEV_LOG_ERR("Callback init failed for dev_id=%d", dev_id);
+		return diag;
+	}
+
 	rte_cryptodev_trace_configure(dev_id, config);
 	return (*dev->dev_ops->dev_configure)(dev, config);
 }
 
-
 int
 rte_cryptodev_start(uint8_t dev_id)
 {
@@ -1136,6 +1263,275 @@ rte_cryptodev_queue_pair_setup(uint8_t dev_id, uint16_t queue_pair_id,
 			socket_id);
 }
 
+struct rte_cryptodev_cb *
+rte_cryptodev_add_enq_callback(uint8_t dev_id,
+			       uint16_t qp_id,
+			       rte_cryptodev_callback_fn cb_fn,
+			       void *cb_arg)
+{
+	struct rte_cryptodev *dev;
+	struct rte_cryptodev_cb_rcu *list;
+	struct rte_cryptodev_cb *cb, *tail;
+
+	if (!cb_fn) {
+		CDEV_LOG_ERR("Callback is NULL on dev_id=%d", dev_id);
+		rte_errno = EINVAL;
+		return NULL;
+	}
+
+	if (!rte_cryptodev_pmd_is_valid_dev(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%d", dev_id);
+		rte_errno = ENODEV;
+		return NULL;
+	}
+
+	dev = &rte_crypto_devices[dev_id];
+	if (qp_id >= dev->data->nb_queue_pairs) {
+		CDEV_LOG_ERR("Invalid queue_pair_id=%d", qp_id);
+		rte_errno = ENODEV;
+		return NULL;
+	}
+
+	cb = rte_zmalloc(NULL, sizeof(*cb), 0);
+	if (cb == NULL) {
+		CDEV_LOG_ERR("Failed to allocate memory for callback on "
+			     "dev=%d, queue_pair_id=%d", dev_id, qp_id);
+		rte_errno = ENOMEM;
+		return NULL;
+	}
+
+	rte_spinlock_lock(&rte_cryptodev_callback_lock);
+
+	cb->fn = cb_fn;
+	cb->arg = cb_arg;
+
+	/* Add the callbacks in fifo order. */
+	list = &dev->enq_cbs[qp_id];
+	tail = list->next;
+
+	if (tail) {
+		while (tail->next)
+			tail = tail->next;
+		/* Stores to cb->fn and cb->param should complete before
+		 * cb is visible to data plane.
+		 */
+		__atomic_store_n(&tail->next, cb, __ATOMIC_RELEASE);
+	} else {
+		/* Stores to cb->fn and cb->param should complete before
+		 * cb is visible to data plane.
+		 */
+		__atomic_store_n(&list->next, cb, __ATOMIC_RELEASE);
+	}
+
+	rte_spinlock_unlock(&rte_cryptodev_callback_lock);
+
+	return cb;
+}
+
+int
+rte_cryptodev_remove_enq_callback(uint8_t dev_id,
+				  uint16_t qp_id,
+				  struct rte_cryptodev_cb *cb)
+{
+	struct rte_cryptodev *dev;
+	struct rte_cryptodev_cb **prev_cb, *curr_cb;
+	struct rte_cryptodev_cb_rcu *list;
+	int ret;
+
+	ret = -EINVAL;
+
+	if (!cb) {
+		CDEV_LOG_ERR("Callback is NULL");
+		return -EINVAL;
+	}
+
+	if (!rte_cryptodev_pmd_is_valid_dev(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%d", dev_id);
+		return -ENODEV;
+	}
+
+	dev = &rte_crypto_devices[dev_id];
+	if (qp_id >= dev->data->nb_queue_pairs) {
+		CDEV_LOG_ERR("Invalid queue_pair_id=%d", qp_id);
+		return -ENODEV;
+	}
+
+	rte_spinlock_lock(&rte_cryptodev_callback_lock);
+	if (dev->enq_cbs == NULL) {
+		CDEV_LOG_ERR("Callback not initialized");
+		goto cb_err;
+	}
+
+	list = &dev->enq_cbs[qp_id];
+	if (list == NULL) {
+		CDEV_LOG_ERR("Callback list is NULL");
+		goto cb_err;
+	}
+
+	if (list->qsbr == NULL) {
+		CDEV_LOG_ERR("Rcu qsbr is NULL");
+		goto cb_err;
+	}
+
+	prev_cb = &list->next;
+	for (; *prev_cb != NULL; prev_cb = &curr_cb->next) {
+		curr_cb = *prev_cb;
+		if (curr_cb == cb) {
+			/* Remove the user cb from the callback list. */
+			__atomic_store_n(prev_cb, curr_cb->next,
+				__ATOMIC_RELAXED);
+			ret = 0;
+			break;
+		}
+	}
+
+	if (!ret) {
+		/* Call sync with invalid thread id as this is part of
+		 * control plane API
