#include <rte_bus_pci.h>
#include <rte_config.h>
#include <rte_cycles.h>
@@ -329,8 +335,9 @@ struct dpdk_qos_ops {
struct netdev_dpdk_queue_state *state);
};
-/* dpdk_qos_ops for each type of user space QoS implementation */
+/* dpdk_qos_ops for each type of user space QoS implementation. */
static const struct dpdk_qos_ops egress_policer_ops;
+static const struct dpdk_qos_ops trtcm_policer_ops;
/*
* Array of dpdk_qos_ops, contains pointer to all supported QoS
@@ -338,6 +345,7 @@ static const struct dpdk_qos_ops egress_policer_ops;
*/
static const struct dpdk_qos_ops *const qos_confs[] = {
&egress_policer_ops,
+ &trtcm_policer_ops,
NULL
};
@@ -2162,9 +2170,9 @@ netdev_dpdk_eth_tx_burst(struct netdev_dpdk *dev, int qid,
}
static inline bool
-netdev_dpdk_policer_pkt_handle(struct rte_meter_srtcm *meter,
- struct rte_meter_srtcm_profile *profile,
- struct rte_mbuf *pkt, uint64_t time)
+netdev_dpdk_srtcm_policer_pkt_handle(struct rte_meter_srtcm *meter,
+ struct rte_meter_srtcm_profile *profile,
+ struct rte_mbuf *pkt, uint64_t time)
{
uint32_t pkt_len = rte_pktmbuf_pkt_len(pkt) - sizeof(struct
rte_ether_hdr);
@@ -2173,10 +2181,10 @@ netdev_dpdk_policer_pkt_handle(struct rte_meter_srtcm *meter,
}
static int
-netdev_dpdk_policer_run(struct rte_meter_srtcm *meter,
- struct rte_meter_srtcm_profile *profile,
- struct rte_mbuf **pkts, int pkt_cnt,
- bool should_steal)
+srtcm_policer_run_single_packet(struct rte_meter_srtcm *meter,
+ struct rte_meter_srtcm_profile *profile,
+ struct rte_mbuf **pkts, int pkt_cnt,
+ bool should_steal)
{
int i = 0;
int cnt = 0;
@@ -2186,8 +2194,8 @@ netdev_dpdk_policer_run(struct rte_meter_srtcm *meter,
for (i = 0; i < pkt_cnt; i++) {
pkt = pkts[i];
/* Handle current packet */
- if (netdev_dpdk_policer_pkt_handle(meter, profile,
- pkt, current_time)) {
+ if (netdev_dpdk_srtcm_policer_pkt_handle(meter, profile,
+ pkt, current_time)) {
if (cnt != i) {
pkts[cnt] = pkt;
}
@@ -2209,8 +2217,9 @@ ingress_policer_run(struct ingress_policer *policer,
struct rte_mbuf **pkts,
int cnt = 0;
rte_spinlock_lock(&policer->policer_lock);
- cnt = netdev_dpdk_policer_run(&policer->in_policer, &policer->in_prof,
- pkts, pkt_cnt, should_steal);
+ cnt = srtcm_policer_run_single_packet(&policer->in_policer,
+ &policer->in_prof,
+ pkts, pkt_cnt, should_steal);
rte_spinlock_unlock(&policer->policer_lock);
return cnt;
@@ -4480,9 +4489,9 @@ egress_policer_run(struct qos_conf *conf, struct rte_mbuf
**pkts, int pkt_cnt,
struct egress_policer *policer =
CONTAINER_OF(conf, struct egress_policer, qos_conf);
- cnt = netdev_dpdk_policer_run(&policer->egress_meter,
- &policer->egress_prof, pkts,
- pkt_cnt, should_steal);
+ cnt = srtcm_policer_run_single_packet(&policer->egress_meter,
+ &policer->egress_prof, pkts,
+ pkt_cnt, should_steal);
return cnt;
}
@@ -4496,6 +4505,326 @@ static const struct dpdk_qos_ops egress_policer_ops = {
.qos_run = egress_policer_run
};
+/* trtcm-policer details */
+
+struct trtcm_policer {
+ struct qos_conf qos_conf;
+ struct rte_meter_trtcm_rfc4115_params meter_params;
+ struct rte_meter_trtcm_rfc4115_profile meter_profile;
+ struct rte_meter_trtcm_rfc4115 meter;
+ struct netdev_queue_stats stats;
+ struct hmap queues;
+};
+
+struct trtcm_policer_queue {
+ struct hmap_node hmap_node;
+ uint32_t queue_id;
+ struct rte_meter_trtcm_rfc4115_params meter_params;
+ struct rte_meter_trtcm_rfc4115_profile meter_profile;
+ struct rte_meter_trtcm_rfc4115 meter;
