diff options
Diffstat (limited to 'net/sched')
91 files changed, 34241 insertions, 12228 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e70ed26485a2..6ddff028b81a 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -1,11 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Traffic control configuration. -# +# menuconfig NET_SCHED bool "QoS and/or fair queueing" select NET_SCH_FIFO - ---help--- + help When the kernel has several packets to send out over a network device, it has to decide which ones to send first, which ones to delay, and which ones to drop. This is the job of the queueing @@ -44,26 +45,9 @@ if NET_SCHED comment "Queueing/Scheduling" -config NET_SCH_CBQ - tristate "Class Based Queueing (CBQ)" - ---help--- - Say Y here if you want to use the Class-Based Queueing (CBQ) packet - scheduling algorithm. This algorithm classifies the waiting packets - into a tree-like hierarchy of classes; the leaves of this tree are - in turn scheduled by separate algorithms. - - See the top of <file:net/sched/sch_cbq.c> for more details. - - CBQ is a commonly used scheduler, so if you're unsure, you should - say Y here. Then say Y to all the queueing algorithms below that you - want to use as leaf disciplines. - - To compile this code as a module, choose M here: the - module will be called sch_cbq. - config NET_SCH_HTB tristate "Hierarchical Token Bucket (HTB)" - ---help--- + help Say Y here if you want to use the Hierarchical Token Buckets (HTB) packet scheduling algorithm. See <http://luxik.cdi.cz/~devik/qos/htb/> for complete manual and @@ -77,30 +61,16 @@ config NET_SCH_HTB config NET_SCH_HFSC tristate "Hierarchical Fair Service Curve (HFSC)" - ---help--- + help Say Y here if you want to use the Hierarchical Fair Service Curve (HFSC) packet scheduling algorithm. To compile this code as a module, choose M here: the module will be called sch_hfsc. -config NET_SCH_ATM - tristate "ATM Virtual Circuits (ATM)" - depends on ATM - ---help--- - Say Y here if you want to use the ATM pseudo-scheduler. This - provides a framework for invoking classifiers, which in turn - select classes of this queuing discipline. Each class maps - the flow(s) it is handling to a given virtual circuit. - - See the top of <file:net/sched/sch_atm.c> for more details. - - To compile this code as a module, choose M here: the - module will be called sch_atm. - config NET_SCH_PRIO tristate "Multi Band Priority Queueing (PRIO)" - ---help--- + help Say Y here if you want to use an n-band priority queue packet scheduler. @@ -109,7 +79,7 @@ config NET_SCH_PRIO config NET_SCH_MULTIQ tristate "Hardware Multiqueue-aware Multi Band Queuing (MULTIQ)" - ---help--- + help Say Y here if you want to use an n-band queue packet scheduler to support devices that have multiple hardware transmit queues. @@ -118,7 +88,7 @@ config NET_SCH_MULTIQ config NET_SCH_RED tristate "Random Early Detection (RED)" - ---help--- + help Say Y here if you want to use the Random Early Detection (RED) packet scheduling algorithm. @@ -129,7 +99,7 @@ config NET_SCH_RED config NET_SCH_SFB tristate "Stochastic Fair Blue (SFB)" - ---help--- + help Say Y here if you want to use the Stochastic Fair Blue (SFB) packet scheduling algorithm. @@ -140,7 +110,7 @@ config NET_SCH_SFB config NET_SCH_SFQ tristate "Stochastic Fairness Queueing (SFQ)" - ---help--- + help Say Y here if you want to use the Stochastic Fairness Queueing (SFQ) packet scheduling algorithm. @@ -151,7 +121,7 @@ config NET_SCH_SFQ config NET_SCH_TEQL tristate "True Link Equalizer (TEQL)" - ---help--- + help Say Y here if you want to use the True Link Equalizer (TLE) packet scheduling algorithm. This queueing discipline allows the combination of several physical devices into one virtual device. @@ -163,7 +133,7 @@ config NET_SCH_TEQL config NET_SCH_TBF tristate "Token Bucket Filter (TBF)" - ---help--- + help Say Y here if you want to use the Token Bucket Filter (TBF) packet scheduling algorithm. @@ -172,9 +142,48 @@ config NET_SCH_TBF To compile this code as a module, choose M here: the module will be called sch_tbf. +config NET_SCH_CBS + tristate "Credit Based Shaper (CBS)" + help + Say Y here if you want to use the Credit Based Shaper (CBS) packet + scheduling algorithm. + + See the top of <file:net/sched/sch_cbs.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_cbs. + +config NET_SCH_ETF + tristate "Earliest TxTime First (ETF)" + help + Say Y here if you want to use the Earliest TxTime First (ETF) packet + scheduling algorithm. + + See the top of <file:net/sched/sch_etf.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_etf. + +config NET_SCH_MQPRIO_LIB + tristate + help + Common library for manipulating mqprio queue configurations. + +config NET_SCH_TAPRIO + tristate "Time Aware Priority (taprio) Scheduler" + select NET_SCH_MQPRIO_LIB + help + Say Y here if you want to use the Time Aware Priority (taprio) packet + scheduling algorithm. + + See the top of <file:net/sched/sch_taprio.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_taprio. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" - ---help--- + help Say Y here if you want to use the Generic Random Early Detection (GRED) packet scheduling algorithm for some of your network devices (see the top of <file:net/sched/sch_red.c> for details and @@ -183,20 +192,9 @@ config NET_SCH_GRED To compile this code as a module, choose M here: the module will be called sch_gred. -config NET_SCH_DSMARK - tristate "Differentiated Services marker (DSMARK)" - ---help--- - Say Y if you want to schedule packets according to the - Differentiated Services architecture proposed in RFC 2475. - Technical information on this method, with pointers to associated - RFCs, is available at <http://www.gta.ufrj.br/diffserv/>. - - To compile this code as a module, choose M here: the - module will be called sch_dsmark. - config NET_SCH_NETEM tristate "Network emulator (NETEM)" - ---help--- + help Say Y if you want to emulate network delay, loss, and packet re-ordering. This is often useful to simulate networks when testing applications or protocols. @@ -219,6 +217,7 @@ config NET_SCH_DRR config NET_SCH_MQPRIO tristate "Multi-queue priority scheduler (MQPRIO)" + select NET_SCH_MQPRIO_LIB help Say Y here if you want to use the Multi-queue Priority scheduler. This scheduler allows QOS to be offloaded on NICs that have support @@ -229,12 +228,25 @@ config NET_SCH_MQPRIO If unsure, say N. +config NET_SCH_SKBPRIO + tristate "SKB priority queue scheduler (SKBPRIO)" + help + Say Y here if you want to use the SKB priority queue + scheduler. This schedules packets according to skb->priority, + which is useful for request packets in DoS mitigation systems such + as Gatekeeper. + + To compile this driver as a module, choose M here: the module will + be called sch_skbprio. + + If unsure, say N. + config NET_SCH_CHOKE tristate "CHOose and Keep responsive flow scheduler (CHOKE)" help Say Y here if you want to use the CHOKe packet scheduler (CHOose and Keep for responsive flows, CHOose and Kill for unresponsive - flows). This is a variation of RED which trys to penalize flows + flows). This is a variation of RED which tries to penalize flows that monopolize the queue. To compile this code as a module, choose M here: the @@ -273,13 +285,24 @@ config NET_SCH_FQ_CODEL If unsure, say N. +config NET_SCH_CAKE + tristate "Common Applications Kept Enhanced (CAKE)" + help + Say Y here if you want to use the Common Applications Kept Enhanced + (CAKE) queue management algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_cake. + + If unsure, say N. + config NET_SCH_FQ tristate "Fair Queue" help Say Y here if you want to use the FQ packet scheduling algorithm. FQ does flow separation, and is able to respect pacing requirements - set by TCP stack into sk->sk_pacing_rate (for localy generated + set by TCP stack into sk->sk_pacing_rate (for locally generated traffic) To compile this driver as a module, choose M here: the module @@ -301,20 +324,31 @@ config NET_SCH_PIE help Say Y here if you want to use the Proportional Integral controller Enhanced scheduler packet scheduling algorithm. - For more information, please see - http://tools.ietf.org/html/draft-pan-tsvwg-pie-00 + For more information, please see https://tools.ietf.org/html/rfc8033 To compile this driver as a module, choose M here: the module will be called sch_pie. If unsure, say N. +config NET_SCH_FQ_PIE + depends on NET_SCH_PIE + tristate "Flow Queue Proportional Integral controller Enhanced (FQ-PIE)" + help + Say Y here if you want to use the Flow Queue Proportional Integral + controller Enhanced (FQ-PIE) packet scheduling algorithm. + For more information, please see https://tools.ietf.org/html/rfc8033 + + To compile this driver as a module, choose M here: the module + will be called sch_fq_pie. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress/classifier-action Qdisc" depends on NET_CLS_ACT - select NET_INGRESS - select NET_EGRESS - ---help--- + select NET_XGRESS + help Say Y here if you want to use classifiers for incoming and/or outgoing packets. This qdisc doesn't do anything else besides running classifiers, which can also have actions attached to them. In case of outgoing packets, @@ -328,7 +362,7 @@ config NET_SCH_INGRESS config NET_SCH_PLUG tristate "Plug network traffic until release (PLUG)" - ---help--- + help This queuing discipline allows userspace to plug/unplug a network output queue, using the netlink interface. When it receives an @@ -352,9 +386,50 @@ config NET_SCH_PLUG To compile this code as a module, choose M here: the module will be called sch_plug. +config NET_SCH_ETS + tristate "Enhanced transmission selection scheduler (ETS)" + help + The Enhanced Transmission Selection scheduler is a classful + queuing discipline that merges functionality of PRIO and DRR + qdiscs in one scheduler. ETS makes it easy to configure a set of + strict and bandwidth-sharing bands to implement the transmission + selection described in 802.1Qaz. + + Say Y here if you want to use the ETS packet scheduling + algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_ets. + + If unsure, say N. + +config NET_SCH_BPF + bool "BPF-based Qdisc" + depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF + help + This option allows BPF-based queueing disiplines. With BPF struct_ops, + users can implement supported operators in Qdisc_ops using BPF programs. + The queue holding skb can be built with BPF maps or graphs. + + Say Y here if you want to use BPF-based Qdisc. + + If unsure, say N. + +config NET_SCH_DUALPI2 + tristate "Dual Queue PI Square (DUALPI2) scheduler" + help + Say Y here if you want to use the Dual Queue Proportional Integral + Controller Improved with a Square scheduling algorithm. + For more information, please see https://tools.ietf.org/html/rfc9332 + + To compile this driver as a module, choose M here: the module + will be called sch_dualpi2. + + If unsure, say N. + menuconfig NET_SCH_DEFAULT bool "Allow override default queue discipline" - ---help--- + help Support for selection of default queuing discipline. Nearly all users can safely say no here, and the default @@ -381,6 +456,9 @@ choice config DEFAULT_FQ_CODEL bool "Fair Queue Controlled Delay" if NET_SCH_FQ_CODEL + config DEFAULT_FQ_PIE + bool "Flow Queue Proportional Integral controller Enhanced" if NET_SCH_FQ_PIE + config DEFAULT_SFQ bool "Stochastic Fair Queue" if NET_SCH_SFQ @@ -393,6 +471,7 @@ config DEFAULT_NET_SCH default "pfifo_fast" if DEFAULT_PFIFO_FAST default "fq" if DEFAULT_FQ default "fq_codel" if DEFAULT_FQ_CODEL + default "fq_pie" if DEFAULT_FQ_PIE default "sfq" if DEFAULT_SFQ default "pfifo_fast" endif @@ -405,30 +484,19 @@ config NET_CLS config NET_CLS_BASIC tristate "Elementary classification (BASIC)" select NET_CLS - ---help--- + help Say Y here if you want to be able to classify packets using only extended matches and actions. To compile this code as a module, choose M here: the module will be called cls_basic. -config NET_CLS_TCINDEX - tristate "Traffic-Control Index (TCINDEX)" - select NET_CLS - ---help--- - Say Y here if you want to be able to classify packets based on - traffic control indices. You will want this feature if you want - to implement Differentiated Services together with DSMARK. - - To compile this code as a module, choose M here: the - module will be called cls_tcindex. - config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" depends on INET select IP_ROUTE_CLASSID select NET_CLS - ---help--- + help If you say Y here, you will be able to classify packets according to the route table entry they matched. @@ -438,7 +506,7 @@ config NET_CLS_ROUTE4 config NET_CLS_FW tristate "Netfilter mark (FW)" select NET_CLS - ---help--- + help If you say Y here, you will be able to classify packets according to netfilter/firewall marks. @@ -448,7 +516,7 @@ config NET_CLS_FW config NET_CLS_U32 tristate "Universal 32bit comparisons w/ hashing (U32)" select NET_CLS - ---help--- + help Say Y here to be able to classify packets using a universal 32bit pieces based comparison scheme. @@ -458,48 +526,20 @@ config NET_CLS_U32 config CLS_U32_PERF bool "Performance counters support" depends on NET_CLS_U32 - ---help--- + help Say Y here to make u32 gather additional statistics useful for fine tuning u32 classifiers. config CLS_U32_MARK bool "Netfilter marks support" depends on NET_CLS_U32 - ---help--- + help Say Y here to be able to use netfilter marks as u32 key. -config NET_CLS_RSVP - tristate "IPv4 Resource Reservation Protocol (RSVP)" - select NET_CLS - ---help--- - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp. - -config NET_CLS_RSVP6 - tristate "IPv6 Resource Reservation Protocol (RSVP6)" - select NET_CLS - ---help--- - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests and you are using the IPv6 protocol. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp6. - config NET_CLS_FLOW tristate "Flow classifier" select NET_CLS - ---help--- + help If you say Y here, you will be able to classify packets based on a configurable combination of packet keys. This is mostly useful in combination with SFQ. @@ -512,7 +552,7 @@ config NET_CLS_CGROUP select NET_CLS select CGROUP_NET_CLASSID depends on CGROUPS - ---help--- + help Say Y here if you want to classify packets based on the control cgroup of their process. @@ -522,7 +562,7 @@ config NET_CLS_CGROUP config NET_CLS_BPF tristate "BPF-based classifier" select NET_CLS - ---help--- + help If you say Y here, you will be able to classify packets based on programmable BPF (JIT'ed) filters as an alternative to ematches. @@ -532,7 +572,7 @@ config NET_CLS_BPF config NET_CLS_FLOWER tristate "Flower classifier" select NET_CLS - ---help--- + help If you say Y here, you will be able to classify packets based on a configurable combination of packet keys and masks. @@ -542,7 +582,7 @@ config NET_CLS_FLOWER config NET_CLS_MATCHALL tristate "Match-all classifier" select NET_CLS - ---help--- + help If you say Y here, you will be able to classify packets based on nothing. Every packet will match. @@ -552,7 +592,7 @@ config NET_CLS_MATCHALL config NET_EMATCH bool "Extended Matches" select NET_CLS - ---help--- + help Say Y here if you want to use extended matches on top of classifiers and select the extended matches below. @@ -566,7 +606,7 @@ config NET_EMATCH_STACK int "Stack size" depends on NET_EMATCH default "32" - ---help--- + help Size of the local stack variable used while evaluating the tree of ematches. Limits the depth of the tree, i.e. the number of encapsulated precedences. Every level requires 4 bytes of additional @@ -575,7 +615,7 @@ config NET_EMATCH_STACK config NET_EMATCH_CMP tristate "Simple packet data comparison" depends on NET_EMATCH - ---help--- + help Say Y here if you want to be able to classify packets based on simple packet data comparisons for 8, 16, and 32bit values. @@ -585,7 +625,7 @@ config NET_EMATCH_CMP config NET_EMATCH_NBYTE tristate "Multi byte comparison" depends on NET_EMATCH - ---help--- + help Say Y here if you want to be able to classify packets based on multiple byte comparisons mainly useful for IPv6 address comparisons. @@ -595,7 +635,7 @@ config NET_EMATCH_NBYTE config NET_EMATCH_U32 tristate "U32 key" depends on NET_EMATCH - ---help--- + help Say Y here if you want to be able to classify packets using the famous u32 key in combination with logic relations. @@ -605,7 +645,7 @@ config NET_EMATCH_U32 config NET_EMATCH_META tristate "Metadata" depends on NET_EMATCH - ---help--- + help Say Y here if you want to be able to classify packets based on metadata such as load average, netfilter attributes, socket attributes and routing decisions. @@ -620,7 +660,7 @@ config NET_EMATCH_TEXT select TEXTSEARCH_KMP select TEXTSEARCH_BM select TEXTSEARCH_FSM - ---help--- + help Say Y here if you want to be able to classify packets based on textsearch comparisons. @@ -630,7 +670,7 @@ config NET_EMATCH_TEXT config NET_EMATCH_CANID tristate "CAN Identifier" depends on NET_EMATCH && (CAN=y || CAN=m) - ---help--- + help Say Y here if you want to be able to classify CAN frames based on CAN Identifier. @@ -640,17 +680,30 @@ config NET_EMATCH_CANID config NET_EMATCH_IPSET tristate "IPset" depends on NET_EMATCH && IP_SET - ---help--- + help Say Y here if you want to be able to classify packets based on ipset membership. To compile this code as a module, choose M here: the module will be called em_ipset. +config NET_EMATCH_IPT + tristate "IPtables Matches" + depends on NET_EMATCH && NETFILTER && NETFILTER_XTABLES + help + Say Y here to be able to classify packets based on iptables + matches. + Current supported match is "policy" which allows packet classification + based on IPsec policy that was used during decapsulation + + To compile this code as a module, choose M here: the + module will be called em_ipt. + config NET_CLS_ACT bool "Actions" select NET_CLS - ---help--- + select NET_XGRESS + help Say Y here if you want to use traffic control actions. Actions get attached to classifiers and are invoked after a successful classification. They are used to overwrite the classification @@ -661,8 +714,8 @@ config NET_CLS_ACT config NET_ACT_POLICE tristate "Traffic Policing" - depends on NET_CLS_ACT - ---help--- + depends on NET_CLS_ACT + help Say Y here if you want to do traffic policing, i.e. strict bandwidth limiting. This action replaces the existing policing module. @@ -671,9 +724,9 @@ config NET_ACT_POLICE module will be called act_police. config NET_ACT_GACT - tristate "Generic actions" - depends on NET_CLS_ACT - ---help--- + tristate "Generic actions" + depends on NET_CLS_ACT + help Say Y here to take generic actions such as dropping and accepting packets. @@ -681,15 +734,15 @@ config NET_ACT_GACT module will be called act_gact. config GACT_PROB - bool "Probability support" - depends on NET_ACT_GACT - ---help--- + bool "Probability support" + depends on NET_ACT_GACT + help Say Y here to use the generic action randomly or deterministically. config NET_ACT_MIRRED - tristate "Redirecting and Mirroring" - depends on NET_CLS_ACT - ---help--- + tristate "Redirecting and Mirroring" + depends on NET_CLS_ACT + help Say Y here to allow packets to be mirrored or redirected to other devices. @@ -697,10 +750,10 @@ config NET_ACT_MIRRED module will be called act_mirred. config NET_ACT_SAMPLE - tristate "Traffic Sampling" - depends on NET_CLS_ACT - select PSAMPLE - ---help--- + tristate "Traffic Sampling" + depends on NET_CLS_ACT + select PSAMPLE + help Say Y here to allow packet sampling tc action. The packet sample action consists of statistically choosing packets and sampling them using the psample module. @@ -708,20 +761,10 @@ config NET_ACT_SAMPLE To compile this code as a module, choose M here: the module will be called act_sample. -config NET_ACT_IPT - tristate "IPtables targets" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - ---help--- - Say Y here to be able to invoke iptables targets after successful - classification. - - To compile this code as a module, choose M here: the - module will be called act_ipt. - config NET_ACT_NAT - tristate "Stateless NAT" - depends on NET_CLS_ACT - ---help--- + tristate "Stateless NAT" + depends on NET_CLS_ACT + help Say Y here to do stateless NAT on IPv4 packets. You should use netfilter for NAT unless you know what you are doing. @@ -729,18 +772,18 @@ config NET_ACT_NAT module will be called act_nat. config NET_ACT_PEDIT - tristate "Packet Editing" - depends on NET_CLS_ACT - ---help--- + tristate "Packet Editing" + depends on NET_CLS_ACT + help Say Y here if you want to mangle the content of packets. To compile this code as a module, choose M here: the module will be called act_pedit. config NET_ACT_SIMP - tristate "Simple Example (Debug)" - depends on NET_CLS_ACT - ---help--- + tristate "Simple Example (Debug)" + depends on NET_CLS_ACT + help Say Y here to add a simple action for demonstration purposes. It is meant as an example and for debugging purposes. It will print a configured policy string followed by the packet count @@ -752,9 +795,9 @@ config NET_ACT_SIMP module will be called act_simple. config NET_ACT_SKBEDIT - tristate "SKB Editing" - depends on NET_CLS_ACT - ---help--- + tristate "SKB Editing" + depends on NET_CLS_ACT + help Say Y here to change skb priority or queue_mapping settings. If unsure, say N. @@ -763,20 +806,31 @@ config NET_ACT_SKBEDIT module will be called act_skbedit. config NET_ACT_CSUM - tristate "Checksum Updating" - depends on NET_CLS_ACT && INET - select LIBCRC32C - ---help--- + tristate "Checksum Updating" + depends on NET_CLS_ACT && INET + select NET_CRC32C + help Say Y here to update some common checksum after some direct packet alterations. To compile this code as a module, choose M here: the module will be called act_csum. +config NET_ACT_MPLS + tristate "MPLS manipulation" + depends on NET_CLS_ACT + help + Say Y here to push or pop MPLS headers. + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_mpls. + config NET_ACT_VLAN - tristate "Vlan manipulation" - depends on NET_CLS_ACT - ---help--- + tristate "Vlan manipulation" + depends on NET_CLS_ACT + help Say Y here to push or pop vlan headers. If unsure, say N. @@ -785,9 +839,9 @@ config NET_ACT_VLAN module will be called act_vlan. config NET_ACT_BPF - tristate "BPF based action" - depends on NET_CLS_ACT - ---help--- + tristate "BPF based action" + depends on NET_CLS_ACT + help Say Y here to execute BPF code on packets. The BPF code will decide if the packet should be dropped or not. @@ -797,10 +851,10 @@ config NET_ACT_BPF module will be called act_bpf. config NET_ACT_CONNMARK - tristate "Netfilter Connection Mark Retriever" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - depends on NF_CONNTRACK && NF_CONNTRACK_MARK - ---help--- + tristate "Netfilter Connection Mark Retriever" + depends on NET_CLS_ACT && NETFILTER + depends on NF_CONNTRACK && NF_CONNTRACK_MARK + help Say Y here to allow retrieving of conn mark If unsure, say N. @@ -808,22 +862,39 @@ config NET_ACT_CONNMARK To compile this code as a module, choose M here: the module will be called act_connmark. +config NET_ACT_CTINFO + tristate "Netfilter Connection Mark Actions" + depends on NET_CLS_ACT && NETFILTER + depends on NF_CONNTRACK && NF_CONNTRACK_MARK + help + Say Y here to allow transfer of a connmark stored information. + Current actions transfer connmark stored DSCP into + ipv4/v6 diffserv and/or to transfer connmark to packet + mark. Both are useful for restoring egress based marks + back onto ingress connections for qdisc priority mapping + purposes. + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_ctinfo. + config NET_ACT_SKBMOD - tristate "skb data modification action" - depends on NET_CLS_ACT - ---help--- - Say Y here to allow modification of skb data + tristate "skb data modification action" + depends on NET_CLS_ACT + help + Say Y here to allow modification of skb data - If unsure, say N. + If unsure, say N. - To compile this code as a module, choose M here: the - module will be called act_skbmod. + To compile this code as a module, choose M here: the + module will be called act_skbmod. config NET_ACT_IFE - tristate "Inter-FE action based on IETF ForCES InterFE LFB" - depends on NET_CLS_ACT - select NET_IFE - ---help--- + tristate "Inter-FE action based on IETF ForCES InterFE LFB" + depends on NET_CLS_ACT + select NET_IFE + help Say Y here to allow for sourcing and terminating metadata For details refer to netdev01 paper: "Distributing Linux Traffic Control Classifier-Action Subsystem" @@ -833,9 +904,9 @@ config NET_ACT_IFE module will be called act_ife. config NET_ACT_TUNNEL_KEY - tristate "IP tunnel metadata manipulation" - depends on NET_CLS_ACT - ---help--- + tristate "IP tunnel metadata manipulation" + depends on NET_CLS_ACT + help Say Y here to set/release ip tunnel metadata. If unsure, say N. @@ -843,28 +914,54 @@ config NET_ACT_TUNNEL_KEY To compile this code as a module, choose M here: the module will be called act_tunnel_key. +config NET_ACT_CT + tristate "connection tracking tc action" + depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE + select NF_CONNTRACK_OVS + select NF_NAT_OVS if NF_NAT + help + Say Y here to allow sending the packets to conntrack module. + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_ct. + +config NET_ACT_GATE + tristate "Frame gate entry list control tc action" + depends on NET_CLS_ACT + help + Say Y here to allow to control the ingress flow to be passed at + specific time slot and be dropped at other specific time slot by + the gate entry list. + + If unsure, say N. + To compile this code as a module, choose M here: the + module will be called act_gate. + config NET_IFE_SKBMARK - tristate "Support to encoding decoding skb mark on IFE action" - depends on NET_ACT_IFE - ---help--- + tristate "Support to encoding decoding skb mark on IFE action" + depends on NET_ACT_IFE config NET_IFE_SKBPRIO - tristate "Support to encoding decoding skb prio on IFE action" - depends on NET_ACT_IFE - ---help--- + tristate "Support to encoding decoding skb prio on IFE action" + depends on NET_ACT_IFE config NET_IFE_SKBTCINDEX - tristate "Support to encoding decoding skb tcindex on IFE action" - depends on NET_ACT_IFE - ---help--- - -config NET_CLS_IND - bool "Incoming device classification" - depends on NET_CLS_U32 || NET_CLS_FW - ---help--- - Say Y here to extend the u32 and fw classifier to support - classification based on the incoming device. This option is - likely to disappear in favour of the metadata ematch. + tristate "Support to encoding decoding skb tcindex on IFE action" + depends on NET_ACT_IFE + +config NET_TC_SKB_EXT + bool "TC recirculation support" + depends on NET_CLS_ACT + select SKB_EXTENSIONS + + help + Say Y here to allow tc chain misses to continue in OvS datapath in + the correct recirc_id, and hardware chain misses to continue in + the correct chain in tc software datapath. + + Say N here if you won't be using tc<->ovs offload or tc chains offload. endif # NET_SCHED diff --git a/net/sched/Makefile b/net/sched/Makefile index 7b915d226de7..5078ea84e6ad 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -1,9 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the Linux Traffic Control Unit. # obj-y := sch_generic.o sch_mq.o +obj-$(CONFIG_INET) += sch_frag.o obj-$(CONFIG_NET_SCHED) += sch_api.o sch_blackhole.o obj-$(CONFIG_NET_CLS) += cls_api.o obj-$(CONFIG_NET_CLS_ACT) += act_api.o @@ -11,54 +13,61 @@ obj-$(CONFIG_NET_ACT_POLICE) += act_police.o obj-$(CONFIG_NET_ACT_GACT) += act_gact.o obj-$(CONFIG_NET_ACT_MIRRED) += act_mirred.o obj-$(CONFIG_NET_ACT_SAMPLE) += act_sample.o -obj-$(CONFIG_NET_ACT_IPT) += act_ipt.o obj-$(CONFIG_NET_ACT_NAT) += act_nat.o obj-$(CONFIG_NET_ACT_PEDIT) += act_pedit.o obj-$(CONFIG_NET_ACT_SIMP) += act_simple.o obj-$(CONFIG_NET_ACT_SKBEDIT) += act_skbedit.o obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o +obj-$(CONFIG_NET_ACT_MPLS) += act_mpls.o obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o +obj-$(CONFIG_NET_ACT_CTINFO) += act_ctinfo.o obj-$(CONFIG_NET_ACT_SKBMOD) += act_skbmod.o obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o +obj-$(CONFIG_NET_ACT_CT) += act_ct.o +obj-$(CONFIG_NET_ACT_GATE) += act_gate.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o -obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o obj-$(CONFIG_NET_SCH_HFSC) += sch_hfsc.o obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o -obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o -obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o +obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o obj-$(CONFIG_NET_SCH_PRIO) += sch_prio.o obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o -obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o +obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_MQPRIO_LIB) += sch_mqprio_lib.o +obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o +obj-$(CONFIG_NET_SCH_CAKE) += sch_cake.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o +obj-$(CONFIG_NET_SCH_FQ_PIE) += sch_fq_pie.o +obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o +obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o +obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o +obj-$(CONFIG_NET_SCH_BPF) += bpf_qdisc.o +obj-$(CONFIG_NET_SCH_DUALPI2) += sch_dualpi2.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o -obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_TCINDEX) += cls_tcindex.o -obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o @@ -73,3 +82,4 @@ obj-$(CONFIG_NET_EMATCH_META) += em_meta.o obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o obj-$(CONFIG_NET_EMATCH_CANID) += em_canid.o obj-$(CONFIG_NET_EMATCH_IPSET) += em_ipset.o +obj-$(CONFIG_NET_EMATCH_IPT) += em_ipt.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f2e9ed34a963..ff6be5cfe2b0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1,14 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_api.c Packet action API. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Author: Jamal Hadi Salim - * - * */ #include <linux/types.h> @@ -25,127 +19,593 @@ #include <net/sock.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include <net/tc_act/tc_pedit.h> #include <net/act_api.h> #include <net/netlink.h> +#include <net/flow_offload.h> +#include <net/tc_wrapper.h> -static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) -{ - u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK; - - if (!tp) - return -EINVAL; - a->goto_chain = tcf_chain_get(tp->chain->block, chain_index, true); - if (!a->goto_chain) - return -ENOMEM; - return 0; -} +#ifdef CONFIG_INET +DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count); +EXPORT_SYMBOL_GPL(tcf_frag_xmit_count); +#endif -static void tcf_action_goto_chain_fini(struct tc_action *a) +int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)) { - tcf_chain_put(a->goto_chain); +#ifdef CONFIG_INET + if (static_branch_unlikely(&tcf_frag_xmit_count)) + return sch_frag_xmit_hook(skb, xmit); +#endif + + return xmit(skb); } +EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit); static void tcf_action_goto_chain_exec(const struct tc_action *a, struct tcf_result *res) { - const struct tcf_chain *chain = a->goto_chain; + const struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain); res->goto_tp = rcu_dereference_bh(chain->filter_chain); } -static void free_tcf(struct rcu_head *head) +static void tcf_free_cookie_rcu(struct rcu_head *p) +{ + struct tc_cookie *cookie = container_of(p, struct tc_cookie, rcu); + + kfree(cookie->data); + kfree(cookie); +} + +static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, + struct tc_cookie *new_cookie) { - struct tc_action *p = container_of(head, struct tc_action, tcfa_rcu); + struct tc_cookie *old; + + old = unrcu_pointer(xchg(old_cookie, RCU_INITIALIZER(new_cookie))); + if (old) + call_rcu(&old->rcu, tcf_free_cookie_rcu); +} + +int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, + struct tcf_chain **newchain, + struct netlink_ext_ack *extack) +{ + int opcode = TC_ACT_EXT_OPCODE(action), ret = -EINVAL; + u32 chain_index; + + if (!opcode) + ret = action > TC_ACT_VALUE_MAX ? -EINVAL : 0; + else if (opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC) + ret = 0; + if (ret) { + NL_SET_ERR_MSG(extack, "invalid control action"); + goto end; + } + + if (TC_ACT_EXT_CMP(action, TC_ACT_GOTO_CHAIN)) { + chain_index = action & TC_ACT_EXT_VAL_MASK; + if (!tp || !newchain) { + ret = -EINVAL; + NL_SET_ERR_MSG(extack, + "can't goto NULL proto/chain"); + goto end; + } + *newchain = tcf_chain_get_by_act(tp->chain->block, chain_index); + if (!*newchain) { + ret = -ENOMEM; + NL_SET_ERR_MSG(extack, + "can't allocate goto_chain"); + } + } +end: + return ret; +} +EXPORT_SYMBOL(tcf_action_check_ctrlact); + +struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, + struct tcf_chain *goto_chain) +{ + a->tcfa_action = action; + goto_chain = rcu_replace_pointer(a->goto_chain, goto_chain, 1); + return goto_chain; +} +EXPORT_SYMBOL(tcf_action_set_ctrlact); + +/* XXX: For standalone actions, we don't need a RCU grace period either, because + * actions are always connected to filters and filters are already destroyed in + * RCU callbacks, so after a RCU grace period actions are already disconnected + * from filters. Readers later can not find us. + */ +static void free_tcf(struct tc_action *p) +{ + struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1); free_percpu(p->cpu_bstats); + free_percpu(p->cpu_bstats_hw); free_percpu(p->cpu_qstats); - if (p->act_cookie) { - kfree(p->act_cookie->data); - kfree(p->act_cookie); - } - if (p->goto_chain) - tcf_action_goto_chain_fini(p); + tcf_set_action_cookie(&p->user_cookie, NULL); + if (chain) + tcf_chain_put_by_act(chain); kfree(p); } -static void tcf_hash_destroy(struct tcf_hashinfo *hinfo, struct tc_action *p) +static void offload_action_hw_count_set(struct tc_action *act, + u32 hw_count) +{ + act->in_hw_count = hw_count; +} + +static void offload_action_hw_count_inc(struct tc_action *act, + u32 hw_count) +{ + act->in_hw_count += hw_count; +} + +static void offload_action_hw_count_dec(struct tc_action *act, + u32 hw_count) +{ + act->in_hw_count = act->in_hw_count > hw_count ? + act->in_hw_count - hw_count : 0; +} + +static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act) +{ + if (is_tcf_pedit(act)) + return tcf_pedit_nkeys(act); + else + return 1; +} + +static bool tc_act_skip_hw(u32 flags) +{ + return (flags & TCA_ACT_FLAGS_SKIP_HW) ? true : false; +} + +static bool tc_act_skip_sw(u32 flags) +{ + return (flags & TCA_ACT_FLAGS_SKIP_SW) ? true : false; +} + +/* SKIP_HW and SKIP_SW are mutually exclusive flags. */ +static bool tc_act_flags_valid(u32 flags) +{ + flags &= TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW; + + return flags ^ (TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW); +} + +static int offload_action_init(struct flow_offload_action *fl_action, + struct tc_action *act, + enum offload_act_command cmd, + struct netlink_ext_ack *extack) +{ + int err; + + fl_action->extack = extack; + fl_action->command = cmd; + fl_action->index = act->tcfa_index; + fl_action->cookie = (unsigned long)act; + + if (act->ops->offload_act_setup) { + spin_lock_bh(&act->tcfa_lock); + err = act->ops->offload_act_setup(act, fl_action, NULL, + false, extack); + spin_unlock_bh(&act->tcfa_lock); + return err; + } + + return -EOPNOTSUPP; +} + +static int tcf_action_offload_cmd_ex(struct flow_offload_action *fl_act, + u32 *hw_count) +{ + int err; + + err = flow_indr_dev_setup_offload(NULL, NULL, TC_SETUP_ACT, + fl_act, NULL, NULL); + if (err < 0) + return err; + + if (hw_count) + *hw_count = err; + + return 0; +} + +static int tcf_action_offload_cmd_cb_ex(struct flow_offload_action *fl_act, + u32 *hw_count, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) +{ + int err; + + err = cb(NULL, NULL, cb_priv, TC_SETUP_ACT, NULL, fl_act, NULL); + if (err < 0) + return err; + + if (hw_count) + *hw_count = 1; + + return 0; +} + +static int tcf_action_offload_cmd(struct flow_offload_action *fl_act, + u32 *hw_count, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) { - spin_lock_bh(&hinfo->lock); - hlist_del(&p->tcfa_head); - spin_unlock_bh(&hinfo->lock); + return cb ? tcf_action_offload_cmd_cb_ex(fl_act, hw_count, + cb, cb_priv) : + tcf_action_offload_cmd_ex(fl_act, hw_count); +} + +static int tcf_action_offload_add_ex(struct tc_action *action, + struct netlink_ext_ack *extack, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) +{ + bool skip_sw = tc_act_skip_sw(action->tcfa_flags); + struct tc_action *actions[TCA_ACT_MAX_PRIO] = { + [0] = action, + }; + struct flow_offload_action *fl_action; + u32 in_hw_count = 0; + int num, err = 0; + + if (tc_act_skip_hw(action->tcfa_flags)) + return 0; + + num = tcf_offload_act_num_actions_single(action); + fl_action = offload_action_alloc(num); + if (!fl_action) + return -ENOMEM; + + err = offload_action_init(fl_action, action, FLOW_ACT_REPLACE, extack); + if (err) + goto fl_err; + + err = tc_setup_action(&fl_action->action, actions, 0, extack); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to setup tc actions for offload"); + goto fl_err; + } + + err = tcf_action_offload_cmd(fl_action, &in_hw_count, cb, cb_priv); + if (!err) + cb ? offload_action_hw_count_inc(action, in_hw_count) : + offload_action_hw_count_set(action, in_hw_count); + + if (skip_sw && !tc_act_in_hw(action)) + err = -EINVAL; + + tc_cleanup_offload_action(&fl_action->action); + +fl_err: + kfree(fl_action); + + return err; +} + +/* offload the tc action after it is inserted */ +static int tcf_action_offload_add(struct tc_action *action, + struct netlink_ext_ack *extack) +{ + return tcf_action_offload_add_ex(action, extack, NULL, NULL); +} + +int tcf_action_update_hw_stats(struct tc_action *action) +{ + struct flow_offload_action fl_act = {}; + int err; + + err = offload_action_init(&fl_act, action, FLOW_ACT_STATS, NULL); + if (err) + return err; + + err = tcf_action_offload_cmd(&fl_act, NULL, NULL, NULL); + if (!err) { + preempt_disable(); + tcf_action_stats_update(action, fl_act.stats.bytes, + fl_act.stats.pkts, + fl_act.stats.drops, + fl_act.stats.lastused, + true); + preempt_enable(); + action->used_hw_stats = fl_act.stats.used_hw_stats; + action->used_hw_stats_valid = true; + } else { + return -EOPNOTSUPP; + } + + return 0; +} +EXPORT_SYMBOL(tcf_action_update_hw_stats); + +static int tcf_action_offload_del_ex(struct tc_action *action, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) +{ + struct flow_offload_action fl_act = {}; + u32 in_hw_count = 0; + int err = 0; + + if (!tc_act_in_hw(action)) + return 0; + + err = offload_action_init(&fl_act, action, FLOW_ACT_DESTROY, NULL); + if (err) + return err; + + err = tcf_action_offload_cmd(&fl_act, &in_hw_count, cb, cb_priv); + if (err < 0) + return err; + + if (!cb && action->in_hw_count != in_hw_count) + return -EINVAL; + + /* do not need to update hw state when deleting action */ + if (cb && in_hw_count) + offload_action_hw_count_dec(action, in_hw_count); + + return 0; +} + +static int tcf_action_offload_del(struct tc_action *action) +{ + return tcf_action_offload_del_ex(action, NULL, NULL); +} + +static void tcf_action_cleanup(struct tc_action *p) +{ + tcf_action_offload_del(p); + if (p->ops->cleanup) + p->ops->cleanup(p); + gen_kill_estimator(&p->tcfa_rate_est); - /* - * gen_estimator est_timer() might access p->tcfa_lock - * or bstats, wait a RCU grace period before freeing p - */ - call_rcu(&p->tcfa_rcu, free_tcf); + free_tcf(p); } -int __tcf_hash_release(struct tc_action *p, bool bind, bool strict) +static int __tcf_action_put(struct tc_action *p, bool bind) +{ + struct tcf_idrinfo *idrinfo = p->idrinfo; + + if (refcount_dec_and_mutex_lock(&p->tcfa_refcnt, &idrinfo->lock)) { + if (bind) + atomic_dec(&p->tcfa_bindcnt); + idr_remove(&idrinfo->action_idr, p->tcfa_index); + mutex_unlock(&idrinfo->lock); + + tcf_action_cleanup(p); + return 1; + } + + if (bind) + atomic_dec(&p->tcfa_bindcnt); + + return 0; +} + +static int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) { int ret = 0; + /* Release with strict==1 and bind==0 is only called through act API + * interface (classifiers always bind). Only case when action with + * positive reference count and zero bind count can exist is when it was + * also created with act API (unbinding last classifier will destroy the + * action if it was created by classifier). So only case when bind count + * can be changed after initial check is when unbound action is + * destroyed by act API while classifier binds to action with same id + * concurrently. This result either creation of new action(same behavior + * as before), or reusing existing action if concurrent process + * increments reference count before action is deleted. Both scenarios + * are acceptable. + */ if (p) { - if (bind) - p->tcfa_bindcnt--; - else if (strict && p->tcfa_bindcnt > 0) + if (!bind && strict && atomic_read(&p->tcfa_bindcnt) > 0) return -EPERM; - p->tcfa_refcnt--; - if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) { - if (p->ops->cleanup) - p->ops->cleanup(p, bind); - tcf_hash_destroy(p->hinfo, p); + if (__tcf_action_put(p, bind)) ret = ACT_P_DELETED; - } } return ret; } -EXPORT_SYMBOL(__tcf_hash_release); -static int tcf_dump_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, +int tcf_idr_release(struct tc_action *a, bool bind) +{ + const struct tc_action_ops *ops = a->ops; + int ret; + + ret = __tcf_idr_release(a, bind, false); + if (ret == ACT_P_DELETED) + module_put(ops->owner); + return ret; +} +EXPORT_SYMBOL(tcf_idr_release); + +static size_t tcf_action_shared_attrs_size(const struct tc_action *act) +{ + struct tc_cookie *user_cookie; + u32 cookie_len = 0; + + rcu_read_lock(); + user_cookie = rcu_dereference(act->user_cookie); + + if (user_cookie) + cookie_len = nla_total_size(user_cookie->len); + rcu_read_unlock(); + + return nla_total_size(0) /* action number nested */ + + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + + cookie_len /* TCA_ACT_COOKIE */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */ + + nla_total_size(0) /* TCA_ACT_STATS nested */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ + /* TCA_STATS_BASIC */ + + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64 */ + + nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_QUEUE */ + + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) + + nla_total_size(0) /* TCA_ACT_OPTIONS nested */ + + nla_total_size(sizeof(struct tcf_t)); /* TCA_GACT_TM */ +} + +static size_t tcf_action_full_attrs_size(size_t sz) +{ + return NLMSG_HDRLEN /* struct nlmsghdr */ + + sizeof(struct tcamsg) + + nla_total_size(0) /* TCA_ACT_TAB nested */ + + sz; +} + +static size_t tcf_action_fill_size(const struct tc_action *act) +{ + size_t sz = tcf_action_shared_attrs_size(act); + + if (act->ops->get_fill_size) + return act->ops->get_fill_size(act) + sz; + return sz; +} + +static int +tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tc_cookie *cookie; + + if (nla_put_string(skb, TCA_ACT_KIND, a->ops->kind)) + goto nla_put_failure; + if (tcf_action_copy_stats(skb, a, 0)) + goto nla_put_failure; + if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index)) + goto nla_put_failure; + + rcu_read_lock(); + cookie = rcu_dereference(a->user_cookie); + if (cookie) { + if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { + rcu_read_unlock(); + goto nla_put_failure; + } + } + rcu_read_unlock(); + + return 0; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static int +tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nest; + int err = -EINVAL; + u32 flags; + + if (tcf_action_dump_terse(skb, a, false)) + goto nla_put_failure; + + if (a->hw_stats != TCA_ACT_HW_STATS_ANY && + nla_put_bitfield32(skb, TCA_ACT_HW_STATS, + a->hw_stats, TCA_ACT_HW_STATS_ANY)) + goto nla_put_failure; + + if (a->used_hw_stats_valid && + nla_put_bitfield32(skb, TCA_ACT_USED_HW_STATS, + a->used_hw_stats, TCA_ACT_HW_STATS_ANY)) + goto nla_put_failure; + + flags = a->tcfa_flags & TCA_ACT_FLAGS_USER_MASK; + if (flags && + nla_put_bitfield32(skb, TCA_ACT_FLAGS, + flags, flags)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_ACT_IN_HW_COUNT, a->in_hw_count)) + goto nla_put_failure; + + nest = nla_nest_start_noflag(skb, TCA_ACT_OPTIONS); + if (nest == NULL) + goto nla_put_failure; + err = tcf_action_dump_old(skb, a, bind, ref); + if (err > 0) { + nla_nest_end(skb, nest); + return err; + } + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct netlink_callback *cb) { - int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; + int err = 0, index = -1, s_i = 0, n_i = 0; + u32 act_flags = cb->args[2]; + unsigned long jiffy_since = cb->args[3]; struct nlattr *nest; + struct idr *idr = &idrinfo->action_idr; + struct tc_action *p; + unsigned long id = 1; + unsigned long tmp; - spin_lock_bh(&hinfo->lock); + mutex_lock(&idrinfo->lock); s_i = cb->args[0]; - for (i = 0; i < (hinfo->hmask + 1); i++) { - struct hlist_head *head; - struct tc_action *p; + idr_for_each_entry_ul(idr, p, tmp, id) { + index++; + if (index < s_i) + continue; + if (IS_ERR(p)) + continue; - head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; + if (jiffy_since && + time_after(jiffy_since, + (unsigned long)p->tcfa_tm.lastuse)) + continue; - hlist_for_each_entry_rcu(p, head, tcfa_head) { - index++; - if (index < s_i) - continue; + tcf_action_update_hw_stats(p); - nest = nla_nest_start(skb, n_i); - if (nest == NULL) - goto nla_put_failure; - err = tcf_action_dump_1(skb, p, 0, 0); - if (err < 0) { - index--; - nlmsg_trim(skb, nest); - goto done; - } - nla_nest_end(skb, nest); - n_i++; - if (n_i >= TCA_ACT_MAX_PRIO) - goto done; + nest = nla_nest_start_noflag(skb, n_i); + if (!nest) { + index--; + goto nla_put_failure; + } + err = (act_flags & TCA_ACT_FLAG_TERSE_DUMP) ? + tcf_action_dump_terse(skb, p, true) : + tcf_action_dump_1(skb, p, 0, 0); + if (err < 0) { + index--; + nlmsg_trim(skb, nest); + goto done; } + nla_nest_end(skb, nest); + n_i++; + if (!(act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) && + n_i >= TCA_ACT_MAX_PRIO) + goto done; } done: - spin_unlock_bh(&hinfo->lock); - if (n_i) - cb->args[0] += n_i; + if (index >= 0) + cb->args[0] = index + 1; + + mutex_unlock(&idrinfo->lock); + if (n_i) { + if (act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) + cb->args[1] = n_i; + } return n_i; nla_put_failure: @@ -153,34 +613,60 @@ nla_put_failure: goto done; } -static int tcf_del_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, - const struct tc_action_ops *ops) +static int tcf_idr_release_unsafe(struct tc_action *p) +{ + if (atomic_read(&p->tcfa_bindcnt) > 0) + return -EPERM; + + if (refcount_dec_and_test(&p->tcfa_refcnt)) { + idr_remove(&p->idrinfo->action_idr, p->tcfa_index); + tcf_action_cleanup(p); + return ACT_P_DELETED; + } + + return 0; +} + +static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct nlattr *nest; - int i = 0, n_i = 0; + int n_i = 0; int ret = -EINVAL; + struct idr *idr = &idrinfo->action_idr; + struct tc_action *p; + unsigned long id = 1; + unsigned long tmp; - nest = nla_nest_start(skb, 0); + nest = nla_nest_start_noflag(skb, 0); if (nest == NULL) goto nla_put_failure; - if (nla_put_string(skb, TCA_KIND, ops->kind)) + if (nla_put_string(skb, TCA_ACT_KIND, ops->kind)) goto nla_put_failure; - for (i = 0; i < (hinfo->hmask + 1); i++) { - struct hlist_head *head; - struct hlist_node *n; - struct tc_action *p; - - head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; - hlist_for_each_entry_safe(p, n, head, tcfa_head) { - ret = __tcf_hash_release(p, false, true); - if (ret == ACT_P_DELETED) { - module_put(p->ops->owner); - n_i++; - } else if (ret < 0) - goto nla_put_failure; - } + + ret = 0; + mutex_lock(&idrinfo->lock); + idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p)) + continue; + ret = tcf_idr_release_unsafe(p); + if (ret == ACT_P_DELETED) + module_put(ops->owner); + else if (ret < 0) + break; + n_i++; } - if (nla_put_u32(skb, TCA_FCNT, n_i)) + mutex_unlock(&idrinfo->lock); + if (ret < 0) { + if (n_i) + NL_SET_ERR_MSG(extack, "Unable to flush all TC actions"); + else + goto nla_put_failure; + } + + ret = nla_put_u32(skb, TCA_FCNT, n_i); + if (ret) goto nla_put_failure; nla_nest_end(skb, nest); @@ -192,177 +678,339 @@ nla_put_failure: int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { - struct tcf_hashinfo *hinfo = tn->hinfo; + struct tcf_idrinfo *idrinfo = tn->idrinfo; if (type == RTM_DELACTION) { - return tcf_del_walker(hinfo, skb, ops); + return tcf_del_walker(idrinfo, skb, ops, extack); } else if (type == RTM_GETACTION) { - return tcf_dump_walker(hinfo, skb, cb); + return tcf_dump_walker(idrinfo, skb, cb); } else { - WARN(1, "tcf_generic_walker: unknown action %d\n", type); + WARN(1, "tcf_generic_walker: unknown command %d\n", type); + NL_SET_ERR_MSG(extack, "tcf_generic_walker: unknown command"); return -EINVAL; } } EXPORT_SYMBOL(tcf_generic_walker); -static struct tc_action *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) +int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) { - struct tc_action *p = NULL; - struct hlist_head *head; + struct tcf_idrinfo *idrinfo = tn->idrinfo; + struct tc_action *p; - spin_lock_bh(&hinfo->lock); - head = &hinfo->htab[tcf_hash(index, hinfo->hmask)]; - hlist_for_each_entry_rcu(p, head, tcfa_head) - if (p->tcfa_index == index) - break; - spin_unlock_bh(&hinfo->lock); + mutex_lock(&idrinfo->lock); + p = idr_find(&idrinfo->action_idr, index); + if (IS_ERR(p)) + p = NULL; + else if (p) + refcount_inc(&p->tcfa_refcnt); + mutex_unlock(&idrinfo->lock); - return p; + if (p) { + *a = p; + return true; + } + return false; } +EXPORT_SYMBOL(tcf_idr_search); -u32 tcf_hash_new_index(struct tc_action_net *tn) +static int __tcf_generic_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { - struct tcf_hashinfo *hinfo = tn->hinfo; - u32 val = hinfo->index; + struct tc_action_net *tn = net_generic(net, ops->net_id); - do { - if (++val == 0) - val = 1; - } while (tcf_hash_lookup(val, hinfo)); + if (unlikely(ops->walk)) + return ops->walk(net, skb, cb, type, ops, extack); - hinfo->index = val; - return val; + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -EXPORT_SYMBOL(tcf_hash_new_index); -int tcf_hash_search(struct tc_action_net *tn, struct tc_action **a, u32 index) +static int __tcf_idr_search(struct net *net, + const struct tc_action_ops *ops, + struct tc_action **a, u32 index) { - struct tcf_hashinfo *hinfo = tn->hinfo; - struct tc_action *p = tcf_hash_lookup(index, hinfo); + struct tc_action_net *tn = net_generic(net, ops->net_id); - if (p) { - *a = p; - return 1; - } - return 0; + if (unlikely(ops->lookup)) + return ops->lookup(net, a, index); + + return tcf_idr_search(tn, a, index); } -EXPORT_SYMBOL(tcf_hash_search); -bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action **a, - int bind) +static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) { - struct tcf_hashinfo *hinfo = tn->hinfo; - struct tc_action *p = NULL; + struct tc_action *p; + int ret = 0; - if (index && (p = tcf_hash_lookup(index, hinfo)) != NULL) { - if (bind) - p->tcfa_bindcnt++; - p->tcfa_refcnt++; - *a = p; - return true; + mutex_lock(&idrinfo->lock); + p = idr_find(&idrinfo->action_idr, index); + if (!p) { + mutex_unlock(&idrinfo->lock); + return -ENOENT; } - return false; -} -EXPORT_SYMBOL(tcf_hash_check); -void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est) -{ - if (est) - gen_kill_estimator(&a->tcfa_rate_est); - call_rcu(&a->tcfa_rcu, free_tcf); + if (!atomic_read(&p->tcfa_bindcnt)) { + if (refcount_dec_and_test(&p->tcfa_refcnt)) { + struct module *owner = p->ops->owner; + + WARN_ON(p != idr_remove(&idrinfo->action_idr, + p->tcfa_index)); + mutex_unlock(&idrinfo->lock); + + tcf_action_cleanup(p); + module_put(owner); + return 0; + } + ret = 0; + } else { + ret = -EPERM; + } + + mutex_unlock(&idrinfo->lock); + return ret; } -EXPORT_SYMBOL(tcf_hash_cleanup); -int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est, - struct tc_action **a, const struct tc_action_ops *ops, - int bind, bool cpustats) +int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, + struct tc_action **a, const struct tc_action_ops *ops, + int bind, bool cpustats, u32 flags) { struct tc_action *p = kzalloc(ops->size, GFP_KERNEL); - struct tcf_hashinfo *hinfo = tn->hinfo; + struct tcf_idrinfo *idrinfo = tn->idrinfo; int err = -ENOMEM; if (unlikely(!p)) return -ENOMEM; - p->tcfa_refcnt = 1; + refcount_set(&p->tcfa_refcnt, 1); if (bind) - p->tcfa_bindcnt = 1; + atomic_set(&p->tcfa_bindcnt, 1); if (cpustats) { - p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); - if (!p->cpu_bstats) { -err1: - kfree(p); - return err; - } - p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); - if (!p->cpu_qstats) { -err2: - free_percpu(p->cpu_bstats); + p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); + if (!p->cpu_bstats) goto err1; - } + p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); + if (!p->cpu_bstats_hw) + goto err2; + p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!p->cpu_qstats) + goto err3; } + gnet_stats_basic_sync_init(&p->tcfa_bstats); + gnet_stats_basic_sync_init(&p->tcfa_bstats_hw); spin_lock_init(&p->tcfa_lock); - INIT_HLIST_NODE(&p->tcfa_head); - p->tcfa_index = index ? index : tcf_hash_new_index(tn); + p->tcfa_index = index; p->tcfa_tm.install = jiffies; p->tcfa_tm.lastuse = jiffies; p->tcfa_tm.firstuse = 0; + p->tcfa_flags = flags; if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, - &p->tcfa_lock, NULL, est); - if (err) { - free_percpu(p->cpu_qstats); - goto err2; - } + &p->tcfa_lock, false, est); + if (err) + goto err4; } - p->hinfo = hinfo; + p->idrinfo = idrinfo; + __module_get(ops->owner); p->ops = ops; - INIT_LIST_HEAD(&p->list); *a = p; return 0; +err4: + free_percpu(p->cpu_qstats); +err3: + free_percpu(p->cpu_bstats_hw); +err2: + free_percpu(p->cpu_bstats); +err1: + kfree(p); + return err; +} +EXPORT_SYMBOL(tcf_idr_create); + +int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, + struct nlattr *est, struct tc_action **a, + const struct tc_action_ops *ops, int bind, + u32 flags) +{ + /* Set cpustats according to actions flags. */ + return tcf_idr_create(tn, index, est, a, ops, bind, + !(flags & TCA_ACT_FLAGS_NO_PERCPU_STATS), flags); } -EXPORT_SYMBOL(tcf_hash_create); +EXPORT_SYMBOL(tcf_idr_create_from_flags); + +/* Cleanup idr index that was allocated but not initialized. */ -void tcf_hash_insert(struct tc_action_net *tn, struct tc_action *a) +void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) { - struct tcf_hashinfo *hinfo = tn->hinfo; - unsigned int h = tcf_hash(a->tcfa_index, hinfo->hmask); + struct tcf_idrinfo *idrinfo = tn->idrinfo; - spin_lock_bh(&hinfo->lock); - hlist_add_head(&a->tcfa_head, &hinfo->htab[h]); - spin_unlock_bh(&hinfo->lock); + mutex_lock(&idrinfo->lock); + /* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ + WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index))); + mutex_unlock(&idrinfo->lock); } -EXPORT_SYMBOL(tcf_hash_insert); +EXPORT_SYMBOL(tcf_idr_cleanup); + +/* Check if action with specified index exists. If actions is found, increments + * its reference and bind counters, and return 1. Otherwise insert temporary + * error pointer (to prevent concurrent users from inserting actions with same + * index) and return 0. + * + * May return -EAGAIN for binding actions in case of a parallel add/delete on + * the requested index. + */ -void tcf_hashinfo_destroy(const struct tc_action_ops *ops, - struct tcf_hashinfo *hinfo) +int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, + struct tc_action **a, int bind) { - int i; + struct tcf_idrinfo *idrinfo = tn->idrinfo; + struct tc_action *p; + int ret; + u32 max; + + if (*index) { + rcu_read_lock(); + p = idr_find(&idrinfo->action_idr, *index); + + if (IS_ERR(p)) { + /* This means that another process allocated + * index but did not assign the pointer yet. + */ + rcu_read_unlock(); + return -EAGAIN; + } - for (i = 0; i < hinfo->hmask + 1; i++) { - struct tc_action *p; - struct hlist_node *n; + if (!p) { + /* Empty slot, try to allocate it */ + max = *index; + rcu_read_unlock(); + goto new; + } - hlist_for_each_entry_safe(p, n, &hinfo->htab[i], tcfa_head) { - int ret; + if (!refcount_inc_not_zero(&p->tcfa_refcnt)) { + /* Action was deleted in parallel */ + rcu_read_unlock(); + return -EAGAIN; + } + + if (bind) + atomic_inc(&p->tcfa_bindcnt); + *a = p; + + rcu_read_unlock(); - ret = __tcf_hash_release(p, false, true); - if (ret == ACT_P_DELETED) - module_put(ops->owner); - else if (ret < 0) - return; + return 1; + } else { + /* Find a slot */ + *index = 1; + max = UINT_MAX; + } + +new: + *a = NULL; + + mutex_lock(&idrinfo->lock); + ret = idr_alloc_u32(&idrinfo->action_idr, ERR_PTR(-EBUSY), index, max, + GFP_KERNEL); + mutex_unlock(&idrinfo->lock); + + /* N binds raced for action allocation, + * retry for all the ones that failed. + */ + if (ret == -ENOSPC && *index == max) + ret = -EAGAIN; + + return ret; +} +EXPORT_SYMBOL(tcf_idr_check_alloc); + +void tcf_idrinfo_destroy(const struct tc_action_ops *ops, + struct tcf_idrinfo *idrinfo) +{ + struct idr *idr = &idrinfo->action_idr; + bool mutex_taken = false; + struct tc_action *p; + unsigned long id = 1; + unsigned long tmp; + int ret; + + idr_for_each_entry_ul(idr, p, tmp, id) { + if (tc_act_in_hw(p) && !mutex_taken) { + rtnl_lock(); + mutex_taken = true; } + ret = __tcf_idr_release(p, false, true); + if (ret == ACT_P_DELETED) + module_put(ops->owner); + else if (ret < 0) + return; } - kfree(hinfo->htab); + if (mutex_taken) + rtnl_unlock(); + idr_destroy(&idrinfo->action_idr); } -EXPORT_SYMBOL(tcf_hashinfo_destroy); +EXPORT_SYMBOL(tcf_idrinfo_destroy); static LIST_HEAD(act_base); static DEFINE_RWLOCK(act_mod_lock); +/* since act ops id is stored in pernet subsystem list, + * then there is no way to walk through only all the action + * subsystem, so we keep tc action pernet ops id for + * reoffload to walk through. + */ +static LIST_HEAD(act_pernet_id_list); +static DEFINE_MUTEX(act_id_mutex); +struct tc_act_pernet_id { + struct list_head list; + unsigned int id; +}; + +static int tcf_pernet_add_id_list(unsigned int id) +{ + struct tc_act_pernet_id *id_ptr; + int ret = 0; + + mutex_lock(&act_id_mutex); + list_for_each_entry(id_ptr, &act_pernet_id_list, list) { + if (id_ptr->id == id) { + ret = -EEXIST; + goto err_out; + } + } + + id_ptr = kzalloc(sizeof(*id_ptr), GFP_KERNEL); + if (!id_ptr) { + ret = -ENOMEM; + goto err_out; + } + id_ptr->id = id; + + list_add_tail(&id_ptr->list, &act_pernet_id_list); + +err_out: + mutex_unlock(&act_id_mutex); + return ret; +} + +static void tcf_pernet_del_id_list(unsigned int id) +{ + struct tc_act_pernet_id *id_ptr; + + mutex_lock(&act_id_mutex); + list_for_each_entry(id_ptr, &act_pernet_id_list, list) { + if (id_ptr->id == id) { + list_del(&id_ptr->list); + kfree(id_ptr); + break; + } + } + mutex_unlock(&act_id_mutex); +} int tcf_register_action(struct tc_action_ops *act, struct pernet_operations *ops) @@ -370,7 +1018,7 @@ int tcf_register_action(struct tc_action_ops *act, struct tc_action_ops *a; int ret; - if (!act->act || !act->dump || !act->init || !act->walk || !act->lookup) + if (!act->act || !act->dump || !act->init) return -EINVAL; /* We have to register pernet ops before making the action ops visible, @@ -381,18 +1029,31 @@ int tcf_register_action(struct tc_action_ops *act, if (ret) return ret; + if (ops->id) { + ret = tcf_pernet_add_id_list(*ops->id); + if (ret) + goto err_id; + } + write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { - if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { - write_unlock(&act_mod_lock); - unregister_pernet_subsys(ops); - return -EEXIST; + if (act->id == a->id || (strcmp(act->kind, a->kind) == 0)) { + ret = -EEXIST; + goto err_out; } } list_add_tail(&act->head, &act_base); write_unlock(&act_mod_lock); return 0; + +err_out: + write_unlock(&act_mod_lock); + if (ops->id) + tcf_pernet_del_id_list(*ops->id); +err_id: + unregister_pernet_subsys(ops); + return ret; } EXPORT_SYMBOL(tcf_register_action); @@ -411,8 +1072,11 @@ int tcf_unregister_action(struct tc_action_ops *act, } } write_unlock(&act_mod_lock); - if (!err) + if (!err) { unregister_pernet_subsys(ops); + if (ops->id) + tcf_pernet_del_id_list(*ops->id); + } return err; } EXPORT_SYMBOL(tcf_unregister_action); @@ -455,14 +1119,15 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) return res; } -/*TCA_ACT_MAX_PRIO is 32, there count upto 32 */ +/*TCA_ACT_MAX_PRIO is 32, there count up to 32 */ #define TCA_ACT_MAX_PRIO_MASK 0x1FF int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res) { - int ret = -1, i; u32 jmp_prgcnt = 0; u32 jmp_ttl = TCA_ACT_MAX_PRIO; /*matches actions per filter */ + int i; + int ret = TC_ACT_OK; if (skb_skip_tc_classify(skb)) return TC_ACT_OK; @@ -470,16 +1135,26 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, restart_act_graph: for (i = 0; i < nr_actions; i++) { const struct tc_action *a = actions[i]; + int repeat_ttl; if (jmp_prgcnt > 0) { jmp_prgcnt -= 1; continue; } -repeat: - ret = a->ops->act(skb, a, res); - if (ret == TC_ACT_REPEAT) - goto repeat; /* we need a ttl - JHS */ + if (tc_act_skip_sw(a->tcfa_flags)) + continue; + + repeat_ttl = 32; +repeat: + ret = tc_act(skb, a, res); + if (unlikely(ret == TC_ACT_REPEAT)) { + if (--repeat_ttl != 0) + goto repeat; + /* suspicious opcode, stop pipeline */ + net_warn_ratelimited("TC_ACT_REPEAT abuse ?\n"); + return TC_ACT_OK; + } if (TC_ACT_EXT_CMP(ret, TC_ACT_JUMP)) { jmp_prgcnt = ret & TCA_ACT_MAX_PRIO_MASK; if (!jmp_prgcnt || (jmp_prgcnt > nr_actions)) { @@ -493,6 +1168,11 @@ repeat: return TC_ACT_OK; } } else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) { + if (unlikely(!rcu_access_pointer(a->goto_chain))) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_CHAIN_NOTFOUND); + return TC_ACT_SHOT; + } tcf_action_goto_chain_exec(a, res); } @@ -504,71 +1184,76 @@ repeat: } EXPORT_SYMBOL(tcf_action_exec); -int tcf_action_destroy(struct list_head *actions, int bind) +int tcf_action_destroy(struct tc_action *actions[], int bind) { - struct tc_action *a, *tmp; - int ret = 0; + const struct tc_action_ops *ops; + struct tc_action *a; + int ret = 0, i; - list_for_each_entry_safe(a, tmp, actions, list) { - ret = __tcf_hash_release(a, bind, true); + tcf_act_for_each_action(i, a, actions) { + actions[i] = NULL; + ops = a->ops; + ret = __tcf_idr_release(a, bind, true); if (ret == ACT_P_DELETED) - module_put(a->ops->owner); + module_put(ops->owner); else if (ret < 0) return ret; } return ret; } -int -tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static int tcf_action_put(struct tc_action *p) { - return a->ops->dump(skb, a, bind, ref); + return __tcf_action_put(p, false); } -int -tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static void tcf_action_put_many(struct tc_action *actions[]) { - int err = -EINVAL; - unsigned char *b = skb_tail_pointer(skb); - struct nlattr *nest; + struct tc_action *a; + int i; - if (nla_put_string(skb, TCA_KIND, a->ops->kind)) - goto nla_put_failure; - if (tcf_action_copy_stats(skb, a, 0)) - goto nla_put_failure; - if (a->act_cookie) { - if (nla_put(skb, TCA_ACT_COOKIE, a->act_cookie->len, - a->act_cookie->data)) - goto nla_put_failure; + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; + if (tcf_action_put(a)) + module_put(ops->owner); } +} - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - err = tcf_action_dump_old(skb, a, bind, ref); - if (err > 0) { - nla_nest_end(skb, nest); - return err; +static void tca_put_bound_many(struct tc_action *actions[], int init_res[]) +{ + struct tc_action *a; + int i; + + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; + + if (init_res[i] == ACT_P_CREATED) + continue; + + if (tcf_action_put(a)) + module_put(ops->owner); } +} -nla_put_failure: - nlmsg_trim(skb, b); - return -1; +int +tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +{ + return a->ops->dump(skb, a, bind, ref); } -EXPORT_SYMBOL(tcf_action_dump_1); -int tcf_action_dump(struct sk_buff *skb, struct list_head *actions, - int bind, int ref) +int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], + int bind, int ref, bool terse) { struct tc_action *a; - int err = -EINVAL; + int err = -EINVAL, i; struct nlattr *nest; - list_for_each_entry(a, actions, list) { - nest = nla_nest_start(skb, a->order); + tcf_act_for_each_action(i, a, actions) { + nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; - err = tcf_action_dump_1(skb, a, bind, ref); + err = terse ? tcf_action_dump_terse(skb, a, false) : + tcf_action_dump_1(skb, a, bind, ref); if (err < 0) goto errout; nla_nest_end(skb, nest); @@ -599,52 +1284,93 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } -struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, - struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind) +static u8 tcf_action_hw_stats_get(struct nlattr *hw_stats_attr) +{ + struct nla_bitfield32 hw_stats_bf; + + /* If the user did not pass the attr, that means he does + * not care about the type. Return "any" in that case + * which is setting on all supported types. + */ + if (!hw_stats_attr) + return TCA_ACT_HW_STATS_ANY; + hw_stats_bf = nla_get_bitfield32(hw_stats_attr); + return hw_stats_bf.value; +} + +static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { + [TCA_ACT_KIND] = { .type = NLA_STRING }, + [TCA_ACT_INDEX] = { .type = NLA_U32 }, + [TCA_ACT_COOKIE] = { .type = NLA_BINARY, + .len = TC_COOKIE_MAX_SIZE }, + [TCA_ACT_OPTIONS] = { .type = NLA_NESTED }, + [TCA_ACT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAGS_NO_PERCPU_STATS | + TCA_ACT_FLAGS_SKIP_HW | + TCA_ACT_FLAGS_SKIP_SW), + [TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY), +}; + +void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]) { struct tc_action *a; + int i; + + tcf_act_for_each_action(i, a, actions) { + struct tcf_idrinfo *idrinfo; + + if (init_res[i] == ACT_P_BOUND) + continue; + + idrinfo = a->idrinfo; + mutex_lock(&idrinfo->lock); + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ + idr_replace(&idrinfo->action_idr, a, a->tcfa_index); + mutex_unlock(&idrinfo->lock); + } +} + +struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags, + struct netlink_ext_ack *extack) +{ + bool police = flags & TCA_ACT_FLAGS_POLICE; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action_ops *a_o; - struct tc_cookie *cookie = NULL; char act_name[IFNAMSIZ]; - struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; int err; - if (name == NULL) { - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + if (!police) { + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) - goto err_out; + return ERR_PTR(err); err = -EINVAL; kind = tb[TCA_ACT_KIND]; - if (kind == NULL) - goto err_out; - if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) - goto err_out; - if (tb[TCA_ACT_COOKIE]) { - int cklen = nla_len(tb[TCA_ACT_COOKIE]); - - if (cklen > TC_COOKIE_MAX_SIZE) - goto err_out; - - cookie = nla_memdup_cookie(tb); - if (!cookie) { - err = -ENOMEM; - goto err_out; - } + if (!kind) { + NL_SET_ERR_MSG(extack, "TC action kind must be specified"); + return ERR_PTR(err); + } + if (nla_strscpy(act_name, kind, IFNAMSIZ) < 0) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + return ERR_PTR(err); } } else { - err = -EINVAL; - if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) - goto err_out; + if (strscpy(act_name, "police", IFNAMSIZ) < 0) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + return ERR_PTR(-EINVAL); + } } a_o = tc_lookup_action_n(act_name); if (a_o == NULL) { #ifdef CONFIG_MODULES - rtnl_unlock(); - request_module("act_%s", act_name); - rtnl_lock(); + bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); + + if (rtnl_held) + rtnl_unlock(); + request_module(NET_ACT_ALIAS_PREFIX "%s", act_name); + if (rtnl_held) + rtnl_lock(); a_o = tc_lookup_action_n(act_name); @@ -655,112 +1381,222 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, * indicate this using -EAGAIN. */ if (a_o != NULL) { - err = -EAGAIN; - goto err_mod; + module_put(a_o->owner); + return ERR_PTR(-EAGAIN); } #endif - err = -ENOENT; - goto err_out; - } - - /* backward compatibility for policer */ - if (name == NULL) - err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind); - else - err = a_o->init(net, nla, est, &a, ovr, bind); - if (err < 0) - goto err_mod; - - if (name == NULL && tb[TCA_ACT_COOKIE]) { - if (a->act_cookie) { - kfree(a->act_cookie->data); - kfree(a->act_cookie); - } - a->act_cookie = cookie; + NL_SET_ERR_MSG(extack, "Failed to load TC action module"); + return ERR_PTR(-ENOENT); } - /* module count goes up only when brand new policy is created - * if it exists and is only bound to in a_o->init() then - * ACT_P_CREATED is not returned (a zero is). - */ - if (err != ACT_P_CREATED) - module_put(a_o->owner); + return a_o; +} - if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { - err = tcf_action_goto_chain_init(a, tp); - if (err) { - LIST_HEAD(actions); +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + struct tc_action_ops *a_o, int *init_res, + u32 flags, struct netlink_ext_ack *extack) +{ + bool police = flags & TCA_ACT_FLAGS_POLICE; + struct nla_bitfield32 userflags = { 0, 0 }; + struct tc_cookie *user_cookie = NULL; + u8 hw_stats = TCA_ACT_HW_STATS_ANY; + struct nlattr *tb[TCA_ACT_MAX + 1]; + struct tc_action *a; + int err; - list_add_tail(&a->list, &actions); - tcf_action_destroy(&actions, bind); + /* backward compatibility for policer */ + if (!police) { + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); + if (err < 0) return ERR_PTR(err); + if (tb[TCA_ACT_COOKIE]) { + user_cookie = nla_memdup_cookie(tb); + if (!user_cookie) { + NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); + err = -ENOMEM; + goto err_out; + } } + hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]); + if (tb[TCA_ACT_FLAGS]) { + userflags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); + if (!tc_act_flags_valid(userflags.value)) { + err = -EINVAL; + goto err_out; + } + } + + err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, tp, + userflags.value | flags, extack); + } else { + err = a_o->init(net, nla, est, &a, tp, userflags.value | flags, + extack); } + if (err < 0) + goto err_out; + *init_res = err; + + if (!police && tb[TCA_ACT_COOKIE]) + tcf_set_action_cookie(&a->user_cookie, user_cookie); + + if (!police) + a->hw_stats = hw_stats; return a; -err_mod: - module_put(a_o->owner); err_out: - if (cookie) { - kfree(cookie->data); - kfree(cookie); + if (user_cookie) { + kfree(user_cookie->data); + kfree(user_cookie); } return ERR_PTR(err); } -static void cleanup_a(struct list_head *actions, int ovr) +static bool tc_act_bind(u32 flags) { - struct tc_action *a; - - if (!ovr) - return; - - list_for_each_entry(a, actions, list) - a->tcfa_refcnt--; + return !!