- 03 Mar, 2022 40 commits
-
-
Martin KaFai Lau authored
This patch adds tests on forwarding the delivery_time for the following cases - tcp/udp + ip4/ip6 + bpf_redirect_neigh - tcp/udp + ip4/ip6 + ip[6]_forward - bpf_skb_set_delivery_time - The old rcv timestamp expectation on tc-bpf@ingress Signed-off-by:
Martin KaFai Lau <kafai@fb.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Martin KaFai Lau authored
* __sk_buff->delivery_time_type: This patch adds __sk_buff->delivery_time_type. It tells if the delivery_time is stored in __sk_buff->tstamp or not. It will be most useful for ingress to tell if the __sk_buff->tstamp has the (rcv) timestamp or delivery_time. If delivery_time_type is 0 (BPF_SKB_DELIVERY_TIME_NONE), it has the (rcv) timestamp. Two non-zero types are defined for the delivery_time_type, BPF_SKB_DELIVERY_TIME_MONO and BPF_SKB_DELIVERY_TIME_UNSPEC. For UNSPEC, it can only happen in egress because only mono delivery_time can be forwarded to ingress now. The clock of UNSPEC delivery_time can be deduced from the skb->sk->sk_clockid which is how the sch_etf doing it also. * Provide forwarded delivery_time to tc-bpf@ingress: With the help of the new delivery_time_type, the tc-bpf has a way to tell if the __sk_buff->tstamp has the (rcv) timestamp or the delivery_time. During bpf load time, the verifier will learn if the bpf prog has accessed the new __sk_buff->delivery_time_type. If it does, it means the tc-bpf@ingress is expecting the skb->tstamp could have the delivery_time. The kernel will then read the skb->tstamp as-is during bpf insn rewrite without checking the skb->mono_delivery_time. This is done by adding a new prog->delivery_time_access bit. The same goes for writing skb->tstamp. * bpf_skb_set_delivery_time(): The bpf_skb_set_delivery_time() helper is added to allow setting both delivery_time and the delivery_time_type at the same time. If the tc-bpf does not need to change the delivery_time_type, it can directly write to the __sk_buff->tstamp as the existing tc-bpf has already been doing. It will be most useful at ingress to change the __sk_buff->tstamp from the (rcv) timestamp to a mono delivery_time and then bpf_redirect_*(). bpf only has mono clock helper (bpf_ktime_get_ns), and the current known use case is the mono EDT for fq, and only mono delivery time can be kept during forward now, so bpf_skb_set_delivery_time() only supports setting BPF_SKB_DELIVERY_TIME_MONO. It can be extended later when use cases come up and the forwarding path also supports other clock bases. Signed-off-by:
-
Martin KaFai Lau authored
The current tc-bpf@ingress reads and writes the __sk_buff->tstamp as a (rcv) timestamp which currently could either be 0 (not available) or ktime_get_real(). This patch is to backward compatible with the (rcv) timestamp expectation at ingress. If the skb->tstamp has the delivery_time, the bpf insn rewrite will read 0 for tc-bpf running at ingress as it is not available. When writing at ingress, it will also clear the skb->mono_delivery_time bit. /* BPF_READ: a = __sk_buff->tstamp */ if (!skb->tc_at_ingress || !skb->mono_delivery_time) a = skb->tstamp; else a = 0 /* BPF_WRITE: __sk_buff->tstamp = a */ if (skb->tc_at_ingress) skb->mono_delivery_time = 0; skb->tstamp = a; [ A note on the BPF_CGROUP_INET_INGRESS which can also access skb->tstamp. At that point, the skb is delivered locally and skb_clear_delivery_time() has already been done, so the skb->tstamp will only have the (rcv) timestamp. ] If the tc-bpf@egress writes 0 to skb->tstamp, the skb->mono_delivery_time has to be cleared also. It could be done together during convert_ctx_access(). However, the latter patch will also expose the skb->mono_delivery_time bit as __sk_buff->delivery_time_type. Changing the delivery_time_type in the background may surprise the user, e.g. the 2nd read on __sk_buff->delivery_time_type may need a READ_ONCE() to avoid compiler optimization. Thus, in expecting the needs in the latter patch, this patch does a check on !skb->tstamp after running the tc-bpf and clears the skb->mono_delivery_time bit if needed. The earlier discussion on v4 [0]. The bpf insn rewrite requires the skb's mono_delivery_time bit and tc_at_ingress bit. They are moved up in sk_buff so that bpf rewrite can be done at a fixed offset. tc_skip_classify is moved together with tc_at_ingress. To get one bit for mono_delivery_time, csum_not_inet is moved down and this bit is currently used by sctp. [0]: https://lore.kernel.org/bpf/20220217015043.khqwqklx45c4m4se@kafai-mbp.dhcp.thefacebook.com/Signed-off-by:
