Currently, metadata can be set on egress path via mbuf tx_meatadata field
with PKT_TX_METADATA flag and RTE_FLOW_ITEM_TYPE_RX_META matches metadata.
This patch extends the usability.
1) RTE_FLOW_ACTION_TYPE_SET_META
When supporting multiple tables, Tx metadata can also be set by a rule and
matched by another rule. This new action allows metadata to be set as a
result of flow match.
2) Metadata on ingress
There's also need to support metadata on packet Rx. Metadata can be set by
SET_META action and matched by META item like Tx. The final value set by
the action will be delivered to application via mbuf metadata field with
PKT_RX_METADATA ol_flag.
For this purpose, mbuf->tx_metadata is moved as a separate new field and
renamed to 'metadata' to support both Rx and Tx metadata.
For loopback/hairpin packet, metadata set on Rx/Tx may or may not be
propagated to the other path depending on HW capability.
Signed-off-by: Yongseok Koh <ys...@mellanox.com>
---
app/test-pmd/cmdline_flow.c | 35 ++++++++++++
app/test-pmd/util.c | 2 +-
doc/guides/prog_guide/rte_flow.rst | 73 ++++++++++++++++++--------
doc/guides/rel_notes/release_19_08.rst | 10 ++++
drivers/net/mlx5/mlx5_rxtx.c | 12 ++---
drivers/net/mlx5/mlx5_rxtx_vec.c | 4 +-
drivers/net/mlx5/mlx5_rxtx_vec_neon.h | 2 +-
drivers/net/mlx5/mlx5_rxtx_vec_sse.h | 2 +-
lib/librte_ethdev/rte_ethdev.h | 5 ++
lib/librte_ethdev/rte_flow.h | 43 +++++++++++++--
lib/librte_mbuf/rte_mbuf.h | 21 ++++----
11 files changed, 161 insertions(+), 48 deletions(-)
diff --git a/app/test-pmd/cmdline_flow.c b/app/test-pmd/cmdline_flow.c
index 201bd9de56..eda5c5491f 100644
--- a/app/test-pmd/cmdline_flow.c
+++ b/app/test-pmd/cmdline_flow.c
@@ -272,6 +272,9 @@ enum index {
ACTION_SET_MAC_SRC_MAC_SRC,
ACTION_SET_MAC_DST,
ACTION_SET_MAC_DST_MAC_DST,
+ ACTION_SET_META,
+ ACTION_SET_META_DATA,
+ ACTION_SET_META_MASK,
};
/** Maximum size for pattern in struct rte_flow_item_raw. */
@@ -885,6 +888,7 @@ static const enum index next_action[] = {
ACTION_SET_TTL,
ACTION_SET_MAC_SRC,
ACTION_SET_MAC_DST,
+ ACTION_SET_META,
ZERO,
};
@@ -1047,6 +1051,13 @@ static const enum index action_set_mac_dst[] = {
ZERO,
};
+static const enum index action_set_meta[] = {
+ ACTION_SET_META_DATA,
+ ACTION_SET_META_MASK,
+ ACTION_NEXT,
+ ZERO,
+};
+
static int parse_init(struct context *, const struct token *,
const char *, unsigned int,
void *, unsigned int);
@@ -2854,6 +2865,30 @@ static const struct token token_list[] = {
(struct rte_flow_action_set_mac, mac_addr)),
.call = parse_vc_conf,
},
+ [ACTION_SET_META] = {
+ .name = "set_meta",
+ .help = "set metadata",
+ .priv = PRIV_ACTION(SET_META,
+ sizeof(struct rte_flow_action_set_meta)),
+ .next = NEXT(action_set_meta),
+ .call = parse_vc,
+ },
+ [ACTION_SET_META_DATA] = {
+ .name = "data",
+ .help = "metadata value",
+ .next = NEXT(action_set_meta, NEXT_ENTRY(UNSIGNED)),
+ .args = ARGS(ARGS_ENTRY_HTON
+ (struct rte_flow_action_set_meta, data)),
+ .call = parse_vc_conf,
+ },
+ [ACTION_SET_META_MASK] = {
+ .name = "mask",
+ .help = "mask for metadata value",
+ .next = NEXT(action_set_meta, NEXT_ENTRY(UNSIGNED)),
+ .args = ARGS(ARGS_ENTRY_HTON
+ (struct rte_flow_action_set_meta, mask)),
+ .call = parse_vc_conf,
+ },
};
/** Remove and return last entry from argument stack. */
diff --git a/app/test-pmd/util.c b/app/test-pmd/util.c
index a1164b7053..6ecc97351f 100644
--- a/app/test-pmd/util.c
+++ b/app/test-pmd/util.c
@@ -182,7 +182,7 @@ tx_pkt_set_md(uint16_t port_id, __rte_unused uint16_t queue,
* and set ol_flags accordingly.
