Tunnel Offload API provides hardware independent, unified model
to offload tunneled traffic. Key model elements are:
- apply matches to both outer and inner packet headers
during entire offload procedure;
- restore outer header of partially offloaded packet;
- model is implemented as a set of helper functions.
Implementation details:
* Create application tunnel:
flow tunnel <port> type <tunnel type>
On success, the command creates application tunnel object and returns
the tunnel descriptor. Tunnel descriptor is used in subsequent flow
creation commands to reference the tunnel.
* Create tunnel steering flow rule:
tunnel_set <tunnel descriptor> parameter used with steering rule
template.
* Create tunnel matching flow rule:
tunnel_match <tunnel descriptor> used with matching rule template.
* If tunnel steering rule was offloaded, outer header of a partially
offloaded packet is restored after miss.
Example:
test packet=
<Ether dst=24:8a:07:8d:ae:d6 src=50:6b:4b:cc:fc:e2 type=IPv4 |
<IP version=4 ihl=5 proto=udp src=1.1.1.1 dst=1.1.1.10 |
<UDP sport=4789 dport=4789 len=58 chksum=0x7f7b |
<VXLAN NextProtocol=Ethernet vni=0x0 |
<Ether dst=24:aa:aa:aa:aa:d6 src=50:bb:bb:bb:bb:e2 type=IPv4 |
<IP version=4 ihl=5 proto=icmp src=2.2.2.2 dst=2.2.2.200 |
<ICMP type=echo-request code=0 chksum=0xf7ff id=0x0 seq=0x0 |>>>>>>>
>>> len(packet)
92
testpmd> flow flush 0
testpmd> port 0/queue 0: received 1 packets
src=50:6B:4B:CC:FC:E2 - dst=24:8A:07:8D:AE:D6 - type=0x0800 -
length=92
testpmd> flow tunnel 0 type vxlan
port 0: flow tunnel #1 type vxlan
testpmd> flow create 0 ingress group 0 tunnel_set 1
pattern eth /ipv4 / udp dst is 4789 / vxlan / end
actions jump group 0 / end
Flow rule #0 created
testpmd> port 0/queue 0: received 1 packets
tunnel restore info: - vxlan tunnel - outer header present # <--
src=50:6B:4B:CC:FC:E2 - dst=24:8A:07:8D:AE:D6 - type=0x0800 -
length=92
testpmd> flow create 0 ingress group 0 tunnel_match 1
pattern eth / ipv4 / udp dst is 4789 / vxlan / eth / ipv4 /
end
actions set_mac_dst mac_addr 02:CA:FE:CA:FA:80 /
queue index 0 / end
Flow rule #1 created
testpmd> port 0/queue 0: received 1 packets
src=50:BB:BB:BB:BB:E2 - dst=02:CA:FE:CA:FA:80 - type=0x0800 -
length=42
TODO: add tunnel destruction command.
Signed-off-by: Gregory Etelson <getel...@nvidia.com>
---
v2:
* introduce testpmd support for tunnel offload API
---
app/test-pmd/cmdline_flow.c | 102 ++++++++++++++++++++++++-
app/test-pmd/config.c | 147 +++++++++++++++++++++++++++++++++++-
app/test-pmd/testpmd.c | 5 +-
app/test-pmd/testpmd.h | 27 ++++++-
app/test-pmd/util.c | 30 +++++++-
5 files changed, 302 insertions(+), 9 deletions(-)
diff --git a/app/test-pmd/cmdline_flow.c b/app/test-pmd/cmdline_flow.c
index 6263d307ed..f0a7a4a9ea 100644
--- a/app/test-pmd/cmdline_flow.c
+++ b/app/test-pmd/cmdline_flow.c
@@ -69,6 +69,10 @@ enum index {
LIST,
AGED,
ISOLATE,
+ TUNNEL,
+
+ /* Tunnel argumens. */
+ TUNNEL_RULE,
/* Destroy arguments. */
DESTROY_RULE,
@@ -88,6 +92,8 @@ enum index {
INGRESS,
EGRESS,
TRANSFER,
+ TUNNEL_SET,
+ TUNNEL_MATCH,
/* Validate/create pattern. */
PATTERN,
@@ -653,6 +659,7 @@ struct buffer {
union {
struct {
struct rte_flow_attr attr;
+ struct tunnel_ops tunnel_ops;
struct rte_flow_item *pattern;
struct rte_flow_action *actions;
uint32_t pattern_n;
@@ -713,10 +720,18 @@ static const enum index next_vc_attr[] = {
INGRESS,
EGRESS,
TRANSFER,
+ TUNNEL_SET,
+ TUNNEL_MATCH,
PATTERN,
ZERO,
};