-
Martin KaFai Lau authored
The previous patches handled the delivery_time in the ingress path before the routing decision is made. This patch can postpone clearing delivery_time in a skb until knowing it is delivered locally and also set the (rcv) timestamp if needed. This patch moves the skb_clear_delivery_time() from dev.c to ip_local_deliver_finish() and ip6_input_finish(). Signed-off-by:
-
Martin KaFai Lau authored
If skb has the (rcv) timestamp available, nfnetlink_{log, queue}.c logs/outputs it to the userspace. When the locally generated skb is looping from egress to ingress over a virtual interface (e.g. veth, loopback...), skb->tstamp may have the delivery time before it is known that will be delivered locally and received by another sk. Like handling the delivery time in network tapping, use ktime_get_real() to get the (rcv) timestamp. The earlier added helper skb_tstamp_cond() is used to do this. false is passed to the second 'cond' arg such that doing ktime_get_real() or not only depends on the netstamp_needed_key static key. Signed-off-by: -
Martin KaFai Lau authored
IOAM is a hop-by-hop option with a temporary iana allocation (49). Since it is hop-by-hop, it is done before the input routing decision. One of the traced data field is the (rcv) timestamp. When the locally generated skb is looping from egress to ingress over a virtual interface (e.g. veth, loopback...), skb->tstamp may have the delivery time before it is known that it will be delivered locally and received by another sk. Like handling the network tapping (tcpdump) in the earlier patch, this patch gets the timestamp if needed without over-writing the delivery_time in the skb->tstamp. skb_tstamp_cond() is added to do the ktime_get_real() with an extra cond arg to check on top of the netstamp_needed_key static key. skb_tstamp_cond() will also be used in a latter patch and it needs the netstamp_needed_key check. Signed-off-by:
-
Martin KaFai Lau authored
A latter patch will postpone the delivery_time clearing until the stack knows the skb is being delivered locally (i.e. calling skb_clear_delivery_time() at ip_local_deliver_finish() for IPv4 and at ip6_input_finish() for IPv6). That will allow other kernel forwarding path (e.g. ip[6]_forward) to keep the delivery_time also. A very similar IPv6 defrag codes have been duplicated in multiple places: regular IPv6, nf_conntrack, and 6lowpan. Unlike the IPv4 defrag which is done before ip_local_deliver_finish(), the regular IPv6 defrag is done after ip6_input_finish(). Thus, no change should be needed in the regular IPv6 defrag logic because skb_clear_delivery_time() should have been called. 6lowpan also does not need special handling on delivery_time because it is a non-inet packet_type. However, cf_conntrack has a case in NF_INET_PRE_ROUTING that needs to do the IPv6 defrag earlier. Thus, it needs to save the mono_delivery_time bit in the inet_frag_queue which is similar to how it is handled in the previous patch for the IPv4 defrag. This patch chooses to do it consistently and stores the mono_delivery_time in the inet_frag_queue for all cases such that it will be easier for the future refactoring effort on the IPv6 reasm code. Signed-off-by:
-
Martin KaFai Lau authored
A latter patch will postpone the delivery_time clearing until the stack knows the skb is being delivered locally. That will allow other kernel forwarding path (e.g. ip[6]_forward) to keep the delivery_time also. An earlier attempt was to do skb_clear_delivery_time() in ip_local_deliver() and ip6_input(). The discussion [0] requested to move it one step later into ip_local_deliver_finish() and ip6_input_finish() so that the delivery_time can be kept for the ip_vs forwarding path also. To do that, this patch also needs to take care of the (rcv) timestamp usecase in ip_is_fragment(). It needs to expect delivery_time in the skb->tstamp, so it needs to save the mono_delivery_time bit in inet_frag_queue such that the delivery_time (if any) can be restored in the final defragmented skb. [Note that it will only happen when the locally generated skb is looping from egress to ingress over a virtual interface (e.g. veth, loopback...), skb->tstamp may have the delivery time before it is known that it will be delivered locally and received by another sk.] [0]: https://lore.kernel.org/netdev/ca728d81-80e8-3767-d5e-d44f6ad96e43@ssi.bg/Signed-off-by:
-
Martin KaFai Lau authored
