summaryrefslogtreecommitdiff
path: root/include/net/pkt_cls.h
diff options
context:
space:
mode:
authorMaxim Mikityanskiy <maximmi@mellanox.com>2021-01-19 14:08:13 +0200
committerJakub Kicinski <kuba@kernel.org>2021-01-22 20:41:29 -0800
commitd03b195b5aa015f6c11988b86a3625f8d5dbac52 (patch)
tree2794b585c9df341b3b130ee5eaae9cac1e4fd2ab /include/net/pkt_cls.h
parent4dd78a73738afa92d33a226ec477b42938b31c83 (diff)
sch_htb: Hierarchical QoS hardware offload
HTB doesn't scale well because of contention on a single lock, and it also consumes CPU. This patch adds support for offloading HTB to hardware that supports hierarchical rate limiting. In the offload mode, HTB passes control commands to the driver using ndo_setup_tc. The driver has to replicate the whole hierarchy of classes and their settings (rate, ceil) in the NIC. Every modification of the HTB tree caused by the admin results in ndo_setup_tc being called. After this setup, the HTB algorithm is done completely in the NIC. An SQ (send queue) is created for every leaf class and attached to the hierarchy, so that the NIC can calculate and obey aggregated rate limits, too. In the future, it can be changed, so that multiple SQs will back a single leaf class. ndo_select_queue is responsible for selecting the right queue that serves the traffic class of each packet. The data path works as follows: a packet is classified by clsact, the driver selects a hardware queue according to its class, and the packet is enqueued into this queue's qdisc. This solution addresses two main problems of scaling HTB: 1. Contention by flow classification. Currently the filters are attached to the HTB instance as follows: # tc filter add dev eth0 parent 1:0 protocol ip flower dst_port 80 classid 1:10 It's possible to move classification to clsact egress hook, which is thread-safe and lock-free: # tc filter add dev eth0 egress protocol ip flower dst_port 80 action skbedit priority 1:10 This way classification still happens in software, but the lock contention is eliminated, and it happens before selecting the TX queue, allowing the driver to translate the class to the corresponding hardware queue in ndo_select_queue. Note that this is already compatible with non-offloaded HTB and doesn't require changes to the kernel nor iproute2. 2. Contention by handling packets. HTB is not multi-queue, it attaches to a whole net device, and handling of all packets takes the same lock. When HTB is offloaded, it registers itself as a multi-queue qdisc, similarly to mq: HTB is attached to the netdev, and each queue has its own qdisc. Some features of HTB may be not supported by some particular hardware, for example, the maximum number of classes may be limited, the granularity of rate and ceil parameters may be different, etc. - so, the offload is not enabled by default, a new parameter is used to enable it: # tc qdisc replace dev eth0 root handle 1: htb offload Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com> Reviewed-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include/net/pkt_cls.h')
-rw-r--r--include/net/pkt_cls.h36
1 files changed, 36 insertions, 0 deletions
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 0f2a9c44171c..255e4f4b521f 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -783,6 +783,42 @@ struct tc_mq_qopt_offload {
};
};
+enum tc_htb_command {
+ /* Root */
+ TC_HTB_CREATE, /* Initialize HTB offload. */
+ TC_HTB_DESTROY, /* Destroy HTB offload. */
+
+ /* Classes */
+ /* Allocate qid and create leaf. */
+ TC_HTB_LEAF_ALLOC_QUEUE,
+ /* Convert leaf to inner, preserve and return qid, create new leaf. */
+ TC_HTB_LEAF_TO_INNER,
+ /* Delete leaf, while siblings remain. */
+ TC_HTB_LEAF_DEL,
+ /* Delete leaf, convert parent to leaf, preserving qid. */
+ TC_HTB_LEAF_DEL_LAST,
+ /* TC_HTB_LEAF_DEL_LAST, but delete driver data on hardware errors. */
+ TC_HTB_LEAF_DEL_LAST_FORCE,
+ /* Modify parameters of a node. */
+ TC_HTB_NODE_MODIFY,
+
+ /* Class qdisc */
+ TC_HTB_LEAF_QUERY_QUEUE, /* Query qid by classid. */
+};
+
+struct tc_htb_qopt_offload {
+ struct netlink_ext_ack *extack;
+ enum tc_htb_command command;
+ u16 classid;
+ u32 parent_classid;
+ u16 qid;
+ u16 moved_qid;
+ u64 rate;
+ u64 ceil;
+};
+
+#define TC_HTB_CLASSID_ROOT U32_MAX
+
enum tc_red_command {
TC_RED_REPLACE,
TC_RED_DESTROY,