+static const enum index next_tunnel_attr[] = {
+ TUNNEL_RULE,
+ END,
+ ZERO,
+};
+
static const enum index next_destroy_attr[] = {
DESTROY_RULE,
END,
@@ -1516,6 +1531,9 @@ static int parse_aged(struct context *, const struct
token *,
static int parse_isolate(struct context *, const struct token *,
const char *, unsigned int,
void *, unsigned int);
+static int parse_tunnel(struct context *, const struct token *,
+ const char *, unsigned int,
+ void *, unsigned int);
static int parse_int(struct context *, const struct token *,
const char *, unsigned int,
void *, unsigned int);
@@ -1698,7 +1716,8 @@ static const struct token token_list[] = {
LIST,
AGED,
QUERY,
- ISOLATE)),
+ ISOLATE,
+ TUNNEL)),
.call = parse_init,
},
/* Sub-level commands. */
@@ -1772,6 +1791,21 @@ static const struct token token_list[] = {
ARGS_ENTRY(struct buffer, port)),
.call = parse_isolate,
},
+ [TUNNEL] = {
+ .name = "tunnel",
+ .help = "new tunnel API",
+ .next = NEXT(NEXT_ENTRY(TUNNEL_RULE), NEXT_ENTRY(PORT_ID)),
+ .args = ARGS(ARGS_ENTRY(struct buffer, port)),
+ .call = parse_tunnel,
+ },
+ /* Tunnel arguments. */
+ [TUNNEL_RULE]{
+ .name = "type",
+ .help = "specify tunnel type",
+ .next = NEXT(next_tunnel_attr, NEXT_ENTRY(FILE_PATH)),
+ .args = ARGS(ARGS_ENTRY(struct tunnel_ops, type)),
+ .call = parse_tunnel,
+ },
/* Destroy arguments. */
[DESTROY_RULE] = {
.name = "rule",
@@ -1835,6 +1869,20 @@ static const struct token token_list[] = {
.next = NEXT(next_vc_attr),
.call = parse_vc,
},
+ [TUNNEL_SET] = {
+ .name = "tunnel_set",
+ .help = "tunnel steer rule",
+ .next = NEXT(next_vc_attr, NEXT_ENTRY(UNSIGNED)),
+ .args = ARGS(ARGS_ENTRY(struct tunnel_ops, id)),
+ .call = parse_vc,
+ },
+ [TUNNEL_MATCH] = {
+ .name = "tunnel_match",
+ .help = "tunnel match rule",
+ .next = NEXT(next_vc_attr, NEXT_ENTRY(UNSIGNED)),
+ .args = ARGS(ARGS_ENTRY(struct tunnel_ops, id)),
+ .call = parse_vc,
+ },
/* Validate/create pattern. */
[PATTERN] = {
.name = "pattern",
@@ -4054,12 +4102,28 @@ parse_vc(struct context *ctx, const struct token *token,
return len;
}
ctx->objdata = 0;
- ctx->object = &out->args.vc.attr;
+ switch (ctx->curr) {
+ default:
+ ctx->object = &out->args.vc.attr;
+ break;
+ case TUNNEL_SET:
+ case TUNNEL_MATCH:
+ ctx->object = &out->args.vc.tunnel_ops;
+ break;
+ }
ctx->objmask = NULL;
switch (ctx->curr) {
case GROUP:
case PRIORITY:
return len;
+ case TUNNEL_SET:
+ out->args.vc.tunnel_ops.enabled = 1;
+ out->args.vc.tunnel_ops.actions = 1;
+ return len;
+ case TUNNEL_MATCH:
+ out->args.vc.tunnel_ops.enabled = 1;
+ out->args.vc.tunnel_ops.items = 1;
+ return len;
case INGRESS:
out->args.vc.attr.ingress = 1;
return len;
@@ -5597,6 +5661,34 @@ parse_isolate(struct context *ctx, const struct token
*token,
return len;
}
+static int
+parse_tunnel(struct context *ctx, const struct token *token,
+ const char *str, unsigned int len,
+ void *buf, unsigned int size)
+{
+ struct buffer *out = buf;
+
+ /* Token name must match. */
+ if (parse_default(ctx, token, str, len, NULL, 0) < 0)
+ return -1;
+ /* Nothing else to do if there is no buffer. */
+ if (!out)
+ return len;
+ if (!out->command) {
+ if (ctx->curr != TUNNEL)
+ return -1;
+ if (sizeof(*out) > size)
+ return -1;
+ out->command = ctx->curr;
+ ctx->objdata = 0;
+ ctx->object = out;
+ ctx->objmask = NULL;
+ }
+ if (ctx->curr == TUNNEL_RULE)
+ ctx->object = &out->args.vc.tunnel_ops;
+ return len;
+}
+
/**
* Parse signed/unsigned integers 8 to 64-bit long.