The previous patches handled the delivery_time before sch_handle_ingress(). This patch can now set the skb->mono_delivery_time to flag the skb->tstamp is used as the mono delivery_time (EDT) instead of the (rcv) timestamp and also clear it with skb_clear_delivery_time() after sch_handle_ingress(). This will make the bpf_redirect_*() to keep the mono delivery_time and used by a qdisc (fq) of the egress-ing interface. A latter patch will postpone the skb_clear_delivery_time() until the stack learns that the skb is being delivered locally and that will make other kernel forwarding paths (ip[6]_forward) able to keep the delivery_time also. Thus, like the previous patches on using the skb->mono_delivery_time bit, calling skb_clear_delivery_time() is not limited within the CONFIG_NET_INGRESS to avoid too many code churns among this set. Signed-off-by:
-
Martin KaFai Lau authored
In __skb_tstamp_tx(), it may clone the egress skb and queues the clone to the sk_error_queue. The outgoing skb may have the mono delivery_time while the (rcv) timestamp is expected for the clone, so the skb->mono_delivery_time bit needs to be cleared from the clone. This patch adds the skb->mono_delivery_time clearing to the existing __net_timestamp() and use it in __skb_tstamp_tx(). The __net_timestamp() fast path usage in dev.c is changed to directly call ktime_get_real() since the mono_delivery_time bit is not set at that point. Signed-off-by:
-
Martin KaFai Lau authored
A latter patch will set the skb->mono_delivery_time to flag the skb->tstamp is used as the mono delivery_time (EDT) instead of the (rcv) timestamp. skb_clear_tstamp() will then keep this delivery_time during forwarding. This patch is to make the network tapping (with af_packet) to handle the delivery_time stored in skb->tstamp. Regardless of tapping at the ingress or egress, the tapped skb is received by the af_packet socket, so it is ingress to the af_packet socket and it expects the (rcv) timestamp. When tapping at egress, dev_queue_xmit_nit() is used. It has already expected skb->tstamp may have delivery_time, so it does skb_clone()+net_timestamp_set() to ensure the cloned skb has the (rcv) timestamp before passing to the af_packet sk. This patch only adds to clear the skb->mono_delivery_time bit in net_timestamp_set(). When tapping at ingress, it currently expects the skb->tstamp is either 0 or the (rcv) timestamp. Meaning, the tapping at ingress path has already expected the skb->tstamp could be 0 and it will get the (rcv) timestamp by ktime_get_real() when needed. There are two cases for tapping at ingress: One case is af_packet queues the skb to its sk_receive_queue. The skb is either not shared or new clone created. The newly added skb_clear_delivery_time() is called to clear the delivery_time (if any) and set the (rcv) timestamp if needed before the skb is queued to the sk_receive_queue. Another case, the ingress skb is directly copied to the rx_ring and tpacket_get_timestamp() is used to get the (rcv) timestamp. The newly added skb_tstamp() is used in tpacket_get_timestamp() to check the skb->mono_delivery_time bit before returning skb->tstamp. As mentioned earlier, the tapping@ingress has already expected the skb may not have the (rcv) timestamp (because no sk has asked for it) and has handled this case by directly calling ktime_get_real(). Signed-off-by:
-
Martin KaFai Lau authored
Right now, skb->tstamp is reset to 0 whenever the skb is forwarded. If skb->tstamp has the mono delivery_time, clearing it can hurt the performance when it finally transmits out to fq@phy-dev. The earlier patch added a skb->mono_delivery_time bit to flag the skb->tstamp carrying the mono delivery_time. This patch adds skb_clear_tstamp() helper which keeps the mono delivery_time and clears everything else. The delivery_time clearing will be postponed until the stack knows the skb will be delivered locally. It will be done in a latter patch. Signed-off-by:
-
Martin KaFai Lau authored