*/
for (i = 0; i < nb_pkts; i++) {
- pkts[i]->tx_metadata = ports[port_id].tx_metadata;
+ pkts[i]->metadata = ports[port_id].tx_metadata;
pkts[i]->ol_flags |= PKT_TX_METADATA;
}
return nb_pkts;
diff --git a/doc/guides/prog_guide/rte_flow.rst
b/doc/guides/prog_guide/rte_flow.rst
index a34d012e55..5092f0074e 100644
--- a/doc/guides/prog_guide/rte_flow.rst
+++ b/doc/guides/prog_guide/rte_flow.rst
@@ -658,6 +658,32 @@ the physical device, with virtual groups in the PMD or not
at all.
| ``mask`` | ``id`` | zeroed to match any value |
+----------+----------+---------------------------+
+Item: ``META``
+^^^^^^^^^^^^^^^^^
+
+Matches 32 bit metadata item set.
+
+On egress, metadata can be set either by mbuf metadata field with
+PKT_TX_METADATA flag or ``SET_META`` action. On ingress, ``SET_META``
+action sets metadata for a packet and the metadata will be reported via
+``metadata`` field of ``rte_mbuf`` field with PKT_RX_METADATA flag.
+
+- Default ``mask`` matches the specified Rx metadata value.
+
+.. _table_rte_flow_item_meta:
+
+.. table:: META
+
+ +----------+----------+---------------------------------------+
+ | Field | Subfield | Value |
+ +==========+==========+=======================================+
+ | ``spec`` | ``data`` | 32 bit metadata value |
+ +----------+----------+---------------------------------------+
+ | ``last`` | ``data`` | upper range value |
+ +----------+----------+---------------------------------------+
+ | ``mask`` | ``data`` | bit-mask applies to "spec" and "last" |
+ +----------+----------+---------------------------------------+
+
Data matching item types
~~~~~~~~~~~~~~~~~~~~~~~~
@@ -1189,27 +1215,6 @@ Normally preceded by any of:
- `Item: ICMP6_ND_NS`_
- `Item: ICMP6_ND_OPT`_
-Item: ``META``
-^^^^^^^^^^^^^^
-
-Matches an application specific 32 bit metadata item.
-
-- Default ``mask`` matches the specified metadata value.
-
-.. _table_rte_flow_item_meta:
-
-.. table:: META
-
- +----------+----------+---------------------------------------+
- | Field | Subfield | Value |
- +==========+==========+=======================================+
- | ``spec`` | ``data`` | 32 bit metadata value |
- +----------+--------------------------------------------------+
- | ``last`` | ``data`` | upper range value |
- +----------+----------+---------------------------------------+
- | ``mask`` | ``data`` | bit-mask applies to "spec" and "last" |
- +----------+----------+---------------------------------------+
-
Actions
~~~~~~~
@@ -2345,6 +2350,32 @@ Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be
returned.
| ``mac_addr`` | MAC address |
+--------------+---------------+
+Action: ``SET_META``
+^^^^^^^^^^^^^^^^^^^^^^^
+
+Set metadata. Item ``META`` matches metadata.