+ struct netdev_queue_stats stats;
+};
+
+static void
+trtcm_policer_details_to_param(const struct smap *details,
+ struct rte_meter_trtcm_rfc4115_params *params)
+{
+ memset(params, 0, sizeof *params);
+ params->cir = smap_get_ullong(details, "cir", 0);
+ params->eir = smap_get_ullong(details, "eir", 0);
+ params->cbs = smap_get_ullong(details, "cbs", 0);
+ params->ebs = smap_get_ullong(details, "ebs", 0);
+}
+
+static void
+trtcm_policer_param_to_detail(
+ const struct rte_meter_trtcm_rfc4115_params *params,
+ struct smap *details)
+{
+ smap_add_format(details, "cir", "%"PRIu64, params->cir);
+ smap_add_format(details, "eir", "%"PRIu64, params->eir);
+ smap_add_format(details, "cbs", "%"PRIu64, params->cbs);
+ smap_add_format(details, "ebs", "%"PRIu64, params->ebs);
+}
+
+
+static int
+trtcm_policer_qos_construct(const struct smap *details,
+ struct qos_conf **conf)
+{
+ struct trtcm_policer *policer;
+ int err = 0;
+
+ policer = xmalloc(sizeof *policer);
+ qos_conf_init(&policer->qos_conf, &trtcm_policer_ops);
+ trtcm_policer_details_to_param(details, &policer->meter_params);
+ err = rte_meter_trtcm_rfc4115_profile_config(&policer->meter_profile,
+ &policer->meter_params);
+ if (!err) {
+ err = rte_meter_trtcm_rfc4115_config(&policer->meter,
+ &policer->meter_profile);
+ }
+
+ if (!err) {
+ *conf = &policer->qos_conf;
+ memset(&policer->stats, 0, sizeof policer->stats);
+ hmap_init(&policer->queues);
+ } else {
+ free(policer);
+ *conf = NULL;
+ err = -err;
+ }
+
+ return err;
+}
+
+static void
+trtcm_policer_qos_destruct(struct qos_conf *conf)
+{
+ struct trtcm_policer_queue *queue, *next_queue;
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ HMAP_FOR_EACH_SAFE (queue, next_queue, hmap_node, &policer->queues) {
+ hmap_remove(&policer->queues, &queue->hmap_node);
+ free(queue);
+ }
+ hmap_destroy(&policer->queues);
+ free(policer);
+}
+
+static int
+trtcm_policer_qos_get(const struct qos_conf *conf, struct smap *details)
+{
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ trtcm_policer_param_to_detail(&policer->meter_params, details);
+ return 0;
+}
+
+static bool
+trtcm_policer_qos_is_equal(const struct qos_conf *conf,
+ const struct smap *details)
+{
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+ struct rte_meter_trtcm_rfc4115_params params;
+
+ trtcm_policer_details_to_param(details, ¶ms);
+
+ return !memcmp(¶ms, &policer->meter_params, sizeof params);
+}
+
+static struct trtcm_policer_queue *
+trtcm_policer_qos_find_queue(struct trtcm_policer *policer, uint32_t queue_id)
+{
+ struct trtcm_policer_queue *queue;
+ HMAP_FOR_EACH_WITH_HASH (queue, hmap_node, hash_2words(queue_id, 0),
+ &policer->queues) {
+ if (queue->queue_id == queue_id) {
+ return queue;
+ }
+ }
+ return NULL;
+}
+
+static inline bool
+trtcm_policer_run_single_packet(struct trtcm_policer *policer,
+ struct rte_mbuf *pkt, uint64_t time)
+{
+ enum rte_color pkt_color;
+ struct trtcm_policer_queue *queue;
+ uint32_t pkt_len = rte_pktmbuf_pkt_len(pkt) - sizeof(struct rte_ether_hdr);
+ struct dp_packet *dpkt = CONTAINER_OF(pkt, struct dp_packet, mbuf);
+
+ queue = trtcm_policer_qos_find_queue(policer, dpkt->md.skb_priority);
+ if (!queue) {
+ /* If no queue is found, use the default queue, which MUST exist. */
+ queue = trtcm_policer_qos_find_queue(policer, 0);
+ if (!queue) {
+ return false;
+ }
+ }
+
+ pkt_color = rte_meter_trtcm_rfc4115_color_blind_check(&queue->meter,
+
&queue->meter_profile,
+ time,