skb->tstamp was first used as the (rcv) timestamp. The major usage is to report it to the user (e.g. SO_TIMESTAMP). Later, skb->tstamp is also set as the (future) delivery_time (e.g. EDT in TCP) during egress and used by the qdisc (e.g. sch_fq) to make decision on when the skb can be passed to the dev. Currently, there is no way to tell skb->tstamp having the (rcv) timestamp or the delivery_time, so it is always reset to 0 whenever forwarded between egress and ingress. While it makes sense to always clear the (rcv) timestamp in skb->tstamp to avoid confusing sch_fq that expects the delivery_time, it is a performance issue [0] to clear the delivery_time if the skb finally egress to a fq@phy-dev. For example, when forwarding from egress to ingress and then finally back to egress: tcp-sender => veth@netns => veth@hostns => fq@eth0@hostns ^ ^ reset rest This patch adds one bit skb->mono_delivery_time to flag the skb->tstamp is storing the mono delivery_time (EDT) instead of the (rcv) timestamp. The current use case is to keep the TCP mono delivery_time (EDT) and to be used with sch_fq. A latter patch will also allow tc-bpf@ingress to read and change the mono delivery_time. In the future, another bit (e.g. skb->user_delivery_time) can be added for the SCM_TXTIME where the clock base is tracked by sk->sk_clockid. [ This patch is a prep work. The following patches will get the other parts of the stack ready first. Then another patch after that will finally set the skb->mono_delivery_time. ] skb_set_delivery_time() function is added. It is used by the tcp_output.c and during ip[6] fragmentation to assign the delivery_time to the skb->tstamp and also set the skb->mono_delivery_time. A note on the change in ip_send_unicast_reply() in ip_output.c. It is only used by TCP to send reset/ack out of a ctl_sk. Like the new skb_set_delivery_time(), this patch sets the skb->mono_delivery_time to 0 for now as a place holder. It will be enabled in a latter patch. A similar case in tcp_ipv6 can be done with skb_set_delivery_time() in tcp_v6_send_response(). [0] (slide 22): https://linuxplumbersconf.org/event/11/contributions/953/attachments/867/1658/LPC_2021_BPF_Datapath_Extensions.pdfSigned-off-by: -
David S. Miller authored
Vladimir Oltean says: ==================== DSA unicast filtering This series doesn't attempt anything extremely brave, it just changes the way in which standalone ports which support FDB isolation work. Up until now, DSA has recommended that switch drivers configure standalone ports in a separate VID/FID with learning disabled, and with the CPU port as the only destination, reached trivially via flooding. That works, except that standalone ports will deliver all packets to the CPU. We can leverage the hardware FDB as a MAC DA filter, and disable flooding towards the CPU port, to force the dropping of packets with unknown MAC DA. We handle port promiscuity by re-enabling flooding towards the CPU port. This is relevant because the bridge puts its automatic (learning + flooding) ports in promiscuous mode, and this makes some things work automagically, like for example bridging with a foreign interface. We don't delve yet into the territory of managing CPU flooding more aggressively while under a bridge. The only switch driver that benefits from this work right now is the NXP LS1028A switch (felix). The others need to implement FDB isolation first, before DSA is going to install entries to the port's standalone database. Otherwise, these entries might collide with bridge FDB/MDB entries. This work was done mainly to have all the required features in place before somebody starts seriously architecting DSA support for multiple CPU ports. Otherwise it is much more difficult to bolt these features on top of multiple CPU ports. ==================== Signed-off-by: -
Vladimir Oltean authored
In order for the Felix DSA driver to be able to turn on/off flooding towards its CPU port, we need to redirect calls on the NPI port to actually act upon the index in the analyzer block that corresponds to the CPU port module. This was never necessary until now because DSA (or the bridge) never called ocelot_port_bridge_flags() for the NPI port. Signed-off-by:
Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by:
-
Vladimir Oltean authored
felix_migrate_flood_to_tag_8021q_port() takes care of clearing the flooding bits on the old CPU port (which was the CPU port module), so manually clearing this bit from PGID_UC, PGID_MC, PGID_BC is redundant. Signed-off-by:
-
Vladimir Oltean authored
The driver probes with all ports as standalone, and it supports unicast filtering. So DSA will call port_fdb_add() for all necessary addresses on the current CPU port. We also handle migrations when the CPU port hardware resource changes (on tagging protocol change), so there should not be any unknown address that we have to receive while not promiscuous. Signed-off-by:
-
Vladimir Oltean authored
When the tagging protocol changes from "ocelot" to "ocelot-8021q" or in reverse, the DSA promiscuity setting that was applied for the old CPU port must be transferred to the new one. Signed-off-by:
-
Vladimir Oltean authored