(flags & TCA_ACT_FLAGS_BIND); } +/* Returns numbers of initialized actions or negative error. */ + int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, int bind, - struct list_head *actions) + struct nlattr *est, struct tc_action *actions[], + int init_res[], size_t *attr_size, + u32 flags, u32 fl_flags, + struct netlink_ext_ack *extack) { - struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; + struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {}; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 2]; struct tc_action *act; + size_t sz = 0; int err; int i; - err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO + 1, nla, NULL, + extack); if (err < 0) return err; + /* The nested attributes are parsed as types, but they are really an + * array of actions. So we parse one more than we can handle, and return + * an error if the last one is set (as that indicates that the request + * contained more than the maximum number of actions). + */ + if (tb[TCA_ACT_MAX_PRIO + 1]) { + NL_SET_ERR_MSG_FMT(extack, + "Only %d actions supported per filter", + TCA_ACT_MAX_PRIO); + return -EINVAL; + } + for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind); + struct tc_action_ops *a_o; + + a_o = tc_action_load_ops(tb[i], flags, extack); + if (IS_ERR(a_o)) { + err = PTR_ERR(a_o); + goto err_mod; + } + ops[i - 1] = a_o; + } + + for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { + act = tcf_action_init_1(net, tp, tb[i], est, ops[i - 1], + &init_res[i - 1], flags, extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; } - act->order = i; - if (ovr) - act->tcfa_refcnt++; - list_add_tail(&act->list, actions); + sz += tcf_action_fill_size(act); + /* Start from index 0 */ + actions[i - 1] = act; + if (tc_act_bind(flags)) { + bool skip_sw = tc_skip_sw(fl_flags); + bool skip_hw = tc_skip_hw(fl_flags); + + if (tc_act_bind(act->tcfa_flags)) { + /* Action is created by classifier and is not + * standalone. Check that the user did not set + * any action flags different than the + * classifier flags, and inherit the flags from + * the classifier for the compatibility case + * where no flags were specified at all. + */ + if ((tc_act_skip_sw(act->tcfa_flags) && !skip_sw) || + (tc_act_skip_hw(act->tcfa_flags) && !skip_hw)) { + NL_SET_ERR_MSG(extack, + "Mismatch between action and filter offload flags"); + err = -EINVAL; + goto err; + } + if (skip_sw) + act->tcfa_flags |= TCA_ACT_FLAGS_SKIP_SW; + if (skip_hw) + act->tcfa_flags |= TCA_ACT_FLAGS_SKIP_HW; + continue; + } + + /* Action is standalone */ + if (skip_sw != tc_act_skip_sw(act->tcfa_flags) || + skip_hw != tc_act_skip_hw(act->tcfa_flags)) { + NL_SET_ERR_MSG(extack, + "Mismatch between action and filter offload flags"); + err = -EINVAL; + goto err; + } + } else { + err = tcf_action_offload_add(act, extack); + if (tc_act_skip_sw(act->tcfa_flags) && err) + goto err; + } } - /* Remove the temp refcnt which was necessary to protect against - * destroying an existing action which was being replaced + /* We have to commit them all together, because if any error happened in + * between, we could not handle the failure gracefully. */ - cleanup_a(actions, ovr); - return 0; + tcf_idr_insert_many(actions, init_res); + + *attr_size = tcf_action_full_attrs_size(sz); + err = i - 1; + goto err_mod; err: - tcf_action_destroy(actions, bind); + tcf_action_destroy(actions, flags & TCA_ACT_FLAGS_BIND); +err_mod: + for (i = 0; i < TCA_ACT_MAX_PRIO && ops[i]; i++) + module_put(ops[i]->owner); return err; } +void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, bool hw) +{ + if (a->cpu_bstats) { + _bstats_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + + this_cpu_ptr(a->cpu_qstats)->drops += drops; + + if (hw) + _bstats_update(this_cpu_ptr(a->cpu_bstats_hw), + bytes, packets); + return; + } + + _bstats_update(&a->tcfa_bstats, bytes, packets); + atomic_add(drops, &a->tcfa_drops); + if (hw) + _bstats_update(&a->tcfa_bstats_hw, bytes, packets); +} +EXPORT_SYMBOL(tcf_action_update_stats); + int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, int compat_mode) { - int err = 0; + struct gnet_stats_queue qstats = {0}; struct gnet_dump d; + int err = 0; if (p == NULL) goto errout; @@ -784,11 +1620,17 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, if (err < 0) goto errout; - if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 || + qstats.drops = atomic_read(&p->tcfa_drops); + qstats.overlimits = atomic_read(&p->tcfa_overlimits); + + if (gnet_stats_copy_basic(&d, p->cpu_bstats, + &p->tcfa_bstats, false) < 0 || + gnet_stats_copy_basic_hw(&d, p->cpu_bstats_hw, + &p->tcfa_bstats_hw, false) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, - &p->tcfa_qstats, - p->tcfa_qstats.qlen) < 0) + &qstats, + qstats.qlen) < 0) goto errout; if (gnet_stats_finish_copy(&d) < 0) @@ -800,9 +1642,9 @@ errout: return -1; } -static int tca_get_fill(struct sk_buff *skb, struct list_head *actions, +static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], u32 portid, u32 seq, u16 flags, int event, int bind, - int ref) + int ref, struct netlink_ext_ack *extack) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -817,16 +1659,21 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions, t->tca__pad1 = 0; t->tca__pad2 = 0; - nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) + if (extack && extack->_msg && + nla_put_string(skb, TCA_ROOT_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); + if (!nest) goto out_nlmsg_trim; - if (tcf_action_dump(skb, actions, bind, ref) < 0) + if (tcf_action_dump(skb, actions, bind, ref, false) < 0) goto out_nlmsg_trim; nla_nest_end(skb, nest); nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -836,7 +1683,8 @@ out_nlmsg_trim: static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct list_head *actions, int event) + struct tc_action *actions[], int event, + struct netlink_ext_ack *extack) { struct sk_buff *skb; @@ -844,7 +1692,8 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, - 0, 0) <= 0) { + 0, 1, NULL) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; } @@ -853,7 +1702,8 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, } static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid) + struct nlmsghdr *n, u32 portid, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_ACT_MAX + 1]; const struct tc_action_ops *ops; @@ -861,23 +1711,30 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, int index; int err; - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; err = -EINVAL; if (tb[TCA_ACT_INDEX] == NULL || - nla_len(tb[TCA_ACT_INDEX]) < sizeof(index)) + nla_len(tb[TCA_ACT_INDEX]) < sizeof(index)) { + NL_SET_ERR_MSG(extack, "Invalid TC action index value"); goto err_out; + } index = nla_get_u32(tb[TCA_ACT_INDEX]); err = -EINVAL; ops = tc_lookup_action(tb[TCA_ACT_KIND]); - if (!ops) /* could happen in batch of actions */ + if (!ops) { /* could happen in batch of actions */ + NL_SET_ERR_MSG(extack, "Specified TC action kind not found"); goto err_out; + } err = -ENOENT; - if (ops->lookup(net, &a, index) == 0) + if (__tcf_idr_search(net, ops, &a, index) == 0) { + NL_SET_ERR_MSG(extack, "TC action with specified index not found"); goto err_mod; + } module_put(ops->owner); return a; @@ -889,7 +1746,8 @@ err_out: } static int tca_action_flush(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid) + struct nlmsghdr *n, u32 portid, + struct netlink_ext_ack *extack) { struct sk_buff *skb; unsigned char *b; @@ -903,39 +1761,46 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, int err = -ENOMEM; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) { - pr_debug("tca_action_flush: failed skb alloc\n"); + if (!skb) return err; - } b = skb_tail_pointer(skb); - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; err = -EINVAL; kind = tb[TCA_ACT_KIND]; ops = tc_lookup_action(kind); - if (!ops) /*some idjot trying to flush unknown action */ + if (!ops) { /*some idjot trying to flush unknown action */ + NL_SET_ERR_MSG(extack, "Cannot flush unknown TC action"); goto err_out; + } nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); - if (!nlh) + if (!nlh) { + NL_SET_ERR_MSG(extack, "Failed to create TC action flush notification"); goto out_module_put; + } t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; - nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); + if (!nest) { + NL_SET_ERR_MSG(extack, "Failed to add new netlink message"); goto out_module_put; + } - err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops); - if (err <= 0) + err = __tcf_generic_walker(net, skb, &dcb, RTM_DELACTION, ops, extack); + if (err <= 0) { + nla_nest_cancel(skb, nest); goto out_module_put; + } nla_nest_end(skb, nest); @@ -944,8 +1809,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, module_put(ops->owner); err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - return 0; + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send TC action flush notification"); return err; @@ -956,137 +1821,329 @@ err_out: return err; } -static int -tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, - u32 portid) +static int tcf_action_delete(struct net *net, struct tc_action *actions[]) +{ + struct tc_action *a; + int i; + + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; + /* Actions can be deleted concurrently so we must save their + * type and id to search again after reference is released. + */ + struct tcf_idrinfo *idrinfo = a->idrinfo; + u32 act_index = a->tcfa_index; + + actions[i] = NULL; + if (tcf_action_put(a)) { + /* last reference, action was deleted concurrently */ + module_put(ops->owner); + } else { + int ret; + + /* now do the delete */ + ret = tcf_idr_delete_index(idrinfo, act_index); + if (ret < 0) + return ret; + } + } + return 0; +} + +static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, + struct tc_action *action) +{ + size_t attr_size = tcf_action_fill_size(action); + struct tc_action *actions[TCA_ACT_MAX_PRIO] = { + [0] = action, + }; + struct sk_buff *skb; + + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOBUFS); + + if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1, NULL) <= 0) { + kfree_skb(skb); + return ERR_PTR(-EINVAL); + } + + return skb; +} + +static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) { + const struct tc_action_ops *ops = action->ops; + struct sk_buff *skb; int ret; + + if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_reoffload_del_notify_msg(net, action); + if (IS_ERR(skb)) + return PTR_ERR(skb); + } + + ret = tcf_idr_release_unsafe(action); + if (ret == ACT_P_DELETED) { + module_put(ops->owner); + ret = rtnetlink_maybe_send(skb, net, 0, RTNLGRP_TC, 0); + } else { + kfree_skb(skb); + } + + return ret; +} + +int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, + void *cb_priv, bool add) +{ + struct tc_act_pernet_id *id_ptr; + struct tcf_idrinfo *idrinfo; + struct tc_action_net *tn; + struct tc_action *p; + unsigned int act_id; + unsigned long tmp; + unsigned long id; + struct idr *idr; + struct net *net; + int ret; + + if (!cb) + return -EINVAL; + + down_read(&net_rwsem); + mutex_lock(&act_id_mutex); + + for_each_net(net) { + list_for_each_entry(id_ptr, &act_pernet_id_list, list) { + act_id = id_ptr->id; + tn = net_generic(net, act_id); + if (!tn) + continue; + idrinfo = tn->idrinfo; + if (!idrinfo) + continue; + + mutex_lock(&idrinfo->lock); + idr = &idrinfo->action_idr; + idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p) || tc_act_bind(p->tcfa_flags)) + continue; + if (add) { + tcf_action_offload_add_ex(p, NULL, cb, + cb_priv); + continue; + } + + /* cb unregister to update hw count */ + ret = tcf_action_offload_del_ex(p, cb, cb_priv); + if (ret < 0) + continue; + if (tc_act_skip_sw(p->tcfa_flags) && + !tc_act_in_hw(p)) + tcf_reoffload_del_notify(net, p); + } + mutex_unlock(&idrinfo->lock); + } + } + mutex_unlock(&act_id_mutex); + up_read(&net_rwsem); + + return 0; +} + +static struct sk_buff *tcf_del_notify_msg(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], + u32 portid, size_t attr_size, + struct netlink_ext_ack *extack) +{ struct sk_buff *skb; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) - return -ENOBUFS; + return ERR_PTR(-ENOBUFS); if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, - 0, 1) <= 0) { + 0, 2, extack) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes"); kfree_skb(skb); - return -EINVAL; + return ERR_PTR(-EINVAL); + } + + return skb; +} + +static int tcf_del_notify(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], u32 portid, + size_t attr_size, struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + int ret; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_del_notify_msg(net, n, actions, portid, attr_size, + extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); } /* now do the delete */ - ret = tcf_action_destroy(actions, 0); + ret = tcf_action_delete(net, actions); if (ret < 0) { + NL_SET_ERR_MSG(extack, "Failed to delete TC action"); kfree_skb(skb); return ret; } - ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (ret > 0) - return 0; - return ret; + return rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, - u32 portid, int event) + u32 portid, int event, struct netlink_ext_ack *extack) { int i, ret; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; - LIST_HEAD(actions); + size_t attr_size = 0; + struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; - ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL); + ret = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO, nla, NULL, + extack); if (ret < 0) return ret; if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) { - if (tb[1] != NULL) - return tca_action_flush(net, tb[1], n, portid); - else - return -EINVAL; + if (tb[1]) + return tca_action_flush(net, tb[1], n, portid, extack); + + NL_SET_ERR_MSG(extack, "Invalid netlink attributes while flushing TC action"); + return -EINVAL; } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_get_1(net, tb[i], n, portid); + act = tcf_action_get_1(net, tb[i], n, portid, extack); if (IS_ERR(act)) { ret = PTR_ERR(act); goto err; } - act->order = i; - list_add_tail(&act->list, &actions); + attr_size += tcf_action_fill_size(act); + actions[i - 1] = act; } + attr_size = tcf_action_full_attrs_size(attr_size); + if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, &actions, event); + ret = tcf_get_notify(net, portid, n, actions, event, extack); else { /* delete */ - ret = tcf_del_notify(net, n, &actions, portid); + ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) goto err; - return ret; + return 0; } err: - if (event != RTM_GETACTION) - tcf_action_destroy(&actions, 0); + tcf_action_put_many(actions); return ret; } -static int -tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, - u32 portid) +static struct sk_buff *tcf_add_notify_msg(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], + u32 portid, size_t attr_size, + struct netlink_ext_ack *extack) { struct sk_buff *skb; - int err = 0; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) - return -ENOBUFS; + return ERR_PTR(-ENOBUFS); if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, - RTM_NEWACTION, 0, 0) <= 0) { + RTM_NEWACTION, 0, 0, extack) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); - return -EINVAL; + return ERR_PTR(-EINVAL); } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - err = 0; - return err; + return skb; +} + +static int tcf_add_notify(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], u32 portid, + size_t attr_size, struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_add_notify_msg(net, n, actions, portid, attr_size, + extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); + } + + return rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int tcf_action_add(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid, int ovr) + struct nlmsghdr *n, u32 portid, u32 flags, + struct netlink_ext_ack *extack) { - int ret = 0; - LIST_HEAD(actions); + size_t attr_size = 0; + int loop, ret; + struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; + int init_res[TCA_ACT_MAX_PRIO] = {}; + + for (loop = 0; loop < 10; loop++) { + ret = tcf_action_init(net, NULL, nla, NULL, actions, init_res, + &attr_size, flags, 0, extack); + if (ret != -EAGAIN) + break; + } - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions); - if (ret) + if (ret < 0) return ret; - return tcf_add_notify(net, n, &actions, portid); + ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); + + /* only put bound actions */ + tca_put_bound_many(actions, init_res); + + return ret; } +static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = { + [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAG_LARGE_DUMP_ON | + TCA_ACT_FLAG_TERSE_DUMP), + [TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 }, +}; + static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); - struct nlattr *tca[TCA_ACT_MAX + 1]; - u32 portid = skb ? NETLINK_CB(skb).portid : 0; - int ret = 0, ovr = 0; + struct nlattr *tca[TCA_ROOT_MAX + 1]; + u32 portid = NETLINK_CB(skb).portid; + u32 flags = 0; + int ret = 0; if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL, - extack); + ret = nlmsg_parse_deprecated(n, sizeof(struct tcamsg), tca, + TCA_ROOT_MAX, NULL, extack); if (ret < 0) return ret; if (tca[TCA_ACT_TAB] == NULL) { - pr_notice("tc_ctl_action: received NO action attribs\n"); + NL_SET_ERR_MSG(extack, "Netlink action attributes missing"); return -EINVAL; } @@ -1100,19 +2157,17 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, * is zero) then just set this */ if (n->nlmsg_flags & NLM_F_REPLACE) - ovr = 1; -replay: - ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr); - if (ret == -EAGAIN) - goto replay; + flags = TCA_ACT_FLAGS_REPLACE; + ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, flags, + extack); break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - portid, RTM_DELACTION); + portid, RTM_DELACTION, extack); break; case RTM_GETACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - portid, RTM_GETACTION); + portid, RTM_GETACTION, extack); break; default: BUG(); @@ -1121,27 +2176,22 @@ replay: return ret; } -static struct nlattr *find_dump_kind(const struct nlmsghdr *n) +static struct nlattr *find_dump_kind(struct nlattr **nla) { struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1]; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; - struct nlattr *nla[TCAA_MAX + 1]; struct nlattr *kind; - if (nlmsg_parse(n, sizeof(struct tcamsg), nla, TCAA_MAX, - NULL, NULL) < 0) - return NULL; tb1 = nla[TCA_ACT_TAB]; if (tb1 == NULL) return NULL; - if (nla_parse(tb, TCA_ACT_MAX_PRIO, nla_data(tb1), - NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0) + if (nla_parse_deprecated(tb, TCA_ACT_MAX_PRIO, nla_data(tb1), NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0) return NULL; if (tb[1] == NULL) return NULL; - if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0) + if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], tcf_action_policy, NULL) < 0) return NULL; kind = tb2[TCA_ACT_KIND]; @@ -1157,8 +2207,20 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) struct tc_action_ops *a_o; int ret = 0; struct tcamsg *t = (struct tcamsg *) nlmsg_data(cb->nlh); - struct nlattr *kind = find_dump_kind(cb->nlh); + struct nlattr *tb[TCA_ROOT_MAX + 1]; + struct nlattr *count_attr = NULL; + unsigned long jiffy_since = 0; + struct nlattr *kind = NULL; + struct nla_bitfield32 bf; + u32 msecs_since = 0; + u32 act_count = 0; + + ret = nlmsg_parse_deprecated(cb->nlh, sizeof(struct tcamsg), tb, + TCA_ROOT_MAX, tcaa_policy, cb->extack); + if (ret < 0) + return ret; + kind = find_dump_kind(tb); if (kind == NULL) { pr_info("tc_dump_action: action bad kind\n"); return 0; @@ -1168,26 +2230,47 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (a_o == NULL) return 0; + cb->args[2] = 0; + if (tb[TCA_ROOT_FLAGS]) { + bf = nla_get_bitfield32(tb[TCA_ROOT_FLAGS]); + cb->args[2] = bf.value; + } + + if (tb[TCA_ROOT_TIME_DELTA]) { + msecs_since = nla_get_u32(tb[TCA_ROOT_TIME_DELTA]); + } + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*t), 0); if (!nlh) goto out_module_put; + + if (msecs_since) + jiffy_since = jiffies - msecs_to_jiffies(msecs_since); + t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; + cb->args[3] = jiffy_since; + count_attr = nla_reserve(skb, TCA_ROOT_COUNT, sizeof(u32)); + if (!count_attr) + goto out_module_put; - nest = nla_nest_start(skb, TCA_ACT_TAB); + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); if (nest == NULL) goto out_module_put; - ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o); + ret = __tcf_generic_walker(net, skb, cb, RTM_GETACTION, a_o, NULL); if (ret < 0) goto out_module_put; if (ret > 0) { nla_nest_end(skb, nest); ret = skb->len; + act_count = cb->args[1]; + memcpy(nla_data(count_attr), &act_count, sizeof(u32)); + cb->args[1] = 0; } else nlmsg_trim(skb, b); @@ -1203,13 +2286,16 @@ out_module_put: return skb->len; } +static const struct rtnl_msg_handler tc_action_rtnl_msg_handlers[] __initconst = { + {.msgtype = RTM_NEWACTION, .doit = tc_ctl_action}, + {.msgtype = RTM_DELACTION, .doit = tc_ctl_action}, + {.msgtype = RTM_GETACTION, .doit = tc_ctl_action, + .dumpit = tc_dump_action}, +}; + static int __init tc_action_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, - NULL); - + rtnl_register_many(tc_action_rtnl_msg_handlers); return 0; } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 9afe1337cfd1..c2b5bc19e091 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -1,10 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include <linux/module.h> @@ -16,12 +12,14 @@ #include <linux/bpf.h> #include <net/netlink.h> +#include <net/sock.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_bpf.h> #include <net/tc_act/tc_bpf.h> +#include <net/tc_wrapper.h> -#define BPF_TAB_MASK 15 #define ACT_BPF_NAME_LEN 256 struct tcf_bpf_cfg { @@ -32,11 +30,11 @@ struct tcf_bpf_cfg { bool is_ebpf; }; -static unsigned int bpf_net_id; static struct tc_action_ops act_bpf_ops; -static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb, + const struct tc_action *act, + struct tcf_result *res) { bool at_ingress = skb_at_tc_ingress(skb); struct tcf_bpf *prog = to_bpf(act); @@ -44,20 +42,20 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, int action, filter_res; tcf_lastuse_update(&prog->tcf_tm); - bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb); - rcu_read_lock(); filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); - filter_res = BPF_PROG_RUN(filter, skb); + filter_res = bpf_prog_run_data_pointers(filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); - filter_res = BPF_PROG_RUN(filter, skb); + filter_res = bpf_prog_run_data_pointers(filter, skb); } - rcu_read_unlock(); + if (unlikely(!skb->tstamp && skb->tstamp_type)) + skb->tstamp_type = SKB_CLOCK_REALTIME; + if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) + skb_orphan(skb); /* A BPF program may overwrite the default action opcode. * Similarly as in cls_bpf, if filter_res == -1 we use the @@ -66,7 +64,7 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, * In case a different well-known TC_ACT opcode has been * returned, it will overwrite the default one. * - * For everything else that is unkown, TC_ACT_UNSPEC is + * For everything else that is unknown, TC_ACT_UNSPEC is * returned. */ switch (filter_res) { @@ -142,13 +140,14 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, struct tcf_bpf *prog = to_bpf(act); struct tc_act_bpf opt = { .index = prog->tcf_index, - .refcnt = prog->tcf_refcnt - ref, - .bindcnt = prog->tcf_bindcnt - bind, - .action = prog->tcf_action, + .refcnt = refcount_read(&prog->tcf_refcnt) - ref, + .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind, }; struct tcf_t tm; int ret; + spin_lock_bh(&prog->tcf_lock); + opt.action = prog->tcf_action; if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -164,9 +163,11 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, TCA_ACT_BPF_PAD)) goto nla_put_failure; + spin_unlock_bh(&prog->tcf_lock); return skb->len; nla_put_failure: + spin_unlock_bh(&prog->tcf_lock); nlmsg_trim(skb, tp); return -1; } @@ -197,12 +198,10 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS])) return -EINVAL; - bpf_ops = kzalloc(bpf_size, GFP_KERNEL); + bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL); if (bpf_ops == NULL) return -ENOMEM; - memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size); - fprog_tmp.len = bpf_num_ops; fprog_tmp.filter = bpf_ops; @@ -249,10 +248,14 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) { - if (cfg->is_ebpf) - bpf_prog_put(cfg->filter); - else - bpf_prog_destroy(cfg->filter); + struct bpf_prog *filter = cfg->filter; + + if (filter) { + if (cfg->is_ebpf) + bpf_prog_put(filter); + else + bpf_prog_destroy(filter); + } kfree(cfg->bpf_ops); kfree(cfg->bpf_name); @@ -263,7 +266,7 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, { cfg->is_ebpf = tcf_bpf_is_ebpf(prog); /* updates to prog->filter are prevented, since it's called either - * with rtnl lock or during final cleanup in rcu callback + * with tcf lock or during final cleanup in rcu callback */ cfg->filter = rcu_dereference_protected(prog->filter, 1); @@ -273,20 +276,25 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, - int replace, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, bpf_net_id); + struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; + u32 index; if (!nla) return -EINVAL; - ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy, NULL); + ret = nla_parse_nested_deprecated(tb, TCA_ACT_BPF_MAX, nla, + act_bpf_policy, NULL); if (ret < 0) return ret; @@ -294,30 +302,40 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - - if (!tcf_hash_check(tn, parm->index, act, bind)) { - ret = tcf_hash_create(tn, parm->index, est, act, - &act_bpf_ops, bind, true); - if (ret < 0) + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, act, bind); + if (!ret) { + ret = tcf_idr_create(tn, index, est, act, + &act_bpf_ops, bind, true, flags); + if (ret < 0) { + tcf_idr_cleanup(tn, index); return ret; + } res = ACT_P_CREATED; - } else { + } else if (ret > 0) { /* Don't override defaults. */ if (bind) - return 0; + return ACT_P_BOUND; - tcf_hash_release(*act, bind); - if (!replace) + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*act, bind); return -EEXIST; + } + } else { + return ret; } + ret = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (ret < 0) + goto release_idr; + is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; is_ebpf = tb[TCA_ACT_BPF_FD]; - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + if (is_bpf == is_ebpf) { ret = -EINVAL; - goto out; + goto put_chain; } memset(&cfg, 0, sizeof(cfg)); @@ -325,11 +343,11 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : tcf_bpf_init_from_efd(tb, &cfg); if (ret < 0) - goto out; + goto put_chain; prog = to_bpf(*act); - ASSERT_RTNL(); + spin_lock_bh(&prog->tcf_lock); if (res != ACT_P_CREATED) tcf_bpf_prog_fill_cfg(prog, &old); @@ -339,26 +357,31 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (cfg.bpf_num_ops) prog->bpf_num_ops = cfg.bpf_num_ops; - prog->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*act, parm->action, goto_ch); rcu_assign_pointer(prog->filter, cfg.filter); + spin_unlock_bh(&prog->tcf_lock); - if (res == ACT_P_CREATED) { - tcf_hash_insert(tn, *act); - } else { + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + + if (res != ACT_P_CREATED) { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); } return res; -out: - if (res == ACT_P_CREATED) - tcf_hash_cleanup(*act, est); +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + +release_idr: + tcf_idr_release(*act, bind); return ret; } -static void tcf_bpf_cleanup(struct tc_action *act, int bind) +static void tcf_bpf_cleanup(struct tc_action *act) { struct tcf_bpf_cfg tmp; @@ -366,53 +389,34 @@ static void tcf_bpf_cleanup(struct tc_action *act, int bind) tcf_bpf_cfg_cleanup(&tmp); } -static int tcf_bpf_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, bpf_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, bpf_net_id); - - return tcf_hash_search(tn, a, index); -} - static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", - .type = TCA_ACT_BPF, + .id = TCA_ID_BPF, .owner = THIS_MODULE, - .act = tcf_bpf, + .act = tcf_bpf_act, .dump = tcf_bpf_dump, .cleanup = tcf_bpf_cleanup, .init = tcf_bpf_init, - .walk = tcf_bpf_walker, - .lookup = tcf_bpf_search, .size = sizeof(struct tcf_bpf), }; +MODULE_ALIAS_NET_ACT("bpf"); static __net_init int bpf_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, bpf_net_id); + struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); - return tc_action_net_init(tn, &act_bpf_ops, BPF_TAB_MASK); + return tc_action_net_init(net, tn, &act_bpf_ops); } -static void __net_exit bpf_exit_net(struct net *net) +static void __net_exit bpf_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, bpf_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_bpf_ops.net_id); } static struct pernet_operations bpf_net_ops = { .init = bpf_init_net, - .exit = bpf_exit_net, - .id = &bpf_net_id, + .exit_batch = bpf_exit_net, + .id = &act_bpf_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2155bc6c6a1e..26ba8c2d20ab 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_connmark.c netfilter connmark retriever action * skb mark is over-written * * Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include <linux/module.h> @@ -21,75 +17,78 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/act_api.h> +#include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_connmark.h> #include <net/tc_act/tc_connmark.h> +#include <net/tc_wrapper.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> -#define CONNMARK_TAB_MASK 3 - -static unsigned int connmark_net_id; static struct tc_action_ops act_connmark_ops; -static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_connmark_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { const struct nf_conntrack_tuple_hash *thash; struct nf_conntrack_tuple tuple; enum ip_conntrack_info ctinfo; struct tcf_connmark_info *ca = to_connmark(a); + struct tcf_connmark_parms *parms; struct nf_conntrack_zone zone; struct nf_conn *c; int proto; - spin_lock(&ca->tcf_lock); tcf_lastuse_update(&ca->tcf_tm); - bstats_update(&ca->tcf_bstats, skb); + tcf_action_update_bstats(&ca->common, skb); - if (skb->protocol == htons(ETH_P_IP)) { + parms = rcu_dereference_bh(ca->parms); + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } c = nf_ct_get(skb, &ctinfo); if (c) { - skb->mark = c->mark; - /* using overlimits stats to count how many packets marked */ - ca->tcf_qstats.overlimits++; - goto out; + skb->mark = READ_ONCE(c->mark); + goto count; } - if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - proto, ca->net, &tuple)) + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, parms->net, + &tuple)) goto out; - zone.id = ca->zone; + zone.id = parms->zone; zone.dir = NF_CT_DEFAULT_ZONE_DIR; - thash = nf_conntrack_find_get(ca->net, &zone, &tuple); + thash = nf_conntrack_find_get(parms->net, &zone, &tuple); if (!thash) goto out; c = nf_ct_tuplehash_to_ctrack(thash); - /* using overlimits stats to count how many packets marked */ - ca->tcf_qstats.overlimits++; - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); nf_ct_put(c); +count: + /* using overlimits stats to count how many packets marked */ + tcf_action_inc_overlimit_qstats(&ca->common); out: - spin_unlock(&ca->tcf_lock); - return ca->tcf_action; + return parms->action; } static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { @@ -98,70 +97,118 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, connmark_net_id); + struct tc_action_net *tn = net_generic(net, act_connmark_ops.net_id); + struct tcf_connmark_parms *nparms, *oparms; struct nlattr *tb[TCA_CONNMARK_MAX + 1]; + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct tcf_chain *goto_ch = NULL; struct tcf_connmark_info *ci; struct tc_connmark *parm; - int ret = 0; + int ret = 0, err; + u32 index; if (!nla) return -EINVAL; - ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy, - NULL); + ret = nla_parse_nested_deprecated(tb, TCA_CONNMARK_MAX, nla, + connmark_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_CONNMARK_PARMS]) return -EINVAL; - parm = nla_data(tb[TCA_CONNMARK_PARMS]); + nparms = kzalloc(sizeof(*nparms), GFP_KERNEL); + if (!nparms) + return -ENOMEM; - if (!tcf_hash_check(tn, parm->index, a, bind)) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_connmark_ops, bind, false); - if (ret) - return ret; + parm = nla_data(tb[TCA_CONNMARK_PARMS]); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, a, bind); + if (!ret) { + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_connmark_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); + err = ret; + goto out_free; + } ci = to_connmark(*a); - ci->tcf_action = parm->action; - ci->net = net; - ci->zone = parm->zone; - tcf_hash_insert(tn, *a); + nparms->net = net; + nparms->zone = parm->zone; + ret = ACT_P_CREATED; - } else { + } else if (ret > 0) { ci = to_connmark(*a); - if (bind) - return 0; - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; - /* replacing action and zone */ - ci->tcf_action = parm->action; - ci->zone = parm->zone; + if (bind) { + err = ACT_P_BOUND; + goto out_free; + } + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + err = -EEXIST; + goto release_idr; + } + + nparms->net = rtnl_dereference(ci->parms)->net; + nparms->zone = parm->zone; + + ret = 0; + } else { + err = ret; + goto out_free; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + nparms->action = parm->action; + + spin_lock_bh(&ci->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + oparms = rcu_replace_pointer(ci->parms, nparms, lockdep_is_held(&ci->tcf_lock)); + spin_unlock_bh(&ci->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + + if (oparms) + kfree_rcu(oparms, rcu); + return ret; + +release_idr: + tcf_idr_release(*a, bind); +out_free: + kfree(nparms); + return err; } static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { + const struct tcf_connmark_info *ci = to_connmark(a); unsigned char *b = skb_tail_pointer(skb); - struct tcf_connmark_info *ci = to_connmark(a); - - struct tc_connmark opt = { - .index = ci->tcf_index, - .refcnt = ci->tcf_refcnt - ref, - .bindcnt = ci->tcf_bindcnt - bind, - .action = ci->tcf_action, - .zone = ci->zone, - }; + const struct tcf_connmark_parms *parms; + struct tc_connmark opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + + opt.index = ci->tcf_index; + opt.refcnt = refcount_read(&ci->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind; + + rcu_read_lock(); + parms = rcu_dereference(ci->parms); + + opt.action = parms->action; + opt.zone = parms->zone; if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -169,59 +216,54 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t, TCA_CONNMARK_PAD)) goto nla_put_failure; + rcu_read_unlock(); return skb->len; + nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tcf_connmark_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static void tcf_connmark_cleanup(struct tc_action *a) { - struct tc_action_net *tn = net_generic(net, connmark_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, connmark_net_id); + struct tcf_connmark_info *ci = to_connmark(a); + struct tcf_connmark_parms *parms; - return tcf_hash_search(tn, a, index); + parms = rcu_dereference_protected(ci->parms, 1); + if (parms) + kfree_rcu(parms, rcu); } static struct tc_action_ops act_connmark_ops = { .kind = "connmark", - .type = TCA_ACT_CONNMARK, + .id = TCA_ID_CONNMARK, .owner = THIS_MODULE, - .act = tcf_connmark, + .act = tcf_connmark_act, .dump = tcf_connmark_dump, .init = tcf_connmark_init, - .walk = tcf_connmark_walker, - .lookup = tcf_connmark_search, + .cleanup = tcf_connmark_cleanup, .size = sizeof(struct tcf_connmark_info), }; +MODULE_ALIAS_NET_ACT("connmark"); static __net_init int connmark_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, connmark_net_id); + struct tc_action_net *tn = net_generic(net, act_connmark_ops.net_id); - return tc_action_net_init(tn, &act_connmark_ops, CONNMARK_TAB_MASK); + return tc_action_net_init(net, tn, &act_connmark_ops); } -static void __net_exit connmark_exit_net(struct net *net) +static void __net_exit connmark_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, connmark_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_connmark_ops.net_id); } static struct pernet_operations connmark_net_ops = { .init = connmark_init_net, - .exit = connmark_exit_net, - .id = &connmark_net_id, + .exit_batch = connmark_exit_net, + .id = &act_connmark_ops.net_id, .size = sizeof(struct tc_action_net), }; @@ -240,4 +282,3 @@ module_exit(connmark_cleanup_module); MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>"); MODULE_DESCRIPTION("Connection tracking mark restoring"); MODULE_LICENSE("GPL"); - diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 3317a2f579da..0939e6b2ba4d 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Checksum updating actions * * Copyright (c) 2010 Gregoire Baron <baronchon@n7mm.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. - * */ #include <linux/types.h> @@ -33,64 +28,97 @@ #include <net/sctp/checksum.h> #include <net/act_api.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_csum.h> #include <net/tc_act/tc_csum.h> - -#define CSUM_TAB_MASK 15 +#include <net/tc_wrapper.h> static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, }; -static unsigned int csum_net_id; static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind) + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, + u32 flags, struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, csum_net_id); + struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct tcf_csum_params *params_new; struct nlattr *tb[TCA_CSUM_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_CSUM_MAX, nla, csum_policy, + NULL); if (err < 0) return err; if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - - if (!tcf_hash_check(tn, parm->index, a, bind)) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_csum_ops, bind, false); - if (ret) + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (!err) { + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_csum_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { - if (bind)/* dont override defaults */ - return 0; - tcf_hash_release(*a, bind); - if (!ovr) + } else if (err > 0) { + if (bind) /* dont override defaults */ + return ACT_P_BOUND; + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); return -EEXIST; + } + } else { + return err; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + p = to_tcf_csum(*a); + + params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + if (unlikely(!params_new)) { + err = -ENOMEM; + goto put_chain; + } + params_new->update_flags = parm->update_flags; + params_new->action = parm->action; + spin_lock_bh(&p->tcf_lock); - p->tcf_action = parm->action; - p->update_flags = parm->update_flags; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + params_new = rcu_replace_pointer(p->params, params_new, + lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (params_new) + kfree_rcu(params_new, rcu); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } /** @@ -340,7 +368,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, { struct sctphdr *sctph; - if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); @@ -349,8 +377,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, sctph->checksum = sctp_compute_cksum(skb, skb_network_offset(skb) + ihl); - skb->ip_summed = CHECKSUM_NONE; - skb->csum_not_inet = 0; + skb_reset_csum_not_inet(skb); return 1; } @@ -537,24 +564,31 @@ fail: return 0; } -static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_csum_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_csum *p = to_tcf_csum(a); - int action; + bool orig_vlan_tag_present = false; + unsigned int vlan_hdr_count = 0; + struct tcf_csum_params *params; u32 update_flags; + __be16 protocol; + int action; + + params = rcu_dereference_bh(p->params); - spin_lock(&p->tcf_lock); tcf_lastuse_update(&p->tcf_tm); - bstats_update(&p->tcf_bstats, skb); - action = p->tcf_action; - update_flags = p->update_flags; - spin_unlock(&p->tcf_lock); + tcf_action_update_bstats(&p->common, skb); + action = params->action; if (unlikely(action == TC_ACT_SHOT)) goto drop; - switch (tc_skb_protocol(skb)) { + update_flags = params->update_flags; + protocol = skb_protocol(skb, false); +again: + switch (protocol) { case cpu_to_be16(ETH_P_IP): if (!tcf_csum_ipv4(skb, update_flags)) goto drop; @@ -563,91 +597,136 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, if (!tcf_csum_ipv6(skb, update_flags)) goto drop; break; + case cpu_to_be16(ETH_P_8021AD): + fallthrough; + case cpu_to_be16(ETH_P_8021Q): + if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) { + protocol = skb->protocol; + orig_vlan_tag_present = true; + } else { + struct vlan_hdr *vlan = (struct vlan_hdr *)skb->data; + + protocol = vlan->h_vlan_encapsulated_proto; + skb_pull(skb, VLAN_HLEN); + skb_reset_network_header(skb); + vlan_hdr_count++; + } + goto again; + } + +out: + /* Restore the skb for the pulled VLAN tags */ + while (vlan_hdr_count--) { + skb_push(skb, VLAN_HLEN); + skb_reset_network_header(skb); } return action; drop: - spin_lock(&p->tcf_lock); - p->tcf_qstats.drops++; - spin_unlock(&p->tcf_lock); - return TC_ACT_SHOT; + tcf_action_inc_drop_qstats(&p->common); + action = TC_ACT_SHOT; + goto out; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { + const struct tcf_csum *p = to_tcf_csum(a); unsigned char *b = skb_tail_pointer(skb); - struct tcf_csum *p = to_tcf_csum(a); + const struct tcf_csum_params *params; struct tc_csum opt = { - .update_flags = p->update_flags, .index = p->tcf_index, - .action = p->tcf_action, - .refcnt = p->tcf_refcnt - ref, - .bindcnt = p->tcf_bindcnt - bind, + .refcnt = refcount_read(&p->tcf_refcnt) - ref, + .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; + rcu_read_lock(); + params = rcu_dereference(p->params); + opt.action = params->action; + opt.update_flags = params->update_flags; + if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD)) goto nla_put_failure; + rcu_read_unlock(); return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tcf_csum_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static void tcf_csum_cleanup(struct tc_action *a) { - struct tc_action_net *tn = net_generic(net, csum_net_id); + struct tcf_csum *p = to_tcf_csum(a); + struct tcf_csum_params *params; - return tcf_generic_walker(tn, skb, cb, type, ops); + params = rcu_dereference_protected(p->params, 1); + if (params) + kfree_rcu(params, rcu); } -static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index) +static size_t tcf_csum_get_fill_size(const struct tc_action *act) { - struct tc_action_net *tn = net_generic(net, csum_net_id); + return nla_total_size(sizeof(struct tc_csum)); +} - return tcf_hash_search(tn, a, index); +static int tcf_csum_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_CSUM; + entry->csum_flags = tcf_csum_update_flags(act); + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_CSUM; + } + + return 0; } static struct tc_action_ops act_csum_ops = { .kind = "csum", - .type = TCA_ACT_CSUM, + .id = TCA_ID_CSUM, .owner = THIS_MODULE, - .act = tcf_csum, + .act = tcf_csum_act, .dump = tcf_csum_dump, .init = tcf_csum_init, - .walk = tcf_csum_walker, - .lookup = tcf_csum_search, + .cleanup = tcf_csum_cleanup, + .get_fill_size = tcf_csum_get_fill_size, + .offload_act_setup = tcf_csum_offload_act_setup, .size = sizeof(struct tcf_csum), }; +MODULE_ALIAS_NET_ACT("csum"); static __net_init int csum_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, csum_net_id); + struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); - return tc_action_net_init(tn, &act_csum_ops, CSUM_TAB_MASK); + return tc_action_net_init(net, tn, &act_csum_ops); } -static void __net_exit csum_exit_net(struct net *net) +static void __net_exit csum_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, csum_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_csum_ops.net_id); } static struct pernet_operations csum_net_ops = { .init = csum_init_net, - .exit = csum_exit_net, - .id = &csum_net_id, + .exit_batch = csum_exit_net, + .id = &act_csum_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c new file mode 100644 index 000000000000..2b6ac7069dc1 --- /dev/null +++ b/net/sched/act_ct.c @@ -0,0 +1,1698 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* - + * net/sched/act_ct.c Connection Tracking action + * + * Authors: Paul Blakey <paulb@mellanox.com> + * Yossi Kuperman <yossiku@mellanox.com> + * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/pkt_cls.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/rhashtable.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/act_api.h> +#include <net/ip.h> +#include <net/ipv6_frag.h> +#include <uapi/linux/tc_act/tc_ct.h> +#include <net/tc_act/tc_ct.h> +#include <net/tc_wrapper.h> + +#include <net/netfilter/nf_flow_table.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_acct.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/netfilter/nf_conntrack_act_ct.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <uapi/linux/netfilter/nf_nat.h> + +static struct workqueue_struct *act_ct_wq; +static struct rhashtable zones_ht; +static DEFINE_MUTEX(zones_mutex); + +struct zones_ht_key { + struct net *net; + u16 zone; +}; + +struct tcf_ct_flow_table { + struct rhash_head node; /* In zones tables */ + + struct rcu_work rwork; + struct nf_flowtable nf_ft; + refcount_t ref; + struct zones_ht_key key; + + bool dying; +}; + +static const struct rhashtable_params zones_params = { + .head_offset = offsetof(struct tcf_ct_flow_table, node), + .key_offset = offsetof(struct tcf_ct_flow_table, key), + .key_len = offsetofend(struct zones_ht_key, zone), + .automatic_shrinking = true, +}; + +static struct flow_action_entry * +tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action) +{ + int i = flow_action->num_entries++; + + return &flow_action->entries[i]; +} + +static void tcf_ct_add_mangle_action(struct flow_action *action, + enum flow_action_mangle_base htype, + u32 offset, + u32 mask, + u32 val) +{ + struct flow_action_entry *entry; + + entry = tcf_ct_flow_table_flow_action_get_next(action); + entry->id = FLOW_ACTION_MANGLE; + entry->mangle.htype = htype; + entry->mangle.mask = ~mask; + entry->mangle.offset = offset; + entry->mangle.val = val; +} + +/* The following nat helper functions check if the inverted reverse tuple + * (target) is different then the current dir tuple - meaning nat for ports + * and/or ip is needed, and add the relevant mangle actions. + */ +static void +tcf_ct_flow_table_add_action_nat_ipv4(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, + offsetof(struct iphdr, saddr), + 0xFFFFFFFF, + be32_to_cpu(target.src.u3.ip)); + if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, + offsetof(struct iphdr, daddr), + 0xFFFFFFFF, + be32_to_cpu(target.dst.u3.ip)); +} + +static void +tcf_ct_add_ipv6_addr_mangle_action(struct flow_action *action, + union nf_inet_addr *addr, + u32 offset) +{ + int i; + + for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP6, + i * sizeof(u32) + offset, + 0xFFFFFFFF, be32_to_cpu(addr->ip6[i])); +} + +static void +tcf_ct_flow_table_add_action_nat_ipv6(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) + tcf_ct_add_ipv6_addr_mangle_action(action, &target.src.u3, + offsetof(struct ipv6hdr, + saddr)); + if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) + tcf_ct_add_ipv6_addr_mangle_action(action, &target.dst.u3, + offsetof(struct ipv6hdr, + daddr)); +} + +static void +tcf_ct_flow_table_add_action_nat_tcp(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + __be16 target_src = target.src.u.tcp.port; + __be16 target_dst = target.dst.u.tcp.port; + + if (target_src != tuple->src.u.tcp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + offsetof(struct tcphdr, source), + 0xFFFF, be16_to_cpu(target_src)); + if (target_dst != tuple->dst.u.tcp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + offsetof(struct tcphdr, dest), + 0xFFFF, be16_to_cpu(target_dst)); +} + +static void +tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + __be16 target_src = target.src.u.udp.port; + __be16 target_dst = target.dst.u.udp.port; + + if (target_src != tuple->src.u.udp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, + offsetof(struct udphdr, source), + 0xFFFF, be16_to_cpu(target_src)); + if (target_dst != tuple->dst.u.udp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, + offsetof(struct udphdr, dest), + 0xFFFF, be16_to_cpu(target_dst)); +} + +static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, + enum ip_conntrack_dir dir, + enum ip_conntrack_info ctinfo, + struct flow_action *action) +{ + struct nf_conn_labels *ct_labels; + struct flow_action_entry *entry; + u32 *act_ct_labels; + + entry = tcf_ct_flow_table_flow_action_get_next(action); + entry->id = FLOW_ACTION_CT_METADATA; +#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) + entry->ct_metadata.mark = READ_ONCE(ct->mark); +#endif + /* aligns with the CT reference on the SKB nf_ct_set */ + entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; + entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; + + act_ct_labels = entry->ct_metadata.labels; + ct_labels = nf_ct_labels_find(ct); + if (ct_labels) + memcpy(act_ct_labels, ct_labels->bits, NF_CT_LABELS_MAX_SIZE); + else + memset(act_ct_labels, 0, NF_CT_LABELS_MAX_SIZE); +} + +static int tcf_ct_flow_table_add_action_nat(struct net *net, + struct nf_conn *ct, + enum ip_conntrack_dir dir, + struct flow_action *action) +{ + const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; + struct nf_conntrack_tuple target; + + if (!(ct->status & IPS_NAT_MASK)) + return 0; + + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); + + switch (tuple->src.l3num) { + case NFPROTO_IPV4: + tcf_ct_flow_table_add_action_nat_ipv4(tuple, target, + action); + break; + case NFPROTO_IPV6: + tcf_ct_flow_table_add_action_nat_ipv6(tuple, target, + action); + break; + default: + return -EOPNOTSUPP; + } + + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + tcf_ct_flow_table_add_action_nat_tcp(tuple, target, action); + break; + case IPPROTO_UDP: + tcf_ct_flow_table_add_action_nat_udp(tuple, target, action); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int tcf_ct_flow_table_fill_actions(struct net *net, + struct flow_offload *flow, + enum flow_offload_tuple_dir tdir, + struct nf_flow_rule *flow_rule) +{ + struct flow_action *action = &flow_rule->rule->action; + int num_entries = action->num_entries; + struct nf_conn *ct = flow->ct; + enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; + int i, err; + + switch (tdir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + dir = IP_CT_DIR_ORIGINAL; + ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? + IP_CT_ESTABLISHED : IP_CT_NEW; + if (ctinfo == IP_CT_ESTABLISHED) + set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); + break; + case FLOW_OFFLOAD_DIR_REPLY: + dir = IP_CT_DIR_REPLY; + ctinfo = IP_CT_ESTABLISHED_REPLY; + break; + default: + return -EOPNOTSUPP; + } + + err = tcf_ct_flow_table_add_action_nat(net, ct, dir, action); + if (err) + goto err_nat; + + tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action); + return 0; + +err_nat: + /* Clear filled actions */ + for (i = num_entries; i < action->num_entries; i++) + memset(&action->entries[i], 0, sizeof(action->entries[i])); + action->num_entries = num_entries; + + return err; +} + +static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_get(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_get_ref(ct_ft); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_put(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_put(ct_ft); +} + +static struct nf_flowtable_type flowtable_ct = { + .gc = tcf_ct_flow_is_outdated, + .action = tcf_ct_flow_table_fill_actions, + .get = tcf_ct_nf_get, + .put = tcf_ct_nf_put, + .owner = THIS_MODULE, +}; + +static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) +{ + struct zones_ht_key key = { .net = net, .zone = params->zone }; + struct tcf_ct_flow_table *ct_ft; + int err = -ENOMEM; + + mutex_lock(&zones_mutex); + ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); + if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) + goto out_unlock; + + ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL); + if (!ct_ft) + goto err_alloc; + refcount_set(&ct_ft->ref, 1); + + ct_ft->key = key; + err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params); + if (err) + goto err_insert; + + ct_ft->nf_ft.type = &flowtable_ct; + ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD | + NF_FLOWTABLE_COUNTER; + err = nf_flow_table_init(&ct_ft->nf_ft); + if (err) + goto err_init; + write_pnet(&ct_ft->nf_ft.net, net); + + __module_get(THIS_MODULE); +out_unlock: + params->ct_ft = ct_ft; + params->nf_ft = &ct_ft->nf_ft; + mutex_unlock(&zones_mutex); + + return 0; + +err_init: + rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); +err_insert: + kfree(ct_ft); +err_alloc: + mutex_unlock(&zones_mutex); + return err; +} + +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) +{ + refcount_inc(&ct_ft->ref); +} + +static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) +{ + struct tcf_ct_flow_table *ct_ft; + struct flow_block *block; + + ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, + rwork); + nf_flow_table_free(&ct_ft->nf_ft); + + block = &ct_ft->nf_ft.flow_block; + down_write(&ct_ft->nf_ft.flow_block_lock); + WARN_ON(!list_empty(&block->cb_list)); + up_write(&ct_ft->nf_ft.flow_block_lock); + kfree(ct_ft); + + module_put(THIS_MODULE); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) +{ + if (refcount_dec_and_test(&ct_ft->ref)) { + rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); + INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); + queue_rcu_work(act_ct_wq, &ct_ft->rwork); + } +} + +static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, + struct nf_conn_act_ct_ext *act_ct_ext, u8 dir) +{ + entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC; + entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; +} + +static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry) +{ + struct nf_conn_act_ct_ext *act_ct_ext; + + act_ct_ext = nf_conn_act_ct_ext_find(entry->ct); + if (act_ct_ext) { + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); + } +} + +static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, + struct nf_conn *ct, + bool tcp, bool bidirectional) +{ + struct nf_conn_act_ct_ext *act_ct_ext; + struct flow_offload *entry; + int err; + + if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) + return; + + entry = flow_offload_alloc(ct); + if (!entry) { + WARN_ON_ONCE(1); + goto err_alloc; + } + + if (tcp) { + ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; + ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; + } + if (bidirectional) + __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags); + + act_ct_ext = nf_conn_act_ct_ext_find(ct); + if (act_ct_ext) { + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); + } + + err = flow_offload_add(&ct_ft->nf_ft, entry); + if (err) + goto err_add; + + return; + +err_add: + flow_offload_free(entry); +err_alloc: + clear_bit(IPS_OFFLOAD_BIT, &ct->status); +} + +static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + bool tcp = false, bidirectional = true; + + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) + return; + + tcp = true; + break; + case IPPROTO_UDP: + if (!nf_ct_is_confirmed(ct)) + return; + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) + bidirectional = false; + break; +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: { + struct nf_conntrack_tuple *tuple; + + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->status & IPS_NAT_MASK) + return; + + tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + /* No support for GRE v1 */ + if (tuple->src.u.gre.key || tuple->dst.u.gre.key) + return; + break; + } +#endif + default: + return; + } + + if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || + ct->status & IPS_SEQ_ADJUST) + return; + + tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional); +} + +static bool +tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb, + struct flow_offload_tuple *tuple, + struct tcphdr **tcph) +{ + struct flow_ports *ports; + unsigned int thoff; + struct iphdr *iph; + size_t hdrsize; + u8 ipproto; + + if (!pskb_network_may_pull(skb, sizeof(*iph))) + return false; + + iph = ip_hdr(skb); + thoff = iph->ihl * 4; + + if (ip_is_fragment(iph) || + unlikely(thoff != sizeof(struct iphdr))) + return false; + + ipproto = iph->protocol; + switch (ipproto) { + case IPPROTO_TCP: + hdrsize = sizeof(struct tcphdr); + break; + case IPPROTO_UDP: + hdrsize = sizeof(*ports); + break; +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: + hdrsize = sizeof(struct gre_base_hdr); + break; +#endif + default: + return false; + } + + if (iph->ttl <= 1) + return false; + + if (!pskb_network_may_pull(skb, thoff + hdrsize)) + return false; + + switch (ipproto) { + case IPPROTO_TCP: + *tcph = (void *)(skb_network_header(skb) + thoff); + fallthrough; + case IPPROTO_UDP: + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + break; + case IPPROTO_GRE: { + struct gre_base_hdr *greh; + + greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff); + if ((greh->flags & GRE_VERSION) != GRE_VERSION_0) + return false; + break; + } + } + + iph = ip_hdr(skb); + + tuple->src_v4.s_addr = iph->saddr; + tuple->dst_v4.s_addr = iph->daddr; + tuple->l3proto = AF_INET; + tuple->l4proto = ipproto; + + return true; +} + +static bool +tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb, + struct flow_offload_tuple *tuple, + struct tcphdr **tcph) +{ + struct flow_ports *ports; + struct ipv6hdr *ip6h; + unsigned int thoff; + size_t hdrsize; + u8 nexthdr; + + if (!pskb_network_may_pull(skb, sizeof(*ip6h))) + return false; + + ip6h = ipv6_hdr(skb); + thoff = sizeof(*ip6h); + + nexthdr = ip6h->nexthdr; + switch (nexthdr) { + case IPPROTO_TCP: + hdrsize = sizeof(struct tcphdr); + break; + case IPPROTO_UDP: + hdrsize = sizeof(*ports); + break; +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: + hdrsize = sizeof(struct gre_base_hdr); + break; +#endif + default: + return false; + } + + if (ip6h->hop_limit <= 1) + return false; + + if (!pskb_network_may_pull(skb, thoff + hdrsize)) + return false; + + switch (nexthdr) { + case IPPROTO_TCP: + *tcph = (void *)(skb_network_header(skb) + thoff); + fallthrough; + case IPPROTO_UDP: + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + break; + case IPPROTO_GRE: { + struct gre_base_hdr *greh; + + greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff); + if ((greh->flags & GRE_VERSION) != GRE_VERSION_0) + return false; + break; + } + } + + ip6h = ipv6_hdr(skb); + + tuple->src_v6 = ip6h->saddr; + tuple->dst_v6 = ip6h->daddr; + tuple->l3proto = AF_INET6; + tuple->l4proto = nexthdr; + + return true; +} + +static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, + struct sk_buff *skb, + u8 family) +{ + struct nf_flowtable *nf_ft = &p->ct_ft->nf_ft; + struct flow_offload_tuple_rhash *tuplehash; + struct flow_offload_tuple tuple = {}; + enum ip_conntrack_info ctinfo; + struct tcphdr *tcph = NULL; + bool force_refresh = false; + struct flow_offload *flow; + struct nf_conn *ct; + u8 dir; + + switch (family) { + case NFPROTO_IPV4: + if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph)) + return false; + break; + case NFPROTO_IPV6: + if (!tcf_ct_flow_table_fill_tuple_ipv6(skb, &tuple, &tcph)) + return false; + break; + default: + return false; + } + + tuplehash = flow_offload_lookup(nf_ft, &tuple); + if (!tuplehash) + return false; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + ct = flow->ct; + + if (dir == FLOW_OFFLOAD_DIR_REPLY && + !test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) { + /* Only offload reply direction after connection became + * assured. + */ + if (test_bit(IPS_ASSURED_BIT, &ct->status)) + set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); + else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags)) + /* If flow_table flow has already been updated to the + * established state, then don't refresh. + */ + return false; + force_refresh = true; + } + + if (tcph && (unlikely(tcph->fin || tcph->rst))) { + flow_offload_teardown(flow); + return false; + } + + if (dir == FLOW_OFFLOAD_DIR_ORIGINAL) + ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? + IP_CT_ESTABLISHED : IP_CT_NEW; + else + ctinfo = IP_CT_ESTABLISHED_REPLY; + + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); + tcf_ct_flow_ct_ext_ifidx_update(flow); + flow_offload_refresh(nf_ft, flow, force_refresh); + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) { + /* Process this flow in SW to allow promoting to ASSURED */ + return false; + } + + nf_conntrack_get(&ct->ct_general); + nf_ct_set(skb, ct, ctinfo); + if (nf_ft->flags & NF_FLOWTABLE_COUNTER) + nf_ct_acct_update(ct, dir, skb->len); + + return true; +} + +static int tcf_ct_flow_tables_init(void) +{ + return rhashtable_init(&zones_ht, &zones_params); +} + +static void tcf_ct_flow_tables_uninit(void) +{ + rhashtable_destroy(&zones_ht); +} + +static struct tc_action_ops act_ct_ops; + +struct tc_ct_action_net { + struct tc_action_net tn; /* Must be first */ +}; + +/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ +static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, + struct tcf_ct_params *p) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return false; + if (!net_eq(net, read_pnet(&ct->ct_net))) + goto drop_ct; + if (nf_ct_zone(ct)->id != p->zone) + goto drop_ct; + if (p->helper) { + struct nf_conn_help *help; + + help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + if (help && rcu_access_pointer(help->helper) != p->helper) + goto drop_ct; + } + + /* Force conntrack entry direction. */ + if ((p->ct_action & TCA_CT_ACT_FORCE) && + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { + if (nf_ct_is_confirmed(ct)) + nf_ct_kill(ct); + + goto drop_ct; + } + + return true; + +drop_ct: + nf_ct_put(ct); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + + return false; +} + +static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) +{ + u8 family = NFPROTO_UNSPEC; + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + family = NFPROTO_IPV4; + break; + case htons(ETH_P_IPV6): + family = NFPROTO_IPV6; + break; + default: + break; + } + + return family; +} + +static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag) +{ + unsigned int len; + + len = skb_network_offset(skb) + sizeof(struct iphdr); + if (unlikely(skb->len < len)) + return -EINVAL; + if (unlikely(!pskb_may_pull(skb, len))) + return -ENOMEM; + + *frag = ip_is_fragment(ip_hdr(skb)); + return 0; +} + +static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag) +{ + unsigned int flags = 0, len, payload_ofs = 0; + unsigned short frag_off; + int nexthdr; + + len = skb_network_offset(skb) + sizeof(struct ipv6hdr); + if (unlikely(skb->len < len)) + return -EINVAL; + if (unlikely(!pskb_may_pull(skb, len))) + return -ENOMEM; + + nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); + if (unlikely(nexthdr < 0)) + return -EPROTO; + + *frag = flags & IP6_FH_F_FRAG; + return 0; +} + +static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, + u8 family, u16 zone, bool *defrag) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + int err = 0; + bool frag; + u8 proto; + u16 mru; + + /* Previously seen (loopback)? Ignore. */ + ct = nf_ct_get(skb, &ctinfo); + if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED) + return 0; + + if (family == NFPROTO_IPV4) + err = tcf_ct_ipv4_is_fragment(skb, &frag); + else + err = tcf_ct_ipv6_is_fragment(skb, &frag); + if (err || !frag) + return err; + + err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru); + if (err) + return err; + + *defrag = true; + tc_skb_cb(skb)->mru = mru; + + return 0; +} + +static void tcf_ct_params_free(struct tcf_ct_params *params) +{ + if (params->helper) { +#if IS_ENABLED(CONFIG_NF_NAT) + if (params->ct_action & TCA_CT_ACT_NAT) + nf_nat_helper_put(params->helper); +#endif + nf_conntrack_helper_put(params->helper); + } + if (params->ct_ft) + tcf_ct_flow_table_put(params->ct_ft); + if (params->tmpl) { + if (params->put_labels) + nf_connlabels_put(nf_ct_net(params->tmpl)); + + nf_ct_put(params->tmpl); + } + + kfree(params); +} + +static void tcf_ct_params_free_rcu(struct rcu_head *head) +{ + struct tcf_ct_params *params; + + params = container_of(head, struct tcf_ct_params, rcu); + tcf_ct_params_free(params); +} + +static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) + u32 new_mark; + + if (!mask) + return; + + new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); + if (nf_ct_is_confirmed(ct)) + nf_conntrack_event_cache(IPCT_MARK, ct); + } +#endif +} + +static void tcf_ct_act_set_labels(struct nf_conn *ct, + u32 *labels, + u32 *labels_m) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) + size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); + + if (!memchr_inv(labels_m, 0, labels_sz)) + return; + + nf_connlabels_replace(ct, labels, labels_m, 4); +#endif +} + +static int tcf_ct_act_nat(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + int ct_action, + struct nf_nat_range2 *range, + bool commit) +{ +#if IS_ENABLED(CONFIG_NF_NAT) + int err, action = 0; + + if (!(ct_action & TCA_CT_ACT_NAT)) + return NF_ACCEPT; + if (ct_action & TCA_CT_ACT_NAT_SRC) + action |= BIT(NF_NAT_MANIP_SRC); + if (ct_action & TCA_CT_ACT_NAT_DST) + action |= BIT(NF_NAT_MANIP_DST); + + err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit); + if (err != NF_ACCEPT) + return err & NF_VERDICT_MASK; + + if (action & BIT(NF_NAT_MANIP_SRC)) + qdisc_skb_cb(skb)->post_ct_snat = 1; + if (action & BIT(NF_NAT_MANIP_DST)) + qdisc_skb_cb(skb)->post_ct_dnat = 1; + + return err; +#else + return NF_ACCEPT; +#endif +} + +TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct net *net = dev_net(skb->dev); + enum ip_conntrack_info ctinfo; + struct tcf_ct *c = to_ct(a); + struct nf_conn *tmpl = NULL; + struct nf_hook_state state; + bool cached, commit, clear; + int nh_ofs, err, retval; + struct tcf_ct_params *p; + bool add_helper = false; + bool skip_add = false; + bool defrag = false; + struct nf_conn *ct; + u8 family; + + p = rcu_dereference_bh(c->params); + + retval = p->action; + commit = p->ct_action & TCA_CT_ACT_COMMIT; + clear = p->ct_action & TCA_CT_ACT_CLEAR; + tmpl = p->tmpl; + + tcf_lastuse_update(&c->tcf_tm); + tcf_action_update_bstats(&c->common, skb); + + if (clear) { + qdisc_skb_cb(skb)->post_ct = false; + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + nf_ct_put(ct); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + } + + goto out_clear; + } + + family = tcf_ct_skb_nf_family(skb); + if (family == NFPROTO_UNSPEC) + goto drop; + + /* The conntrack module expects to be working at L3. + * We also try to pull the IPv4/6 header to linear area + */ + nh_ofs = skb_network_offset(skb); + skb_pull_rcsum(skb, nh_ofs); + err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); + if (err) + goto out_frag; + + err = nf_ct_skb_network_trim(skb, family); + if (err) + goto drop; + + /* If we are recirculating packets to match on ct fields and + * committing with a separate ct action, then we don't need to + * actually run the packet through conntrack twice unless it's for a + * different zone. + */ + cached = tcf_ct_skb_nfct_cached(net, skb, p); + if (!cached) { + if (tcf_ct_flow_table_lookup(p, skb, family)) { + skip_add = true; + goto do_nat; + } + + /* Associate skb with specified zone. */ + if (tmpl) { + nf_conntrack_put(skb_nfct(skb)); + nf_conntrack_get(&tmpl->ct_general); + nf_ct_set(skb, tmpl, IP_CT_NEW); + } + + state.hook = NF_INET_PRE_ROUTING; + state.net = net; + state.pf = family; + err = nf_conntrack_in(skb, &state); + if (err != NF_ACCEPT) + goto nf_error; + } + +do_nat: + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + goto out_push; + nf_ct_deliver_cached_events(ct); + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); + + err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit); + if (err != NF_ACCEPT) + goto nf_error; + + if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { + err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); + if (err) + goto drop; + add_helper = true; + if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) { + if (!nfct_seqadj_ext_add(ct)) + goto drop; + } + } + + if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { + err = nf_ct_helper(skb, ct, ctinfo, family); + if (err != NF_ACCEPT) + goto nf_error; + } + + if (commit) { + tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); + tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); + + if (!nf_ct_is_confirmed(ct)) + nf_conn_act_ct_ext_add(skb, ct, ctinfo); + + /* This will take care of sending queued events + * even if the connection is already confirmed. + */ + err = nf_conntrack_confirm(skb); + if (err != NF_ACCEPT) + goto nf_error; + + /* The ct may be dropped if a clash has been resolved, + * so it's necessary to retrieve it from skb again to + * prevent UAF. + */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + skip_add = true; + } + + if (!skip_add) + tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo); + +out_push: + skb_push_rcsum(skb, nh_ofs); + + qdisc_skb_cb(skb)->post_ct = true; + tc_skb_cb(skb)->zone = p->zone; +out_clear: + if (defrag) + qdisc_skb_cb(skb)->pkt_len = skb->len; + return retval; + +out_frag: + if (err != -EINPROGRESS) + tcf_action_inc_drop_qstats(&c->common); + return TC_ACT_CONSUMED; + +drop: + tcf_action_inc_drop_qstats(&c->common); + return TC_ACT_SHOT; + +nf_error: + /* some verdicts store extra data in upper bits, such + * as errno or queue number. + */ + switch (err & NF_VERDICT_MASK) { + case NF_DROP: + goto drop; + case NF_STOLEN: + tcf_action_inc_drop_qstats(&c->common); + return TC_ACT_CONSUMED; + default: + DEBUG_NET_WARN_ON_ONCE(1); + goto drop; + } +} + +static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { + [TCA_CT_ACTION] = { .type = NLA_U16 }, + [TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)), + [TCA_CT_ZONE] = { .type = NLA_U16 }, + [TCA_CT_MARK] = { .type = NLA_U32 }, + [TCA_CT_MARK_MASK] = { .type = NLA_U32 }, + [TCA_CT_LABELS] = { .type = NLA_BINARY, + .len = 128 / BITS_PER_BYTE }, + [TCA_CT_LABELS_MASK] = { .type = NLA_BINARY, + .len = 128 / BITS_PER_BYTE }, + [TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 }, + [TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 }, + [TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, + [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, + [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN }, + [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 }, + [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 }, +}; + +static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, + struct tc_ct *parm, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct nf_nat_range2 *range; + + if (!(p->ct_action & TCA_CT_ACT_NAT)) + return 0; + + if (!IS_ENABLED(CONFIG_NF_NAT)) { + NL_SET_ERR_MSG_MOD(extack, "Netfilter nat isn't enabled in kernel"); + return -EOPNOTSUPP; + } + + if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) + return 0; + + if ((p->ct_action & TCA_CT_ACT_NAT_SRC) && + (p->ct_action & TCA_CT_ACT_NAT_DST)) { + NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time"); + return -EOPNOTSUPP; + } + + range = &p->range; + if (tb[TCA_CT_NAT_IPV4_MIN]) { + struct nlattr *max_attr = tb[TCA_CT_NAT_IPV4_MAX]; + + p->ipv4_range = true; + range->flags |= NF_NAT_RANGE_MAP_IPS; + range->min_addr.ip = + nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]); + + range->max_addr.ip = + nla_get_in_addr_default(max_attr, range->min_addr.ip); + } else if (tb[TCA_CT_NAT_IPV6_MIN]) { + struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX]; + + p->ipv4_range = false; + range->flags |= NF_NAT_RANGE_MAP_IPS; + range->min_addr.in6 = + nla_get_in6_addr(tb[TCA_CT_NAT_IPV6_MIN]); + + range->max_addr.in6 = max_attr ? + nla_get_in6_addr(max_attr) : + range->min_addr.in6; + } + + if (tb[TCA_CT_NAT_PORT_MIN]) { + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + range->min_proto.all = nla_get_be16(tb[TCA_CT_NAT_PORT_MIN]); + + range->max_proto.all = tb[TCA_CT_NAT_PORT_MAX] ? + nla_get_be16(tb[TCA_CT_NAT_PORT_MAX]) : + range->min_proto.all; + } + + return 0; +} + +static void tcf_ct_set_key_val(struct nlattr **tb, + void *val, int val_type, + void *mask, int mask_type, + int len) +{ + if (!tb[val_type]) + return; + nla_memcpy(val, tb[val_type], len); + + if (!mask) + return; + + if (mask_type == TCA_CT_UNSPEC || !tb[mask_type]) + memset(mask, 0xff, len); + else + nla_memcpy(mask, tb[mask_type], len); +} + +static int tcf_ct_fill_params(struct net *net, + struct tcf_ct_params *p, + struct tc_ct *parm, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct nf_conntrack_zone zone; + int err, family, proto, len; + bool put_labels = false; + struct nf_conn *tmpl; + char *name; + + p->zone = NF_CT_DEFAULT_ZONE_ID; + + tcf_ct_set_key_val(tb, + &p->ct_action, TCA_CT_ACTION, + NULL, TCA_CT_UNSPEC, + sizeof(p->ct_action)); + + if (p->ct_action & TCA_CT_ACT_CLEAR) + return 0; + + err = tcf_ct_fill_params_nat(p, parm, tb, extack); + if (err) + return err; + + if (tb[TCA_CT_MARK]) { + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) { + NL_SET_ERR_MSG_MOD(extack, "Conntrack mark isn't enabled."); + return -EOPNOTSUPP; + } + tcf_ct_set_key_val(tb, + &p->mark, TCA_CT_MARK, + &p->mark_mask, TCA_CT_MARK_MASK, + sizeof(p->mark)); + } + + if (tb[TCA_CT_LABELS]) { + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; + + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) { + NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled."); + return -EOPNOTSUPP; + } + + if (nf_connlabels_get(net, n_bits - 1)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length"); + return -EOPNOTSUPP; + } else { + put_labels = true; + } + + tcf_ct_set_key_val(tb, + p->labels, TCA_CT_LABELS, + p->labels_mask, TCA_CT_LABELS_MASK, + sizeof(p->labels)); + } + + if (tb[TCA_CT_ZONE]) { + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) { + NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled."); + return -EOPNOTSUPP; + } + + tcf_ct_set_key_val(tb, + &p->zone, TCA_CT_ZONE, + NULL, TCA_CT_UNSPEC, + sizeof(p->zone)); + } + + nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0); + tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL); + if (!tmpl) { + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template"); + return -ENOMEM; + } + p->tmpl = tmpl; + if (tb[TCA_CT_HELPER_NAME]) { + name = nla_data(tb[TCA_CT_HELPER_NAME]); + len = nla_len(tb[TCA_CT_HELPER_NAME]); + if (len > 16 || name[len - 1] != '\0') { + NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name."); + err = -EINVAL; + goto err; + } + family = nla_get_u8_default(tb[TCA_CT_HELPER_FAMILY], AF_INET); + proto = nla_get_u8_default(tb[TCA_CT_HELPER_PROTO], + IPPROTO_TCP); + err = nf_ct_add_helper(tmpl, name, family, proto, + p->ct_action & TCA_CT_ACT_NAT, &p->helper); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to add helper"); + goto err; + } + } + + p->put_labels = put_labels; + + if (p->ct_action & TCA_CT_ACT_COMMIT) + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); + return 0; +err: + if (put_labels) + nf_connlabels_put(net); + + nf_ct_put(p->tmpl); + p->tmpl = NULL; + return err; +} + +static int tcf_ct_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, act_ct_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct tcf_ct_params *params = NULL; + struct nlattr *tb[TCA_CT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; + struct tc_ct *parm; + struct tcf_ct *c; + int err, res = 0; + u32 index; + + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_CT_PARMS]) { + NL_SET_ERR_MSG_MOD(extack, "Missing required ct parameters"); + return -EINVAL; + } + parm = nla_data(tb[TCA_CT_PARMS]); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + + if (!err) { + err = tcf_idr_create_from_flags(tn, index, est, a, + &act_ct_ops, bind, flags); + if (err) { + tcf_idr_cleanup(tn, index); + return err; + } + res = ACT_P_CREATED; + } else { + if (bind) + return ACT_P_BOUND; + + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto cleanup; + + c = to_ct(*a); + + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (unlikely(!params)) { + err = -ENOMEM; + goto cleanup; + } + + err = tcf_ct_fill_params(net, params, parm, tb, extack); + if (err) + goto cleanup; + + err = tcf_ct_flow_table_get(net, params); + if (err) + goto cleanup; + + params->action = parm->action; + spin_lock_bh(&c->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + params = rcu_replace_pointer(c->params, params, + lockdep_is_held(&c->tcf_lock)); + spin_unlock_bh(&c->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (params) + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); + + return res; + +cleanup: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (params) + tcf_ct_params_free(params); + tcf_idr_release(*a, bind); + return err; +} + +static void tcf_ct_cleanup(struct tc_action *a) +{ + struct tcf_ct_params *params; + struct tcf_ct *c = to_ct(a); + + params = rcu_dereference_protected(c->params, 1); + if (params) + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); +} + +static int tcf_ct_dump_key_val(struct sk_buff *skb, + const void *val, int val_type, + const void *mask, int mask_type, + int len) +{ + int err; + + if (mask && !memchr_inv(mask, 0, len)) + return 0; + + err = nla_put(skb, val_type, len, val); + if (err) + return err; + + if (mask_type != TCA_CT_UNSPEC) { + err = nla_put(skb, mask_type, len, mask); + if (err) + return err; + } + + return 0; +} + +static int tcf_ct_dump_nat(struct sk_buff *skb, const struct tcf_ct_params *p) +{ + const struct nf_nat_range2 *range = &p->range; + + if (!(p->ct_action & TCA_CT_ACT_NAT)) + return 0; + + if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) + return 0; + + if (range->flags & NF_NAT_RANGE_MAP_IPS) { + if (p->ipv4_range) { + if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MIN, + range->min_addr.ip)) + return -1; + if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MAX, + range->max_addr.ip)) + return -1; + } else { + if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MIN, + &range->min_addr.in6)) + return -1; + if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MAX, + &range->max_addr.in6)) + return -1; + } + } + + if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { + if (nla_put_be16(skb, TCA_CT_NAT_PORT_MIN, + range->min_proto.all)) + return -1; + if (nla_put_be16(skb, TCA_CT_NAT_PORT_MAX, + range->max_proto.all)) + return -1; + } + + return 0; +} + +static int tcf_ct_dump_helper(struct sk_buff *skb, + const struct nf_conntrack_helper *helper) +{ + if (!helper) + return 0; + + if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) || + nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) || + nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum)) + return -1; + + return 0; +} + +static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + const struct tcf_ct *c = to_ct(a); + const struct tcf_ct_params *p; + struct tc_ct opt = { + .index = c->tcf_index, + .refcnt = refcount_read(&c->tcf_refcnt) - ref, + .bindcnt = atomic_read(&c->tcf_bindcnt) - bind, + }; + struct tcf_t t; + + rcu_read_lock(); + p = rcu_dereference(c->params); + opt.action = p->action; + + if (tcf_ct_dump_key_val(skb, + &p->ct_action, TCA_CT_ACTION, + NULL, TCA_CT_UNSPEC, + sizeof(p->ct_action))) + goto nla_put_failure; + + if (p->ct_action & TCA_CT_ACT_CLEAR) + goto skip_dump; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + tcf_ct_dump_key_val(skb, + &p->mark, TCA_CT_MARK, + &p->mark_mask, TCA_CT_MARK_MASK, + sizeof(p->mark))) + goto nla_put_failure; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + tcf_ct_dump_key_val(skb, + p->labels, TCA_CT_LABELS, + p->labels_mask, TCA_CT_LABELS_MASK, + sizeof(p->labels))) + goto nla_put_failure; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && + tcf_ct_dump_key_val(skb, + &p->zone, TCA_CT_ZONE, + NULL, TCA_CT_UNSPEC, + sizeof(p->zone))) + goto nla_put_failure; + + if (tcf_ct_dump_nat(skb, p)) + goto nla_put_failure; + + if (tcf_ct_dump_helper(skb, p->helper)) + goto nla_put_failure; + +skip_dump: + if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + tcf_tm_dump(&t, &c->tcf_tm); + if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD)) + goto nla_put_failure; + rcu_read_unlock(); + + return skb->len; +nla_put_failure: + rcu_read_unlock(); + nlmsg_trim(skb, b); + return -1; +} + +static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) +{ + struct tcf_ct *c = to_ct(a); + + tcf_action_update_stats(a, bytes, packets, drops, hw); + c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse); +} + +static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (tcf_ct_helper(act)) + return -EOPNOTSUPP; + + entry->id = FLOW_ACTION_CT; + entry->ct.action = tcf_ct_action(act); + entry->ct.zone = tcf_ct_zone(act); + entry->ct.flow_table = tcf_ct_ft(act); + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_CT; + } + + return 0; +} + +static struct tc_action_ops act_ct_ops = { + .kind = "ct", + .id = TCA_ID_CT, + .owner = THIS_MODULE, + .act = tcf_ct_act, + .dump = tcf_ct_dump, + .init = tcf_ct_init, + .cleanup = tcf_ct_cleanup, + .stats_update = tcf_stats_update, + .offload_act_setup = tcf_ct_offload_act_setup, + .size = sizeof(struct tcf_ct), +}; +MODULE_ALIAS_NET_ACT("ct"); + +static __net_init int ct_init_net(struct net *net) +{ + struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); + + return tc_action_net_init(net, &tn->tn, &act_ct_ops); +} + +static void __net_exit ct_exit_net(struct list_head *net_list) +{ + tc_action_net_exit(net_list, act_ct_ops.net_id); +} + +static struct pernet_operations ct_net_ops = { + .init = ct_init_net, + .exit_batch = ct_exit_net, + .id = &act_ct_ops.net_id, + .size = sizeof(struct tc_ct_action_net), +}; + +static int __init ct_init_module(void) +{ + int err; + + act_ct_wq = alloc_ordered_workqueue("act_ct_workqueue", 0); + if (!act_ct_wq) + return -ENOMEM; + + err = tcf_ct_flow_tables_init(); + if (err) + goto err_tbl_init; + + err = tcf_register_action(&act_ct_ops, &ct_net_ops); + if (err) + goto err_register; + + static_branch_inc(&tcf_frag_xmit_count); + + return 0; + +err_register: + tcf_ct_flow_tables_uninit(); +err_tbl_init: + destroy_workqueue(act_ct_wq); + return err; +} + +static void __exit ct_cleanup_module(void) +{ + static_branch_dec(&tcf_frag_xmit_count); + tcf_unregister_action(&act_ct_ops, &ct_net_ops); + tcf_ct_flow_tables_uninit(); + destroy_workqueue(act_ct_wq); +} + +module_init(ct_init_module); +module_exit(ct_cleanup_module); +MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>"); +MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>"); +MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>"); +MODULE_DESCRIPTION("Connection tracking action"); +MODULE_LICENSE("GPL v2"); diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c new file mode 100644 index 000000000000..71efe04d00b5 --- /dev/null +++ b/net/sched/act_ctinfo.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* net/sched/act_ctinfo.c netfilter ctinfo connmark actions + * + * Copyright (c) 2019 Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/pkt_cls.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/act_api.h> +#include <net/pkt_cls.h> +#include <uapi/linux/tc_act/tc_ctinfo.h> +#include <net/tc_act/tc_ctinfo.h> +#include <net/tc_wrapper.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_zones.h> + +static struct tc_action_ops act_ctinfo_ops; + +static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, + struct tcf_ctinfo_params *cp, + struct sk_buff *skb, int wlen, int proto) +{ + u8 dscp, newdscp; + + newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + ~INET_ECN_MASK; + + switch (proto) { + case NFPROTO_IPV4: + dscp = ipv4_get_dsfield(ip_hdr(skb)) & ~INET_ECN_MASK; + if (dscp != newdscp) { + if (likely(!skb_try_make_writable(skb, wlen))) { + ipv4_change_dsfield(ip_hdr(skb), + INET_ECN_MASK, + newdscp); + atomic64_inc(&ca->stats_dscp_set); + } else { + atomic64_inc(&ca->stats_dscp_error); + } + } + break; + case NFPROTO_IPV6: + dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK; + if (dscp != newdscp) { + if (likely(!skb_try_make_writable(skb, wlen))) { + ipv6_change_dsfield(ipv6_hdr(skb), + INET_ECN_MASK, + newdscp); + atomic64_inc(&ca->stats_dscp_set); + } else { + atomic64_inc(&ca->stats_dscp_error); + } + } + break; + default: + break; + } +} + +static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, + struct tcf_ctinfo_params *cp, + struct sk_buff *skb) +{ + atomic64_inc(&ca->stats_cpmark_set); + skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; +} + +TC_INDIRECT_SCOPE int tcf_ctinfo_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) +{ + const struct nf_conntrack_tuple_hash *thash = NULL; + struct tcf_ctinfo *ca = to_ctinfo(a); + struct nf_conntrack_tuple tuple; + struct nf_conntrack_zone zone; + enum ip_conntrack_info ctinfo; + struct tcf_ctinfo_params *cp; + struct nf_conn *ct; + int proto, wlen; + + cp = rcu_dereference_bh(ca->params); + + tcf_lastuse_update(&ca->tcf_tm); + tcf_action_update_bstats(&ca->common, skb); + + wlen = skb_network_offset(skb); + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen)) + goto out; + + proto = NFPROTO_IPV4; + break; + case htons(ETH_P_IPV6): + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen)) + goto out; + + proto = NFPROTO_IPV6; + break; + default: + goto out; + } + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) { /* look harder, usually ingress */ + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), + proto, cp->net, &tuple)) + goto out; + zone.id = cp->zone; + zone.dir = NF_CT_DEFAULT_ZONE_DIR; + + thash = nf_conntrack_find_get(cp->net, &zone, &tuple); + if (!thash) + goto out; + + ct = nf_ct_tuplehash_to_ctrack(thash); + } + + if (cp->mode & CTINFO_MODE_DSCP) + if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) + tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); + + if (cp->mode & CTINFO_MODE_CPMARK) + tcf_ctinfo_cpmark_set(ct, ca, cp, skb); + + if (thash) + nf_ct_put(ct); +out: + return cp->action; +} + +static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { + [TCA_CTINFO_ACT] = + NLA_POLICY_EXACT_LEN(sizeof(struct tc_ctinfo)), + [TCA_CTINFO_ZONE] = { .type = NLA_U16 }, + [TCA_CTINFO_PARMS_DSCP_MASK] = { .type = NLA_U32 }, + [TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 }, + [TCA_CTINFO_PARMS_CPMARK_MASK] = { .type = NLA_U32 }, +}; + +static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, act_ctinfo_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; + u32 dscpmask = 0, dscpstatemask, index; + struct nlattr *tb[TCA_CTINFO_MAX + 1]; + struct tcf_ctinfo_params *cp_new; + struct tcf_chain *goto_ch = NULL; + struct tc_ctinfo *actparm; + struct tcf_ctinfo *ci; + u8 dscpmaskshift; + int ret = 0, err; + + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "ctinfo requires attributes to be passed"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_CTINFO_MAX, nla, ctinfo_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_CTINFO_ACT]) { + NL_SET_ERR_MSG_MOD(extack, + "Missing required TCA_CTINFO_ACT attribute"); + return -EINVAL; + } + actparm = nla_data(tb[TCA_CTINFO_ACT]); + + /* do some basic validation here before dynamically allocating things */ + /* that we would otherwise have to clean up. */ + if (tb[TCA_CTINFO_PARMS_DSCP_MASK]) { + dscpmask = nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_MASK]); + /* need contiguous 6 bit mask */ + dscpmaskshift = dscpmask ? __ffs(dscpmask) : 0; + if ((~0 & (dscpmask >> dscpmaskshift)) != 0x3f) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_CTINFO_PARMS_DSCP_MASK], + "dscp mask must be 6 contiguous bits"); + return -EINVAL; + } + dscpstatemask = + nla_get_u32_default(tb[TCA_CTINFO_PARMS_DSCP_STATEMASK], + 0); + /* mask & statemask must not overlap */ + if (dscpmask & dscpstatemask) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_CTINFO_PARMS_DSCP_STATEMASK], + "dscp statemask must not overlap dscp mask"); + return -EINVAL; + } + } + + /* done the validation:now to the actual action allocation */ + index = actparm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (!err) { + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_ctinfo_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); + return ret; + } + ret = ACT_P_CREATED; + } else if (err > 0) { + if (bind) /* don't override defaults */ + return ACT_P_BOUND; + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + } else { + return err; + } + + err = tcf_action_check_ctrlact(actparm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + ci = to_ctinfo(*a); + + cp_new = kzalloc(sizeof(*cp_new), GFP_KERNEL); + if (unlikely(!cp_new)) { + err = -ENOMEM; + goto put_chain; + } + + cp_new->net = net; + cp_new->zone = nla_get_u16_default(tb[TCA_CTINFO_ZONE], 0); + if (dscpmask) { + cp_new->dscpmask = dscpmask; + cp_new->dscpmaskshift = dscpmaskshift; + cp_new->dscpstatemask = dscpstatemask; + cp_new->mode |= CTINFO_MODE_DSCP; + } + + if (tb[TCA_CTINFO_PARMS_CPMARK_MASK]) { + cp_new->cpmarkmask = + nla_get_u32(tb[TCA_CTINFO_PARMS_CPMARK_MASK]); + cp_new->mode |= CTINFO_MODE_CPMARK; + } + + cp_new->action = actparm->action; + + spin_lock_bh(&ci->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch); + cp_new = rcu_replace_pointer(ci->params, cp_new, + lockdep_is_held(&ci->tcf_lock)); + spin_unlock_bh(&ci->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (cp_new) + kfree_rcu(cp_new, rcu); + + return ret; + +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; +} + +static int tcf_ctinfo_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + const struct tcf_ctinfo *ci = to_ctinfo(a); + unsigned char *b = skb_tail_pointer(skb); + const struct tcf_ctinfo_params *cp; + struct tc_ctinfo opt = { + .index = ci->tcf_index, + .refcnt = refcount_read(&ci->tcf_refcnt) - ref, + .