*
@@ -6547,7 +6639,8 @@ cmd_flow_parsed(const struct buffer *in)
break;
case CREATE:
port_flow_create(in->port, &in->args.vc.attr,
- in->args.vc.pattern, in->args.vc.actions);
+ in->args.vc.pattern, in->args.vc.actions,
+ &in->args.vc.tunnel_ops);
break;
case DESTROY:
port_flow_destroy(in->port, in->args.destroy.rule_n,
@@ -6573,6 +6666,9 @@ cmd_flow_parsed(const struct buffer *in)
case AGED:
port_flow_aged(in->port, in->args.aged.destroy);
break;
+ case TUNNEL:
+ port_flow_add_tunnel(in->port, &in->args.vc.tunnel_ops);
+ break;
default:
break;
}
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index 30bee33248..b90927f451 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -1337,6 +1337,58 @@ port_mtu_set(portid_t port_id, uint16_t mtu)
/* Generic flow management functions. */
+static struct port_flow_tunnel *
+port_flow_locate_tunnel(struct rte_port *port, uint32_t port_tunnel_id)
+{
+ struct port_flow_tunnel *flow_tunnel;
+
+ LIST_FOREACH(flow_tunnel, &port->flow_tunnel_list, chain) {
+ if (flow_tunnel->id == port_tunnel_id)
+ goto out;
+ }
+ flow_tunnel = NULL;
+
+out:
+ return flow_tunnel;
+}
+
+void port_flow_release_tunnel(struct port_flow_tunnel *flow_tunnel)
+{
+ LIST_REMOVE(flow_tunnel, chain);
+ free(flow_tunnel);
+}
+
+void port_flow_add_tunnel(portid_t port_id, const struct tunnel_ops *ops)
+{
+ struct rte_port *port = &ports[port_id];
+ enum rte_flow_item_type type;
+ struct port_flow_tunnel *flow_tunnel;
+
+ if (!strncmp(ops->type, "vxlan", strlen("vxlan")))
+ type = RTE_FLOW_ITEM_TYPE_VXLAN;
+ else {
+ printf("cannot offload \"%s\" tunnel type\n", ops->type);
+ return;
+ }
+ LIST_FOREACH(flow_tunnel, &port->flow_tunnel_list, chain) {
+ if (flow_tunnel->tunnel.type == type)
+ break;
+ }
+ if (!flow_tunnel) {
+ flow_tunnel = calloc(1, sizeof(*flow_tunnel));
+ if (!flow_tunnel) {
+ printf("failed to allocate port flow_tunnel object\n");
+ return;
+ }
+ flow_tunnel->tunnel.type = type;
+ flow_tunnel->id = LIST_EMPTY(&port->flow_tunnel_list) ? 1 :
+ LIST_FIRST(&port->flow_tunnel_list)->id + 1;
+ LIST_INSERT_HEAD(&port->flow_tunnel_list, flow_tunnel, chain);
+ }
+ printf("port %d: flow tunnel #%u type %s\n",
+ port_id, flow_tunnel->id, ops->type);
+}
+
/** Generate a port_flow entry from attributes/pattern/actions. */
static struct port_flow *
port_flow_new(const struct rte_flow_attr *attr,
@@ -1503,13 +1555,15 @@ int
port_flow_create(portid_t port_id,
const struct rte_flow_attr *attr,
const struct rte_flow_item *pattern,
- const struct rte_flow_action *actions)
+ const struct rte_flow_action *actions,