The "ocelot" and "ocelot-8021q" tagging protocols make use of different hardware resources, and host FDB entries have different destination ports in the switch analyzer module, practically speaking. So when the user requests a tagging protocol change, the driver must migrate all host FDB and MDB entries from the NPI port (in fact CPU port module) towards the same physical port, but this time used as a regular port. It is pointless for the felix driver to keep a copy of the host addresses, when we can create and export DSA helpers for walking through the addresses that it already needs to keep on the CPU port, for refcounting purposes. felix_classify_db() is moved up to avoid a forward declaration. We pass "bool change" because dp->fdbs and dp->mdbs are uninitialized lists when felix_setup() first calls felix_set_tag_protocol(), so we need to avoid calling dsa_port_walk_fdbs() during probe time. Signed-off-by:
-
Vladimir Oltean authored
DSA can treat IFF_PROMISC and IFF_ALLMULTI on standalone user ports as signifying whether packets with an unknown MAC DA will be received or not. Since known MAC DAs are handled by FDB/MDB entries, this means that promiscuity is analogous to including/excluding the CPU port from the flood domain of those packets. There are two ways to signal CPU flooding to drivers. The first (chosen here) is to synthesize a call to ds->ops->port_bridge_flags() for the CPU port, with a mask of BR_FLOOD | BR_MCAST_FLOOD. This has the effect of turning on egress flooding on the CPU port regardless of source. The alternative would be to create a new ds->ops->port_host_flood() which is called per user port. Some switches (sja1105) have a flood domain that is managed per {ingress port, egress port} pair, so it would make more sense for this kind of switch to not flood the CPU from port A if just port B requires it. Nonetheless, the sja1105 has other quirks that prevent it from making use of unicast filtering, and without a concrete user making use of this feature, I chose not to implement it. Signed-off-by: -
Vladimir Oltean authored
To be able to safely turn off CPU flooding for standalone ports, we need to ensure that the dev_addr of each DSA slave interface is installed as a standalone host FDB entry for compatible switches. Signed-off-by:
-
Vladimir Oltean authored
In preparation of disabling flooding towards the CPU in standalone ports mode, identify the addresses requested by upper interfaces and use the new API for DSA FDB isolation to request the hardware driver to offload these as FDB or MDB objects. The objects belong to the user port's database, and are installed pointing towards the CPU port. Because dev_uc_add()/dev_mc_add() is VLAN-unaware, we offload to the port standalone database addresses with VID 0 (also VLAN-unaware). So this excludes switches with global VLAN filtering from supporting unicast filtering, because there, it is possible for a port of a switch to join a VLAN-aware bridge, and this changes the VLAN awareness of standalone ports, requiring VLAN-aware standalone host FDB entries. For the same reason, hellcreek, which requires VLAN awareness in standalone mode, is also exempted from unicast filtering. We create "standalone" variants of dsa_port_host_fdb_add() and dsa_port_host_mdb_add() (and the _del coresponding functions). We also create a separate work item type for handling deferred standalone host FDB/MDB entries compared to the switchdev one. This is done for the purpose of clarity - the procedure for offloading a bridge FDB entry is different than offloading a standalone one, and the switchdev event work handles only FDBs anyway, not MDBs. Deferral is needed for standalone entries because ndo_set_rx_mode runs in atomic context. We could probably optimize things a little by first queuing up all entries that need to be offloaded, and scheduling the work item just once, but the data structures that we can pass through __dev_uc_sync() and __dev_mc_sync() are limiting (there is nothing like a void *priv), so we'd have to keep the list of queued events somewhere in struct dsa_switch, and possibly a lock for it. Too complicated for now. Adding the address to the master is handled by dev_uc_sync(), adding it to the hardware is handled by __dev_uc_sync(). So this is the reason why dsa_port_standalone_host_fdb_add() does not call dev_uc_add(). Not that it had the rtnl_mutex anyway - ndo_set_rx_mode has it, but is atomic. Signed-off-by:
-
Vladimir Oltean authored