+
+Metadata set by mbuf metadata field with PKT_TX_METADATA flag on egress will be
+overridden by this action. On ingress, the metadata will be carried by mbuf
+metadata field with PKT_RX_METADATA flag if set.
+
+Altering partial bits is supported with ``mask``. For bits which have never
been
+set, unpredictable value will be seen depending on driver implementation. For
+loopback/hairpin packet, metadata set on Rx/Tx may or may not be propagated to
+the other path depending on HW capability.
+
+.. _table_rte_flow_action_set_meta:
+
+.. table:: SET_META
+
+ +----------+----------------------------+
+ | Field | Value |
+ +==========+============================+
+ | ``data`` | 32 bit metadata value |
+ +----------+----------------------------+
+ | ``mask`` | bit-mask applies to "data" |
+ +----------+----------------------------+
+
Negative types
~~~~~~~~~~~~~~
diff --git a/doc/guides/rel_notes/release_19_08.rst
b/doc/guides/rel_notes/release_19_08.rst
index 223479c6d4..e087266da0 100644
--- a/doc/guides/rel_notes/release_19_08.rst
+++ b/doc/guides/rel_notes/release_19_08.rst
@@ -68,6 +68,16 @@ New Features
rte_rand_max() which supplies unbiased, bounded pseudo-random
numbers.
+* **Extended metadata support in rte_flow.**
+
+ Flow metadata is extended to both Rx and Tx.
+
+ * ``tx_metadata`` field of ``rte_mbuf`` has been moved to an independent
+ field and renamed as ``metadata``.
+ * Tx metadata can also be set by SET_META action of rte_flow.
+ * Rx metadata is delivered to host via ``metadata`` field of ``rte_mbuf``
+ with PKT_RX_METADATA.
+
* **Updated the bnxt PMD.**
Updated the bnxt PMD. The major enhancements include:
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index c1dc8c4e17..4b23a0176d 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -784,8 +784,7 @@ mlx5_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts,
uint16_t pkts_n)
txq_mbuf_to_swp(txq, buf, (uint8_t *)&swp_offsets, &swp_types);
raw = ((uint8_t *)(uintptr_t)wqe) + 2 * MLX5_WQE_DWORD_SIZE;
/* Copy metadata from mbuf if valid */
- metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
- 0;
+ metadata = buf->ol_flags & PKT_TX_METADATA ? buf->metadata : 0;
/* Replace the Ethernet type by the VLAN if necessary. */
if (buf->ol_flags & PKT_TX_VLAN_PKT) {
uint32_t vlan = rte_cpu_to_be_32(0x81000000 |
@@ -1193,8 +1192,7 @@ mlx5_tx_burst_mpw(void *dpdk_txq, struct rte_mbuf **pkts,
uint16_t pkts_n)
--pkts_n;
cs_flags = txq_ol_cksum_to_cs(buf);
/* Copy metadata from mbuf if valid */
- metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
- 0;
+ metadata = buf->ol_flags & PKT_TX_METADATA ? buf->metadata : 0;
/* Retrieve packet information. */
length = PKT_LEN(buf);
assert(length);
@@ -1430,8 +1428,7 @@ mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf
**pkts,
max_wqe = (1u << txq->wqe_n) - (txq->wqe_ci - txq->wqe_pi);
cs_flags = txq_ol_cksum_to_cs(buf);
/* Copy metadata from mbuf if valid */
- metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
- 0;
+ metadata = buf->ol_flags & PKT_TX_METADATA ? buf->metadata : 0;
/* Retrieve packet information. */
length = PKT_LEN(buf);
/* Start new session if packet differs. */
@@ -1715,8 +1712,7 @@ txq_burst_empw(struct mlx5_txq_data *txq, struct rte_mbuf
**pkts,
break;
cs_flags = txq_ol_cksum_to_cs(buf);
/* Copy metadata from mbuf if valid */
- metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
- 0;
+ metadata = buf->ol_flags & PKT_TX_METADATA ? buf->metadata : 0;
/* Retrieve packet information. */
length = PKT_LEN(buf);
/* Start new session if:
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.c b/drivers/net/mlx5/mlx5_rxtx_vec.c
index 073044f6d1..b8e042c5d2 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec.c
+++ b/drivers/net/mlx5/mlx5_rxtx_vec.c
@@ -71,7 +71,7 @@ txq_calc_offload(struct rte_mbuf **pkts, uint16_t pkts_n,
uint8_t *cs_flags,
if (!pkts_n)
return 0;
p0_metadata = pkts[0]->ol_flags & PKT_TX_METADATA ?