+ const struct tunnel_ops *tunnel_ops)
{
struct rte_flow *flow;
struct rte_port *port;
struct port_flow *pf;
uint32_t id = 0;
struct rte_flow_error error;
+ struct port_flow_tunnel *pft;
port = &ports[port_id];
if (port->flow_list) {
@@ -1520,6 +1574,75 @@ port_flow_create(portid_t port_id,
}
id = port->flow_list->id + 1;
}
+ if (tunnel_ops->enabled) {
+ int ret;
+ pft = port_flow_locate_tunnel(port, tunnel_ops->id);
+ if (!pft) {
+ printf("failed to locate port flow tunnel #%u\n",
+ tunnel_ops->id);
+ return -ENOENT;
+ }
+ if (tunnel_ops->actions) {
+ uint32_t num_actions;
+ const struct rte_flow_action *aptr;
+
+ ret = rte_flow_tunnel_decap_set(port_id, &pft->tunnel,
+ &pft->pmd_actions,
+ &pft->num_pmd_actions,
+ &error);
+ if (ret) {
+ port_flow_complain(&error);
+ return -EINVAL;
+ }
+ for (aptr = actions, num_actions = 1;
+ aptr->type != RTE_FLOW_ACTION_TYPE_END;
+ aptr++, num_actions++);
+ pft->actions = malloc(
+ (num_actions + pft->num_pmd_actions) *
+ sizeof(actions[0]));
+ if (!pft->actions) {
+ rte_flow_tunnel_action_decap_release(
+ port_id, pft->actions,
+ pft->num_pmd_actions, &error);
+ return -ENOMEM;
+ }
+ rte_memcpy(pft->actions, pft->pmd_actions,
+ pft->num_pmd_actions * sizeof(actions[0]));
+ rte_memcpy(pft->actions + pft->num_pmd_actions, actions,
+ num_actions * sizeof(actions[0]));
+ actions = pft->actions;
+ }
+ if (tunnel_ops->items) {
+ uint32_t num_items;
+ const struct rte_flow_item *iptr;
+
+ ret = rte_flow_tunnel_match(port_id, &pft->tunnel,
+ &pft->pmd_items,
+ &pft->num_pmd_items,
+ &error);
+ if (ret) {
+ port_flow_complain(&error);
+ return -EINVAL;
+ }
+ for (iptr = pattern, num_items = 1;
+ iptr->type != RTE_FLOW_ITEM_TYPE_END;
+ iptr++, num_items++);
+ pft->items = malloc((num_items + pft->num_pmd_items) *
+ sizeof(pattern[0]));
+ if (!pft->items) {
+ rte_flow_tunnel_item_release(
+ port_id, pft->pmd_items,
+ pft->num_pmd_items, &error);
+ return -ENOMEM;
+ }
+ rte_memcpy(pft->items, pft->pmd_items,
+ pft->num_pmd_items * sizeof(pattern[0]));
+ rte_memcpy(pft->items + pft->num_pmd_items, pattern,
+ num_items * sizeof(pattern[0]));
+ pattern = pft->items;
+ }
+
+ }
pf = port_flow_new(attr, pattern, actions, &error);
if (!pf)
return port_flow_complain(&error);
@@ -1535,6 +1658,20 @@ port_flow_create(portid_t port_id,
pf->id = id;
pf->flow = flow;
port->flow_list = pf;
+ if (tunnel_ops->enabled) {
+ if (tunnel_ops->actions) {
+ free(pft->actions);
+ rte_flow_tunnel_action_decap_release(
+ port_id, pft->pmd_actions,
+ pft->num_pmd_actions, &error);
+ }
+ if (tunnel_ops->items) {
+ free(pft->items);