We are preparing to add API in port.c that adds FDB and MDB entries that correspond to the port's standalone database. Rename the existing methods to make it clear that the FDB and MDB entries offloaded come from the bridge database. Since the function names lengthen in dsa_slave_switchdev_event_work(), we place "addr" and "vid" in temporary variables, to shorten those. Signed-off-by:
-
Vladimir Oltean authored
Lennert Buytenhek explains in commit df02c6ff ("dsa: fix master interface allmulti/promisc handling"), dated Nov 2008, that changing the promiscuity of interfaces that are down (here the master) is broken. This fact regarding promisc/allmulti has changed since commit b6c40d68 ("net: only invoke dev->change_rx_flags when device is UP") by Vlad Yasevich, dated Nov 2013. Therefore, DSA now has unnecessary complexity to handle master state transitions from down to up. In fact, syncing the unicast and multicast addresses can happen completely asynchronously to the administrative state changes. This change reduces that complexity by effectively fully reverting commit df02c6ff ("dsa: fix master interface allmulti/promisc handling"). Signed-off-by:
-
Karol Kolacinski authored
Add a new ice_gnss.c file for holding the basic GNSS module functions. If the device supports GNSS module, call the new ice_gnss_init and ice_gnss_release functions where appropriate. Implement basic functionality for reading the data from GNSS module using TTY device. Add I2C read AQ command. It is now required for controlling the external physical connectors via external I2C port expander on E810-T adapters. Future changes will introduce write functionality. Signed-off-by:
Karol Kolacinski <karol.kolacinski@intel.com> Signed-off-by:
Sudhansu Sekhar Mishra <sudhansu.mishra@intel.com> Tested-by:
Sunitha Mekala <sunithax.d.mekala@intel.com> Signed-off-by:
Tony Nguyen <anthony.l.nguyen@intel.com> Signed-off-by:
-
David S. Miller authored
Krzysztof Kozlowski says: ==================== nfc: llcp: few cleanups/improvements These are improvements, not fixing any experienced issue, just looking correct to me from the code point of view. Changes since v1 ================ 1. Split from the fix. Testing ======= Under QEMU only. The NFC/LLCP code was not really tested on a device. ==================== Signed-off-by: -
Krzysztof Kozlowski authored
This reverts commit 17f7ae16. The commit brought a new socket state LLCP_DISCONNECTING, which was never set, only read, so socket could never set to such state. Remove the dead code. Signed-off-by:
Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> Signed-off-by:
-
Krzysztof Kozlowski authored
nfc_llcp_sock_link() is called in all paths (bind/connect) as a last action, still protected with lock_sock(). When cleaning up in llcp_sock_release(), call nfc_llcp_sock_unlink() in a mirrored way: earlier and still under the lock_sock(). Signed-off-by:
-
Krzysztof Kozlowski authored
Use test_bit() instead of open-coding it, just like in other places touching the bitmap. Signed-off-by:
-
Krzysztof Kozlowski authored
Coding style encourages centralized exiting of functions, so rewrite llcp_sock_bind() error paths to use such pattern. This reduces the duplicated cleanup code, make success path visually shorter and also cleans up the errors in proper order (in reversed way from initialization). No functional impact expected. Signed-off-by:
-
Krzysztof Kozlowski authored
The llcp_sock_connect() error paths were using a mixed way of central exit (goto) and cleanup Signed-off-by:
-
Krzysztof Kozlowski authored
Nullify the llcp_sock->dev on llcp_sock_connect() error paths, symmetrically to the code llcp_sock_bind(). The non-NULL value of llcp_sock->dev is used in a few places to check whether the socket is still valid. There was no particular issue observed with missing NULL assignment in connect() error path, however a similar case - in the bind() error path - was triggereable. That one was fixed in commit 4ac06a1e ("nfc: fix NULL ptr dereference in llcp_sock_getname() after failed connect"), so the change here seems logical as well. Signed-off-by:
-
David S. Miller authored