+ pkt_len);
+
+ if (pkt_color == RTE_COLOR_RED) {
+ queue->stats.tx_errors++;
+ } else {
+ queue->stats.tx_bytes += pkt_len;
+ queue->stats.tx_packets++;
+ }
+
+ pkt_color = rte_meter_trtcm_rfc4115_color_aware_check(&policer->meter,
+ &policer->meter_profile,
+ time, pkt_len,
+ pkt_color);
+
+ if (pkt_color == RTE_COLOR_RED) {
+ policer->stats.tx_errors++;
+ return false;
+ }
+
+ policer->stats.tx_bytes += pkt_len;
+ policer->stats.tx_packets++;
+ return true;
+}
+
+static int
+trtcm_policer_run(struct qos_conf *conf, struct rte_mbuf **pkts, int pkt_cnt,
+ bool should_steal)
+{
+ int i = 0;
+ int cnt = 0;
+ struct rte_mbuf *pkt = NULL;
+ uint64_t current_time = rte_rdtsc();
+
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ for (i = 0; i < pkt_cnt; i++) {
+ pkt = pkts[i];
+
+ if (trtcm_policer_run_single_packet(policer, pkt, current_time)) {
+ if (cnt != i) {
+ pkts[cnt] = pkt;
+ }
+ cnt++;
+ } else {
+ if (should_steal) {
+ rte_pktmbuf_free(pkt);
+ }
+ }
+ }
+ return cnt;
+}
+
+static int
+trtcm_policer_qos_queue_construct(const struct smap *details,
+ uint32_t queue_id, struct qos_conf *conf)
+{
+ int err = 0;
+ struct trtcm_policer_queue *queue;
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ queue = trtcm_policer_qos_find_queue(policer, queue_id);
+ if (!queue) {
+ queue = xmalloc(sizeof *queue);
+ queue->queue_id = queue_id;
+ memset(&queue->stats, 0, sizeof queue->stats);
+ queue->stats.created = time_msec();
+ hmap_insert(&policer->queues, &queue->hmap_node,
+ hash_2words(queue_id, 0));
+ }
+ if (queue_id == 0 && smap_is_empty(details)) {
+ /* No default queue configured, use port values */
+ memcpy(&queue->meter_params, &policer->meter_params,
+ sizeof queue->meter_params);
+ } else {
+ trtcm_policer_details_to_param(details, &queue->meter_params);
+ }
+
+ err = rte_meter_trtcm_rfc4115_profile_config(&queue->meter_profile,
+ &queue->meter_params);
+
+ if (!err) {
+ err = rte_meter_trtcm_rfc4115_config(&queue->meter,
+ &queue->meter_profile);
+ }
+ if (err) {
+ hmap_remove(&policer->queues, &queue->hmap_node);
+ free(queue);
+ err = -err;
+ }
+ return err;
+}
+
+static void
+trtcm_policer_qos_queue_destruct(struct qos_conf *conf, uint32_t queue_id)
+{
+ struct trtcm_policer_queue *queue;
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ queue = trtcm_policer_qos_find_queue(policer, queue_id);
+ if (queue) {
+ hmap_remove(&policer->queues, &queue->hmap_node);
+ free(queue);
+ }
+}
+
+static int
+trtcm_policer_qos_queue_get(struct smap *details, uint32_t queue_id,
+ const struct qos_conf *conf)
+{
+ struct trtcm_policer_queue *queue;
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ queue = trtcm_policer_qos_find_queue(policer, queue_id);
+ if (!queue) {
+ return EINVAL;
+ }
+
+ trtcm_policer_param_to_detail(&queue->meter_params, details);
+ return 0;
+}
+
+static int
+trtcm_policer_qos_queue_get_stats(const struct qos_conf *conf,
+ uint32_t queue_id,
+ struct netdev_queue_stats *stats)
+{
+ struct trtcm_policer_queue *queue;
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ queue = trtcm_policer_qos_find_queue(policer, queue_id);
+ if (!queue) {
+ return EINVAL;
+ }
+ memcpy(stats, &queue->stats, sizeof *stats);
+ return 0;
+}
+
+static int
+trtcm_policer_qos_queue_dump_state_init(const struct qos_conf *conf,
+ struct netdev_dpdk_queue_state *state)
+{
+ uint32_t i = 0;
+ struct trtcm_policer_queue *queue;
+ struct trtcm_policer *policer = CONTAINER_OF(conf, struct trtcm_policer,