+		 */
+		rte_rcu_qsbr_synchronize(list->qsbr, RTE_QSBR_THRID_INVALID);
+		rte_free(cb);
+	}
+
+cb_err:
+	rte_spinlock_unlock(&rte_cryptodev_callback_lock);
+	return ret;
+}
+
+struct rte_cryptodev_cb *
+rte_cryptodev_add_deq_callback(uint8_t dev_id,
+			       uint16_t qp_id,
+			       rte_cryptodev_callback_fn cb_fn,
+			       void *cb_arg)
+{
+	struct rte_cryptodev *dev;
+	struct rte_cryptodev_cb_rcu *list;
+	struct rte_cryptodev_cb *cb, *tail;
+
+	if (!cb_fn) {
+		CDEV_LOG_ERR("Callback is NULL on dev_id=%d", dev_id);
+		rte_errno = EINVAL;
+		return NULL;
+	}
+
+	if (!rte_cryptodev_pmd_is_valid_dev(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%d", dev_id);
+		rte_errno = ENODEV;
+		return NULL;
+	}
+
+	dev = &rte_crypto_devices[dev_id];
+	if (qp_id >= dev->data->nb_queue_pairs) {
+		CDEV_LOG_ERR("Invalid queue_pair_id=%d", qp_id);
+		rte_errno = ENODEV;
+		return NULL;
+	}
+
+	cb = rte_zmalloc(NULL, sizeof(*cb), 0);
+	if (cb == NULL) {
+		CDEV_LOG_ERR("Failed to allocate memory for callback on "
+			     "dev=%d, queue_pair_id=%d", dev_id, qp_id);
+		rte_errno = ENOMEM;
+		return NULL;
+	}
+
+	rte_spinlock_lock(&rte_cryptodev_callback_lock);
+
+	cb->fn = cb_fn;
+	cb->arg = cb_arg;
+
+	/* Add the callbacks in fifo order. */
+	list = &dev->deq_cbs[qp_id];
+	tail = list->next;
+
+	if (tail) {
+		while (tail->next)
+			tail = tail->next;
+		/* Stores to cb->fn and cb->param should complete before
+		 * cb is visible to data plane.
+		 */
+		__atomic_store_n(&tail->next, cb, __ATOMIC_RELEASE);
+	} else {
+		/* Stores to cb->fn and cb->param should complete before
+		 * cb is visible to data plane.
+		 */
+		__atomic_store_n(&list->next, cb, __ATOMIC_RELEASE);
+	}
+
+	rte_spinlock_unlock(&rte_cryptodev_callback_lock);
+
+	return cb;
+}
+
+int
+rte_cryptodev_remove_deq_callback(uint8_t dev_id,
+				  uint16_t qp_id,
+				  struct rte_cryptodev_cb *cb)
+{
+	struct rte_cryptodev *dev;
+	struct rte_cryptodev_cb **prev_cb, *curr_cb;
+	struct rte_cryptodev_cb_rcu *list;
+	int ret;
+
+	ret = -EINVAL;
+
+	if (!cb) {
+		CDEV_LOG_ERR("Callback is NULL");
+		return -EINVAL;
+	}
+
+	if (!rte_cryptodev_pmd_is_valid_dev(dev_id)) {
+		CDEV_LOG_ERR("Invalid dev_id=%d", dev_id);
+		return -ENODEV;
+	}
+
+	dev = &rte_crypto_devices[dev_id];
+	if (qp_id >= dev->data->nb_queue_pairs) {
+		CDEV_LOG_ERR("Invalid queue_pair_id=%d", qp_id);
+		return -ENODEV;
+	}
+
+	rte_spinlock_lock(&rte_cryptodev_callback_lock);
+	if (dev->enq_cbs == NULL) {
+		CDEV_LOG_ERR("Callback not initialized");
+		goto cb_err;
+	}
+
+	list = &dev->deq_cbs[qp_id];
+	if (list == NULL) {
+		CDEV_LOG_ERR("Callback list is NULL");
+		goto cb_err;
+	}
+
+	if (list->qsbr == NULL) {
+		CDEV_LOG_ERR("Rcu qsbr is NULL");
+		goto cb_err;
+	}
+
+	prev_cb = &list->next;
+	for (; *prev_cb != NULL; prev_cb = &curr_cb->next) {
+		curr_cb = *prev_cb;
+		if (curr_cb == cb) {
+			/* Remove the user cb from the callback list. */
+			__atomic_store_n(prev_cb, curr_cb->next,
+				__ATOMIC_RELAXED);
+			ret = 0;
+			break;
+		}
+	}
+
+	if (!ret) {
+		/* Call sync with invalid thread id as this is part of
+		 * control plane API
+		 */
+		rte_rcu_qsbr_synchronize(list->qsbr, RTE_QSBR_THRID_INVALID);
+		rte_free(cb);
+	}
+
+cb_err:
+	rte_spinlock_unlock(&rte_cryptodev_callback_lock);
+	return ret;
+}
 