Ido Schimmel says: ==================== HW counters for soft devices Petr says: Offloading switch device drivers may be able to collect statistics of the traffic taking place in the HW datapath that pertains to a certain soft netdevice, such as a VLAN. In this patch set, add the necessary infrastructure to allow exposing these statistics to the offloaded netdevice in question, and add mlxsw offload. Across HW platforms, the counter itself very likely constitutes a limited resource, and the act of counting may have a performance impact. Therefore this patch set makes the HW statistics collection opt-in and togglable from userspace on a per-netdevice basis. Additionally, HW devices may have various limiting conditions under which they can realize the counter. Therefore it is also possible to query whether the requested counter is realized by any driver. In TC parlance, which is to a degree reused in this patch set, two values are recognized: "request" tracks whether the user enabled collecting HW statistics, and "used" tracks whether any HW statistics are actually collected. In the past, this author has expressed the opinion that `a typical user doing "ip -s l sh", including various scripts, wants to see the full picture and not worry what's going on where'. While that would be nice, unfortunately it cannot work: - Packets that trap from the HW datapath to the SW datapath would be double counted. For a given netdevice, some traffic can be purely a SW artifact, and some may flow through the HW object corresponding to the netdevice. But some traffic can also get trapped to the SW datapath after bumping the HW counter. It is not clear how to make sure double-counting does not occur in the SW datapath in that case, while still making sure that possibly divergent SW forwarding path gets bumped as appropriate. So simply adding HW and SW stats may work roughly, most of the time, but there are scenarios where the result is nonsensical. - HW devices will have limitations as to what type of traffic they can count. In case of mlxsw, which is part of this patch set, there is no reasonable way to count all traffic going through a certain netdevice, such as a VLAN netdevice enslaved to a bridge. It is however very simple to count traffic flowing through an L3 object, such as a VLAN netdevice with an IP address. Similarly for physical netdevices, the L3 object at which the counter is installed is the subport carrying untagged traffic. These are not "just counters". It is important that the user understands what is being counted. It would be incorrect to conflate these statistics with another existing statistics suite. To that end, this patch set introduces a statistics suite called "L3 stats". This label should make it easy to understand what is being counted, and to decide whether a given device can or cannot implement this suite for some type of netdevice. At the same time, the code is written to make future extensions easy, should a device pop up that can implement a different flavor of statistics suite (say L2, or an address-family-specific suite). For example, using a work-in-progress iproute2[1], to turn on and then list the counters on a VLAN netdevice: # ip stats set dev swp1.200 l3_stats on # ip stats show dev swp1.200 group offload subgroup l3_stats 56: swp1.200: group offload subgroup l3_stats on used on RX: bytes packets errors dropped missed mcast 0 0 0 0 0 0 TX: bytes packets errors dropped carrier collsns 0 0 0 0 0 0 The patchset progresses as follows: - Patch #1 is a cleanup. - In patch #2, remove the assumption that all LINK_OFFLOAD_XSTATS are dev-backed. The only attribute defined under the nest is currently IFLA_OFFLOAD_XSTATS_CPU_HIT. L3_STATS differs from CPU_HIT in that the driver that supplies the statistics is not the same as the driver that implements the netdevice. Make the code compatible with this in patch #2. - In patch #3, add the possibility to filter inside nests. The filter_mask field of RTM_GETSTATS header determines which top-level attributes should be included in the netlink response. This saves processing time by only including the bits that the user cares about instead of always dumping everything. This is doubly important for HW-backed statistics that would typically require a trip to the device to fetch the stats. In this patch, the UAPI is extended to allow filtering inside IFLA_STATS_LINK_OFFLOAD_XSTATS in particular, but the scheme is easily extensible to other nests as well. - In patch #4, propagate extack where we need it. In patch #5, make it possible to propagate errors from drivers to the user. - In patch #6, add the in-kernel APIs for keeping track of the new stats suite, and the notifiers that the core uses to communicate with the drivers. - In patch #7, add UAPI for obtaining the new stats suite. - In patch #8, add a new UAPI message, RTM_SETSTATS, which will carry the message to toggle the newly-added stats suite. In patch #9, add the toggle itself. At this point the core is ready