+ qos_conf);
+
+ state->n_queues = hmap_count(&policer->queues);
+ state->cur_queue = 0;
+ state->queues = xmalloc(state->n_queues * sizeof *state->queues);
+
+ HMAP_FOR_EACH (queue, hmap_node, &policer->queues) {
+ state->queues[i++] = queue->queue_id;
+ }
+ return 0;
+}
+
+static const struct dpdk_qos_ops trtcm_policer_ops = {
+ .qos_name = "trtcm-policer",
+ .qos_construct = trtcm_policer_qos_construct,
+ .qos_destruct = trtcm_policer_qos_destruct,
+ .qos_get = trtcm_policer_qos_get,
+ .qos_is_equal = trtcm_policer_qos_is_equal,
+ .qos_run = trtcm_policer_run,
+ .qos_queue_construct = trtcm_policer_qos_queue_construct,
+ .qos_queue_destruct = trtcm_policer_qos_queue_destruct,
+ .qos_queue_get = trtcm_policer_qos_queue_get,
+ .qos_queue_get_stats = trtcm_policer_qos_queue_get_stats,
+ .qos_queue_dump_state_init = trtcm_policer_qos_queue_dump_state_init
+};
+
static int
netdev_dpdk_reconfigure(struct netdev *netdev)
{
diff --git a/vswitchd/vswitch.xml b/vswitchd/vswitch.xml
index 0ec726c..c43cb1a 100644
--- a/vswitchd/vswitch.xml
+++ b/vswitchd/vswitch.xml
@@ -4441,6 +4441,19 @@ ovs-vsctl add-port br0 p0 -- set Interface p0 type=patch
options:peer=p1 \
in performance will be noticed in terms of overall aggregate traffic
throughput.
</dd>
+ <dt><code>trtcm-policer</code></dt>
+ <dd>
+ A DPDK egress policer algorithm using RFC 4115's Two-Rate,
+ Three-Color marker. It's a two-level hierarchical policer
+ which first does a color-blind marking of the traffic at the queue
+ level, followed by a color-aware marking at the port level. At the
+ end traffic marked as Green or Yellow is forwarded, Red is dropped.
+ For details on how traffic is marked, see RFC 4115.
+
+ If the ``default queue'', 0, is not configured it's automatically
+ created with the same <code>other_config</code> values as the
+ physical port.
+ </dd>
</dl>
</column>
@@ -4508,6 +4521,27 @@ ovs-vsctl add-port br0 p0 -- set Interface p0 type=patch options:peer=p1 \
bytes/tokens of the packet. If there are not enough tokens in the cbs
bucket the packet will be dropped.
</column>
+ <column name="other_config" key="eir" type='{"type": "integer"}'>
+ The Excess Information Rate (EIR) is measured in bytes of IP
+ packets per second, i.e. it includes the IP header, but not link
+ specific (e.g. Ethernet) headers. This represents the bytes per second
+ rate at which the token bucket will be updated. The eir value is
+ calculated by (pps x packet data size). For example assuming a user
+ wishes to limit a stream consisting of 64 byte packets to 1 million
+ packets per second the EIR would be set to to to 46000000. This value
+ can be broken into '1,000,000 x 46'. Where 1,000,000 is the policing
+ rate for the number of packets per second and 46 represents the size
+ of the packet data for a 64 byte ip packet.
+ </column>
+ <column name="other_config" key="ebs" type='{"type": "integer"}'>
+ The Excess Burst Size (EBS) is measured in bytes and represents a
+ token bucket. At a minimum this value should be be set to the expected
+ largest size packet in the traffic stream. In practice larger values
+ may be used to increase the size of the token bucket. If a packet can
+ be transmitted then the ebs will be decremented by the number of
+ bytes/tokens of the packet. If there are not enough tokens in the cbs
+ bucket the packet might be dropped.
+ </column>
</group>
<group title="Configuration for linux-sfq">