 int
 rte_cryptodev_stats_get(uint8_t dev_id, struct rte_cryptodev_stats *stats)

lib/librte_cryptodev/rte_cryptodev.h

@@ -23,6 +23,7 @@ extern "C" {
 #include "rte_dev.h"
 #include <rte_common.h>
 #include <rte_config.h>
+#include <rte_rcu_qsbr.h>
 
 #include "rte_cryptodev_trace_fp.h"
 
@@ -522,6 +523,30 @@ struct rte_cryptodev_qp_conf {
 	/**< The mempool for creating sess private data in sessionless mode */
 };
 
+/**
+ * Function type used for processing crypto ops when enqueue/dequeue burst is
+ * called.
+ *
+ * The callback function is called on enqueue/dequeue burst immediately.
+ *
+ * @param	dev_id		The identifier of the device.
+ * @param	qp_id		The index of the queue pair on which ops are
+ *				enqueued/dequeued. The value must be in the
+ *				range [0, nb_queue_pairs - 1] previously
+ *				supplied to *rte_cryptodev_configure*.
+ * @param	ops		The address of an array of *nb_ops* pointers
+ *				to *rte_crypto_op* structures which contain
+ *				the crypto operations to be processed.
+ * @param	nb_ops		The number of operations to process.
+ * @param	user_param	The arbitrary user parameter passed in by the
+ *				application when the callback was originally
+ *				registered.
+ * @return			The number of ops to be enqueued to the
+ *				crypto device.
+ */
+typedef uint16_t (*rte_cryptodev_callback_fn)(uint16_t dev_id, uint16_t qp_id,
+		struct rte_crypto_op **ops, uint16_t nb_ops, void *user_param);
+
 /**
  * Typedef for application callback function to be registered by application
  * software for notification of device events
@@ -822,7 +847,6 @@ rte_cryptodev_callback_unregister(uint8_t dev_id,
 		enum rte_cryptodev_event_type event,
 		rte_cryptodev_cb_fn cb_fn, void *cb_arg);
 
-
 typedef uint16_t (*dequeue_pkt_burst_t)(void *qp,
 		struct rte_crypto_op **ops,	uint16_t nb_ops);
 /**< Dequeue processed packets from queue pair of a device. */
@@ -839,6 +863,30 @@ struct rte_cryptodev_callback;
 /** Structure to keep track of registered callbacks */
 TAILQ_HEAD(rte_cryptodev_cb_list, rte_cryptodev_callback);
 
+/**
+ * Structure used to hold information about the callbacks to be called for a
+ * queue pair on enqueue/dequeue.
+ */
+struct rte_cryptodev_cb {
+	struct rte_cryptodev_cb *next;
+	/**< Pointer to next callback */
+	rte_cryptodev_callback_fn fn;
+	/**< Pointer to callback function */
+	void *arg;
+	/**< Pointer to argument */
+};
+
+/**
+ * @internal
+ * Structure used to hold information about the RCU for a queue pair.
+ */
+struct rte_cryptodev_cb_rcu {
+	struct rte_cryptodev_cb *next;
+	/**< Pointer to next callback */
+	struct rte_rcu_qsbr *qsbr;
+	/**< RCU QSBR variable per queue pair */
+};
+
 /** The data structure associated with each crypto device. */
 struct rte_cryptodev {
 	dequeue_pkt_burst_t dequeue_burst;
@@ -867,6 +915,12 @@ struct rte_cryptodev {
 	__extension__
 	uint8_t attached : 1;
 	/**< Flag indicating the device is attached */
+
+	struct rte_cryptodev_cb_rcu *enq_cbs;
+	/**< User application callback for pre enqueue processing */
+
+	struct rte_cryptodev_cb_rcu *deq_cbs;
+	/**< User application callback for post dequeue processing */
 } __rte_cache_aligned;
 
 void *
@@ -945,10 +999,33 @@ rte_cryptodev_dequeue_burst(uint8_t dev_id, uint16_t qp_id,
 {
 	struct rte_cryptodev *dev = &rte_cryptodevs[dev_id];
 