+ rte_flow_tunnel_item_release(port_id, pft->pmd_items,
+ pft->num_pmd_items,
+ &error);
+ }
+ }
printf("Flow rule #%u created\n", pf->id);
return 0;
}
@@ -1829,7 +1966,9 @@ port_flow_list(portid_t port_id, uint32_t n, const
uint32_t group[n])
pf->rule.attr->egress ? 'e' : '-',
pf->rule.attr->transfer ? 't' : '-');
while (item->type != RTE_FLOW_ITEM_TYPE_END) {
- if (rte_flow_conv(RTE_FLOW_CONV_OP_ITEM_NAME_PTR,
+ if ((uint32_t)item->type > INT_MAX)
+ name = "PMD_INTERNAL";
+ else if (rte_flow_conv(RTE_FLOW_CONV_OP_ITEM_NAME_PTR,
&name, sizeof(name),
(void *)(uintptr_t)item->type,
NULL) <= 0)
@@ -1840,7 +1979,9 @@ port_flow_list(portid_t port_id, uint32_t n, const
uint32_t group[n])
}
printf("=>");
while (action->type != RTE_FLOW_ACTION_TYPE_END) {
- if (rte_flow_conv(RTE_FLOW_CONV_OP_ACTION_NAME_PTR,
+ if ((uint32_t)action->type > INT_MAX)
+ name = "PMD_INTERNAL";
+ else if (rte_flow_conv(RTE_FLOW_CONV_OP_ACTION_NAME_PTR,
&name, sizeof(name),
(void *)(uintptr_t)action->type,
NULL) <= 0)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 7842c3b781..e2330116e1 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -3591,6 +3591,8 @@ init_port_dcb_config(portid_t pid,
static void
init_port(void)
{
+ int i;
+
/* Configuration of Ethernet ports. */
ports = rte_zmalloc("testpmd: ports",
sizeof(struct rte_port) * RTE_MAX_ETHPORTS,
@@ -3600,7 +3602,8 @@ init_port(void)
"rte_zmalloc(%d struct rte_port) failed\n",
RTE_MAX_ETHPORTS);
}
-
+ for (i = 0; i < RTE_MAX_ETHPORTS; i++)
+ LIST_INIT(&ports[i].flow_tunnel_list);
/* Initialize ports NUMA structures */
memset(port_numa, NUMA_NO_CONFIG, RTE_MAX_ETHPORTS);
memset(rxring_numa, NUMA_NO_CONFIG, RTE_MAX_ETHPORTS);
diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
index 25a12b14f2..9c47533c68 100644
--- a/app/test-pmd/testpmd.h
+++ b/app/test-pmd/testpmd.h
@@ -12,6 +12,7 @@
#include <rte_gro.h>
#include <rte_gso.h>
#include <cmdline.h>
+#include <sys/queue.h>
#define RTE_PORT_ALL (~(portid_t)0x0)
@@ -148,6 +149,26 @@ struct port_flow {
uint8_t data[]; /**< Storage for flow rule description */
};
+struct port_flow_tunnel {
+ LIST_ENTRY(port_flow_tunnel) chain;
+ struct rte_flow_action *pmd_actions;
+ struct rte_flow_item *pmd_items;
+ uint32_t id;
+ uint32_t num_pmd_actions;
+ uint32_t num_pmd_items;
+ struct rte_flow_tunnel tunnel;
+ struct rte_flow_action *actions;
+ struct rte_flow_item *items;
+};
+
+struct tunnel_ops {
+ uint32_t id;
+ char type[16];
+ uint32_t enabled:1;
+ uint32_t actions:1;
+ uint32_t items:1;
+};
+
/**
* The data structure associated with each port.