- pkts[0]->tx_metadata : 0;
+ pkts[0]->metadata : 0;
/* Count the number of packets having same offload parameters. */
for (pos = 1; pos < pkts_n; ++pos) {
/* Check if packet has same checksum flags. */
@@ -81,7 +81,7 @@ txq_calc_offload(struct rte_mbuf **pkts, uint16_t pkts_n,
uint8_t *cs_flags,
/* Check if packet has same metadata. */
if (txq_offloads & DEV_TX_OFFLOAD_MATCH_METADATA) {
pn_metadata = pkts[pos]->ol_flags & PKT_TX_METADATA ?
- pkts[pos]->tx_metadata : 0;
+ pkts[pos]->metadata : 0;
if (pn_metadata != p0_metadata)
break;
}
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
index 1c7e3b444a..900cd9db43 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
@@ -131,7 +131,7 @@ txq_scatter_v(struct mlx5_txq_data *txq, struct rte_mbuf
**pkts,
uint8x16_t ctrl;
rte_be32_t metadata =
metadata_ol && (buf->ol_flags & PKT_TX_METADATA) ?
- buf->tx_metadata : 0;
+ buf->metadata : 0;
assert(segs_n);
max_elts = elts_n - (elts_head - txq->elts_tail);
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
index 503ca0f6ad..df7e22b9b9 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
@@ -129,7 +129,7 @@ txq_scatter_v(struct mlx5_txq_data *txq, struct rte_mbuf
**pkts,
__m128i ctrl;
rte_be32_t metadata =
metadata_ol && (buf->ol_flags & PKT_TX_METADATA) ?
- buf->tx_metadata : 0;
+ buf->metadata : 0;
assert(segs_n);
max_elts = elts_n - (elts_head - txq->elts_tail);
diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib/librte_ethdev/rte_ethdev.h
index c85212649c..ee0707e2d8 100644
--- a/lib/librte_ethdev/rte_ethdev.h
+++ b/lib/librte_ethdev/rte_ethdev.h
@@ -1011,6 +1011,11 @@ struct rte_eth_conf {
#define DEV_RX_OFFLOAD_KEEP_CRC 0x00010000
#define DEV_RX_OFFLOAD_SCTP_CKSUM 0x00020000
#define DEV_RX_OFFLOAD_OUTER_UDP_CKSUM 0x00040000
+/**
+ * Device supports match on metadata Rx offload.
+ * Driver sets PKT_RX_METADATA and mbuf metadata field.
+ */
+#define DEV_RX_OFFLOAD_MATCH_METADATA 0x00080000
#define DEV_RX_OFFLOAD_CHECKSUM (DEV_RX_OFFLOAD_IPV4_CKSUM | \
DEV_RX_OFFLOAD_UDP_CKSUM | \
diff --git a/lib/librte_ethdev/rte_flow.h b/lib/librte_ethdev/rte_flow.h
index f3a8fb103f..cda8628183 100644
--- a/lib/librte_ethdev/rte_flow.h
+++ b/lib/librte_ethdev/rte_flow.h
@@ -417,7 +417,8 @@ enum rte_flow_item_type {
/**
* [META]
*
- * Matches a metadata value specified in mbuf metadata field.