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, + }; + struct tcf_t t; + + rcu_read_lock(); + cp = rcu_dereference(ci->params); + + tcf_tm_dump(&t, &ci->tcf_tm); + if (nla_put_64bit(skb, TCA_CTINFO_TM, sizeof(t), &t, TCA_CTINFO_PAD)) + goto nla_put_failure; + + opt.action = cp->action; + if (nla_put(skb, TCA_CTINFO_ACT, sizeof(opt), &opt)) + goto nla_put_failure; + + if (nla_put_u16(skb, TCA_CTINFO_ZONE, cp->zone)) + goto nla_put_failure; + + if (cp->mode & CTINFO_MODE_DSCP) { + if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_MASK, + cp->dscpmask)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_STATEMASK, + cp->dscpstatemask)) + goto nla_put_failure; + } + + if (cp->mode & CTINFO_MODE_CPMARK) { + if (nla_put_u32(skb, TCA_CTINFO_PARMS_CPMARK_MASK, + cp->cpmarkmask)) + goto nla_put_failure; + } + + if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_SET, + atomic64_read(&ci->stats_dscp_set), + TCA_CTINFO_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_ERROR, + atomic64_read(&ci->stats_dscp_error), + TCA_CTINFO_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_CPMARK_SET, + atomic64_read(&ci->stats_cpmark_set), + TCA_CTINFO_PAD)) + goto nla_put_failure; + + rcu_read_unlock(); + return skb->len; + +nla_put_failure: + rcu_read_unlock(); + nlmsg_trim(skb, b); + return -1; +} + +static void tcf_ctinfo_cleanup(struct tc_action *a) +{ + struct tcf_ctinfo *ci = to_ctinfo(a); + struct tcf_ctinfo_params *cp; + + cp = rcu_dereference_protected(ci->params, 1); + if (cp) + kfree_rcu(cp, rcu); +} + +static struct tc_action_ops act_ctinfo_ops = { + .kind = "ctinfo", + .id = TCA_ID_CTINFO, + .owner = THIS_MODULE, + .act = tcf_ctinfo_act, + .dump = tcf_ctinfo_dump, + .init = tcf_ctinfo_init, + .cleanup= tcf_ctinfo_cleanup, + .size = sizeof(struct tcf_ctinfo), +}; +MODULE_ALIAS_NET_ACT("ctinfo"); + +static __net_init int ctinfo_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, act_ctinfo_ops.net_id); + + return tc_action_net_init(net, tn, &act_ctinfo_ops); +} + +static void __net_exit ctinfo_exit_net(struct list_head *net_list) +{ + tc_action_net_exit(net_list, act_ctinfo_ops.net_id); +} + +static struct pernet_operations ctinfo_net_ops = { + .init = ctinfo_init_net, + .exit_batch = ctinfo_exit_net, + .id = &act_ctinfo_ops.net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init ctinfo_init_module(void) +{ + return tcf_register_action(&act_ctinfo_ops, &ctinfo_net_ops); +} + +static void __exit ctinfo_cleanup_module(void) +{ + tcf_unregister_action(&act_ctinfo_ops, &ctinfo_net_ops); +} + +module_init(ctinfo_init_module); +module_exit(ctinfo_cleanup_module); +MODULE_AUTHOR("Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>"); +MODULE_DESCRIPTION("Connection tracking mark actions"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 99afe8b1f1fb..e949280eb800 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_gact.c Generic actions * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * copyright Jamal Hadi Salim (2002-4) - * */ #include <linux/types.h> @@ -20,19 +15,18 @@ #include <linux/init.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_gact.h> #include <net/tc_act/tc_gact.h> +#include <net/tc_wrapper.h> -#define GACT_TAB_MASK 15 - -static unsigned int gact_net_id; static struct tc_action_ops act_gact_ops; #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ - if (prandom_u32() % gact->tcfg_pval) + if (get_random_u32_below(gact->tcfg_pval)) return gact->tcf_action; return gact->tcfg_paction; } @@ -58,13 +52,17 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, gact_net_id); + struct tc_action_net *tn = net_generic(net, act_gact_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GACT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_gact *parm; struct tcf_gact *gact; int ret = 0; + u32 index; int err; #ifdef CONFIG_GACT_PROB struct tc_gact_p *p_parm = NULL; @@ -73,13 +71,15 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_GACT_MAX, nla, gact_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_GACT_MAX, nla, gact_policy, + NULL); if (err < 0) return err; if (tb[TCA_GACT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_GACT_PARMS]); + index = parm->index; #ifndef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB] != NULL) @@ -89,27 +89,41 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, p_parm = nla_data(tb[TCA_GACT_PROB]); if (p_parm->ptype >= MAX_RAND) return -EINVAL; + if (TC_ACT_EXT_CMP(p_parm->paction, TC_ACT_GOTO_CHAIN)) { + NL_SET_ERR_MSG(extack, + "goto chain not allowed on fallback"); + return -EINVAL; + } } #endif - if (!tcf_hash_check(tn, parm->index, a, bind)) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_gact_ops, bind, true); - if (ret) + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (!err) { + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_gact_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { + } else if (err > 0) { if (bind)/* dont override defaults */ - return 0; - tcf_hash_release(*a, bind); - if (!ovr) + return ACT_P_BOUND; + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); return -EEXIST; + } + } else { + return err; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; gact = to_gact(*a); - ASSERT_RTNL(); - gact->tcf_action = parm->action; + spin_lock_bh(&gact->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); #ifdef CONFIG_GACT_PROB if (p_parm) { gact->tcfg_paction = p_parm->paction; @@ -121,13 +135,20 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, gact->tcfg_ptype = p_parm->ptype; } #endif - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); + spin_unlock_bh(&gact->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + return ret; +release_idr: + tcf_idr_release(*a, bind); + return err; } -static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_gact_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_gact *gact = to_gact(a); int action = READ_ONCE(gact->tcf_action); @@ -140,28 +161,25 @@ static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, action = gact_rand[ptype](gact); } #endif - bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb); + tcf_action_update_bstats(&gact->common, skb); if (action == TC_ACT_SHOT) - qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats)); + tcf_action_inc_drop_qstats(&gact->common); tcf_lastuse_update(&gact->tcf_tm); return action; } -static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse) +static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_gact *gact = to_gact(a); int action = READ_ONCE(gact->tcf_action); struct tcf_t *tm = &gact->tcf_tm; - _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes, - packets); - if (action == TC_ACT_SHOT) - this_cpu_ptr(gact->common.cpu_qstats)->drops += packets; - - tm->lastuse = lastuse; + tcf_action_update_stats(a, bytes, packets, + action == TC_ACT_SHOT ? packets : drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, @@ -171,12 +189,13 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_gact *gact = to_gact(a); struct tc_gact opt = { .index = gact->tcf_index, - .refcnt = gact->tcf_refcnt - ref, - .bindcnt = gact->tcf_bindcnt - bind, - .action = gact->tcf_action, + .refcnt = refcount_read(&gact->tcf_refcnt) - ref, + .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind, }; struct tcf_t t; + spin_lock_bh(&gact->tcf_lock); + opt.action = gact->tcf_action; if (nla_put(skb, TCA_GACT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; #ifdef CONFIG_GACT_PROB @@ -194,60 +213,107 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD)) goto nla_put_failure; + spin_unlock_bh(&gact->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&gact->tcf_lock); nlmsg_trim(skb, b); return -1; } -static int tcf_gact_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static size_t tcf_gact_get_fill_size(const struct tc_action *act) { - struct tc_action_net *tn = net_generic(net, gact_net_id); + size_t sz = nla_total_size(sizeof(struct tc_gact)); /* TCA_GACT_PARMS */ - return tcf_generic_walker(tn, skb, cb, type, ops); +#ifdef CONFIG_GACT_PROB + if (to_gact(act)->tcfg_ptype) + /* TCA_GACT_PROB */ + sz += nla_total_size(sizeof(struct tc_gact_p)); +#endif + + return sz; } -static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_gact_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, gact_net_id); + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_gact_ok(act)) { + entry->id = FLOW_ACTION_ACCEPT; + } else if (is_tcf_gact_shot(act)) { + entry->id = FLOW_ACTION_DROP; + } else if (is_tcf_gact_trap(act)) { + entry->id = FLOW_ACTION_TRAP; + } else if (is_tcf_gact_goto_chain(act)) { + entry->id = FLOW_ACTION_GOTO; + entry->chain_index = tcf_gact_goto_chain_index(act); + } else if (is_tcf_gact_continue(act)) { + NL_SET_ERR_MSG_MOD(extack, "Offload of \"continue\" action is not supported"); + return -EOPNOTSUPP; + } else if (is_tcf_gact_reclassify(act)) { + NL_SET_ERR_MSG_MOD(extack, "Offload of \"reclassify\" action is not supported"); + return -EOPNOTSUPP; + } else if (is_tcf_gact_pipe(act)) { + NL_SET_ERR_MSG_MOD(extack, "Offload of \"pipe\" action is not supported"); + return -EOPNOTSUPP; + } else { + NL_SET_ERR_MSG_MOD(extack, "Unsupported generic action offload"); + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_gact_ok(act)) + fl_action->id = FLOW_ACTION_ACCEPT; + else if (is_tcf_gact_shot(act)) + fl_action->id = FLOW_ACTION_DROP; + else if (is_tcf_gact_trap(act)) + fl_action->id = FLOW_ACTION_TRAP; + else if (is_tcf_gact_goto_chain(act)) + fl_action->id = FLOW_ACTION_GOTO; + else + return -EOPNOTSUPP; + } - return tcf_hash_search(tn, a, index); + return 0; } static struct tc_action_ops act_gact_ops = { .kind = "gact", - .type = TCA_ACT_GACT, + .id = TCA_ID_GACT, .owner = THIS_MODULE, - .act = tcf_gact, + .act = tcf_gact_act, .stats_update = tcf_gact_stats_update, .dump = tcf_gact_dump, .init = tcf_gact_init, - .walk = tcf_gact_walker, - .lookup = tcf_gact_search, + .get_fill_size = tcf_gact_get_fill_size, + .offload_act_setup = tcf_gact_offload_act_setup, .size = sizeof(struct tcf_gact), }; +MODULE_ALIAS_NET_ACT("gact"); static __net_init int gact_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, gact_net_id); + struct tc_action_net *tn = net_generic(net, act_gact_ops.net_id); - return tc_action_net_init(tn, &act_gact_ops, GACT_TAB_MASK); + return tc_action_net_init(net, tn, &act_gact_ops); } -static void __net_exit gact_exit_net(struct net *net) +static void __net_exit gact_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, gact_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_gact_ops.net_id); } static struct pernet_operations gact_net_ops = { .init = gact_init_net, - .exit = gact_exit_net, - .id = &gact_net_id, + .exit_batch = gact_exit_net, + .id = &act_gact_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c new file mode 100644 index 000000000000..c1f75f272757 --- /dev/null +++ b/net/sched/act_gate.c @@ -0,0 +1,676 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright 2020 NXP */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <net/act_api.h> +#include <net/netlink.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gate.h> +#include <net/tc_wrapper.h> + +static struct tc_action_ops act_gate_ops; + +static ktime_t gate_get_time(struct tcf_gate *gact) +{ + ktime_t mono = ktime_get(); + + switch (gact->tk_offset) { + case TK_OFFS_MAX: + return mono; + default: + return ktime_mono_to_any(mono, gact->tk_offset); + } + + return KTIME_MAX; +} + +static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +{ + struct tcf_gate_params *param = &gact->param; + ktime_t now, base, cycle; + u64 n; + + base = ns_to_ktime(param->tcfg_basetime); + now = gate_get_time(gact); + + if (ktime_after(base, now)) { + *start = base; + return; + } + + cycle = param->tcfg_cycletime; + + n = div64_u64(ktime_sub_ns(now, base), cycle); + *start = ktime_add_ns(base, (n + 1) * cycle); +} + +static void gate_start_timer(struct tcf_gate *gact, ktime_t start) +{ + ktime_t expires; + + expires = hrtimer_get_expires(&gact->hitimer); + if (expires == 0) + expires = KTIME_MAX; + + start = min_t(ktime_t, start, expires); + + hrtimer_start(&gact->hitimer, start, HRTIMER_MODE_ABS_SOFT); +} + +static enum hrtimer_restart gate_timer_func(struct hrtimer *timer) +{ + struct tcf_gate *gact = container_of(timer, struct tcf_gate, + hitimer); + struct tcf_gate_params *p = &gact->param; + struct tcfg_gate_entry *next; + ktime_t close_time, now; + + spin_lock(&gact->tcf_lock); + + next = gact->next_entry; + + /* cycle start, clear pending bit, clear total octets */ + gact->current_gate_status = next->gate_state ? GATE_ACT_GATE_OPEN : 0; + gact->current_entry_octets = 0; + gact->current_max_octets = next->maxoctets; + + gact->current_close_time = ktime_add_ns(gact->current_close_time, + next->interval); + + close_time = gact->current_close_time; + + if (list_is_last(&next->list, &p->entries)) + next = list_first_entry(&p->entries, + struct tcfg_gate_entry, list); + else + next = list_next_entry(next, list); + + now = gate_get_time(gact); + + if (ktime_after(now, close_time)) { + ktime_t cycle, base; + u64 n; + + cycle = p->tcfg_cycletime; + base = ns_to_ktime(p->tcfg_basetime); + n = div64_u64(ktime_sub_ns(now, base), cycle); + close_time = ktime_add_ns(base, (n + 1) * cycle); + } + + gact->next_entry = next; + + hrtimer_set_expires(&gact->hitimer, close_time); + + spin_unlock(&gact->tcf_lock); + + return HRTIMER_RESTART; +} + +TC_INDIRECT_SCOPE int tcf_gate_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_gate *gact = to_gate(a); + int action = READ_ONCE(gact->tcf_action); + + tcf_lastuse_update(&gact->tcf_tm); + tcf_action_update_bstats(&gact->common, skb); + + spin_lock(&gact->tcf_lock); + if (unlikely(gact->current_gate_status & GATE_ACT_PENDING)) { + spin_unlock(&gact->tcf_lock); + return action; + } + + if (!(gact->current_gate_status & GATE_ACT_GATE_OPEN)) { + spin_unlock(&gact->tcf_lock); + goto drop; + } + + if (gact->current_max_octets >= 0) { + gact->current_entry_octets += qdisc_pkt_len(skb); + if (gact->current_entry_octets > gact->current_max_octets) { + spin_unlock(&gact->tcf_lock); + goto overlimit; + } + } + spin_unlock(&gact->tcf_lock); + + return action; + +overlimit: + tcf_action_inc_overlimit_qstats(&gact->common); +drop: + tcf_action_inc_drop_qstats(&gact->common); + return TC_ACT_SHOT; +} + +static const struct nla_policy entry_policy[TCA_GATE_ENTRY_MAX + 1] = { + [TCA_GATE_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_GATE_ENTRY_GATE] = { .type = NLA_FLAG }, + [TCA_GATE_ENTRY_INTERVAL] = { .type = NLA_U32 }, + [TCA_GATE_ENTRY_IPV] = { .type = NLA_S32 }, + [TCA_GATE_ENTRY_MAX_OCTETS] = { .type = NLA_S32 }, +}; + +static const struct nla_policy gate_policy[TCA_GATE_MAX + 1] = { + [TCA_GATE_PARMS] = + NLA_POLICY_EXACT_LEN(sizeof(struct tc_gate)), + [TCA_GATE_PRIORITY] = { .type = NLA_S32 }, + [TCA_GATE_ENTRY_LIST] = { .type = NLA_NESTED }, + [TCA_GATE_BASE_TIME] = { .type = NLA_U64 }, + [TCA_GATE_CYCLE_TIME] = { .type = NLA_U64 }, + [TCA_GATE_CYCLE_TIME_EXT] = { .type = NLA_U64 }, + [TCA_GATE_FLAGS] = { .type = NLA_U32 }, + [TCA_GATE_CLOCKID] = { .type = NLA_S32 }, +}; + +static int fill_gate_entry(struct nlattr **tb, struct tcfg_gate_entry *entry, + struct netlink_ext_ack *extack) +{ + u32 interval = 0; + + entry->gate_state = nla_get_flag(tb[TCA_GATE_ENTRY_GATE]); + + if (tb[TCA_GATE_ENTRY_INTERVAL]) + interval = nla_get_u32(tb[TCA_GATE_ENTRY_INTERVAL]); + + if (interval == 0) { + NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); + return -EINVAL; + } + + entry->interval = interval; + + entry->ipv = nla_get_s32_default(tb[TCA_GATE_ENTRY_IPV], -1); + + entry->maxoctets = nla_get_s32_default(tb[TCA_GATE_ENTRY_MAX_OCTETS], + -1); + + return 0; +} + +static int parse_gate_entry(struct nlattr *n, struct tcfg_gate_entry *entry, + int index, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_GATE_ENTRY_MAX + 1] = { }; + int err; + + err = nla_parse_nested(tb, TCA_GATE_ENTRY_MAX, n, entry_policy, extack); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + entry->index = index; + + return fill_gate_entry(tb, entry, extack); +} + +static void release_entry_list(struct list_head *entries) +{ + struct tcfg_gate_entry *entry, *e; + + list_for_each_entry_safe(entry, e, entries, list) { + list_del(&entry->list); + kfree(entry); + } +} + +static int parse_gate_list(struct nlattr *list_attr, + struct tcf_gate_params *sched, + struct netlink_ext_ack *extack) +{ + struct tcfg_gate_entry *entry; + struct nlattr *n; + int err, rem; + int i = 0; + + if (!list_attr) + return -EINVAL; + + nla_for_each_nested(n, list_attr, rem) { + if (nla_type(n) != TCA_GATE_ONE_ENTRY) { + NL_SET_ERR_MSG(extack, "Attribute isn't type 'entry'"); + continue; + } + + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + err = -ENOMEM; + goto release_list; + } + + err = parse_gate_entry(n, entry, i, extack); + if (err < 0) { + kfree(entry); + goto release_list; + } + + list_add_tail(&entry->list, &sched->entries); + i++; + } + + sched->num_entries = i; + + return i; + +release_list: + release_entry_list(&sched->entries); + + return err; +} + +static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, + enum tk_offsets tko, s32 clockid, + bool do_init) +{ + if (!do_init) { + if (basetime == gact->param.tcfg_basetime && + tko == gact->tk_offset && + clockid == gact->param.tcfg_clockid) + return; + + spin_unlock_bh(&gact->tcf_lock); + hrtimer_cancel(&gact->hitimer); + spin_lock_bh(&gact->tcf_lock); + } + gact->param.tcfg_basetime = basetime; + gact->param.tcfg_clockid = clockid; + gact->tk_offset = tko; + hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT); +} + +static int tcf_gate_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); + enum tk_offsets tk_offset = TK_OFFS_TAI; + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct nlattr *tb[TCA_GATE_MAX + 1]; + struct tcf_chain *goto_ch = NULL; + u64 cycletime = 0, basetime = 0; + struct tcf_gate_params *p; + s32 clockid = CLOCK_TAI; + struct tcf_gate *gact; + struct tc_gate *parm; + int ret = 0, err; + u32 gflags = 0; + s32 prio = -1; + ktime_t start; + u32 index; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_GATE_MAX, nla, gate_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_GATE_PARMS]) + return -EINVAL; + + if (tb[TCA_GATE_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); + switch (clockid) { + case CLOCK_REALTIME: + tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; + } + } + + parm = nla_data(tb[TCA_GATE_PARMS]); + index = parm->index; + + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + + if (err && bind) + return ACT_P_BOUND; + + if (!err) { + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_gate_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); + return ret; + } + + ret = ACT_P_CREATED; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + + if (tb[TCA_GATE_PRIORITY]) + prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); + + if (tb[TCA_GATE_BASE_TIME]) + basetime = nla_get_u64(tb[TCA_GATE_BASE_TIME]); + + if (tb[TCA_GATE_FLAGS]) + gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); + + gact = to_gate(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&gact->param.entries); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + spin_lock_bh(&gact->tcf_lock); + p = &gact->param; + + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); + + if (tb[TCA_GATE_ENTRY_LIST]) { + err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); + if (err < 0) + goto chain_put; + } + + if (!cycletime) { + struct tcfg_gate_entry *entry; + ktime_t cycle = 0; + + list_for_each_entry(entry, &p->entries, list) + cycle = ktime_add_ns(cycle, entry->interval); + cycletime = cycle; + if (!cycletime) { + err = -EINVAL; + goto chain_put; + } + } + p->tcfg_cycletime = cycletime; + + if (tb[TCA_GATE_CYCLE_TIME_EXT]) + p->tcfg_cycletime_ext = + nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); + + gate_setup_timer(gact, basetime, tk_offset, clockid, + ret == ACT_P_CREATED); + p->tcfg_priority = prio; + p->tcfg_flags = gflags; + gate_get_start_time(gact, &start); + + gact->current_close_time = start; + gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; + + gact->next_entry = list_first_entry(&p->entries, + struct tcfg_gate_entry, list); + + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + + gate_start_timer(gact, start); + + spin_unlock_bh(&gact->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + + return ret; + +chain_put: + spin_unlock_bh(&gact->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + /* action is not inserted in any list: it's safe to init hitimer + * without taking tcf_lock. + */ + if (ret == ACT_P_CREATED) + gate_setup_timer(gact, gact->param.tcfg_basetime, + gact->tk_offset, gact->param.tcfg_clockid, + true); + tcf_idr_release(*a, bind); + return err; +} + +static void tcf_gate_cleanup(struct tc_action *a) +{ + struct tcf_gate *gact = to_gate(a); + struct tcf_gate_params *p; + + p = &gact->param; + hrtimer_cancel(&gact->hitimer); + release_entry_list(&p->entries); +} + +static int dumping_entry(struct sk_buff *skb, + struct tcfg_gate_entry *entry) +{ + struct nlattr *item; + + item = nla_nest_start_noflag(skb, TCA_GATE_ONE_ENTRY); + if (!item) + return -ENOSPC; + + if (nla_put_u32(skb, TCA_GATE_ENTRY_INDEX, entry->index)) + goto nla_put_failure; + + if (entry->gate_state && nla_put_flag(skb, TCA_GATE_ENTRY_GATE)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GATE_ENTRY_INTERVAL, entry->interval)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_ENTRY_MAX_OCTETS, entry->maxoctets)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_ENTRY_IPV, entry->ipv)) + goto nla_put_failure; + + return nla_nest_end(skb, item); + +nla_put_failure: + nla_nest_cancel(skb, item); + return -1; +} + +static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_gate *gact = to_gate(a); + struct tc_gate opt = { + .index = gact->tcf_index, + .refcnt = refcount_read(&gact->tcf_refcnt) - ref, + .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind, + }; + struct tcfg_gate_entry *entry; + struct tcf_gate_params *p; + struct nlattr *entry_list; + struct tcf_t t; + + spin_lock_bh(&gact->tcf_lock); + opt.action = gact->tcf_action; + + p = &gact->param; + + if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_BASE_TIME, + p->tcfg_basetime, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME, + p->tcfg_cycletime, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME_EXT, + p->tcfg_cycletime_ext, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_CLOCKID, p->tcfg_clockid)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GATE_FLAGS, p->tcfg_flags)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_PRIORITY, p->tcfg_priority)) + goto nla_put_failure; + + entry_list = nla_nest_start_noflag(skb, TCA_GATE_ENTRY_LIST); + if (!entry_list) + goto nla_put_failure; + + list_for_each_entry(entry, &p->entries, list) { + if (dumping_entry(skb, entry) < 0) + goto nla_put_failure; + } + + nla_nest_end(skb, entry_list); + + tcf_tm_dump(&t, &gact->tcf_tm); + if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD)) + goto nla_put_failure; + spin_unlock_bh(&gact->tcf_lock); + + return skb->len; + +nla_put_failure: + spin_unlock_bh(&gact->tcf_lock); + nlmsg_trim(skb, b); + return -1; +} + +static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) +{ + struct tcf_gate *gact = to_gate(a); + struct tcf_t *tm = &gact->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); +} + +static size_t tcf_gate_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_gate)); +} + +static void tcf_gate_entry_destructor(void *priv) +{ + struct action_gate_entry *oe = priv; + + kfree(oe); +} + +static int tcf_gate_get_entries(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->gate.entries = tcf_gate_get_list(act); + + if (!entry->gate.entries) + return -EINVAL; + + entry->destructor = tcf_gate_entry_destructor; + entry->destructor_priv = entry->gate.entries; + + return 0; +} + +static int tcf_gate_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) +{ + int err; + + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_GATE; + entry->gate.prio = tcf_gate_prio(act); + entry->gate.basetime = tcf_gate_basetime(act); + entry->gate.cycletime = tcf_gate_cycletime(act); + entry->gate.cycletimeext = tcf_gate_cycletimeext(act); + entry->gate.num_entries = tcf_gate_num_entries(act); + err = tcf_gate_get_entries(entry, act); + if (err) + return err; + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_GATE; + } + + return 0; +} + +static struct tc_action_ops act_gate_ops = { + .kind = "gate", + .id = TCA_ID_GATE, + .owner = THIS_MODULE, + .act = tcf_gate_act, + .dump = tcf_gate_dump, + .init = tcf_gate_init, + .cleanup = tcf_gate_cleanup, + .stats_update = tcf_gate_stats_update, + .get_fill_size = tcf_gate_get_fill_size, + .offload_act_setup = tcf_gate_offload_act_setup, + .size = sizeof(struct tcf_gate), +}; +MODULE_ALIAS_NET_ACT("gate"); + +static __net_init int gate_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); + + return tc_action_net_init(net, tn, &act_gate_ops); +} + +static void __net_exit gate_exit_net(struct list_head *net_list) +{ + tc_action_net_exit(net_list, act_gate_ops.net_id); +} + +static struct pernet_operations gate_net_ops = { + .init = gate_init_net, + .exit_batch = gate_exit_net, + .id = &act_gate_ops.net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init gate_init_module(void) +{ + return tcf_register_action(&act_gate_ops, &gate_net_ops); +} + +static void __exit gate_cleanup_module(void) +{ + tcf_unregister_action(&act_gate_ops, &gate_net_ops); +} + +module_init(gate_init_module); +module_exit(gate_cleanup_module); +MODULE_DESCRIPTION("TC gate action"); +MODULE_LICENSE("GPL v2"); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index c5dec308b8b1..1dfdda6c2d4c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/ife.c Inter-FE action based on ForCES WG InterFE LFB * @@ -9,13 +10,7 @@ * Subsystem" * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * copyright Jamal Hadi Salim (2015) - * */ #include <linux/types.h> @@ -29,14 +24,13 @@ #include <net/net_namespace.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> #include <linux/etherdevice.h> #include <net/ife.h> +#include <net/tc_wrapper.h> -#define IFE_TAB_MASK 15 - -static unsigned int ife_net_id; static int max_metacnt = IFE_META_MAX + 1; static struct tc_action_ops act_ife_ops; @@ -250,11 +244,25 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) return ret; } +#ifdef CONFIG_MODULES +static const char *ife_meta_id2name(u32 metaid) +{ + switch (metaid) { + case IFE_META_SKBMARK: + return "skbmark"; + case IFE_META_PRIO: + return "skbprio"; + case IFE_META_TCINDEX: + return "tcindex"; + default: + return "unknown"; + } +} +#endif + /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, - void *val, int len, bool exists) +static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) { struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; @@ -262,13 +270,11 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (!ops) { ret = -ENOENT; #ifdef CONFIG_MODULES - if (exists) - spin_unlock_bh(&ife->tcf_lock); - rtnl_unlock(); - request_module("ifemeta%u", metaid); - rtnl_lock(); - if (exists) - spin_lock_bh(&ife->tcf_lock); + if (rtnl_held) + rtnl_unlock(); + request_module("ife-meta-%s", ife_meta_id2name(metaid)); + if (rtnl_held) + rtnl_lock(); ops = find_ife_oplist(metaid); #endif } @@ -285,24 +291,17 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, } /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic) +static int __add_metainfo(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool atomic, bool exists) { struct tcf_meta_info *mi = NULL; - struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; - if (!ops) - return -ENOENT; - mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL); - if (!mi) { - /*put back what find_ife_oplist took */ - module_put(ops->owner); + if (!mi) return -ENOMEM; - } mi->metaid = metaid; mi->ops = ops; @@ -310,17 +309,49 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL); if (ret != 0) { kfree(mi); - module_put(ops->owner); return ret; } } + if (exists) + spin_lock_bh(&ife->tcf_lock); list_add_tail(&mi->metalist, &ife->metalist); + if (exists) + spin_unlock_bh(&ife->tcf_lock); + + return ret; +} +static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, + bool exists) +{ + int ret; + + if (!try_module_get(ops->owner)) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + if (ret) + module_put(ops->owner); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife) +static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool exists) +{ + const struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret; + + if (!ops) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + if (ret) + /*put back what find_ife_oplist took */ + module_put(ops->owner); + return ret; +} + +static int use_all_metadata(struct tcf_ife_info *ife, bool exists) { struct tcf_meta_ops *o; int rc = 0; @@ -328,7 +359,7 @@ static int use_all_metadata(struct tcf_ife_info *ife) read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo(ife, o->metaid, NULL, 0, true); + rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); if (rc == 0) installed += 1; } @@ -351,7 +382,7 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) if (list_empty(&ife->metalist)) return 0; - nest = nla_nest_start(skb, TCA_IFE_METALST); + nest = nla_nest_start_noflag(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; @@ -373,13 +404,12 @@ out_nlmsg_trim: } /* under ife->tcf_lock */ -static void _tcf_ife_cleanup(struct tc_action *a, int bind) +static void _tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { - module_put(e->ops->owner); list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -387,22 +417,46 @@ static void _tcf_ife_cleanup(struct tc_action *a, int bind) else kfree(e->metaval); } + module_put(e->ops->owner); kfree(e); } } -static void tcf_ife_cleanup(struct tc_action *a, int bind) +static void tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; spin_lock_bh(&ife->tcf_lock); - _tcf_ife_cleanup(a, bind); + _tcf_ife_cleanup(a); spin_unlock_bh(&ife->tcf_lock); + + p = rcu_dereference_protected(ife->params, 1); + if (p) + kfree_rcu(p, rcu); +} + +static int load_metalist(struct nlattr **tb, bool rtnl_held) +{ + int i; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + void *val = nla_data(tb[i]); + int len = nla_len(tb[i]); + int rc; + + rc = load_metaops_and_vet(i, val, len, rtnl_held); + if (rc != 0) + return rc; + } + } + + return 0; } -/* under ife->tcf_lock for existing action */ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, - bool exists) + bool exists, bool rtnl_held) { int len = 0; int rc = 0; @@ -414,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(ife, i, val, len, exists); - if (rc != 0) - return rc; - rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; @@ -429,21 +479,32 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, ife_net_id); + struct tc_action_net *tn = net_generic(net, act_ife_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_chain *goto_ch = NULL; + struct tcf_ife_params *p; struct tcf_ife_info *ife; + u16 ife_type = ETH_P_IFE; struct tc_ife *parm; - u16 ife_type = 0; u8 *daddr = NULL; u8 *saddr = NULL; bool exists = false; int ret = 0; + u32 index; int err; - err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy, NULL); + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed"); + return -EINVAL; + } + + err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy, + NULL); if (err < 0) return err; @@ -452,109 +513,129 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_IFE_PARMS]); - exists = tcf_hash_check(tn, parm->index, a, bind); - if (exists && bind) - return 0; + /* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because + * they cannot run as the same time. Check on all other values which + * are not supported right now. + */ + if (parm->flags & ~IFE_ENCODE) + return -EINVAL; - if (parm->flags & IFE_ENCODE) { - /* Until we get issued the ethertype, we cant have - * a default.. - **/ - if (!tb[TCA_IFE_TYPE]) { - if (exists) - tcf_hash_release(*a, bind); - pr_info("You MUST pass etherype for encoding\n"); - return -EINVAL; + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, + tb[TCA_IFE_METALST], NULL, + NULL); + if (err) { + kfree(p); + return err; + } + err = load_metalist(tb2, !(flags & TCA_ACT_FLAGS_NO_RTNL)); + if (err) { + kfree(p); + return err; } } + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) { + kfree(p); + return err; + } + exists = err; + if (exists && bind) { + kfree(p); + return ACT_P_BOUND; + } + if (!exists) { - ret = tcf_hash_create(tn, parm->index, est, a, &act_ife_ops, - bind, false); - if (ret) + ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, + bind, true, flags); + if (ret) { + tcf_idr_cleanup(tn, index); + kfree(p); return ret; + } ret = ACT_P_CREATED; - } else { - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + kfree(p); + return -EEXIST; } ife = to_ife(*a); - ife->flags = parm->flags; + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&ife->metalist); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + p->flags = parm->flags; if (parm->flags & IFE_ENCODE) { - ife_type = nla_get_u16(tb[TCA_IFE_TYPE]); + if (tb[TCA_IFE_TYPE]) + ife_type = nla_get_u16(tb[TCA_IFE_TYPE]); if (tb[TCA_IFE_DMAC]) daddr = nla_data(tb[TCA_IFE_DMAC]); if (tb[TCA_IFE_SMAC]) saddr = nla_data(tb[TCA_IFE_SMAC]); } - if (exists) - spin_lock_bh(&ife->tcf_lock); - ife->tcf_action = parm->action; - if (parm->flags & IFE_ENCODE) { if (daddr) - ether_addr_copy(ife->eth_dst, daddr); + ether_addr_copy(p->eth_dst, daddr); else - eth_zero_addr(ife->eth_dst); + eth_zero_addr(p->eth_dst); if (saddr) - ether_addr_copy(ife->eth_src, saddr); + ether_addr_copy(p->eth_src, saddr); else - eth_zero_addr(ife->eth_src); + eth_zero_addr(p->eth_src); - ife->eth_type = ife_type; + p->eth_type = ife_type; } - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&ife->metalist); - if (tb[TCA_IFE_METALST]) { - err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], - NULL, NULL); - if (err) { -metadata_parse_err: - if (exists) - tcf_hash_release(*a, bind); - if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a, bind); - - if (exists) - spin_unlock_bh(&ife->tcf_lock); - return err; - } - - err = populate_metalist(ife, tb2, exists); + err = populate_metalist(ife, tb2, exists, + !(flags & TCA_ACT_FLAGS_NO_RTNL)); if (err) goto metadata_parse_err; - } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife); - if (err) { - if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a, bind); - - if (exists) - spin_unlock_bh(&ife->tcf_lock); - return err; - } + err = use_all_metadata(ife, exists); + if (err) + goto metadata_parse_err; } if (exists) - spin_unlock_bh(&ife->tcf_lock); + spin_lock_bh(&ife->tcf_lock); + /* protected by tcf_lock when modifying existing action */ + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + p = rcu_replace_pointer(ife->params, p, 1); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); + if (exists) + spin_unlock_bh(&ife->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (p) + kfree_rcu(p, rcu); return ret; +metadata_parse_err: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + kfree(p); + tcf_idr_release(*a, bind); + return err; } static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, @@ -562,15 +643,22 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, { unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); - struct tc_ife opt = { - .index = ife->tcf_index, - .refcnt = ife->tcf_refcnt - ref, - .bindcnt = ife->tcf_bindcnt - bind, - .action = ife->tcf_action, - .flags = ife->flags, - }; + struct tcf_ife_params *p; + struct tc_ife opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + + opt.index = ife->tcf_index; + opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind; + + spin_lock_bh(&ife->tcf_lock); + opt.action = ife->tcf_action; + p = rcu_dereference_protected(ife->params, + lockdep_is_held(&ife->tcf_lock)); + opt.flags = p->flags; + if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -578,17 +666,17 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; - if (!is_zero_ether_addr(ife->eth_dst)) { - if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) + if (!is_zero_ether_addr(p->eth_dst)) { + if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; } - if (!is_zero_ether_addr(ife->eth_src)) { - if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) + if (!is_zero_ether_addr(p->eth_src)) { + if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; } - if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) + if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; if (dump_metalist(skb, ife)) { @@ -596,9 +684,11 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, pr_info("Failed to dump metalist\n"); } + spin_unlock_bh(&ife->tcf_lock); return skb->len; nla_put_failure: + spin_unlock_bh(&ife->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -618,7 +708,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, } } - return 0; + return -ENOENT; } static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, @@ -630,19 +720,15 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlv_data; u16 metalen; - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); - spin_unlock(&ife->tcf_lock); if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); tlv_data = ife_decode(skb, &metalen); if (unlikely(!tlv_data)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -652,7 +738,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u16 mtype; u16 dlen; - curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); + curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, + &dlen, NULL); + if (!curr_data) { + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); + return TC_ACT_SHOT; + } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata @@ -660,14 +751,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, */ pr_info_ratelimited("Unknown metaid %d dlen %d\n", mtype, dlen); - ife->tcf_qstats.overlimits++; + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); } } if (WARN_ON(tlv_data != ifehdr_end)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -696,7 +785,7 @@ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) } static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) + struct tcf_result *res, struct tcf_ife_params *p) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; @@ -719,23 +808,20 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, exceed_mtu = true; } - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet * with no metadata */ - ife->tcf_qstats.overlimits++; - spin_unlock(&ife->tcf_lock); + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); return action; } /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -744,6 +830,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, ife_meta = ife_encode(skb, metalen); + spin_lock(&ife->tcf_lock); + /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... @@ -755,96 +843,72 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } if (err < 0) { /* too corrupt to keep around if overwritten */ - ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } skboff += err; } + spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; - if (!is_zero_ether_addr(ife->eth_src)) - ether_addr_copy(oethh->h_source, ife->eth_src); - if (!is_zero_ether_addr(ife->eth_dst)) - ether_addr_copy(oethh->h_dest, ife->eth_dst); - oethh->h_proto = htons(ife->eth_type); + if (!is_zero_ether_addr(p->eth_src)) + ether_addr_copy(oethh->h_source, p->eth_src); + if (!is_zero_ether_addr(p->eth_dst)) + ether_addr_copy(oethh->h_dest, p->eth_dst); + oethh->h_proto = htons(p->eth_type); if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); - spin_unlock(&ife->tcf_lock); - return action; } -static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_ife_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; + int ret; - if (ife->flags & IFE_ENCODE) - return tcf_ife_encode(skb, a, res); - - if (!(ife->flags & IFE_ENCODE)) - return tcf_ife_decode(skb, a, res); - - pr_info_ratelimited("unknown failure(policy neither de/encode\n"); - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); - tcf_lastuse_update(&ife->tcf_tm); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); - - return TC_ACT_SHOT; -} - -static int tcf_ife_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, ife_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ife_net_id); + p = rcu_dereference_bh(ife->params); + if (p->flags & IFE_ENCODE) { + ret = tcf_ife_encode(skb, a, res, p); + return ret; + } - return tcf_hash_search(tn, a, index); + return tcf_ife_decode(skb, a, res); } static struct tc_action_ops act_ife_ops = { .kind = "ife", - .type = TCA_ACT_IFE, + .id = TCA_ID_IFE, .owner = THIS_MODULE, .act = tcf_ife_act, .dump = tcf_ife_dump, .cleanup = tcf_ife_cleanup, .init = tcf_ife_init, - .walk = tcf_ife_walker, - .lookup = tcf_ife_search, .size = sizeof(struct tcf_ife_info), }; +MODULE_ALIAS_NET_ACT("ife"); static __net_init int ife_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, ife_net_id); + struct tc_action_net *tn = net_generic(net, act_ife_ops.net_id); - return tc_action_net_init(tn, &act_ife_ops, IFE_TAB_MASK); + return tc_action_net_init(net, tn, &act_ife_ops); } -static void __net_exit ife_exit_net(struct net *net) +static void __net_exit ife_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, ife_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_ife_ops.net_id); } static struct pernet_operations ife_net_ops = { .init = ife_init_net, - .exit = ife_exit_net, - .id = &ife_net_id, + .exit_batch = ife_exit_net, + .id = &act_ife_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c deleted file mode 100644 index 36f0ced9e60c..000000000000 --- a/net/sched/act_ipt.c +++ /dev/null @@ -1,434 +0,0 @@ -/* - * net/sched/act_ipt.c iptables target interface - * - *TODO: Add other tables. For now we only support the ipv4 table targets - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Copyright: Jamal Hadi Salim (2002-13) - */ - -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <linux/tc_act/tc_ipt.h> -#include <net/tc_act/tc_ipt.h> - -#include <linux/netfilter_ipv4/ip_tables.h> - - -#define IPT_TAB_MASK 15 - -static unsigned int ipt_net_id; -static struct tc_action_ops act_ipt_ops; - -static unsigned int xt_net_id; -static struct tc_action_ops act_xt_ops; - -static int ipt_init_target(struct xt_entry_target *t, char *table, - unsigned int hook) -{ - struct xt_tgchk_param par; - struct xt_target *target; - int ret = 0; - - target = xt_request_find_target(AF_INET, t->u.user.name, - t->u.user.revision); - if (IS_ERR(target)) - return PTR_ERR(target); - - t->u.kernel.target = target; - par.table = table; - par.entryinfo = NULL; - par.target = target; - par.targinfo = t->data; - par.hook_mask = hook; - par.family = NFPROTO_IPV4; - - ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); - if (ret < 0) { - module_put(t->u.kernel.target->me); - return ret; - } - return 0; -} - -static void ipt_destroy_target(struct xt_entry_target *t) -{ - struct xt_tgdtor_param par = { - .target = t->u.kernel.target, - .targinfo = t->data, - .family = NFPROTO_IPV4, - }; - if (par.target->destroy != NULL) - par.target->destroy(&par); - module_put(par.target->me); -} - -static void tcf_ipt_release(struct tc_action *a, int bind) -{ - struct tcf_ipt *ipt = to_ipt(a); - ipt_destroy_target(ipt->tcfi_t); - kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); -} - -static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { - [TCA_IPT_TABLE] = { .type = NLA_STRING, .len = IFNAMSIZ }, - [TCA_IPT_HOOK] = { .type = NLA_U32 }, - [TCA_IPT_INDEX] = { .type = NLA_U32 }, - [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, -}; - -static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, - const struct tc_action_ops *ops, int ovr, int bind) -{ - struct nlattr *tb[TCA_IPT_MAX + 1]; - struct tcf_ipt *ipt; - struct xt_entry_target *td, *t; - char *tname; - bool exists = false; - int ret = 0, err; - u32 hook = 0; - u32 index = 0; - - if (nla == NULL) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_IPT_MAX, nla, ipt_policy, NULL); - if (err < 0) - return err; - - if (tb[TCA_IPT_INDEX] != NULL) - index = nla_get_u32(tb[TCA_IPT_INDEX]); - - exists = tcf_hash_check(tn, index, a, bind); - if (exists && bind) - return 0; - - if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) { - if (exists) - tcf_hash_release(*a, bind); - return -EINVAL; - } - - td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); - if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) { - if (exists) - tcf_hash_release(*a, bind); - return -EINVAL; - } - - if (!exists) { - ret = tcf_hash_create(tn, index, est, a, ops, bind, - false); - if (ret) - return ret; - ret = ACT_P_CREATED; - } else { - if (bind)/* dont override defaults */ - return 0; - tcf_hash_release(*a, bind); - - if (!ovr) - return -EEXIST; - } - hook = nla_get_u32(tb[TCA_IPT_HOOK]); - - err = -ENOMEM; - tname = kmalloc(IFNAMSIZ, GFP_KERNEL); - if (unlikely(!tname)) - goto err1; - if (tb[TCA_IPT_TABLE] == NULL || - nla_strlcpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ) - strcpy(tname, "mangle"); - - t = kmemdup(td, td->u.target_size, GFP_KERNEL); - if (unlikely(!t)) - goto err2; - - err = ipt_init_target(t, tname, hook); - if (err < 0) - goto err3; - - ipt = to_ipt(*a); - - spin_lock_bh(&ipt->tcf_lock); - if (ret != ACT_P_CREATED) { - ipt_destroy_target(ipt->tcfi_t); - kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); - } - ipt->tcfi_tname = tname; - ipt->tcfi_t = t; - ipt->tcfi_hook = hook; - spin_unlock_bh(&ipt->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); - return ret; - -err3: - kfree(t); -err2: - kfree(tname); -err1: - if (ret == ACT_P_CREATED) - tcf_hash_cleanup(*a, est); - return err; -} - -static int tcf_ipt_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_ipt_ops, ovr, bind); -} - -static int tcf_xt_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_xt_ops, ovr, bind); -} - -static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) -{ - int ret = 0, result = 0; - struct tcf_ipt *ipt = to_ipt(a); - struct xt_action_param par; - struct nf_hook_state state = { - .net = dev_net(skb->dev), - .in = skb->dev, - .hook = ipt->tcfi_hook, - .pf = NFPROTO_IPV4, - }; - - if (skb_unclone(skb, GFP_ATOMIC)) - return TC_ACT_UNSPEC; - - spin_lock(&ipt->tcf_lock); - - tcf_lastuse_update(&ipt->tcf_tm); - bstats_update(&ipt->tcf_bstats, skb); - - /* yes, we have to worry about both in and out dev - * worry later - danger - this API seems to have changed - * from earlier kernels - */ - par.state = &state; - par.target = ipt->tcfi_t->u.kernel.target; - par.targinfo = ipt->tcfi_t->data; - ret = par.target->target(skb, &par); - - switch (ret) { - case NF_ACCEPT: - result = TC_ACT_OK; - break; - case NF_DROP: - result = TC_ACT_SHOT; - ipt->tcf_qstats.drops++; - break; - case XT_CONTINUE: - result = TC_ACT_PIPE; - break; - default: - net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n", - ret); - result = TC_ACT_OK; - break; - } - spin_unlock(&ipt->tcf_lock); - return result; - -} - -static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, - int ref) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tcf_ipt *ipt = to_ipt(a); - struct xt_entry_target *t; - struct tcf_t tm; - struct tc_cnt c; - - /* for simple targets kernel size == user size - * user name = target name - * for foolproof you need to not assume this - */ - - t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC); - if (unlikely(!t)) - goto nla_put_failure; - - c.bindcnt = ipt->tcf_bindcnt - bind; - c.refcnt = ipt->tcf_refcnt - ref; - strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name); - - if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) || - nla_put_u32(skb, TCA_IPT_INDEX, ipt->tcf_index) || - nla_put_u32(skb, TCA_IPT_HOOK, ipt->tcfi_hook) || - nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) || - nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname)) - goto nla_put_failure; - - tcf_tm_dump(&tm, &ipt->tcf_tm); - if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD)) - goto nla_put_failure; - - kfree(t); - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - kfree(t); - return -1; -} - -static int tcf_ipt_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return tcf_hash_search(tn, a, index); -} - -static struct tc_action_ops act_ipt_ops = { - .kind = "ipt", - .type = TCA_ACT_IPT, - .owner = THIS_MODULE, - .act = tcf_ipt, - .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_release, - .init = tcf_ipt_init, - .walk = tcf_ipt_walker, - .lookup = tcf_ipt_search, - .size = sizeof(struct tcf_ipt), -}; - -static __net_init int ipt_init_net(struct net *net) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return tc_action_net_init(tn, &act_ipt_ops, IPT_TAB_MASK); -} - -static void __net_exit ipt_exit_net(struct net *net) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - tc_action_net_exit(tn); -} - -static struct pernet_operations ipt_net_ops = { - .init = ipt_init_net, - .exit = ipt_exit_net, - .id = &ipt_net_id, - .size = sizeof(struct tc_action_net), -}; - -static int tcf_xt_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return tcf_hash_search(tn, a, index); -} - -static struct tc_action_ops act_xt_ops = { - .kind = "xt", - .type = TCA_ACT_XT, - .owner = THIS_MODULE, - .act = tcf_ipt, - .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_release, - .init = tcf_xt_init, - .walk = tcf_xt_walker, - .lookup = tcf_xt_search, - .size = sizeof(struct tcf_ipt), -}; - -static __net_init int xt_init_net(struct net *net) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return tc_action_net_init(tn, &act_xt_ops, IPT_TAB_MASK); -} - -static void __net_exit xt_exit_net(struct net *net) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - tc_action_net_exit(tn); -} - -static struct pernet_operations xt_net_ops = { - .init = xt_init_net, - .exit = xt_exit_net, - .id = &xt_net_id, - .size = sizeof(struct tc_action_net), -}; - -MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); -MODULE_DESCRIPTION("Iptables target actions"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("act_xt"); - -static int __init ipt_init_module(void) -{ - int ret1, ret2; - - ret1 = tcf_register_action(&act_xt_ops, &xt_net_ops); - if (ret1 < 0) - pr_err("Failed to load xt action\n"); - - ret2 = tcf_register_action(&act_ipt_ops, &ipt_net_ops); - if (ret2 < 0) - pr_err("Failed to load ipt action\n"); - - if (ret1 < 0 && ret2 < 0) { - return ret1; - } else - return 0; -} - -static void __exit ipt_cleanup_module(void) -{ - tcf_unregister_action(&act_ipt_ops, &ipt_net_ops); - tcf_unregister_action(&act_xt_ops, &xt_net_ops); -} - -module_init(ipt_init_module); -module_exit(ipt_cleanup_module); diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c index 82892170ce4f..ea0573cb8b2d 100644 --- a/net/sched/act_meta_mark.c +++ b/net/sched/act_meta_mark.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_meta_mark.c IFE skb->mark metadata module * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * copyright Jamal Hadi Salim (2015) - * */ #include <linux/types.h> @@ -22,7 +17,6 @@ #include <net/pkt_sched.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> -#include <linux/rtnetlink.h> static int skbmark_encode(struct sk_buff *skb, void *skbdata, struct tcf_meta_info *e) @@ -76,4 +70,4 @@ module_exit(ifemark_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb mark metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBMARK); +MODULE_ALIAS_IFE_META("skbmark"); diff --git a/net/sched/act_meta_skbprio.c b/net/sched/act_meta_skbprio.c index 26bf4d86030b..2df3133ce5ad 100644 --- a/net/sched/act_meta_skbprio.c +++ b/net/sched/act_meta_skbprio.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_meta_prio.c IFE skb->priority metadata module * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * copyright Jamal Hadi Salim (2015) - * */ #include <linux/types.h> @@ -73,4 +68,4 @@ module_exit(ifeprio_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb prio metadata action"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_PRIO); +MODULE_ALIAS_IFE_META("skbprio"); diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c index 3b35774ce890..44547caead46 100644 --- a/net/sched/act_meta_skbtcindex.c +++ b/net/sched/act_meta_skbtcindex.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_meta_tc_index.c IFE skb->tc_index metadata module * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * copyright Jamal Hadi Salim (2016) - * */ #include <linux/types.h> @@ -22,7 +17,6 @@ #include <net/pkt_sched.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> -#include <linux/rtnetlink.h> static int skbtcindex_encode(struct sk_buff *skb, void *skbdata, struct tcf_meta_info *e) @@ -76,4 +70,4 @@ module_exit(ifetc_index_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2016)"); MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX); +MODULE_ALIAS_IFE_META("tcindex"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1b5549ababd4..f27b583def78 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -1,15 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_mirred.c packet mirroring and redirect actions * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Jamal Hadi Salim (2002-4) * * TODO: Add ingress support (and socket redirect support) - * */ #include <linux/types.h> @@ -24,11 +19,13 @@ #include <linux/if_arp.h> #include <net/net_namespace.h> #include <net/netlink.h> +#include <net/dst.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_mirred.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_wrapper.h> -#define MIRRED_TAB_MASK 7 static LIST_HEAD(mirred_list); static DEFINE_SPINLOCK(mirred_list_lock); @@ -51,52 +48,102 @@ static bool tcf_mirred_act_wants_ingress(int action) } } -static void tcf_mirred_release(struct tc_action *a, int bind) +static bool tcf_mirred_can_reinsert(int action) +{ + switch (action) { + case TC_ACT_SHOT: + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + return true; + } + return false; +} + +static struct net_device *tcf_mirred_dev_dereference(struct tcf_mirred *m) +{ + return rcu_dereference_protected(m->tcfm_dev, + lockdep_is_held(&m->tcf_lock)); +} + +static void tcf_mirred_release(struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; - /* We could be called either in a RCU callback or with RTNL lock held. */ - spin_lock_bh(&mirred_list_lock); + spin_lock(&mirred_list_lock); list_del(&m->tcfm_list); + spin_unlock(&mirred_list_lock); + + /* last reference to action, no need to lock */ dev = rcu_dereference_protected(m->tcfm_dev, 1); - if (dev) - dev_put(dev); - spin_unlock_bh(&mirred_list_lock); + netdev_put(dev, &m->tcfm_dev_tracker); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, + [TCA_MIRRED_BLOCKID] = NLA_POLICY_MIN(NLA_U32, 1), }; -static unsigned int mirred_net_id; static struct tc_action_ops act_mirred_ops; +static void tcf_mirred_replace_dev(struct tcf_mirred *m, + struct net_device *ndev) +{ + struct net_device *odev; + + odev = rcu_replace_pointer(m->tcfm_dev, ndev, + lockdep_is_held(&m->tcf_lock)); + netdev_put(odev, &m->tcfm_dev_tracker); +} + static int tcf_mirred_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind) + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, + u32 flags, struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, mirred_net_id); + struct tc_action_net *tn = net_generic(net, act_mirred_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_MIRRED_MAX + 1]; + struct tcf_chain *goto_ch = NULL; bool mac_header_xmit = false; struct tc_mirred *parm; struct tcf_mirred *m; - struct net_device *dev; bool exists = false; - int ret; + int ret, err; + u32 index; - if (nla == NULL) + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); return -EINVAL; - ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, NULL); + } + ret = nla_parse_nested_deprecated(tb, TCA_MIRRED_MAX, nla, + mirred_policy, extack); if (ret < 0) return ret; - if (tb[TCA_MIRRED_PARMS] == NULL) + if (!tb[TCA_MIRRED_PARMS]) { + NL_SET_ERR_MSG_MOD(extack, "Missing required mirred parameters"); return -EINVAL; + } parm = nla_data(tb[TCA_MIRRED_PARMS]); - - exists = tcf_hash_check(tn, parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; + + if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot specify Block ID and dev simultaneously"); + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); + + return -EINVAL; + } switch (parm->eaction) { case TCA_EGRESS_MIRROR: @@ -106,140 +153,326 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, break; default: if (exists) - tcf_hash_release(*a, bind); + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); + NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } - if (parm->ifindex) { - dev = __dev_get_by_index(net, parm->ifindex); - if (dev == NULL) { - if (exists) - tcf_hash_release(*a, bind); - return -ENODEV; - } - mac_header_xmit = dev_is_mac_header_xmit(dev); - } else { - dev = NULL; - } if (!exists) { - if (dev == NULL) + if (!parm->ifindex && !tb[TCA_MIRRED_BLOCKID]) { + tcf_idr_cleanup(tn, index); + NL_SET_ERR_MSG_MOD(extack, + "Must specify device or block"); return -EINVAL; - ret = tcf_hash_create(tn, parm->index, est, a, - &act_mirred_ops, bind, true); - if (ret) + } + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_mirred_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; } + m = to_mirred(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&m->tcfm_list); - ASSERT_RTNL(); - m->tcf_action = parm->action; - m->tcfm_eaction = parm->eaction; - if (dev != NULL) { - m->tcfm_ifindex = parm->ifindex; - if (ret != ACT_P_CREATED) - dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); - dev_hold(dev); - rcu_assign_pointer(m->tcfm_dev, dev); + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + spin_lock_bh(&m->tcf_lock); + + if (parm->ifindex) { + struct net_device *ndev; + + ndev = dev_get_by_index(net, parm->ifindex); + if (!ndev) { + spin_unlock_bh(&m->tcf_lock); + err = -ENODEV; + goto put_chain; + } + mac_header_xmit = dev_is_mac_header_xmit(ndev); + tcf_mirred_replace_dev(m, ndev); + netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC); m->tcfm_mac_header_xmit = mac_header_xmit; + m->tcfm_blockid = 0; + } else if (tb[TCA_MIRRED_BLOCKID]) { + tcf_mirred_replace_dev(m, NULL); + m->tcfm_mac_header_xmit = false; + m->tcfm_blockid = nla_get_u32(tb[TCA_MIRRED_BLOCKID]); } + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + m->tcfm_eaction = parm->eaction; + spin_unlock_bh(&m->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) { - spin_lock_bh(&mirred_list_lock); + spin_lock(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); - spin_unlock_bh(&mirred_list_lock); - tcf_hash_insert(tn, *a); + spin_unlock(&mirred_list_lock); } return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } -static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +static int +tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb) { - struct tcf_mirred *m = to_mirred(a); - bool m_mac_header_xmit; - struct net_device *dev; - struct sk_buff *skb2; - int retval, err = 0; - int m_eaction; - int mac_len; + int err; - tcf_lastuse_update(&m->tcf_tm); - bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); + if (!want_ingress) + err = tcf_dev_queue_xmit(skb, dev_queue_xmit); + else if (!at_ingress) + err = netif_rx(skb); + else + err = netif_receive_skb(skb); - rcu_read_lock(); - m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); - m_eaction = READ_ONCE(m->tcfm_eaction); - retval = READ_ONCE(m->tcf_action); - dev = rcu_dereference(m->tcfm_dev); - if (unlikely(!dev)) { - pr_notice_once("tc mirred: target device is gone\n"); - goto out; - } + return err; +} + +static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, + struct net_device *dev, + const bool m_mac_header_xmit, int m_eaction, + int retval) +{ + struct sk_buff *skb_to_send = skb; + bool want_ingress; + bool is_redirect; + bool expects_nh; + bool at_ingress; + bool dont_clone; + int mac_len; + bool at_nh; + int err; - if (unlikely(!(dev->flags & IFF_UP))) { + is_redirect = tcf_mirred_is_act_redirect(m_eaction); + if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); - goto out; + goto err_cant_do; } - skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) - goto out; - - /* If action's target direction differs than filter's direction, - * and devices expect a mac header on xmit, then mac push/pull is - * needed. + /* we could easily avoid the clone only if called by ingress and clsact; + * since we can't easily detect the clsact caller, skip clone only for + * ingress - that covers the TC S/W datapath. */ - if (skb_at_tc_ingress(skb) != tcf_mirred_act_wants_ingress(m_eaction) && - m_mac_header_xmit) { - if (!skb_at_tc_ingress(skb)) { - /* caught at egress, act ingress: pull mac */ - mac_len = skb_network_header(skb) - skb_mac_header(skb); - skb_pull_rcsum(skb2, mac_len); + at_ingress = skb_at_tc_ingress(skb); + dont_clone = skb_at_tc_ingress(skb) && is_redirect && + tcf_mirred_can_reinsert(retval); + if (!dont_clone) { + skb_to_send = skb_clone(skb, GFP_ATOMIC); + if (!skb_to_send) + goto err_cant_do; + } + + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + + /* All mirred/redirected skbs should clear previous ct info */ + nf_reset_ct(skb_to_send); + if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ + skb_dst_drop(skb_to_send); + + expects_nh = want_ingress || !m_mac_header_xmit; + at_nh = skb->data == skb_network_header(skb); + if (at_nh != expects_nh) { + mac_len = at_ingress ? skb->mac_len : + skb_network_offset(skb); + if (expects_nh) { + /* target device/action expect data at nh */ + skb_pull_rcsum(skb_to_send, mac_len); } else { - /* caught at ingress, act egress: push mac */ - skb_push_rcsum(skb2, skb->mac_len); + /* target device/action expect data at mac */ + skb_push_rcsum(skb_to_send, mac_len); } } - /* mirror is always swallowed */ - if (tcf_mirred_is_act_redirect(m_eaction)) { - skb2->tc_redirected = 1; - skb2->tc_from_ingress = skb2->tc_at_ingress; + skb_to_send->skb_iif = skb->dev->ifindex; + skb_to_send->dev = dev; + + if (is_redirect) { + if (skb == skb_to_send) + retval = TC_ACT_CONSUMED; + + skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress); + + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); + } else { + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } + if (err) + tcf_action_inc_overlimit_qstats(&m->common); - skb2->skb_iif = skb->dev->ifindex; - skb2->dev = dev; - if (!tcf_mirred_act_wants_ingress(m_eaction)) - err = dev_queue_xmit(skb2); - else - err = netif_receive_skb(skb2); + return retval; - if (err) { -out: - qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats)); - if (tcf_mirred_is_act_redirect(m_eaction)) - retval = TC_ACT_SHOT; +err_cant_do: + if (is_redirect) + retval = TC_ACT_SHOT; + tcf_action_inc_overlimit_qstats(&m->common); + return retval; +} + +static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, + struct tcf_block *block, int m_eaction, + const u32 exception_ifindex, int retval) +{ + struct net_device *dev_prev = NULL; + struct net_device *dev = NULL; + unsigned long index; + int mirred_eaction; + + mirred_eaction = tcf_mirred_act_wants_ingress(m_eaction) ? + TCA_INGRESS_MIRROR : TCA_EGRESS_MIRROR; + + xa_for_each(&block->ports, index, dev) { + if (index == exception_ifindex) + continue; + + if (!dev_prev) + goto assign_prev; + + tcf_mirred_to_dev(skb, m, dev_prev, + dev_is_mac_header_xmit(dev), + mirred_eaction, retval); +assign_prev: + dev_prev = dev; } - rcu_read_unlock(); + + if (dev_prev) + return tcf_mirred_to_dev(skb, m, dev_prev, + dev_is_mac_header_xmit(dev_prev), + m_eaction, retval); return retval; } -static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse) +static int tcf_blockcast_mirror(struct sk_buff *skb, struct tcf_mirred *m, + struct tcf_block *block, int m_eaction, + const u32 exception_ifindex, int retval) +{ + struct net_device *dev = NULL; + unsigned long index; + + xa_for_each(&block->ports, index, dev) { + if (index == exception_ifindex) + continue; + + tcf_mirred_to_dev(skb, m, dev, + dev_is_mac_header_xmit(dev), + m_eaction, retval); + } + + return retval; +} + +static int tcf_blockcast(struct sk_buff *skb, struct tcf_mirred *m, + const u32 blockid, struct tcf_result *res, + int retval) +{ + const u32 exception_ifindex = skb->dev->ifindex; + struct tcf_block *block; + bool is_redirect; + int m_eaction; + + m_eaction = READ_ONCE(m->tcfm_eaction); + is_redirect = tcf_mirred_is_act_redirect(m_eaction); + + /* we are already under rcu protection, so can call block lookup + * directly. + */ + block = tcf_block_lookup(dev_net(skb->dev), blockid); + if (!block || xa_empty(&block->ports)) { + tcf_action_inc_overlimit_qstats(&m->common); + return retval; + } + + if (is_redirect) + return tcf_blockcast_redir(skb, m, block, m_eaction, + exception_ifindex, retval); + + /* If it's not redirect, it is mirror */ + return tcf_blockcast_mirror(skb, m, block, m_eaction, exception_ifindex, + retval); +} + +TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_mirred *m = to_mirred(a); + int retval = READ_ONCE(m->tcf_action); + struct netdev_xmit *xmit; + bool m_mac_header_xmit; + struct net_device *dev; + int i, m_eaction; + u32 blockid; + +#ifdef CONFIG_PREEMPT_RT + xmit = ¤t->net_xmit; +#else + xmit = this_cpu_ptr(&softnet_data.xmit); +#endif + if (unlikely(xmit->sched_mirred_nest >= MIRRED_NEST_LIMIT)) { + net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", + netdev_name(skb->dev)); + return TC_ACT_SHOT; + } + + tcf_lastuse_update(&m->tcf_tm); + tcf_action_update_bstats(&m->common, skb); + + blockid = READ_ONCE(m->tcfm_blockid); + if (blockid) + return tcf_blockcast(skb, m, blockid, res, retval); + + dev = rcu_dereference_bh(m->tcfm_dev); + if (unlikely(!dev)) { + pr_notice_once("tc mirred: target device is gone\n"); + tcf_action_inc_overlimit_qstats(&m->common); + return retval; + } + for (i = 0; i < xmit->sched_mirred_nest; i++) { + if (xmit->sched_mirred_dev[i] != dev) + continue; + pr_notice_once("tc mirred: loop on device %s\n", + netdev_name(dev)); + tcf_action_inc_overlimit_qstats(&m->common); + return retval; + } + + xmit->sched_mirred_dev[xmit->sched_mirred_nest++] = dev; + + m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); + m_eaction = READ_ONCE(m->tcfm_eaction); + + retval = tcf_mirred_to_dev(skb, m, dev, m_mac_header_xmit, m_eaction, + retval); + xmit->sched_mirred_nest--; + + return retval; +} + +static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - tm->lastuse = lastuse; + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, @@ -249,43 +482,40 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, struct tcf_mirred *m = to_mirred(a); struct tc_mirred opt = { .index = m->tcf_index, - .action = m->tcf_action, - .refcnt = m->tcf_refcnt - ref, - .bindcnt = m->tcf_bindcnt - bind, - .eaction = m->tcfm_eaction, - .ifindex = m->tcfm_ifindex, + .refcnt = refcount_read(&m->tcf_refcnt) - ref, + .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, }; + struct net_device *dev; struct tcf_t t; + u32 blockid; + + spin_lock_bh(&m->tcf_lock); + opt.action = m->tcf_action; + opt.eaction = m->tcfm_eaction; + dev = tcf_mirred_dev_dereference(m); + if (dev) + opt.ifindex = dev->ifindex; if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) goto nla_put_failure; + blockid = m->tcfm_blockid; + if (blockid && nla_put_u32(skb, TCA_MIRRED_BLOCKID, blockid)) + goto nla_put_failure; + tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; + spin_unlock_bh(&m->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&m->tcf_lock); nlmsg_trim(skb, b); return -1; } -static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - return tcf_hash_search(tn, a, index); -} - static int mirred_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -294,17 +524,19 @@ static int mirred_device_event(struct notifier_block *unused, ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) { - spin_lock_bh(&mirred_list_lock); + spin_lock(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { - if (rcu_access_pointer(m->tcfm_dev) == dev) { - dev_put(dev); + spin_lock_bh(&m->tcf_lock); + if (tcf_mirred_dev_dereference(m) == dev) { + netdev_put(dev, &m->tcfm_dev_tracker); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } + spin_unlock_bh(&m->tcf_lock); } - spin_unlock_bh(&mirred_list_lock); + spin_unlock(&mirred_list_lock); } return NOTIFY_DONE; @@ -314,50 +546,119 @@ static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; -static int tcf_mirred_device(const struct tc_action *a, struct net *net, - struct net_device **mirred_dev) +static void tcf_mirred_dev_put(void *priv) { - int ifindex = tcf_mirred_ifindex(a); + struct net_device *dev = priv; + + dev_put(dev); +} + +static struct net_device * +tcf_mirred_get_dev(const struct tc_action *a, + tc_action_priv_destructor *destructor) +{ + struct tcf_mirred *m = to_mirred(a); + struct net_device *dev; + + rcu_read_lock(); + dev = rcu_dereference(m->tcfm_dev); + if (dev) { + dev_hold(dev); + *destructor = tcf_mirred_dev_put; + } + rcu_read_unlock(); + + return dev; +} + +static size_t tcf_mirred_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_mirred)); +} + +static void tcf_offload_mirred_get_dev(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->dev = act->ops->get_dev(act, &entry->destructor); + if (!entry->dev) + return; + entry->destructor_priv = entry->dev; +} + +static int tcf_mirred_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_mirred_egress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT; + tcf_offload_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_egress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED; + tcf_offload_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_ingress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT_INGRESS; + tcf_offload_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_ingress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED_INGRESS; + tcf_offload_mirred_get_dev(entry, act); + } else { + NL_SET_ERR_MSG_MOD(extack, "Unsupported mirred offload"); + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_mirred_egress_redirect(act)) + fl_action->id = FLOW_ACTION_REDIRECT; + else if (is_tcf_mirred_egress_mirror(act)) + fl_action->id = FLOW_ACTION_MIRRED; + else if (is_tcf_mirred_ingress_redirect(act)) + fl_action->id = FLOW_ACTION_REDIRECT_INGRESS; + else if (is_tcf_mirred_ingress_mirror(act)) + fl_action->id = FLOW_ACTION_MIRRED_INGRESS; + else + return -EOPNOTSUPP; + } - *mirred_dev = __dev_get_by_index(net, ifindex); - if (!*mirred_dev) - return -EINVAL; return 0; } static struct tc_action_ops act_mirred_ops = { .kind = "mirred", - .type = TCA_ACT_MIRRED, + .id = TCA_ID_MIRRED, .owner = THIS_MODULE, - .act = tcf_mirred, + .act = tcf_mirred_act, .stats_update = tcf_stats_update, .dump = tcf_mirred_dump, .cleanup = tcf_mirred_release, .init = tcf_mirred_init, - .walk = tcf_mirred_walker, - .lookup = tcf_mirred_search, + .get_fill_size = tcf_mirred_get_fill_size, + .offload_act_setup = tcf_mirred_offload_act_setup, .size = sizeof(struct tcf_mirred), - .get_dev = tcf_mirred_device, + .get_dev = tcf_mirred_get_dev, }; +MODULE_ALIAS_NET_ACT("mirred"); static __net_init int mirred_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, mirred_net_id); + struct tc_action_net *tn = net_generic(net, act_mirred_ops.net_id); - return tc_action_net_init(tn, &act_mirred_ops, MIRRED_TAB_MASK); + return tc_action_net_init(net, tn, &act_mirred_ops); } -static void __net_exit mirred_exit_net(struct net *net) +static void __net_exit mirred_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_mirred_ops.net_id); } static struct pernet_operations mirred_net_ops = { .init = mirred_init_net, - .exit = mirred_exit_net, - .id = &mirred_net_id, + .exit_batch = mirred_exit_net, + .id = &act_mirred_ops.net_id, .size = sizeof(struct tc_action_net), }; @@ -372,7 +673,11 @@ static int __init mirred_init_module(void) return err; pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops, &mirred_net_ops); + err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); + if (err) + unregister_netdevice_notifier(&mirred_device_notifier); + + return err; } static void __exit mirred_cleanup_module(void) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c new file mode 100644 index 000000000000..6654011dcd2b --- /dev/null +++ b/net/sched/act_mpls.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Netronome Systems, Inc. */ + +#include <linux/if_arp.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mpls.h> +#include <linux/rtnetlink.h> +#include <linux/skbuff.h> +#include <linux/tc_act/tc_mpls.h> +#include <net/mpls.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_mpls.h> +#include <net/tc_wrapper.h> + +static struct tc_action_ops act_mpls_ops; + +#define ACT_MPLS_TTL_DEFAULT 255 + +static __be32 tcf_mpls_get_lse(struct mpls_shim_hdr *lse, + struct tcf_mpls_params *p, bool set_bos) +{ + u32 new_lse = 0; + + if (lse) + new_lse = be32_to_cpu(lse->label_stack_entry); + + if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET) { + new_lse &= ~MPLS_LS_LABEL_MASK; + new_lse |= p->tcfm_label << MPLS_LS_LABEL_SHIFT; + } + if (p->tcfm_ttl) { + new_lse &= ~MPLS_LS_TTL_MASK; + new_lse |= p->tcfm_ttl << MPLS_LS_TTL_SHIFT; + } + if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET) { + new_lse &= ~MPLS_LS_TC_MASK; + new_lse |= p->tcfm_tc << MPLS_LS_TC_SHIFT; + } + if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET) { + new_lse &= ~MPLS_LS_S_MASK; + new_lse |= p->tcfm_bos << MPLS_LS_S_SHIFT; + } else if (set_bos) { + new_lse |= 1 << MPLS_LS_S_SHIFT; + } + + return cpu_to_be32(new_lse); +} + +TC_INDIRECT_SCOPE int tcf_mpls_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_mpls *m = to_mpls(a); + struct tcf_mpls_params *p; + __be32 new_lse; + int mac_len; + + tcf_lastuse_update(&m->tcf_tm); + bstats_update(this_cpu_ptr(m->common.cpu_bstats), skb); + + /* Ensure 'data' points at mac_header prior calling mpls manipulating + * functions. + */ + if (skb_at_tc_ingress(skb)) { + skb_push_rcsum(skb, skb->mac_len); + mac_len = skb->mac_len; + } else { + mac_len = skb_network_offset(skb); + } + + p = rcu_dereference_bh(m->mpls_p); + + switch (p->tcfm_action) { + case TCA_MPLS_ACT_POP: + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) + goto drop; + break; + case TCA_MPLS_ACT_PUSH: + new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true))); + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) + goto drop; + break; + case TCA_MPLS_ACT_MAC_PUSH: + if (skb_vlan_tag_present(skb)) { + if (__vlan_insert_inner_tag(skb, skb->vlan_proto, + skb_vlan_tag_get(skb), + ETH_HLEN) < 0) + goto drop; + + skb->protocol = skb->vlan_proto; + __vlan_hwaccel_clear_tag(skb); + } + + new_lse = tcf_mpls_get_lse(NULL, p, mac_len || + !eth_p_mpls(skb->protocol)); + + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false)) + goto drop; + break; + case TCA_MPLS_ACT_MODIFY: + if (!pskb_may_pull(skb, + skb_network_offset(skb) + MPLS_HLEN)) + goto drop; + new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false); + if (skb_mpls_update_lse(skb, new_lse)) + goto drop; + break; + case TCA_MPLS_ACT_DEC_TTL: + if (skb_mpls_dec_ttl(skb)) + goto drop; + break; + } + + if (skb_at_tc_ingress(skb)) + skb_pull_rcsum(skb, skb->mac_len); + + return p->action; + +drop: + qstats_drop_inc(this_cpu_ptr(m->common.cpu_qstats)); + return TC_ACT_SHOT; +} + +static int valid_label(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + const u32 *label = nla_data(attr); + + if (nla_len(attr) != sizeof(*label)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length"); + return -EINVAL; + } + + if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) { + NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range"); + return -EINVAL; + } + + return 0; +} + +static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { + [TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)), + [TCA_MPLS_PROTO] = { .type = NLA_U16 }, + [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + valid_label), + [TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7), + [TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1), + [TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1), +}; + +static int tcf_mpls_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, act_mpls_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct nlattr *tb[TCA_MPLS_MAX + 1]; + struct tcf_chain *goto_ch = NULL; + struct tcf_mpls_params *p; + struct tc_mpls *parm; + bool exists = false; + struct tcf_mpls *m; + int ret = 0, err; + u8 mpls_ttl = 0; + u32 index; + + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_MPLS_MAX, nla, mpls_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_MPLS_PARMS]) { + NL_SET_ERR_MSG_MOD(extack, "No MPLS params"); + return -EINVAL; + } + parm = nla_data(tb[TCA_MPLS_PARMS]); + index = parm->index; + + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; + if (exists && bind) + return ACT_P_BOUND; + + if (!exists) { + ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, + true, flags); + if (ret) { + tcf_idr_cleanup(tn, index); + return ret; + } + + ret = ACT_P_CREATED; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + + /* Verify parameters against action type. */ + switch (parm->m_action) { + case TCA_MPLS_ACT_POP: + if (!tb[TCA_MPLS_PROTO]) { + NL_SET_ERR_MSG_MOD(extack, "Protocol must be set for MPLS pop"); + err = -EINVAL; + goto release_idr; + } + if (!eth_proto_is_802_3(nla_get_be16(tb[TCA_MPLS_PROTO]))) { + NL_SET_ERR_MSG_MOD(extack, "Invalid protocol type for MPLS pop"); + err = -EINVAL; + goto release_idr; + } + if (tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || + tb[TCA_MPLS_BOS]) { + NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC or BOS cannot be used with MPLS pop"); + err = -EINVAL; + goto release_idr; + } + break; + case TCA_MPLS_ACT_DEC_TTL: + if (tb[TCA_MPLS_PROTO] || tb[TCA_MPLS_LABEL] || + tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) { + NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC, BOS or protocol cannot be used with MPLS dec_ttl"); + err = -EINVAL; + goto release_idr; + } + break; + case TCA_MPLS_ACT_PUSH: + case TCA_MPLS_ACT_MAC_PUSH: + if (!tb[TCA_MPLS_LABEL]) { + NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push"); + err = -EINVAL; + goto release_idr; + } + if (tb[TCA_MPLS_PROTO] && + !eth_p_mpls(nla_get_be16(tb[TCA_MPLS_PROTO]))) { + NL_SET_ERR_MSG_MOD(extack, "Protocol must be an MPLS type for MPLS push"); + err = -EPROTONOSUPPORT; + goto release_idr; + } + /* Push needs a TTL - if not specified, set a default value. */ + if (!tb[TCA_MPLS_TTL]) { +#if IS_ENABLED(CONFIG_MPLS) + mpls_ttl = net->mpls.default_ttl ? + net->mpls.default_ttl : ACT_MPLS_TTL_DEFAULT; +#else + mpls_ttl = ACT_MPLS_TTL_DEFAULT; +#endif + } + break; + case TCA_MPLS_ACT_MODIFY: + if (tb[TCA_MPLS_PROTO]) { + NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be used with MPLS modify"); + err = -EINVAL; + goto release_idr; + } + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unknown MPLS action"); + err = -EINVAL; + goto release_idr; + } + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + m = to_mpls(*a); + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + err = -ENOMEM; + goto put_chain; + } + + p->tcfm_action = parm->m_action; + p->tcfm_label = nla_get_u32_default(tb[TCA_MPLS_LABEL], + ACT_MPLS_LABEL_NOT_SET); + p->tcfm_tc = nla_get_u8_default(tb[TCA_MPLS_TC], ACT_MPLS_TC_NOT_SET); + p->tcfm_ttl = nla_get_u8_default(tb[TCA_MPLS_TTL], mpls_ttl); + p->tcfm_bos = nla_get_u8_default(tb[TCA_MPLS_BOS], + ACT_MPLS_BOS_NOT_SET); + p->tcfm_proto = nla_get_be16_default(tb[TCA_MPLS_PROTO], + htons(ETH_P_MPLS_UC)); + p->action = parm->action; + + spin_lock_bh(&m->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + p = rcu_replace_pointer(m->mpls_p, p, lockdep_is_held(&m->tcf_lock)); + spin_unlock_bh(&m->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (p) + kfree_rcu(p, rcu); + + return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; +} + +static void tcf_mpls_cleanup(struct tc_action *a) +{ + struct tcf_mpls *m = to_mpls(a); + struct tcf_mpls_params *p; + + p = rcu_dereference_protected(m->mpls_p, 1); + if (p) + kfree_rcu(p, rcu); +} + +static int tcf_mpls_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + const struct tcf_mpls *m = to_mpls(a); + const struct tcf_mpls_params *p; + struct tc_mpls opt = { + .index = m->tcf_index, + .refcnt = refcount_read(&m->tcf_refcnt) - ref, + .