[PATCH v5 2/3] ethdev: add mbuf dynfield for incomplete IP reassembly

[Akhil Goyal <gakhil@marvell.com>]

Hardware IP reassembly may be incomplete for multiple reasons like
reassembly timeout reached, duplicate fragments, etc.
To save application cycles to process these packets again, a new
mbuf dynflag is added to show that the mbuf received is not
reassembled properly.

Now if this dynflag is set, application can retrieve corresponding
chain of mbufs using mbuf dynfield set by the PMD. Now, it will be
up to application to either drop those fragments or wait for more time.

Signed-off-by: Akhil Goyal <gakhil@marvell.com>
---
 lib/ethdev/ethdev_driver.h |  8 ++++++++
 lib/ethdev/rte_ethdev.c    | 28 ++++++++++++++++++++++++++++
 lib/ethdev/rte_ethdev.h    | 28 +++++++++++++++++++++++++++-
 lib/ethdev/version.map     |  1 +
 lib/mbuf/rte_mbuf_dyn.h    |  9 +++++++++
 5 files changed, 73 insertions(+), 1 deletion(-)

diff --git a/lib/ethdev/ethdev_driver.h b/lib/ethdev/ethdev_driver.h
index 4acf75781d..81be991191 100644
--- a/lib/ethdev/ethdev_driver.h
+++ b/lib/ethdev/ethdev_driver.h
@@ -1707,6 +1707,14 @@ int
 rte_eth_hairpin_queue_peer_unbind(uint16_t cur_port, uint16_t cur_queue,
 				  uint32_t direction);
 
+/**
+ * @internal
+ * Register mbuf dynamic field and flag for IP reassembly incomplete case.
+ */
+__rte_internal
+int
+rte_eth_ip_reassembly_dynfield_register(int *field_offset, int *flag);
+
 
 /*
  * Legacy ethdev API used internally by drivers.
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 6b37cffd07..a707f395c4 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -6570,6 +6570,34 @@ rte_eth_ip_reassembly_conf_set(uint16_t port_id,
 		       (*dev->dev_ops->ip_reassembly_conf_set)(dev, conf));
 }
 
+int
+rte_eth_ip_reassembly_dynfield_register(int *field_offset, int *flag_offset)
+{
+	static const struct rte_mbuf_dynfield field_desc = {
+		.name = RTE_MBUF_DYNFIELD_IP_REASSEMBLY_NAME,
+		.size = sizeof(rte_eth_ip_reassembly_dynfield_t),
+		.align = __alignof__(rte_eth_ip_reassembly_dynfield_t),
+	};
+	static const struct rte_mbuf_dynflag ip_reassembly_dynflag = {
+		.name = RTE_MBUF_DYNFLAG_IP_REASSEMBLY_INCOMPLETE_NAME,
+	};
+	int offset;
+
+	offset = rte_mbuf_dynfield_register(&field_desc);
+	if (offset < 0)
+		return -1;
+	if (field_offset != NULL)
+		*field_offset = offset;
+
+	offset = rte_mbuf_dynflag_register(&ip_reassembly_dynflag);
+	if (offset < 0)
+		return -1;
+	if (flag_offset != NULL)
+		*flag_offset = offset;
+
+	return 0;
+}
+
 RTE_LOG_REGISTER_DEFAULT(rte_eth_dev_logtype, INFO);
 
 RTE_INIT(ethdev_init_telemetry)
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index dd416fda37..b2c41ceb9a 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -5285,6 +5285,12 @@ int rte_eth_ip_reassembly_conf_get(uint16_t port_id,
  * configuration. The use of this API is mandatory to enable this feature and
  * should be called before rte_eth_dev_start().
  *
+ * In datapath, PMD cannot guarantee that IP reassembly is always successful.
+ * Hence, PMD shall register mbuf dynamic field and dynamic flag using
+ * rte_eth_ip_reassembly_dynfield_register() to denote incomplete IP reassembly.
+ * If dynfield is not successfully registered, error will be returned and
+ * IP reassembly offload cannnot be used.
+ *
  * @param port_id
  *   The port identifier of the device.
  * @param conf
@@ -5294,13 +5300,33 @@ int rte_eth_ip_reassembly_conf_get(uint16_t port_id,
  *   - (-ENODEV) if *port_id* invalid.
  *   - (-EIO) if device is removed.
  *   - (-EINVAL) if device is not configured or if device is already started or
- *               if *conf* passed is NULL.
+ *               if *conf* passed is NULL or if mbuf dynfield is not registered
+ *               successfully by the PMD.
  *   - (0) on success.
  */
 __rte_experimental
 int rte_eth_ip_reassembly_conf_set(uint16_t port_id,
 		const struct rte_eth_ip_reassembly_params *conf);
 
+/**
+ * In case of IP reassembly offload failure, packet will be updated with
+ * dynamic flag - RTE_MBUF_DYNFLAG_IP_REASSEMBLY_INCOMPLETE_NAME and packets
+ * will be returned without alteration.
+ * The application can retrieve the attached fragments using mbuf dynamic field
+ * RTE_MBUF_DYNFIELD_IP_REASSEMBLY_NAME.
+ */
+typedef struct {
+	/**
+	 * Next fragment packet. Application should fetch dynamic field of
+	 * each fragment until a NULL is received and nb_frags is 0.
+	 */
+	struct rte_mbuf *next_frag;
+	/** Time spent(in ms) by HW in waiting for further fragments. */
+	uint16_t time_spent;
+	/** Number of more fragments attached in mbuf dynamic fields. */
+	uint16_t nb_frags;
+} rte_eth_ip_reassembly_dynfield_t;
+
 
 #include <rte_ethdev_core.h>
 
diff --git a/lib/ethdev/version.map b/lib/ethdev/version.map
index e22c102818..b5499cd9b5 100644
--- a/lib/ethdev/version.map
+++ b/lib/ethdev/version.map
@@ -284,6 +284,7 @@ INTERNAL {
 	rte_eth_hairpin_queue_peer_bind;
 	rte_eth_hairpin_queue_peer_unbind;
 	rte_eth_hairpin_queue_peer_update;
+	rte_eth_ip_reassembly_dynfield_register;
 	rte_eth_representor_id_get;
 	rte_eth_switch_domain_alloc;
 	rte_eth_switch_domain_free;
diff --git a/lib/mbuf/rte_mbuf_dyn.h b/lib/mbuf/rte_mbuf_dyn.h
index 29abe8da53..1c948e996e 100644
--- a/lib/mbuf/rte_mbuf_dyn.h
+++ b/lib/mbuf/rte_mbuf_dyn.h
@@ -320,6 +320,15 @@ int rte_mbuf_dyn_rx_timestamp_register(int *field_offset, uint64_t *rx_flag);
  */
 int rte_mbuf_dyn_tx_timestamp_register(int *field_offset, uint64_t *tx_flag);
 
+/**
+ * For the PMDs which support IP reassembly of packets, PMD will updated the
+ * packet with RTE_MBUF_DYNFLAG_IP_REASSEMBLY_INCOMPLETE_NAME to denote that
+ * IP reassembly is incomplete and application can retrieve the packets back
+ * using RTE_MBUF_DYNFIELD_IP_REASSEMBLY_NAME.
+ */
+#define RTE_MBUF_DYNFIELD_IP_REASSEMBLY_NAME "rte_dynfield_ip_reassembly"
+#define RTE_MBUF_DYNFLAG_IP_REASSEMBLY_INCOMPLETE_NAME "rte_dynflag_ip_reassembly_incomplete"
+
 #ifdef __cplusplus
 }
 #endif
-- 
2.25.1