+ * Matches a metadata value.
+ *
* See struct rte_flow_item_meta.
*/
RTE_FLOW_ITEM_TYPE_META,
@@ -1164,9 +1165,16 @@ rte_flow_item_icmp6_nd_opt_tla_eth_mask = {
#endif
/**
- * RTE_FLOW_ITEM_TYPE_META.
+ * @warning
+ * @b EXPERIMENTAL: this structure may change without prior notice
*
- * Matches a specified metadata value.
+ * RTE_FLOW_ITEM_TYPE_META
+ *
+ * Matches a specified metadata value. On egress, metadata can be set either by
+ * mbuf metadata field with PKT_TX_METADATA flag or
+ * RTE_FLOW_ACTION_TYPE_SET_META. On ingress, RTE_FLOW_ACTION_TYPE_SET_META
sets
+ * metadata for a packet and the metadata will be reported via mbuf metadata
+ * field with PKT_RX_METADATA flag.
*/
struct rte_flow_item_meta {
rte_be32_t data;
@@ -1650,6 +1658,13 @@ enum rte_flow_action_type {
* See struct rte_flow_action_set_mac.
*/
RTE_FLOW_ACTION_TYPE_SET_MAC_DST,
+
+ /**
+ * Set metadata on ingress or egress path.
+ *
+ * See struct rte_flow_action_set_meta.
+ */
+ RTE_FLOW_ACTION_TYPE_SET_META,
};
/**
@@ -2131,6 +2146,28 @@ struct rte_flow_action_set_mac {
uint8_t mac_addr[RTE_ETHER_ADDR_LEN];
};
+/**
+ * @warning
+ * @b EXPERIMENTAL: this structure may change without prior notice
+ *
+ * RTE_FLOW_ACTION_TYPE_SET_META
+ *
+ * Set metadata. Metadata set by mbuf metadata field with PKT_TX_METADATA flag
+ * on egress will be overridden by this action. On ingress, the metadata will
be
+ * carried by mbuf metadata field with PKT_RX_METADATA flag if set.
+ *
+ * Altering partial bits is supported with mask. For bits which have never been
+ * set, unpredictable value will be seen depending on driver implementation.
For
+ * loopback/hairpin packet, metadata set on Rx/Tx may or may not be propagated
+ * to the other path depending on HW capability.
+ *
+ * RTE_FLOW_ITEM_TYPE_META matches metadata.
+ */
+struct rte_flow_action_set_meta {
+ rte_be32_t data;
+ rte_be32_t mask;
+};
+
/*
* Definition of a single action.
*
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index 9542488554..ba2da874f5 100644
--- a/lib/librte_mbuf/rte_mbuf.h
+++ b/lib/librte_mbuf/rte_mbuf.h
@@ -200,6 +200,11 @@ extern "C" {
/* add new RX flags here */
+/**
+ * Indicate that mbuf has metadata from device.
+ */
+#define PKT_RX_METADATA (1ULL << 23)
+
/* add new TX flags here */
/**
@@ -648,17 +653,6 @@ struct rte_mbuf {
/**< User defined tags. See rte_distributor_process() */
uint32_t usr;
} hash; /**< hash information */
- struct {
- /**
- * Application specific metadata value
- * for egress flow rule match.
- * Valid if PKT_TX_METADATA is set.
- * Located here to allow conjunct use
- * with hash.sched.hi.
- */
- uint32_t tx_metadata;
- uint32_t reserved;
- };
};
/** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ is set. */
@@ -727,6 +721,11 @@ struct rte_mbuf {
*/
struct rte_mbuf_ext_shared_info *shinfo;
+ /** Application specific metadata value for flow rule match.
+ * Valid if PKT_RX_METADATA or PKT_TX_METADATA is set.
+ */
+ uint32_t metadata;
+
} __rte_cache_aligned;
/**
--
2.21.0