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, + }; + struct tcf_t t; + + rcu_read_lock(); + p = rcu_dereference(m->mpls_p); + opt.m_action = p->tcfm_action; + opt.action = p->action; + + if (nla_put(skb, TCA_MPLS_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET && + nla_put_u32(skb, TCA_MPLS_LABEL, p->tcfm_label)) + goto nla_put_failure; + + if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET && + nla_put_u8(skb, TCA_MPLS_TC, p->tcfm_tc)) + goto nla_put_failure; + + if (p->tcfm_ttl && nla_put_u8(skb, TCA_MPLS_TTL, p->tcfm_ttl)) + goto nla_put_failure; + + if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET && + nla_put_u8(skb, TCA_MPLS_BOS, p->tcfm_bos)) + goto nla_put_failure; + + if (nla_put_be16(skb, TCA_MPLS_PROTO, p->tcfm_proto)) + goto nla_put_failure; + + tcf_tm_dump(&t, &m->tcf_tm); + + if (nla_put_64bit(skb, TCA_MPLS_TM, sizeof(t), &t, TCA_MPLS_PAD)) + goto nla_put_failure; + + rcu_read_unlock(); + + return skb->len; + +nla_put_failure: + rcu_read_unlock(); + nlmsg_trim(skb, b); + return -EMSGSIZE; +} + +static int tcf_mpls_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + switch (tcf_mpls_action(act)) { + case TCA_MPLS_ACT_PUSH: + entry->id = FLOW_ACTION_MPLS_PUSH; + entry->mpls_push.proto = tcf_mpls_proto(act); + entry->mpls_push.label = tcf_mpls_label(act); + entry->mpls_push.tc = tcf_mpls_tc(act); + entry->mpls_push.bos = tcf_mpls_bos(act); + entry->mpls_push.ttl = tcf_mpls_ttl(act); + break; + case TCA_MPLS_ACT_POP: + entry->id = FLOW_ACTION_MPLS_POP; + entry->mpls_pop.proto = tcf_mpls_proto(act); + break; + case TCA_MPLS_ACT_MODIFY: + entry->id = FLOW_ACTION_MPLS_MANGLE; + entry->mpls_mangle.label = tcf_mpls_label(act); + entry->mpls_mangle.tc = tcf_mpls_tc(act); + entry->mpls_mangle.bos = tcf_mpls_bos(act); + entry->mpls_mangle.ttl = tcf_mpls_ttl(act); + break; + case TCA_MPLS_ACT_DEC_TTL: + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"dec_ttl\" option is used"); + return -EOPNOTSUPP; + case TCA_MPLS_ACT_MAC_PUSH: + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"mac_push\" option is used"); + return -EOPNOTSUPP; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported MPLS mode offload"); + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + switch (tcf_mpls_action(act)) { + case TCA_MPLS_ACT_PUSH: + fl_action->id = FLOW_ACTION_MPLS_PUSH; + break; + case TCA_MPLS_ACT_POP: + fl_action->id = FLOW_ACTION_MPLS_POP; + break; + case TCA_MPLS_ACT_MODIFY: + fl_action->id = FLOW_ACTION_MPLS_MANGLE; + break; + default: + return -EOPNOTSUPP; + } + } + + return 0; +} + +static struct tc_action_ops act_mpls_ops = { + .kind = "mpls", + .id = TCA_ID_MPLS, + .owner = THIS_MODULE, + .act = tcf_mpls_act, + .dump = tcf_mpls_dump, + .init = tcf_mpls_init, + .cleanup = tcf_mpls_cleanup, + .offload_act_setup = tcf_mpls_offload_act_setup, + .size = sizeof(struct tcf_mpls), +}; +MODULE_ALIAS_NET_ACT("mpls"); + +static __net_init int mpls_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, act_mpls_ops.net_id); + + return tc_action_net_init(net, tn, &act_mpls_ops); +} + +static void __net_exit mpls_exit_net(struct list_head *net_list) +{ + tc_action_net_exit(net_list, act_mpls_ops.net_id); +} + +static struct pernet_operations mpls_net_ops = { + .init = mpls_init_net, + .exit_batch = mpls_exit_net, + .id = &act_mpls_ops.net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init mpls_init_module(void) +{ + return tcf_register_action(&act_mpls_ops, &mpls_net_ops); +} + +static void __exit mpls_cleanup_module(void) +{ + tcf_unregister_action(&act_mpls_ops, &mpls_net_ops); +} + +module_init(mpls_init_module); +module_exit(mpls_cleanup_module); + +MODULE_SOFTDEP("post: mpls_gso"); +MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MPLS manipulation actions"); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 9016ab8a0649..26241d80ebe0 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Stateless NAT actions * * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. */ #include <linux/errno.h> @@ -21,17 +17,15 @@ #include <linux/string.h> #include <linux/tc_act/tc_nat.h> #include <net/act_api.h> +#include <net/pkt_cls.h> #include <net/icmp.h> #include <net/ip.h> #include <net/netlink.h> #include <net/tc_act/tc_nat.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/tc_wrapper.h> - -#define NAT_TAB_MASK 15 - -static unsigned int nat_net_id; static struct tc_action_ops act_nat_ops; static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { @@ -39,59 +33,91 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { }; static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, - struct tc_action **a, int ovr, int bind) + struct tc_action **a, struct tcf_proto *tp, + u32 flags, struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, nat_net_id); + struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct tcf_nat_parms *nparm, *oparm; struct nlattr *tb[TCA_NAT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; + u32 index; if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_NAT_MAX, nla, nat_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_NAT_MAX, nla, nat_policy, + NULL); if (err < 0) return err; if (tb[TCA_NAT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - - if (!tcf_hash_check(tn, parm->index, a, bind)) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_nat_ops, bind, false); - if (ret) + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (!err) { + ret = tcf_idr_create_from_flags(tn, index, est, a, &act_nat_ops, + bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { + } else if (err > 0) { if (bind) - return 0; - tcf_hash_release(*a, bind); - if (!ovr) + return ACT_P_BOUND; + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); return -EEXIST; + } + } else { + return err; + } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + nparm = kzalloc(sizeof(*nparm), GFP_KERNEL); + if (!nparm) { + err = -ENOMEM; + goto release_idr; } + + nparm->old_addr = parm->old_addr; + nparm->new_addr = parm->new_addr; + nparm->mask = parm->mask; + nparm->flags = parm->flags; + nparm->action = parm->action; + p = to_tcf_nat(*a); spin_lock_bh(&p->tcf_lock); - p->old_addr = parm->old_addr; - p->new_addr = parm->new_addr; - p->mask = parm->mask; - p->flags = parm->flags; - - p->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + oparm = rcu_replace_pointer(p->parms, nparm, lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + + if (oparm) + kfree_rcu(oparm, rcu); return ret; +release_idr: + tcf_idr_release(*a, bind); + return err; } -static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_nat *p = to_tcf_nat(a); + struct tcf_nat_parms *parms; struct iphdr *iph; __be32 old_addr; __be32 new_addr; @@ -102,22 +128,19 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, int ihl; int noff; - spin_lock(&p->tcf_lock); - tcf_lastuse_update(&p->tcf_tm); - old_addr = p->old_addr; - new_addr = p->new_addr; - mask = p->mask; - egress = p->flags & TCA_NAT_FLAG_EGRESS; - action = p->tcf_action; - - bstats_update(&p->tcf_bstats, skb); - - spin_unlock(&p->tcf_lock); + tcf_action_update_bstats(&p->common, skb); + parms = rcu_dereference_bh(p->parms); + action = parms->action; if (unlikely(action == TC_ACT_SHOT)) goto drop; + old_addr = parms->old_addr; + new_addr = parms->new_addr; + mask = parms->mask; + egress = parms->flags & TCA_NAT_FLAG_EGRESS; + noff = skb_network_offset(skb); if (!pskb_may_pull(skb, sizeof(*iph) + noff)) goto drop; @@ -192,9 +215,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, icmph = (void *)(skb_network_header(skb) + ihl); - if ((icmph->type != ICMP_DEST_UNREACH) && - (icmph->type != ICMP_TIME_EXCEEDED) && - (icmph->type != ICMP_PARAMETERPROB)) + if (!icmp_is_err(icmph->type)) break; if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) + @@ -239,9 +260,7 @@ out: return action; drop: - spin_lock(&p->tcf_lock); - p->tcf_qstats.drops++; - spin_unlock(&p->tcf_lock); + tcf_action_inc_drop_qstats(&p->common); return TC_ACT_SHOT; } @@ -249,80 +268,79 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); - struct tcf_nat *p = to_tcf_nat(a); + const struct tcf_nat *p = to_tcf_nat(a); + const struct tcf_nat_parms *parms; struct tc_nat opt = { - .old_addr = p->old_addr, - .new_addr = p->new_addr, - .mask = p->mask, - .flags = p->flags, - .index = p->tcf_index, - .action = p->tcf_action, - .refcnt = p->tcf_refcnt - ref, - .bindcnt = p->tcf_bindcnt - bind, + .refcnt = refcount_read(&p->tcf_refcnt) - ref, + .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; + rcu_read_lock(); + + parms = rcu_dereference(p->parms); + + opt.action = parms->action; + opt.old_addr = parms->old_addr; + opt.new_addr = parms->new_addr; + opt.mask = parms->mask; + opt.flags = parms->flags; + if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD)) goto nla_put_failure; + rcu_read_unlock(); return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tcf_nat_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static void tcf_nat_cleanup(struct tc_action *a) { - struct tc_action_net *tn = net_generic(net, nat_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, nat_net_id); + struct tcf_nat *p = to_tcf_nat(a); + struct tcf_nat_parms *parms; - return tcf_hash_search(tn, a, index); + parms = rcu_dereference_protected(p->parms, 1); + if (parms) + kfree_rcu(parms, rcu); } static struct tc_action_ops act_nat_ops = { .kind = "nat", - .type = TCA_ACT_NAT, + .id = TCA_ID_NAT, .owner = THIS_MODULE, - .act = tcf_nat, + .act = tcf_nat_act, .dump = tcf_nat_dump, .init = tcf_nat_init, - .walk = tcf_nat_walker, - .lookup = tcf_nat_search, + .cleanup = tcf_nat_cleanup, .size = sizeof(struct tcf_nat), }; +MODULE_ALIAS_NET_ACT("nat"); static __net_init int nat_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, nat_net_id); + struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id); - return tc_action_net_init(tn, &act_nat_ops, NAT_TAB_MASK); + return tc_action_net_init(net, tn, &act_nat_ops); } -static void __net_exit nat_exit_net(struct net *net) +static void __net_exit nat_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, nat_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_nat_ops.net_id); } static struct pernet_operations nat_net_ops = { .init = nat_init_net, - .exit = nat_exit_net, - .id = &nat_net_id, + .exit_batch = nat_exit_net, + .id = &act_nat_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 7dc5892671c8..4b65901397a8 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_pedit.c Generic packet editor * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Jamal Hadi Salim (2002-4) */ @@ -17,30 +13,34 @@ #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/slab.h> +#include <net/ipv6.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_pedit.h> #include <net/tc_act/tc_pedit.h> #include <uapi/linux/tc_act/tc_pedit.h> +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> -#define PEDIT_TAB_MASK 15 - -static unsigned int pedit_net_id; static struct tc_action_ops act_pedit_ops; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, + [TCA_PEDIT_PARMS_EX] = { .len = sizeof(struct tc_pedit) }, [TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED }, }; static const struct nla_policy pedit_key_ex_policy[TCA_PEDIT_KEY_EX_MAX + 1] = { - [TCA_PEDIT_KEY_EX_HTYPE] = { .type = NLA_U16 }, - [TCA_PEDIT_KEY_EX_CMD] = { .type = NLA_U16 }, + [TCA_PEDIT_KEY_EX_HTYPE] = + NLA_POLICY_MAX(NLA_U16, TCA_PEDIT_HDR_TYPE_MAX), + [TCA_PEDIT_KEY_EX_CMD] = NLA_POLICY_MAX(NLA_U16, TCA_PEDIT_CMD_MAX), }; static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, - u8 n) + u8 n, struct netlink_ext_ack *extack) { struct tcf_pedit_key_ex *keys_ex; struct tcf_pedit_key_ex *k; @@ -48,7 +48,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, int err = -EINVAL; int rem; - if (!nla || !n) + if (!nla) return NULL; keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL); @@ -61,40 +61,44 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, struct nlattr *tb[TCA_PEDIT_KEY_EX_MAX + 1]; if (!n) { + NL_SET_ERR_MSG_MOD(extack, "Can't parse more extended keys than requested"); err = -EINVAL; goto err_out; } n--; if (nla_type(ka) != TCA_PEDIT_KEY_EX) { + NL_SET_ERR_MSG_ATTR(extack, ka, "Unknown attribute, expected extended key"); err = -EINVAL; goto err_out; } - err = nla_parse_nested(tb, TCA_PEDIT_KEY_EX_MAX, ka, - pedit_key_ex_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_PEDIT_KEY_EX_MAX, + ka, pedit_key_ex_policy, + NULL); if (err) goto err_out; - if (!tb[TCA_PEDIT_KEY_EX_HTYPE] || - !tb[TCA_PEDIT_KEY_EX_CMD]) { + if (NL_REQ_ATTR_CHECK(extack, nla, tb, TCA_PEDIT_KEY_EX_HTYPE)) { + NL_SET_ERR_MSG(extack, "Missing required attribute"); err = -EINVAL; goto err_out; } - k->htype = nla_get_u16(tb[TCA_PEDIT_KEY_EX_HTYPE]); - k->cmd = nla_get_u16(tb[TCA_PEDIT_KEY_EX_CMD]); - - if (k->htype > TCA_PEDIT_HDR_TYPE_MAX || - k->cmd > TCA_PEDIT_CMD_MAX) { + if (NL_REQ_ATTR_CHECK(extack, nla, tb, TCA_PEDIT_KEY_EX_CMD)) { + NL_SET_ERR_MSG(extack, "Missing required attribute"); err = -EINVAL; goto err_out; } + k->htype = nla_get_u16(tb[TCA_PEDIT_KEY_EX_HTYPE]); + k->cmd = nla_get_u16(tb[TCA_PEDIT_KEY_EX_CMD]); + k++; } if (n) { + NL_SET_ERR_MSG_MOD(extack, "Not enough extended keys to parse"); err = -EINVAL; goto err_out; } @@ -109,18 +113,21 @@ err_out: static int tcf_pedit_key_ex_dump(struct sk_buff *skb, struct tcf_pedit_key_ex *keys_ex, int n) { - struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX); + struct nlattr *keys_start = nla_nest_start_noflag(skb, + TCA_PEDIT_KEYS_EX); + if (!keys_start) + goto nla_failure; for (; n > 0; n--) { struct nlattr *key_start; - key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX); + key_start = nla_nest_start_noflag(skb, TCA_PEDIT_KEY_EX); + if (!key_start) + goto nla_failure; if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) || - nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) { - nlmsg_trim(skb, keys_start); - return -EINVAL; - } + nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) + goto nla_failure; nla_nest_end(skb, key_start); @@ -130,100 +137,185 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, nla_nest_end(skb, keys_start); return 0; +nla_failure: + nla_nest_cancel(skb, keys_start); + return -EINVAL; +} + +static void tcf_pedit_cleanup_rcu(struct rcu_head *head) +{ + struct tcf_pedit_parms *parms = + container_of(head, struct tcf_pedit_parms, rcu); + + kfree(parms->tcfp_keys_ex); + kfree(parms->tcfp_keys); + + kfree(parms); } static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, pedit_net_id); + struct tc_action_net *tn = net_generic(net, act_pedit_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct tcf_chain *goto_ch = NULL; + struct tcf_pedit_parms *oparms, *nparms; struct nlattr *tb[TCA_PEDIT_MAX + 1]; - struct nlattr *pattr; struct tc_pedit *parm; - int ret = 0, err; + struct nlattr *pattr; struct tcf_pedit *p; - struct tc_pedit_key *keys = NULL; - struct tcf_pedit_key_ex *keys_ex; - int ksize; + int ret = 0, err; + int i, ksize; + u32 index; - if (nla == NULL) + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed"); return -EINVAL; + } - err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_PEDIT_MAX, nla, + pedit_policy, NULL); if (err < 0) return err; pattr = tb[TCA_PEDIT_PARMS]; if (!pattr) pattr = tb[TCA_PEDIT_PARMS_EX]; - if (!pattr) + if (!pattr) { + NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute"); return -EINVAL; + } parm = nla_data(pattr); - ksize = parm->nkeys * sizeof(struct tc_pedit_key); - if (nla_len(pattr) < sizeof(*parm) + ksize) - return -EINVAL; - keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys); - if (IS_ERR(keys_ex)) - return PTR_ERR(keys_ex); - - if (!tcf_hash_check(tn, parm->index, a, bind)) { - if (!parm->nkeys) - return -EINVAL; - ret = tcf_hash_create(tn, parm->index, est, a, - &act_pedit_ops, bind, false); - if (ret) + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (!err) { + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_pedit_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; - p = to_pedit(*a); - keys = kmalloc(ksize, GFP_KERNEL); - if (keys == NULL) { - tcf_hash_cleanup(*a, est); - kfree(keys_ex); - return -ENOMEM; } ret = ACT_P_CREATED; - } else { + } else if (err > 0) { if (bind) - return 0; - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; - p = to_pedit(*a); - if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) { - keys = kmalloc(ksize, GFP_KERNEL); - if (!keys) { - kfree(keys_ex); - return -ENOMEM; - } + return ACT_P_BOUND; + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + ret = -EEXIST; + goto out_release; } + } else { + return err; } - spin_lock_bh(&p->tcf_lock); - p->tcfp_flags = parm->flags; - p->tcf_action = parm->action; - if (keys) { - kfree(p->tcfp_keys); - p->tcfp_keys = keys; - p->tcfp_nkeys = parm->nkeys; + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); + ret = -EINVAL; + goto out_release; } - memcpy(p->tcfp_keys, parm->keys, ksize); + ksize = parm->nkeys * sizeof(struct tc_pedit_key); + if (nla_len(pattr) < sizeof(*parm) + ksize) { + NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); + ret = -EINVAL; + goto out_release; + } + + nparms = kzalloc(sizeof(*nparms), GFP_KERNEL); + if (!nparms) { + ret = -ENOMEM; + goto out_release; + } + + nparms->tcfp_keys_ex = + tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys, extack); + if (IS_ERR(nparms->tcfp_keys_ex)) { + ret = PTR_ERR(nparms->tcfp_keys_ex); + goto out_free; + } + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) { + ret = err; + goto out_free_ex; + } + + nparms->tcfp_off_max_hint = 0; + nparms->tcfp_flags = parm->flags; + nparms->tcfp_nkeys = parm->nkeys; + + nparms->tcfp_keys = kmemdup(parm->keys, ksize, GFP_KERNEL); + if (!nparms->tcfp_keys) { + ret = -ENOMEM; + goto put_chain; + } + + for (i = 0; i < nparms->tcfp_nkeys; ++i) { + u32 offmask = nparms->tcfp_keys[i].offmask; + u32 cur = nparms->tcfp_keys[i].off; + + /* The AT option can be added to static offsets in the datapath */ + if (!offmask && cur % 4) { + NL_SET_ERR_MSG_MOD(extack, "Offsets must be on 32bit boundaries"); + ret = -EINVAL; + goto out_free_keys; + } + + /* sanitize the shift value for any later use */ + nparms->tcfp_keys[i].shift = min_t(size_t, + BITS_PER_TYPE(int) - 1, + nparms->tcfp_keys[i].shift); - kfree(p->tcfp_keys_ex); - p->tcfp_keys_ex = keys_ex; + /* The AT option can read a single byte, we can bound the actual + * value with uchar max. + */ + cur += (0xff & offmask) >> nparms->tcfp_keys[i].shift; + /* Each key touches 4 bytes starting from the computed offset */ + nparms->tcfp_off_max_hint = + max(nparms->tcfp_off_max_hint, cur + 4); + } + + p = to_pedit(*a); + nparms->action = parm->action; + spin_lock_bh(&p->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + oparms = rcu_replace_pointer(p->parms, nparms, 1); spin_unlock_bh(&p->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); + + if (oparms) + call_rcu(&oparms->rcu, tcf_pedit_cleanup_rcu); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + + return ret; + +out_free_keys: + kfree(nparms->tcfp_keys); +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +out_free_ex: + kfree(nparms->tcfp_keys_ex); +out_free: + kfree(nparms); +out_release: + tcf_idr_release(*a, bind); return ret; } -static void tcf_pedit_cleanup(struct tc_action *a, int bind) +static void tcf_pedit_cleanup(struct tc_action *a) { struct tcf_pedit *p = to_pedit(a); - struct tc_pedit_key *keys = p->tcfp_keys; - kfree(keys); - kfree(p->tcfp_keys_ex); + struct tcf_pedit_parms *parms; + + parms = rcu_dereference_protected(p->parms, 1); + + if (parms) + call_rcu(&parms->rcu, tcf_pedit_cleanup_rcu); } static bool offset_valid(struct sk_buff *skb, int offset) @@ -237,11 +329,35 @@ static bool offset_valid(struct sk_buff *skb, int offset) return true; } -static int pedit_skb_hdr_offset(struct sk_buff *skb, - enum pedit_header_type htype, int *hoffset) +static int pedit_l4_skb_offset(struct sk_buff *skb, int *hoffset, const int header_type) { + const int noff = skb_network_offset(skb); int ret = -EINVAL; + struct iphdr _iph; + + switch (skb->protocol) { + case htons(ETH_P_IP): { + const struct iphdr *iph = skb_header_pointer(skb, noff, sizeof(_iph), &_iph); + + if (!iph) + goto out; + *hoffset = noff + iph->ihl * 4; + ret = 0; + break; + } + case htons(ETH_P_IPV6): + ret = ipv6_find_hdr(skb, hoffset, header_type, NULL, NULL) == header_type ? 0 : -EINVAL; + break; + } +out: + return ret; +} +static int pedit_skb_hdr_offset(struct sk_buff *skb, + enum pedit_header_type htype, int *hoffset) +{ + int ret = -EINVAL; + /* 'htype' is validated in the netlink parsing */ switch (htype) { case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: if (skb_mac_header_was_set(skb)) { @@ -256,148 +372,163 @@ static int pedit_skb_hdr_offset(struct sk_buff *skb, ret = 0; break; case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + ret = pedit_l4_skb_offset(skb, hoffset, IPPROTO_TCP); + break; case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: - if (skb_transport_header_was_set(skb)) { - *hoffset = skb_transport_offset(skb); - ret = 0; - } + ret = pedit_l4_skb_offset(skb, hoffset, IPPROTO_UDP); break; default: - ret = -EINVAL; break; - }; - + } return ret; } -static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { + enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; + enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET; struct tcf_pedit *p = to_pedit(a); + struct tcf_pedit_key_ex *tkey_ex; + struct tcf_pedit_parms *parms; + struct tc_pedit_key *tkey; + u32 max_offset; int i; - if (skb_unclone(skb, GFP_ATOMIC)) - return p->tcf_action; + parms = rcu_dereference_bh(p->parms); - spin_lock(&p->tcf_lock); + max_offset = (skb_transport_header_was_set(skb) ? + skb_transport_offset(skb) : + skb_network_offset(skb)) + + parms->tcfp_off_max_hint; + if (skb_ensure_writable(skb, min(skb->len, max_offset))) + goto done; tcf_lastuse_update(&p->tcf_tm); + tcf_action_update_bstats(&p->common, skb); - if (p->tcfp_nkeys > 0) { - struct tc_pedit_key *tkey = p->tcfp_keys; - struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex; - enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; - enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET; + tkey = parms->tcfp_keys; + tkey_ex = parms->tcfp_keys_ex; - for (i = p->tcfp_nkeys; i > 0; i--, tkey++) { - u32 *ptr, _data; - int offset = tkey->off; - int hoffset; - u32 val; - int rc; + for (i = parms->tcfp_nkeys; i > 0; i--, tkey++) { + int offset = tkey->off; + int hoffset = 0; + u32 *ptr, hdata; + u32 val; + int rc; - if (tkey_ex) { - htype = tkey_ex->htype; - cmd = tkey_ex->cmd; + if (tkey_ex) { + htype = tkey_ex->htype; + cmd = tkey_ex->cmd; - tkey_ex++; - } + tkey_ex++; + } - rc = pedit_skb_hdr_offset(skb, htype, &hoffset); - if (rc) { - pr_info("tc filter pedit bad header type specified (0x%x)\n", - htype); - goto bad; - } + rc = pedit_skb_hdr_offset(skb, htype, &hoffset); + if (rc) { + pr_info_ratelimited("tc action pedit unable to extract header offset for header type (0x%x)\n", htype); + goto bad; + } - if (tkey->offmask) { - char *d, _d; - - if (!offset_valid(skb, hoffset + tkey->at)) { - pr_info("tc filter pedit 'at' offset %d out of bounds\n", - hoffset + tkey->at); - goto bad; - } - d = skb_header_pointer(skb, hoffset + tkey->at, 1, - &_d); - if (!d) - goto bad; - offset += (*d & tkey->offmask) >> tkey->shift; - } + if (tkey->offmask) { + u8 *d, _d; - if (offset % 4) { - pr_info("tc filter pedit" - " offset must be on 32 bit boundaries\n"); + if (!offset_valid(skb, hoffset + tkey->at)) { + pr_info_ratelimited("tc action pedit 'at' offset %d out of bounds\n", + hoffset + tkey->at); goto bad; } - - if (!offset_valid(skb, hoffset + offset)) { - pr_info("tc filter pedit offset %d out of bounds\n", - hoffset + offset); + d = skb_header_pointer(skb, hoffset + tkey->at, + sizeof(_d), &_d); + if (!d) goto bad; - } - ptr = skb_header_pointer(skb, hoffset + offset, 4, &_data); - if (!ptr) - goto bad; - /* just do it, baby */ - switch (cmd) { - case TCA_PEDIT_KEY_EX_CMD_SET: - val = tkey->val; - break; - case TCA_PEDIT_KEY_EX_CMD_ADD: - val = (*ptr + tkey->val) & ~tkey->mask; - break; - default: - pr_info("tc filter pedit bad command (%d)\n", - cmd); + offset += (*d & tkey->offmask) >> tkey->shift; + if (offset % 4) { + pr_info_ratelimited("tc action pedit offset must be on 32 bit boundaries\n"); goto bad; } + } - *ptr = ((*ptr & tkey->mask) ^ val); - if (ptr == &_data) - skb_store_bits(skb, hoffset + offset, ptr, 4); + if (!offset_valid(skb, hoffset + offset)) { + pr_info_ratelimited("tc action pedit offset %d out of bounds\n", hoffset + offset); + goto bad; } - goto done; - } else - WARN(1, "pedit BUG: index %d\n", p->tcf_index); + ptr = skb_header_pointer(skb, hoffset + offset, + sizeof(hdata), &hdata); + if (!ptr) + goto bad; + /* just do it, baby */ + switch (cmd) { + case TCA_PEDIT_KEY_EX_CMD_SET: + val = tkey->val; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + val = (*ptr + tkey->val) & ~tkey->mask; + break; + default: + pr_info_ratelimited("tc action pedit bad command (%d)\n", cmd); + goto bad; + } + + *ptr = ((*ptr & tkey->mask) ^ val); + if (ptr == &hdata) + skb_store_bits(skb, hoffset + offset, ptr, 4); + } + + goto done; bad: - p->tcf_qstats.overlimits++; + tcf_action_inc_overlimit_qstats(&p->common); done: - bstats_update(&p->tcf_bstats, skb); - spin_unlock(&p->tcf_lock); - return p->tcf_action; + return parms->action; +} + +static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) +{ + struct tcf_pedit *d = to_pedit(a); + struct tcf_t *tm = &d->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); - struct tcf_pedit *p = to_pedit(a); + const struct tcf_pedit *p = to_pedit(a); + const struct tcf_pedit_parms *parms; struct tc_pedit *opt; struct tcf_t t; int s; - s = sizeof(*opt) + p->tcfp_nkeys * sizeof(struct tc_pedit_key); + rcu_read_lock(); + parms = rcu_dereference(p->parms); + s = struct_size(opt, keys, parms->tcfp_nkeys); - /* netlink spinlocks held above us - must use ATOMIC */ opt = kzalloc(s, GFP_ATOMIC); - if (unlikely(!opt)) + if (unlikely(!opt)) { + rcu_read_unlock(); return -ENOBUFS; + } + opt->nkeys = parms->tcfp_nkeys; - memcpy(opt->keys, p->tcfp_keys, - p->tcfp_nkeys * sizeof(struct tc_pedit_key)); + memcpy(opt->keys, parms->tcfp_keys, + flex_array_size(opt, keys, parms->tcfp_nkeys)); opt->index = p->tcf_index; - opt->nkeys = p->tcfp_nkeys; - opt->flags = p->tcfp_flags; - opt->action = p->tcf_action; - opt->refcnt = p->tcf_refcnt - ref; - opt->bindcnt = p->tcf_bindcnt - bind; - - if (p->tcfp_keys_ex) { - tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys); + opt->flags = parms->tcfp_flags; + opt->action = parms->action; + opt->refcnt = refcount_read(&p->tcf_refcnt) - ref; + opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind; + + if (parms->tcfp_keys_ex) { + if (tcf_pedit_key_ex_dump(skb, parms->tcfp_keys_ex, + parms->tcfp_nkeys)) + goto nla_put_failure; if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt)) goto nla_put_failure; @@ -409,63 +540,104 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD)) goto nla_put_failure; + rcu_read_unlock(); kfree(opt); return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); kfree(opt); return -1; } -static int tcf_pedit_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, pedit_net_id); + if (bind) { + struct flow_action_entry *entry = entry_data; + int k; - return tcf_generic_walker(tn, skb, cb, type, ops); -} + for (k = 0; k < tcf_pedit_nkeys(act); k++) { + switch (tcf_pedit_cmd(act, k)) { + case TCA_PEDIT_KEY_EX_CMD_SET: + entry->id = FLOW_ACTION_MANGLE; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + entry->id = FLOW_ACTION_ADD; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload"); + return -EOPNOTSUPP; + } + entry->mangle.htype = tcf_pedit_htype(act, k); + entry->mangle.mask = tcf_pedit_mask(act, k); + entry->mangle.val = tcf_pedit_val(act, k); + entry->mangle.offset = tcf_pedit_offset(act, k); + entry->hw_stats = tc_act_hw_stats(act->hw_stats); + entry++; + } + *index_inc = k; + } else { + struct flow_offload_action *fl_action = entry_data; + u32 cmd = tcf_pedit_cmd(act, 0); + int k; + + switch (cmd) { + case TCA_PEDIT_KEY_EX_CMD_SET: + fl_action->id = FLOW_ACTION_MANGLE; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + fl_action->id = FLOW_ACTION_ADD; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload"); + return -EOPNOTSUPP; + } -static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, pedit_net_id); + for (k = 1; k < tcf_pedit_nkeys(act); k++) { + if (cmd != tcf_pedit_cmd(act, k)) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload"); + return -EOPNOTSUPP; + } + } + } - return tcf_hash_search(tn, a, index); + return 0; } static struct tc_action_ops act_pedit_ops = { .kind = "pedit", - .type = TCA_ACT_PEDIT, + .id = TCA_ID_PEDIT, .owner = THIS_MODULE, - .act = tcf_pedit, + .act = tcf_pedit_act, + .stats_update = tcf_pedit_stats_update, .dump = tcf_pedit_dump, .cleanup = tcf_pedit_cleanup, .init = tcf_pedit_init, - .walk = tcf_pedit_walker, - .lookup = tcf_pedit_search, + .offload_act_setup = tcf_pedit_offload_act_setup, .size = sizeof(struct tcf_pedit), }; +MODULE_ALIAS_NET_ACT("pedit"); static __net_init int pedit_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, pedit_net_id); + struct tc_action_net *tn = net_generic(net, act_pedit_ops.net_id); - return tc_action_net_init(tn, &act_pedit_ops, PEDIT_TAB_MASK); + return tc_action_net_init(net, tn, &act_pedit_ops); } -static void __net_exit pedit_exit_net(struct net *net) +static void __net_exit pedit_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, pedit_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_pedit_ops.net_id); } static struct pernet_operations pedit_net_ops = { .init = pedit_init_net, - .exit = pedit_exit_net, - .id = &pedit_net_id, + .exit_batch = pedit_exit_net, + .id = &act_pedit_ops.net_id, .size = sizeof(struct tc_action_net), }; @@ -485,4 +657,3 @@ static void __exit pedit_cleanup_module(void) module_init(pedit_init_module); module_exit(pedit_cleanup_module); - diff --git a/net/sched/act_police.c b/net/sched/act_police.c index b062bc80c7cb..0e1c61183379 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_police.c Input police filter * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * J Hadi Salim (action changes) */ @@ -20,77 +16,51 @@ #include <linux/init.h> #include <linux/slab.h> #include <net/act_api.h> +#include <net/gso.h> #include <net/netlink.h> - -struct tcf_police { - struct tc_action common; - int tcfp_result; - u32 tcfp_ewma_rate; - s64 tcfp_burst; - u32 tcfp_mtu; - s64 tcfp_toks; - s64 tcfp_ptoks; - s64 tcfp_mtu_ptoks; - s64 tcfp_t_c; - struct psched_ratecfg rate; - bool rate_present; - struct psched_ratecfg peak; - bool peak_present; -}; - -#define to_police(pc) ((struct tcf_police *)pc) - -#define POL_TAB_MASK 15 - -/* old policer structure from before tc actions */ -struct tc_police_compat { - u32 index; - int action; - u32 limit; - u32 burst; - u32 mtu; - struct tc_ratespec rate; - struct tc_ratespec peakrate; -}; +#include <net/pkt_cls.h> +#include <net/tc_act/tc_police.h> +#include <net/tc_wrapper.h> /* Each policer is serialized by its individual spinlock */ -static unsigned int police_net_id; static struct tc_action_ops act_police_ops; -static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, police_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_PEAKRATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_AVRATE] = { .type = NLA_U32 }, [TCA_POLICE_RESULT] = { .type = NLA_U32 }, + [TCA_POLICE_RATE64] = { .type = NLA_U64 }, + [TCA_POLICE_PEAKRATE64] = { .type = NLA_U64 }, + [TCA_POLICE_PKTRATE64] = { .type = NLA_U64, .min = 1 }, + [TCA_POLICE_PKTBURST64] = { .type = NLA_U64, .min = 1 }, }; -static int tcf_act_police_init(struct net *net, struct nlattr *nla, +static int tcf_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - int ret = 0, err; + int ret = 0, tcfp_result = TC_ACT_OK, err, size; + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_POLICE_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; - struct tc_action_net *tn = net_generic(net, police_net_id); + struct tc_action_net *tn = net_generic(net, act_police_ops.net_id); + struct tcf_police_params *new; bool exists = false; - int size; + u32 index; + u64 rate64, prate64; + u64 pps, ppsburst; if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_POLICE_MAX, nla, police_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_POLICE_MAX, nla, + police_policy, NULL); if (err < 0) return err; @@ -101,42 +71,52 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); - exists = tcf_hash_check(tn, parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; if (!exists) { - ret = tcf_hash_create(tn, parm->index, NULL, a, - &act_police_ops, bind, false); - if (ret) + ret = tcf_idr_create(tn, index, NULL, a, + &act_police_ops, bind, true, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + spin_lock_init(&(to_police(*a)->tcfp_lock)); + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; - R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE]); + R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE], NULL); if (R_tab == NULL) goto failure; if (parm->peakrate.rate) { P_tab = qdisc_get_rtab(&parm->peakrate, - tb[TCA_POLICE_PEAKRATE]); + tb[TCA_POLICE_PEAKRATE], NULL); if (P_tab == NULL) goto failure; } } if (est) { - err = gen_replace_estimator(&police->tcf_bstats, NULL, + err = gen_replace_estimator(&police->tcf_bstats, + police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, - NULL, est); + false, est); if (err) goto failure; } else if (tb[TCA_POLICE_AVRATE] && @@ -146,171 +126,362 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, goto failure; } - spin_lock_bh(&police->tcf_lock); + if (tb[TCA_POLICE_RESULT]) { + tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { + NL_SET_ERR_MSG(extack, + "goto chain not allowed on fallback"); + err = -EINVAL; + goto failure; + } + } + + if ((tb[TCA_POLICE_PKTRATE64] && !tb[TCA_POLICE_PKTBURST64]) || + (!tb[TCA_POLICE_PKTRATE64] && tb[TCA_POLICE_PKTBURST64])) { + NL_SET_ERR_MSG(extack, + "Both or neither packet-per-second burst and rate must be provided"); + err = -EINVAL; + goto failure; + } + + if (tb[TCA_POLICE_PKTRATE64] && R_tab) { + NL_SET_ERR_MSG(extack, + "packet-per-second and byte-per-second rate limits not allowed in same action"); + err = -EINVAL; + goto failure; + } + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (unlikely(!new)) { + err = -ENOMEM; + goto failure; + } + /* No failure allowed after this point */ - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; + new->tcfp_result = tcfp_result; + new->tcfp_mtu = parm->mtu; + if (!new->tcfp_mtu) { + new->tcfp_mtu = ~0; if (R_tab) - police->tcfp_mtu = 255 << R_tab->rate.cell_log; + new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { - police->rate_present = true; - psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0); + new->rate_present = true; + rate64 = nla_get_u64_default(tb[TCA_POLICE_RATE64], 0); + psched_ratecfg_precompute(&new->rate, &R_tab->rate, rate64); qdisc_put_rtab(R_tab); } else { - police->rate_present = false; + new->rate_present = false; } if (P_tab) { - police->peak_present = true; - psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0); + new->peak_present = true; + prate64 = nla_get_u64_default(tb[TCA_POLICE_PEAKRATE64], 0); + psched_ratecfg_precompute(&new->peak, &P_tab->rate, prate64); qdisc_put_rtab(P_tab); } else { - police->peak_present = false; + new->peak_present = false; } - if (tb[TCA_POLICE_RESULT]) - police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); - police->tcfp_burst = PSCHED_TICKS2NS(parm->burst); - police->tcfp_toks = police->tcfp_burst; - if (police->peak_present) { - police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak, - police->tcfp_mtu); - police->tcfp_ptoks = police->tcfp_mtu_ptoks; - } - police->tcf_action = parm->action; + new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); + if (new->peak_present) + new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, + new->tcfp_mtu); if (tb[TCA_POLICE_AVRATE]) - police->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + + if (tb[TCA_POLICE_PKTRATE64]) { + pps = nla_get_u64(tb[TCA_POLICE_PKTRATE64]); + ppsburst = nla_get_u64(tb[TCA_POLICE_PKTBURST64]); + new->pps_present = true; + new->tcfp_pkt_burst = PSCHED_TICKS2NS(ppsburst); + psched_ppscfg_precompute(&new->ppsrate, pps); + } + new->action = parm->action; + spin_lock_bh(&police->tcf_lock); + spin_lock_bh(&police->tcfp_lock); + police->tcfp_t_c = ktime_get_ns(); + police->tcfp_toks = new->tcfp_burst; + if (new->peak_present) + police->tcfp_ptoks = new->tcfp_mtu_ptoks; + spin_unlock_bh(&police->tcfp_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + new = rcu_replace_pointer(police->params, + new, + lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); - if (ret != ACT_P_CREATED) - return ret; - police->tcfp_t_c = ktime_get_ns(); - tcf_hash_insert(tn, *a); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (new) + kfree_rcu(new, rcu); return ret; failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); - if (ret == ACT_P_CREATED) - tcf_hash_cleanup(*a, est); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); return err; } -static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +static bool tcf_police_mtu_check(struct sk_buff *skb, u32 limit) { - struct tcf_police *police = to_police(a); - s64 now; - s64 toks; - s64 ptoks = 0; + u32 len; + + if (skb_is_gso(skb)) + return skb_gso_validate_mac_len(skb, limit); - spin_lock(&police->tcf_lock); + len = qdisc_pkt_len(skb); + if (skb_at_tc_ingress(skb)) + len += skb->mac_len; + + return len <= limit; +} + +TC_INDIRECT_SCOPE int tcf_police_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_police *police = to_police(a); + s64 now, toks, ppstoks = 0, ptoks = 0; + struct tcf_police_params *p; + int ret; - bstats_update(&police->tcf_bstats, skb); tcf_lastuse_update(&police->tcf_tm); + bstats_update(this_cpu_ptr(police->common.cpu_bstats), skb); + + p = rcu_dereference_bh(police->params); + ret = p->action; - if (police->tcfp_ewma_rate) { + if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || - sample.bps >= police->tcfp_ewma_rate) { - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; - } + sample.bps >= p->tcfp_ewma_rate) + goto inc_overlimits; } - if (qdisc_pkt_len(skb) <= police->tcfp_mtu) { - if (!police->rate_present) { - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + if (tcf_police_mtu_check(skb, p->tcfp_mtu)) { + if (!p->rate_present && !p->pps_present) { + ret = p->tcfp_result; + goto end; } now = ktime_get_ns(); - toks = min_t(s64, now - police->tcfp_t_c, - police->tcfp_burst); - if (police->peak_present) { + spin_lock_bh(&police->tcfp_lock); + toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst); + if (p->peak_present) { ptoks = toks + police->tcfp_ptoks; - if (ptoks > police->tcfp_mtu_ptoks) - ptoks = police->tcfp_mtu_ptoks; - ptoks -= (s64) psched_l2t_ns(&police->peak, - qdisc_pkt_len(skb)); + if (ptoks > p->tcfp_mtu_ptoks) + ptoks = p->tcfp_mtu_ptoks; + ptoks -= (s64)psched_l2t_ns(&p->peak, + qdisc_pkt_len(skb)); + } + if (p->rate_present) { + toks += police->tcfp_toks; + if (toks > p->tcfp_burst) + toks = p->tcfp_burst; + toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); + } else if (p->pps_present) { + ppstoks = min_t(s64, now - police->tcfp_t_c, p->tcfp_pkt_burst); + ppstoks += police->tcfp_pkttoks; + if (ppstoks > p->tcfp_pkt_burst) + ppstoks = p->tcfp_pkt_burst; + ppstoks -= (s64)psched_pkt2t_ns(&p->ppsrate, 1); } - toks += police->tcfp_toks; - if (toks > police->tcfp_burst) - toks = police->tcfp_burst; - toks -= (s64) psched_l2t_ns(&police->rate, qdisc_pkt_len(skb)); - if ((toks|ptoks) >= 0) { + if ((toks | ptoks | ppstoks) >= 0) { police->tcfp_t_c = now; police->tcfp_toks = toks; police->tcfp_ptoks = ptoks; - if (police->tcfp_result == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + police->tcfp_pkttoks = ppstoks; + spin_unlock_bh(&police->tcfp_lock); + ret = p->tcfp_result; + goto inc_drops; } + spin_unlock_bh(&police->tcfp_lock); } - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; +inc_overlimits: + qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); +inc_drops: + if (ret == TC_ACT_SHOT) + qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); +end: + return ret; +} + +static void tcf_police_cleanup(struct tc_action *a) +{ + struct tcf_police *police = to_police(a); + struct tcf_police_params *p; + + p = rcu_dereference_protected(police->params, 1); + if (p) + kfree_rcu(p, rcu); +} + +static void tcf_police_stats_update(struct tc_action *a, + u64 bytes, u64 packets, u64 drops, + u64 lastuse, bool hw) +{ + struct tcf_police *police = to_police(a); + struct tcf_t *tm = &police->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } -static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, +static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { + const struct tcf_police *police = to_police(a); unsigned char *b = skb_tail_pointer(skb); - struct tcf_police *police = to_police(a); + const struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, - .action = police->tcf_action, - .mtu = police->tcfp_mtu, - .burst = PSCHED_NS2TICKS(police->tcfp_burst), - .refcnt = police->tcf_refcnt - ref, - .bindcnt = police->tcf_bindcnt - bind, + .refcnt = refcount_read(&police->tcf_refcnt) - ref, + .bindcnt = atomic_read(&police->tcf_bindcnt) - bind, }; struct tcf_t t; - if (police->rate_present) - psched_ratecfg_getrate(&opt.rate, &police->rate); - if (police->peak_present) - psched_ratecfg_getrate(&opt.peakrate, &police->peak); + rcu_read_lock(); + p = rcu_dereference(police->params); + opt.action = p->action; + opt.mtu = p->tcfp_mtu; + opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); + if (p->rate_present) { + psched_ratecfg_getrate(&opt.rate, &p->rate); + if ((p->rate.rate_bytes_ps >= (1ULL << 32)) && + nla_put_u64_64bit(skb, TCA_POLICE_RATE64, + p->rate.rate_bytes_ps, + TCA_POLICE_PAD)) + goto nla_put_failure; + } + if (p->peak_present) { + psched_ratecfg_getrate(&opt.peakrate, &p->peak); + if ((p->peak.rate_bytes_ps >= (1ULL << 32)) && + nla_put_u64_64bit(skb, TCA_POLICE_PEAKRATE64, + p->peak.rate_bytes_ps, + TCA_POLICE_PAD)) + goto nla_put_failure; + } + if (p->pps_present) { + if (nla_put_u64_64bit(skb, TCA_POLICE_PKTRATE64, + p->ppsrate.rate_pkts_ps, + TCA_POLICE_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, TCA_POLICE_PKTBURST64, + PSCHED_NS2TICKS(p->tcfp_pkt_burst), + TCA_POLICE_PAD)) + goto nla_put_failure; + } if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; - if (police->tcfp_result && - nla_put_u32(skb, TCA_POLICE_RESULT, police->tcfp_result)) + if (p->tcfp_result && + nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; - if (police->tcfp_ewma_rate && - nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate)) + if (p->tcfp_ewma_rate && + nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse); - t.firstuse = jiffies_to_clock_t(jiffies - police->tcf_tm.firstuse); - t.expires = jiffies_to_clock_t(police->tcf_tm.expires); + tcf_tm_dump(&t, &police->tcf_tm); if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD)) goto nla_put_failure; + rcu_read_unlock(); return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_police_act_to_flow_act(int tc_act, u32 *extval, + struct netlink_ext_ack *extack) +{ + int act_id = -EOPNOTSUPP; + + if (!TC_ACT_EXT_OPCODE(tc_act)) { + if (tc_act == TC_ACT_OK) + act_id = FLOW_ACTION_ACCEPT; + else if (tc_act == TC_ACT_SHOT) + act_id = FLOW_ACTION_DROP; + else if (tc_act == TC_ACT_PIPE) + act_id = FLOW_ACTION_PIPE; + else if (tc_act == TC_ACT_RECLASSIFY) + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when conform/exceed action is \"reclassify\""); + else + NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload"); + } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_GOTO_CHAIN)) { + act_id = FLOW_ACTION_GOTO; + *extval = tc_act & TC_ACT_EXT_VAL_MASK; + } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_JUMP)) { + act_id = FLOW_ACTION_JUMP; + *extval = tc_act & TC_ACT_EXT_VAL_MASK; + } else if (tc_act == TC_ACT_UNSPEC) { + act_id = FLOW_ACTION_CONTINUE; + } else { + NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload"); + } + + return act_id; +} + +static int tcf_police_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, police_net_id); + if (bind) { + struct flow_action_entry *entry = entry_data; + struct tcf_police *police = to_police(act); + struct tcf_police_params *p; + int act_id; + + p = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + + entry->id = FLOW_ACTION_POLICE; + entry->police.burst = tcf_police_burst(act); + entry->police.rate_bytes_ps = + tcf_police_rate_bytes_ps(act); + entry->police.peakrate_bytes_ps = tcf_police_peakrate_bytes_ps(act); + entry->police.avrate = tcf_police_tcfp_ewma_rate(act); + entry->police.overhead = tcf_police_rate_overhead(act); + entry->police.burst_pkt = tcf_police_burst_pkt(act); + entry->police.rate_pkt_ps = + tcf_police_rate_pkt_ps(act); + entry->police.mtu = tcf_police_tcfp_mtu(act); + + act_id = tcf_police_act_to_flow_act(police->tcf_action, + &entry->police.exceed.extval, + extack); + if (act_id < 0) + return act_id; + + entry->police.exceed.act_id = act_id; + + act_id = tcf_police_act_to_flow_act(p->tcfp_result, + &entry->police.notexceed.extval, + extack); + if (act_id < 0) + return act_id; + + entry->police.notexceed.act_id = act_id; + + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_POLICE; + } - return tcf_hash_search(tn, a, index); + return 0; } MODULE_AUTHOR("Alexey Kuznetsov"); @@ -319,34 +490,34 @@ MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", - .type = TCA_ID_POLICE, + .id = TCA_ID_POLICE, .owner = THIS_MODULE, - .act = tcf_act_police, - .dump = tcf_act_police_dump, - .init = tcf_act_police_init, - .walk = tcf_act_police_walker, - .lookup = tcf_police_search, + .stats_update = tcf_police_stats_update, + .act = tcf_police_act, + .dump = tcf_police_dump, + .init = tcf_police_init, + .cleanup = tcf_police_cleanup, + .offload_act_setup = tcf_police_offload_act_setup, .size = sizeof(struct tcf_police), }; +MODULE_ALIAS_NET_ACT("police"); static __net_init int police_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, police_net_id); + struct tc_action_net *tn = net_generic(net, act_police_ops.net_id); - return tc_action_net_init(tn, &act_police_ops, POL_TAB_MASK); + return tc_action_net_init(net, tn, &act_police_ops); } -static void __net_exit police_exit_net(struct net *net) +static void __net_exit police_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, police_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_police_ops.net_id); } static struct pernet_operations police_net_ops = { .init = police_init_net, - .exit = police_exit_net, - .id = &police_net_id, + .exit_batch = police_exit_net, + .id = &act_police_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 59d6645a4007..2ceb4d141b71 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/act_sample.c - Packet sampling tc action * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/types.h> @@ -22,11 +19,11 @@ #include <linux/tc_act/tc_sample.h> #include <net/tc_act/tc_sample.h> #include <net/psample.h> +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> #include <linux/if_arp.h> -#define SAMPLE_TAB_MASK 7 -static unsigned int sample_net_id; static struct tc_action_ops act_sample_ops; static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { @@ -37,81 +34,115 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { }; static int tcf_sample_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind) + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, + u32 flags, struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, sample_net_id); + struct tc_action_net *tn = net_generic(net, act_sample_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + u32 psample_group_num, rate, index; + struct tcf_chain *goto_ch = NULL; struct tc_sample *parm; struct tcf_sample *s; bool exists = false; - int ret; + int ret, err; if (!nla) return -EINVAL; - ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy, NULL); + ret = nla_parse_nested_deprecated(tb, TCA_SAMPLE_MAX, nla, + sample_policy, NULL); if (ret < 0) return ret; - if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] || - !tb[TCA_SAMPLE_PSAMPLE_GROUP]) + + if (!tb[TCA_SAMPLE_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); - - exists = tcf_hash_check(tn, parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; if (!exists) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_sample_ops, bind, false); - if (ret) + ret = tcf_idr_create(tn, index, est, a, + &act_sample_ops, bind, true, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; } - s = to_sample(*a); - s->tcf_action = parm->action; - s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); - s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); - psample_group = psample_group_get(net, s->psample_group_num); + if (!tb[TCA_SAMPLE_RATE] || !tb[TCA_SAMPLE_PSAMPLE_GROUP]) { + NL_SET_ERR_MSG(extack, "sample rate and group are required"); + err = -EINVAL; + goto release_idr; + } + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + if (!rate) { + NL_SET_ERR_MSG(extack, "invalid sample rate"); + err = -EINVAL; + goto put_chain; + } + psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); + psample_group = psample_group_get(net, psample_group_num); if (!psample_group) { - if (ret == ACT_P_CREATED) - tcf_hash_release(*a, bind); - return -ENOMEM; + err = -ENOMEM; + goto put_chain; } - RCU_INIT_POINTER(s->psample_group, psample_group); + + s = to_sample(*a); + + spin_lock_bh(&s->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + s->rate = rate; + s->psample_group_num = psample_group_num; + psample_group = rcu_replace_pointer(s->psample_group, psample_group, + lockdep_is_held(&s->tcf_lock)); if (tb[TCA_SAMPLE_TRUNC_SIZE]) { s->truncate = true; s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } + spin_unlock_bh(&s->tcf_lock); + + if (psample_group) + psample_group_put(psample_group); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } -static void tcf_sample_cleanup_rcu(struct rcu_head *rcu) +static void tcf_sample_cleanup(struct tc_action *a) { - struct tcf_sample *s = container_of(rcu, struct tcf_sample, rcu); + struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; + /* last reference to action, no need to lock */ psample_group = rcu_dereference_protected(s->psample_group, 1); RCU_INIT_POINTER(s->psample_group, NULL); - psample_group_put(psample_group); -} - -static void tcf_sample_cleanup(struct tc_action *a, int bind) -{ - struct tcf_sample *s = to_sample(a); - - call_rcu(&s->rcu, tcf_sample_cleanup_rcu); + if (psample_group) + psample_group_put(psample_group); } static bool tcf_sample_dev_ok_push(struct net_device *dev) @@ -121,6 +152,7 @@ static bool tcf_sample_dev_ok_push(struct net_device *dev) case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: + case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: return false; @@ -129,49 +161,66 @@ static bool tcf_sample_dev_ok_push(struct net_device *dev) } } -static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_sample_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; + u8 cookie_data[TC_COOKIE_MAX_SIZE]; + struct psample_metadata md = {}; + struct tc_cookie *user_cookie; int retval; - int size; - int iif; - int oif; tcf_lastuse_update(&s->tcf_tm); - bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(s->common.cpu_bstats), skb); retval = READ_ONCE(s->tcf_action); - rcu_read_lock(); - psample_group = rcu_dereference(s->psample_group); + psample_group = rcu_dereference_bh(s->psample_group); /* randomly sample packets according to rate */ - if (psample_group && (prandom_u32() % s->rate == 0)) { + if (psample_group && (get_random_u32_below(s->rate) == 0)) { if (!skb_at_tc_ingress(skb)) { - iif = skb->skb_iif; - oif = skb->dev->ifindex; + md.in_ifindex = skb->skb_iif; + md.out_ifindex = skb->dev->ifindex; } else { - iif = skb->dev->ifindex; - oif = 0; + md.in_ifindex = skb->dev->ifindex; } /* on ingress, the mac header gets popped, so push it back */ if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_push(skb, skb->mac_len); - size = s->truncate ? s->trunc_size : skb->len; - psample_sample_packet(psample_group, skb, size, iif, oif, - s->rate); + rcu_read_lock(); + user_cookie = rcu_dereference(a->user_cookie); + if (user_cookie) { + memcpy(cookie_data, user_cookie->data, + user_cookie->len); + md.user_cookie = cookie_data; + md.user_cookie_len = user_cookie->len; + } + rcu_read_unlock(); + + md.trunc_size = s->truncate ? s->trunc_size : skb->len; + psample_sample_packet(psample_group, skb, s->rate, &md); if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_pull(skb, skb->mac_len); } - rcu_read_unlock(); return retval; } +static void tcf_sample_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) +{ + struct tcf_sample *s = to_sample(a); + struct tcf_t *tm = &s->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); +} + static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -179,12 +228,13 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_sample *s = to_sample(a); struct tc_sample opt = { .index = s->tcf_index, - .action = s->tcf_action, - .refcnt = s->tcf_refcnt - ref, - .bindcnt = s->tcf_bindcnt - bind, + .refcnt = refcount_read(&s->tcf_refcnt) - ref, + .bindcnt = atomic_read(&s->tcf_bindcnt) - bind, }; struct tcf_t t; + spin_lock_bh(&s->tcf_lock); + opt.action = s->tcf_action; if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -201,60 +251,101 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num)) goto nla_put_failure; + spin_unlock_bh(&s->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&s->tcf_lock); nlmsg_trim(skb, b); return -1; } -static int tcf_sample_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static void tcf_psample_group_put(void *priv) +{ + struct psample_group *group = priv; + + psample_group_put(group); +} + +static struct psample_group * +tcf_sample_get_group(const struct tc_action *a, + tc_action_priv_destructor *destructor) { - struct tc_action_net *tn = net_generic(net, sample_net_id); + struct tcf_sample *s = to_sample(a); + struct psample_group *group; + + group = rcu_dereference_protected(s->psample_group, + lockdep_is_held(&s->tcf_lock)); + if (group) { + psample_group_take(group); + *destructor = tcf_psample_group_put; + } + + return group; +} - return tcf_generic_walker(tn, skb, cb, type, ops); +static void tcf_offload_sample_get_group(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->sample.psample_group = + act->ops->get_psample_group(act, &entry->destructor); + entry->destructor_priv = entry->sample.psample_group; } -static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_sample_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, sample_net_id); + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_SAMPLE; + entry->sample.trunc_size = tcf_sample_trunc_size(act); + entry->sample.truncate = tcf_sample_truncate(act); + entry->sample.rate = tcf_sample_rate(act); + tcf_offload_sample_get_group(entry, act); + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; - return tcf_hash_search(tn, a, index); + fl_action->id = FLOW_ACTION_SAMPLE; + } + + return 0; } static struct tc_action_ops act_sample_ops = { .kind = "sample", - .type = TCA_ACT_SAMPLE, + .id = TCA_ID_SAMPLE, .owner = THIS_MODULE, .act = tcf_sample_act, + .stats_update = tcf_sample_stats_update, .dump = tcf_sample_dump, .init = tcf_sample_init, .cleanup = tcf_sample_cleanup, - .walk = tcf_sample_walker, - .lookup = tcf_sample_search, + .get_psample_group = tcf_sample_get_group, + .offload_act_setup = tcf_sample_offload_act_setup, .size = sizeof(struct tcf_sample), }; +MODULE_ALIAS_NET_ACT("sample"); static __net_init int sample_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, sample_net_id); + struct tc_action_net *tn = net_generic(net, act_sample_ops.net_id); - return tc_action_net_init(tn, &act_sample_ops, SAMPLE_TAB_MASK); + return tc_action_net_init(net, tn, &act_sample_ops); } -static void __net_exit sample_exit_net(struct net *net) +static void __net_exit sample_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, sample_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_sample_ops.net_id); } static struct pernet_operations sample_net_ops = { .init = sample_init_net, - .exit = sample_exit_net, - .id = &sample_net_id, + .exit_batch = sample_exit_net, + .id = &act_sample_ops.net_id, .size = sizeof(struct tc_action_net), }; @@ -271,6 +362,6 @@ static void __exit sample_cleanup_module(void) module_init(sample_init_module); module_exit(sample_cleanup_module); -MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>"); +MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>"); MODULE_DESCRIPTION("Packet sampling action"); MODULE_LICENSE("GPL v2"); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 43605e7ce051..8e69a919b4fe 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_simple.c Simple example of an action * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Jamal Hadi Salim (2005-8) - * */ #include <linux/module.h> @@ -18,20 +13,18 @@ #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> - -#define TCA_ACT_SIMP 22 +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> -#define SIMP_TAB_MASK 7 - -static unsigned int simp_net_id; static struct tc_action_ops act_simp_ops; #define SIMP_MAX_DATA 32 -static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_simp_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_defact *d = to_defact(a); @@ -43,35 +36,47 @@ static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) */ - pr_info("simple: %s_%d\n", - (char *)d->tcfd_defdata, d->tcf_bstats.packets); + pr_info("simple: %s_%llu\n", + (char *)d->tcfd_defdata, + u64_stats_read(&d->tcf_bstats.packets)); spin_unlock(&d->tcf_lock); return d->tcf_action; } -static void tcf_simp_release(struct tc_action *a, int bind) +static void tcf_simp_release(struct tc_action *a) { struct tcf_defact *d = to_defact(a); kfree(d->tcfd_defdata); } -static int alloc_defdata(struct tcf_defact *d, char *defdata) +static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata) { d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL); if (unlikely(!d->tcfd_defdata)) return -ENOMEM; - strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); + nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); return 0; } -static void reset_policy(struct tcf_defact *d, char *defdata, - struct tc_defact *p) +static int reset_policy(struct tc_action *a, const struct nlattr *defdata, + struct tc_defact *p, struct tcf_proto *tp, + struct netlink_ext_ack *extack) { + struct tcf_chain *goto_ch = NULL; + struct tcf_defact *d; + int err; + + err = tcf_action_check_ctrlact(p->action, tp, &goto_ch, extack); + if (err < 0) + return err; + d = to_defact(a); spin_lock_bh(&d->tcf_lock); - d->tcf_action = p->action; - memset(d->tcfd_defdata, 0, SIMP_MAX_DATA); - strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); + goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch); + nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); spin_unlock_bh(&d->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + return 0; } static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { @@ -81,20 +86,24 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, simp_net_id); + struct tc_action_net *tn = net_generic(net, act_simp_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_DEF_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_defact *parm; struct tcf_defact *d; bool exists = false; int ret = 0, err; - char *defdata; + u32 index; if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_DEF_MAX, nla, simple_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_DEF_MAX, nla, simple_policy, + NULL); if (err < 0) return err; @@ -102,45 +111,60 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); - exists = tcf_hash_check(tn, parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; if (tb[TCA_DEF_DATA] == NULL) { if (exists) - tcf_hash_release(*a, bind); + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EINVAL; } - defdata = nla_data(tb[TCA_DEF_DATA]); - if (!exists) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_simp_ops, bind, false); - if (ret) + ret = tcf_idr_create(tn, index, est, a, + &act_simp_ops, bind, false, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } d = to_defact(*a); - ret = alloc_defdata(d, defdata); - if (ret < 0) { - tcf_hash_cleanup(*a, est); - return ret; - } - d->tcf_action = parm->action; + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, + extack); + if (err < 0) + goto release_idr; + + err = alloc_defdata(d, tb[TCA_DEF_DATA]); + if (err < 0) + goto put_chain; + + tcf_action_set_ctrlact(*a, parm->action, goto_ch); ret = ACT_P_CREATED; } else { - d = to_defact(*a); - - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + err = -EEXIST; + goto release_idr; + } - reset_policy(d, defdata, parm); + err = reset_policy(*a, tb[TCA_DEF_DATA], parm, tp, extack); + if (err) + goto release_idr; } - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, @@ -150,12 +174,13 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_defact *d = to_defact(a); struct tc_defact opt = { .index = d->tcf_index, - .refcnt = d->tcf_refcnt - ref, - .bindcnt = d->tcf_bindcnt - bind, - .action = d->tcf_action, + .refcnt = refcount_read(&d->tcf_refcnt) - ref, + .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, }; struct tcf_t t; + spin_lock_bh(&d->tcf_lock); + opt.action = d->tcf_action; if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) || nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata)) goto nla_put_failure; @@ -163,60 +188,44 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD)) goto nla_put_failure; + spin_unlock_bh(&d->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } -static int tcf_simp_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, simp_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, simp_net_id); - - return tcf_hash_search(tn, a, index); -} - static struct tc_action_ops act_simp_ops = { .kind = "simple", - .type = TCA_ACT_SIMP, + .id = TCA_ID_SIMP, .owner = THIS_MODULE, - .act = tcf_simp, + .act = tcf_simp_act, .dump = tcf_simp_dump, .cleanup = tcf_simp_release, .init = tcf_simp_init, - .walk = tcf_simp_walker, - .lookup = tcf_simp_search, .size = sizeof(struct tcf_defact), }; +MODULE_ALIAS_NET_ACT("simple"); static __net_init int simp_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, simp_net_id); + struct tc_action_net *tn = net_generic(net, act_simp_ops.net_id); - return tc_action_net_init(tn, &act_simp_ops, SIMP_TAB_MASK); + return tc_action_net_init(net, tn, &act_simp_ops); } -static void __net_exit simp_exit_net(struct net *net) +static void __net_exit simp_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, simp_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_simp_ops.net_id); } static struct pernet_operations simp_net_ops = { .init = simp_init_net, - .exit = simp_exit_net, - .id = &simp_net_id, + .exit_batch = simp_exit_net, + .id = &act_simp_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 6b3e65d7de0c..8c1d1554f657 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -1,18 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, Intel Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ @@ -23,38 +12,93 @@ #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/dsfield.h> +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> #include <linux/tc_act/tc_skbedit.h> #include <net/tc_act/tc_skbedit.h> -#define SKBEDIT_TAB_MASK 15 - -static unsigned int skbedit_net_id; static struct tc_action_ops act_skbedit_ops; -static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +static u16 tcf_skbedit_hash(struct tcf_skbedit_params *params, + struct sk_buff *skb) +{ + u16 queue_mapping = params->queue_mapping; + + if (params->flags & SKBEDIT_F_TXQ_SKBHASH) { + u32 hash = skb_get_hash(skb); + + queue_mapping += hash % params->mapping_mod; + } + + return netdev_cap_txqueue(skb->dev, queue_mapping); +} + +TC_INDIRECT_SCOPE int tcf_skbedit_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_skbedit *d = to_skbedit(a); + struct tcf_skbedit_params *params; - spin_lock(&d->tcf_lock); tcf_lastuse_update(&d->tcf_tm); - bstats_update(&d->tcf_bstats, skb); - - if (d->flags & SKBEDIT_F_PRIORITY) - skb->priority = d->priority; - if (d->flags & SKBEDIT_F_QUEUE_MAPPING && - skb->dev->real_num_tx_queues > d->queue_mapping) - skb_set_queue_mapping(skb, d->queue_mapping); - if (d->flags & SKBEDIT_F_MARK) { - skb->mark &= ~d->mask; - skb->mark |= d->mark & d->mask; + bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); + + params = rcu_dereference_bh(d->params); + + if (params->flags & SKBEDIT_F_PRIORITY) + skb->priority = params->priority; + if (params->flags & SKBEDIT_F_INHERITDSFIELD) { + int wlen = skb_network_offset(skb); + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen)) + goto err; + skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2; + break; + + case htons(ETH_P_IPV6): + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen)) + goto err; + skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; + break; + } } - if (d->flags & SKBEDIT_F_PTYPE) - skb->pkt_type = d->ptype; + if (params->flags & SKBEDIT_F_QUEUE_MAPPING && + skb->dev->real_num_tx_queues > params->queue_mapping) { +#ifdef CONFIG_NET_EGRESS + netdev_xmit_skip_txqueue(true); +#endif + skb_set_queue_mapping(skb, tcf_skbedit_hash(params, skb)); + } + if (params->flags & SKBEDIT_F_MARK) { + skb->mark &= ~params->mask; + skb->mark |= params->mark & params->mask; + } + if (params->flags & SKBEDIT_F_PTYPE) + skb->pkt_type = params->ptype; + return params->action; + +err: + qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats)); + return TC_ACT_SHOT; +} + +static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes, + u64 packets, u64 drops, + u64 lastuse, bool hw) +{ + struct tcf_skbedit *d = to_skbedit(a); + struct tcf_t *tm = &d->tcf_tm; - spin_unlock(&d->tcf_lock); - return d->tcf_action; + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { @@ -64,25 +108,34 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, [TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) }, [TCA_SKBEDIT_MASK] = { .len = sizeof(u32) }, + [TCA_SKBEDIT_FLAGS] = { .len = sizeof(u64) }, + [TCA_SKBEDIT_QUEUE_MAPPING_MAX] = { .len = sizeof(u16) }, }; static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 act_flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, skbedit_net_id); + struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id); + bool bind = act_flags & TCA_ACT_FLAGS_BIND; + struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_skbedit *parm; struct tcf_skbedit *d; u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL; u16 *queue_mapping = NULL, *ptype = NULL; + u16 mapping_mod = 1; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_SKBEDIT_MAX, nla, + skbedit_policy, NULL); if (err < 0) return err; @@ -95,6 +148,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) { + if (is_tcf_skbedit_ingress(act_flags) && + !(act_flags & TCA_ACT_FLAGS_SKIP_SW)) { + NL_SET_ERR_MSG_MOD(extack, "\"queue_mapping\" option on receive side is hardware only, use skip_sw"); + return -EOPNOTSUPP; + } flags |= SKBEDIT_F_QUEUE_MAPPING; queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]); } @@ -116,144 +174,274 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, mask = nla_data(tb[TCA_SKBEDIT_MASK]); } - parm = nla_data(tb[TCA_SKBEDIT_PARMS]); + if (tb[TCA_SKBEDIT_FLAGS] != NULL) { + u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]); + + if (*pure_flags & SKBEDIT_F_TXQ_SKBHASH) { + u16 *queue_mapping_max; + + if (!tb[TCA_SKBEDIT_QUEUE_MAPPING] || + !tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]) { + NL_SET_ERR_MSG_MOD(extack, "Missing required range of queue_mapping."); + return -EINVAL; + } + + queue_mapping_max = + nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]); + if (*queue_mapping_max < *queue_mapping) { + NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid, max < min."); + return -EINVAL; + } + + mapping_mod = *queue_mapping_max - *queue_mapping + 1; + flags |= SKBEDIT_F_TXQ_SKBHASH; + } + if (*pure_flags & SKBEDIT_F_INHERITDSFIELD) + flags |= SKBEDIT_F_INHERITDSFIELD; + } - exists = tcf_hash_check(tn, parm->index, a, bind); + parm = nla_data(tb[TCA_SKBEDIT_PARMS]); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; if (!flags) { - tcf_hash_release(*a, bind); + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_skbedit_ops, bind, false); - if (ret) + ret = tcf_idr_create(tn, index, est, a, + &act_skbedit_ops, bind, true, act_flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } d = to_skbedit(*a); ret = ACT_P_CREATED; } else { d = to_skbedit(*a); - tcf_hash_release(*a, bind); - if (!ovr) + if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); return -EEXIST; + } } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; - spin_lock_bh(&d->tcf_lock); + params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + if (unlikely(!params_new)) { + err = -ENOMEM; + goto put_chain; + } - d->flags = flags; + params_new->flags = flags; if (flags & SKBEDIT_F_PRIORITY) - d->priority = *priority; - if (flags & SKBEDIT_F_QUEUE_MAPPING) - d->queue_mapping = *queue_mapping; + params_new->priority = *priority; + if (flags & SKBEDIT_F_QUEUE_MAPPING) { + params_new->queue_mapping = *queue_mapping; + params_new->mapping_mod = mapping_mod; + } if (flags & SKBEDIT_F_MARK) - d->mark = *mark; + params_new->mark = *mark; if (flags & SKBEDIT_F_PTYPE) - d->ptype = *ptype; + params_new->ptype = *ptype; /* default behaviour is to use all the bits */ - d->mask = 0xffffffff; + params_new->mask = 0xffffffff; if (flags & SKBEDIT_F_MASK) - d->mask = *mask; - - d->tcf_action = parm->action; + params_new->mask = *mask; + params_new->action = parm->action; + spin_lock_bh(&d->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + params_new = rcu_replace_pointer(d->params, params_new, + lockdep_is_held(&d->tcf_lock)); spin_unlock_bh(&d->tcf_lock); + if (params_new) + kfree_rcu(params_new, rcu); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { + const struct tcf_skbedit *d = to_skbedit(a); unsigned char *b = skb_tail_pointer(skb); - struct tcf_skbedit *d = to_skbedit(a); + const struct tcf_skbedit_params *params; struct tc_skbedit opt = { .index = d->tcf_index, - .refcnt = d->tcf_refcnt - ref, - .bindcnt = d->tcf_bindcnt - bind, - .action = d->tcf_action, + .refcnt = refcount_read(&d->tcf_refcnt) - ref, + .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, }; + u64 pure_flags = 0; struct tcf_t t; + rcu_read_lock(); + params = rcu_dereference(d->params); + opt.action = params->action; + if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_PRIORITY) && - nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, d->priority)) + if ((params->flags & SKBEDIT_F_PRIORITY) && + nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_QUEUE_MAPPING) && - nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, d->queue_mapping)) + if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) && + nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_MARK) && - nla_put_u32(skb, TCA_SKBEDIT_MARK, d->mark)) + if ((params->flags & SKBEDIT_F_MARK) && + nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_PTYPE) && - nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype)) + if ((params->flags & SKBEDIT_F_PTYPE) && + nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_MASK) && - nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask)) + if ((params->flags & SKBEDIT_F_MASK) && + nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask)) + goto nla_put_failure; + if (params->flags & SKBEDIT_F_INHERITDSFIELD) + pure_flags |= SKBEDIT_F_INHERITDSFIELD; + if (params->flags & SKBEDIT_F_TXQ_SKBHASH) { + if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX, + params->queue_mapping + params->mapping_mod - 1)) + goto nla_put_failure; + + pure_flags |= SKBEDIT_F_TXQ_SKBHASH; + } + if (pure_flags != 0 && + nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags)) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; + rcu_read_unlock(); + return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static void tcf_skbedit_cleanup(struct tc_action *a) { - struct tc_action_net *tn = net_generic(net, skbedit_net_id); + struct tcf_skbedit *d = to_skbedit(a); + struct tcf_skbedit_params *params; + + params = rcu_dereference_protected(d->params, 1); + if (params) + kfree_rcu(params, rcu); +} - return tcf_generic_walker(tn, skb, cb, type, ops); +static size_t tcf_skbedit_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_skbedit)) + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */ + + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */ + + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING_MAX */ + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */ + + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */ + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */ + + nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */ } -static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, skbedit_net_id); + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_skbedit_mark(act)) { + entry->id = FLOW_ACTION_MARK; + entry->mark = tcf_skbedit_mark(act); + } else if (is_tcf_skbedit_ptype(act)) { + entry->id = FLOW_ACTION_PTYPE; + entry->ptype = tcf_skbedit_ptype(act); + } else if (is_tcf_skbedit_priority(act)) { + entry->id = FLOW_ACTION_PRIORITY; + entry->priority = tcf_skbedit_priority(act); + } else if (is_tcf_skbedit_tx_queue_mapping(act)) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used on transmit side"); + return -EOPNOTSUPP; + } else if (is_tcf_skbedit_rx_queue_mapping(act)) { + entry->id = FLOW_ACTION_RX_QUEUE_MAPPING; + entry->rx_queue = tcf_skbedit_rx_queue_mapping(act); + } else if (is_tcf_skbedit_inheritdsfield(act)) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used"); + return -EOPNOTSUPP; + } else { + NL_SET_ERR_MSG_MOD(extack, "Unsupported skbedit option offload"); + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_skbedit_mark(act)) + fl_action->id = FLOW_ACTION_MARK; + else if (is_tcf_skbedit_ptype(act)) + fl_action->id = FLOW_ACTION_PTYPE; + else if (is_tcf_skbedit_priority(act)) + fl_action->id = FLOW_ACTION_PRIORITY; + else if (is_tcf_skbedit_rx_queue_mapping(act)) + fl_action->id = FLOW_ACTION_RX_QUEUE_MAPPING; + else + return -EOPNOTSUPP; + } - return tcf_hash_search(tn, a, index); + return 0; } static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", - .type = TCA_ACT_SKBEDIT, + .id = TCA_ID_SKBEDIT, .owner = THIS_MODULE, - .act = tcf_skbedit, + .act = tcf_skbedit_act, + .stats_update = tcf_skbedit_stats_update, .dump = tcf_skbedit_dump, .init = tcf_skbedit_init, - .walk = tcf_skbedit_walker, - .lookup = tcf_skbedit_search, + .cleanup = tcf_skbedit_cleanup, + .get_fill_size = tcf_skbedit_get_fill_size, + .offload_act_setup = tcf_skbedit_offload_act_setup, .size = sizeof(struct tcf_skbedit), }; +MODULE_ALIAS_NET_ACT("skbedit"); static __net_init int skbedit_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, skbedit_net_id); + struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id); - return tc_action_net_init(tn, &act_skbedit_ops, SKBEDIT_TAB_MASK); + return tc_action_net_init(net, tn, &act_skbedit_ops); } -static void __net_exit skbedit_exit_net(struct net *net) +static void __net_exit skbedit_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, skbedit_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_skbedit_ops.net_id); } static struct pernet_operations skbedit_net_ops = { .init = skbedit_init_net, - .exit = skbedit_exit_net, - .id = &skbedit_net_id, + .exit_batch = skbedit_exit_net, + .id = &act_skbedit_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index a73c4bbcada2..a9e0c1326e2a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -1,70 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_skbmod.c skb data modifier * * Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include <linux/module.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> +#include <net/inet_ecn.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> #include <linux/tc_act/tc_skbmod.h> #include <net/tc_act/tc_skbmod.h> -#define SKBMOD_TAB_MASK 15 - -static unsigned int skbmod_net_id; static struct tc_action_ops act_skbmod_ops; -#define MAX_EDIT_LEN ETH_HLEN -static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_skbmod *d = to_skbmod(a); - int action; struct tcf_skbmod_params *p; + int max_edit_len, err; u64 flags; - int err; tcf_lastuse_update(&d->tcf_tm); - bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); - - /* XXX: if you are going to edit more fields beyond ethernet header - * (example when you add IP header replacement or vlan swap) - * then MAX_EDIT_LEN needs to change appropriately - */ - err = skb_ensure_writable(skb, MAX_EDIT_LEN); - if (unlikely(err)) { /* best policy is to drop on the floor */ - qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); - return TC_ACT_SHOT; - } + bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); - rcu_read_lock(); - action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) { - qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); - rcu_read_unlock(); - return action; - } + p = rcu_dereference_bh(d->skbmod_p); + if (unlikely(p->action == TC_ACT_SHOT)) + goto drop; - p = rcu_dereference(d->skbmod_p); + max_edit_len = skb_mac_header_len(skb); flags = p->flags; + + /* tcf_skbmod_init() guarantees "flags" to be one of the following: + * 1. a combination of SKBMOD_F_{DMAC,SMAC,ETYPE} + * 2. SKBMOD_F_SWAPMAC + * 3. SKBMOD_F_ECN + * SKBMOD_F_ECN only works with IP packets; all other flags only work with Ethernet + * packets. + */ + if (flags == SKBMOD_F_ECN) { + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + case cpu_to_be16(ETH_P_IPV6): + max_edit_len += skb_network_header_len(skb); + break; + default: + goto out; + } + } else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) { + goto out; + } + + err = skb_ensure_writable(skb, max_edit_len); + if (unlikely(err)) /* best policy is to drop on the floor */ + goto drop; + if (flags & SKBMOD_F_DMAC) ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); if (flags & SKBMOD_F_SMAC) ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src); if (flags & SKBMOD_F_ETYPE) eth_hdr(skb)->h_proto = p->eth_type; - rcu_read_unlock(); if (flags & SKBMOD_F_SWAPMAC) { u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */ @@ -74,7 +80,15 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr); } - return action; + if (flags & SKBMOD_F_ECN) + INET_ECN_set_ce(skb); + +out: + return p->action; + +drop: + qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); + return TC_ACT_SHOT; } static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { @@ -86,24 +100,29 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, skbmod_net_id); + struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id); + bool ovr = flags & TCA_ACT_FLAGS_REPLACE; + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SKBMOD_MAX + 1]; struct tcf_skbmod_params *p, *p_old; + struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; + u32 lflags = 0, index; struct tcf_skbmod *d; bool exists = false; u8 *daddr = NULL; u8 *saddr = NULL; u16 eth_type = 0; - u32 lflags = 0; int ret = 0, err; if (!nla) return -EINVAL; - err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_SKBMOD_MAX, nla, + skbmod_policy, NULL); if (err < 0) return err; @@ -126,46 +145,59 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBMOD_PARMS]); + index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; + if (parm->flags & SKBMOD_F_ECN) + lflags = SKBMOD_F_ECN; - exists = tcf_hash_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; - if (!lflags) + if (!lflags) { + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EINVAL; + } if (!exists) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_skbmod_ops, bind, true); - if (ret) + ret = tcf_idr_create(tn, index, est, a, + &act_skbmod_ops, bind, true, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + } else if (!ovr) { + tcf_idr_release(*a, bind); + return -EEXIST; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; d = to_skbmod(*a); - ASSERT_RTNL(); p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); if (unlikely(!p)) { - if (ovr) - tcf_hash_release(*a, bind); - return -ENOMEM; + err = -ENOMEM; + goto put_chain; } p->flags = lflags; - d->tcf_action = parm->action; - - p_old = rtnl_dereference(d->skbmod_p); - + p->action = parm->action; if (ovr) spin_lock_bh(&d->tcf_lock); + /* Protected by tcf_lock if overwriting existing action. */ + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + p_old = rcu_dereference_protected(d->skbmod_p, 1); if (lflags & SKBMOD_F_DMAC) ether_addr_copy(p->eth_dst, daddr); @@ -180,19 +212,26 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (p_old) kfree_rcu(p_old, rcu); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } -static void tcf_skbmod_cleanup(struct tc_action *a, int bind) +static void tcf_skbmod_cleanup(struct tc_action *a) { struct tcf_skbmod *d = to_skbmod(a); struct tcf_skbmod_params *p; p = rcu_dereference_protected(d->skbmod_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, @@ -200,15 +239,17 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, { struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); - struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p); - struct tc_skbmod opt = { - .index = d->tcf_index, - .refcnt = d->tcf_refcnt - ref, - .bindcnt = d->tcf_bindcnt - bind, - .action = d->tcf_action, - }; + struct tcf_skbmod_params *p; + struct tc_skbmod opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + opt.index = d->tcf_index; + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; + rcu_read_lock(); + p = rcu_dereference(d->skbmod_p); + opt.action = p->action; opt.flags = p->flags; if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -226,59 +267,42 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD)) goto nla_put_failure; + rcu_read_unlock(); return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) -{ - struct tc_action_net *tn = net_generic(net, skbmod_net_id); - - return tcf_generic_walker(tn, skb, cb, type, ops); -} - -static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) -{ - struct tc_action_net *tn = net_generic(net, skbmod_net_id); - - return tcf_hash_search(tn, a, index); -} - static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", - .type = TCA_ACT_SKBMOD, + .id = TCA_ACT_SKBMOD, .owner = THIS_MODULE, - .act = tcf_skbmod_run, + .act = tcf_skbmod_act, .dump = tcf_skbmod_dump, .init = tcf_skbmod_init, .cleanup = tcf_skbmod_cleanup, - .walk = tcf_skbmod_walker, - .lookup = tcf_skbmod_search, .size = sizeof(struct tcf_skbmod), }; +MODULE_ALIAS_NET_ACT("skbmod"); static __net_init int skbmod_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, skbmod_net_id); + struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id); - return tc_action_net_init(tn, &act_skbmod_ops, SKBMOD_TAB_MASK); + return tc_action_net_init(net, tn, &act_skbmod_ops); } -static void __net_exit skbmod_exit_net(struct net *net) +static void __net_exit skbmod_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, skbmod_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_skbmod_ops.net_id); } static struct pernet_operations skbmod_net_ops = { .init = skbmod_init_net, - .exit = skbmod_exit_net, - .id = &skbmod_net_id, + .exit_batch = skbmod_exit_net, + .id = &act_skbmod_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index fd7e75679c69..876b30c5709e 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016, Amir Vadai <amir@vadai.me> * Copyright (c) 2016, Mellanox Technologies. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include <linux/module.h> @@ -13,32 +9,31 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> +#include <net/geneve.h> +#include <net/vxlan.h> +#include <net/erspan.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/dst.h> +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> #include <linux/tc_act/tc_tunnel_key.h> #include <net/tc_act/tc_tunnel_key.h> -#define TUNNEL_KEY_TAB_MASK 15 - -static unsigned int tunnel_key_net_id; static struct tc_action_ops act_tunnel_key_ops; -static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tunnel_key_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; - int action; - - rcu_read_lock(); - params = rcu_dereference(t->params); + params = rcu_dereference_bh(t->params); tcf_lastuse_update(&t->tcf_tm); - bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); - action = params->action; + tcf_action_update_bstats(&t->common, skb); switch (params->tcft_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: @@ -54,9 +49,283 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, break; } - rcu_read_unlock(); + return params->action; +} + +static const struct nla_policy +enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC] = { + .strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN }, + [TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, + [TCA_TUNNEL_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, + [TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, + .len = 127 }, +}; + +static const struct nla_policy +vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, +}; + +static int +tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1]; + int err, data_len, opt_len; + u8 *data; + + err = nla_parse_nested_deprecated(tb, + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX, + nla, geneve_opt_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data"); + return -EINVAL; + } + + data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); + data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); + if (data_len < 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long"); + return -ERANGE; + } + if (data_len % 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long"); + return -ERANGE; + } + + opt_len = sizeof(struct geneve_opt) + data_len; + if (dst) { + struct geneve_opt *opt = dst; + + WARN_ON(dst_len < opt_len); + + opt->opt_class = + nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]); + opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]); + opt->length = data_len / 4; /* length is in units of 4 bytes */ + opt->r1 = 0; + opt->r2 = 0; + opt->r3 = 0; + + memcpy(opt + 1, data, data_len); + } + + return opt_len; +} + +static int +tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1]; + int err; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla, + vxlan_opt_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp"); + return -EINVAL; + } + + if (dst) { + struct vxlan_metadata *md = dst; + + md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; + } - return action; + return sizeof(struct vxlan_metadata); +} + +static int +tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1]; + int err; + u8 ver; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla, + erspan_opt_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver"); + return -EINVAL; + } + + ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]); + if (ver == 1) { + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index"); + return -EINVAL; + } + } else if (ver == 2) { + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid"); + return -EINVAL; + } + } else { + NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect"); + return -EINVAL; + } + + if (dst) { + struct erspan_metadata *md = dst; + + md->version = ver; + if (ver == 1) { + nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]; + md->u.index = nla_get_be32(nla); + } else { + nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR]; + md->u.md2.dir = nla_get_u8(nla); + nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]; + set_hwid(&md->u.md2, nla_get_u8(nla)); + } + } + + return sizeof(struct erspan_metadata); +} + +static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, + int dst_len, struct netlink_ext_ack *extack) +{ + int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0; + const struct nlattr *attr, *head = nla_data(nla); + + err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + + nla_for_each_attr(attr, head, len, rem) { + switch (nla_type(attr)) { + case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) { + NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); + return -EINVAL; + } + opt_len = tunnel_key_copy_geneve_opt(attr, dst, + dst_len, extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + if (opts_len > IP_TUNNEL_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -EINVAL; + } + if (dst) { + dst_len -= opt_len; + dst += opt_len; + } + type = IP_TUNNEL_GENEVE_OPT_BIT; + break; + case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: + if (type) { + NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options"); + return -EINVAL; + } + opt_len = tunnel_key_copy_vxlan_opt(attr, dst, + dst_len, extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + type = IP_TUNNEL_VXLAN_OPT_BIT; + break; + case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: + if (type) { + NL_SET_ERR_MSG(extack, "Duplicate type for erspan options"); + return -EINVAL; + } + opt_len = tunnel_key_copy_erspan_opt(attr, dst, + dst_len, extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + type = IP_TUNNEL_ERSPAN_OPT_BIT; + break; + } + } + + if (!opts_len) { + NL_SET_ERR_MSG(extack, "Empty list of tunnel options"); + return -EINVAL; + } + + if (rem > 0) { + NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes"); + return -EINVAL; + } + + return opts_len; +} + +static int tunnel_key_get_opts_len(struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + return tunnel_key_copy_opts(nla, NULL, 0, extack); +} + +static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, + int opts_len, struct netlink_ext_ack *extack) +{ + info->options_len = opts_len; + switch (nla_type(nla_data(nla))) { + case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: +#if IS_ENABLED(CONFIG_INET) + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); + return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), + opts_len, extack); +#else + return -EAFNOSUPPORT; +#endif + case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: +#if IS_ENABLED(CONFIG_INET) + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); + return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), + opts_len, extack); +#else + return -EAFNOSUPPORT; +#endif + case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: +#if IS_ENABLED(CONFIG_INET) + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); + return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), + opts_len, extack); +#else + return -EAFNOSUPPORT; +#endif + default: + NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type"); + return -EINVAL; + } } static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { @@ -68,61 +337,109 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, [TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED }, + [TCA_TUNNEL_KEY_ENC_TOS] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 }, }; +static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) +{ + if (!p) + return; + if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(&p->tcft_enc_metadata->dst); + + kfree_rcu(p, rcu); +} + static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 act_flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + struct tc_action_net *tn = net_generic(net, act_tunnel_key_ops.net_id); + bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; - struct tcf_tunnel_key_params *params_old; struct tcf_tunnel_key_params *params_new; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *metadata = NULL; + struct tcf_chain *goto_ch = NULL; struct tc_tunnel_key *parm; struct tcf_tunnel_key *t; bool exists = false; __be16 dst_port = 0; - __be64 key_id; - __be16 flags; + __be64 key_id = 0; + int opts_len = 0; + u8 tos, ttl; int ret = 0; + u32 index; int err; - if (!nla) + if (!nla) { + NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed"); return -EINVAL; + } - err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy, - NULL); - if (err < 0) + err = nla_parse_nested_deprecated(tb, TCA_TUNNEL_KEY_MAX, nla, + tunnel_key_policy, extack); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes"); return err; + } - if (!tb[TCA_TUNNEL_KEY_PARMS]) + if (!tb[TCA_TUNNEL_KEY_PARMS]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key parameters"); return -EINVAL; + } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); - exists = tcf_hash_check(tn, parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; switch (parm->t_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: break; case TCA_TUNNEL_KEY_ACT_SET: - if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { - ret = -EINVAL; - goto err_out; - } + if (tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { + __be32 key32; - key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID])); + key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]); + key_id = key32_to_tunnel_id(key32); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + } - flags = TUNNEL_KEY | TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, flags); if (tb[TCA_TUNNEL_KEY_NO_CSUM] && nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) - flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, flags); + + if (nla_get_flag(tb[TCA_TUNNEL_KEY_NO_FRAG])) + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, flags); if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); + if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) { + opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS], + extack); + if (opts_len < 0) { + ret = opts_len; + goto err_out; + } + } + + tos = 0; + if (tb[TCA_TUNNEL_KEY_ENC_TOS]) + tos = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TOS]); + ttl = 0; + if (tb[TCA_TUNNEL_KEY_ENC_TTL]) + ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]); + if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { __be32 saddr; @@ -131,9 +448,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]); daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); - metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, + metadata = __ip_tun_set_dst(saddr, daddr, tos, ttl, dst_port, flags, - key_id, 0); + key_id, opts_len); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { struct in6_addr saddr; @@ -142,78 +459,229 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]); daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); - metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port, + metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, - key_id, 0); + key_id, opts_len); + } else { + NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); + ret = -EINVAL; + goto err_out; } if (!metadata) { - ret = -EINVAL; + NL_SET_ERR_MSG(extack, "Cannot allocate tunnel metadata dst"); + ret = -ENOMEM; goto err_out; } +#ifdef CONFIG_DST_CACHE + ret = dst_cache_init(&metadata->u.tun_info.dst_cache, GFP_KERNEL); + if (ret) + goto release_tun_meta; +#endif + + if (opts_len) { + ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS], + &metadata->u.tun_info, + opts_len, extack); + if (ret < 0) + goto release_tun_meta; + } + metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: + NL_SET_ERR_MSG(extack, "Unknown tunnel key action"); + ret = -EINVAL; goto err_out; } if (!exists) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_tunnel_key_ops, bind, true); - if (ret) - return ret; + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_tunnel_key_ops, bind, + act_flags); + if (ret) { + NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); + goto release_tun_meta; + } ret = ACT_P_CREATED; - } else { - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + } else if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { + NL_SET_ERR_MSG(extack, "TC IDR already exists"); + ret = -EEXIST; + goto release_tun_meta; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) { + ret = err; + exists = true; + goto release_tun_meta; + } t = to_tunnel_key(*a); - ASSERT_RTNL(); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - if (ret == ACT_P_CREATED) - tcf_hash_release(*a, bind); - return -ENOMEM; + NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); + ret = -ENOMEM; + exists = true; + goto put_chain; } - - params_old = rtnl_dereference(t->params); - - params_new->action = parm->action; params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; - rcu_assign_pointer(t->params, params_new); + params_new->action = parm->action; + spin_lock_bh(&t->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + params_new = rcu_replace_pointer(t->params, params_new, + lockdep_is_held(&t->tcf_lock)); + spin_unlock_bh(&t->tcf_lock); + tunnel_key_release_params(params_new); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); - if (params_old) - kfree_rcu(params_old, rcu); + return ret; - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); - return ret; +release_tun_meta: + if (metadata) + dst_release(&metadata->dst); err_out: if (exists) - tcf_hash_release(*a, bind); + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return ret; } -static void tunnel_key_release(struct tc_action *a, int bind) +static void tunnel_key_release(struct tc_action *a) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); + tunnel_key_release_params(params); +} + +static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + const u8 *src = ip_tunnel_info_opts(info); + int len = info->options_len; + struct nlattr *start; + + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); + if (!start) + return -EMSGSIZE; + + while (len > 0) { + const struct geneve_opt *opt = (const struct geneve_opt *)src; + + if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, + opt->opt_class) || + nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, + opt->type) || + nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, + opt->length * 4, opt + 1)) { + nla_nest_cancel(skb, start); + return -EMSGSIZE; + } + + len -= sizeof(struct geneve_opt) + opt->length * 4; + src += sizeof(struct geneve_opt) + opt->length * 4; + } - if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) - dst_release(¶ms->tcft_enc_metadata->dst); + nla_nest_end(skb, start); + return 0; +} + +static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + const struct vxlan_metadata *md = ip_tunnel_info_opts(info); + struct nlattr *start; + + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN); + if (!start) + return -EMSGSIZE; + + if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) { + nla_nest_cancel(skb, start); + return -EMSGSIZE; + } - kfree_rcu(params, rcu); + nla_nest_end(skb, start); + return 0; +} + +static int tunnel_key_erspan_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + const struct erspan_metadata *md = ip_tunnel_info_opts(info); + struct nlattr *start; + + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN); + if (!start) + return -EMSGSIZE; + + if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version)) + goto err; + + if (md->version == 1 && + nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index)) + goto err; + + if (md->version == 2 && + (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR, + md->u.md2.dir) || + nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID, + get_hwid(&md->u.md2)))) + goto err; + + nla_nest_end(skb, start); + return 0; +err: + nla_nest_cancel(skb, start); + return -EMSGSIZE; +} + +static int tunnel_key_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + struct nlattr *start; + int err = -EINVAL; + + if (!info->options_len) + return 0; + + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS); + if (!start) + return -EMSGSIZE; + + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { + err = tunnel_key_geneve_opts_dump(skb, info); + if (err) + goto err_out; + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { + err = tunnel_key_vxlan_opts_dump(skb, info); + if (err) + goto err_out; + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { + err = tunnel_key_erspan_opts_dump(skb, info); + if (err) + goto err_out; + } else { +err_out: + nla_nest_cancel(skb, start); + return err; + } + + nla_nest_end(skb, start); + return 0; } static int tunnel_key_dump_addresses(struct sk_buff *skb, @@ -252,30 +720,43 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_tunnel_key_params *params; struct tc_tunnel_key opt = { .index = t->tcf_index, - .refcnt = t->tcf_refcnt - ref, - .bindcnt = t->tcf_bindcnt - bind, + .refcnt = refcount_read(&t->tcf_refcnt) - ref, + .bindcnt = atomic_read(&t->tcf_bindcnt) - bind, }; struct tcf_t tm; - params = rtnl_dereference(t->params); - + rcu_read_lock(); + params = rcu_dereference(t->params); + opt.action = params->action; opt.t_action = params->tcft_action; - opt.action = params->action; if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { - struct ip_tunnel_key *key = - ¶ms->tcft_enc_metadata->u.tun_info.key; + struct ip_tunnel_info *info = + ¶ms->tcft_enc_metadata->u.tun_info; + struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); - if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || + if ((test_bit(IP_TUNNEL_KEY_BIT, key->tun_flags) && + nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || - nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) || + (key->tp_dst && + nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, + key->tp_dst)) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, - !(key->tun_flags & TUNNEL_CSUM))) + !test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) || + (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) && + nla_put_flag(skb, TCA_TUNNEL_KEY_NO_FRAG)) || + tunnel_key_opts_dump(skb, info)) + goto nla_put_failure; + + if (key->tos && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TOS, key->tos)) + goto nla_put_failure; + + if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl)) goto nla_put_failure; } @@ -283,61 +764,100 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm), &tm, TCA_TUNNEL_KEY_PAD)) goto nla_put_failure; + rcu_read_unlock(); return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tunnel_key_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static void tcf_tunnel_encap_put_tunnel(void *priv) { - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + struct ip_tunnel_info *tunnel = priv; - return tcf_generic_walker(tn, skb, cb, type, ops); + kfree(tunnel); } -static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_tunnel_encap_get_tunnel(struct flow_action_entry *entry, + const struct tc_action *act) { - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + entry->tunnel = tcf_tunnel_info_copy(act); + if (!entry->tunnel) + return -ENOMEM; + entry->destructor = tcf_tunnel_encap_put_tunnel; + entry->destructor_priv = entry->tunnel; + return 0; +} + +static int tcf_tunnel_key_offload_act_setup(struct tc_action *act, + void *entry_data, + u32 *index_inc, + bool bind, + struct netlink_ext_ack *extack) +{ + int err; - return tcf_hash_search(tn, a, index); + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_tunnel_set(act)) { + entry->id = FLOW_ACTION_TUNNEL_ENCAP; + err = tcf_tunnel_encap_get_tunnel(entry, act); + if (err) + return err; + } else if (is_tcf_tunnel_release(act)) { + entry->id = FLOW_ACTION_TUNNEL_DECAP; + } else { + NL_SET_ERR_MSG_MOD(extack, "Unsupported tunnel key mode offload"); + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_tunnel_set(act)) + fl_action->id = FLOW_ACTION_TUNNEL_ENCAP; + else if (is_tcf_tunnel_release(act)) + fl_action->id = FLOW_ACTION_TUNNEL_DECAP; + else + return -EOPNOTSUPP; + } + + return 0; } static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", - .type = TCA_ACT_TUNNEL_KEY, + .id = TCA_ID_TUNNEL_KEY, .owner = THIS_MODULE, .act = tunnel_key_act, .dump = tunnel_key_dump, .init = tunnel_key_init, .cleanup = tunnel_key_release, - .walk = tunnel_key_walker, - .lookup = tunnel_key_search, + .offload_act_setup = tcf_tunnel_key_offload_act_setup, .size = sizeof(struct tcf_tunnel_key), }; +MODULE_ALIAS_NET_ACT("tunnel_key"); static __net_init int tunnel_key_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + struct tc_action_net *tn = net_generic(net, act_tunnel_key_ops.net_id); - return tc_action_net_init(tn, &act_tunnel_key_ops, TUNNEL_KEY_TAB_MASK); + return tc_action_net_init(net, tn, &act_tunnel_key_ops); } -static void __net_exit tunnel_key_exit_net(struct net *net) +static void __net_exit tunnel_key_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_tunnel_key_ops.net_id); } static struct pernet_operations tunnel_key_net_ops = { .init = tunnel_key_init_net, - .exit = tunnel_key_exit_net, - .id = &tunnel_key_net_id, + .exit_batch = tunnel_key_exit_net, + .id = &act_tunnel_key_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 13ba3a89f675..a74621797d69 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -1,10 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include <linux/module.h> @@ -15,27 +11,25 @@ #include <linux/if_vlan.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> #include <linux/tc_act/tc_vlan.h> #include <net/tc_act/tc_vlan.h> -#define VLAN_TAB_MASK 15 - -static unsigned int vlan_net_id; static struct tc_action_ops act_vlan_ops; -static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) +TC_INDIRECT_SCOPE int tcf_vlan_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) { struct tcf_vlan *v = to_vlan(a); - int action; + struct tcf_vlan_params *p; int err; u16 tci; - spin_lock(&v->tcf_lock); tcf_lastuse_update(&v->tcf_tm); - bstats_update(&v->tcf_bstats, skb); - action = v->tcf_action; + tcf_action_update_bstats(&v->common, skb); /* Ensure 'data' points at mac_header prior calling vlan manipulating * functions. @@ -43,26 +37,28 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, if (skb_at_tc_ingress(skb)) skb_push_rcsum(skb, skb->mac_len); - switch (v->tcfv_action) { + p = rcu_dereference_bh(v->vlan_p); + + switch (p->tcfv_action) { case TCA_VLAN_ACT_POP: err = skb_vlan_pop(skb); if (err) goto drop; break; case TCA_VLAN_ACT_PUSH: - err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid | - (v->tcfv_push_prio << VLAN_PRIO_SHIFT)); + err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid | + (p->tcfv_push_prio << VLAN_PRIO_SHIFT)); if (err) goto drop; break; case TCA_VLAN_ACT_MODIFY: /* No-op if no vlan tag (either hw-accel or in-payload) */ if (!skb_vlan_tagged(skb)) - goto unlock; + goto out; /* extract existing tag (and guarantee no hw-accel tag) */ if (skb_vlan_tag_present(skb)) { tci = skb_vlan_tag_get(skb); - skb->vlan_tci = 0; + __vlan_hwaccel_clear_tag(skb); } else { /* in-payload vlan tag, pop it */ err = __skb_vlan_pop(skb, &tci); @@ -70,67 +66,90 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, goto drop; } /* replace the vid */ - tci = (tci & ~VLAN_VID_MASK) | v->tcfv_push_vid; + tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid; /* replace prio bits, if tcfv_push_prio specified */ - if (v->tcfv_push_prio) { + if (p->tcfv_push_prio_exists) { tci &= ~VLAN_PRIO_MASK; - tci |= v->tcfv_push_prio << VLAN_PRIO_SHIFT; + tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT; } /* put updated tci as hwaccel tag */ - __vlan_hwaccel_put_tag(skb, v->tcfv_push_proto, tci); + __vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci); + break; + case TCA_VLAN_ACT_POP_ETH: + err = skb_eth_pop(skb); + if (err) + goto drop; + break; + case TCA_VLAN_ACT_PUSH_ETH: + err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src); + if (err) + goto drop; break; default: BUG(); } - goto unlock; - -drop: - action = TC_ACT_SHOT; - v->tcf_qstats.drops++; -unlock: +out: if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); - spin_unlock(&v->tcf_lock); - return action; + skb_reset_mac_len(skb); + return p->action; + +drop: + tcf_action_inc_drop_qstats(&v->common); + return TC_ACT_SHOT; } static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { + [TCA_VLAN_UNSPEC] = { .strict_start_type = TCA_VLAN_PUSH_ETH_DST }, [TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) }, [TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 }, + [TCA_VLAN_PUSH_ETH_DST] = NLA_POLICY_ETH_ADDR, + [TCA_VLAN_PUSH_ETH_SRC] = NLA_POLICY_ETH_ADDR, }; static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { - struct tc_action_net *tn = net_generic(net, vlan_net_id); + struct tc_action_net *tn = net_generic(net, act_vlan_ops.net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_VLAN_MAX + 1]; + struct tcf_chain *goto_ch = NULL; + bool push_prio_exists = false; + struct tcf_vlan_params *p; struct tc_vlan *parm; struct tcf_vlan *v; int action; - __be16 push_vid = 0; + u16 push_vid = 0; __be16 push_proto = 0; u8 push_prio = 0; bool exists = false; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; - err = nla_parse_nested(tb, TCA_VLAN_MAX, nla, vlan_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_VLAN_MAX, nla, vlan_policy, + NULL); if (err < 0) return err; if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); - exists = tcf_hash_check(tn, parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) - return 0; + return ACT_P_BOUND; switch (parm->v_action) { case TCA_VLAN_ACT_POP: @@ -139,13 +158,17 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, case TCA_VLAN_ACT_MODIFY: if (!tb[TCA_VLAN_PUSH_VLAN_ID]) { if (exists) - tcf_hash_release(*a, bind); + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); if (push_vid >= VLAN_VID_MASK) { if (exists) - tcf_hash_release(*a, bind); + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -ERANGE; } @@ -156,51 +179,107 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, case htons(ETH_P_8021AD): break; default: + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EPROTONOSUPPORT; } } else { push_proto = htons(ETH_P_8021Q); } - if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY]) + push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY]; + if (push_prio_exists) push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; + case TCA_VLAN_ACT_POP_ETH: + break; + case TCA_VLAN_ACT_PUSH_ETH: + if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) { + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); + return -EINVAL; + } + break; default: if (exists) - tcf_hash_release(*a, bind); + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EINVAL; } action = parm->v_action; if (!exists) { - ret = tcf_hash_create(tn, parm->index, est, a, - &act_vlan_ops, bind, false); - if (ret) + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_vlan_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; - } else { - tcf_hash_release(*a, bind); - if (!ovr) - return -EEXIST; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; } - v = to_vlan(*a); + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; - spin_lock_bh(&v->tcf_lock); + v = to_vlan(*a); - v->tcfv_action = action; - v->tcfv_push_vid = push_vid; - v->tcfv_push_prio = push_prio; - v->tcfv_push_proto = push_proto; + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + err = -ENOMEM; + goto put_chain; + } - v->tcf_action = parm->action; + p->tcfv_action = action; + p->tcfv_push_vid = push_vid; + p->tcfv_push_prio = push_prio; + p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH; + p->tcfv_push_proto = push_proto; + + if (action == TCA_VLAN_ACT_PUSH_ETH) { + nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST], + ETH_ALEN); + nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC], + ETH_ALEN); + } + p->action = parm->action; + spin_lock_bh(&v->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); spin_unlock_bh(&v->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_hash_insert(tn, *a); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (p) + kfree_rcu(p, rcu); + return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; +} + +static void tcf_vlan_cleanup(struct tc_action *a) +{ + struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p; + + p = rcu_dereference_protected(v->vlan_p, 1); + if (p) + kfree_rcu(p, rcu); } static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, @@ -208,83 +287,163 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p; struct tc_vlan opt = { .index = v->tcf_index, - .refcnt = v->tcf_refcnt - ref, - .bindcnt = v->tcf_bindcnt - bind, - .action = v->tcf_action, - .v_action = v->tcfv_action, + .refcnt = refcount_read(&v->tcf_refcnt) - ref, + .bindcnt = atomic_read(&v->tcf_bindcnt) - bind, }; struct tcf_t t; + rcu_read_lock(); + p = rcu_dereference(v->vlan_p); + opt.action = p->action; + opt.v_action = p->tcfv_action; if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if ((v->tcfv_action == TCA_VLAN_ACT_PUSH || - v->tcfv_action == TCA_VLAN_ACT_MODIFY) && - (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || + if ((p->tcfv_action == TCA_VLAN_ACT_PUSH || + p->tcfv_action == TCA_VLAN_ACT_MODIFY) && + (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, - v->tcfv_push_proto) || - (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, - v->tcfv_push_prio)))) + p->tcfv_push_proto) || + (p->tcfv_push_prio_exists && + nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio)))) goto nla_put_failure; + if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) { + if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN, + p->tcfv_push_dst)) + goto nla_put_failure; + if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN, + p->tcfv_push_src)) + goto nla_put_failure; + } + tcf_tm_dump(&t, &v->tcf_tm); if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD)) goto nla_put_failure; + rcu_read_unlock(); + return skb->len; nla_put_failure: + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } -static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, - struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) +static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) { - struct tc_action_net *tn = net_generic(net, vlan_net_id); + struct tcf_vlan *v = to_vlan(a); + struct tcf_t *tm = &v->tcf_tm; - return tcf_generic_walker(tn, skb, cb, type, ops); + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } -static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) +static size_t tcf_vlan_get_fill_size(const struct tc_action *act) { - struct tc_action_net *tn = net_generic(net, vlan_net_id); + return nla_total_size(sizeof(struct tc_vlan)) + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ +} - return tcf_hash_search(tn, a, index); +static int tcf_vlan_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + entry->id = FLOW_ACTION_VLAN_PUSH; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + case TCA_VLAN_ACT_POP: + entry->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + entry->id = FLOW_ACTION_VLAN_MANGLE; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + case TCA_VLAN_ACT_POP_ETH: + entry->id = FLOW_ACTION_VLAN_POP_ETH; + break; + case TCA_VLAN_ACT_PUSH_ETH: + entry->id = FLOW_ACTION_VLAN_PUSH_ETH; + tcf_vlan_push_eth(entry->vlan_push_eth.src, entry->vlan_push_eth.dst, act); + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported vlan action mode offload"); + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + fl_action->id = FLOW_ACTION_VLAN_PUSH; + break; + case TCA_VLAN_ACT_POP: + fl_action->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + fl_action->id = FLOW_ACTION_VLAN_MANGLE; + break; + case TCA_VLAN_ACT_POP_ETH: + fl_action->id = FLOW_ACTION_VLAN_POP_ETH; + break; + case TCA_VLAN_ACT_PUSH_ETH: + fl_action->id = FLOW_ACTION_VLAN_PUSH_ETH; + break; + default: + return -EOPNOTSUPP; + } + } + + return 0; } static struct tc_action_ops act_vlan_ops = { .kind = "vlan", - .type = TCA_ACT_VLAN, + .id = TCA_ID_VLAN, .owner = THIS_MODULE, - .act = tcf_vlan, + .act = tcf_vlan_act, .dump = tcf_vlan_dump, .init = tcf_vlan_init, - .walk = tcf_vlan_walker, - .lookup = tcf_vlan_search, + .cleanup = tcf_vlan_cleanup, + .stats_update = tcf_vlan_stats_update, + .get_fill_size = tcf_vlan_get_fill_size, + .offload_act_setup = tcf_vlan_offload_act_setup, .size = sizeof(struct tcf_vlan), }; +MODULE_ALIAS_NET_ACT("vlan"); static __net_init int vlan_init_net(struct net *net) { - struct tc_action_net *tn = net_generic(net, vlan_net_id); + struct tc_action_net *tn = net_generic(net, act_vlan_ops.net_id); - return tc_action_net_init(tn, &act_vlan_ops, VLAN_TAB_MASK); + return tc_action_net_init(net, tn, &act_vlan_ops); } -static void __net_exit vlan_exit_net(struct net *net) +static void __net_exit vlan_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, vlan_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, act_vlan_ops.net_id); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, - .exit = vlan_exit_net, - .id = &vlan_net_id, + .exit_batch = vlan_exit_net, + .id = &act_vlan_ops.net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/bpf_qdisc.c b/net/sched/bpf_qdisc.c new file mode 100644 index 000000000000..adcb618a2bfc --- /dev/null +++ b/net/sched/bpf_qdisc.c @@ -0,0 +1,472 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/types.h> +#include <linux/bpf_verifier.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/filter.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> + +#define QDISC_OP_IDX(op) (offsetof(struct Qdisc_ops, op) / sizeof(void (*)(void))) +#define QDISC_MOFF_IDX(moff) (moff / sizeof(void (*)(void))) + +static struct bpf_struct_ops bpf_Qdisc_ops; + +struct bpf_sched_data { + struct qdisc_watchdog watchdog; +}; + +struct bpf_sk_buff_ptr { + struct sk_buff *skb; +}; + +static int bpf_qdisc_init(struct btf *btf) +{ + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_qdisc_ids, struct, Qdisc) +BTF_ID_LIST_SINGLE(bpf_sk_buff_ids, struct, sk_buff) +BTF_ID_LIST_SINGLE(bpf_sk_buff_ptr_ids, struct, bpf_sk_buff_ptr) + +static bool bpf_qdisc_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + struct btf *btf = prog->aux->attach_btf; + u32 arg; + + arg = btf_ctx_arg_idx(btf, prog->aux->attach_func_proto, off); + if (prog->aux->attach_st_ops_member_off == offsetof(struct Qdisc_ops, enqueue)) { + if (arg == 2 && type == BPF_READ) { + info->reg_type = PTR_TO_BTF_ID | PTR_TRUSTED; + info->btf = btf; + info->btf_id = bpf_sk_buff_ptr_ids[0]; + return true; + } + } + + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_qdisc_qdisc_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, size_t *end) +{ + switch (off) { + case offsetof(struct Qdisc, limit): + *end = offsetofend(struct Qdisc, limit); + break; + case offsetof(struct Qdisc, q) + offsetof(struct qdisc_skb_head, qlen): + *end = offsetof(struct Qdisc, q) + offsetofend(struct qdisc_skb_head, qlen); + break; + case offsetof(struct Qdisc, qstats) ... offsetofend(struct Qdisc, qstats) - 1: + *end = offsetofend(struct Qdisc, qstats); + break; + default: + return -EACCES; + } + + return 0; +} + +static int bpf_qdisc_sk_buff_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, size_t *end) +{ + switch (off) { + case offsetof(struct sk_buff, tstamp): + *end = offsetofend(struct sk_buff, tstamp); + break; + case offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data[0]) ... + offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, + data[QDISC_CB_PRIV_LEN - 1]): + *end = offsetof(struct sk_buff, cb) + + offsetofend(struct qdisc_skb_cb, data[QDISC_CB_PRIV_LEN - 1]); + break; + default: + return -EACCES; + } + + return 0; +} + +static int bpf_qdisc_btf_struct_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, int size) +{ + const struct btf_type *t, *skbt, *qdisct; + size_t end; + int err; + + skbt = btf_type_by_id(reg->btf, bpf_sk_buff_ids[0]); + qdisct = btf_type_by_id(reg->btf, bpf_qdisc_ids[0]); + t = btf_type_by_id(reg->btf, reg->btf_id); + + if (t == skbt) { + err = bpf_qdisc_sk_buff_access(log, reg, off, &end); + } else if (t == qdisct) { + err = bpf_qdisc_qdisc_access(log, reg, off, &end); + } else { + bpf_log(log, "only read is supported\n"); + return -EACCES; + } + + if (err) { + bpf_log(log, "no write support to %s at off %d\n", + btf_name_by_offset(reg->btf, t->name_off), off); + return -EACCES; + } + + if (off + size > end) { + bpf_log(log, + "write access at off %d with size %d beyond the member of %s ended at %zu\n", + off, size, btf_name_by_offset(reg->btf, t->name_off), end); + return -EACCES; + } + + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_qdisc_init_prologue_ids, func, bpf_qdisc_init_prologue) + +static int bpf_qdisc_gen_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + if (prog->aux->attach_st_ops_member_off != offsetof(struct Qdisc_ops, init)) + return 0; + + /* r6 = r1; // r6 will be "u64 *ctx". r1 is "u64 *ctx". + * r2 = r1[16]; // r2 will be "struct netlink_ext_ack *extack" + * r1 = r1[0]; // r1 will be "struct Qdisc *sch" + * r0 = bpf_qdisc_init_prologue(r1, r2); + * if r0 == 0 goto pc+1; + * BPF_EXIT; + * r1 = r6; // r1 will be "u64 *ctx". + */ + *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 16); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0); + *insn++ = BPF_CALL_KFUNC(0, bpf_qdisc_init_prologue_ids[0]); + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1); + *insn++ = BPF_EXIT_INSN(); + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + *insn++ = prog->insnsi[0]; + + return insn - insn_buf; +} + +BTF_ID_LIST_SINGLE(bpf_qdisc_reset_destroy_epilogue_ids, func, bpf_qdisc_reset_destroy_epilogue) + +static int bpf_qdisc_gen_epilogue(struct bpf_insn *insn_buf, const struct bpf_prog *prog, + s16 ctx_stack_off) +{ + struct bpf_insn *insn = insn_buf; + + if (prog->aux->attach_st_ops_member_off != offsetof(struct Qdisc_ops, reset) && + prog->aux->attach_st_ops_member_off != offsetof(struct Qdisc_ops, destroy)) + return 0; + + /* r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx" + * r1 = r1[0]; // r1 will be "struct Qdisc *sch" + * r0 = bpf_qdisc_reset_destroy_epilogue(r1); + * BPF_EXIT; + */ + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0); + *insn++ = BPF_CALL_KFUNC(0, bpf_qdisc_reset_destroy_epilogue_ids[0]); + *insn++ = BPF_EXIT_INSN(); + + return insn - insn_buf; +} + +__bpf_kfunc_start_defs(); + +/* bpf_skb_get_hash - Get the flow hash of an skb. + * @skb: The skb to get the flow hash from. + */ +__bpf_kfunc u32 bpf_skb_get_hash(struct sk_buff *skb) +{ + return skb_get_hash(skb); +} + +/* bpf_kfree_skb - Release an skb's reference and drop it immediately. + * @skb: The skb whose reference to be released and dropped. + */ +__bpf_kfunc void bpf_kfree_skb(struct sk_buff *skb) +{ + kfree_skb(skb); +} + +/* bpf_qdisc_skb_drop - Drop an skb by adding it to a deferred free list. + * @skb: The skb whose reference to be released and dropped. + * @to_free_list: The list of skbs to be dropped. + */ +__bpf_kfunc void bpf_qdisc_skb_drop(struct sk_buff *skb, + struct bpf_sk_buff_ptr *to_free_list) +{ + __qdisc_drop(skb, (struct sk_buff **)to_free_list); +} + +/* bpf_qdisc_watchdog_schedule - Schedule a qdisc to a later time using a timer. + * @sch: The qdisc to be scheduled. + * @expire: The expiry time of the timer. + * @delta_ns: The slack range of the timer. + */ +__bpf_kfunc void bpf_qdisc_watchdog_schedule(struct Qdisc *sch, u64 expire, u64 delta_ns) +{ + struct bpf_sched_data *q = qdisc_priv(sch); + + qdisc_watchdog_schedule_range_ns(&q->watchdog, expire, delta_ns); +} + +/* bpf_qdisc_init_prologue - Hidden kfunc called in prologue of .init. */ +__bpf_kfunc int bpf_qdisc_init_prologue(struct Qdisc *sch, + struct netlink_ext_ack *extack) +{ + struct bpf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *p; + + qdisc_watchdog_init(&q->watchdog, sch); + + if (sch->parent != TC_H_ROOT) { + /* If qdisc_lookup() returns NULL, it means .init is called by + * qdisc_create_dflt() in mq/mqprio_init and the parent qdisc + * has not been added to qdisc_hash yet. + */ + p = qdisc_lookup(dev, TC_H_MAJ(sch->parent)); + if (p && !(p->flags & TCQ_F_MQROOT)) { + NL_SET_ERR_MSG(extack, "BPF qdisc only supported on root or mq"); + return -EINVAL; + } + } + + return 0; +} + +/* bpf_qdisc_reset_destroy_epilogue - Hidden kfunc called in epilogue of .reset + * and .destroy + */ +__bpf_kfunc void bpf_qdisc_reset_destroy_epilogue(struct Qdisc *sch) +{ + struct bpf_sched_data *q = qdisc_priv(sch); + + qdisc_watchdog_cancel(&q->watchdog); +} + +/* bpf_qdisc_bstats_update - Update Qdisc basic statistics + * @sch: The qdisc from which an skb is dequeued. + * @skb: The skb to be dequeued. + */ +__bpf_kfunc void bpf_qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb) +{ + bstats_update(&sch->bstats, skb); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(qdisc_kfunc_ids) +BTF_ID_FLAGS(func, bpf_skb_get_hash, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_kfree_skb, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_qdisc_skb_drop, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_qdisc_watchdog_schedule, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_qdisc_init_prologue, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_qdisc_reset_destroy_epilogue, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_qdisc_bstats_update, KF_TRUSTED_ARGS) +BTF_KFUNCS_END(qdisc_kfunc_ids) + +BTF_SET_START(qdisc_common_kfunc_set) +BTF_ID(func, bpf_skb_get_hash) +BTF_ID(func, bpf_kfree_skb) +BTF_ID(func, bpf_dynptr_from_skb) +BTF_SET_END(qdisc_common_kfunc_set) + +BTF_SET_START(qdisc_enqueue_kfunc_set) +BTF_ID(func, bpf_qdisc_skb_drop) +BTF_ID(func, bpf_qdisc_watchdog_schedule) +BTF_SET_END(qdisc_enqueue_kfunc_set) + +BTF_SET_START(qdisc_dequeue_kfunc_set) +BTF_ID(func, bpf_qdisc_watchdog_schedule) +BTF_ID(func, bpf_qdisc_bstats_update) +BTF_SET_END(qdisc_dequeue_kfunc_set) + +enum qdisc_ops_kf_flags { + QDISC_OPS_KF_COMMON = 0, + QDISC_OPS_KF_ENQUEUE = 1 << 0, + QDISC_OPS_KF_DEQUEUE = 1 << 1, +}; + +static const u32 qdisc_ops_context_flags[] = { + [QDISC_OP_IDX(enqueue)] = QDISC_OPS_KF_ENQUEUE, + [QDISC_OP_IDX(dequeue)] = QDISC_OPS_KF_DEQUEUE, + [QDISC_OP_IDX(init)] = QDISC_OPS_KF_COMMON, + [QDISC_OP_IDX(reset)] = QDISC_OPS_KF_COMMON, + [QDISC_OP_IDX(destroy)] = QDISC_OPS_KF_COMMON, +}; + +static int bpf_qdisc_kfunc_filter(const struct bpf_prog *prog, u32 kfunc_id) +{ + u32 moff, flags; + + if (!btf_id_set8_contains(&qdisc_kfunc_ids, kfunc_id)) + return 0; + + if (prog->aux->st_ops != &bpf_Qdisc_ops) + return -EACCES; + + moff = prog->aux->attach_st_ops_member_off; + flags = qdisc_ops_context_flags[QDISC_MOFF_IDX(moff)]; + + if ((flags & QDISC_OPS_KF_ENQUEUE) && + btf_id_set_contains(&qdisc_enqueue_kfunc_set, kfunc_id)) + return 0; + + if ((flags & QDISC_OPS_KF_DEQUEUE) && + btf_id_set_contains(&qdisc_dequeue_kfunc_set, kfunc_id)) + return 0; + + if (btf_id_set_contains(&qdisc_common_kfunc_set, kfunc_id)) + return 0; + + return -EACCES; +} + +static const struct btf_kfunc_id_set bpf_qdisc_kfunc_set = { + .owner = THIS_MODULE, + .set = &qdisc_kfunc_ids, + .filter = bpf_qdisc_kfunc_filter, +}; + +static const struct bpf_verifier_ops bpf_qdisc_verifier_ops = { + .get_func_proto = bpf_base_func_proto, + .is_valid_access = bpf_qdisc_is_valid_access, + .btf_struct_access = bpf_qdisc_btf_struct_access, + .gen_prologue = bpf_qdisc_gen_prologue, + .gen_epilogue = bpf_qdisc_gen_epilogue, +}; + +static int bpf_qdisc_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + const struct Qdisc_ops *uqdisc_ops; + struct Qdisc_ops *qdisc_ops; + u32 moff; + + uqdisc_ops = (const struct Qdisc_ops *)udata; + qdisc_ops = (struct Qdisc_ops *)kdata; + + moff = __btf_member_bit_offset(t, member) / 8; + switch (moff) { + case offsetof(struct Qdisc_ops, priv_size): + if (uqdisc_ops->priv_size) + return -EINVAL; + qdisc_ops->priv_size = sizeof(struct bpf_sched_data); + return 1; + case offsetof(struct Qdisc_ops, peek): + qdisc_ops->peek = qdisc_peek_dequeued; + return 0; + case offsetof(struct Qdisc_ops, id): + if (bpf_obj_name_cpy(qdisc_ops->id, uqdisc_ops->id, + sizeof(qdisc_ops->id)) <= 0) + return -EINVAL; + return 1; + } + + return 0; +} + +static int bpf_qdisc_reg(void *kdata, struct bpf_link *link) +{ + return register_qdisc(kdata); +} + +static void bpf_qdisc_unreg(void *kdata, struct bpf_link *link) +{ + return unregister_qdisc(kdata); +} + +static int bpf_qdisc_validate(void *kdata) +{ + struct Qdisc_ops *ops = (struct Qdisc_ops *)kdata; + + if (!ops->enqueue || !ops->dequeue || !ops->init || + !ops->reset || !ops->destroy) + return -EINVAL; + + return 0; +} + +static int Qdisc_ops__enqueue(struct sk_buff *skb__ref, struct Qdisc *sch, + struct sk_buff **to_free) +{ + return 0; +} + +static struct sk_buff *Qdisc_ops__dequeue(struct Qdisc *sch) +{ + return NULL; +} + +static int Qdisc_ops__init(struct Qdisc *sch, struct nlattr *arg, + struct netlink_ext_ack *extack) +{ + return 0; +} + +static void Qdisc_ops__reset(struct Qdisc *sch) +{ +} + +static void Qdisc_ops__destroy(struct Qdisc *sch) +{ +} + +static struct Qdisc_ops __bpf_ops_qdisc_ops = { + .enqueue = Qdisc_ops__enqueue, + .dequeue = Qdisc_ops__dequeue, + .init = Qdisc_ops__init, + .reset = Qdisc_ops__reset, + .destroy = Qdisc_ops__destroy, +}; + +static struct bpf_struct_ops bpf_Qdisc_ops = { + .verifier_ops = &bpf_qdisc_verifier_ops, + .reg = bpf_qdisc_reg, + .unreg = bpf_qdisc_unreg, + .validate = bpf_qdisc_validate, + .init_member = bpf_qdisc_init_member, + .init = bpf_qdisc_init, + .name = "Qdisc_ops", + .cfi_stubs = &__bpf_ops_qdisc_ops, + .owner = THIS_MODULE, +}; + +BTF_ID_LIST_SINGLE(bpf_sk_buff_dtor_ids, func, bpf_kfree_skb) + +static int __init bpf_qdisc_kfunc_init(void) +{ + int ret; + const struct btf_id_dtor_kfunc skb_kfunc_dtors[] = { + { + .btf_id = bpf_sk_buff_ids[0], + .kfunc_btf_id = bpf_sk_buff_dtor_ids[0] + }, + }; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_qdisc_kfunc_set); + ret = ret ?: register_btf_id_dtor_kfuncs(skb_kfunc_dtors, + ARRAY_SIZE(skb_kfunc_dtors), + THIS_MODULE); + ret = ret ?: register_bpf_struct_ops(&bpf_Qdisc_ops, Qdisc_ops); + + return ret; +} +late_initcall(bpf_qdisc_kfunc_init); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 39da0c5801c9..ebca4b926dcf 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1,17 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_api.c Packet classifier API. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * * Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support - * */ #include <linux/module.h> @@ -23,13 +18,30 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/kmod.h> -#include <linux/err.h> #include <linux/slab.h> +#include <linux/idr.h> +#include <linux/jhash.h> +#include <linux/rculist.h> +#include <linux/rhashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> +#include <net/tc_act/tc_pedit.h> +#include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_vlan.h> +#include <net/tc_act/tc_tunnel_key.h> +#include <net/tc_act/tc_csum.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_police.h> +#include <net/tc_act/tc_sample.h> +#include <net/tc_act/tc_skbedit.h> +#include <net/tc_act/tc_ct.h> +#include <net/tc_act/tc_mpls.h> +#include <net/tc_act/tc_gate.h> +#include <net/flow_offload.h> +#include <net/tc_wrapper.h> /* The list of all installed classifier types */ static LIST_HEAD(tcf_proto_base); @@ -37,9 +49,185 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +static struct xarray tcf_exts_miss_cookies_xa; +struct tcf_exts_miss_cookie_node { + const struct tcf_chain *chain; + const struct tcf_proto *tp; + const struct tcf_exts *exts; + u32 chain_index; + u32 tp_prio; + u32 handle; + u32 miss_cookie_base; + struct rcu_head rcu; +}; + +/* Each tc action entry cookie will be comprised of 32bit miss_cookie_base + + * action index in the exts tc actions array. + */ +union tcf_exts_miss_cookie { + struct { + u32 miss_cookie_base; + u32 act_index; + }; + u64 miss_cookie; +}; + +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static int +tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, + u32 handle) +{ + struct tcf_exts_miss_cookie_node *n; + static u32 next; + int err; + + if (WARN_ON(!handle || !tp->ops->get_exts)) + return -EINVAL; + + n = kzalloc(sizeof(*n), GFP_KERNEL); + if (!n) + return -ENOMEM; + + n->chain_index = tp->chain->index; + n->chain = tp->chain; + n->tp_prio = tp->prio; + n->tp = tp; + n->exts = exts; + n->handle = handle; + + err = xa_alloc_cyclic(&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, + n, xa_limit_32b, &next, GFP_KERNEL); + if (err < 0) + goto err_xa_alloc; + + exts->miss_cookie_node = n; + return 0; + +err_xa_alloc: + kfree(n); + return err; +} + +static void tcf_exts_miss_cookie_base_destroy(struct tcf_exts *exts) +{ + struct tcf_exts_miss_cookie_node *n; + + if (!exts->miss_cookie_node) + return; + + n = exts->miss_cookie_node; + xa_erase(&tcf_exts_miss_cookies_xa, n->miss_cookie_base); + kfree_rcu(n, rcu); +} + +static struct tcf_exts_miss_cookie_node * +tcf_exts_miss_cookie_lookup(u64 miss_cookie, int *act_index) +{ + union tcf_exts_miss_cookie mc = { .miss_cookie = miss_cookie, }; + + *act_index = mc.act_index; + return xa_load(&tcf_exts_miss_cookies_xa, mc.miss_cookie_base); +} +#else /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ +static int +tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, + u32 handle) +{ + return 0; +} + +static void tcf_exts_miss_cookie_base_destroy(struct tcf_exts *exts) +{ +} +#endif /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ + +static u64 tcf_exts_miss_cookie_get(u32 miss_cookie_base, int act_index) +{ + union tcf_exts_miss_cookie mc = { .act_index = act_index, }; + + if (!miss_cookie_base) + return 0; + + mc.miss_cookie_base = miss_cookie_base; + return mc.miss_cookie; +} + +#ifdef CONFIG_NET_CLS_ACT +DEFINE_STATIC_KEY_FALSE(tc_skb_ext_tc); +EXPORT_SYMBOL(tc_skb_ext_tc); + +void tc_skb_ext_tc_enable(void) +{ + static_branch_inc(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_enable); + +void tc_skb_ext_tc_disable(void) +{ + static_branch_dec(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_disable); +#endif + +static u32 destroy_obj_hashfn(const struct tcf_proto *tp) +{ + return jhash_3words(tp->chain->index, tp->prio, + (__force __u32)tp->protocol, 0); +} + +static void tcf_proto_signal_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node, + destroy_obj_hashfn(tp)); + mutex_unlock(&block->proto_destroy_lock); +} + +static bool tcf_proto_cmp(const struct tcf_proto *tp1, + const struct tcf_proto *tp2) +{ + return tp1->chain->index == tp2->chain->index && + tp1->prio == tp2->prio && + tp1->protocol == tp2->protocol; +} + +static bool tcf_proto_exists_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + u32 hash = destroy_obj_hashfn(tp); + struct tcf_proto *iter; + bool found = false; + + rcu_read_lock(); + hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter, + destroy_ht_node, hash) { + if (tcf_proto_cmp(tp, iter)) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; +} + +static void +tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + if (hash_hashed(&tp->destroy_ht_node)) + hash_del_rcu(&tp->destroy_ht_node); + mutex_unlock(&block->proto_destroy_lock); +} + /* Find classifier type by string name */ -static const struct tcf_proto_ops *tcf_proto_lookup_ops(const char *kind) +static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) { const struct tcf_proto_ops *t, *res = NULL; @@ -57,6 +245,36 @@ static const struct tcf_proto_ops *tcf_proto_lookup_ops(const char *kind) return res; } +static const struct tcf_proto_ops * +tcf_proto_lookup_ops(const char *kind, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + const struct tcf_proto_ops *ops; + + ops = __tcf_proto_lookup_ops(kind); + if (ops) + return ops; +#ifdef CONFIG_MODULES + if (rtnl_held) + rtnl_unlock(); + request_module(NET_CLS_ALIAS_PREFIX "%s", kind); + if (rtnl_held) + rtnl_lock(); + ops = __tcf_proto_lookup_ops(kind); + /* We dropped the RTNL semaphore in order to perform + * the module load. So, even if we succeeded in loading + * the module we have to replay the request. We indicate + * this using -EAGAIN. + */ + if (ops) { + module_put(ops->owner); + return ERR_PTR(-EAGAIN); + } +#endif + NL_SET_ERR_MSG(extack, "TC classifier not found"); + return ERR_PTR(-ENOENT); +} + /* Register(unregister) new classifier type */ int register_tcf_proto_ops(struct tcf_proto_ops *ops) @@ -77,7 +295,9 @@ out: } EXPORT_SYMBOL(register_tcf_proto_ops); -int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) +static struct workqueue_struct *tc_filter_wq; + +void unregister_tcf_proto_ops(struct tcf_proto_ops *ops) { struct tcf_proto_ops *t; int rc = -ENOENT; @@ -86,6 +306,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) * tcf_proto_ops's destroy() handler. */ rcu_barrier(); + flush_workqueue(tc_filter_wq); write_lock(&cls_mod_lock); list_for_each_entry(t, &tcf_proto_base, head) { @@ -96,24 +317,17 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) } } write_unlock(&cls_mod_lock); - return rc; + + WARN(rc, "unregister tc filter kind(%s) failed %d\n", ops->kind, rc); } EXPORT_SYMBOL(unregister_tcf_proto_ops); -static int tfilter_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, struct tcf_proto *tp, - unsigned long fh, int event, bool unicast); - -static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, - struct tcf_chain *chain, int event) +bool tcf_queue_work(struct rcu_work *rwork, work_func_t func) { - struct tcf_proto *tp; - - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, 0, event, false); + INIT_RCU_WORK(rwork, func); + return queue_rcu_work(tc_filter_wq, rwork); } +EXPORT_SYMBOL(tcf_queue_work); /* Select new prio value from the range, managed by kernel. */ @@ -127,9 +341,38 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_check_kind(struct nlattr *kind, char *name) +{ + if (kind) + return nla_strscpy(name, kind, IFNAMSIZ) < 0; + memset(name, 0, IFNAMSIZ); + return false; +} + +static bool tcf_proto_is_unlocked(const char *kind) +{ + const struct tcf_proto_ops *ops; + bool ret; + + if (strlen(kind) == 0) + return false; + + ops = tcf_proto_lookup_ops(kind, false, NULL); + /* On error return false to take rtnl lock. Proto lookup/create + * functions will perform lookup again and properly handle errors. + */ + if (IS_ERR(ops)) + return false; + + ret = !!(ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED); + module_put(ops->owner); + return ret; +} + static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, - u32 prio, u32 parent, struct Qdisc *q, - struct tcf_chain *chain) + u32 prio, struct tcf_chain *chain, + bool rtnl_held, + struct netlink_ext_ack *extack) { struct tcf_proto *tp; int err; @@ -138,34 +381,18 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, if (!tp) return ERR_PTR(-ENOBUFS); - err = -ENOENT; - tp->ops = tcf_proto_lookup_ops(kind); - if (!tp->ops) { -#ifdef CONFIG_MODULES - rtnl_unlock(); - request_module("cls_%s", kind); - rtnl_lock(); - tp->ops = tcf_proto_lookup_ops(kind); - /* We dropped the RTNL semaphore in order to perform - * the module load. So, even if we succeeded in loading - * the module we have to replay the request. We indicate - * this using -EAGAIN. - */ - if (tp->ops) { - module_put(tp->ops->owner); - err = -EAGAIN; - } else { - err = -ENOENT; - } + tp->ops = tcf_proto_lookup_ops(kind, rtnl_held, extack); + if (IS_ERR(tp->ops)) { + err = PTR_ERR(tp->ops); goto errout; -#endif } tp->classify = tp->ops->classify; tp->protocol = protocol; tp->prio = prio; - tp->classid = parent; - tp->q = q; tp->chain = chain; + tp->usesw = !tp->ops->reoffload; + spin_lock_init(&tp->lock); + refcount_set(&tp->refcnt, 1); err = tp->ops->init(tp); if (err) { @@ -179,151 +406,1371 @@ errout: return ERR_PTR(err); } -static void tcf_proto_destroy(struct tcf_proto *tp) +static void tcf_proto_get(struct tcf_proto *tp) +{ + refcount_inc(&tp->refcnt); +} + +static void tcf_proto_count_usesw(struct tcf_proto *tp, bool add) { - tp->ops->destroy(tp); +#ifdef CONFIG_NET_CLS_ACT + struct tcf_block *block = tp->chain->block; + bool counted = false; + + if (!add) { + if (tp->usesw && tp->counted) { + if (!atomic_dec_return(&block->useswcnt)) + static_branch_dec(&tcf_sw_enabled_key); + tp->counted = false; + } + return; + } + + spin_lock(&tp->lock); + if (tp->usesw && !tp->counted) { + counted = true; + tp->counted = true; + } + spin_unlock(&tp->lock); + + if (counted && atomic_inc_return(&block->useswcnt) == 1) + static_branch_inc(&tcf_sw_enabled_key); +#endif +} + +static void tcf_chain_put(struct tcf_chain *chain); + +static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, + bool sig_destroy, struct netlink_ext_ack *extack) +{ + tp->ops->destroy(tp, rtnl_held, extack); + tcf_proto_count_usesw(tp, false); + if (sig_destroy) + tcf_proto_signal_destroyed(tp->chain, tp); + tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); } +static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + if (refcount_dec_and_test(&tp->refcnt)) + tcf_proto_destroy(tp, rtnl_held, true, extack); +} + +static bool tcf_proto_check_delete(struct tcf_proto *tp) +{ + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); + + tp->deleting = true; + return tp->deleting; +} + +static void tcf_proto_mark_delete(struct tcf_proto *tp) +{ + spin_lock(&tp->lock); + tp->deleting = true; + spin_unlock(&tp->lock); +} + +static bool tcf_proto_is_deleting(struct tcf_proto *tp) +{ + bool deleting; + + spin_lock(&tp->lock); + deleting = tp->deleting; + spin_unlock(&tp->lock); + + return deleting; +} + +#define ASSERT_BLOCK_LOCKED(block) \ + lockdep_assert_held(&(block)->lock) + +struct tcf_filter_chain_list_item { + struct list_head list; + tcf_chain_head_change_t *chain_head_change; + void *chain_head_change_priv; +}; + static struct tcf_chain *tcf_chain_create(struct tcf_block *block, u32 chain_index) { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (!chain) return NULL; - list_add_tail(&chain->list, &block->chain_list); + list_add_tail_rcu(&chain->list, &block->chain_list); + mutex_init(&chain->filter_chain_lock); chain->block = block; chain->index = chain_index; chain->refcnt = 1; + if (!chain->index) + block->chain0.chain = chain; return chain; } -static void tcf_chain_flush(struct tcf_chain *chain) +static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item, + struct tcf_proto *tp_head) { - struct tcf_proto *tp; + if (item->chain_head_change) + item->chain_head_change(tp_head, item->chain_head_change_priv); +} - if (*chain->p_filter_chain) - RCU_INIT_POINTER(*chain->p_filter_chain, NULL); - while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { - RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_proto_destroy(tp); - } +static void tcf_chain0_head_change(struct tcf_chain *chain, + struct tcf_proto *tp_head) +{ + struct tcf_filter_chain_list_item *item; + struct tcf_block *block = chain->block; + + if (chain->index) + return; + + mutex_lock(&block->lock); + list_for_each_entry(item, &block->chain0.filter_chain_list, list) + tcf_chain_head_change_item(item, tp_head); + mutex_unlock(&block->lock); +} + +/* Returns true if block can be safely freed. */ + +static bool tcf_chain_detach(struct tcf_chain *chain) +{ + struct tcf_block *block = chain->block; + + ASSERT_BLOCK_LOCKED(block); + + list_del_rcu(&chain->list); + if (!chain->index) + block->chain0.chain = NULL; + + if (list_empty(&block->chain_list) && + refcount_read(&block->refcnt) == 0) + return true; + + return false; } -static void tcf_chain_destroy(struct tcf_chain *chain) +static void tcf_block_destroy(struct tcf_block *block) { - list_del(&chain->list); - tcf_chain_flush(chain); - kfree(chain); + mutex_destroy(&block->lock); + mutex_destroy(&block->proto_destroy_lock); + xa_destroy(&block->ports); + kfree_rcu(block, rcu); } -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, - bool create) +static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block) +{ + struct tcf_block *block = chain->block; + + mutex_destroy(&chain->filter_chain_lock); + kfree_rcu(chain, rcu); + if (free_block) + tcf_block_destroy(block); +} + +static void tcf_chain_hold(struct tcf_chain *chain) +{ + ASSERT_BLOCK_LOCKED(chain->block); + + ++chain->refcnt; +} + +static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain) +{ + ASSERT_BLOCK_LOCKED(chain->block); + + /* In case all the references are action references, this + * chain should not be shown to the user. + */ + return chain->refcnt == chain->action_refcnt; +} + +static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, + u32 chain_index) { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + list_for_each_entry(chain, &block->chain_list, list) { - if (chain->index == chain_index) { - chain->refcnt++; + if (chain->index == chain_index) return chain; + } + return NULL; +} + +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block, + u32 chain_index) +{ + struct tcf_chain *chain; + + list_for_each_entry_rcu(chain, &block->chain_list, list) { + if (chain->index == chain_index) + return chain; + } + return NULL; +} +#endif + +static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack); + +static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, + u32 chain_index, bool create, + bool by_act) +{ + struct tcf_chain *chain = NULL; + bool is_first_reference; + + mutex_lock(&block->lock); + chain = tcf_chain_lookup(block, chain_index); + if (chain) { + tcf_chain_hold(chain); + } else { + if (!create) + goto errout; + chain = tcf_chain_create(block, chain_index); + if (!chain) + goto errout; + } + + if (by_act) + ++chain->action_refcnt; + is_first_reference = chain->refcnt - chain->action_refcnt == 1; + mutex_unlock(&block->lock); + + /* Send notification only in case we got the first + * non-action reference. Until then, the chain acts only as + * a placeholder for actions pointing to it and user ought + * not know about them. + */ + if (is_first_reference && !by_act) + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, + RTM_NEWCHAIN, false, NULL); + + return chain; + +errout: + mutex_unlock(&block->lock); + return chain; +} + +static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create) +{ + return __tcf_chain_get(block, chain_index, create, false); +} + +struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index) +{ + return __tcf_chain_get(block, chain_index, true, true); +} +EXPORT_SYMBOL(tcf_chain_get_by_act); + +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv); +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags); + +static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, + bool explicitly_created) +{ + struct tcf_block *block = chain->block; + const struct tcf_proto_ops *tmplt_ops; + unsigned int refcnt, non_act_refcnt; + bool free_block = false; + void *tmplt_priv; + + mutex_lock(&block->lock); + if (explicitly_created) { + if (!chain->explicitly_created) { + mutex_unlock(&block->lock); + return; } + chain->explicitly_created = false; } - if (create) - return tcf_chain_create(block, chain_index); - else - return NULL; + + if (by_act) + chain->action_refcnt--; + + /* tc_chain_notify_delete can't be called while holding block lock. + * However, when block is unlocked chain can be changed concurrently, so + * save these to temporary variables. + */ + refcnt = --chain->refcnt; + non_act_refcnt = refcnt - chain->action_refcnt; + tmplt_ops = chain->tmplt_ops; + tmplt_priv = chain->tmplt_priv; + + if (non_act_refcnt == chain->explicitly_created && !by_act) { + if (non_act_refcnt == 0) + tc_chain_notify_delete(tmplt_ops, tmplt_priv, + chain->index, block, NULL, 0, 0); + /* Last reference to chain, no need to lock. */ + chain->flushing = false; + } + + if (refcnt == 0) + free_block = tcf_chain_detach(chain); + mutex_unlock(&block->lock); + + if (refcnt == 0) { + tc_chain_tmplt_del(tmplt_ops, tmplt_priv); + tcf_chain_destroy(chain, free_block); + } +} + +static void tcf_chain_put(struct tcf_chain *chain) +{ + __tcf_chain_put(chain, false, false); +} + +void tcf_chain_put_by_act(struct tcf_chain *chain) +{ + __tcf_chain_put(chain, true, false); +} +EXPORT_SYMBOL(tcf_chain_put_by_act); + +static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) +{ + __tcf_chain_put(chain, false, true); } -EXPORT_SYMBOL(tcf_chain_get); -void tcf_chain_put(struct tcf_chain *chain) +static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) { - /* Destroy unused chain, with exception of chain 0, which is the - * default one and has to be always present. + struct tcf_proto *tp, *tp_next; + + mutex_lock(&chain->filter_chain_lock); + tp = tcf_chain_dereference(chain->filter_chain, chain); + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_signal_destroying(chain, tp); + tp = tp_next; + } + tp = tcf_chain_dereference(chain->filter_chain, chain); + RCU_INIT_POINTER(chain->filter_chain, NULL); + tcf_chain0_head_change(chain, NULL); + chain->flushing = true; + mutex_unlock(&chain->filter_chain_lock); + + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_put(tp, rtnl_held, NULL); + tp = tp_next; + } +} + +static int tcf_block_setup(struct tcf_block *block, + struct flow_block_offload *bo); + +static void tcf_block_offload_init(struct flow_block_offload *bo, + struct net_device *dev, struct Qdisc *sch, + enum flow_block_command command, + enum flow_block_binder_type binder_type, + struct flow_block *flow_block, + bool shared, struct netlink_ext_ack *extack) +{ + bo->net = dev_net(dev); + bo->command = command; + bo->binder_type = binder_type; + bo->block = flow_block; + bo->block_shared = shared; + bo->extack = extack; + bo->sch = sch; + bo->cb_list_head = &flow_block->cb_list; + INIT_LIST_HEAD(&bo->cb_list); +} + +static void tcf_block_unbind(struct tcf_block *block, + struct flow_block_offload *bo); + +static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) +{ + struct tcf_block *block = block_cb->indr.data; + struct net_device *dev = block_cb->indr.dev; + struct Qdisc *sch = block_cb->indr.sch; + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + + tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND, + block_cb->indr.binder_type, + &block->flow_block, tcf_block_shared(block), + &extack); + rtnl_lock(); + down_write(&block->cb_lock); + list_del(&block_cb->driver_list); + list_move(&block_cb->list, &bo.cb_list); + tcf_block_unbind(block, &bo); + up_write(&block->cb_lock); + rtnl_unlock(); +} + +static bool tcf_block_offload_in_use(struct tcf_block *block) +{ + return atomic_read(&block->offloadcnt); +} + +static int tcf_block_offload_cmd(struct tcf_block *block, + struct net_device *dev, struct Qdisc *sch, + struct tcf_block_ext_info *ei, + enum flow_block_command command, + struct netlink_ext_ack *extack) +{ + struct flow_block_offload bo = {}; + + tcf_block_offload_init(&bo, dev, sch, command, ei->binder_type, + &block->flow_block, tcf_block_shared(block), + extack); + + if (dev->netdev_ops->ndo_setup_tc) { + int err; + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + if (err < 0) { + if (err != -EOPNOTSUPP) + NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); + return err; + } + + return tcf_block_setup(block, &bo); + } + + flow_indr_dev_setup_offload(dev, sch, TC_SETUP_BLOCK, block, &bo, + tc_block_indr_cleanup); + tcf_block_setup(block, &bo); + + return -EOPNOTSUPP; +} + +static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = q->dev_queue->dev; + int err; + + down_write(&block->cb_lock); + + /* If tc offload feature is disabled and the block we try to bind + * to already has some offloaded filters, forbid to bind. */ - if (--chain->refcnt == 0 && !chain->filter_chain && chain->index != 0) - tcf_chain_destroy(chain); + if (dev->netdev_ops->ndo_setup_tc && + !tc_can_offload(dev) && + tcf_block_offload_in_use(block)) { + NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled"); + err = -EOPNOTSUPP; + goto err_unlock; + } + + err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_BIND, extack); + if (err == -EOPNOTSUPP) + goto no_offload_dev_inc; + if (err) + goto err_unlock; + + up_write(&block->cb_lock); + return 0; + +no_offload_dev_inc: + if (tcf_block_offload_in_use(block)) + goto err_unlock; + + err = 0; + block->nooffloaddevcnt++; +err_unlock: + up_write(&block->cb_lock); + return err; +} + +static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) +{ + struct net_device *dev = q->dev_queue->dev; + int err; + + down_write(&block->cb_lock); + err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_UNBIND, NULL); + if (err == -EOPNOTSUPP) + goto no_offload_dev_dec; + up_write(&block->cb_lock); + return; + +no_offload_dev_dec: + WARN_ON(block->nooffloaddevcnt-- == 0); + up_write(&block->cb_lock); +} + +static int +tcf_chain0_head_change_cb_add(struct tcf_block *block, + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) +{ + struct tcf_filter_chain_list_item *item; + struct tcf_chain *chain0; + + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) { + NL_SET_ERR_MSG(extack, "Memory allocation for head change callback item failed"); + return -ENOMEM; + } + item->chain_head_change = ei->chain_head_change; + item->chain_head_change_priv = ei->chain_head_change_priv; + + mutex_lock(&block->lock); + chain0 = block->chain0.chain; + if (chain0) + tcf_chain_hold(chain0); + else + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + if (chain0) { + struct tcf_proto *tp_head; + + mutex_lock(&chain0->filter_chain_lock); + + tp_head = tcf_chain_dereference(chain0->filter_chain, chain0); + if (tp_head) + tcf_chain_head_change_item(item, tp_head); + + mutex_lock(&block->lock); + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + mutex_unlock(&chain0->filter_chain_lock); + tcf_chain_put(chain0); + } + + return 0; } -EXPORT_SYMBOL(tcf_chain_put); static void -tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, - struct tcf_proto __rcu **p_filter_chain) +tcf_chain0_head_change_cb_del(struct tcf_block *block, + struct tcf_block_ext_info *ei) { - chain->p_filter_chain = p_filter_chain; + struct tcf_filter_chain_list_item *item; + + mutex_lock(&block->lock); + list_for_each_entry(item, &block->chain0.filter_chain_list, list) { + if ((!ei->chain_head_change && !ei->chain_head_change_priv) || + (item->chain_head_change == ei->chain_head_change && + item->chain_head_change_priv == ei->chain_head_change_priv)) { + if (block->chain0.chain) + tcf_chain_head_change_item(item, NULL); + list_del(&item->list); + mutex_unlock(&block->lock); + + kfree(item); + return; + } + } + mutex_unlock(&block->lock); + WARN_ON(1); } -int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain) +struct tcf_net { + spinlock_t idr_lock; /* Protects idr */ + struct idr idr; +}; + +static unsigned int tcf_net_id; + +static int tcf_block_insert(struct tcf_block *block, struct net *net, + struct netlink_ext_ack *extack) { - struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); - struct tcf_chain *chain; + struct tcf_net *tn = net_generic(net, tcf_net_id); int err; - if (!block) - return -ENOMEM; + idr_preload(GFP_KERNEL); + spin_lock(&tn->idr_lock); + err = idr_alloc_u32(&tn->idr, block, &block->index, block->index, + GFP_NOWAIT); + spin_unlock(&tn->idr_lock); + idr_preload_end(); + + return err; +} + +static void tcf_block_remove(struct tcf_block *block, struct net *net) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + spin_lock(&tn->idr_lock); + idr_remove(&tn->idr, block->index); + spin_unlock(&tn->idr_lock); +} + +static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, + u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + + block = kzalloc(sizeof(*block), GFP_KERNEL); + if (!block) { + NL_SET_ERR_MSG(extack, "Memory allocation for block failed"); + return ERR_PTR(-ENOMEM); + } + mutex_init(&block->lock); + mutex_init(&block->proto_destroy_lock); + init_rwsem(&block->cb_lock); + flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); - /* Create chain 0 by default, it has to be always present. */ - chain = tcf_chain_create(block, 0); - if (!chain) { - err = -ENOMEM; - goto err_chain_create; + INIT_LIST_HEAD(&block->owner_list); + INIT_LIST_HEAD(&block->chain0.filter_chain_list); + + refcount_set(&block->refcnt, 1); + block->net = net; + block->index = block_index; + xa_init(&block->ports); + + /* Don't store q pointer for blocks which are shared */ + if (!tcf_block_shared(block)) + block->q = q; + return block; +} + +struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + return idr_find(&tn->idr, block_index); +} +EXPORT_SYMBOL(tcf_block_lookup); + +static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) +{ + struct tcf_block *block; + + rcu_read_lock(); + block = tcf_block_lookup(net, block_index); + if (block && !refcount_inc_not_zero(&block->refcnt)) + block = NULL; + rcu_read_unlock(); + + return block; +} + +static struct tcf_chain * +__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) +{ + mutex_lock(&block->lock); + if (chain) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + else + chain = list_first_entry_or_null(&block->chain_list, + struct tcf_chain, list); + + /* skip all action-only chains */ + while (chain && tcf_chain_held_by_acts_only(chain)) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + + if (chain) + tcf_chain_hold(chain); + mutex_unlock(&block->lock); + + return chain; +} + +/* Function to be used by all clients that want to iterate over all chains on + * block. It properly obtains block->lock and takes reference to chain before + * returning it. Users of this function must be tolerant to concurrent chain + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_chain * +tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) +{ + struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain); + + if (chain) + tcf_chain_put(chain); + + return chain_next; +} +EXPORT_SYMBOL(tcf_get_next_chain); + +static struct tcf_proto * +__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp) +{ + u32 prio = 0; + + ASSERT_RTNL(); + mutex_lock(&chain->filter_chain_lock); + + if (!tp) { + tp = tcf_chain_dereference(chain->filter_chain, chain); + } else if (tcf_proto_is_deleting(tp)) { + /* 'deleting' flag is set and chain->filter_chain_lock was + * unlocked, which means next pointer could be invalid. Restart + * search. + */ + prio = tp->prio + 1; + tp = tcf_chain_dereference(chain->filter_chain, chain); + + for (; tp; tp = tcf_chain_dereference(tp->next, chain)) + if (!tp->deleting && tp->prio >= prio) + break; + } else { + tp = tcf_chain_dereference(tp->next, chain); + } + + if (tp) + tcf_proto_get(tp); + + mutex_unlock(&chain->filter_chain_lock); + + return tp; +} + +/* Function to be used by all clients that want to iterate over all tp's on + * chain. Users of this function must be tolerant to concurrent tp + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_proto * +tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp); + + if (tp) + tcf_proto_put(tp, true, NULL); + + return tp_next; +} +EXPORT_SYMBOL(tcf_get_next_proto); + +static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held) +{ + struct tcf_chain *chain; + + /* Last reference to block. At this point chains cannot be added or + * removed concurrently. + */ + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { + tcf_chain_put_explicitly_created(chain); + tcf_chain_flush(chain, rtnl_held); + } +} + +/* Lookup Qdisc and increments its reference counter. + * Set parent, if necessary. + */ + +static int __tcf_qdisc_find(struct net *net, struct Qdisc **q, + u32 *parent, int ifindex, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + const struct Qdisc_class_ops *cops; + struct net_device *dev; + int err = 0; + + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; + + rcu_read_lock(); + + /* Find link */ + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + + /* Find qdisc */ + if (!*parent) { + *q = rcu_dereference(dev->qdisc); + *parent = (*q)->handle; + } else { + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } + } + + *q = qdisc_refcount_inc_nz(*q); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } + + /* Is it classful? */ + cops = (*q)->ops->cl_ops; + if (!cops) { + NL_SET_ERR_MSG(extack, "Qdisc not classful"); + err = -EINVAL; + goto errout_qdisc; + } + + if (!cops->tcf_block) { + NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); + err = -EOPNOTSUPP; + goto errout_qdisc; + } + +errout_rcu: + /* At this point we know that qdisc is not noop_qdisc, + * which means that qdisc holds a reference to net_device + * and we hold a reference to qdisc, so it is safe to release + * rcu read lock. + */ + rcu_read_unlock(); + return err; + +errout_qdisc: + rcu_read_unlock(); + + if (rtnl_held) + qdisc_put(*q); + else + qdisc_put_unlocked(*q); + *q = NULL; + + return err; +} + +static int __tcf_qdisc_cl_find(struct Qdisc *q, u32 parent, unsigned long *cl, + int ifindex, struct netlink_ext_ack *extack) +{ + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; + + /* Do we search for filter, attached to class? */ + if (TC_H_MIN(parent)) { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + *cl = cops->find(q, parent); + if (*cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); + return -ENOENT; + } + } + + return 0; +} + +static struct tcf_block *__tcf_block_find(struct net *net, struct Qdisc *q, + unsigned long cl, int ifindex, + u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_refcnt_get(net, block_index); + if (!block) { + NL_SET_ERR_MSG(extack, "Block of given index was not found"); + return ERR_PTR(-EINVAL); + } + } else { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + block = cops->tcf_block(q, cl, extack); + if (!block) + return ERR_PTR(-EINVAL); + + if (tcf_block_shared(block)) { + NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); + return ERR_PTR(-EOPNOTSUPP); + } + + /* Always take reference to block in order to support execution + * of rules update path of cls API without rtnl lock. Caller + * must release block when it is finished using it. 