for drivers to add support for the new stats suite. - In patches #10, #11 and #12, apply small tweaks to mlxsw code. - In patch #13, add support for L3 stats, which are realized as RIF counters. - Finally in patch #14, a selftest is added to the net/forwarding directory. Technically this is a HW-specific test, in that without a HW implementing the counters, it just will not pass. But devices that support L3 statistics at all are likely to be able to reuse this selftest, so it seems appropriate to put it in the general forwarding directory. We also have a netdevsim implementation, and a corresponding selftest that verifies specifically some of the core code. We intend to contribute these later. Interested parties can take a look at the raw code at [2]. [1] https://github.com/pmachata/iproute2/commits/soft_counters [2] https://github.com/pmachata/linux_mlxsw/commits/petrm_soft_counters_2 v2: - Patch #3: - Do not declare strict_start_type at the new policies, since they are used with nla_parse_nested() (sans _deprecated). - Use NLA_POLICY_NESTED to declare what the nest contents should be - Use NLA_POLICY_MASK instead of BITFIELD32 for the filtering attribute. - Patch #6: - s/monotonous/monotonic/ in commit message - Use a newly-added struct rtnl_hw_stats64 for stats transfer - Patch #7: - Use a newly-added struct rtnl_hw_stats64 for stats transfer - Patch #8: - Do not declare strict_start_type at the new policies, since they are used with nla_parse_nested() (sans _deprecated). - Patch #13: - Use a newly-added struct rtnl_hw_stats64 for stats transfer ==================== Signed-off-by: -
Petr Machata authored
Add a test that verifies operation of L3 HW statistics. Signed-off-by:
Petr Machata <petrm@nvidia.com> Signed-off-by:
Ido Schimmel <idosch@nvidia.com> Signed-off-by:
-
Petr Machata authored
Spectrum machines support L3 stats by binding a counter to a RIF, a hardware object representing a router interface. Recognize the netdevice notifier events, NETDEV_OFFLOAD_XSTATS_*, to support enablement, disablement, and reporting back to core. As a netdevice gains a RIF, if L3 stats are enabled, install the counters, and ping the core so that a userspace notification can be emitted. Similarly, as a netdevice loses a RIF, push the as-yet-unreported statistics to the core, so that they are not lost, and ping the core to emit userspace notification. Signed-off-by:
-
Petr Machata authored
Several more events are coming in the following patches, and extending the if statement is getting awkward. Instead, convert it to a switch. Signed-off-by:
-
Petr Machata authored
The mlxsw_sp reference is carried by the mlxsw_sp_rif object that is passed to these functions as well. Just deduce the former from the latter, and drop the explicit mlxsw_sp parameter. Adapt callers. Signed-off-by:
-
Petr Machata authored
The function mlxsw_reg_ritr_counter_pack() formats a register to configure a router interface (RIF) counter. The parameter `egress' determines whether an ingress or egress counter is to be configured. RITR, the register in question, has two sets of counter-related fields: one for ingress, one for egress. When setting values of the fields, the function sets the proper counter index field, but when setting the counter type, it always sets the egress field. Thus configuration of ingress counters is broken, and in fact an attempt to configure an ingress counter mangles a previously configured egress counter. This was never discovered, because there is currently no way to enable ingress counters on a router interface, only the egress one. Fix in an obvious way. Signed-off-by:
-
Petr Machata authored
The offloaded HW stats are designed to allow per-netdevice enablement and disablement. Add an attribute, IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, which should be carried by the RTM_SETSTATS message, and expresses a desire to toggle L3 offload xstats on or off. As part of the above, add an exported function rtnl_offload_xstats_notify() that drivers can use when they have installed or deinstalled the counters backing the HW stats. At this point, it is possible to enable, disable and query L3 offload xstats on netdevices. (However there is no driver actually implementing these.) Signed-off-by:
-
Petr Machata authored
The offloaded HW stats are designed to allow per-netdevice enablement and disablement. These stats are only accessible through RTM_GETSTATS, and therefore should be toggled by a RTM_SETSTATS message. Add it, and the necessary skeleton handler. Signed-off-by:
-