+	rte_cryptodev_trace_dequeue_burst(dev_id, qp_id, (void **)ops, nb_ops);
 	nb_ops = (*dev->dequeue_burst)
 			(dev->data->queue_pairs[qp_id], ops, nb_ops);
+#ifdef RTE_CRYPTO_CALLBACKS
+	if (unlikely(dev->deq_cbs != NULL)) {
+		struct rte_cryptodev_cb_rcu *list;
+		struct rte_cryptodev_cb *cb;
 
-	rte_cryptodev_trace_dequeue_burst(dev_id, qp_id, (void **)ops, nb_ops);
+		/* __ATOMIC_RELEASE memory order was used when the
+		 * call back was inserted into the list.
+		 * Since there is a clear dependency between loading
+		 * cb and cb->fn/cb->next, __ATOMIC_ACQUIRE memory order is
+		 * not required.
+		 */
+		list = &dev->deq_cbs[qp_id];
+		rte_rcu_qsbr_thread_online(list->qsbr, 0);
+		cb = __atomic_load_n(&list->next, __ATOMIC_RELAXED);
+
+		while (cb != NULL) {
+			nb_ops = cb->fn(dev_id, qp_id, ops, nb_ops,
+					cb->arg);
+			cb = cb->next;
+		};
+
+		rte_rcu_qsbr_thread_offline(list->qsbr, 0);
+	}
+#endif
 	return nb_ops;
 }
 
@@ -989,6 +1066,31 @@ rte_cryptodev_enqueue_burst(uint8_t dev_id, uint16_t qp_id,
 {
 	struct rte_cryptodev *dev = &rte_cryptodevs[dev_id];
 
+#ifdef RTE_CRYPTO_CALLBACKS
+	if (unlikely(dev->enq_cbs != NULL)) {
+		struct rte_cryptodev_cb_rcu *list;
+		struct rte_cryptodev_cb *cb;
+
+		/* __ATOMIC_RELEASE memory order was used when the
+		 * call back was inserted into the list.
+		 * Since there is a clear dependency between loading
+		 * cb and cb->fn/cb->next, __ATOMIC_ACQUIRE memory order is
+		 * not required.
+		 */
+		list = &dev->enq_cbs[qp_id];
+		rte_rcu_qsbr_thread_online(list->qsbr, 0);
+		cb = __atomic_load_n(&list->next, __ATOMIC_RELAXED);
+
+		while (cb != NULL) {
+			nb_ops = cb->fn(dev_id, qp_id, ops, nb_ops,
+					cb->arg);
+			cb = cb->next;
+		};
+
+		rte_rcu_qsbr_thread_offline(list->qsbr, 0);
+	}
+#endif
+
 	rte_cryptodev_trace_enqueue_burst(dev_id, qp_id, (void **)ops, nb_ops);
 	return (*dev->enqueue_burst)(
 			dev->data->queue_pairs[qp_id], ops, nb_ops);
@@ -1730,6 +1832,144 @@ int
 rte_cryptodev_raw_dequeue_done(struct rte_crypto_raw_dp_ctx *ctx,
 		uint32_t n);
 