'if' block + * of this conditional obtain reference to block by calling + * tcf_block_refcnt_get(). + */ + refcount_inc(&block->refcnt); + } + + return block; +} + +static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei, bool rtnl_held) +{ + if (refcount_dec_and_mutex_lock(&block->refcnt, &block->lock)) { + /* Flushing/putting all chains will cause the block to be + * deallocated when last chain is freed. However, if chain_list + * is empty, block has to be manually deallocated. After block + * reference counter reached 0, it is no longer possible to + * increment it or add new chains to block. + */ + bool free_block = list_empty(&block->chain_list); + + mutex_unlock(&block->lock); + if (tcf_block_shared(block)) + tcf_block_remove(block, block->net); + + if (q) + tcf_block_offload_unbind(block, q, ei); + + if (free_block) + tcf_block_destroy(block); + else + tcf_block_flush_all_chains(block, rtnl_held); + } else if (q) { + tcf_block_offload_unbind(block, q, ei); + } +} + +static void tcf_block_refcnt_put(struct tcf_block *block, bool rtnl_held) +{ + __tcf_block_put(block, NULL, NULL, rtnl_held); +} + +/* Find tcf block. + * Set q, parent, cl when appropriate. + */ + +static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, + u32 *parent, unsigned long *cl, + int ifindex, u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + int err = 0; + + ASSERT_RTNL(); + + err = __tcf_qdisc_find(net, q, parent, ifindex, true, extack); + if (err) + goto errout; + + err = __tcf_qdisc_cl_find(*q, *parent, cl, ifindex, extack); + if (err) + goto errout_qdisc; + + block = __tcf_block_find(net, *q, *cl, ifindex, block_index, extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto errout_qdisc; + } + + return block; + +errout_qdisc: + if (*q) + qdisc_put(*q); +errout: + *q = NULL; + return ERR_PTR(err); +} + +static void tcf_block_release(struct Qdisc *q, struct tcf_block *block, + bool rtnl_held) +{ + if (!IS_ERR_OR_NULL(block)) + tcf_block_refcnt_put(block, rtnl_held); + + if (q) { + if (rtnl_held) + qdisc_put(q); + else + qdisc_put_unlocked(q); + } +} + +struct tcf_block_owner_item { + struct list_head list; + struct Qdisc *q; + enum flow_block_binder_type binder_type; +}; + +static void +tcf_block_owner_netif_keep_dst(struct tcf_block *block, + struct Qdisc *q, + enum flow_block_binder_type binder_type) +{ + if (block->keep_dst && + binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS && + binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) + netif_keep_dst(qdisc_dev(q)); +} + +void tcf_block_netif_keep_dst(struct tcf_block *block) +{ + struct tcf_block_owner_item *item; + + block->keep_dst = true; + list_for_each_entry(item, &block->owner_list, list) + tcf_block_owner_netif_keep_dst(block, item->q, + item->binder_type); +} +EXPORT_SYMBOL(tcf_block_netif_keep_dst); + +static int tcf_block_owner_add(struct tcf_block *block, + struct Qdisc *q, + enum flow_block_binder_type binder_type) +{ + struct tcf_block_owner_item *item; + + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) + return -ENOMEM; + item->q = q; + item->binder_type = binder_type; + list_add(&item->list, &block->owner_list); + return 0; +} + +static void tcf_block_owner_del(struct tcf_block *block, + struct Qdisc *q, + enum flow_block_binder_type binder_type) +{ + struct tcf_block_owner_item *item; + + list_for_each_entry(item, &block->owner_list, list) { + if (item->q == q && item->binder_type == binder_type) { + list_del(&item->list); + kfree(item); + return; + } + } + WARN_ON(1); +} + +static bool tcf_block_tracks_dev(struct tcf_block *block, + struct tcf_block_ext_info *ei) +{ + return tcf_block_shared(block) && + (ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS || + ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS); +} + +int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = qdisc_dev(q); + struct net *net = qdisc_net(q); + struct tcf_block *block = NULL; + int err; + + if (ei->block_index) + /* block_index not 0 means the shared block is requested */ + block = tcf_block_refcnt_get(net, ei->block_index); + + if (!block) { + block = tcf_block_create(net, q, ei->block_index, extack); + if (IS_ERR(block)) + return PTR_ERR(block); + if (tcf_block_shared(block)) { + err = tcf_block_insert(block, net, extack); + if (err) + goto err_block_insert; + } + } + + err = tcf_block_owner_add(block, q, ei->binder_type); + if (err) + goto err_block_owner_add; + + tcf_block_owner_netif_keep_dst(block, q, ei->binder_type); + + err = tcf_chain0_head_change_cb_add(block, ei, extack); + if (err) + goto err_chain0_head_change_cb_add; + + err = tcf_block_offload_bind(block, q, ei, extack); + if (err) + goto err_block_offload_bind; + + if (tcf_block_tracks_dev(block, ei)) { + err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL); + if (err) { + NL_SET_ERR_MSG(extack, "block dev insert failed"); + goto err_dev_insert; + } } - tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); + *p_block = block; return 0; -err_chain_create: - kfree(block); +err_dev_insert: + tcf_block_offload_unbind(block, q, ei); +err_block_offload_bind: + tcf_chain0_head_change_cb_del(block, ei); +err_chain0_head_change_cb_add: + tcf_block_owner_del(block, q, ei->binder_type); +err_block_owner_add: +err_block_insert: + tcf_block_refcnt_put(block, true); return err; } +EXPORT_SYMBOL(tcf_block_get_ext); + +static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv) +{ + struct tcf_proto __rcu **p_filter_chain = priv; + + rcu_assign_pointer(*p_filter_chain, tp_head); +} + +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, + struct netlink_ext_ack *extack) +{ + struct tcf_block_ext_info ei = { + .chain_head_change = tcf_chain_head_change_dflt, + .chain_head_change_priv = p_filter_chain, + }; + + WARN_ON(!p_filter_chain); + return tcf_block_get_ext(p_block, q, &ei, extack); +} EXPORT_SYMBOL(tcf_block_get); -void tcf_block_put(struct tcf_block *block) +/* XXX: Standalone actions are not allowed to jump to any chain, and bound + * actions should be all removed after flushing. + */ +void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) { - struct tcf_chain *chain, *tmp; + struct net_device *dev = qdisc_dev(q); if (!block) return; + if (tcf_block_tracks_dev(block, ei)) + xa_erase(&block->ports, dev->ifindex); + tcf_chain0_head_change_cb_del(block, ei); + tcf_block_owner_del(block, q, ei->binder_type); - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) - tcf_chain_destroy(chain); - kfree(block); + __tcf_block_put(block, q, ei, true); } +EXPORT_SYMBOL(tcf_block_put_ext); + +void tcf_block_put(struct tcf_block *block) +{ + struct tcf_block_ext_info ei = {0, }; + + if (!block) + return; + tcf_block_put_ext(block, block->q, &ei); +} + EXPORT_SYMBOL(tcf_block_put); +static int +tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, + void *cb_priv, bool add, bool offload_in_use, + struct netlink_ext_ack *extack) +{ + struct tcf_chain *chain, *chain_prev; + struct tcf_proto *tp, *tp_prev; + int err; + + lockdep_assert_held(&block->cb_lock); + + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { + if (chain->tmplt_ops && add) + chain->tmplt_ops->tmplt_reoffload(chain, true, cb, + cb_priv); + for (tp = __tcf_get_next_proto(chain, NULL); tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL)) { + if (tp->ops->reoffload) { + err = tp->ops->reoffload(tp, add, cb, cb_priv, + extack); + if (err && add) + goto err_playback_remove; + } else if (add && offload_in_use) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support"); + goto err_playback_remove; + } + } + if (chain->tmplt_ops && !add) + chain->tmplt_ops->tmplt_reoffload(chain, false, cb, + cb_priv); + } + + return 0; + +err_playback_remove: + tcf_proto_put(tp, true, NULL); + tcf_chain_put(chain); + tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use, + extack); + return err; +} + +static int tcf_block_bind(struct tcf_block *block, + struct flow_block_offload *bo) +{ + struct flow_block_cb *block_cb, *next; + int err, i = 0; + + lockdep_assert_held(&block->cb_lock); + + list_for_each_entry(block_cb, &bo->cb_list, list) { + err = tcf_block_playback_offloads(block, block_cb->cb, + block_cb->cb_priv, true, + tcf_block_offload_in_use(block), + bo->extack); + if (err) + goto err_unroll; + if (!bo->unlocked_driver_cb) + block->lockeddevcnt++; + + i++; + } + list_splice(&bo->cb_list, &block->flow_block.cb_list); + + return 0; + +err_unroll: + list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + list_del(&block_cb->driver_list); + if (i-- > 0) { + list_del(&block_cb->list); + tcf_block_playback_offloads(block, block_cb->cb, + block_cb->cb_priv, false, + tcf_block_offload_in_use(block), + NULL); + if (!bo->unlocked_driver_cb) + block->lockeddevcnt--; + } + flow_block_cb_free(block_cb); + } + + return err; +} + +static void tcf_block_unbind(struct tcf_block *block, + struct flow_block_offload *bo) +{ + struct flow_block_cb *block_cb, *next; + + lockdep_assert_held(&block->cb_lock); + + list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + tcf_block_playback_offloads(block, block_cb->cb, + block_cb->cb_priv, false, + tcf_block_offload_in_use(block), + NULL); + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + if (!bo->unlocked_driver_cb) + block->lockeddevcnt--; + } +} + +static int tcf_block_setup(struct tcf_block *block, + struct flow_block_offload *bo) +{ + int err; + + switch (bo->command) { + case FLOW_BLOCK_BIND: + err = tcf_block_bind(block, bo); + break; + case FLOW_BLOCK_UNBIND: + err = 0; + tcf_block_unbind(block, bo); + break; + default: + WARN_ON_ONCE(1); + err = -EOPNOTSUPP; + } + + return err; +} + /* Main classifier routine: scans classifier chain attached * to this qdisc, (optionally) tests for protocol and asks * specific classifiers. */ -int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) +static inline int __tcf_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + const struct tcf_proto *orig_tp, + struct tcf_result *res, + bool compat_mode, + struct tcf_exts_miss_cookie_node *n, + int act_index, + u32 *last_executed_chain) { - __be16 protocol = tc_skb_protocol(skb); #ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; - const struct tcf_proto *orig_tp = tp; + const int max_reclassify_loop = 16; const struct tcf_proto *first_tp; int limit = 0; reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - int err; + __be16 protocol = skb_protocol(skb, false); + int err = 0; - if (tp->protocol != protocol && - tp->protocol != htons(ETH_P_ALL)) - continue; + if (n) { + struct tcf_exts *exts; + + if (n->tp_prio != tp->prio) + continue; + + /* We re-lookup the tp and chain based on index instead + * of having hard refs and locks to them, so do a sanity + * check if any of tp,chain,exts was replaced by the + * time we got here with a cookie from hardware. + */ + if (unlikely(n->tp != tp || n->tp->chain != n->chain || + !tp->ops->get_exts)) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } - err = tp->classify(skb, tp, res); + exts = tp->ops->get_exts(tp, n->handle); + if (unlikely(!exts || n->exts != exts)) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } + + n = NULL; + err = tcf_exts_exec_ex(skb, exts, act_index, res); + } else { + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + + err = tc_classify(skb, tp, res); + } #ifdef CONFIG_NET_CLS_ACT if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) { first_tp = orig_tp; + *last_executed_chain = first_tp->chain->index; goto reset; } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { first_tp = res->goto_tp; + *last_executed_chain = err & TC_ACT_EXT_VAL_MASK; goto reset; } #endif @@ -331,21 +1778,110 @@ reclassify: return err; } + if (unlikely(n)) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } + return TC_ACT_UNSPEC; /* signal: continue lookup */ #ifdef CONFIG_NET_CLS_ACT reset: if (unlikely(limit++ >= max_reclassify_loop)) { - net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", - tp->q->ops->id, tp->prio & 0xffff, + net_notice_ratelimited("%u: reclassify loop, rule prio %u, protocol %02x\n", + tp->chain->block->index, + tp->prio & 0xffff, ntohs(tp->protocol)); + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_RECLASSIFY_LOOP); return TC_ACT_SHOT; } tp = first_tp; - protocol = tc_skb_protocol(skb); goto reclassify; #endif } + +int tcf_classify(struct sk_buff *skb, + const struct tcf_block *block, + const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ +#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + u32 last_executed_chain = 0; + + return __tcf_classify(skb, tp, tp, res, compat_mode, NULL, 0, + &last_executed_chain); +#else + u32 last_executed_chain = tp ? tp->chain->index : 0; + struct tcf_exts_miss_cookie_node *n = NULL; + const struct tcf_proto *orig_tp = tp; + struct tc_skb_ext *ext; + int act_index = 0; + int ret; + + if (block) { + ext = skb_ext_find(skb, TC_SKB_EXT); + + if (ext && (ext->chain || ext->act_miss)) { + struct tcf_chain *fchain; + u32 chain; + + if (ext->act_miss) { + n = tcf_exts_miss_cookie_lookup(ext->act_miss_cookie, + &act_index); + if (!n) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } + + chain = n->chain_index; + } else { + chain = ext->chain; + } + + fchain = tcf_chain_lookup_rcu(block, chain); + if (!fchain) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_CHAIN_NOTFOUND); + + return TC_ACT_SHOT; + } + + /* Consume, so cloned/redirect skbs won't inherit ext */ + skb_ext_del(skb, TC_SKB_EXT); + + tp = rcu_dereference_bh(fchain->filter_chain); + last_executed_chain = fchain->index; + } + } + + ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, n, act_index, + &last_executed_chain); + + if (tc_skb_ext_tc_enabled()) { + /* If we missed on some chain */ + if (ret == TC_ACT_UNSPEC && last_executed_chain) { + struct tc_skb_cb *cb = tc_skb_cb(skb); + + ext = tc_skb_ext_alloc(skb); + if (!ext) { + tcf_set_drop_reason(skb, SKB_DROP_REASON_NOMEM); + return TC_ACT_SHOT; + } + ext->chain = last_executed_chain; + ext->mru = cb->mru; + ext->post_ct = qdisc_skb_cb(skb)->post_ct; + ext->post_ct_snat = qdisc_skb_cb(skb)->post_ct_snat; + ext->post_ct_dnat = qdisc_skb_cb(skb)->post_ct_dnat; + ext->zone = cb->zone; + } + } + + return ret; +#endif +} EXPORT_SYMBOL(tcf_classify); struct tcf_chain_info { @@ -353,49 +1889,148 @@ struct tcf_chain_info { struct tcf_proto __rcu *next; }; -static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info) +static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain *chain, + struct tcf_chain_info *chain_info) { - return rtnl_dereference(*chain_info->pprev); + return tcf_chain_dereference(*chain_info->pprev, chain); } -static void tcf_chain_tp_insert(struct tcf_chain *chain, - struct tcf_chain_info *chain_info, - struct tcf_proto *tp) +static int tcf_chain_tp_insert(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) { - if (chain->p_filter_chain && - *chain_info->pprev == chain->filter_chain) - rcu_assign_pointer(*chain->p_filter_chain, tp); - RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); + if (chain->flushing) + return -EAGAIN; + + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); + if (*chain_info->pprev == chain->filter_chain) + tcf_chain0_head_change(chain, tp); + tcf_proto_get(tp); rcu_assign_pointer(*chain_info->pprev, tp); + + return 0; } static void tcf_chain_tp_remove(struct tcf_chain *chain, struct tcf_chain_info *chain_info, struct tcf_proto *tp) { - struct tcf_proto *next = rtnl_dereference(chain_info->next); + struct tcf_proto *next = tcf_chain_dereference(chain_info->next, chain); - if (chain->p_filter_chain && tp == chain->filter_chain) - RCU_INIT_POINTER(*chain->p_filter_chain, next); + tcf_proto_mark_delete(tp); + if (tp == chain->filter_chain) + tcf_chain0_head_change(chain, next); RCU_INIT_POINTER(*chain_info->pprev, next); } static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, struct tcf_chain_info *chain_info, u32 protocol, u32 prio, - bool prio_allocate) + bool prio_allocate, + struct netlink_ext_ack *extack); + +/* Try to insert new proto. + * If proto with specified priority already exists, free new proto + * and return existing one. + */ + +static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, + struct tcf_proto *tp_new, + u32 protocol, u32 prio, + bool rtnl_held) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp; + int err = 0; + + mutex_lock(&chain->filter_chain_lock); + + if (tcf_proto_exists_destroying(chain, tp_new)) { + mutex_unlock(&chain->filter_chain_lock); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + return ERR_PTR(-EAGAIN); + } + + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false, NULL); + if (!tp) + err = tcf_chain_tp_insert(chain, &chain_info, tp_new); + mutex_unlock(&chain->filter_chain_lock); + + if (tp) { + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + tp_new = tp; + } else if (err) { + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + tp_new = ERR_PTR(err); + } + + return tp_new; +} + +static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, + struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp_iter; + struct tcf_proto **pprev; + struct tcf_proto *next; + + mutex_lock(&chain->filter_chain_lock); + + /* Atomically find and remove tp from chain. */ + for (pprev = &chain->filter_chain; + (tp_iter = tcf_chain_dereference(*pprev, chain)); + pprev = &tp_iter->next) { + if (tp_iter == tp) { + chain_info.pprev = pprev; + chain_info.next = tp_iter->next; + WARN_ON(tp_iter->deleting); + break; + } + } + /* Verify that tp still exists and no new filters were inserted + * concurrently. + * Mark tp for deletion if it is empty. + */ + if (!tp_iter || !tcf_proto_check_delete(tp)) { + mutex_unlock(&chain->filter_chain_lock); + return; + } + + tcf_proto_signal_destroying(chain, tp); + next = tcf_chain_dereference(chain_info.next, chain); + if (tp == chain->filter_chain) + tcf_chain0_head_change(chain, next); + RCU_INIT_POINTER(*chain_info.pprev, next); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, extack); +} + +static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + u32 protocol, u32 prio, + bool prio_allocate, + struct netlink_ext_ack *extack) { struct tcf_proto **pprev; struct tcf_proto *tp; /* Check the chain for existence of proto-tcf with this priority */ for (pprev = &chain->filter_chain; - (tp = rtnl_dereference(*pprev)); pprev = &tp->next) { + (tp = tcf_chain_dereference(*pprev, chain)); + pprev = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { - if (prio_allocate || - (tp->protocol != protocol && protocol)) + if (prio_allocate) { + NL_SET_ERR_MSG(extack, "Lowest ID from auto-alloc range already in use"); + return ERR_PTR(-ENOSPC); + } + if (tp->protocol != protocol && protocol) { + NL_SET_ERR_MSG(extack, "Protocol mismatch for filter with specified priority"); return ERR_PTR(-EINVAL); + } } else { tp = NULL; } @@ -403,43 +2038,225 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } } chain_info->pprev = pprev; - chain_info->next = tp ? tp->next : NULL; + if (tp) { + chain_info->next = tp->next; + tcf_proto_get(tp); + } else { + chain_info->next = NULL; + } return tp; } -/* Add/change/delete/get a filter node */ +static int tcf_fill_node(struct net *net, struct sk_buff *skb, + struct tcf_proto *tp, struct tcf_block *block, + struct Qdisc *q, u32 parent, void *fh, + u32 portid, u32 seq, u16 flags, int event, + bool terse_dump, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct tcmsg *tcm; + struct nlmsghdr *nlh; + unsigned char *b = skb_tail_pointer(skb); + int ret = -EMSGSIZE; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); + tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; + if (q) { + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = parent; + } else { + tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK; + tcm->tcm_block_index = block->index; + } + tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); + if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index)) + goto nla_put_failure; + if (!fh) { + tcm->tcm_handle = 0; + } else if (terse_dump) { + if (tp->ops->terse_dump) { + if (tp->ops->terse_dump(net, tp, fh, skb, tcm, + rtnl_held) < 0) + goto nla_put_failure; + } else { + goto cls_op_not_supp; + } + } else { + if (tp->ops->dump && + tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0) + goto nla_put_failure; + } + + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto nla_put_failure; + + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + + return skb->len; + +cls_op_not_supp: + ret = -EOPNOTSUPP; +out_nlmsg_trim: +nla_put_failure: + nlmsg_trim(skb, b); + return ret; +} + +static struct sk_buff *tfilter_notify_prep(struct net *net, + struct sk_buff *oskb, + struct nlmsghdr *n, + struct tcf_proto *tp, + struct tcf_block *block, + struct Qdisc *q, u32 parent, + void *fh, int event, + u32 portid, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + unsigned int size = oskb ? max(NLMSG_GOODSIZE, oskb->len) : NLMSG_GOODSIZE; + struct sk_buff *skb; + int ret; + +retry: + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOBUFS); + + ret = tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, + n->nlmsg_seq, n->nlmsg_flags, event, false, + rtnl_held, extack); + if (ret <= 0) { + kfree_skb(skb); + if (ret == -EMSGSIZE) { + size += NLMSG_GOODSIZE; + goto retry; + } + return ERR_PTR(-EINVAL); + } + return skb; +} + +static int tfilter_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, struct tcf_proto *tp, + struct tcf_block *block, struct Qdisc *q, + u32 parent, void *fh, int event, bool unicast, + bool rtnl_held, struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + int err = 0; + + if (!unicast && !rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return 0; + + skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, event, + portid, rtnl_held, extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + if (unicast) + err = rtnl_unicast(skb, net, portid); + else + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + return err; +} + +static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, struct tcf_proto *tp, + struct tcf_block *block, struct Qdisc *q, + u32 parent, void *fh, bool *last, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + int err; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return tp->ops->delete(tp, fh, last, rtnl_held, extack); + + skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, portid, rtnl_held, extack); + if (IS_ERR(skb)) { + NL_SET_ERR_MSG(extack, "Failed to build del event notification"); + return PTR_ERR(skb); + } + + err = tp->ops->delete(tp, fh, last, rtnl_held, extack); + if (err) { + kfree_skb(skb); + return err; + } + + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send filter delete notification"); + + return err; +} + +static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, + struct tcf_block *block, struct Qdisc *q, + u32 parent, struct nlmsghdr *n, + struct tcf_chain *chain, int event, + struct netlink_ext_ack *extack) +{ + struct tcf_proto *tp; + + for (tp = tcf_get_next_proto(chain, NULL); + tp; tp = tcf_get_next_proto(chain, tp)) + tfilter_notify(net, oskb, n, tp, block, q, parent, NULL, + event, false, true, extack); +} + +static void tfilter_put(struct tcf_proto *tp, void *fh) +{ + if (tp->ops->put && fh) + tp->ops->put(tp, fh); +} + +static bool is_qdisc_ingress(__u32 classid) +{ + return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); +} -static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, +static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; bool prio_allocate; u32 parent; u32 chain_index; - struct net_device *dev; - struct Qdisc *q; + struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain = NULL; + struct tcf_chain *chain; struct tcf_block *block; struct tcf_proto *tp; - const struct Qdisc_class_ops *cops; unsigned long cl; - unsigned long fh; + void *fh; int err; int tp_created; - - if ((n->nlmsg_type != RTM_GETTFILTER) && - !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) - return -EPERM; + bool rtnl_held = false; + u32 flags; replay: tp_created = 0; - err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -448,284 +2265,524 @@ replay: prio = TC_H_MAJ(t->tcm_info); prio_allocate = false; parent = t->tcm_parent; + tp = NULL; cl = 0; + block = NULL; + q = NULL; + chain = NULL; + flags = 0; if (prio == 0) { - switch (n->nlmsg_type) { - case RTM_DELTFILTER: - if (protocol || t->tcm_handle || tca[TCA_KIND]) - return -ENOENT; - break; - case RTM_NEWTFILTER: - /* If no priority is provided by the user, - * we allocate one. - */ - if (n->nlmsg_flags & NLM_F_CREATE) { - prio = TC_H_MAKE(0x80000000U, 0U); - prio_allocate = true; - break; - } - /* fall-through */ - default: + /* If no priority is provided by the user, + * we allocate one. + */ + if (n->nlmsg_flags & NLM_F_CREATE) { + prio = TC_H_MAKE(0x80000000U, 0U); + prio_allocate = true; + } else { + NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero"); return -ENOENT; } } /* Find head of filter chain. */ - /* Find link */ - dev = __dev_get_by_index(net, t->tcm_ifindex); - if (dev == NULL) - return -ENODEV; + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; - /* Find qdisc */ - if (!parent) { - q = dev->qdisc; - parent = q->handle; - } else { - q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent)); - if (q == NULL) - return -EINVAL; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; } - /* Is it classful? */ - cops = q->ops->cl_ops; - if (!cops) - return -EINVAL; - - if (!cops->tcf_block) - return -EOPNOTSUPP; - - /* Do we search for filter, attached to class? */ - if (TC_H_MIN(parent)) { - cl = cops->get(q, parent); - if (cl == 0) - return -ENOENT; + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, + * block is shared (no qdisc found), qdisc is not unlocked, classifier + * type is not specified, classifier is not unlocked. + */ + if (rtnl_held || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tcf_proto_is_unlocked(name)) { + rtnl_held = true; + rtnl_lock(); } - /* And the last stroke */ - block = cops->tcf_block(q, cl); - if (!block) { - err = -EINVAL; + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); goto errout; } + block->classid = parent; - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; goto errout; } - chain = tcf_chain_get(block, chain_index, - n->nlmsg_type == RTM_NEWTFILTER); + chain = tcf_chain_get(block, chain_index, true); if (!chain) { - err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL; - goto errout; - } - - if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { - tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); - tcf_chain_flush(chain); - err = 0; + NL_SET_ERR_MSG(extack, "Cannot create specified filter chain"); + err = -ENOMEM; goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, - prio, prio_allocate); + prio, prio_allocate, extack); if (IS_ERR(tp)) { err = PTR_ERR(tp); - goto errout; + goto errout_locked; } if (tp == NULL) { + struct tcf_proto *tp_new = NULL; + + if (chain->flushing) { + err = -EAGAIN; + goto errout_locked; + } + /* Proto-tcf does not exist, create new one */ if (tca[TCA_KIND] == NULL || !protocol) { + NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified"); err = -EINVAL; - goto errout; + goto errout_locked; } - if (n->nlmsg_type != RTM_NEWTFILTER || - !(n->nlmsg_flags & NLM_F_CREATE)) { + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; - goto errout; + goto errout_locked; } if (prio_allocate) - prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); + prio = tcf_auto_prio(tcf_chain_tp_prev(chain, + &chain_info)); + + mutex_unlock(&chain->filter_chain_lock); + tp_new = tcf_proto_create(name, protocol, prio, chain, + rtnl_held, extack); + if (IS_ERR(tp_new)) { + err = PTR_ERR(tp_new); + goto errout_tp; + } - tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, parent, q, chain); + tp_created = 1; + tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio, + rtnl_held); if (IS_ERR(tp)) { err = PTR_ERR(tp); - goto errout; + goto errout_tp; } - tp_created = 1; - } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + } else { + mutex_unlock(&chain->filter_chain_lock); + } + + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; goto errout; } fh = tp->ops->get(tp, t->tcm_handle); - if (fh == 0) { - if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, - RTM_DELTFILTER, false); - tcf_proto_destroy(tp); - err = 0; - goto errout; - } - - if (n->nlmsg_type != RTM_NEWTFILTER || - !(n->nlmsg_flags & NLM_F_CREATE)) { + if (!fh) { + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; goto errout; } - } else { - bool last; + } else if (n->nlmsg_flags & NLM_F_EXCL) { + tfilter_put(tp, fh); + NL_SET_ERR_MSG(extack, "Filter already exists"); + err = -EEXIST; + goto errout; + } - switch (n->nlmsg_type) { - case RTM_NEWTFILTER: - if (n->nlmsg_flags & NLM_F_EXCL) { - if (tp_created) - tcf_proto_destroy(tp); - err = -EEXIST; - goto errout; - } - break; - case RTM_DELTFILTER: - err = tp->ops->delete(tp, fh, &last); - if (err) - goto errout; - tfilter_notify(net, skb, n, tp, t->tcm_handle, - RTM_DELTFILTER, false); - if (last) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tcf_proto_destroy(tp); - } - goto errout; - case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, fh, - RTM_NEWTFILTER, true); - goto errout; - default: - err = -EINVAL; - goto errout; - } + if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) { + tfilter_put(tp, fh); + NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind"); + err = -EINVAL; + goto errout; } + if (!(n->nlmsg_flags & NLM_F_CREATE)) + flags |= TCA_ACT_FLAGS_REPLACE; + if (!rtnl_held) + flags |= TCA_ACT_FLAGS_NO_RTNL; + if (is_qdisc_ingress(parent)) + flags |= TCA_ACT_FLAGS_AT_INGRESS; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, - n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE); + flags, extack); if (err == 0) { - if (tp_created) - tcf_chain_tp_insert(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); - } else { - if (tp_created) - tcf_proto_destroy(tp); + tfilter_notify(net, skb, n, tp, block, q, parent, fh, + RTM_NEWTFILTER, false, rtnl_held, extack); + tfilter_put(tp, fh); + tcf_proto_count_usesw(tp, true); + /* q pointer is NULL for shared blocks */ + if (q) + q->flags &= ~TCQ_F_CAN_BYPASS; } errout: - if (chain) - tcf_chain_put(chain); - if (cl) - cops->put(q, cl); - if (err == -EAGAIN) + if (err && tp_created) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, NULL); +errout_tp: + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); + if (!tp_created) + tcf_chain_put(chain); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + + if (err == -EAGAIN) { + /* Take rtnl lock in case EAGAIN is caused by concurrent flush + * of target chain. + */ + rtnl_held = true; /* Replay the request. */ goto replay; + } return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } -static int tcf_fill_node(struct net *net, struct sk_buff *skb, - struct tcf_proto *tp, unsigned long fh, u32 portid, - u32 seq, u16 flags, int event) +static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) { - struct tcmsg *tcm; - struct nlmsghdr *nlh; - unsigned char *b = skb_tail_pointer(skb); + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; + struct tcmsg *t; + u32 protocol; + u32 prio; + u32 parent; + u32 chain_index; + struct Qdisc *q = NULL; + struct tcf_chain_info chain_info; + struct tcf_chain *chain = NULL; + struct tcf_block *block = NULL; + struct tcf_proto *tp = NULL; + unsigned long cl = 0; + void *fh = NULL; + int err; + bool rtnl_held = false; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); - if (!nlh) - goto out_nlmsg_trim; - tcm = nlmsg_data(nlh); - tcm->tcm_family = AF_UNSPEC; - tcm->tcm__pad1 = 0; - tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; - tcm->tcm_parent = tp->classid; - tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); - if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) - goto nla_put_failure; - if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index)) - goto nla_put_failure; - tcm->tcm_handle = fh; - if (RTM_DELTFILTER != event) { - tcm->tcm_handle = 0; - if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) - goto nla_put_failure; + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); + if (err < 0) + return err; + + t = nlmsg_data(n); + protocol = TC_H_MIN(t->tcm_info); + prio = TC_H_MAJ(t->tcm_info); + parent = t->tcm_parent; + + if (prio == 0 && (protocol || t->tcm_handle || tca[TCA_KIND])) { + NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set"); + return -ENOENT; } - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; -out_nlmsg_trim: -nla_put_failure: - nlmsg_trim(skb, b); - return -1; + /* Find head of filter chain. */ + + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc + * found), qdisc is not unlocked, classifier type is not specified, + * classifier is not unlocked. + */ + if (!prio || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tcf_proto_is_unlocked(name)) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto errout; + } + + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); + if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); + err = -EINVAL; + goto errout; + } + chain = tcf_chain_get(block, chain_index, false); + if (!chain) { + /* User requested flush on non-existent chain. Nothing to do, + * so just return success. + */ + if (prio == 0) { + err = 0; + goto errout; + } + NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + err = -ENOENT; + goto errout; + } + + if (prio == 0) { + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER, extack); + tcf_chain_flush(chain, rtnl_held); + err = 0; + goto errout; + } + + mutex_lock(&chain->filter_chain_lock); + tp = tcf_chain_tp_find(chain, &chain_info, protocol, + prio, false, extack); + if (!tp) { + err = -ENOENT; + NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); + goto errout_locked; + } else if (IS_ERR(tp)) { + err = PTR_ERR(tp); + goto errout_locked; + } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); + err = -EINVAL; + goto errout_locked; + } else if (t->tcm_handle == 0) { + tcf_proto_signal_destroying(chain, tp); + tcf_chain_tp_remove(chain, &chain_info, tp); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, NULL); + tfilter_notify(net, skb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, false, rtnl_held, extack); + err = 0; + goto errout; + } + mutex_unlock(&chain->filter_chain_lock); + + fh = tp->ops->get(tp, t->tcm_handle); + + if (!fh) { + NL_SET_ERR_MSG(extack, "Specified filter handle not found"); + err = -ENOENT; + } else { + bool last; + + err = tfilter_del_notify(net, skb, n, tp, block, q, parent, fh, + &last, rtnl_held, extack); + + if (err) + goto errout; + if (last) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, extack); + } + +errout: + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); + tcf_chain_put(chain); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + + return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } -static int tfilter_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, struct tcf_proto *tp, - unsigned long fh, int event, bool unicast) +static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) { - struct sk_buff *skb; - u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; + struct tcmsg *t; + u32 protocol; + u32 prio; + u32 parent; + u32 chain_index; + struct Qdisc *q = NULL; + struct tcf_chain_info chain_info; + struct tcf_chain *chain = NULL; + struct tcf_block *block = NULL; + struct tcf_proto *tp = NULL; + unsigned long cl = 0; + void *fh = NULL; + int err; + bool rtnl_held = false; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); + if (err < 0) + return err; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, - n->nlmsg_flags, event) <= 0) { - kfree_skb(skb); - return -EINVAL; + t = nlmsg_data(n); + protocol = TC_H_MIN(t->tcm_info); + prio = TC_H_MAJ(t->tcm_info); + parent = t->tcm_parent; + + if (prio == 0) { + NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero"); + return -ENOENT; } - if (unicast) - return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + /* Find head of filter chain. */ + + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not + * unlocked, classifier type is not specified, classifier is not + * unlocked. + */ + if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tcf_proto_is_unlocked(name)) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto errout; + } + + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); + if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); + err = -EINVAL; + goto errout; + } + chain = tcf_chain_get(block, chain_index, false); + if (!chain) { + NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + err = -EINVAL; + goto errout; + } + + mutex_lock(&chain->filter_chain_lock); + tp = tcf_chain_tp_find(chain, &chain_info, protocol, + prio, false, extack); + mutex_unlock(&chain->filter_chain_lock); + if (!tp) { + err = -ENOENT; + NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); + goto errout; + } else if (IS_ERR(tp)) { + err = PTR_ERR(tp); + goto errout; + } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); + err = -EINVAL; + goto errout; + } - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + fh = tp->ops->get(tp, t->tcm_handle); + + if (!fh) { + NL_SET_ERR_MSG(extack, "Specified filter handle not found"); + err = -ENOENT; + } else { + err = tfilter_notify(net, skb, n, tp, block, q, parent, + fh, RTM_NEWTFILTER, true, rtnl_held, NULL); + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); + } + + tfilter_put(tp, fh); +errout: + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); + tcf_chain_put(chain); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + + return err; } struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; struct netlink_callback *cb; + struct tcf_block *block; + struct Qdisc *q; + u32 parent; + bool terse_dump; }; -static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, - struct tcf_walker *arg) +static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) { struct tcf_dump_args *a = (void *)arg; struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, + n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER); + RTM_NEWTFILTER, a->terse_dump, true, NULL); } -static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, - struct netlink_callback *cb, - long index_start, long *p_index) +static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, + struct sk_buff *skb, struct netlink_callback *cb, + long index_start, long *p_index, bool terse) { struct net *net = sock_net(skb->sk); + struct tcf_block *block = chain->block; struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct tcf_proto *tp, *tp_prev; struct tcf_dump_args arg; - struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next), (*p_index)++) { + for (tp = __tcf_get_next_proto(chain, NULL); + tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL), + (*p_index)++) { if (*p_index < index_start) continue; if (TC_H_MAJ(tcm->tcm_info) && @@ -738,12 +2795,11 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, 0, + if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER) <= 0) - return false; - + RTM_NEWTFILTER, false, true, NULL) <= 0) + goto errout; cb->args[1] = 1; } if (!tp->ops->walk) @@ -751,150 +2807,650 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, arg.w.fn = tcf_node_dump; arg.skb = skb; arg.cb = cb; + arg.block = block; + arg.q = q; + arg.parent = parent; arg.w.stop = 0; arg.w.skip = cb->args[1] - 1; arg.w.count = 0; - tp->ops->walk(tp, &arg.w); + arg.w.cookie = cb->args[2]; + arg.terse_dump = terse; + tp->ops->walk(tp, &arg.w, true); + cb->args[2] = arg.w.cookie; cb->args[1] = arg.w.count + 1; if (arg.w.stop) - return false; + goto errout; } return true; + +errout: + tcf_proto_put(tp, true, NULL); + return false; } +static const struct nla_policy tcf_tfilter_dump_policy[TCA_MAX + 1] = { + [TCA_CHAIN] = { .type = NLA_U32 }, + [TCA_DUMP_FLAGS] = NLA_POLICY_BITFIELD32(TCA_DUMP_FLAGS_TERSE), +}; + /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { + struct tcf_chain *chain, *chain_prev; struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; - struct net_device *dev; - struct Qdisc *q; + struct Qdisc *q = NULL; struct tcf_block *block; - struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); - unsigned long cl = 0; - const struct Qdisc_class_ops *cops; + bool terse_dump = false; long index_start; long index; + u32 parent; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return skb->len; - err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX, + tcf_tfilter_dump_policy, cb->extack); if (err) return err; - dev = __dev_get_by_index(net, tcm->tcm_ifindex); - if (!dev) - return skb->len; + if (tca[TCA_DUMP_FLAGS]) { + struct nla_bitfield32 flags = + nla_get_bitfield32(tca[TCA_DUMP_FLAGS]); - if (!tcm->tcm_parent) - q = dev->qdisc; - else - q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - if (!q) - goto out; - cops = q->ops->cl_ops; - if (!cops) - goto errout; - if (!cops->tcf_block) - goto errout; - if (TC_H_MIN(tcm->tcm_parent)) { - cl = cops->get(q, tcm->tcm_parent); - if (cl == 0) - goto errout; + terse_dump = flags.value & TCA_DUMP_FLAGS_TERSE; + } + + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_refcnt_get(net, tcm->tcm_block_index); + if (!block) + goto out; + /* If we work with block index, q is NULL and parent value + * will never be used in the following code. The check + * in tcf_fill_node prevents it. However, compiler does not + * see that far, so set parent to zero to silence the warning + * about parent being uninitialized. + */ + parent = 0; + } else { + const struct Qdisc_class_ops *cops; + struct net_device *dev; + unsigned long cl = 0; + + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) + return skb->len; + + parent = tcm->tcm_parent; + if (!parent) + q = rtnl_dereference(dev->qdisc); + else + q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + if (!q) + goto out; + cops = q->ops->cl_ops; + if (!cops) + goto out; + if (!cops->tcf_block) + goto out; + if (TC_H_MIN(tcm->tcm_parent)) { + cl = cops->find(q, tcm->tcm_parent); + if (cl == 0) + goto out; + } + block = cops->tcf_block(q, cl, NULL); + if (!block) + goto out; + parent = block->classid; + if (tcf_block_shared(block)) + q = NULL; } - block = cops->tcf_block(q, cl); - if (!block) - goto errout; index_start = cb->args[0]; index = 0; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; - if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) + if (!tcf_chain_dump(chain, q, parent, skb, cb, + index_start, &index, terse_dump)) { + tcf_chain_put(chain); + err = -EMSGSIZE; break; + } } + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) + tcf_block_refcnt_put(block, true); cb->args[0] = index; +out: + /* If we did no progress, the error (EMSGSIZE) is real */ + if (skb->len == 0 && err) + return err; + return skb->len; +} + +static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct net *net, struct sk_buff *skb, + struct tcf_block *block, + u32 portid, u32 seq, u16 flags, int event, + struct netlink_ext_ack *extack) +{ + unsigned char *b = skb_tail_pointer(skb); + const struct tcf_proto_ops *ops; + struct nlmsghdr *nlh; + struct tcmsg *tcm; + void *priv; + + ops = tmplt_ops; + priv = tmplt_priv; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); + tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; + tcm->tcm_handle = 0; + if (block->q) { + tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex; + tcm->tcm_parent = block->q->handle; + } else { + tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK; + tcm->tcm_block_index = block->index; + } + + if (nla_put_u32(skb, TCA_CHAIN, chain_index)) + goto nla_put_failure; + + if (ops) { + if (nla_put_string(skb, TCA_KIND, ops->kind)) + goto nla_put_failure; + if (ops->tmplt_dump(skb, net, priv) < 0) + goto nla_put_failure; + } + + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + + return skb->len; + +out_nlmsg_trim: +nla_put_failure: + nlmsg_trim(skb, b); + return -EMSGSIZE; +} + +static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack) +{ + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct tcf_block *block = chain->block; + struct net *net = block->net; + struct sk_buff *skb; + int err = 0; + + if (!unicast && !rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, portid, + seq, flags, event, extack) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + if (unicast) + err = rtnl_unicast(skb, net, portid); + else + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + flags & NLM_F_ECHO); + + return err; +} + +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags) +{ + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct net *net = block->net; + struct sk_buff *skb; + + if (!rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb, + block, portid, seq, flags, RTM_DELCHAIN, NULL) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); +} + +static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, + struct nlattr **tca, + struct netlink_ext_ack *extack) +{ + const struct tcf_proto_ops *ops; + char name[IFNAMSIZ]; + void *tmplt_priv; + + /* If kind is not set, user did not specify template. */ + if (!tca[TCA_KIND]) + return 0; + + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC chain template name too long"); + return -EINVAL; + } + + ops = tcf_proto_lookup_ops(name, true, extack); + if (IS_ERR(ops)) + return PTR_ERR(ops); + if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump || + !ops->tmplt_reoffload) { + NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); + module_put(ops->owner); + return -EOPNOTSUPP; + } + + tmplt_priv = ops->tmplt_create(net, chain, tca, extack); + if (IS_ERR(tmplt_priv)) { + module_put(ops->owner); + return PTR_ERR(tmplt_priv); + } + chain->tmplt_ops = ops; + chain->tmplt_priv = tmplt_priv; + return 0; +} + +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv) +{ + /* If template ops are set, no work to do for us. */ + if (!tmplt_ops) + return; + + tmplt_ops->tmplt_destroy(tmplt_priv); + module_put(tmplt_ops->owner); +} + +/* Add/delete/get a chain */ + +static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + struct tcmsg *t; + u32 parent; + u32 chain_index; + struct Qdisc *q; + struct tcf_chain *chain; + struct tcf_block *block; + unsigned long cl; + int err; + +replay: + q = NULL; + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); + if (err < 0) + return err; + + t = nlmsg_data(n); + parent = t->tcm_parent; + cl = 0; + + block = tcf_block_find(net, &q, &parent, &cl, + t->tcm_ifindex, t->tcm_block_index, extack); + if (IS_ERR(block)) + return PTR_ERR(block); + + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); + if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); + err = -EINVAL; + goto errout_block; + } + + mutex_lock(&block->lock); + chain = tcf_chain_lookup(block, chain_index); + if (n->nlmsg_type == RTM_NEWCHAIN) { + if (chain) { + if (tcf_chain_held_by_acts_only(chain)) { + /* The chain exists only because there is + * some action referencing it. + */ + tcf_chain_hold(chain); + } else { + NL_SET_ERR_MSG(extack, "Filter chain already exists"); + err = -EEXIST; + goto errout_block_locked; + } + } else { + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); + err = -ENOENT; + goto errout_block_locked; + } + chain = tcf_chain_create(block, chain_index); + if (!chain) { + NL_SET_ERR_MSG(extack, "Failed to create filter chain"); + err = -ENOMEM; + goto errout_block_locked; + } + } + } else { + if (!chain || tcf_chain_held_by_acts_only(chain)) { + NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + err = -EINVAL; + goto errout_block_locked; + } + tcf_chain_hold(chain); + } + + if (n->nlmsg_type == RTM_NEWCHAIN) { + /* Modifying chain requires holding parent block lock. In case + * the chain was successfully added, take a reference to the + * chain. This ensures that an empty chain does not disappear at + * the end of this function. + */ + tcf_chain_hold(chain); + chain->explicitly_created = true; + } + mutex_unlock(&block->lock); + + switch (n->nlmsg_type) { + case RTM_NEWCHAIN: + err = tc_chain_tmplt_add(chain, net, tca, extack); + if (err) { + tcf_chain_put_explicitly_created(chain); + goto errout; + } + + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, + RTM_NEWCHAIN, false, extack); + break; + case RTM_DELCHAIN: + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER, extack); + /* Flush the chain first as the user requested chain removal. */ + tcf_chain_flush(chain, true); + /* In case the chain was successfully deleted, put a reference + * to the chain previously taken during addition. + */ + tcf_chain_put_explicitly_created(chain); + break; + case RTM_GETCHAIN: + err = tc_chain_notify(chain, skb, n->nlmsg_seq, + n->nlmsg_flags, n->nlmsg_type, true, extack); + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); + break; + default: + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(extack, "Unsupported message type"); + goto errout; + } + errout: - if (cl) - cops->put(q, cl); + tcf_chain_put(chain); +errout_block: + tcf_block_release(q, block, true); + if (err == -EAGAIN) + /* Replay the request. */ + goto replay; + return err; + +errout_block_locked: + mutex_unlock(&block->lock); + goto errout_block; +} + +/* called with RTNL */ +static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + struct Qdisc *q = NULL; + struct tcf_block *block; + struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct tcf_chain *chain; + long index_start; + long index; + int err; + + if (nlmsg_len(cb->nlh) < sizeof(*tcm)) + return skb->len; + + err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, cb->extack); + if (err) + return err; + + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_refcnt_get(net, tcm->tcm_block_index); + if (!block) + goto out; + } else { + const struct Qdisc_class_ops *cops; + struct net_device *dev; + unsigned long cl = 0; + + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) + return skb->len; + + if (!tcm->tcm_parent) + q = rtnl_dereference(dev->qdisc); + else + q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + + if (!q) + goto out; + cops = q->ops->cl_ops; + if (!cops) + goto out; + if (!cops->tcf_block) + goto out; + if (TC_H_MIN(tcm->tcm_parent)) { + cl = cops->find(q, tcm->tcm_parent); + if (cl == 0) + goto out; + } + block = cops->tcf_block(q, cl, NULL); + if (!block) + goto out; + if (tcf_block_shared(block)) + q = NULL; + } + + index_start = cb->args[0]; + index = 0; + + mutex_lock(&block->lock); + list_for_each_entry(chain, &block->chain_list, list) { + if ((tca[TCA_CHAIN] && + nla_get_u32(tca[TCA_CHAIN]) != chain->index)) + continue; + if (index < index_start) { + index++; + continue; + } + if (tcf_chain_held_by_acts_only(chain)) + continue; + err = tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWCHAIN, NULL); + if (err <= 0) + break; + index++; + } + mutex_unlock(&block->lock); + + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) + tcf_block_refcnt_put(block, true); + cb->args[0] = index; + out: + /* If we did no progress, the error (EMSGSIZE) is real */ + if (skb->len == 0 && err) + return err; return skb->len; } -void tcf_exts_destroy(struct tcf_exts *exts) +int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, + int police, struct tcf_proto *tp, u32 handle, + bool use_action_miss) { + int err = 0; + #ifdef CONFIG_NET_CLS_ACT - LIST_HEAD(actions); + exts->type = 0; + exts->nr_actions = 0; + exts->miss_cookie_node = NULL; + /* Note: we do not own yet a reference on net. + * This reference might be taken later from tcf_exts_get_net(). + */ + exts->net = net; + exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), + GFP_KERNEL); + if (!exts->actions) + return -ENOMEM; +#endif + + exts->action = action; + exts->police = police; + + if (!use_action_miss) + return 0; + + err = tcf_exts_miss_cookie_base_alloc(exts, tp, handle); + if (err) + goto err_miss_alloc; + + return 0; + +err_miss_alloc: + tcf_exts_destroy(exts); +#ifdef CONFIG_NET_CLS_ACT + exts->actions = NULL; +#endif + return err; +} +EXPORT_SYMBOL(tcf_exts_init_ex); + +void tcf_exts_destroy(struct tcf_exts *exts) +{ + tcf_exts_miss_cookie_base_destroy(exts); - tcf_exts_to_list(exts, &actions); - tcf_action_destroy(&actions, TCA_ACT_UNBIND); - kfree(exts->actions); +#ifdef CONFIG_NET_CLS_ACT + if (exts->actions) { + tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); + kfree(exts->actions); + } exts->nr_actions = 0; #endif } EXPORT_SYMBOL(tcf_exts_destroy); -int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, - struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr) +int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **tb, + struct nlattr *rate_tlv, struct tcf_exts *exts, + u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { #ifdef CONFIG_NET_CLS_ACT { + int init_res[TCA_ACT_MAX_PRIO] = {}; struct tc_action *act; + size_t attr_size = 0; if (exts->police && tb[exts->police]) { + struct tc_action_ops *a_o; + + flags |= TCA_ACT_FLAGS_POLICE | TCA_ACT_FLAGS_BIND; + a_o = tc_action_load_ops(tb[exts->police], flags, + extack); + if (IS_ERR(a_o)) + return PTR_ERR(a_o); act = tcf_action_init_1(net, tp, tb[exts->police], - rate_tlv, "police", ovr, - TCA_ACT_BIND); + rate_tlv, a_o, init_res, flags, + extack); + module_put(a_o->owner); if (IS_ERR(act)) return PTR_ERR(act); act->type = exts->type = TCA_OLD_COMPAT; exts->actions[0] = act; exts->nr_actions = 1; + tcf_idr_insert_many(exts->actions, init_res); } else if (exts->action && tb[exts->action]) { - LIST_HEAD(actions); - int err, i = 0; + int err; + flags |= TCA_ACT_FLAGS_BIND; err = tcf_action_init(net, tp, tb[exts->action], - rate_tlv, NULL, ovr, TCA_ACT_BIND, - &actions); - if (err) + rate_tlv, exts->actions, init_res, + &attr_size, flags, fl_flags, + extack); + if (err < 0) return err; - list_for_each_entry(act, &actions, list) - exts->actions[i++] = act; - exts->nr_actions = i; + exts->nr_actions = err; } } #else if ((exts->action && tb[exts->action]) || - (exts->police && tb[exts->police])) + (exts->police && tb[exts->police])) { + NL_SET_ERR_MSG(extack, "Classifier actions are not supported per compile options (CONFIG_NET_CLS_ACT)"); return -EOPNOTSUPP; + } #endif return 0; } +EXPORT_SYMBOL(tcf_exts_validate_ex); + +int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, + struct nlattr *rate_tlv, struct tcf_exts *exts, + u32 flags, struct netlink_ext_ack *extack) +{ + return tcf_exts_validate_ex(net, tp, tb, rate_tlv, exts, + flags, 0, extack); +} EXPORT_SYMBOL(tcf_exts_validate); -void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, - struct tcf_exts *src) +void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src) { #ifdef CONFIG_NET_CLS_ACT struct tcf_exts old = *dst; - tcf_tree_lock(tp); - dst->nr_actions = src->nr_actions; - dst->actions = src->actions; - dst->type = src->type; - tcf_tree_unlock(tp); - + *dst = *src; tcf_exts_destroy(&old); #endif } @@ -915,26 +3471,24 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) #ifdef CONFIG_NET_CLS_ACT struct nlattr *nest; - if (exts->action && exts->nr_actions) { + if (exts->action && tcf_exts_has_actions(exts)) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { - LIST_HEAD(actions); - - nest = nla_nest_start(skb, exts->action); + nest = nla_nest_start_noflag(skb, exts->action); if (nest == NULL) goto nla_put_failure; - tcf_exts_to_list(exts, &actions); - if (tcf_action_dump(skb, &actions, 0, 0) < 0) + if (tcf_action_dump(skb, exts->actions, 0, 0, false) + < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (exts->police) { struct tc_action *act = tcf_exts_first_act(exts); - nest = nla_nest_start(skb, exts->police); + nest = nla_nest_start_noflag(skb, exts->police); if (nest == NULL || !act) goto nla_put_failure; if (tcf_action_dump_old(skb, act, 0, 0) < 0) @@ -953,6 +3507,31 @@ nla_put_failure: } EXPORT_SYMBOL(tcf_exts_dump); +int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts) +{ +#ifdef CONFIG_NET_CLS_ACT + struct nlattr *nest; + + if (!exts->action || !tcf_exts_has_actions(exts)) + return 0; + + nest = nla_nest_start_noflag(skb, exts->action); + if (!nest) + goto nla_put_failure; + + if (tcf_action_dump(skb, exts->actions, 0, 0, true) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +#else + return 0; +#endif +} +EXPORT_SYMBOL(tcf_exts_terse_dump); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) { @@ -965,38 +3544,575 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, - struct net_device **hw_dev) +static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) +{ + if (*flags & TCA_CLS_FLAGS_IN_HW) + return; + *flags |= TCA_CLS_FLAGS_IN_HW; + atomic_inc(&block->offloadcnt); +} + +static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) +{ + if (!(*flags & TCA_CLS_FLAGS_IN_HW)) + return; + *flags &= ~TCA_CLS_FLAGS_IN_HW; + atomic_dec(&block->offloadcnt); +} + +static void tc_cls_offload_cnt_update(struct tcf_block *block, + struct tcf_proto *tp, u32 *cnt, + u32 *flags, u32 diff, bool add) +{ + lockdep_assert_held(&block->cb_lock); + + spin_lock(&tp->lock); + if (add) { + if (!*cnt) + tcf_block_offload_inc(block, flags); + *cnt += diff; + } else { + *cnt -= diff; + if (!*cnt) + tcf_block_offload_dec(block, flags); + } + spin_unlock(&tp->lock); +} + +static void +tc_cls_offload_cnt_reset(struct tcf_block *block, struct tcf_proto *tp, + u32 *cnt, u32 *flags) +{ + lockdep_assert_held(&block->cb_lock); + + spin_lock(&tp->lock); + tcf_block_offload_dec(block, flags); + *cnt = 0; + spin_unlock(&tp->lock); +} + +static int +__tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop) +{ + struct flow_block_cb *block_cb; + int ok_count = 0; + int err; + + list_for_each_entry(block_cb, &block->flow_block.cb_list, list) { + err = block_cb->cb(type, type_data, block_cb->cb_priv); + if (err) { + if (err_stop) + return err; + } else { + ok_count++; + } + } + return ok_count; +} + +int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return ok_count; +} +EXPORT_SYMBOL(tc_setup_cb_call); + +/* Non-destructive filter add. If filter that wasn't already in hardware is + * successfully offloaded, increment block offloads counter. On failure, + * previously offloaded filter is considered to be intact and offloads counter + * is not decremented. + */ + +int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *flags, unsigned int *in_hw_count, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) { + ok_count = -EOPNOTSUPP; + goto err_unlock; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + if (ok_count < 0) + goto err_unlock; + + if (tp->ops->hw_add) + tp->ops->hw_add(tp, type_data); + if (ok_count > 0) + tc_cls_offload_cnt_update(block, tp, in_hw_count, flags, + ok_count, true); +err_unlock: + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return min(ok_count, 0); +} +EXPORT_SYMBOL(tc_setup_cb_add); + +/* Destructive filter replace. If filter that wasn't already in hardware is + * successfully offloaded, increment block offload counter. On failure, + * previously offloaded filter is considered to be destroyed and offload counter + * is decremented. + */ + +int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *old_flags, unsigned int *old_in_hw_count, + u32 *new_flags, unsigned int *new_in_hw_count, + bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) { + ok_count = -EOPNOTSUPP; + goto err_unlock; + } + + tc_cls_offload_cnt_reset(block, tp, old_in_hw_count, old_flags); + if (tp->ops->hw_del) + tp->ops->hw_del(tp, type_data); + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + if (ok_count < 0) + goto err_unlock; + + if (tp->ops->hw_add) + tp->ops->hw_add(tp, type_data); + if (ok_count > 0) + tc_cls_offload_cnt_update(block, tp, new_in_hw_count, + new_flags, ok_count, true); +err_unlock: + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return min(ok_count, 0); +} +EXPORT_SYMBOL(tc_setup_cb_replace); + +/* Destroy filter and decrement block offload counter, if filter was previously + * offloaded. + */ + +int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *flags, unsigned int *in_hw_count, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + + tc_cls_offload_cnt_reset(block, tp, in_hw_count, flags); + if (tp->ops->hw_del) + tp->ops->hw_del(tp, type_data); + + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return min(ok_count, 0); +} +EXPORT_SYMBOL(tc_setup_cb_destroy); + +int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, + bool add, flow_setup_cb_t *cb, + enum tc_setup_type type, void *type_data, + void *cb_priv, u32 *flags, unsigned int *in_hw_count) +{ + int err = cb(type, type_data, cb_priv); + + if (err) { + if (add && tc_skip_sw(*flags)) + return err; + } else { + tc_cls_offload_cnt_update(block, tp, in_hw_count, flags, 1, + add); + } + + return 0; +} +EXPORT_SYMBOL(tc_setup_cb_reoffload); + +static int tcf_act_get_user_cookie(struct flow_action_entry *entry, + const struct tc_action *act) +{ + struct tc_cookie *user_cookie; + int err = 0; + + rcu_read_lock(); + user_cookie = rcu_dereference(act->user_cookie); + if (user_cookie) { + entry->user_cookie = flow_action_cookie_create(user_cookie->data, + user_cookie->len, + GFP_ATOMIC); + if (!entry->user_cookie) + err = -ENOMEM; + } + rcu_read_unlock(); + return err; +} + +static void tcf_act_put_user_cookie(struct flow_action_entry *entry) +{ + flow_action_cookie_destroy(entry->user_cookie); +} + +void tc_cleanup_offload_action(struct flow_action *flow_action) +{ + struct flow_action_entry *entry; + int i; + + flow_action_for_each(i, entry, flow_action) { + tcf_act_put_user_cookie(entry); + if (entry->destructor) + entry->destructor(entry->destructor_priv); + } +} +EXPORT_SYMBOL(tc_cleanup_offload_action); + +static int tc_setup_offload_act(struct tc_action *act, + struct flow_action_entry *entry, + u32 *index_inc, + struct netlink_ext_ack *extack) { #ifdef CONFIG_NET_CLS_ACT - const struct tc_action *a; - LIST_HEAD(actions); + if (act->ops->offload_act_setup) { + return act->ops->offload_act_setup(act, entry, index_inc, true, + extack); + } else { + NL_SET_ERR_MSG(extack, "Action does not support offload"); + return -EOPNOTSUPP; + } +#else + return 0; +#endif +} - if (tc_no_actions(exts)) - return -EINVAL; +int tc_setup_action(struct flow_action *flow_action, + struct tc_action *actions[], + u32 miss_cookie_base, + struct netlink_ext_ack *extack) +{ + int i, j, k, index, err = 0; + struct tc_action *act; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { - if (a->ops->get_dev) { - a->ops->get_dev(a, dev_net(dev), hw_dev); - break; + BUILD_BUG_ON(TCA_ACT_HW_STATS_ANY != FLOW_ACTION_HW_STATS_ANY); + BUILD_BUG_ON(TCA_ACT_HW_STATS_IMMEDIATE != FLOW_ACTION_HW_STATS_IMMEDIATE); + BUILD_BUG_ON(TCA_ACT_HW_STATS_DELAYED != FLOW_ACTION_HW_STATS_DELAYED); + + if (!actions) + return 0; + + j = 0; + tcf_act_for_each_action(i, act, actions) { + struct flow_action_entry *entry; + + entry = &flow_action->entries[j]; + spin_lock_bh(&act->tcfa_lock); + err = tcf_act_get_user_cookie(entry, act); + if (err) + goto err_out_locked; + + index = 0; + err = tc_setup_offload_act(act, entry, &index, extack); + if (err) + goto err_out_locked; + + for (k = 0; k < index ; k++) { + entry[k].hw_stats = tc_act_hw_stats(act->hw_stats); + entry[k].hw_index = act->tcfa_index; + entry[k].cookie = (unsigned long)act; + entry[k].miss_cookie = + tcf_exts_miss_cookie_get(miss_cookie_base, i); } + + j += index; + + spin_unlock_bh(&act->tcfa_lock); } - if (*hw_dev) + +err_out: + if (err) + tc_cleanup_offload_action(flow_action); + + return err; +err_out_locked: + spin_unlock_bh(&act->tcfa_lock); + goto err_out; +} + +int tc_setup_offload_action(struct flow_action *flow_action, + const struct tcf_exts *exts, + struct netlink_ext_ack *extack) +{ +#ifdef CONFIG_NET_CLS_ACT + u32 miss_cookie_base; + + if (!exts) return 0; + + miss_cookie_base = exts->miss_cookie_node ? + exts->miss_cookie_node->miss_cookie_base : 0; + return tc_setup_action(flow_action, exts->actions, miss_cookie_base, + extack); +#else + return 0; #endif - return -EOPNOTSUPP; } -EXPORT_SYMBOL(tcf_exts_get_dev); +EXPORT_SYMBOL(tc_setup_offload_action); + +unsigned int tcf_exts_num_actions(struct tcf_exts *exts) +{ + unsigned int num_acts = 0; + struct tc_action *act; + int i; + + tcf_exts_for_each_action(i, act, exts) { + if (is_tcf_pedit(act)) + num_acts += tcf_pedit_nkeys(act); + else + num_acts++; + } + return num_acts; +} +EXPORT_SYMBOL(tcf_exts_num_actions); + +#ifdef CONFIG_NET_CLS_ACT +static int tcf_qevent_parse_block_index(struct nlattr *block_index_attr, + u32 *p_block_index, + struct netlink_ext_ack *extack) +{ + *p_block_index = nla_get_u32(block_index_attr); + if (!*p_block_index) { + NL_SET_ERR_MSG(extack, "Block number may not be zero"); + return -EINVAL; + } + + return 0; +} + +int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, + enum flow_block_binder_type binder_type, + struct nlattr *block_index_attr, + struct netlink_ext_ack *extack) +{ + u32 block_index; + int err; + + if (!block_index_attr) + return 0; + + err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack); + if (err) + return err; + + qe->info.binder_type = binder_type; + qe->info.chain_head_change = tcf_chain_head_change_dflt; + qe->info.chain_head_change_priv = &qe->filter_chain; + qe->info.block_index = block_index; + + return tcf_block_get_ext(&qe->block, sch, &qe->info, extack); +} +EXPORT_SYMBOL(tcf_qevent_init); + +void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch) +{ + if (qe->info.block_index) + tcf_block_put_ext(qe->block, sch, &qe->info); +} +EXPORT_SYMBOL(tcf_qevent_destroy); + +int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, + struct netlink_ext_ack *extack) +{ + u32 block_index; + int err; + + if (!block_index_attr) + return 0; + + err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack); + if (err) + return err; + + /* Bounce newly-configured block or change in block. */ + if (block_index != qe->info.block_index) { + NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL(tcf_qevent_validate_change); + +struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, + struct sk_buff **to_free, int *ret) +{ + struct tcf_result cl_res; + struct tcf_proto *fl; + + if (!qe->info.block_index) + return skb; + + fl = rcu_dereference_bh(qe->filter_chain); + + switch (tcf_classify(skb, NULL, fl, &cl_res, false)) { + case TC_ACT_SHOT: + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + *ret = __NET_XMIT_BYPASS; + return NULL; + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + __qdisc_drop(skb, to_free); + *ret = __NET_XMIT_STOLEN; + return NULL; + case TC_ACT_REDIRECT: + skb_do_redirect(skb); + *ret = __NET_XMIT_STOLEN; + return NULL; + } + + return skb; +} +EXPORT_SYMBOL(tcf_qevent_handle); + +int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe) +{ + if (!qe->info.block_index) + return 0; + return nla_put_u32(skb, attr_name, qe->info.block_index); +} +EXPORT_SYMBOL(tcf_qevent_dump); +#endif + +static __net_init int tcf_net_init(struct net *net) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + spin_lock_init(&tn->idr_lock); + idr_init(&tn->idr); + return 0; +} + +static void __net_exit tcf_net_exit(struct net *net) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + idr_destroy(&tn->idr); +} + +static struct pernet_operations tcf_net_ops = { + .init = tcf_net_init, + .exit = tcf_net_exit, + .id = &tcf_net_id, + .size = sizeof(struct tcf_net), +}; + +static const struct rtnl_msg_handler tc_filter_rtnl_msg_handlers[] __initconst = { + {.msgtype = RTM_NEWTFILTER, .doit = tc_new_tfilter, + .flags = RTNL_FLAG_DOIT_UNLOCKED}, + {.msgtype = RTM_DELTFILTER, .doit = tc_del_tfilter, + .flags = RTNL_FLAG_DOIT_UNLOCKED}, + {.msgtype = RTM_GETTFILTER, .doit = tc_get_tfilter, + .dumpit = tc_dump_tfilter, .flags = RTNL_FLAG_DOIT_UNLOCKED}, + {.msgtype = RTM_NEWCHAIN, .doit = tc_ctl_chain}, + {.msgtype = RTM_DELCHAIN, .doit = tc_ctl_chain}, + {.msgtype = RTM_GETCHAIN, .doit = tc_ctl_chain, + .dumpit = tc_dump_chain}, +}; static int __init tc_filter_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, - tc_dump_tfilter, NULL); + int err; + + tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0); + if (!tc_filter_wq) + return -ENOMEM; + + err = register_pernet_subsys(&tcf_net_ops); + if (err) + goto err_register_pernet_subsys; + + xa_init_flags(&tcf_exts_miss_cookies_xa, XA_FLAGS_ALLOC1); + rtnl_register_many(tc_filter_rtnl_msg_handlers); return 0; + +err_register_pernet_subsys: + destroy_workqueue(tc_filter_wq); + return err; } subsys_initcall(tc_filter_init); diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index c4fd63a068f9..ecfaa4f9a04e 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_basic.c Basic Packet Classifier. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> */ @@ -17,13 +13,16 @@ #include <linux/errno.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> +#include <linux/idr.h> +#include <linux/percpu.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> +#include <net/tc_wrapper.h> struct basic_head { - u32 hgenerator; struct list_head flist; + struct idr handle_idr; struct rcu_head rcu; }; @@ -34,19 +33,23 @@ struct basic_filter { struct tcf_result res; struct tcf_proto *tp; struct list_head link; - struct rcu_head rcu; + struct tc_basic_pcnt __percpu *pf; + struct rcu_work rwork; }; -static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int basic_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { int r; struct basic_head *head = rcu_dereference_bh(tp->root); struct basic_filter *f; list_for_each_entry_rcu(f, &head->flist, link) { + __this_cpu_inc(f->pf->rcnt); if (!tcf_em_tree_match(skb, &f->ematches, NULL)) continue; + __this_cpu_inc(f->pf->rhit); *res = f->res; r = tcf_exts_exec(skb, &f->exts, res); if (r < 0) @@ -56,20 +59,18 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static unsigned long basic_get(struct tcf_proto *tp, u32 handle) +static void *basic_get(struct tcf_proto *tp, u32 handle) { - unsigned long l = 0UL; struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { if (f->handle == handle) { - l = (unsigned long) f; - break; + return f; } } - return l; + return NULL; } static int basic_init(struct tcf_proto *tp) @@ -80,20 +81,32 @@ static int basic_init(struct tcf_proto *tp) if (head == NULL) return -ENOBUFS; INIT_LIST_HEAD(&head->flist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; } -static void basic_delete_filter(struct rcu_head *head) +static void __basic_delete_filter(struct basic_filter *f) { - struct basic_filter *f = container_of(head, struct basic_filter, rcu); - tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); + tcf_exts_put_net(&f->exts); + free_percpu(f->pf); kfree(f); } -static void basic_destroy(struct tcf_proto *tp) +static void basic_delete_filter_work(struct work_struct *work) +{ + struct basic_filter *f = container_of(to_rcu_work(work), + struct basic_filter, + rwork); + rtnl_lock(); + __basic_delete_filter(f); + rtnl_unlock(); +} + +static void basic_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f, *n; @@ -101,19 +114,27 @@ static void basic_destroy(struct tcf_proto *tp) list_for_each_entry_safe(f, n, &head->flist, link) { list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, basic_delete_filter); + idr_remove(&head->handle_idr, f->handle); + if (tcf_exts_get_net(&f->exts)) + tcf_queue_work(&f->rwork, basic_delete_filter_work); + else + __basic_delete_filter(f); } + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } -static int basic_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int basic_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); - struct basic_filter *f = (struct basic_filter *) arg; + struct basic_filter *f = arg; list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, basic_delete_filter); + idr_remove(&head->handle_idr, f->handle); + tcf_exts_get_net(&f->exts); + tcf_queue_work(&f->rwork, basic_delete_filter_work); *last = list_empty(&head->flist); return 0; } @@ -126,41 +147,32 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { static int basic_set_parms(struct net *net, struct tcf_proto *tp, struct basic_filter *f, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) + struct nlattr *est, u32 flags, + struct netlink_ext_ack *extack) { int err; - struct tcf_exts e; - struct tcf_ematch_tree t; - err = tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - err = tcf_em_tree_validate(tp, tb[TCA_BASIC_EMATCHES], &t); + err = tcf_em_tree_validate(tp, tb[TCA_BASIC_EMATCHES], &f->ematches); if (err < 0) - goto errout; + return err; if (tb[TCA_BASIC_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_BASIC_CLASSID]); tcf_bind_filter(tp, &f->res, base); } - tcf_exts_change(tp, &f->exts, &e); - tcf_em_tree_change(tp, &f->ematches, &t); f->tp = tp; - return 0; -errout: - tcf_exts_destroy(&e); - return err; } static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) + struct nlattr **tca, void **arg, + u32 flags, struct netlink_ext_ack *extack) { int err; struct basic_head *head = rtnl_dereference(tp->root); @@ -171,8 +183,8 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (tca[TCA_OPTIONS] == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_BASIC_MAX, tca[TCA_OPTIONS], - basic_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_BASIC_MAX, tca[TCA_OPTIONS], + basic_policy, NULL); if (err < 0) return err; @@ -185,81 +197,89 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (!fnew) return -ENOBUFS; - err = tcf_exts_init(&fnew->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE); + err = tcf_exts_init(&fnew->exts, net, TCA_BASIC_ACT, TCA_BASIC_POLICE); if (err < 0) goto errout; - err = -EINVAL; - if (handle) { - fnew->handle = handle; - } else if (fold) { - fnew->handle = fold->handle; - } else { - unsigned int i = 0x80000000; - do { - if (++head->hgenerator == 0x7FFFFFFF) - head->hgenerator = 1; - } while (--i > 0 && basic_get(tp, head->hgenerator)); - - if (i <= 0) { - pr_err("Insufficient number of handles\n"); - goto errout; - } - - fnew->handle = head->hgenerator; + if (!handle) { + handle = 1; + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + INT_MAX, GFP_KERNEL); + } else if (!fold) { + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + handle, GFP_KERNEL); + } + if (err) + goto errout; + fnew->handle = handle; + fnew->pf = alloc_percpu(struct tc_basic_pcnt); + if (!fnew->pf) { + err = -ENOMEM; + goto errout; } - err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr); - if (err < 0) + err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], flags, + extack); + if (err < 0) { + if (!fold) + idr_remove(&head->handle_idr, fnew->handle); goto errout; + } - *arg = (unsigned long)fnew; + *arg = fnew; if (fold) { + idr_replace(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->link, &fnew->link); tcf_unbind_filter(tp, &fold->res); - call_rcu(&fold->rcu, basic_delete_filter); + tcf_exts_get_net(&fold->exts); + tcf_queue_work(&fold->rwork, basic_delete_filter_work); } else { list_add_rcu(&fnew->link, &head->flist); } return 0; errout: + free_percpu(fnew->pf); tcf_exts_destroy(&fnew->exts); kfree(fnew); return err; } -static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { - if (arg->count < arg->skip) - goto skip; - - if (arg->fn(tp, (unsigned long) f, arg) < 0) { - arg->stop = 1; + if (!tc_cls_stats_dump(tp, arg, f)) break; - } -skip: - arg->count++; } } -static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { - struct basic_filter *f = (struct basic_filter *) fh; + struct basic_filter *f = fh; + + tc_cls_bind_class(classid, cl, q, &f->res, base); +} + +static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) +{ + struct tc_basic_pcnt gpf = {}; + struct basic_filter *f = fh; struct nlattr *nest; + int cpu; if (f == NULL) return skb->len; t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -267,6 +287,18 @@ static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_BASIC_CLASSID, f->res.classid)) goto nla_put_failure; + for_each_possible_cpu(cpu) { + struct tc_basic_pcnt *pf = per_cpu_ptr(f->pf, cpu); + + gpf.rcnt += pf->rcnt; + gpf.rhit += pf->rhit; + } + + if (nla_put_64bit(skb, TCA_BASIC_PCNT, + sizeof(struct tc_basic_pcnt), + &gpf, TCA_BASIC_PAD)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &f->exts) < 0 || tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0) goto nla_put_failure; @@ -293,8 +325,10 @@ static struct tcf_proto_ops cls_basic_ops __read_mostly = { .delete = basic_delete, .walk = basic_walk, .dump = basic_dump, + .bind_class = basic_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("basic"); static int __init init_basic(void) { @@ -308,5 +342,5 @@ static void __exit exit_basic(void) module_init(init_basic) module_exit(exit_basic) +MODULE_DESCRIPTION("TC basic classifier"); MODULE_LICENSE("GPL"); - diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index f57bd531ba98..a32754a2658b 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Berkeley Packet Filter based traffic classifier * @@ -6,10 +7,6 @@ * ematches. * * (C) 2013 Daniel Borkmann <dborkman@redhat.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/module.h> @@ -17,10 +14,12 @@ #include <linux/skbuff.h> #include <linux/filter.h> #include <linux/bpf.h> +#include <linux/idr.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> +#include <net/tc_wrapper.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); @@ -32,7 +31,7 @@ MODULE_DESCRIPTION("TC BPF based classifier"); struct cls_bpf_head { struct list_head plist; - u32 hgen; + struct idr handle_idr; struct rcu_head rcu; }; @@ -41,15 +40,15 @@ struct cls_bpf_prog { struct list_head link; struct tcf_result res; bool exts_integrated; - bool offloaded; u32 gen_flags; + unsigned int in_hw_count; struct tcf_exts exts; u32 handle; u16 bpf_num_ops; struct sock_filter *bpf_ops; const char *bpf_name; struct tcf_proto *tp; - struct rcu_head rcu; + struct rcu_work rwork; }; static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { @@ -79,16 +78,15 @@ static int cls_bpf_exec_opcode(int code) } } -static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int cls_bpf_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { struct cls_bpf_head *head = rcu_dereference_bh(tp->root); bool at_ingress = skb_at_tc_ingress(skb); struct cls_bpf_prog *prog; int ret = -1; - /* Needed here for accessing maps. */ - rcu_read_lock(); list_for_each_entry_rcu(prog, &head->plist, link) { int filter_res; @@ -99,13 +97,13 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, } else if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = bpf_prog_run_data_pointers(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = bpf_prog_run_data_pointers(prog->filter, skb); } + if (unlikely(!skb->tstamp && skb->tstamp_type)) + skb->tstamp_type = SKB_CLOCK_REALTIME; if (prog->exts_integrated) { res->class = 0; @@ -133,7 +131,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, break; } - rcu_read_unlock(); return ret; } @@ -144,95 +141,101 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) } static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, - enum tc_clsbpf_command cmd) + struct cls_bpf_prog *oldprog, + struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_bpf_offload bpf_offload = {}; - struct tc_to_netdev offload; + struct tcf_block *block = tp->chain->block; + struct tc_cls_bpf_offload cls_bpf = {}; + struct cls_bpf_prog *obj; + bool skip_sw; int err; - offload.type = TC_SETUP_CLSBPF; - offload.cls_bpf = &bpf_offload; + skip_sw = prog && tc_skip_sw(prog->gen_flags); + obj = prog ?: oldprog; + + tc_cls_common_offload_init(&cls_bpf.common, tp, obj->gen_flags, extack); + cls_bpf.command = TC_CLSBPF_OFFLOAD; + cls_bpf.exts = &obj->exts; + cls_bpf.prog = prog ? prog->filter : NULL; + cls_bpf.oldprog = oldprog ? oldprog->filter : NULL; + cls_bpf.name = obj->bpf_name; + cls_bpf.exts_integrated = obj->exts_integrated; + + if (oldprog && prog) + err = tc_setup_cb_replace(block, tp, TC_SETUP_CLSBPF, &cls_bpf, + skip_sw, &oldprog->gen_flags, + &oldprog->in_hw_count, + &prog->gen_flags, &prog->in_hw_count, + true); + else if (prog) + err = tc_setup_cb_add(block, tp, TC_SETUP_CLSBPF, &cls_bpf, + skip_sw, &prog->gen_flags, + &prog->in_hw_count, true); + else + err = tc_setup_cb_destroy(block, tp, TC_SETUP_CLSBPF, &cls_bpf, + skip_sw, &oldprog->gen_flags, + &oldprog->in_hw_count, true); - bpf_offload.command = cmd; - bpf_offload.exts = &prog->exts; - bpf_offload.prog = prog->filter; - bpf_offload.name = prog->bpf_name; - bpf_offload.exts_integrated = prog->exts_integrated; - bpf_offload.gen_flags = prog->gen_flags; + if (prog && err) { + cls_bpf_offload_cmd(tp, oldprog, prog, extack); + return err; + } - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, - tp->protocol, &offload); + if (prog && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - if (!err && (cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE)) - prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; + return 0; +} - return err; +static u32 cls_bpf_flags(u32 flags) +{ + return flags & CLS_BPF_SUPPORTED_GEN_FLAGS; } static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, - struct cls_bpf_prog *oldprog) + struct cls_bpf_prog *oldprog, + struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct cls_bpf_prog *obj = prog; - enum tc_clsbpf_command cmd; - bool skip_sw; - int ret; - - skip_sw = tc_skip_sw(prog->gen_flags) || - (oldprog && tc_skip_sw(oldprog->gen_flags)); - - if (oldprog && oldprog->offloaded) { - if (tc_should_offload(dev, tp, prog->gen_flags)) { - cmd = TC_CLSBPF_REPLACE; - } else if (!tc_skip_sw(prog->gen_flags)) { - obj = oldprog; - cmd = TC_CLSBPF_DESTROY; - } else { - return -EINVAL; - } - } else { - if (!tc_should_offload(dev, tp, prog->gen_flags)) - return skip_sw ? -EINVAL : 0; - cmd = TC_CLSBPF_ADD; - } - - ret = cls_bpf_offload_cmd(tp, obj, cmd); - if (ret) - return skip_sw ? ret : 0; + if (prog && oldprog && + cls_bpf_flags(prog->gen_flags) != + cls_bpf_flags(oldprog->gen_flags)) + return -EINVAL; - obj->offloaded = true; - if (oldprog) - oldprog->offloaded = false; + if (prog && tc_skip_hw(prog->gen_flags)) + prog = NULL; + if (oldprog && tc_skip_hw(oldprog->gen_flags)) + oldprog = NULL; + if (!prog && !oldprog) + return 0; - return 0; + return cls_bpf_offload_cmd(tp, prog, oldprog, extack); } static void cls_bpf_stop_offload(struct tcf_proto *tp, - struct cls_bpf_prog *prog) + struct cls_bpf_prog *prog, + struct netlink_ext_ack *extack) { int err; - if (!prog->offloaded) - return; - - err = cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); - if (err) { + err = cls_bpf_offload_cmd(tp, NULL, prog, extack); + if (err) pr_err("Stopping hardware offload failed: %d\n", err); - return; - } - - prog->offloaded = false; } static void cls_bpf_offload_update_stats(struct tcf_proto *tp, struct cls_bpf_prog *prog) { - if (!prog->offloaded) - return; + struct tcf_block *block = tp->chain->block; + struct tc_cls_bpf_offload cls_bpf = {}; + + tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, NULL); + cls_bpf.command = TC_CLSBPF_STATS; + cls_bpf.exts = &prog->exts; + cls_bpf.prog = prog->filter; + cls_bpf.name = prog->bpf_name; + cls_bpf.exts_integrated = prog->exts_integrated; - cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_STATS); + tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, false, true); } static int cls_bpf_init(struct tcf_proto *tp) @@ -244,15 +247,14 @@ static int cls_bpf_init(struct tcf_proto *tp) return -ENOBUFS; INIT_LIST_HEAD_RCU(&head->plist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; } -static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog) +static void cls_bpf_free_parms(struct cls_bpf_prog *prog) { - tcf_exts_destroy(&prog->exts); - if (cls_bpf_is_ebpf(prog)) bpf_prog_put(prog->filter); else @@ -260,56 +262,76 @@ static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog) kfree(prog->bpf_name); kfree(prog->bpf_ops); +} + +static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog) +{ + tcf_exts_destroy(&prog->exts); + tcf_exts_put_net(&prog->exts); + + cls_bpf_free_parms(prog); kfree(prog); } -static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) +static void cls_bpf_delete_prog_work(struct work_struct *work) { - __cls_bpf_delete_prog(container_of(rcu, struct cls_bpf_prog, rcu)); + struct cls_bpf_prog *prog = container_of(to_rcu_work(work), + struct cls_bpf_prog, + rwork); + rtnl_lock(); + __cls_bpf_delete_prog(prog); + rtnl_unlock(); } -static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) +static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog, + struct netlink_ext_ack *extack) { - cls_bpf_stop_offload(tp, prog); + struct cls_bpf_head *head = rtnl_dereference(tp->root); + + idr_remove(&head->handle_idr, prog->handle); + cls_bpf_stop_offload(tp, prog, extack); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); - call_rcu(&prog->rcu, cls_bpf_delete_prog_rcu); + if (tcf_exts_get_net(&prog->exts)) + tcf_queue_work(&prog->rwork, cls_bpf_delete_prog_work); + else + __cls_bpf_delete_prog(prog); } -static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); - __cls_bpf_delete(tp, (struct cls_bpf_prog *) arg); + __cls_bpf_delete(tp, arg, extack); *last = list_empty(&head->plist); return 0; } -static void cls_bpf_destroy(struct tcf_proto *tp) +static void cls_bpf_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog, *tmp; list_for_each_entry_safe(prog, tmp, &head->plist, link) - __cls_bpf_delete(tp, prog); + __cls_bpf_delete(tp, prog, extack); + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } -static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) +static void *cls_bpf_get(struct tcf_proto *tp, u32 handle) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog; - unsigned long ret = 0UL; list_for_each_entry(prog, &head->plist, link) { - if (prog->handle == handle) { - ret = (unsigned long) prog; - break; - } + if (prog->handle == handle) + return prog; } - return ret; + return NULL; } static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) @@ -328,12 +350,10 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) if (bpf_size != nla_len(tb[TCA_BPF_OPS])) return -EINVAL; - bpf_ops = kzalloc(bpf_size, GFP_KERNEL); + bpf_ops = kmemdup(nla_data(tb[TCA_BPF_OPS]), bpf_size, GFP_KERNEL); if (bpf_ops == NULL) return -ENOMEM; - memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size); - fprog_tmp.len = bpf_num_ops; fprog_tmp.filter = bpf_ops; @@ -352,15 +372,17 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) } static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, - const struct tcf_proto *tp) + u32 gen_flags, const struct tcf_proto *tp) { struct bpf_prog *fp; char *name = NULL; + bool skip_sw; u32 bpf_fd; bpf_fd = nla_get_u32(tb[TCA_BPF_FD]); + skip_sw = gen_flags & TCA_CLS_FLAGS_SKIP_SW; - fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); + fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS, skip_sw); if (IS_ERR(fp)) return PTR_ERR(fp); @@ -376,40 +398,81 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, prog->bpf_name = name; prog->filter = fp; - if (fp->dst_needed && !