*/
@@ -178,6 +199,7 @@ struct rte_port {
uint32_t mc_addr_nb; /**< nb. of addr. in mc_addr_pool */
uint8_t slave_flag; /**< bonding slave port */
struct port_flow *flow_list; /**< Associated flows. */
+ LIST_HEAD(, port_flow_tunnel) flow_tunnel_list;
const struct rte_eth_rxtx_callback
*rx_dump_cb[RTE_MAX_QUEUES_PER_PORT+1];
const struct rte_eth_rxtx_callback
*tx_dump_cb[RTE_MAX_QUEUES_PER_PORT+1];
/**< metadata value to insert in Tx packets. */
@@ -729,7 +751,8 @@ int port_flow_validate(portid_t port_id,
int port_flow_create(portid_t port_id,
const struct rte_flow_attr *attr,
const struct rte_flow_item *pattern,
- const struct rte_flow_action *actions);
+ const struct rte_flow_action *actions,
+ const struct tunnel_ops *tunnel_ops);
void update_age_action_context(const struct rte_flow_action *actions,
struct port_flow *pf);
int port_flow_destroy(portid_t port_id, uint32_t n, const uint32_t *rule);
@@ -739,6 +762,8 @@ int port_flow_query(portid_t port_id, uint32_t rule,
const struct rte_flow_action *action);
void port_flow_list(portid_t port_id, uint32_t n, const uint32_t *group);
void port_flow_aged(portid_t port_id, uint8_t destroy);
+void port_flow_release_tunnel(struct port_flow_tunnel *flow_tunnel);
+void port_flow_add_tunnel(portid_t port_id, const struct tunnel_ops *ops);
int port_flow_isolate(portid_t port_id, int set);
void rx_ring_desc_display(portid_t port_id, queueid_t rxq_id, uint16_t rxd_id);
diff --git a/app/test-pmd/util.c b/app/test-pmd/util.c
index 8488fa1a8f..6757acde9a 100644
--- a/app/test-pmd/util.c
+++ b/app/test-pmd/util.c
@@ -22,6 +22,12 @@ print_ether_addr(const char *what, const struct
rte_ether_addr *eth_addr)
printf("%s%s", what, buf);
}
+static bool tunnel_missed_packet(struct rte_mbuf *mb)
+{
+ uint64_t mask = PKT_RX_FDIR | PKT_RX_FDIR_ID;
+ return (mb->ol_flags & mask) == mask;
+}
+
static inline void
dump_pkt_burst(uint16_t port_id, uint16_t queue, struct rte_mbuf *pkts[],
uint16_t nb_pkts, int is_rx)
@@ -51,15 +57,37 @@ dump_pkt_burst(uint16_t port_id, uint16_t queue, struct
rte_mbuf *pkts[],
mb = pkts[i];
eth_hdr = rte_pktmbuf_read(mb, 0, sizeof(_eth_hdr), &_eth_hdr);
eth_type = RTE_BE_TO_CPU_16(eth_hdr->ether_type);
- ol_flags = mb->ol_flags;
packet_type = mb->packet_type;
is_encapsulation = RTE_ETH_IS_TUNNEL_PKT(packet_type);
+ if (tunnel_missed_packet(mb)) {
+ int ret;
+ struct rte_flow_error error;
+ struct rte_flow_restore_info info = { 0, };
+
+ ret = rte_flow_tunnel_get_restore_info(port_id, mb,
+ &info, &error);
+ if (!ret) {
+ printf("tunnel restore info:");
+ if (info.flags & RTE_FLOW_RESTORE_INFO_TUNNEL)
+ if (info.tunnel.type ==
+ RTE_FLOW_ITEM_TYPE_VXLAN)
+ printf(" - vxlan tunnel");
+ if (info.flags &
+ RTE_FLOW_RESTORE_INFO_ENCAPSULATED)
+ printf(" - outer header present");
+ if (info.flags & RTE_FLOW_RESTORE_INFO_GROUP_ID)
+ printf(" - miss group %u",
+ info.group_id);
+ }
+ printf("\n");
+ }
print_ether_addr(" src=", ð_hdr->s_addr);
print_ether_addr(" - dst=", ð_hdr->d_addr);
printf(" - type=0x%04x - length=%u - nb_segs=%d",
eth_type, (unsigned int) mb->pkt_len,
(int)mb->nb_segs);
+ ol_flags = mb->ol_flags;
if (ol_flags & PKT_RX_RSS_HASH) {
printf(" - RSS hash=0x%x", (unsigned int) mb->hash.rss);
printf(" - RSS queue=0x%x", (unsigned int) queue);
--
2.25.1