+/**
+ * Add a user callback for a given crypto device and queue pair which will be
+ * called on crypto ops enqueue.
+ *
+ * This API configures a function to be called for each burst of crypto ops
+ * received on a given crypto device queue pair. The return value is a pointer
+ * that can be used later to remove the callback using
+ * rte_cryptodev_remove_enq_callback().
+ *
+ * Callbacks registered by application would not survive
+ * rte_cryptodev_configure() as it reinitializes the callback list.
+ * It is user responsibility to remove all installed callbacks before
+ * calling rte_cryptodev_configure() to avoid possible memory leakage.
+ * Application is expected to call add API after rte_cryptodev_configure().
+ *
+ * Multiple functions can be registered per queue pair & they are called
+ * in the order they were added. The API does not restrict on maximum number
+ * of callbacks.
+ *
+ * @param	dev_id		The identifier of the device.
+ * @param	qp_id		The index of the queue pair on which ops are
+ *				to be enqueued for processing. The value
+ *				must be in the range [0, nb_queue_pairs - 1]
+ *				previously supplied to
+ *				*rte_cryptodev_configure*.
+ * @param	cb_fn		The callback function
+ * @param	cb_arg		A generic pointer parameter which will be passed
+ *				to each invocation of the callback function on
+ *				this crypto device and queue pair.
+ *
+ * @return
+ *  - NULL on error & rte_errno will contain the error code.
+ *  - On success, a pointer value which can later be used to remove the
+ *    callback.
+ */
+
+__rte_experimental
+struct rte_cryptodev_cb *
+rte_cryptodev_add_enq_callback(uint8_t dev_id,
+			       uint16_t qp_id,
+			       rte_cryptodev_callback_fn cb_fn,
+			       void *cb_arg);
+
+/**
+ * Remove a user callback function for given crypto device and queue pair.
+ *
+ * This function is used to remove enqueue callbacks that were added to a
+ * crypto device queue pair using rte_cryptodev_add_enq_callback().
+ *
+ *
+ *
+ * @param	dev_id		The identifier of the device.
+ * @param	qp_id		The index of the queue pair on which ops are
+ *				to be enqueued. The value must be in the
+ *				range [0, nb_queue_pairs - 1] previously
+ *				supplied to *rte_cryptodev_configure*.
+ * @param	cb		Pointer to user supplied callback created via
+ *				rte_cryptodev_add_enq_callback().
+ *
+ * @return
+ *   -  0: Success. Callback was removed.
+ *   - <0: The dev_id or the qp_id is out of range, or the callback
+ *         is NULL or not found for the crypto device queue pair.
+ */
+
+__rte_experimental
+int rte_cryptodev_remove_enq_callback(uint8_t dev_id,
+				      uint16_t qp_id,
+				      struct rte_cryptodev_cb *cb);
+
+/**
+ * Add a user callback for a given crypto device and queue pair which will be
+ * called on crypto ops dequeue.
+ *
+ * This API configures a function to be called for each burst of crypto ops
+ * received on a given crypto device queue pair. The return value is a pointer
+ * that can be used later to remove the callback using
+ * rte_cryptodev_remove_deq_callback().
+ *
+ * Callbacks registered by application would not survive
+ * rte_cryptodev_configure() as it reinitializes the callback list.
+ * It is user responsibility to remove all installed callbacks before
+ * calling rte_cryptodev_configure() to avoid possible memory leakage.
+ * Application is expected to call add API after rte_cryptodev_configure().
+ *
+ * Multiple functions can be registered per queue pair & they are called
+ * in the order they were added. The API does not restrict on maximum number
+ * of callbacks.
+ *
+ * @param	dev_id		The identifier of the device.
+ * @param	qp_id		The index of the queue pair on which ops are
+ *				to be dequeued. The value must be in the
+ *				range [0, nb_queue_pairs - 1] previously
+ *				supplied to *rte_cryptodev_configure*.
+ * @param	cb_fn		The callback function
+ * @param	cb_arg		A generic pointer parameter which will be passed
+ *				to each invocation of the callback function on
+ *				this crypto device and queue pair.
+ *
+ * @return
+ *   - NULL on error & rte_errno will contain the error code.
+ *   - On success, a pointer value which can later be used to remove the
+ *     callback.
+ */
+
+__rte_experimental
+struct rte_cryptodev_cb *
+rte_cryptodev_add_deq_callback(uint8_t dev_id,
+			       uint16_t qp_id,
+			       rte_cryptodev_callback_fn cb_fn,
+			       void *cb_arg);
+
+/**
+ * Remove a user callback function for given crypto device and queue pair.
+ *
+ * This function is used to remove dequeue callbacks that were added to a
+ * crypto device queue pair using rte_cryptodev_add_deq_callback().
+ *
+ *
+ *
+ * @param	dev_id		The identifier of the device.
+ * @param	qp_id		The index of the queue pair on which ops are
+ *				to be dequeued. The value must be in the
+ *				range [0, nb_queue_pairs - 1] previously
+ *				supplied to *rte_cryptodev_configure*.
+ * @param	cb		Pointer to user supplied callback created via
+ *				rte_cryptodev_add_deq_callback().
+ *
+ * @return
+ *   -  0: Success. Callback was removed.
+ *   - <0: The dev_id or the qp_id is out of range, or the callback
+ *         is NULL or not found for the crypto device queue pair.
+ */
+__rte_experimental
+int rte_cryptodev_remove_deq_callback(uint8_t dev_id,
+				      uint16_t qp_id,
+				      struct rte_cryptodev_cb *cb);
+
 #ifdef __cplusplus
 }
 #endif

lib/librte_cryptodev/version.map

@@ -109,4 +109,11 @@ EXPERIMENTAL {
 	rte_cryptodev_raw_enqueue;
 	rte_cryptodev_raw_enqueue_burst;
 	rte_cryptodev_raw_enqueue_done;
+
+	# added in 21.02
+	rte_cryptodev_add_deq_callback;
+	rte_cryptodev_add_enq_callback;
+	rte_cryptodev_remove_deq_callback;
+	rte_cryptodev_remove_enq_callback;
+
 };