(tp->q->flags & TCQ_F_INGRESS)) - netif_keep_dst(qdisc_dev(tp->q)); + if (fp->dst_needed) + tcf_block_netif_keep_dst(tp->chain->block); return 0; } -static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, - unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) +static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, + struct tcf_proto *tp, unsigned long base, + u32 handle, struct nlattr **tca, + void **arg, u32 flags, + struct netlink_ext_ack *extack) { + struct cls_bpf_head *head = rtnl_dereference(tp->root); bool is_bpf, is_ebpf, have_exts = false; - struct tcf_exts exts; + struct cls_bpf_prog *oldprog = *arg; + struct nlattr *tb[TCA_BPF_MAX + 1]; + bool bound_to_filter = false; + struct cls_bpf_prog *prog; u32 gen_flags = 0; int ret; - is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; - is_ebpf = tb[TCA_BPF_FD]; - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) + if (tca[TCA_OPTIONS] == NULL) return -EINVAL; - ret = tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); + ret = nla_parse_nested_deprecated(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], + bpf_policy, NULL); if (ret < 0) return ret; - ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); + + prog = kzalloc(sizeof(*prog), GFP_KERNEL); + if (!prog) + return -ENOBUFS; + + ret = tcf_exts_init(&prog->exts, net, TCA_BPF_ACT, TCA_BPF_POLICE); if (ret < 0) goto errout; + if (oldprog) { + if (handle && oldprog->handle != handle) { + ret = -EINVAL; + goto errout; + } + } + + if (handle == 0) { + handle = 1; + ret = idr_alloc_u32(&head->handle_idr, prog, &handle, + INT_MAX, GFP_KERNEL); + } else if (!oldprog) { + ret = idr_alloc_u32(&head->handle_idr, prog, &handle, + handle, GFP_KERNEL); + } + + if (ret) + goto errout; + prog->handle = handle; + + is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; + is_ebpf = tb[TCA_BPF_FD]; + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + ret = -EINVAL; + goto errout_idr; + } + + ret = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &prog->exts, + flags, extack); + if (ret < 0) + goto errout_idr; + if (tb[TCA_BPF_FLAGS]) { u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { ret = -EINVAL; - goto errout; + goto errout_idr; } have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; @@ -419,7 +482,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || !tc_flags_valid(gen_flags)) { ret = -EINVAL; - goto errout; + goto errout_idr; } } @@ -427,112 +490,45 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, prog->gen_flags = gen_flags; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, tp); + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) - goto errout; + goto errout_idr; if (tb[TCA_BPF_CLASSID]) { prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); tcf_bind_filter(tp, &prog->res, base); + bound_to_filter = true; } - tcf_exts_change(tp, &prog->exts, &exts); - return 0; - -errout: - tcf_exts_destroy(&exts); - return ret; -} - -static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, - struct cls_bpf_head *head) -{ - unsigned int i = 0x80000000; - u32 handle; - - do { - if (++head->hgen == 0x7FFFFFFF) - head->hgen = 1; - } while (--i > 0 && cls_bpf_get(tp, head->hgen)); - - if (unlikely(i == 0)) { - pr_err("Insufficient number of handles\n"); - handle = 0; - } else { - handle = head->hgen; - } - - return handle; -} - -static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) -{ - struct cls_bpf_head *head = rtnl_dereference(tp->root); - struct cls_bpf_prog *oldprog = (struct cls_bpf_prog *) *arg; - struct nlattr *tb[TCA_BPF_MAX + 1]; - struct cls_bpf_prog *prog; - int ret; - - if (tca[TCA_OPTIONS] == NULL) - return -EINVAL; - - ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy, - NULL); - if (ret < 0) - return ret; - - prog = kzalloc(sizeof(*prog), GFP_KERNEL); - if (!prog) - return -ENOBUFS; - - ret = tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE); - if (ret < 0) - goto errout; - - if (oldprog) { - if (handle && oldprog->handle != handle) { - ret = -EINVAL; - goto errout; - } - } - - if (handle == 0) - prog->handle = cls_bpf_grab_new_handle(tp, head); - else - prog->handle = handle; - if (prog->handle == 0) { - ret = -EINVAL; - goto errout; - } - - ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], - ovr); - if (ret < 0) - goto errout; - - ret = cls_bpf_offload(tp, prog, oldprog); - if (ret) { - __cls_bpf_delete_prog(prog); - return ret; - } + ret = cls_bpf_offload(tp, prog, oldprog, extack); + if (ret) + goto errout_parms; if (!tc_in_hw(prog->gen_flags)) prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, prog->gen_flags); + if (oldprog) { + idr_replace(&head->handle_idr, prog, handle); list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); - call_rcu(&oldprog->rcu, cls_bpf_delete_prog_rcu); + tcf_exts_get_net(&oldprog->exts); + tcf_queue_work(&oldprog->rwork, cls_bpf_delete_prog_work); } else { list_add_rcu(&prog->link, &head->plist); } - *arg = (unsigned long) prog; + *arg = prog; return 0; +errout_parms: + if (bound_to_filter) + tcf_unbind_filter(tp, &prog->res); + cls_bpf_free_parms(prog); +errout_idr: + if (!oldprog) + idr_remove(&head->handle_idr, prog->handle); errout: tcf_exts_destroy(&prog->exts); kfree(prog); @@ -578,10 +574,10 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, return 0; } -static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *tm) +static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *tm, bool rtnl_held) { - struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; + struct cls_bpf_prog *prog = fh; struct nlattr *nest; u32 bpf_flags = 0; int ret; @@ -593,7 +589,7 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, cls_bpf_offload_update_stats(tp, prog); - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -631,23 +627,58 @@ nla_put_failure: return -1; } -static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl, + void *q, unsigned long base) +{ + struct cls_bpf_prog *prog = fh; + + tc_cls_bind_class(classid, cl, q, &prog->res, base); +} + +static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog; list_for_each_entry(prog, &head->plist, link) { - if (arg->count < arg->skip) - goto skip; - if (arg->fn(tp, (unsigned long) prog, arg) < 0) { - arg->stop = 1; + if (!tc_cls_stats_dump(tp, arg, prog)) break; - } -skip: - arg->count++; } } +static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct cls_bpf_head *head = rtnl_dereference(tp->root); + struct tcf_block *block = tp->chain->block; + struct tc_cls_bpf_offload cls_bpf = {}; + struct cls_bpf_prog *prog; + int err; + + list_for_each_entry(prog, &head->plist, link) { + if (tc_skip_hw(prog->gen_flags)) + continue; + + tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, + extack); + cls_bpf.command = TC_CLSBPF_OFFLOAD; + cls_bpf.exts = &prog->exts; + cls_bpf.prog = add ? prog->filter : NULL; + cls_bpf.oldprog = add ? NULL : prog->filter; + cls_bpf.name = prog->bpf_name; + cls_bpf.exts_integrated = prog->exts_integrated; + + err = tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSBPF, + &cls_bpf, cb_priv, &prog->gen_flags, + &prog->in_hw_count); + if (err) + return err; + } + + return 0; +} + static struct tcf_proto_ops cls_bpf_ops __read_mostly = { .kind = "bpf", .owner = THIS_MODULE, @@ -658,8 +689,11 @@ static struct tcf_proto_ops cls_bpf_ops __read_mostly = { .change = cls_bpf_change, .delete = cls_bpf_delete, .walk = cls_bpf_walk, + .reoffload = cls_bpf_reoffload, .dump = cls_bpf_dump, + .bind_class = cls_bpf_bind_class, }; +MODULE_ALIAS_NET_CLS("bpf"); static int __init cls_bpf_init_mod(void) { diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 12ce547eea04..424252982d6a 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_cgroup.c Control Group Classifier * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> */ @@ -17,21 +13,25 @@ #include <net/pkt_cls.h> #include <net/sock.h> #include <net/cls_cgroup.h> +#include <net/tc_wrapper.h> struct cls_cgroup_head { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; struct tcf_proto *tp; - struct rcu_head rcu; + struct rcu_work rwork; }; -static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int cls_cgroup_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { struct cls_cgroup_head *head = rcu_dereference_bh(tp->root); u32 classid = task_get_classid(skb); + if (unlikely(!head)) + return -1; if (!classid) return -1; if (!tcf_em_tree_match(skb, &head->ematches, NULL)) @@ -43,9 +43,9 @@ static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, return tcf_exts_exec(skb, &head->exts, res); } -static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle) +static void *cls_cgroup_get(struct tcf_proto *tp, u32 handle) { - return 0UL; + return NULL; } static int cls_cgroup_init(struct tcf_proto *tp) @@ -57,27 +57,33 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = { [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED }, }; -static void cls_cgroup_destroy_rcu(struct rcu_head *root) +static void __cls_cgroup_destroy(struct cls_cgroup_head *head) { - struct cls_cgroup_head *head = container_of(root, - struct cls_cgroup_head, - rcu); - tcf_exts_destroy(&head->exts); tcf_em_tree_destroy(&head->ematches); + tcf_exts_put_net(&head->exts); kfree(head); } +static void cls_cgroup_destroy_work(struct work_struct *work) +{ + struct cls_cgroup_head *head = container_of(to_rcu_work(work), + struct cls_cgroup_head, + rwork); + rtnl_lock(); + __cls_cgroup_destroy(head); + rtnl_unlock(); +} + static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, u32 flags, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_CGROUP_MAX + 1]; struct cls_cgroup_head *head = rtnl_dereference(tp->root); struct cls_cgroup_head *new; - struct tcf_ematch_tree t; - struct tcf_exts e; int err; if (!tca[TCA_OPTIONS]) @@ -93,37 +99,31 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOBUFS; - err = tcf_exts_init(&new->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); + err = tcf_exts_init(&new->exts, net, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); if (err < 0) goto errout; new->handle = handle; new->tp = tp; - err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS], - cgroup_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_CGROUP_MAX, + tca[TCA_OPTIONS], cgroup_policy, + NULL); if (err < 0) goto errout; - err = tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, flags, + extack); if (err < 0) goto errout; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); - if (err < 0) { - tcf_exts_destroy(&e); - goto errout; - } - err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t); - if (err < 0) { - tcf_exts_destroy(&e); + err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &new->ematches); + if (err < 0) goto errout; - } - - tcf_exts_change(tp, &new->exts, &e); - tcf_em_tree_change(tp, &new->ematches, &t); rcu_assign_pointer(tp->root, new); - if (head) - call_rcu(&head->rcu, cls_cgroup_destroy_rcu); + if (head) { + tcf_exts_get_net(&head->exts); + tcf_queue_work(&head->rwork, cls_cgroup_destroy_work); + } return 0; errout: tcf_exts_destroy(&new->exts); @@ -131,28 +131,37 @@ errout: return err; } -static void cls_cgroup_destroy(struct tcf_proto *tp) +static void cls_cgroup_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); /* Head can still be NULL due to cls_cgroup_init(). */ - if (head) - call_rcu(&head->rcu, cls_cgroup_destroy_rcu); + if (head) { + if (tcf_exts_get_net(&head->exts)) + tcf_queue_work(&head->rwork, cls_cgroup_destroy_work); + else + __cls_cgroup_destroy(head); + } } -static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int cls_cgroup_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long) head, arg) < 0) { + if (!head) + return; + if (arg->fn(tp, head, arg) < 0) { arg->stop = 1; return; } @@ -160,15 +169,15 @@ skip: arg->count++; } -static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); struct nlattr *nest; t->tcm_handle = head->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -200,6 +209,7 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = { .dump = cls_cgroup_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("cgroup"); static int __init init_cgroup_cls(void) { @@ -213,4 +223,5 @@ static void __exit exit_cgroup_cls(void) module_init(init_cgroup_cls); module_exit(exit_cgroup_cls); +MODULE_DESCRIPTION("TC cgroup classifier"); MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 3065752b9cda..5693b41b093f 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_flow.c Generic flow classifier * * Copyright (c) 2007, 2008 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. */ #include <linux/kernel.h> @@ -28,6 +24,7 @@ #include <net/ip.h> #include <net/route.h> #include <net/flow_dissector.h> +#include <net/tc_wrapper.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> @@ -57,7 +54,7 @@ struct flow_filter { u32 divisor; u32 baseclass; u32 hashrnd; - struct rcu_head rcu; + struct rcu_work rwork; }; static inline u32 addr_fold(void *addr) @@ -84,7 +81,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) if (dst) return ntohl(dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_proto(const struct sk_buff *skb, @@ -108,7 +105,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, if (flow->ports.ports) return ntohs(flow->ports.dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -155,7 +152,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -168,7 +165,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): @@ -229,7 +226,7 @@ static u32 flow_get_skgid(const struct sk_buff *skb) static u32 flow_get_vlan_tag(const struct sk_buff *skb) { - u16 uninitialized_var(tag); + u16 tag; if (vlan_get_tag(skb, &tag) < 0) return 0; @@ -296,8 +293,9 @@ static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow) (1 << FLOW_KEY_NFCT_PROTO_SRC) | \ (1 << FLOW_KEY_NFCT_PROTO_DST)) -static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int flow_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { struct flow_head *head = rcu_dereference_bh(tp->root); struct flow_filter *f; @@ -345,9 +343,9 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static void flow_perturbation(unsigned long arg) +static void flow_perturbation(struct timer_list *t) { - struct flow_filter *f = (struct flow_filter *)arg; + struct flow_filter *f = timer_container_of(f, t, perturb_timer); get_random_bytes(&f->hashrnd, 4); if (f->perturb_period) @@ -358,7 +356,8 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_KEYS] = { .type = NLA_U32 }, [TCA_FLOW_MODE] = { .type = NLA_U32 }, [TCA_FLOW_BASECLASS] = { .type = NLA_U32 }, - [TCA_FLOW_RSHIFT] = { .type = NLA_U32 }, + [TCA_FLOW_RSHIFT] = NLA_POLICY_MAX(NLA_U32, + 31 /* BITS_PER_U32 - 1 */), [TCA_FLOW_ADDEND] = { .type = NLA_U32 }, [TCA_FLOW_MASK] = { .type = NLA_U32 }, [TCA_FLOW_XOR] = { .type = NLA_U32 }, @@ -369,27 +368,35 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_PERTURB] = { .type = NLA_U32 }, }; -static void flow_destroy_filter(struct rcu_head *head) +static void __flow_destroy_filter(struct flow_filter *f) { - struct flow_filter *f = container_of(head, struct flow_filter, rcu); - - del_timer_sync(&f->perturb_timer); + timer_shutdown_sync(&f->perturb_timer); tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); + tcf_exts_put_net(&f->exts); kfree(f); } +static void flow_destroy_filter_work(struct work_struct *work) +{ + struct flow_filter *f = container_of(to_rcu_work(work), + struct flow_filter, + rwork); + rtnl_lock(); + __flow_destroy_filter(f); + rtnl_unlock(); +} + static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, u32 flags, + struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *fold, *fnew; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FLOW_MAX + 1]; - struct tcf_exts e; - struct tcf_ematch_tree t; unsigned int nkeys = 0; unsigned int perturb_period = 0; u32 baseclass = 0; @@ -400,7 +407,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (opt == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_FLOW_MAX, opt, flow_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_FLOW_MAX, opt, flow_policy, + NULL); if (err < 0) return err; @@ -425,31 +433,28 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, return -EOPNOTSUPP; } - err = tcf_exts_init(&e, TCA_FLOW_ACT, TCA_FLOW_POLICE); - if (err < 0) - goto err1; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); - if (err < 0) - goto err1; + fnew = kzalloc(sizeof(*fnew), GFP_KERNEL); + if (!fnew) + return -ENOBUFS; - err = tcf_em_tree_validate(tp, tb[TCA_FLOW_EMATCHES], &t); + err = tcf_em_tree_validate(tp, tb[TCA_FLOW_EMATCHES], &fnew->ematches); if (err < 0) goto err1; - err = -ENOBUFS; - fnew = kzalloc(sizeof(*fnew), GFP_KERNEL); - if (!fnew) + err = tcf_exts_init(&fnew->exts, net, TCA_FLOW_ACT, TCA_FLOW_POLICE); + if (err < 0) goto err2; - err = tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, flags, + extack); if (err < 0) - goto err3; + goto err2; - fold = (struct flow_filter *)*arg; + fold = *arg; if (fold) { err = -EINVAL; if (fold->handle != handle && handle) - goto err3; + goto err2; /* Copy fold into fnew */ fnew->tp = fold->tp; @@ -469,36 +474,39 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (tb[TCA_FLOW_MODE]) mode = nla_get_u32(tb[TCA_FLOW_MODE]); if (mode != FLOW_MODE_HASH && nkeys > 1) - goto err3; + goto err2; if (mode == FLOW_MODE_HASH) perturb_period = fold->perturb_period; if (tb[TCA_FLOW_PERTURB]) { if (mode != FLOW_MODE_HASH) - goto err3; + goto err2; perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } } else { err = -EINVAL; if (!handle) - goto err3; + goto err2; if (!tb[TCA_FLOW_KEYS]) - goto err3; + goto err2; mode = FLOW_MODE_MAP; if (tb[TCA_FLOW_MODE]) mode = nla_get_u32(tb[TCA_FLOW_MODE]); if (mode != FLOW_MODE_HASH && nkeys > 1) - goto err3; + goto err2; if (tb[TCA_FLOW_PERTURB]) { if (mode != FLOW_MODE_HASH) - goto err3; + goto err2; perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } - if (TC_H_MAJ(baseclass) == 0) - baseclass = TC_H_MAKE(tp->q->handle, baseclass); + if (TC_H_MAJ(baseclass) == 0) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + + baseclass = TC_H_MAKE(q->handle, baseclass); + } if (TC_H_MIN(baseclass) == 0) baseclass = TC_H_MAKE(baseclass, 1); @@ -508,13 +516,9 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, get_random_bytes(&fnew->hashrnd, 4); } - setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation, - (unsigned long)fnew); - - tcf_exts_change(tp, &fnew->exts, &e); - tcf_em_tree_change(tp, &fnew->ematches, &t); + timer_setup(&fnew->perturb_timer, flow_perturbation, TIMER_DEFERRABLE); - netif_keep_dst(qdisc_dev(tp->q)); + tcf_block_netif_keep_dst(tp->chain->block); if (tb[TCA_FLOW_KEYS]) { fnew->keymask = keymask; @@ -541,34 +545,36 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (perturb_period) mod_timer(&fnew->perturb_timer, jiffies + perturb_period); - if (*arg == 0) + if (!*arg) list_add_tail_rcu(&fnew->list, &head->filters); else list_replace_rcu(&fold->list, &fnew->list); - *arg = (unsigned long)fnew; + *arg = fnew; - if (fold) - call_rcu(&fold->rcu, flow_destroy_filter); + if (fold) { + tcf_exts_get_net(&fold->exts); + tcf_queue_work(&fold->rwork, flow_destroy_filter_work); + } return 0; -err3: - tcf_exts_destroy(&fnew->exts); err2: - tcf_em_tree_destroy(&t); - kfree(fnew); + tcf_exts_destroy(&fnew->exts); + tcf_em_tree_destroy(&fnew->ematches); err1: - tcf_exts_destroy(&e); + kfree(fnew); return err; } -static int flow_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int flow_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); - struct flow_filter *f = (struct flow_filter *)arg; + struct flow_filter *f = arg; list_del_rcu(&f->list); - call_rcu(&f->rcu, flow_destroy_filter); + tcf_exts_get_net(&f->exts); + tcf_queue_work(&f->rwork, flow_destroy_filter_work); *last = list_empty(&head->filters); return 0; } @@ -585,33 +591,37 @@ static int flow_init(struct tcf_proto *tp) return 0; } -static void flow_destroy(struct tcf_proto *tp) +static void flow_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f, *next; list_for_each_entry_safe(f, next, &head->filters, list) { list_del_rcu(&f->list); - call_rcu(&f->rcu, flow_destroy_filter); + if (tcf_exts_get_net(&f->exts)) + tcf_queue_work(&f->rwork, flow_destroy_filter_work); + else + __flow_destroy_filter(f); } kfree_rcu(head, rcu); } -static unsigned long flow_get(struct tcf_proto *tp, u32 handle) +static void *flow_get(struct tcf_proto *tp, u32 handle) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f; list_for_each_entry(f, &head->filters, list) if (f->handle == handle) - return (unsigned long)f; - return 0; + return f; + return NULL; } -static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { - struct flow_filter *f = (struct flow_filter *)fh; + struct flow_filter *f = fh; struct nlattr *nest; if (f == NULL) @@ -619,7 +629,7 @@ static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -669,20 +679,15 @@ nla_put_failure: return -1; } -static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f; list_for_each_entry(f, &head->filters, list) { - if (arg->count < arg->skip) - goto skip; - if (arg->fn(tp, (unsigned long)f, arg) < 0) { - arg->stop = 1; + if (!tc_cls_stats_dump(tp, arg, f)) break; - } -skip: - arg->count++; } } @@ -698,6 +703,7 @@ static struct tcf_proto_ops cls_flow_ops __read_mostly = { .walk = flow_walk, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("flow"); static int __init cls_flow_init(void) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7832eb93379b..7669371c1354 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_flower.c Flower classifier * * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include <linux/kernel.h> @@ -14,27 +10,55 @@ #include <linux/module.h> #include <linux/rhashtable.h> #include <linux/workqueue.h> +#include <linux/refcount.h> +#include <linux/bitfield.h> #include <linux/if_ether.h> #include <linux/in6.h> #include <linux/ip.h> #include <linux/mpls.h> +#include <linux/ppp_defs.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/ip.h> #include <net/flow_dissector.h> +#include <net/geneve.h> +#include <net/vxlan.h> +#include <net/erspan.h> +#include <net/gtp.h> +#include <net/pfcp.h> +#include <net/tc_wrapper.h> #include <net/dst.h> #include <net/dst_metadata.h> +#include <uapi/linux/netfilter/nf_conntrack_common.h> + +#define TCA_FLOWER_KEY_CT_FLAGS_MAX \ + ((__TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) << 1) +#define TCA_FLOWER_KEY_CT_FLAGS_MASK \ + (TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) + +#define TCA_FLOWER_KEY_FLAGS_POLICY_MASK \ + (TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT | \ + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST) + +#define TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK \ + (TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT) + struct fl_flow_key { - int indev_ifindex; + struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; struct flow_dissector_key_control enc_control; struct flow_dissector_key_basic basic; struct flow_dissector_key_eth_addrs eth; struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_vlan cvlan; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; @@ -51,6 +75,16 @@ struct fl_flow_key { struct flow_dissector_key_mpls mpls; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ip ip; + struct flow_dissector_key_ip enc_ip; + struct flow_dissector_key_enc_opts enc_opts; + struct flow_dissector_key_ports_range tp_range; + struct flow_dissector_key_ct ct; + struct flow_dissector_key_hash hash; + struct flow_dissector_key_num_of_vlans num_of_vlans; + struct flow_dissector_key_pppoe pppoe; + struct flow_dissector_key_l2tpv3 l2tpv3; + struct flow_dissector_key_ipsec ipsec; + struct flow_dissector_key_cfm cfm; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -61,35 +95,61 @@ struct fl_flow_mask_range { struct fl_flow_mask { struct fl_flow_key key; struct fl_flow_mask_range range; - struct rcu_head rcu; + u32 flags; + struct rhash_head ht_node; + struct rhashtable ht; + struct rhashtable_params filter_ht_params; + struct flow_dissector dissector; + struct list_head filters; + struct rcu_work rwork; + struct list_head list; + refcount_t refcnt; +}; + +struct fl_flow_tmplt { + struct fl_flow_key dummy_key; + struct fl_flow_key mask; + struct flow_dissector dissector; + struct tcf_chain *chain; }; struct cls_fl_head { struct rhashtable ht; - struct fl_flow_mask mask; - struct flow_dissector dissector; - u32 hgen; - bool mask_assigned; - struct list_head filters; - struct rhashtable_params ht_params; - union { - struct work_struct work; - struct rcu_head rcu; - }; + spinlock_t masks_lock; /* Protect masks list */ + struct list_head masks; + struct list_head hw_filters; + struct rcu_work rwork; + struct idr handle_idr; }; struct cls_fl_filter { + struct fl_flow_mask *mask; struct rhash_head ht_node; struct fl_flow_key mkey; struct tcf_exts exts; struct tcf_result res; struct fl_flow_key key; struct list_head list; + struct list_head hw_list; u32 handle; u32 flags; - struct rcu_head rcu; - struct tc_to_netdev tc; + u32 in_hw_count; + u8 needs_tc_skb_ext:1; + struct rcu_work rwork; struct net_device *hw_dev; + /* Flower classifier is unlocked, which means that its reference counter + * can be changed concurrently without any kind of external + * synchronization. Use atomic reference counter to be concurrency-safe. + */ + refcount_t refcnt; + bool deleted; +}; + +static const struct rhashtable_params mask_ht_params = { + .key_offset = offsetof(struct fl_flow_mask, key), + .key_len = sizeof(struct fl_flow_key), + .head_offset = offsetof(struct fl_flow_mask, ht_node), + .automatic_shrinking = true, }; static unsigned short int fl_mask_range(const struct fl_flow_mask *mask) @@ -101,13 +161,19 @@ static void fl_mask_update_range(struct fl_flow_mask *mask) { const u8 *bytes = (const u8 *) &mask->key; size_t size = sizeof(mask->key); - size_t i, first = 0, last = size - 1; + size_t i, first = 0, last; - for (i = 0; i < sizeof(mask->key); i++) { + for (i = 0; i < size; i++) { + if (bytes[i]) { + first = i; + break; + } + } + last = first; + for (i = size - 1; i != first; i--) { if (bytes[i]) { - if (!first && i) - first = i; last = i; + break; } } mask->range.start = rounddown(first, sizeof(long)); @@ -132,71 +198,163 @@ static void fl_set_masked_key(struct fl_flow_key *mkey, struct fl_flow_key *key, *lmkey++ = *lkey++ & *lmask++; } +static bool fl_mask_fits_tmplt(struct fl_flow_tmplt *tmplt, + struct fl_flow_mask *mask) +{ + const long *lmask = fl_key_get_start(&mask->key, mask); + const long *ltmplt; + int i; + + if (!tmplt) + return true; + ltmplt = fl_key_get_start(&tmplt->mask, mask); + for (i = 0; i < fl_mask_range(mask); i += sizeof(long)) { + if (~*ltmplt++ & *lmask++) + return false; + } + return true; +} + static void fl_clear_masked_range(struct fl_flow_key *key, struct fl_flow_mask *mask) { memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask)); } -static struct cls_fl_filter *fl_lookup(struct cls_fl_head *head, - struct fl_flow_key *mkey) +static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, + struct fl_flow_key *key, + struct fl_flow_key *mkey) { - return rhashtable_lookup_fast(&head->ht, - fl_key_get_start(mkey, &head->mask), - head->ht_params); + u16 min_mask, max_mask, min_val, max_val; + + min_mask = ntohs(filter->mask->key.tp_range.tp_min.dst); + max_mask = ntohs(filter->mask->key.tp_range.tp_max.dst); + min_val = ntohs(filter->key.tp_range.tp_min.dst); + max_val = ntohs(filter->key.tp_range.tp_max.dst); + + if (min_mask && max_mask) { + if (ntohs(key->tp_range.tp.dst) < min_val || + ntohs(key->tp_range.tp.dst) > max_val) + return false; + + /* skb does not have min and max values */ + mkey->tp_range.tp_min.dst = filter->mkey.tp_range.tp_min.dst; + mkey->tp_range.tp_max.dst = filter->mkey.tp_range.tp_max.dst; + } + return true; } -static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, + struct fl_flow_key *key, + struct fl_flow_key *mkey) { - struct cls_fl_head *head = rcu_dereference_bh(tp->root); - struct cls_fl_filter *f; - struct fl_flow_key skb_key; - struct fl_flow_key skb_mkey; - struct ip_tunnel_info *info; + u16 min_mask, max_mask, min_val, max_val; - if (!atomic_read(&head->ht.nelems)) - return -1; + min_mask = ntohs(filter->mask->key.tp_range.tp_min.src); + max_mask = ntohs(filter->mask->key.tp_range.tp_max.src); + min_val = ntohs(filter->key.tp_range.tp_min.src); + max_val = ntohs(filter->key.tp_range.tp_max.src); - fl_clear_masked_range(&skb_key, &head->mask); + if (min_mask && max_mask) { + if (ntohs(key->tp_range.tp.src) < min_val || + ntohs(key->tp_range.tp.src) > max_val) + return false; - info = skb_tunnel_info(skb); - if (info) { - struct ip_tunnel_key *key = &info->key; + /* skb does not have min and max values */ + mkey->tp_range.tp_min.src = filter->mkey.tp_range.tp_min.src; + mkey->tp_range.tp_max.src = filter->mkey.tp_range.tp_max.src; + } + return true; +} - switch (ip_tunnel_info_af(info)) { - case AF_INET: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV4_ADDRS; - skb_key.enc_ipv4.src = key->u.ipv4.src; - skb_key.enc_ipv4.dst = key->u.ipv4.dst; - break; - case AF_INET6: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV6_ADDRS; - skb_key.enc_ipv6.src = key->u.ipv6.src; - skb_key.enc_ipv6.dst = key->u.ipv6.dst; - break; - } +static struct cls_fl_filter *__fl_lookup(struct fl_flow_mask *mask, + struct fl_flow_key *mkey) +{ + return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask), + mask->filter_ht_params); +} + +static struct cls_fl_filter *fl_lookup_range(struct fl_flow_mask *mask, + struct fl_flow_key *mkey, + struct fl_flow_key *key) +{ + struct cls_fl_filter *filter, *f; + + list_for_each_entry_rcu(filter, &mask->filters, list) { + if (!fl_range_port_dst_cmp(filter, key, mkey)) + continue; - skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); - skb_key.enc_tp.src = key->tp_src; - skb_key.enc_tp.dst = key->tp_dst; + if (!fl_range_port_src_cmp(filter, key, mkey)) + continue; + + f = __fl_lookup(mask, mkey); + if (f) + return f; } + return NULL; +} - skb_key.indev_ifindex = skb->skb_iif; - /* skb_flow_dissect() does not set n_proto in case an unknown protocol, - * so do it rather here. - */ - skb_key.basic.n_proto = skb->protocol; - skb_flow_dissect(skb, &head->dissector, &skb_key, 0); +static noinline_for_stack +struct cls_fl_filter *fl_mask_lookup(struct fl_flow_mask *mask, struct fl_flow_key *key) +{ + struct fl_flow_key mkey; + + fl_set_masked_key(&mkey, key, mask); + if ((mask->flags & TCA_FLOWER_MASK_FLAGS_RANGE)) + return fl_lookup_range(mask, &mkey, key); + + return __fl_lookup(mask, &mkey); +} - fl_set_masked_key(&skb_mkey, &skb_key, &head->mask); +static u16 fl_ct_info_to_flower_map[] = { + [IP_CT_ESTABLISHED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED, + [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_RELATED, + [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, + [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_RELATED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, + [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_NEW, +}; + +TC_INDIRECT_SCOPE int fl_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) +{ + struct cls_fl_head *head = rcu_dereference_bh(tp->root); + bool post_ct = qdisc_skb_cb(skb)->post_ct; + u16 zone = tc_skb_cb(skb)->zone; + struct fl_flow_key skb_key; + struct fl_flow_mask *mask; + struct cls_fl_filter *f; - f = fl_lookup(head, &skb_mkey); - if (f && !tc_skip_sw(f->flags)) { - *res = f->res; - return tcf_exts_exec(skb, &f->exts, res); + list_for_each_entry_rcu(mask, &head->masks, list) { + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); + fl_clear_masked_range(&skb_key, mask); + + skb_flow_dissect_meta(skb, &mask->dissector, &skb_key); + /* skb_flow_dissect() does not set n_proto in case an unknown + * protocol, so do it rather here. + */ + skb_key.basic.n_proto = skb_protocol(skb, false); + skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); + skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, + fl_ct_info_to_flower_map, + ARRAY_SIZE(fl_ct_info_to_flower_map), + post_ct, zone); + skb_flow_dissect_hash(skb, &mask->dissector, &skb_key); + skb_flow_dissect(skb, &mask->dissector, &skb_key, + FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP); + + f = fl_mask_lookup(mask, &skb_key); + if (f && !tc_skip_sw(f->flags)) { + *res = f->res; + return tcf_exts_exec(skb, &f->exts, res); + } } return -1; } @@ -209,156 +367,273 @@ static int fl_init(struct tcf_proto *tp) if (!head) return -ENOBUFS; - INIT_LIST_HEAD_RCU(&head->filters); + spin_lock_init(&head->masks_lock); + INIT_LIST_HEAD_RCU(&head->masks); + INIT_LIST_HEAD(&head->hw_filters); rcu_assign_pointer(tp->root, head); + idr_init(&head->handle_idr); - return 0; + return rhashtable_init(&head->ht, &mask_ht_params); +} + +static void fl_mask_free(struct fl_flow_mask *mask, bool mask_init_done) +{ + /* temporary masks don't have their filters list and ht initialized */ + if (mask_init_done) { + WARN_ON(!list_empty(&mask->filters)); + rhashtable_destroy(&mask->ht); + } + kfree(mask); +} + +static void fl_mask_free_work(struct work_struct *work) +{ + struct fl_flow_mask *mask = container_of(to_rcu_work(work), + struct fl_flow_mask, rwork); + + fl_mask_free(mask, true); +} + +static void fl_uninit_mask_free_work(struct work_struct *work) +{ + struct fl_flow_mask *mask = container_of(to_rcu_work(work), + struct fl_flow_mask, rwork); + + fl_mask_free(mask, false); +} + +static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask) +{ + if (!refcount_dec_and_test(&mask->refcnt)) + return false; + + rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params); + + spin_lock(&head->masks_lock); + list_del_rcu(&mask->list); + spin_unlock(&head->masks_lock); + + tcf_queue_work(&mask->rwork, fl_mask_free_work); + + return true; } -static void fl_destroy_filter(struct rcu_head *head) +static struct cls_fl_head *fl_head_dereference(struct tcf_proto *tp) { - struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu); + /* Flower classifier only changes root pointer during init and destroy. + * Users must obtain reference to tcf_proto instance before calling its + * API, so tp->root pointer is protected from concurrent call to + * fl_destroy() by reference counting. + */ + return rcu_dereference_raw(tp->root); +} +static void __fl_destroy_filter(struct cls_fl_filter *f) +{ + if (f->needs_tc_skb_ext) + tc_skb_ext_tc_disable(); tcf_exts_destroy(&f->exts); + tcf_exts_put_net(&f->exts); kfree(f); } -static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) +static void fl_destroy_filter_work(struct work_struct *work) { - struct tc_cls_flower_offload offload = {0}; - struct net_device *dev = f->hw_dev; - struct tc_to_netdev *tc = &f->tc; + struct cls_fl_filter *f = container_of(to_rcu_work(work), + struct cls_fl_filter, rwork); - if (!tc_can_offload(dev, tp)) - return; + __fl_destroy_filter(f); +} + +static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, + bool rtnl_held, struct netlink_ext_ack *extack) +{ + struct tcf_block *block = tp->chain->block; + struct flow_cls_offload cls_flower = {}; - offload.command = TC_CLSFLOWER_DESTROY; - offload.prio = tp->prio; - offload.cookie = (unsigned long)f; + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); + cls_flower.command = FLOW_CLS_DESTROY; + cls_flower.cookie = (unsigned long) f; - tc->type = TC_SETUP_CLSFLOWER; - tc->cls_flower = &offload; + tc_setup_cb_destroy(block, tp, TC_SETUP_CLSFLOWER, &cls_flower, false, + &f->flags, &f->in_hw_count, rtnl_held); - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->chain->index, - tp->protocol, tc); } static int fl_hw_replace_filter(struct tcf_proto *tp, - struct flow_dissector *dissector, - struct fl_flow_key *mask, - struct cls_fl_filter *f) + struct cls_fl_filter *f, bool rtnl_held, + struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_flower_offload offload = {0}; - struct tc_to_netdev *tc = &f->tc; - int err; - - if (!tc_can_offload(dev, tp)) { - if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) || - (f->hw_dev && !tc_can_offload(f->hw_dev, tp))) { - f->hw_dev = dev; - return tc_skip_sw(f->flags) ? -EINVAL : 0; - } - dev = f->hw_dev; - tc->egress_dev = true; - } else { - f->hw_dev = dev; + struct tcf_block *block = tp->chain->block; + struct flow_cls_offload cls_flower = {}; + bool skip_sw = tc_skip_sw(f->flags); + int err = 0; + + cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts)); + if (!cls_flower.rule) + return -ENOMEM; + + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); + cls_flower.command = FLOW_CLS_REPLACE; + cls_flower.cookie = (unsigned long) f; + cls_flower.rule->match.dissector = &f->mask->dissector; + cls_flower.rule->match.mask = &f->mask->key; + cls_flower.rule->match.key = &f->mkey; + cls_flower.classid = f->res.classid; + + err = tc_setup_offload_action(&cls_flower.rule->action, &f->exts, + cls_flower.common.extack); + if (err) { + kfree(cls_flower.rule); + + return skip_sw ? err : 0; } - offload.command = TC_CLSFLOWER_REPLACE; - offload.prio = tp->prio; - offload.cookie = (unsigned long)f; - offload.dissector = dissector; - offload.mask = mask; - offload.key = &f->mkey; - offload.exts = &f->exts; + err = tc_setup_cb_add(block, tp, TC_SETUP_CLSFLOWER, &cls_flower, + skip_sw, &f->flags, &f->in_hw_count, rtnl_held); + tc_cleanup_offload_action(&cls_flower.rule->action); + kfree(cls_flower.rule); - tc->type = TC_SETUP_CLSFLOWER; - tc->cls_flower = &offload; + if (err) { + fl_hw_destroy_filter(tp, f, rtnl_held, NULL); + return err; + } - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, tc); - if (!err) - f->flags |= TCA_CLS_FLAGS_IN_HW; + if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - if (tc_skip_sw(f->flags)) - return err; return 0; } -static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) +static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f, + bool rtnl_held) { - struct tc_cls_flower_offload offload = {0}; - struct net_device *dev = f->hw_dev; - struct tc_to_netdev *tc = &f->tc; + struct tcf_block *block = tp->chain->block; + struct flow_cls_offload cls_flower = {}; + + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL); + cls_flower.command = FLOW_CLS_STATS; + cls_flower.cookie = (unsigned long) f; + cls_flower.classid = f->res.classid; - if (!tc_can_offload(dev, tp)) + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, + rtnl_held); + + tcf_exts_hw_stats_update(&f->exts, &cls_flower.stats, cls_flower.use_act_stats); +} + +static void __fl_put(struct cls_fl_filter *f) +{ + if (!refcount_dec_and_test(&f->refcnt)) return; - offload.command = TC_CLSFLOWER_STATS; - offload.prio = tp->prio; - offload.cookie = (unsigned long)f; - offload.exts = &f->exts; + if (tcf_exts_get_net(&f->exts)) + tcf_queue_work(&f->rwork, fl_destroy_filter_work); + else + __fl_destroy_filter(f); +} - tc->type = TC_SETUP_CLSFLOWER; - tc->cls_flower = &offload; +static struct cls_fl_filter *__fl_get(struct cls_fl_head *head, u32 handle) +{ + struct cls_fl_filter *f; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, tc); + rcu_read_lock(); + f = idr_find(&head->handle_idr, handle); + if (f && !refcount_inc_not_zero(&f->refcnt)) + f = NULL; + rcu_read_unlock(); + + return f; +} + +static struct tcf_exts *fl_get_exts(const struct tcf_proto *tp, u32 handle) +{ + struct cls_fl_head *head = rcu_dereference_bh(tp->root); + struct cls_fl_filter *f; + + f = idr_find(&head->handle_idr, handle); + return f ? &f->exts : NULL; } -static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) +static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, + bool *last, bool rtnl_held, + struct netlink_ext_ack *extack) { + struct cls_fl_head *head = fl_head_dereference(tp); + + *last = false; + + spin_lock(&tp->lock); + if (f->deleted) { + spin_unlock(&tp->lock); + return -ENOENT; + } + + f->deleted = true; + rhashtable_remove_fast(&f->mask->ht, &f->ht_node, + f->mask->filter_ht_params); + idr_remove(&head->handle_idr, f->handle); list_del_rcu(&f->list); + spin_unlock(&tp->lock); + + *last = fl_mask_put(head, f->mask); if (!tc_skip_hw(f->flags)) - fl_hw_destroy_filter(tp, f); + fl_hw_destroy_filter(tp, f, rtnl_held, extack); tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, fl_destroy_filter); + __fl_put(f); + + return 0; } static void fl_destroy_sleepable(struct work_struct *work) { - struct cls_fl_head *head = container_of(work, struct cls_fl_head, - work); - if (head->mask_assigned) - rhashtable_destroy(&head->ht); + struct cls_fl_head *head = container_of(to_rcu_work(work), + struct cls_fl_head, + rwork); + + rhashtable_destroy(&head->ht); kfree(head); module_put(THIS_MODULE); } -static void fl_destroy_rcu(struct rcu_head *rcu) +static void fl_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { - struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu); + struct cls_fl_head *head = fl_head_dereference(tp); + struct fl_flow_mask *mask, *next_mask; + struct cls_fl_filter *f, *next; + bool last; + + list_for_each_entry_safe(mask, next_mask, &head->masks, list) { + list_for_each_entry_safe(f, next, &mask->filters, list) { + __fl_delete(tp, f, &last, rtnl_held, extack); + if (last) + break; + } + } + idr_destroy(&head->handle_idr); - INIT_WORK(&head->work, fl_destroy_sleepable); - schedule_work(&head->work); + __module_get(THIS_MODULE); + tcf_queue_work(&head->rwork, fl_destroy_sleepable); } -static void fl_destroy(struct tcf_proto *tp) +static void fl_put(struct tcf_proto *tp, void *arg) { - struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *f, *next; + struct cls_fl_filter *f = arg; - list_for_each_entry_safe(f, next, &head->filters, list) - __fl_delete(tp, f); - - __module_get(THIS_MODULE); - call_rcu(&head->rcu, fl_destroy_rcu); + __fl_put(f); } -static unsigned long fl_get(struct tcf_proto *tp, u32 handle) +static void *fl_get(struct tcf_proto *tp, u32 handle) { - struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *f; + struct cls_fl_head *head = fl_head_dereference(tp); - list_for_each_entry(f, &head->filters, list) - if (f->handle == handle) - return (unsigned long) f; - return 0; + return __fl_get(head, handle); } static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { - [TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC }, + [TCA_FLOWER_UNSPEC] = { .strict_start_type = + TCA_FLOWER_L2_MISS }, [TCA_FLOWER_CLASSID] = { .type = NLA_U32 }, [TCA_FLOWER_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ }, @@ -404,8 +679,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 }, - [TCA_FLOWER_KEY_FLAGS] = { .type = NLA_U32 }, - [TCA_FLOWER_KEY_FLAGS_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_FLAGS] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_FLAGS_POLICY_MASK), + [TCA_FLOWER_KEY_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_FLAGS_POLICY_MASK), [TCA_FLOWER_KEY_ICMPV4_TYPE] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ICMPV4_TYPE_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ICMPV4_CODE] = { .type = NLA_U8 }, @@ -428,12 +705,109 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_BOS] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_TC] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_LABEL] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_MPLS_OPTS] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_TCP_FLAGS] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_TCP_FLAGS_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_IP_TOS] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_IP_TOS_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_IP_TTL] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_IP_TTL_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_CVLAN_ID] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_CVLAN_PRIO] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_CVLAN_ETH_TYPE] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_IP_TOS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_IP_TOS_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_IP_TTL] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_CT_STATE] = + NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK), + [TCA_FLOWER_KEY_CT_STATE_MASK] = + NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK), + [TCA_FLOWER_KEY_CT_ZONE] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_CT_ZONE_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_CT_MARK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_CT_MARK_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_CT_LABELS] = { .type = NLA_BINARY, + .len = 128 / BITS_PER_BYTE }, + [TCA_FLOWER_KEY_CT_LABELS_MASK] = { .type = NLA_BINARY, + .len = 128 / BITS_PER_BYTE }, + [TCA_FLOWER_FLAGS] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_HASH] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_HASH_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_NUM_OF_VLANS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_SPI] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), + [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), + [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), +}; + +static const struct nla_policy +enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPTS_UNSPEC] = { + .strict_start_type = TCA_FLOWER_KEY_ENC_OPTS_VXLAN }, + [TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_GTP] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_PFCP] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, + .len = 127 }, +}; + +static const struct nla_policy +vxlan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, +}; + +static const struct nla_policy +gtp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_GTP_QFI] = { .type = NLA_U8 }, +}; + +static const struct nla_policy +pfcp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID] = { .type = NLA_U64 }, +}; + +static const struct nla_policy +mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { + [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_TC] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX + 1] = { + [TCA_FLOWER_KEY_CFM_MD_LEVEL] = NLA_POLICY_MAX(NLA_U8, + FLOW_DIS_CFM_MDL_MAX), + [TCA_FLOWER_KEY_CFM_OPCODE] = { .type = NLA_U8 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -442,65 +816,348 @@ static void fl_set_key_val(struct nlattr **tb, { if (!tb[val_type]) return; - memcpy(val, nla_data(tb[val_type]), len); + nla_memcpy(val, tb[val_type], len); if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type]) memset(mask, 0xff, len); else - memcpy(mask, nla_data(tb[mask_type]), len); + nla_memcpy(mask, tb[mask_type], len); +} + +static int fl_set_key_spi(struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + if (key->basic.ip_proto != IPPROTO_ESP && + key->basic.ip_proto != IPPROTO_AH) { + NL_SET_ERR_MSG(extack, + "Protocol must be either ESP or AH"); + return -EINVAL; + } + + fl_set_key_val(tb, &key->ipsec.spi, + TCA_FLOWER_KEY_SPI, + &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK, + sizeof(key->ipsec.spi)); + return 0; +} + +static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + fl_set_key_val(tb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.dst)); + fl_set_key_val(tb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_range.tp_max.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.dst)); + fl_set_key_val(tb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_range.tp_min.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.src)); + fl_set_key_val(tb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + + if (mask->tp_range.tp_min.dst != mask->tp_range.tp_max.dst) { + NL_SET_ERR_MSG(extack, + "Both min and max destination ports must be specified"); + return -EINVAL; + } + if (mask->tp_range.tp_min.src != mask->tp_range.tp_max.src) { + NL_SET_ERR_MSG(extack, + "Both min and max source ports must be specified"); + return -EINVAL; + } + if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && + ntohs(key->tp_range.tp_max.dst) <= + ntohs(key->tp_range.tp_min.dst)) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_PORT_DST_MIN], + "Invalid destination port range (min must be strictly smaller than max)"); + return -EINVAL; + } + if (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && + ntohs(key->tp_range.tp_max.src) <= + ntohs(key->tp_range.tp_min.src)) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_PORT_SRC_MIN], + "Invalid source port range (min must be strictly smaller than max)"); + return -EINVAL; + } + + return 0; +} + +static int fl_set_key_mpls_lse(const struct nlattr *nla_lse, + struct flow_dissector_key_mpls *key_val, + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1]; + struct flow_dissector_mpls_lse *lse_mask; + struct flow_dissector_mpls_lse *lse_val; + u8 lse_index; + u8 depth; + int err; + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX, nla_lse, + mpls_stack_entry_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]) { + NL_SET_ERR_MSG(extack, "Missing MPLS option \"depth\""); + return -EINVAL; + } + + depth = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH]); + + /* LSE depth starts at 1, for consistency with terminology used by + * RFC 3031 (section 3.9), where depth 0 refers to unlabeled packets. + */ + if (depth < 1 || depth > FLOW_DIS_MPLS_MAX) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH], + "Invalid MPLS depth"); + return -EINVAL; + } + lse_index = depth - 1; + + dissector_set_mpls_lse(key_val, lse_index); + dissector_set_mpls_lse(key_mask, lse_index); + + lse_val = &key_val->ls[lse_index]; + lse_mask = &key_mask->ls[lse_index]; + + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]) { + lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL]); + lse_mask->mpls_ttl = MPLS_TTL_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]) { + u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS]); + + if (bos & ~MPLS_BOS_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS], + "Bottom Of Stack (BOS) must be 0 or 1"); + return -EINVAL; + } + lse_val->mpls_bos = bos; + lse_mask->mpls_bos = MPLS_BOS_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]) { + u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC]); + + if (tc & ~MPLS_TC_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_TC], + "Traffic Class (TC) must be between 0 and 7"); + return -EINVAL; + } + lse_val->mpls_tc = tc; + lse_mask->mpls_tc = MPLS_TC_MASK; + } + if (tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]) { + u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL]); + + if (label & ~MPLS_LABEL_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL], + "Label must be between 0 and 1048575"); + return -EINVAL; + } + lse_val->mpls_label = label; + lse_mask->mpls_label = MPLS_LABEL_MASK; + } + + return 0; +} + +static int fl_set_key_mpls_opts(const struct nlattr *nla_mpls_opts, + struct flow_dissector_key_mpls *key_val, + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *nla_lse; + int rem; + int err; + + if (!(nla_mpls_opts->nla_type & NLA_F_NESTED)) { + NL_SET_ERR_MSG_ATTR(extack, nla_mpls_opts, + "NLA_F_NESTED is missing"); + return -EINVAL; + } + + nla_for_each_nested(nla_lse, nla_mpls_opts, rem) { + if (nla_type(nla_lse) != TCA_FLOWER_KEY_MPLS_OPTS_LSE) { + NL_SET_ERR_MSG_ATTR(extack, nla_lse, + "Invalid MPLS option type"); + return -EINVAL; + } + + err = fl_set_key_mpls_lse(nla_lse, key_val, key_mask, extack); + if (err < 0) + return err; + } + if (rem) { + NL_SET_ERR_MSG(extack, + "Bytes leftover after parsing MPLS options"); + return -EINVAL; + } + + return 0; } static int fl_set_key_mpls(struct nlattr **tb, struct flow_dissector_key_mpls *key_val, - struct flow_dissector_key_mpls *key_mask) + struct flow_dissector_key_mpls *key_mask, + struct netlink_ext_ack *extack) { + struct flow_dissector_mpls_lse *lse_mask; + struct flow_dissector_mpls_lse *lse_val; + + if (tb[TCA_FLOWER_KEY_MPLS_OPTS]) { + if (tb[TCA_FLOWER_KEY_MPLS_TTL] || + tb[TCA_FLOWER_KEY_MPLS_BOS] || + tb[TCA_FLOWER_KEY_MPLS_TC] || + tb[TCA_FLOWER_KEY_MPLS_LABEL]) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_OPTS], + "MPLS label, Traffic Class, Bottom Of Stack and Time To Live must be encapsulated in the MPLS options attribute"); + return -EBADMSG; + } + + return fl_set_key_mpls_opts(tb[TCA_FLOWER_KEY_MPLS_OPTS], + key_val, key_mask, extack); + } + + lse_val = &key_val->ls[0]; + lse_mask = &key_mask->ls[0]; + if (tb[TCA_FLOWER_KEY_MPLS_TTL]) { - key_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]); - key_mask->mpls_ttl = MPLS_TTL_MASK; + lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]); + lse_mask->mpls_ttl = MPLS_TTL_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } if (tb[TCA_FLOWER_KEY_MPLS_BOS]) { u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_BOS]); - if (bos & ~MPLS_BOS_MASK) + if (bos & ~MPLS_BOS_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_BOS], + "Bottom Of Stack (BOS) must be 0 or 1"); return -EINVAL; - key_val->mpls_bos = bos; - key_mask->mpls_bos = MPLS_BOS_MASK; + } + lse_val->mpls_bos = bos; + lse_mask->mpls_bos = MPLS_BOS_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } if (tb[TCA_FLOWER_KEY_MPLS_TC]) { u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TC]); - if (tc & ~MPLS_TC_MASK) + if (tc & ~MPLS_TC_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_TC], + "Traffic Class (TC) must be between 0 and 7"); return -EINVAL; - key_val->mpls_tc = tc; - key_mask->mpls_tc = MPLS_TC_MASK; + } + lse_val->mpls_tc = tc; + lse_mask->mpls_tc = MPLS_TC_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } if (tb[TCA_FLOWER_KEY_MPLS_LABEL]) { u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_LABEL]); - if (label & ~MPLS_LABEL_MASK) + if (label & ~MPLS_LABEL_MASK) { + NL_SET_ERR_MSG_ATTR(extack, + tb[TCA_FLOWER_KEY_MPLS_LABEL], + "Label must be between 0 and 1048575"); return -EINVAL; - key_val->mpls_label = label; - key_mask->mpls_label = MPLS_LABEL_MASK; + } + lse_val->mpls_label = label; + lse_mask->mpls_label = MPLS_LABEL_MASK; + dissector_set_mpls_lse(key_val, 0); + dissector_set_mpls_lse(key_mask, 0); } return 0; } static void fl_set_key_vlan(struct nlattr **tb, + __be16 ethertype, + int vlan_id_key, int vlan_prio_key, + int vlan_next_eth_type_key, struct flow_dissector_key_vlan *key_val, struct flow_dissector_key_vlan *key_mask) { #define VLAN_PRIORITY_MASK 0x7 - if (tb[TCA_FLOWER_KEY_VLAN_ID]) { + if (tb[vlan_id_key]) { key_val->vlan_id = - nla_get_u16(tb[TCA_FLOWER_KEY_VLAN_ID]) & VLAN_VID_MASK; + nla_get_u16(tb[vlan_id_key]) & VLAN_VID_MASK; key_mask->vlan_id = VLAN_VID_MASK; } - if (tb[TCA_FLOWER_KEY_VLAN_PRIO]) { + if (tb[vlan_prio_key]) { key_val->vlan_priority = - nla_get_u8(tb[TCA_FLOWER_KEY_VLAN_PRIO]) & + nla_get_u8(tb[vlan_prio_key]) & VLAN_PRIORITY_MASK; key_mask->vlan_priority = VLAN_PRIORITY_MASK; } + if (ethertype) { + key_val->vlan_tpid = ethertype; + key_mask->vlan_tpid = cpu_to_be16(~0); + } + if (tb[vlan_next_eth_type_key]) { + key_val->vlan_eth_type = + nla_get_be16(tb[vlan_next_eth_type_key]); + key_mask->vlan_eth_type = cpu_to_be16(~0); + } +} + +static void fl_set_key_pppoe(struct nlattr **tb, + struct flow_dissector_key_pppoe *key_val, + struct flow_dissector_key_pppoe *key_mask, + struct fl_flow_key *key, + struct fl_flow_key *mask) +{ + /* key_val::type must be set to ETH_P_PPP_SES + * because ETH_P_PPP_SES was stored in basic.n_proto + * which might get overwritten by ppp_proto + * or might be set to 0, the role of key_val::type + * is similar to vlan_key::tpid + */ + key_val->type = htons(ETH_P_PPP_SES); + key_mask->type = cpu_to_be16(~0); + + if (tb[TCA_FLOWER_KEY_PPPOE_SID]) { + key_val->session_id = + nla_get_be16(tb[TCA_FLOWER_KEY_PPPOE_SID]); + key_mask->session_id = cpu_to_be16(~0); + } + if (tb[TCA_FLOWER_KEY_PPP_PROTO]) { + key_val->ppp_proto = + nla_get_be16(tb[TCA_FLOWER_KEY_PPP_PROTO]); + key_mask->ppp_proto = cpu_to_be16(~0); + + if (key_val->ppp_proto == htons(PPP_IP)) { + key->basic.n_proto = htons(ETH_P_IP); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_IPV6)) { + key->basic.n_proto = htons(ETH_P_IPV6); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_MPLS_UC)) { + key->basic.n_proto = htons(ETH_P_MPLS_UC); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_MPLS_MC)) { + key->basic.n_proto = htons(ETH_P_MPLS_MC); + mask->basic.n_proto = cpu_to_be16(~0); + } + } else { + key->basic.n_proto = 0; + mask->basic.n_proto = cpu_to_be16(0); + } } static void fl_set_key_flag(u32 flower_key, u32 flower_mask, @@ -514,54 +1171,720 @@ static void fl_set_key_flag(u32 flower_key, u32 flower_mask, } } -static int fl_set_key_flags(struct nlattr **tb, - u32 *flags_key, u32 *flags_mask) +static int fl_set_key_flags(struct nlattr *tca_opts, struct nlattr **tb, + bool encap, u32 *flags_key, u32 *flags_mask, + struct netlink_ext_ack *extack) { + int fl_key, fl_mask; u32 key, mask; + if (encap) { + fl_key = TCA_FLOWER_KEY_ENC_FLAGS; + fl_mask = TCA_FLOWER_KEY_ENC_FLAGS_MASK; + } else { + fl_key = TCA_FLOWER_KEY_FLAGS; + fl_mask = TCA_FLOWER_KEY_FLAGS_MASK; + } + /* mask is mandatory for flags */ - if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) + if (NL_REQ_ATTR_CHECK(extack, tca_opts, tb, fl_mask)) { + NL_SET_ERR_MSG(extack, "Missing flags mask"); return -EINVAL; + } - key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS])); - mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK])); + key = be32_to_cpu(nla_get_be32(tb[fl_key])); + mask = be32_to_cpu(nla_get_be32(tb[fl_mask])); *flags_key = 0; *flags_mask = 0; fl_set_key_flag(key, mask, flags_key, flags_mask, TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_IS_FRAGMENT); + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, + FLOW_DIS_FIRST_FRAG); + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, + FLOW_DIS_F_TUNNEL_CSUM); + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, + FLOW_DIS_F_TUNNEL_DONT_FRAGMENT); + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_OAM); + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, + FLOW_DIS_F_TUNNEL_CRIT_OPT); return 0; } -static void fl_set_key_ip(struct nlattr **tb, +static void fl_set_key_ip(struct nlattr **tb, bool encap, struct flow_dissector_key_ip *key, struct flow_dissector_key_ip *mask) { - fl_set_key_val(tb, &key->tos, TCA_FLOWER_KEY_IP_TOS, - &mask->tos, TCA_FLOWER_KEY_IP_TOS_MASK, - sizeof(key->tos)); + int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS; + int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL; + int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK; + int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK; + + fl_set_key_val(tb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos)); + fl_set_key_val(tb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl)); +} + +static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1]; + struct nlattr *class = NULL, *type = NULL, *data = NULL; + struct geneve_opt *opt; + int err, data_len = 0; + + if (option_len > sizeof(struct geneve_opt)) + data_len = option_len - sizeof(struct geneve_opt); + + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; + memset(opt, 0xff, option_len); + opt->length = data_len / 4; + opt->r1 = 0; + opt->r2 = 0; + opt->r3 = 0; + + /* If no mask has been prodived we assume an exact match. */ + if (!depth) + return sizeof(struct geneve_opt) + data_len; + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GENEVE) { + NL_SET_ERR_MSG(extack, "Non-geneve option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested_deprecated(tb, + TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX, + nla, geneve_opt_policy, extack); + if (err < 0) + return err; + + /* We are not allowed to omit any of CLASS, TYPE or DATA + * fields from the key. + */ + if (!option_len && + (!tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] || + !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] || + !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA])) { + NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data"); + return -EINVAL; + } + + /* Omitting any of CLASS, TYPE or DATA fields is allowed + * for the mask. + */ + if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]) { + int new_len = key->enc_opts.len; + + data = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]; + data_len = nla_len(data); + if (data_len < 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long"); + return -ERANGE; + } + if (data_len % 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long"); + return -ERANGE; + } + + new_len += sizeof(struct geneve_opt) + data_len; + BUILD_BUG_ON(FLOW_DIS_TUN_OPTS_MAX != IP_TUNNEL_OPTS_MAX); + if (new_len > FLOW_DIS_TUN_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -ERANGE; + } + opt->length = data_len / 4; + memcpy(opt->opt_data, nla_data(data), data_len); + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]) { + class = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]; + opt->opt_class = nla_get_be16(class); + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]) { + type = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]; + opt->type = nla_get_u8(type); + } + + return sizeof(struct geneve_opt) + data_len; +} + +static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1]; + struct vxlan_metadata *md; + int err; + + md = (struct vxlan_metadata *)&key->enc_opts.data[key->enc_opts.len]; + memset(md, 0xff, sizeof(*md)); + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_VXLAN) { + NL_SET_ERR_MSG(extack, "Non-vxlan option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX, nla, + vxlan_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) { + md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; + } + + return sizeof(*md); +} + +static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1]; + struct erspan_metadata *md; + int err; + + md = (struct erspan_metadata *)&key->enc_opts.data[key->enc_opts.len]; + md->version = 1; + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_ERSPAN) { + NL_SET_ERR_MSG(extack, "Non-erspan option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX, nla, + erspan_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]) + md->version = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]); + + if (md->version == 1) { + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index"); + return -EINVAL; + } + memset(&md->u.index, 0xff, sizeof(md->u.index)); + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { + nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]; + md->u.index = nla_get_be32(nla); + } + } else if (md->version == 2) { + if (!option_len && (!tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] || + !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID])) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid"); + return -EINVAL; + } + md->u.md2.dir = 1; + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]) { + nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]; + md->u.md2.dir = nla_get_u8(nla); + } + set_hwid(&md->u.md2, 0xff); + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]) { + nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]; + set_hwid(&md->u.md2, nla_get_u8(nla)); + } + } else { + NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect"); + return -EINVAL; + } + + return sizeof(*md); +} + +static int fl_set_gtp_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1]; + struct gtp_pdu_session_info *sinfo; + u8 len = key->enc_opts.len; + int err; + + sinfo = (struct gtp_pdu_session_info *)&key->enc_opts.data[len]; + memset(sinfo, 0xff, option_len); + + if (!depth) + return sizeof(*sinfo); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GTP) { + NL_SET_ERR_MSG_MOD(extack, "Non-gtp option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GTP_MAX, nla, + gtp_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && + (!tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] || + !tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI])) { + NL_SET_ERR_MSG_MOD(extack, + "Missing tunnel key gtp option pdu type or qfi"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE]) + sinfo->pdu_type = + nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE]); + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI]) + sinfo->qfi = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI]); + + return sizeof(*sinfo); +} + +static int fl_set_pfcp_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1]; + struct pfcp_metadata *md; + int err; + + md = (struct pfcp_metadata *)&key->enc_opts.data[key->enc_opts.len]; + memset(md, 0xff, sizeof(*md)); + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_PFCP) { + NL_SET_ERR_MSG_MOD(extack, "Non-pfcp option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX, nla, + pfcp_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing tunnel key pfcp option type"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) + md->type = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]); + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]) + md->seid = nla_get_be64(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]); + + return sizeof(*md); +} + +static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; + int err, option_len, key_depth, msk_depth = 0; + + err = nla_validate_nested_deprecated(tb[TCA_FLOWER_KEY_ENC_OPTS], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + + nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); + + if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + err = nla_validate_nested_deprecated(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); + msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); + if (!nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "Invalid nested attribute for masks"); + return -EINVAL; + } + } + + nla_for_each_attr(nla_opt_key, nla_enc_key, + nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) { + switch (nla_type(nla_opt_key)) { + case TCA_FLOWER_KEY_ENC_OPTS_GENEVE: + if (key->enc_opts.dst_opt_type && + key->enc_opts.dst_opt_type != + IP_TUNNEL_GENEVE_OPT_BIT) { + NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; + option_len = fl_set_geneve_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; + option_len = fl_set_geneve_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); + return -EINVAL; + } + break; + case TCA_FLOWER_KEY_ENC_OPTS_VXLAN: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; + option_len = fl_set_vxlan_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; + option_len = fl_set_vxlan_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); + return -EINVAL; + } + break; + case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG(extack, "Duplicate type for erspan options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; + option_len = fl_set_erspan_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; + option_len = fl_set_erspan_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); + return -EINVAL; + } + break; + case TCA_FLOWER_KEY_ENC_OPTS_GTP: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG_MOD(extack, + "Duplicate type for gtp options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; + option_len = fl_set_gtp_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; + option_len = fl_set_gtp_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG_MOD(extack, + "Key and mask miss aligned"); + return -EINVAL; + } + break; + case TCA_FLOWER_KEY_ENC_OPTS_PFCP: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG_MOD(extack, "Duplicate type for pfcp options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG_MOD(extack, "Key and mask miss aligned"); + return -EINVAL; + } + break; + default: + NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); + return -EINVAL; + } + + if (!msk_depth) + continue; + + if (!nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "A mask attribute is invalid"); + return -EINVAL; + } + nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + } + + return 0; +} + +static int fl_validate_ct_state(u16 state, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + if (state && !(state & TCA_FLOWER_KEY_CT_FLAGS_TRACKED)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "no trk, so no other flag can be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and est are mutually exclusive"); + return -EINVAL; + } - fl_set_key_val(tb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, - &mask->ttl, TCA_FLOWER_KEY_IP_TTL_MASK, - sizeof(key->ttl)); + if (state & TCA_FLOWER_KEY_CT_FLAGS_INVALID && + state & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "when inv is set, only trk may be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_REPLY) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and rpl are mutually exclusive"); + return -EINVAL; + } + + return 0; } -static int fl_set_key(struct net *net, struct nlattr **tb, - struct fl_flow_key *key, struct fl_flow_key *mask) +static int fl_set_key_ct(struct nlattr **tb, + struct flow_dissector_key_ct *key, + struct flow_dissector_key_ct *mask, + struct netlink_ext_ack *extack) +{ + if (tb[TCA_FLOWER_KEY_CT_STATE]) { + int err; + + if (!IS_ENABLED(CONFIG_NF_CONNTRACK)) { + NL_SET_ERR_MSG(extack, "Conntrack isn't enabled"); + return -EOPNOTSUPP; + } + fl_set_key_val(tb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE, + &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK, + sizeof(key->ct_state)); + + err = fl_validate_ct_state(key->ct_state & mask->ct_state, + tb[TCA_FLOWER_KEY_CT_STATE_MASK], + extack); + if (err) + return err; + + } + if (tb[TCA_FLOWER_KEY_CT_ZONE]) { + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) { + NL_SET_ERR_MSG(extack, "Conntrack zones isn't enabled"); + return -EOPNOTSUPP; + } + fl_set_key_val(tb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE, + &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK, + sizeof(key->ct_zone)); + } + if (tb[TCA_FLOWER_KEY_CT_MARK]) { + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) { + NL_SET_ERR_MSG(extack, "Conntrack mark isn't enabled"); + return -EOPNOTSUPP; + } + fl_set_key_val(tb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK, + &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK, + sizeof(key->ct_mark)); + } + if (tb[TCA_FLOWER_KEY_CT_LABELS]) { + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) { + NL_SET_ERR_MSG(extack, "Conntrack labels aren't enabled"); + return -EOPNOTSUPP; + } + fl_set_key_val(tb, key->ct_labels, TCA_FLOWER_KEY_CT_LABELS, + mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK, + sizeof(key->ct_labels)); + } + + return 0; +} + +static bool is_vlan_key(struct nlattr *tb, __be16 *ethertype, + struct fl_flow_key *key, struct fl_flow_key *mask, + int vthresh) +{ + const bool good_num_of_vlans = key->num_of_vlans.num_of_vlans > vthresh; + + if (!tb) { + *ethertype = 0; + return good_num_of_vlans; + } + + *ethertype = nla_get_be16(tb); + if (good_num_of_vlans || eth_type_vlan(*ethertype)) + return true; + + key->basic.n_proto = *ethertype; + mask->basic.n_proto = cpu_to_be16(~0); + return false; +} + +static void fl_set_key_cfm_md_level(struct nlattr **tb, + struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + u8 level; + + if (!tb[TCA_FLOWER_KEY_CFM_MD_LEVEL]) + return; + + level = nla_get_u8(tb[TCA_FLOWER_KEY_CFM_MD_LEVEL]); + key->cfm.mdl_ver = FIELD_PREP(FLOW_DIS_CFM_MDL_MASK, level); + mask->cfm.mdl_ver = FLOW_DIS_CFM_MDL_MASK; +} + +static void fl_set_key_cfm_opcode(struct nlattr **tb, + struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + fl_set_key_val(tb, &key->cfm.opcode, TCA_FLOWER_KEY_CFM_OPCODE, + &mask->cfm.opcode, TCA_FLOWER_UNSPEC, + sizeof(key->cfm.opcode)); +} + +static int fl_set_key_cfm(struct nlattr **tb, + struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX + 1]; + int err; + + if (!tb[TCA_FLOWER_KEY_CFM]) + return 0; + + err = nla_parse_nested(nla_cfm_opt, TCA_FLOWER_KEY_CFM_OPT_MAX, + tb[TCA_FLOWER_KEY_CFM], cfm_opt_policy, extack); + if (err < 0) + return err; + + fl_set_key_cfm_opcode(nla_cfm_opt, key, mask, extack); + fl_set_key_cfm_md_level(nla_cfm_opt, key, mask, extack); + + return 0; +} + +static int fl_set_key(struct net *net, struct nlattr *tca_opts, + struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask, struct netlink_ext_ack *extack) { __be16 ethertype; int ret = 0; -#ifdef CONFIG_NET_CLS_IND + if (tb[TCA_FLOWER_INDEV]) { - int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]); + int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV], extack); if (err < 0) return err; - key->indev_ifindex = err; - mask->indev_ifindex = 0xffffffff; + key->meta.ingress_ifindex = err; + mask->meta.ingress_ifindex = 0xffffffff; } -#endif + + fl_set_key_val(tb, &key->meta.l2_miss, TCA_FLOWER_L2_MISS, + &mask->meta.l2_miss, TCA_FLOWER_UNSPEC, + sizeof(key->meta.l2_miss)); fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, @@ -569,28 +1892,42 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC, mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, sizeof(key->eth.src)); - - if (tb[TCA_FLOWER_KEY_ETH_TYPE]) { - ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]); - - if (ethertype == htons(ETH_P_8021Q)) { - fl_set_key_vlan(tb, &key->vlan, &mask->vlan); + fl_set_key_val(tb, &key->num_of_vlans, + TCA_FLOWER_KEY_NUM_OF_VLANS, + &mask->num_of_vlans, + TCA_FLOWER_UNSPEC, + sizeof(key->num_of_vlans)); + + if (is_vlan_key(tb[TCA_FLOWER_KEY_ETH_TYPE], ðertype, key, mask, 0)) { + fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, + TCA_FLOWER_KEY_VLAN_PRIO, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &key->vlan, &mask->vlan); + + if (is_vlan_key(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE], + ðertype, key, mask, 1)) { + fl_set_key_vlan(tb, ethertype, + TCA_FLOWER_KEY_CVLAN_ID, + TCA_FLOWER_KEY_CVLAN_PRIO, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, + &key->cvlan, &mask->cvlan); fl_set_key_val(tb, &key->basic.n_proto, - TCA_FLOWER_KEY_VLAN_ETH_TYPE, - &mask->basic.n_proto, TCA_FLOWER_UNSPEC, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, + &mask->basic.n_proto, + TCA_FLOWER_UNSPEC, sizeof(key->basic.n_proto)); - } else { - key->basic.n_proto = ethertype; - mask->basic.n_proto = cpu_to_be16(~0); } } + if (key->basic.n_proto == htons(ETH_P_PPP_SES)) + fl_set_key_pppoe(tb, &key->pppoe, &mask->pppoe, key, mask); + if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)); - fl_set_key_ip(tb, &key->ip, &mask->ip); + fl_set_key_ip(tb, false, &key->ip, &mask->ip); } if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) { @@ -659,7 +1996,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, sizeof(key->icmp.code)); } else if (key->basic.n_proto == htons(ETH_P_MPLS_UC) || key->basic.n_proto == htons(ETH_P_MPLS_MC)) { - ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls); + ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls, extack); if (ret) return ret; } else if (key->basic.n_proto == htons(ETH_P_ARP) || @@ -679,6 +2016,29 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA, mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK, sizeof(key->arp.tha)); + } else if (key->basic.ip_proto == IPPROTO_L2TP) { + fl_set_key_val(tb, &key->l2tpv3.session_id, + TCA_FLOWER_KEY_L2TPV3_SID, + &mask->l2tpv3.session_id, TCA_FLOWER_UNSPEC, + sizeof(key->l2tpv3.session_id)); + } else if (key->basic.n_proto == htons(ETH_P_CFM)) { + ret = fl_set_key_cfm(tb, key, mask, extack); + if (ret) + return ret; + } + + if (key->basic.ip_proto == IPPROTO_TCP || + key->basic.ip_proto == IPPROTO_UDP || + key->basic.ip_proto == IPPROTO_SCTP) { + ret = fl_set_key_port_range(tb, key, mask, extack); + if (ret) + return ret; + } + + if (tb[TCA_FLOWER_KEY_SPI]) { + ret = fl_set_key_spi(tb, key, mask, extack); + if (ret) + return ret; } if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || @@ -725,20 +2085,46 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, sizeof(key->enc_tp.dst)); - if (tb[TCA_FLOWER_KEY_FLAGS]) - ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags); + fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip); + + fl_set_key_val(tb, &key->hash.hash, TCA_FLOWER_KEY_HASH, + &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK, + sizeof(key->hash.hash)); + + if (tb[TCA_FLOWER_KEY_ENC_OPTS]) { + ret = fl_set_enc_opt(tb, key, mask, extack); + if (ret) + return ret; + } + + ret = fl_set_key_ct(tb, &key->ct, &mask->ct, extack); + if (ret) + return ret; + + if (tb[TCA_FLOWER_KEY_FLAGS]) { + ret = fl_set_key_flags(tca_opts, tb, false, + &key->control.flags, + &mask->control.flags, extack); + if (ret) + return ret; + } + + if (tb[TCA_FLOWER_KEY_ENC_FLAGS]) + ret = fl_set_key_flags(tca_opts, tb, true, + &key->enc_control.flags, + &mask->enc_control.flags, extack); return ret; } -static bool fl_mask_eq(struct fl_flow_mask *mask1, - struct fl_flow_mask *mask2) +static void fl_mask_copy(struct fl_flow_mask *dst, + struct fl_flow_mask *src) { - const long *lmask1 = fl_key_get_start(&mask1->key, mask1); - const long *lmask2 = fl_key_get_start(&mask2->key, mask2); + const void *psrc = fl_key_get_start(&src->key, src); + void *pdst = fl_key_get_start(&dst->key, src); - return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) && - !memcmp(lmask1, lmask2, fl_mask_range(mask1)); + memcpy(pdst, psrc, fl_mask_range(src)); + dst->range = src->range; } static const struct rhashtable_params fl_ht_params = { @@ -747,18 +2133,17 @@ static const struct rhashtable_params fl_ht_params = { .automatic_shrinking = true, }; -static int fl_init_hashtable(struct cls_fl_head *head, - struct fl_flow_mask *mask) +static int fl_init_mask_hashtable(struct fl_flow_mask *mask) { - head->ht_params = fl_ht_params; - head->ht_params.key_len = fl_mask_range(mask); - head->ht_params.key_offset += mask->range.start; + mask->filter_ht_params = fl_ht_params; + mask->filter_ht_params.key_len = fl_mask_range(mask); + mask->filter_ht_params.key_offset += mask->range.start; - return rhashtable_init(&head->ht, &head->ht_params); + return rhashtable_init(&mask->ht, &mask->filter_ht_params); } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member)) +#define FL_KEY_MEMBER_SIZE(member) sizeof_field(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ @@ -777,153 +2162,234 @@ static int fl_init_hashtable(struct cls_fl_head *head, FL_KEY_SET(keys, cnt, id, member); \ } while(0); -static void fl_init_dissector(struct cls_fl_head *head, - struct fl_flow_mask *mask) +static void fl_init_dissector(struct flow_dissector *dissector, + struct fl_flow_key *mask) { struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX]; size_t cnt = 0; + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_META, meta); FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control); FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ETH_ADDRS, eth); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS_RANGE, tp_range); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IP, ip); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_TCP, tcp); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ICMP, icmp); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ARP, arp); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_MPLS, mpls); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_VLAN, vlan); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_CVLAN, cvlan); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, enc_ipv4); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6); - if (FL_KEY_IS_MASKED(&mask->key, enc_ipv4) || - FL_KEY_IS_MASKED(&mask->key, enc_ipv6)) + if (FL_KEY_IS_MASKED(mask, enc_ipv4) || + FL_KEY_IS_MASKED(mask, enc_ipv6) || + FL_KEY_IS_MASKED(mask, enc_control)) FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL, enc_control); - FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp); - - skb_flow_dissector_init(&head->dissector, keys, cnt); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_IP, enc_ip); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_CT, ct); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_HASH, hash); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_NUM_OF_VLANS, num_of_vlans); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PPPOE, pppoe); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_IPSEC, ipsec); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_CFM, cfm); + + skb_flow_dissector_init(dissector, keys, cnt); } -static int fl_check_assign_mask(struct cls_fl_head *head, - struct fl_flow_mask *mask) +static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, + struct fl_flow_mask *mask) { + struct fl_flow_mask *newmask; int err; - if (head->mask_assigned) { - if (!fl_mask_eq(&head->mask, mask)) - return -EINVAL; - else - return 0; - } + newmask = kzalloc(sizeof(*newmask), GFP_KERNEL); + if (!newmask) + return ERR_PTR(-ENOMEM); - /* Mask is not assigned yet. So assign it and init hashtable - * according to that. - */ - err = fl_init_hashtable(head, mask); + fl_mask_copy(newmask, mask); + + if ((newmask->key.tp_range.tp_min.dst && + newmask->key.tp_range.tp_max.dst) || + (newmask->key.tp_range.tp_min.src && + newmask->key.tp_range.tp_max.src)) + newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE; + + err = fl_init_mask_hashtable(newmask); if (err) - return err; - memcpy(&head->mask, mask, sizeof(head->mask)); - head->mask_assigned = true; + goto errout_free; - fl_init_dissector(head, mask); + fl_init_dissector(&newmask->dissector, &newmask->key); - return 0; + INIT_LIST_HEAD_RCU(&newmask->filters); + + refcount_set(&newmask->refcnt, 1); + err = rhashtable_replace_fast(&head->ht, &mask->ht_node, + &newmask->ht_node, mask_ht_params); + if (err) + goto errout_destroy; + + spin_lock(&head->masks_lock); + list_add_tail_rcu(&newmask->list, &head->masks); + spin_unlock(&head->masks_lock); + + return newmask; + +errout_destroy: + rhashtable_destroy(&newmask->ht); +errout_free: + kfree(newmask); + + return ERR_PTR(err); } -static int fl_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_fl_filter *f, struct fl_flow_mask *mask, - unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) +static int fl_check_assign_mask(struct cls_fl_head *head, + struct cls_fl_filter *fnew, + struct cls_fl_filter *fold, + struct fl_flow_mask *mask) { - struct tcf_exts e; - int err; - - err = tcf_exts_init(&e, TCA_FLOWER_ACT, 0); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; + struct fl_flow_mask *newmask; + int ret = 0; - if (tb[TCA_FLOWER_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); - tcf_bind_filter(tp, &f->res, base); - } + rcu_read_lock(); - err = fl_set_key(net, tb, &f->key, &mask->key); - if (err) - goto errout; + /* Insert mask as temporary node to prevent concurrent creation of mask + * with same key. Any concurrent lookups with same key will return + * -EAGAIN because mask's refcnt is zero. + */ + fnew->mask = rhashtable_lookup_get_insert_fast(&head->ht, + &mask->ht_node, + mask_ht_params); + if (!fnew->mask) { + rcu_read_unlock(); + + if (fold) { + ret = -EINVAL; + goto errout_cleanup; + } - fl_mask_update_range(mask); - fl_set_masked_key(&f->mkey, &f->key, mask); + newmask = fl_create_new_mask(head, mask); + if (IS_ERR(newmask)) { + ret = PTR_ERR(newmask); + goto errout_cleanup; + } - tcf_exts_change(tp, &f->exts, &e); + fnew->mask = newmask; + return 0; + } else if (IS_ERR(fnew->mask)) { + ret = PTR_ERR(fnew->mask); + } else if (fold && fold->mask != fnew->mask) { + ret = -EINVAL; + } else if (!refcount_inc_not_zero(&fnew->mask->refcnt)) { + /* Mask was deleted concurrently, try again */ + ret = -EAGAIN; + } + rcu_read_unlock(); + return ret; - return 0; -errout: - tcf_exts_destroy(&e); - return err; +errout_cleanup: + rhashtable_remove_fast(&head->ht, &mask->ht_node, + mask_ht_params); + return ret; } -static u32 fl_grab_new_handle(struct tcf_proto *tp, - struct cls_fl_head *head) +static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask) { - unsigned int i = 0x80000000; - u32 handle; + return mask->meta.l2_miss; +} - do { - if (++head->hgen == 0x7FFFFFFF) - head->hgen = 1; - } while (--i > 0 && fl_get(tp, head->hgen)); +static int fl_ht_insert_unique(struct cls_fl_filter *fnew, + struct cls_fl_filter *fold, + bool *in_ht) +{ + struct fl_flow_mask *mask = fnew->mask; + int err; - if (unlikely(i == 0)) { - pr_err("Insufficient number of handles\n"); - handle = 0; - } else { - handle = head->hgen; + err = rhashtable_lookup_insert_fast(&mask->ht, + &fnew->ht_node, + mask->filter_ht_params); + if (err) { + *in_ht = false; + /* It is okay if filter with same key exists when + * overwriting. + */ + return fold && err == -EEXIST ? 0 : err; } - return handle; + *in_ht = true; + return 0; } static int fl_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, u32 flags, + struct netlink_ext_ack *extack) { - struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *fold = (struct cls_fl_filter *) *arg; + struct cls_fl_head *head = fl_head_dereference(tp); + bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); + struct nlattr *tca_opts = tca[TCA_OPTIONS]; + struct cls_fl_filter *fold = *arg; + bool bound_to_filter = false; struct cls_fl_filter *fnew; + struct fl_flow_mask *mask; struct nlattr **tb; - struct fl_flow_mask mask = {}; + bool in_ht; int err; - if (!tca[TCA_OPTIONS]) - return -EINVAL; + if (!tca_opts) { + err = -EINVAL; + goto errout_fold; + } + + mask = kzalloc(sizeof(struct fl_flow_mask), GFP_KERNEL); + if (!mask) { + err = -ENOBUFS; + goto errout_fold; + } tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); - if (!tb) - return -ENOBUFS; + if (!tb) { + err = -ENOBUFS; + goto errout_mask_alloc; + } - err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], - fl_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX, + tca_opts, fl_policy, NULL); if (err < 0) goto errout_tb; @@ -937,118 +2403,481 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, err = -ENOBUFS; goto errout_tb; } + INIT_LIST_HEAD(&fnew->hw_list); + refcount_set(&fnew->refcnt, 1); - err = tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0); - if (err < 0) - goto errout; + if (tb[TCA_FLOWER_FLAGS]) { + fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); - if (!handle) { - handle = fl_grab_new_handle(tp, head); - if (!handle) { + if (!tc_flags_valid(fnew->flags)) { + kfree(fnew); err = -EINVAL; - goto errout; + goto errout_tb; } } - fnew->handle = handle; - if (tb[TCA_FLOWER_FLAGS]) { - fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); + if (!fold) { + spin_lock(&tp->lock); + if (!handle) { + handle = 1; + err = idr_alloc_u32(&head->handle_idr, NULL, &handle, + INT_MAX, GFP_ATOMIC); + } else { + err = idr_alloc_u32(&head->handle_idr, NULL, &handle, + handle, GFP_ATOMIC); + + /* Filter with specified handle was concurrently + * inserted after initial check in cls_api. This is not + * necessarily an error if NLM_F_EXCL is not set in + * message flags. Returning EAGAIN will cause cls_api to + * try to update concurrently inserted rule. + */ + if (err == -ENOSPC) + err = -EAGAIN; + } + spin_unlock(&tp->lock); - if (!tc_flags_valid(fnew->flags)) { - err = -EINVAL; - goto errout; + if (err) { + kfree(fnew); + goto errout_tb; } } + fnew->handle = handle; - err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); - if (err) - goto errout; + err = tcf_exts_init_ex(&fnew->exts, net, TCA_FLOWER_ACT, 0, tp, handle, + !tc_skip_hw(fnew->flags)); + if (err < 0) + goto errout_idr; + + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &fnew->exts, flags, fnew->flags, + extack); + if (err < 0) + goto errout_idr; - err = fl_check_assign_mask(head, &mask); + if (tb[TCA_FLOWER_CLASSID]) { + fnew->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_bind_filter(tp, &fnew->res, base); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + bound_to_filter = true; + } + + err = fl_set_key(net, tca_opts, tb, &fnew->key, &mask->key, extack); if (err) - goto errout; + goto unbind_filter; - if (!tc_skip_sw(fnew->flags)) { - if (!fold && fl_lookup(head, &fnew->mkey)) { - err = -EEXIST; - goto errout; - } + fl_mask_update_range(mask); + fl_set_masked_key(&fnew->mkey, &fnew->key, mask); - err = rhashtable_insert_fast(&head->ht, &fnew->ht_node, - head->ht_params); - if (err) - goto errout; + if (!fl_mask_fits_tmplt(tp->chain->tmplt_priv, mask)) { + NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); + err = -EINVAL; + goto unbind_filter; } + /* Enable tc skb extension if filter matches on data extracted from + * this extension. + */ + if (fl_needs_tc_skb_ext(&mask->key)) { + fnew->needs_tc_skb_ext = 1; + tc_skb_ext_tc_enable(); + } + + err = fl_check_assign_mask(head, fnew, fold, mask); + if (err) + goto unbind_filter; + + err = fl_ht_insert_unique(fnew, fold, &in_ht); + if (err) + goto errout_mask; + if (!tc_skip_hw(fnew->flags)) { - err = fl_hw_replace_filter(tp, - &head->dissector, - &mask.key, - fnew); + err = fl_hw_replace_filter(tp, fnew, rtnl_held, extack); if (err) - goto errout; + goto errout_ht; } if (!tc_in_hw(fnew->flags)) fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW; - if (fold) { - if (!tc_skip_sw(fold->flags)) - rhashtable_remove_fast(&head->ht, &fold->ht_node, - head->ht_params); - if (!tc_skip_hw(fold->flags)) - fl_hw_destroy_filter(tp, fold); - } + tcf_proto_update_usesw(tp, fnew->flags); - *arg = (unsigned long) fnew; + spin_lock(&tp->lock); + + /* tp was deleted concurrently. -EAGAIN will cause caller to lookup + * proto again or create new one, if necessary. + */ + if (tp->deleting) { + err = -EAGAIN; + goto errout_hw; + } if (fold) { + /* Fold filter was deleted concurrently. Retry lookup. */ + if (fold->deleted) { + err = -EAGAIN; + goto errout_hw; + } + + fnew->handle = handle; + + if (!in_ht) { + struct rhashtable_params params = + fnew->mask->filter_ht_params; + + err = rhashtable_insert_fast(&fnew->mask->ht, + &fnew->ht_node, + params); + if (err) + goto errout_hw; + in_ht = true; + } + + refcount_inc(&fnew->refcnt); + rhashtable_remove_fast(&fold->mask->ht, + &fold->ht_node, + fold->mask->filter_ht_params); + idr_replace(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->list, &fnew->list); + fold->deleted = true; + + spin_unlock(&tp->lock); + + fl_mask_put(head, fold->mask); + if (!tc_skip_hw(fold->flags)) + fl_hw_destroy_filter(tp, fold, rtnl_held, NULL); tcf_unbind_filter(tp, &fold->res); - call_rcu(&fold->rcu, fl_destroy_filter); + /* Caller holds reference to fold, so refcnt is always > 0 + * after this. + */ + refcount_dec(&fold->refcnt); + __fl_put(fold); } else { - list_add_tail_rcu(&fnew->list, &head->filters); + idr_replace(&head->handle_idr, fnew, fnew->handle); + + refcount_inc(&fnew->refcnt); + list_add_tail_rcu(&fnew->list, &fnew->mask->filters); + spin_unlock(&tp->lock); } + *arg = fnew; + kfree(tb); + tcf_queue_work(&mask->rwork, fl_uninit_mask_free_work); return 0; -errout: - tcf_exts_destroy(&fnew->exts); - kfree(fnew); +errout_ht: + spin_lock(&tp->lock); +errout_hw: + fnew->deleted = true; + spin_unlock(&tp->lock); + if (!tc_skip_hw(fnew->flags)) + fl_hw_destroy_filter(tp, fnew, rtnl_held, NULL); + if (in_ht) + rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); +errout_mask: + fl_mask_put(head, fnew->mask); + +unbind_filter: + if (bound_to_filter) { + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_unbind_filter(tp, &fnew->res); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + } + +errout_idr: + if (!fold) { + spin_lock(&tp->lock); + idr_remove(&head->handle_idr, fnew->handle); + spin_unlock(&tp->lock); + } + __fl_put(fnew); errout_tb: kfree(tb); +errout_mask_alloc: + tcf_queue_work(&mask->rwork, fl_uninit_mask_free_work); +errout_fold: + if (fold) + __fl_put(fold); return err; } -static int fl_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { - struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *f = (struct cls_fl_filter *) arg; + struct cls_fl_head *head = fl_head_dereference(tp); + struct cls_fl_filter *f = arg; + bool last_on_mask; + int err = 0; - if (!tc_skip_sw(f->flags)) - rhashtable_remove_fast(&head->ht, &f->ht_node, - head->ht_params); - __fl_delete(tp, f); - *last = list_empty(&head->filters); - return 0; + err = __fl_delete(tp, f, &last_on_mask, rtnl_held, extack); + *last = list_empty(&head->masks); + __fl_put(f); + + return err; } -static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { - struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_head *head = fl_head_dereference(tp); + unsigned long id = arg->cookie, tmp; struct cls_fl_filter *f; - list_for_each_entry_rcu(f, &head->filters, list) { - if (arg->count < arg->skip) - goto skip; - if (arg->fn(tp, (unsigned long) f, arg) < 0) { + arg->count = arg->skip; + + rcu_read_lock(); + idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) { + /* don't return filters that are being deleted */ + if (!f || !refcount_inc_not_zero(&f->refcnt)) + continue; + rcu_read_unlock(); + + if (arg->fn(tp, f, arg) < 0) { + __fl_put(f); arg->stop = 1; + rcu_read_lock(); break; } -skip: + __fl_put(f); arg->count++; + rcu_read_lock(); + } + rcu_read_unlock(); + arg->cookie = id; +} + +static struct cls_fl_filter * +fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + if (list_empty(&head->hw_filters)) { + spin_unlock(&tp->lock); + return NULL; + } + + if (!f) + f = list_entry(&head->hw_filters, struct cls_fl_filter, + hw_list); + list_for_each_entry_continue(f, &head->hw_filters, hw_list) { + if (!(add && f->deleted) && refcount_inc_not_zero(&f->refcnt)) { + spin_unlock(&tp->lock); + return f; + } + } + + spin_unlock(&tp->lock); + return NULL; +} + +static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct tcf_block *block = tp->chain->block; + struct flow_cls_offload cls_flower = {}; + struct cls_fl_filter *f = NULL; + int err; + + /* hw_filters list can only be changed by hw offload functions after + * obtaining rtnl lock. Make sure it is not changed while reoffload is + * iterating it. + */ + ASSERT_RTNL(); + + while ((f = fl_get_next_hw_filter(tp, f, add))) { + cls_flower.rule = + flow_rule_alloc(tcf_exts_num_actions(&f->exts)); + if (!cls_flower.rule) { + __fl_put(f); + return -ENOMEM; + } + + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, + extack); + cls_flower.command = add ? + FLOW_CLS_REPLACE : FLOW_CLS_DESTROY; + cls_flower.cookie = (unsigned long)f; + cls_flower.rule->match.dissector = &f->mask->dissector; + cls_flower.rule->match.mask = &f->mask->key; + cls_flower.rule->match.key = &f->mkey; + + err = tc_setup_offload_action(&cls_flower.rule->action, &f->exts, + cls_flower.common.extack); + if (err) { + kfree(cls_flower.rule); + if (tc_skip_sw(f->flags)) { + __fl_put(f); + return err; + } + goto next_flow; + } + + cls_flower.classid = f->res.classid; + + err = tc_setup_cb_reoffload(block, tp, add, cb, + TC_SETUP_CLSFLOWER, &cls_flower, + cb_priv, &f->flags, + &f->in_hw_count); + tc_cleanup_offload_action(&cls_flower.rule->action); + kfree(cls_flower.rule); + + if (err) { + __fl_put(f); + return err; + } +next_flow: + __fl_put(f); + } + + return 0; +} + +static void fl_hw_add(struct tcf_proto *tp, void *type_data) +{ + struct flow_cls_offload *cls_flower = type_data; + struct cls_fl_filter *f = + (struct cls_fl_filter *) cls_flower->cookie; + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + list_add(&f->hw_list, &head->hw_filters); + spin_unlock(&tp->lock); +} + +static void fl_hw_del(struct tcf_proto *tp, void *type_data) +{ + struct flow_cls_offload *cls_flower = type_data; + struct cls_fl_filter *f = + (struct cls_fl_filter *) cls_flower->cookie; + + spin_lock(&tp->lock); + if (!list_empty(&f->hw_list)) + list_del_init(&f->hw_list); + spin_unlock(&tp->lock); +} + +static int fl_hw_create_tmplt(struct tcf_chain *chain, + struct fl_flow_tmplt *tmplt) +{ + struct flow_cls_offload cls_flower = {}; + struct tcf_block *block = chain->block; + + cls_flower.rule = flow_rule_alloc(0); + if (!cls_flower.rule) + return -ENOMEM; + + cls_flower.common.chain_index = chain->index; + cls_flower.command = FLOW_CLS_TMPLT_CREATE; + cls_flower.cookie = (unsigned long) tmplt; + cls_flower.rule->match.dissector = &tmplt->dissector; + cls_flower.rule->match.mask = &tmplt->mask; + cls_flower.rule->match.key = &tmplt->dummy_key; + + /* We don't care if driver (any of them) fails to handle this + * call. It serves just as a hint for it. + */ + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, true); + kfree(cls_flower.rule); + + return 0; +} + +static void fl_hw_destroy_tmplt(struct tcf_chain *chain, + struct fl_flow_tmplt *tmplt) +{ + struct flow_cls_offload cls_flower = {}; + struct tcf_block *block = chain->block; + + cls_flower.common.chain_index = chain->index; + cls_flower.command = FLOW_CLS_TMPLT_DESTROY; + cls_flower.cookie = (unsigned long) tmplt; + + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, true); +} + +static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, + struct nlattr **tca, + struct netlink_ext_ack *extack) +{ + struct nlattr *tca_opts = tca[TCA_OPTIONS]; + struct fl_flow_tmplt *tmplt; + struct nlattr **tb; + int err; + + if (!tca_opts) + return ERR_PTR(-EINVAL); + + tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); + if (!tb) + return ERR_PTR(-ENOBUFS); + err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX, + tca_opts, fl_policy, NULL); + if (err) + goto errout_tb; + + tmplt = kzalloc(sizeof(*tmplt), GFP_KERNEL); + if (!tmplt) { + err = -ENOMEM; + goto errout_tb; } + tmplt->chain = chain; + err = fl_set_key(net, tca_opts, tb, &tmplt->dummy_key, + &tmplt->mask, extack); + if (err) + goto errout_tmplt; + + fl_init_dissector(&tmplt->dissector, &tmplt->mask); + + err = fl_hw_create_tmplt(chain, tmplt); + if (err) + goto errout_tmplt; + + kfree(tb); + return tmplt; + +errout_tmplt: + kfree(tmplt); +errout_tb: + kfree(tb); + return ERR_PTR(err); +} + +static void fl_tmplt_destroy(void *tmplt_priv) +{ + struct fl_flow_tmplt *tmplt = tmplt_priv; + + fl_hw_destroy_tmplt(tmplt->chain, tmplt); + kfree(tmplt); +} + +static void fl_tmplt_reoffload(struct tcf_chain *chain, bool add, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct fl_flow_tmplt *tmplt = chain->tmplt_priv; + struct flow_cls_offload cls_flower = {}; + + cls_flower.rule = flow_rule_alloc(0); + if (!cls_flower.rule) + return; + + cls_flower.common.chain_index = chain->index; + cls_flower.command = add ? FLOW_CLS_TMPLT_CREATE : + FLOW_CLS_TMPLT_DESTROY; + cls_flower.cookie = (unsigned long) tmplt; + cls_flower.rule->match.dissector = &tmplt->dissector; + cls_flower.rule->match.mask = &tmplt->mask; + cls_flower.rule->match.key = &tmplt->dummy_key; + + cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + kfree(cls_flower.rule); } static int fl_dump_key_val(struct sk_buff *skb, @@ -1070,55 +2899,180 @@ static int fl_dump_key_val(struct sk_buff *skb, return 0; } +static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, + struct fl_flow_key *mask) +{ + if (fl_dump_key_val(skb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, + &mask->tp_range.tp_min.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, + &mask->tp_range.tp_max.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, + &mask->tp_range.tp_min.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.src)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, + &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.src))) + return -1; + + return 0; +} + +static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb, + struct flow_dissector_key_mpls *mpls_key, + struct flow_dissector_key_mpls *mpls_mask, + u8 lse_index) +{ + struct flow_dissector_mpls_lse *lse_mask = &mpls_mask->ls[lse_index]; + struct flow_dissector_mpls_lse *lse_key = &mpls_key->ls[lse_index]; + int err; + + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH, + lse_index + 1); + if (err) + return err; + + if (lse_mask->mpls_ttl) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL, + lse_key->mpls_ttl); + if (err) + return err; + } + if (lse_mask->mpls_bos) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS, + lse_key->mpls_bos); + if (err) + return err; + } + if (lse_mask->mpls_tc) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_TC, + lse_key->mpls_tc); + if (err) + return err; + } + if (lse_mask->mpls_label) { + err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, + lse_key->mpls_label); + if (err) + return err; + } + + return 0; +} + +static int fl_dump_key_mpls_opts(struct sk_buff *skb, + struct flow_dissector_key_mpls *mpls_key, + struct flow_dissector_key_mpls *mpls_mask) +{ + struct nlattr *opts; + struct nlattr *lse; + u8 lse_index; + int err; + + opts = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS); + if (!opts) + return -EMSGSIZE; + + for (lse_index = 0; lse_index < FLOW_DIS_MPLS_MAX; lse_index++) { + if (!(mpls_mask->used_lses & 1 << lse_index)) + continue; + + lse = nla_nest_start(skb, TCA_FLOWER_KEY_MPLS_OPTS_LSE); + if (!lse) { + err = -EMSGSIZE; + goto err_opts; + } + + err = fl_dump_key_mpls_opt_lse(skb, mpls_key, mpls_mask, + lse_index); + if (err) + goto err_opts_lse; + nla_nest_end(skb, lse); + } + nla_nest_end(skb, opts); + + return 0; + +err_opts_lse: + nla_nest_cancel(skb, lse); +err_opts: + nla_nest_cancel(skb, opts); + + return err; +} + static int fl_dump_key_mpls(struct sk_buff *skb, struct flow_dissector_key_mpls *mpls_key, struct flow_dissector_key_mpls *mpls_mask) { + struct flow_dissector_mpls_lse *lse_mask; + struct flow_dissector_mpls_lse *lse_key; int err; - if (!memchr_inv(mpls_mask, 0, sizeof(*mpls_mask))) + if (!mpls_mask->used_lses) return 0; - if (mpls_mask->mpls_ttl) { + + lse_mask = &mpls_mask->ls[0]; + lse_key = &mpls_key->ls[0]; + + /* For backward compatibility, don't use the MPLS nested attributes if + * the rule can be expressed using the old attributes. + */ + if (mpls_mask->used_lses & ~1 || + (!lse_mask->mpls_ttl && !lse_mask->mpls_bos && + !lse_mask->mpls_tc && !lse_mask->mpls_label)) + return fl_dump_key_mpls_opts(skb, mpls_key, mpls_mask); + + if (lse_mask->mpls_ttl) { err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TTL, - mpls_key->mpls_ttl); + lse_key->mpls_ttl); if (err) return err; } - if (mpls_mask->mpls_tc) { + if (lse_mask->mpls_tc) { err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TC, - mpls_key->mpls_tc); + lse_key->mpls_tc); if (err) return err; } - if (mpls_mask->mpls_label) { + if (lse_mask->mpls_label) { err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_LABEL, - mpls_key->mpls_label); + lse_key->mpls_label); if (err) return err; } - if (mpls_mask->mpls_bos) { + if (lse_mask->mpls_bos) { err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_BOS, - mpls_key->mpls_bos); + lse_key->mpls_bos); if (err) return err; } return 0; } -static int fl_dump_key_ip(struct sk_buff *skb, +static int fl_dump_key_ip(struct sk_buff *skb, bool encap, struct flow_dissector_key_ip *key, struct flow_dissector_key_ip *mask) { - if (fl_dump_key_val(skb, &key->tos, TCA_FLOWER_KEY_IP_TOS, &mask->tos, - TCA_FLOWER_KEY_IP_TOS_MASK, sizeof(key->tos)) || - fl_dump_key_val(skb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, &mask->ttl, - TCA_FLOWER_KEY_IP_TTL_MASK, sizeof(key->ttl))) + int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS; + int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL; + int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK; + int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK; + + if (fl_dump_key_val(skb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos)) || + fl_dump_key_val(skb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl))) return -1; return 0; } static int fl_dump_key_vlan(struct sk_buff *skb, + int vlan_id_key, int vlan_prio_key, struct flow_dissector_key_vlan *vlan_key, struct flow_dissector_key_vlan *vlan_mask) { @@ -1127,13 +3081,13 @@ static int fl_dump_key_vlan(struct sk_buff *skb, if (!memchr_inv(vlan_mask, 0, sizeof(*vlan_mask))) return 0; if (vlan_mask->vlan_id) { - err = nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ID, + err = nla_put_u16(skb, vlan_id_key, vlan_key->vlan_id); if (err) return err; } if (vlan_mask->vlan_priority) { - err = nla_put_u8(skb, TCA_FLOWER_KEY_VLAN_PRIO, + err = nla_put_u8(skb, vlan_prio_key, vlan_key->vlan_priority); if (err) return err; @@ -1152,12 +3106,22 @@ static void fl_get_key_flag(u32 dissector_key, u32 dissector_mask, } } -static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) +static int fl_dump_key_flags(struct sk_buff *skb, bool encap, + u32 flags_key, u32 flags_mask) { - u32 key, mask; + int fl_key, fl_mask; __be32 _key, _mask; + u32 key, mask; int err; + if (encap) { + fl_key = TCA_FLOWER_KEY_ENC_FLAGS; + fl_mask = TCA_FLOWER_KEY_ENC_FLAGS_MASK; + } else { + fl_key = TCA_FLOWER_KEY_FLAGS; + fl_mask = TCA_FLOWER_KEY_FLAGS_MASK; + } + if (!memchr_inv(&flags_mask, 0, sizeof(flags_mask))) return 0; @@ -1166,51 +3130,327 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) fl_get_key_flag(flags_key, flags_mask, &key, &mask, TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_IS_FRAGMENT); + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, + FLOW_DIS_FIRST_FRAG); + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, + FLOW_DIS_F_TUNNEL_CSUM); + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, + FLOW_DIS_F_TUNNEL_DONT_FRAGMENT); + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_OAM); + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, + FLOW_DIS_F_TUNNEL_CRIT_OPT); _key = cpu_to_be32(key); _mask = cpu_to_be32(mask); - err = nla_put(skb, TCA_FLOWER_KEY_FLAGS, 4, &_key); + err = nla_put(skb, fl_key, 4, &_key); if (err) return err; - return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask); + return nla_put(skb, fl_mask, 4, &_mask); } -static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static int fl_dump_key_geneve_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) { - struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *f = (struct cls_fl_filter *) fh; + struct geneve_opt *opt; struct nlattr *nest; - struct fl_flow_key *key, *mask; + int opt_off = 0; - if (!f) - return skb->len; + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE); + if (!nest) + goto nla_put_failure; - t->tcm_handle = f->handle; + while (enc_opts->len > opt_off) { + opt = (struct geneve_opt *)&enc_opts->data[opt_off]; + + if (nla_put_be16(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, + opt->opt_class)) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, + opt->type)) + goto nla_put_failure; + if (nla_put(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, + opt->length * 4, opt->opt_data)) + goto nla_put_failure; + + opt_off += sizeof(struct geneve_opt) + opt->length * 4; + } + nla_nest_end(skb, nest); + return 0; - nest = nla_nest_start(skb, TCA_OPTIONS); +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_vxlan_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct vxlan_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_VXLAN); if (!nest) goto nla_put_failure; - if (f->res.classid && - nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid)) + md = (struct vxlan_metadata *)&enc_opts->data[0]; + if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) goto nla_put_failure; - key = &f->key; - mask = &head->mask.key; + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_erspan_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct erspan_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_ERSPAN); + if (!nest) + goto nla_put_failure; + + md = (struct erspan_metadata *)&enc_opts->data[0]; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER, md->version)) + goto nla_put_failure; + + if (md->version == 1 && + nla_put_be32(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index)) + goto nla_put_failure; + + if (md->version == 2 && + (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR, + md->u.md2.dir) || + nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID, + get_hwid(&md->u.md2)))) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_gtp_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) + +{ + struct gtp_pdu_session_info *session_info; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GTP); + if (!nest) + goto nla_put_failure; + + session_info = (struct gtp_pdu_session_info *)&enc_opts->data[0]; + + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE, + session_info->pdu_type)) + goto nla_put_failure; + + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_QFI, session_info->qfi)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_pfcp_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct pfcp_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_PFCP); + if (!nest) + goto nla_put_failure; + + md = (struct pfcp_metadata *)&enc_opts->data[0]; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, md->type)) + goto nla_put_failure; + + if (nla_put_be64(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, + md->seid, 0)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_ct(struct sk_buff *skb, + struct flow_dissector_key_ct *key, + struct flow_dissector_key_ct *mask) +{ + if (IS_ENABLED(CONFIG_NF_CONNTRACK) && + fl_dump_key_val(skb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE, + &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK, + sizeof(key->ct_state))) + goto nla_put_failure; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && + fl_dump_key_val(skb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE, + &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK, + sizeof(key->ct_zone))) + goto nla_put_failure; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + fl_dump_key_val(skb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK, + &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK, + sizeof(key->ct_mark))) + goto nla_put_failure; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + fl_dump_key_val(skb, &key->ct_labels, TCA_FLOWER_KEY_CT_LABELS, + &mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK, + sizeof(key->ct_labels))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int fl_dump_key_cfm(struct sk_buff *skb, + struct flow_dissector_key_cfm *key, + struct flow_dissector_key_cfm *mask) +{ + struct nlattr *opts; + int err; + u8 mdl; + + if (!memchr_inv(mask, 0, sizeof(*mask))) + return 0; + + opts = nla_nest_start(skb, TCA_FLOWER_KEY_CFM); + if (!opts) + return -EMSGSIZE; + + if (FIELD_GET(FLOW_DIS_CFM_MDL_MASK, mask->mdl_ver)) { + mdl = FIELD_GET(FLOW_DIS_CFM_MDL_MASK, key->mdl_ver); + err = nla_put_u8(skb, TCA_FLOWER_KEY_CFM_MD_LEVEL, mdl); + if (err) + goto err_cfm_opts; + } + + if (mask->opcode) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_CFM_OPCODE, key->opcode); + if (err) + goto err_cfm_opts; + } + + nla_nest_end(skb, opts); + + return 0; + +err_cfm_opts: + nla_nest_cancel(skb, opts); + return err; +} + +static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct nlattr *nest; + int err; + + if (!enc_opts->len) + return 0; + + nest = nla_nest_start_noflag(skb, enc_opt_type); + if (!nest) + goto nla_put_failure; + + switch (enc_opts->dst_opt_type) { + case IP_TUNNEL_GENEVE_OPT_BIT: + err = fl_dump_key_geneve_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; + case IP_TUNNEL_VXLAN_OPT_BIT: + err = fl_dump_key_vxlan_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; + case IP_TUNNEL_ERSPAN_OPT_BIT: + err = fl_dump_key_erspan_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; + case IP_TUNNEL_GTP_OPT_BIT: + err = fl_dump_key_gtp_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; + case IP_TUNNEL_PFCP_OPT_BIT: + err = fl_dump_key_pfcp_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; + default: + goto nla_put_failure; + } + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_enc_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *key_opts, + struct flow_dissector_key_enc_opts *msk_opts) +{ + int err; + + err = fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS, key_opts); + if (err) + return err; - if (mask->indev_ifindex) { + return fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS_MASK, msk_opts); +} + +static int fl_dump_key(struct sk_buff *skb, struct net *net, + struct fl_flow_key *key, struct fl_flow_key *mask) +{ + if (mask->meta.ingress_ifindex) { struct net_device *dev; - dev = __dev_get_by_index(net, key->indev_ifindex); + dev = __dev_get_by_index(net, key->meta.ingress_ifindex); if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name)) goto nla_put_failure; } - if (!tc_skip_hw(f->flags)) - fl_hw_update_stats(tp, f); + if (fl_dump_key_val(skb, &key->meta.l2_miss, + TCA_FLOWER_L2_MISS, &mask->meta.l2_miss, + TCA_FLOWER_UNSPEC, sizeof(key->meta.l2_miss))) + goto nla_put_failure; if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, @@ -1223,20 +3463,57 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, sizeof(key->basic.n_proto))) goto nla_put_failure; + if (mask->num_of_vlans.num_of_vlans) { + if (nla_put_u8(skb, TCA_FLOWER_KEY_NUM_OF_VLANS, key->num_of_vlans.num_of_vlans)) + goto nla_put_failure; + } + if (fl_dump_key_mpls(skb, &key->mpls, &mask->mpls)) goto nla_put_failure; - if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan)) + if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_VLAN_ID, + TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, &mask->vlan)) goto nla_put_failure; + if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_CVLAN_ID, + TCA_FLOWER_KEY_CVLAN_PRIO, + &key->cvlan, &mask->cvlan) || + (mask->cvlan.vlan_tpid && + nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, + key->cvlan.vlan_tpid))) + goto nla_put_failure; + + if (mask->basic.n_proto) { + if (mask->cvlan.vlan_eth_type) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, + key->basic.n_proto)) + goto nla_put_failure; + } else if (mask->vlan.vlan_eth_type) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, + key->vlan.vlan_eth_type)) + goto nla_put_failure; + } + } + if ((key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) && (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)) || - fl_dump_key_ip(skb, &key->ip, &mask->ip))) + fl_dump_key_ip(skb, false, &key->ip, &mask->ip))) goto nla_put_failure; + if (mask->pppoe.session_id) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_PPPOE_SID, + key->pppoe.session_id)) + goto nla_put_failure; + } + if (mask->basic.n_proto && mask->pppoe.ppp_proto) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_PPP_PROTO, + key->pppoe.ppp_proto)) + goto nla_put_failure; + } + if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, @@ -1324,6 +3601,25 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK, sizeof(key->arp.tha)))) goto nla_put_failure; + else if (key->basic.ip_proto == IPPROTO_L2TP && + fl_dump_key_val(skb, &key->l2tpv3.session_id, + TCA_FLOWER_KEY_L2TPV3_SID, + &mask->l2tpv3.session_id, + TCA_FLOWER_UNSPEC, + sizeof(key->l2tpv3.session_id))) + goto nla_put_failure; + + if (key->ipsec.spi && + fl_dump_key_val(skb, &key->ipsec.spi, TCA_FLOWER_KEY_SPI, + &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK, + sizeof(key->ipsec.spi))) + goto nla_put_failure; + + if ((key->basic.ip_proto == IPPROTO_TCP || + key->basic.ip_proto == IPPROTO_UDP || + key->basic.ip_proto == IPPROTO_SCTP) && + fl_dump_key_port_range(skb, key, mask)) + goto nla_put_failure; if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->enc_ipv4.src, @@ -1359,13 +3655,75 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, TCA_FLOWER_KEY_ENC_UDP_DST_PORT, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, - sizeof(key->enc_tp.dst))) + sizeof(key->enc_tp.dst)) || + fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip) || + fl_dump_key_enc_opt(skb, &key->enc_opts, &mask->enc_opts)) + goto nla_put_failure; + + if (fl_dump_key_ct(skb, &key->ct, &mask->ct)) + goto nla_put_failure; + + if (fl_dump_key_flags(skb, false, key->control.flags, + mask->control.flags)) + goto nla_put_failure; + + if (fl_dump_key_val(skb, &key->hash.hash, TCA_FLOWER_KEY_HASH, + &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK, + sizeof(key->hash.hash))) + goto nla_put_failure; + + if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm)) goto nla_put_failure; - if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags)) + if (fl_dump_key_flags(skb, true, key->enc_control.flags, + mask->enc_control.flags)) goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) +{ + struct cls_fl_filter *f = fh; + struct nlattr *nest; + struct fl_flow_key *key, *mask; + bool skip_hw; + + if (!f) + return skb->len; + + t->tcm_handle = f->handle; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + spin_lock(&tp->lock); + + if (f->res.classid && + nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid)) + goto nla_put_failure_locked; + + key = &f->key; + mask = &f->mask->key; + skip_hw = tc_skip_hw(f->flags); + + if (fl_dump_key(skb, net, key, mask)) + goto nla_put_failure_locked; + if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) + goto nla_put_failure_locked; + + spin_unlock(&tp->lock); + + if (!skip_hw) + fl_hw_update_stats(tp, f, rtnl_held); + + if (nla_put_u32(skb, TCA_FLOWER_IN_HW_COUNT, f->in_hw_count)) goto nla_put_failure; if (tcf_exts_dump(skb, &f->exts)) @@ -1378,23 +3736,125 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, return skb->len; +nla_put_failure_locked: + spin_unlock(&tp->lock); +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static int fl_terse_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) +{ + struct cls_fl_filter *f = fh; + struct nlattr *nest; + bool skip_hw; + + if (!f) + return skb->len; + + t->tcm_handle = f->handle; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + spin_lock(&tp->lock); + + skip_hw = tc_skip_hw(f->flags); + + if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) + goto nla_put_failure_locked; + + spin_unlock(&tp->lock); + + if (!skip_hw) + fl_hw_update_stats(tp, f, rtnl_held); + + if (tcf_exts_terse_dump(skb, &f->exts)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + return skb->len; + +nla_put_failure_locked: + spin_unlock(&tp->lock); nla_put_failure: nla_nest_cancel(skb, nest); return -1; } +static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv) +{ + struct fl_flow_tmplt *tmplt = tmplt_priv; + struct fl_flow_key *key, *mask; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + key = &tmplt->dummy_key; + mask = &tmplt->mask; + + if (fl_dump_key(skb, net, key, mask)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + return skb->len; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) +{ + struct cls_fl_filter *f = fh; + + tc_cls_bind_class(classid, cl, q, &f->res, base); +} + +static bool fl_delete_empty(struct tcf_proto *tp) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + tp->deleting = idr_is_empty(&head->handle_idr); + spin_unlock(&tp->lock); + + return tp->deleting; +} + static struct tcf_proto_ops cls_fl_ops __read_mostly = { .kind = "flower", .classify = fl_classify, .init = fl_init, .destroy = fl_destroy, .get = fl_get, + .put = fl_put, .change = fl_change, .delete = fl_delete, + .delete_empty = fl_delete_empty, .walk = fl_walk, + .reoffload = fl_reoffload, + .hw_add = fl_hw_add, + .hw_del = fl_hw_del, .dump = fl_dump, + .terse_dump = fl_terse_dump, + .bind_class = fl_bind_class, + .tmplt_create = fl_tmplt_create, + .tmplt_destroy = fl_tmplt_destroy, + .tmplt_reoffload = fl_tmplt_reoffload, + .tmplt_dump = fl_tmplt_dump, + .get_exts = fl_get_exts, .owner = THIS_MODULE, + .flags = TCF_PROTO_OPS_DOIT_UNLOCKED, }; +MODULE_ALIAS_NET_CLS("flower"); static int __init cls_fl_init(void) { diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index d3885362e017..cdddc8695228 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -1,21 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_fw.c Classifier mapping ipchains' fwmark to traffic class. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * Karlis Peisenieks <karlis@mt.lv> : 990415 : fw_walk off by one * Karlis Peisenieks <karlis@mt.lv> : 990415 : fw_delete killed all the filter (and kernel). * Alex <alex@pilotsoft.com> : 2004xxyy: Added Action extension - * - * JHS: We should remove the CONFIG_NET_CLS_IND from here - * eventually when the meta match extension is made available - * */ #include <linux/module.h> @@ -28,6 +20,8 @@ #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> +#include <net/sch_generic.h> +#include <net/tc_wrapper.h> #define HTSIZE 256 @@ -41,12 +35,10 @@ struct fw_filter { struct fw_filter __rcu *next; u32 id; struct tcf_result res; -#ifdef CONFIG_NET_CLS_IND int ifindex; -#endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; struct tcf_proto *tp; - struct rcu_head rcu; + struct rcu_work rwork; }; static u32 fw_hash(u32 handle) @@ -56,8 +48,9 @@ static u32 fw_hash(u32 handle) return handle % HTSIZE; } -static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int fw_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { struct fw_head *head = rcu_dereference_bh(tp->root); struct fw_filter *f; @@ -71,10 +64,8 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, f = rcu_dereference_bh(f->next)) { if (f->id == id) { *res = f->res; -#ifdef CONFIG_NET_CLS_IND if (!tcf_match_indev(skb, f->ifindex)) continue; -#endif /* CONFIG_NET_CLS_IND */ r = tcf_exts_exec(skb, &f->exts, res); if (r < 0) continue; @@ -83,9 +74,11 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { + struct Qdisc *q = tcf_block_q(tp->chain->block); + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || - !(TC_H_MAJ(id ^ tp->q->handle)))) { + !(TC_H_MAJ(id ^ q->handle)))) { res->classid = id; res->class = 0; return 0; @@ -95,20 +88,20 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static unsigned long fw_get(struct tcf_proto *tp, u32 handle) +static void *fw_get(struct tcf_proto *tp, u32 handle) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; if (head == NULL) - return 0; + return NULL; f = rtnl_dereference(head->ht[fw_hash(handle)]); for (; f; f = rtnl_dereference(f->next)) { if (f->id == handle) - return (unsigned long)f; + return f; } - return 0; + return NULL; } static int fw_init(struct tcf_proto *tp) @@ -119,15 +112,25 @@ static int fw_init(struct tcf_proto *tp) return 0; } -static void fw_delete_filter(struct rcu_head *head) +static void __fw_delete_filter(struct fw_filter *f) { - struct fw_filter *f = container_of(head, struct fw_filter, rcu); - tcf_exts_destroy(&f->exts); + tcf_exts_put_net(&f->exts); kfree(f); } -static void fw_destroy(struct tcf_proto *tp) +static void fw_delete_filter_work(struct work_struct *work) +{ + struct fw_filter *f = container_of(to_rcu_work(work), + struct fw_filter, + rwork); + rtnl_lock(); + __fw_delete_filter(f); + rtnl_unlock(); +} + +static void fw_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; @@ -141,16 +144,20 @@ static void fw_destroy(struct tcf_proto *tp) RCU_INIT_POINTER(head->ht[h], rtnl_dereference(f->next)); tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, fw_delete_filter); + if (tcf_exts_get_net(&f->exts)) + tcf_queue_work(&f->rwork, fw_delete_filter_work); + else + __fw_delete_filter(f); } } kfree_rcu(head, rcu); } -static int fw_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int fw_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); - struct fw_filter *f = (struct fw_filter *)arg; + struct fw_filter *f = arg; struct fw_filter __rcu **fp; struct fw_filter *pfp; int ret = -EINVAL; @@ -166,7 +173,8 @@ static int fw_delete(struct tcf_proto *tp, unsigned long arg, bool *last) if (pfp == f) { RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, fw_delete_filter); + tcf_exts_get_net(&f->exts); + tcf_queue_work(&f->rwork, fw_delete_filter_work); ret = 0; break; } @@ -190,63 +198,51 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = { [TCA_FW_MASK] = { .type = NLA_U32 }, }; -static int -fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, - struct nlattr **tb, struct nlattr **tca, unsigned long base, - bool ovr) +static int fw_set_parms(struct net *net, struct tcf_proto *tp, + struct fw_filter *f, struct nlattr **tb, + struct nlattr **tca, unsigned long base, u32 flags, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); - struct tcf_exts e; u32 mask; int err; - err = tcf_exts_init(&e, TCA_FW_ACT, TCA_FW_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, flags, + extack); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); - if (err < 0) - goto errout; - - if (tb[TCA_FW_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); - tcf_bind_filter(tp, &f->res, base); - } -#ifdef CONFIG_NET_CLS_IND if (tb[TCA_FW_INDEV]) { int ret; - ret = tcf_change_indev(net, tb[TCA_FW_INDEV]); - if (ret < 0) { - err = ret; - goto errout; - } + ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack); + if (ret < 0) + return ret; f->ifindex = ret; } -#endif /* CONFIG_NET_CLS_IND */ err = -EINVAL; if (tb[TCA_FW_MASK]) { mask = nla_get_u32(tb[TCA_FW_MASK]); if (mask != head->mask) - goto errout; + return err; } else if (head->mask != 0xFFFFFFFF) - goto errout; + return err; - tcf_exts_change(tp, &f->exts, &e); + if (tb[TCA_FW_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } return 0; -errout: - tcf_exts_destroy(&e); - return err; } static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, - u32 handle, struct nlattr **tca, unsigned long *arg, - bool ovr) + u32 handle, struct nlattr **tca, void **arg, + u32 flags, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); - struct fw_filter *f = (struct fw_filter *) *arg; + struct fw_filter *f = *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; int err; @@ -254,7 +250,8 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (!opt) return handle ? -EINVAL : 0; /* Succeed if it is old method. */ - err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_FW_MAX, opt, fw_policy, + NULL); if (err < 0) return err; @@ -270,19 +267,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; -#ifdef CONFIG_NET_CLS_IND fnew->ifindex = f->ifindex; -#endif /* CONFIG_NET_CLS_IND */ fnew->tp = f->tp; - err = tcf_exts_init(&fnew->exts, TCA_FW_ACT, TCA_FW_POLICE); + err = tcf_exts_init(&fnew->exts, net, TCA_FW_ACT, + TCA_FW_POLICE); if (err < 0) { kfree(fnew); return err; } - err = fw_change_attrs(net, tp, fnew, tb, tca, base, ovr); + err = fw_set_parms(net, tp, fnew, tb, tca, base, flags, extack); if (err < 0) { tcf_exts_destroy(&fnew->exts); kfree(fnew); @@ -298,9 +293,10 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(fnew->next, rtnl_dereference(pfp->next)); rcu_assign_pointer(*fp, fnew); tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, fw_delete_filter); + tcf_exts_get_net(&f->exts); + tcf_queue_work(&f->rwork, fw_delete_filter_work); - *arg = (unsigned long)fnew; + *arg = fnew; return err; } @@ -324,20 +320,20 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (f == NULL) return -ENOBUFS; - err = tcf_exts_init(&f->exts, TCA_FW_ACT, TCA_FW_POLICE); + err = tcf_exts_init(&f->exts, net, TCA_FW_ACT, TCA_FW_POLICE); if (err < 0) goto errout; f->id = handle; f->tp = tp; - err = fw_change_attrs(net, tp, f, tb, tca, base, ovr); + err = fw_set_parms(net, tp, f, tb, tca, base, flags, extack); if (err < 0) goto errout; RCU_INIT_POINTER(f->next, head->ht[fw_hash(handle)]); rcu_assign_pointer(head->ht[fw_hash(handle)], f); - *arg = (unsigned long)f; + *arg = f; return 0; errout: @@ -346,7 +342,8 @@ errout: return err; } -static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct fw_head *head = rtnl_dereference(tp->root); int h; @@ -362,24 +359,17 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) for (f = rtnl_dereference(head->ht[h]); f; f = rtnl_dereference(f->next)) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(tp, (unsigned long)f, arg) < 0) { - arg->stop = 1; + if (!tc_cls_stats_dump(tp, arg, f)) return; - } - arg->count++; } } } -static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct fw_head *head = rtnl_dereference(tp->root); - struct fw_filter *f = (struct fw_filter *)fh; + struct fw_filter *f = fh; struct nlattr *nest; if (f == NULL) @@ -387,24 +377,22 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, t->tcm_handle = f->id; - if (!f->res.classid && !tcf_exts_is_available(&f->exts)) + if (!f->res.classid && !tcf_exts_has_actions(&f->exts)) return skb->len; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (f->res.classid && nla_put_u32(skb, TCA_FW_CLASSID, f->res.classid)) goto nla_put_failure; -#ifdef CONFIG_NET_CLS_IND if (f->ifindex) { struct net_device *dev; dev = __dev_get_by_index(net, f->ifindex); if (dev && nla_put_string(skb, TCA_FW_INDEV, dev->name)) goto nla_put_failure; } -#endif /* CONFIG_NET_CLS_IND */ if (head->mask != 0xFFFFFFFF && nla_put_u32(skb, TCA_FW_MASK, head->mask)) goto nla_put_failure; @@ -424,6 +412,14 @@ nla_put_failure: return -1; } +static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) +{ + struct fw_filter *f = fh; + + tc_cls_bind_class(classid, cl, q, &f->res, base); +} + static struct tcf_proto_ops cls_fw_ops __read_mostly = { .kind = "fw", .classify = fw_classify, @@ -434,8 +430,10 @@ static struct tcf_proto_ops cls_fw_ops __read_mostly = { .delete = fw_delete, .walk = fw_walk, .dump = fw_dump, + .bind_class = fw_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("fw"); static int __init init_fw(void) { @@ -449,4 +447,5 @@ static void __exit exit_fw(void) module_init(init_fw) module_exit(exit_fw) +MODULE_DESCRIPTION("SKB mark based TC classifier"); MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 9dc26c32cf32..f03bf5da39ee 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -1,37 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_matchll.c Match-all classifier * * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> +#include <linux/percpu.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include <net/tc_wrapper.h> struct cls_mall_head { struct tcf_exts exts; struct tcf_result res; u32 handle; u32 flags; - struct rcu_head rcu; + unsigned int in_hw_count; + struct tc_matchall_pcnt __percpu *pf; + struct rcu_work rwork; + bool deleting; }; -static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int mall_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { struct cls_mall_head *head = rcu_dereference_bh(tp->root); + if (unlikely(!head)) + return -1; + if (tc_skip_sw(head->flags)) return -1; + *res = head->res; + __this_cpu_inc(head->pf->rhit); return tcf_exts_exec(skb, &head->exts, res); } @@ -40,119 +47,129 @@ static int mall_init(struct tcf_proto *tp) return 0; } -static void mall_destroy_rcu(struct rcu_head *rcu) +static void __mall_destroy(struct cls_mall_head *head) { - struct cls_mall_head *head = container_of(rcu, struct cls_mall_head, - rcu); - tcf_exts_destroy(&head->exts); + tcf_exts_put_net(&head->exts); + free_percpu(head->pf); kfree(head); } +static void mall_destroy_work(struct work_struct *work) +{ + struct cls_mall_head *head = container_of(to_rcu_work(work), + struct cls_mall_head, + rwork); + rtnl_lock(); + __mall_destroy(head); + rtnl_unlock(); +} + +static void mall_destroy_hw_filter(struct tcf_proto *tp, + struct cls_mall_head *head, + unsigned long cookie, + struct netlink_ext_ack *extack) +{ + struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + + tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack); + cls_mall.command = TC_CLSMATCHALL_DESTROY; + cls_mall.cookie = cookie; + + tc_setup_cb_destroy(block, tp, TC_SETUP_CLSMATCHALL, &cls_mall, false, + &head->flags, &head->in_hw_count, true); +} + static int mall_replace_hw_filter(struct tcf_proto *tp, struct cls_mall_head *head, - unsigned long cookie) + unsigned long cookie, + struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_to_netdev offload; - struct tc_cls_matchall_offload mall_offload = {0}; + struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + bool skip_sw = tc_skip_sw(head->flags); int err; - offload.type = TC_SETUP_MATCHALL; - offload.cls_mall = &mall_offload; - offload.cls_mall->command = TC_CLSMATCHALL_REPLACE; - offload.cls_mall->exts = &head->exts; - offload.cls_mall->cookie = cookie; + cls_mall.rule = flow_rule_alloc(tcf_exts_num_actions(&head->exts)); + if (!cls_mall.rule) + return -ENOMEM; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, - tp->protocol, &offload); - if (!err) - head->flags |= TCA_CLS_FLAGS_IN_HW; + tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack); + cls_mall.command = TC_CLSMATCHALL_REPLACE; + cls_mall.cookie = cookie; - return err; -} + err = tc_setup_offload_action(&cls_mall.rule->action, &head->exts, + cls_mall.common.extack); + if (err) { + kfree(cls_mall.rule); + mall_destroy_hw_filter(tp, head, cookie, NULL); -static void mall_destroy_hw_filter(struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long cookie) -{ - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_to_netdev offload; - struct tc_cls_matchall_offload mall_offload = {0}; - - offload.type = TC_SETUP_MATCHALL; - offload.cls_mall = &mall_offload; - offload.cls_mall->command = TC_CLSMATCHALL_DESTROY; - offload.cls_mall->exts = NULL; - offload.cls_mall->cookie = cookie; - - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->chain->index, - tp->protocol, &offload); + return skip_sw ? err : 0; + } + + err = tc_setup_cb_add(block, tp, TC_SETUP_CLSMATCHALL, &cls_mall, + skip_sw, &head->flags, &head->in_hw_count, true); + tc_cleanup_offload_action(&cls_mall.rule->action); + kfree(cls_mall.rule); + + if (err) { + mall_destroy_hw_filter(tp, head, cookie, NULL); + return err; + } + + if (skip_sw && !(head->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; + + return 0; } -static void mall_destroy(struct tcf_proto *tp) +static void mall_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); - struct net_device *dev = tp->q->dev_queue->dev; if (!head) return; - if (tc_should_offload(dev, tp, head->flags)) - mall_destroy_hw_filter(tp, head, (unsigned long) head); + tcf_unbind_filter(tp, &head->res); + + if (!tc_skip_hw(head->flags)) + mall_destroy_hw_filter(tp, head, (unsigned long) head, extack); - call_rcu(&head->rcu, mall_destroy_rcu); + if (tcf_exts_get_net(&head->exts)) + tcf_queue_work(&head->rwork, mall_destroy_work); + else + __mall_destroy(head); } -static unsigned long mall_get(struct tcf_proto *tp, u32 handle) +static void *mall_get(struct tcf_proto *tp, u32 handle) { - return 0UL; + struct cls_mall_head *head = rtnl_dereference(tp->root); + + if (head && head->handle == handle) + return head; + + return NULL; } static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_UNSPEC] = { .type = NLA_UNSPEC }, [TCA_MATCHALL_CLASSID] = { .type = NLA_U32 }, + [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; -static int mall_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) -{ - struct tcf_exts e; - int err; - - err = tcf_exts_init(&e, TCA_MATCHALL_ACT, 0); - if (err) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - - if (tb[TCA_MATCHALL_CLASSID]) { - head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); - tcf_bind_filter(tp, &head->res, base); - } - - tcf_exts_change(tp, &head->exts, &e); - - return 0; -errout: - tcf_exts_destroy(&e); - return err; -} - static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, u32 flags, + struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); - struct net_device *dev = tp->q->dev_queue->dev; struct nlattr *tb[TCA_MATCHALL_MAX + 1]; + bool bound_to_filter = false; struct cls_mall_head *new; - u32 flags = 0; + u32 userflags = 0; int err; if (!tca[TCA_OPTIONS]) @@ -161,14 +178,14 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (head) return -EEXIST; - err = nla_parse_nested(tb, TCA_MATCHALL_MAX, tca[TCA_OPTIONS], - mall_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_MATCHALL_MAX, + tca[TCA_OPTIONS], mall_policy, NULL); if (err < 0) return err; if (tb[TCA_MATCHALL_FLAGS]) { - flags = nla_get_u32(tb[TCA_MATCHALL_FLAGS]); - if (!tc_flags_valid(flags)) + userflags = nla_get_u32(tb[TCA_MATCHALL_FLAGS]); + if (!tc_flags_valid(userflags)) return -EINVAL; } @@ -176,73 +193,155 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOBUFS; - err = tcf_exts_init(&new->exts, TCA_MATCHALL_ACT, 0); + err = tcf_exts_init(&new->exts, net, TCA_MATCHALL_ACT, 0); if (err) goto err_exts_init; if (!handle) handle = 1; new->handle = handle; - new->flags = flags; + new->flags = userflags; + new->pf = alloc_percpu(struct tc_matchall_pcnt); + if (!new->pf) { + err = -ENOMEM; + goto err_alloc_percpu; + } - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &new->exts, flags, new->flags, extack); + if (err < 0) goto err_set_parms; - if (tc_should_offload(dev, tp, flags)) { - err = mall_replace_hw_filter(tp, new, (unsigned long) new); - if (err) { - if (tc_skip_sw(flags)) - goto err_replace_hw_filter; - else - err = 0; - } + if (tb[TCA_MATCHALL_CLASSID]) { + new->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); + tcf_bind_filter(tp, &new->res, base); + bound_to_filter = true; + } + + if (!tc_skip_hw(new->flags)) { + err = mall_replace_hw_filter(tp, new, (unsigned long)new, + extack); + if (err) + goto err_replace_hw_filter; } if (!tc_in_hw(new->flags)) new->flags |= TCA_CLS_FLAGS_NOT_IN_HW; - *arg = (unsigned long) head; + tcf_proto_update_usesw(tp, new->flags); + + *arg = head; rcu_assign_pointer(tp->root, new); return 0; err_replace_hw_filter: + if (bound_to_filter) + tcf_unbind_filter(tp, &new->res); err_set_parms: + free_percpu(new->pf); +err_alloc_percpu: tcf_exts_destroy(&new->exts); err_exts_init: kfree(new); return err; } -static int mall_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int mall_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { - return -EOPNOTSUPP; + struct cls_mall_head *head = rtnl_dereference(tp->root); + + head->deleting = true; + *last = true; + return 0; } -static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_mall_head *head = rtnl_dereference(tp->root); if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long) head, arg) < 0) + + if (!head || head->deleting) + return; + if (arg->fn(tp, head, arg) < 0) arg->stop = 1; skip: arg->count++; } -static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct cls_mall_head *head = rtnl_dereference(tp->root); + struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + int err; + + if (tc_skip_hw(head->flags)) + return 0; + + cls_mall.rule = flow_rule_alloc(tcf_exts_num_actions(&head->exts)); + if (!cls_mall.rule) + return -ENOMEM; + + tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack); + cls_mall.command = add ? + TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY; + cls_mall.cookie = (unsigned long)head; + + err = tc_setup_offload_action(&cls_mall.rule->action, &head->exts, + cls_mall.common.extack); + if (err) { + kfree(cls_mall.rule); + + return add && tc_skip_sw(head->flags) ? err : 0; + } + + err = tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSMATCHALL, + &cls_mall, cb_priv, &head->flags, + &head->in_hw_count); + tc_cleanup_offload_action(&cls_mall.rule->action); + kfree(cls_mall.rule); + + return err; +} + +static void mall_stats_hw_filter(struct tcf_proto *tp, + struct cls_mall_head *head, + unsigned long cookie) +{ + struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + + tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, NULL); + cls_mall.command = TC_CLSMATCHALL_STATS; + cls_mall.cookie = cookie; + + tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false, true); + + tcf_exts_hw_stats_update(&head->exts, &cls_mall.stats, cls_mall.use_act_stats); +} + +static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { - struct cls_mall_head *head = (struct cls_mall_head *) fh; + struct tc_matchall_pcnt gpf = {}; + struct cls_mall_head *head = fh; struct nlattr *nest; + int cpu; if (!head) return skb->len; + if (!tc_skip_hw(head->flags)) + mall_stats_hw_filter(tp, head, (unsigned long)head); + t->tcm_handle = head->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; @@ -253,6 +352,17 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (head->flags && nla_put_u32(skb, TCA_MATCHALL_FLAGS, head->flags)) goto nla_put_failure; + for_each_possible_cpu(cpu) { + struct tc_matchall_pcnt *pf = per_cpu_ptr(head->pf, cpu); + + gpf.rhit += pf->rhit; + } + + if (nla_put_64bit(skb, TCA_MATCHALL_PCNT, + sizeof(struct tc_matchall_pcnt), + &gpf, TCA_MATCHALL_PAD)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &head->exts)) goto nla_put_failure; @@ -268,6 +378,14 @@ nla_put_failure: return -1; } +static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) +{ + struct cls_mall_head *head = fh; + + tc_cls_bind_class(classid, cl, q, &head->res, base); +} + static struct tcf_proto_ops cls_mall_ops __read_mostly = { .kind = "matchall", .classify = mall_classify, @@ -277,9 +395,12 @@ static struct tcf_proto_ops cls_mall_ops __read_mostly = { .change = mall_change, .delete = mall_delete, .walk = mall_walk, + .reoffload = mall_reoffload, .dump = mall_dump, + .bind_class = mall_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("matchall"); static int __init cls_mall_init(void) { diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index d63d5502ee02..b9c58c040c30 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_route.c ROUTE4 classifier. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ @@ -21,6 +17,7 @@ #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> +#include <net/tc_wrapper.h> /* * 1. For now we assume that route tags < 256. @@ -57,7 +54,7 @@ struct route4_filter { u32 handle; struct route4_bucket *bkt; struct tcf_proto *tp; - struct rcu_head rcu; + struct rcu_work rwork; }; #define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) @@ -113,7 +110,7 @@ static inline int route4_hash_wild(void) #define ROUTE4_APPLY_RESULT() \ { \ *res = f->res; \ - if (tcf_exts_is_available(&f->exts)) { \ + if (tcf_exts_has_actions(&f->exts)) { \ int r = tcf_exts_exec(skb, &f->exts, res); \ if (r < 0) { \ dont_cache = 1; \ @@ -125,8 +122,9 @@ static inline int route4_hash_wild(void) return 0; \ } -static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int route4_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { struct route4_head *head = rcu_dereference_bh(tp->root); struct dst_entry *dst; @@ -216,7 +214,7 @@ static inline u32 from_hash(u32 id) return 16 + (id & 0xF); } -static unsigned long route4_get(struct tcf_proto *tp, u32 handle) +static void *route4_get(struct tcf_proto *tp, u32 handle) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_bucket *b; @@ -225,11 +223,11 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) h1 = to_hash(handle); if (h1 > 256) - return 0; + return NULL; h2 = from_hash(handle >> 16); if (h2 > 32) - return 0; + return NULL; b = rtnl_dereference(head->table[h1]); if (b) { @@ -237,9 +235,9 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) f; f = rtnl_dereference(f->next)) if (f->handle == handle) - return (unsigned long)f; + return f; } - return 0; + return NULL; } static int route4_init(struct tcf_proto *tp) @@ -254,15 +252,30 @@ static int route4_init(struct tcf_proto *tp) return 0; } -static void route4_delete_filter(struct rcu_head *head) +static void __route4_delete_filter(struct route4_filter *f) { - struct route4_filter *f = container_of(head, struct route4_filter, rcu); - tcf_exts_destroy(&f->exts); + tcf_exts_put_net(&f->exts); kfree(f); } -static void route4_destroy(struct tcf_proto *tp) +static void route4_delete_filter_work(struct work_struct *work) +{ + struct route4_filter *f = container_of(to_rcu_work(work), + struct route4_filter, + rwork); + rtnl_lock(); + __route4_delete_filter(f); + rtnl_unlock(); +} + +static void route4_queue_work(struct route4_filter *f) +{ + tcf_queue_work(&f->rwork, route4_delete_filter_work); +} + +static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); int h1, h2; @@ -284,7 +297,10 @@ static void route4_destroy(struct tcf_proto *tp) next = rtnl_dereference(f->next); RCU_INIT_POINTER(b->ht[h2], next); tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, route4_delete_filter); + if (tcf_exts_get_net(&f->exts)) + route4_queue_work(f); + else + __route4_delete_filter(f); } } RCU_INIT_POINTER(head->table[h1], NULL); @@ -294,10 +310,11 @@ static void route4_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static int route4_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); - struct route4_filter *f = (struct route4_filter *)arg; + struct route4_filter *f = arg; struct route4_filter __rcu **fp; struct route4_filter *nf; struct route4_bucket *b; @@ -325,7 +342,8 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg, bool *last) /* Delete it */ tcf_unbind_filter(tp, &f->res); - call_rcu(&f->rcu, route4_delete_filter); + tcf_exts_get_net(&f->exts); + tcf_queue_work(&f->rwork, route4_delete_filter_work); /* Strip RTNL protected tree */ for (i = 0; i <= 32; i++) { @@ -357,80 +375,82 @@ out: static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = { [TCA_ROUTE4_CLASSID] = { .type = NLA_U32 }, - [TCA_ROUTE4_TO] = { .type = NLA_U32 }, - [TCA_ROUTE4_FROM] = { .type = NLA_U32 }, - [TCA_ROUTE4_IIF] = { .type = NLA_U32 }, + [TCA_ROUTE4_TO] = NLA_POLICY_MAX(NLA_U32, 0xFF), + [TCA_ROUTE4_FROM] = NLA_POLICY_MAX(NLA_U32, 0xFF), + [TCA_ROUTE4_IIF] = NLA_POLICY_MAX(NLA_U32, 0x7FFF), }; static int route4_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct route4_filter *f, u32 handle, struct route4_head *head, struct nlattr **tb, struct nlattr *est, int new, - bool ovr) + u32 flags, struct netlink_ext_ack *extack) { u32 id = 0, to = 0, nhandle = 0x8000; struct route4_filter *fp; unsigned int h1; struct route4_bucket *b; - struct tcf_exts e; int err; - err = tcf_exts_init(&e, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - err = -EINVAL; if (tb[TCA_ROUTE4_TO]) { - if (new && handle & 0x8000) - goto errout; + if (new && handle & 0x8000) { + NL_SET_ERR_MSG(extack, "Invalid handle"); + return -EINVAL; + } to = nla_get_u32(tb[TCA_ROUTE4_TO]); - if (to > 0xFF) - goto errout; nhandle = to; } + if (tb[TCA_ROUTE4_FROM] && tb[TCA_ROUTE4_IIF]) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_ROUTE4_FROM], + "'from' and 'fromif' are mutually exclusive"); + return -EINVAL; + } + if (tb[TCA_ROUTE4_FROM]) { - if (tb[TCA_ROUTE4_IIF]) - goto errout; id = nla_get_u32(tb[TCA_ROUTE4_FROM]); - if (id > 0xFF) - goto errout; nhandle |= id << 16; } else if (tb[TCA_ROUTE4_IIF]) { id = nla_get_u32(tb[TCA_ROUTE4_IIF]); - if (id > 0x7FFF) - goto errout; nhandle |= (id | 0x8000) << 16; } else nhandle |= 0xFFFF << 16; if (handle && new) { nhandle |= handle & 0x7F00; - if (nhandle != handle) - goto errout; + if (nhandle != handle) { + NL_SET_ERR_MSG_FMT(extack, + "Handle mismatch constructed: %x (expected: %x)", + handle, nhandle); + return -EINVAL; + } + } + + if (!nhandle) { + NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid"); + return -EINVAL; } h1 = to_hash(nhandle); b = rtnl_dereference(head->table[h1]); if (!b) { - err = -ENOBUFS; b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL); if (b == NULL) - goto errout; + return -ENOBUFS; rcu_assign_pointer(head->table[h1], b); } else { unsigned int h2 = from_hash(nhandle >> 16); - err = -EEXIST; for (fp = rtnl_dereference(b->ht[h2]); fp; fp = rtnl_dereference(fp->next)) if (fp->handle == f->handle) - goto errout; + return -EEXIST; } if (tb[TCA_ROUTE4_TO]) @@ -450,37 +470,40 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, tcf_bind_filter(tp, &f->res, base); } - tcf_exts_change(tp, &f->exts, &e); - return 0; -errout: - tcf_exts_destroy(&e); - return err; } static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) + struct nlattr **tca, void **arg, u32 flags, + struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; struct route4_filter *fold, *f1, *pfp, *f = NULL; struct route4_bucket *b; - struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_ROUTE4_MAX + 1]; unsigned int h, th; int err; bool new = true; - if (opt == NULL) - return handle ? -EINVAL : 0; + if (!handle) { + NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid"); + return -EINVAL; + } - err = nla_parse_nested(tb, TCA_ROUTE4_MAX, opt, route4_policy, NULL); + if (NL_REQ_ATTR_CHECK(extack, NULL, tca, TCA_OPTIONS)) { + NL_SET_ERR_MSG_MOD(extack, "Missing options"); + return -EINVAL; + } + + err = nla_parse_nested_deprecated(tb, TCA_ROUTE4_MAX, tca[TCA_OPTIONS], + route4_policy, NULL); if (err < 0) return err; - fold = (struct route4_filter *)*arg; - if (fold && handle && fold->handle != handle) + fold = *arg; + if (fold && fold->handle != handle) return -EINVAL; err = -ENOBUFS; @@ -488,14 +511,13 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (!f) goto errout; - err = tcf_exts_init(&f->exts, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); + err = tcf_exts_init(&f->exts, net, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); if (err < 0) goto errout; if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; @@ -504,7 +526,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } err = route4_set_parms(net, tp, base, f, handle, head, tb, - tca[TCA_RATE], new, ovr); + tca[TCA_RATE], new, flags, extack); if (err < 0) goto errout; @@ -516,11 +538,11 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (f->handle < f1->handle) break; - netif_keep_dst(qdisc_dev(tp->q)); + tcf_block_netif_keep_dst(tp->chain->block); rcu_assign_pointer(f->next, f1); rcu_assign_pointer(*fp, f); - if (fold && fold->handle && f->handle != fold->handle) { + if (fold) { th = to_hash(fold->handle); h = from_hash(fold->handle >> 16); b = rtnl_dereference(head->table[th]); @@ -528,8 +550,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, fp = &b->ht[h]; for (pfp = rtnl_dereference(*fp); pfp; fp = &pfp->next, pfp = rtnl_dereference(*fp)) { - if (pfp == f) { - *fp = f->next; + if (pfp == fold) { + rcu_assign_pointer(*fp, fold->next); break; } } @@ -537,10 +559,11 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } route4_reset_fastmap(head); - *arg = (unsigned long)f; + *arg = f; if (fold) { tcf_unbind_filter(tp, &fold->res); - call_rcu(&fold->rcu, route4_delete_filter); + tcf_exts_get_net(&fold->exts); + tcf_queue_work(&fold->rwork, route4_delete_filter_work); } return 0; @@ -551,15 +574,13 @@ errout: return err; } -static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct route4_head *head = rtnl_dereference(tp->root); unsigned int h, h1; - if (head == NULL) - arg->stop = 1; - - if (arg->stop) + if (head == NULL || arg->stop) return; for (h = 0; h <= 256; h++) { @@ -572,25 +593,18 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) for (f = rtnl_dereference(b->ht[h1]); f; f = rtnl_dereference(f->next)) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(tp, (unsigned long)f, arg) < 0) { - arg->stop = 1; + if (!tc_cls_stats_dump(tp, arg, f)) return; - } - arg->count++; } } } } } -static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { - struct route4_filter *f = (struct route4_filter *)fh; + struct route4_filter *f = fh; struct nlattr *nest; u32 id; @@ -599,7 +613,7 @@ static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, t->tcm_handle = f->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -636,6 +650,14 @@ nla_put_failure: return -1; } +static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) +{ + struct route4_filter *f = fh; + + tc_cls_bind_class(classid, cl, q, &f->res, base); +} + static struct tcf_proto_ops cls_route4_ops __read_mostly = { .kind = "route", .classify = route4_classify, @@ -646,8 +668,10 @@ static struct tcf_proto_ops cls_route4_ops __read_mostly = { .delete = route4_delete, .walk = route4_walk, .dump = route4_dump, + .bind_class = route4_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("route"); static int __init init_route4(void) { @@ -661,4 +685,5 @@ static void __exit exit_route4(void) module_init(init_route4) module_exit(exit_route4) +MODULE_DESCRIPTION("Routing table realm based TC classifier"); MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c deleted file mode 100644 index cbb5e0d600f3..000000000000 --- a/net/sched/cls_rsvp.c +++ /dev/null @@ -1,28 +0,0 @@ -/* - * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> - -#define RSVP_DST_LEN 1 -#define RSVP_ID "rsvp" -#define RSVP_OPS cls_rsvp_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h deleted file mode 100644 index 0d9d07798699..000000000000 --- a/net/sched/cls_rsvp.h +++ /dev/null @@ -1,750 +0,0 @@ -/* - * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -/* - Comparing to general packet classification problem, - RSVP needs only sevaral relatively simple rules: - - * (dst, protocol) are always specified, - so that we are able to hash them. - * src may be exact, or may be wildcard, so that - we can keep a hash table plus one wildcard entry. - * source port (or flow label) is important only if src is given. - - IMPLEMENTATION. - - We use a two level hash table: The top level is keyed by - destination address and protocol ID, every bucket contains a list - of "rsvp sessions", identified by destination address, protocol and - DPI(="Destination Port ID"): triple (key, mask, offset). - - Every bucket has a smaller hash table keyed by source address - (cf. RSVP flowspec) and one wildcard entry for wildcard reservations. - Every bucket is again a list of "RSVP flows", selected by - source address and SPI(="Source Port ID" here rather than - "security parameter index"): triple (key, mask, offset). - - - NOTE 1. All the packets with IPv6 extension headers (but AH and ESP) - and all fragmented packets go to the best-effort traffic class. - - - NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires - only one "Generalized Port Identifier". So that for classic - ah, esp (and udp,tcp) both *pi should coincide or one of them - should be wildcard. - - At first sight, this redundancy is just a waste of CPU - resources. But DPI and SPI add the possibility to assign different - priorities to GPIs. Look also at note 4 about tunnels below. - - - NOTE 3. One complication is the case of tunneled packets. - We implement it as following: if the first lookup - matches a special session with "tunnelhdr" value not zero, - flowid doesn't contain the true flow ID, but the tunnel ID (1...255). - In this case, we pull tunnelhdr bytes and restart lookup - with tunnel ID added to the list of keys. Simple and stupid 8)8) - It's enough for PIMREG and IPIP. - - - NOTE 4. Two GPIs make it possible to parse even GRE packets. - F.e. DPI can select ETH_P_IP (and necessary flags to make - tunnelhdr correct) in GRE protocol field and SPI matches - GRE key. Is it not nice? 8)8) - - - Well, as result, despite its simplicity, we get a pretty - powerful classification engine. */ - - -struct rsvp_head { - u32 tmap[256/32]; - u32 hgenerator; - u8 tgenerator; - struct rsvp_session __rcu *ht[256]; - struct rcu_head rcu; -}; - -struct rsvp_session { - struct rsvp_session __rcu *next; - __be32 dst[RSVP_DST_LEN]; - struct tc_rsvp_gpi dpi; - u8 protocol; - u8 tunnelid; - /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter __rcu *ht[16 + 1]; - struct rcu_head rcu; -}; - - -struct rsvp_filter { - struct rsvp_filter __rcu *next; - __be32 src[RSVP_DST_LEN]; - struct tc_rsvp_gpi spi; - u8 tunnelhdr; - - struct tcf_result res; - struct tcf_exts exts; - - u32 handle; - struct rsvp_session *sess; - struct rcu_head rcu; -}; - -static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) -{ - unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; - - h ^= h>>16; - h ^= h>>8; - return (h ^ protocol ^ tunnelid) & 0xFF; -} - -static inline unsigned int hash_src(__be32 *src) -{ - unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; - - h ^= h>>16; - h ^= h>>8; - h ^= h>>4; - return h & 0xF; -} - -#define RSVP_APPLY_RESULT() \ -{ \ - int r = tcf_exts_exec(skb, &f->exts, res); \ - if (r < 0) \ - continue; \ - else if (r > 0) \ - return r; \ -} - -static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct rsvp_head *head = rcu_dereference_bh(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1, h2; - __be32 *dst, *src; - u8 protocol; - u8 tunnelid = 0; - u8 *xprt; -#if RSVP_DST_LEN == 4 - struct ipv6hdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ipv6_hdr(skb); -#else - struct iphdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ip_hdr(skb); -#endif -restart: - -#if RSVP_DST_LEN == 4 - src = &nhptr->saddr.s6_addr32[0]; - dst = &nhptr->daddr.s6_addr32[0]; - protocol = nhptr->nexthdr; - xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); -#else - src = &nhptr->saddr; - dst = &nhptr->daddr; - protocol = nhptr->protocol; - xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (ip_is_fragment(nhptr)) - return -1; -#endif - - h1 = hash_dst(dst, protocol, tunnelid); - h2 = hash_src(src); - - for (s = rcu_dereference_bh(head->ht[h1]); s; - s = rcu_dereference_bh(s->next)) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && - protocol == s->protocol && - !(s->dpi.mask & - (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - tunnelid == s->tunnelid) { - - for (f = rcu_dereference_bh(s->ht[h2]); f; - f = rcu_dereference_bh(f->next)) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && - !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) -#if RSVP_DST_LEN == 4 - && - src[0] == f->src[0] && - src[1] == f->src[1] && - src[2] == f->src[2] -#endif - ) { - *res = f->res; - RSVP_APPLY_RESULT(); - -matched: - if (f->tunnelhdr == 0) - return 0; - - tunnelid = f->res.classid; - nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); - goto restart; - } - } - - /* And wildcard bucket... */ - for (f = rcu_dereference_bh(s->ht[16]); f; - f = rcu_dereference_bh(f->next)) { - *res = f->res; - RSVP_APPLY_RESULT(); - goto matched; - } - return -1; - } - } - return -1; -} - -static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter __rcu **ins; - struct rsvp_filter *pins; - unsigned int h1 = h & 0xFF; - unsigned int h2 = (h >> 8) & 0xFF; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ; - ins = &pins->next, pins = rtnl_dereference(*ins)) { - if (pins->handle == h) { - RCU_INIT_POINTER(n->next, pins->next); - rcu_assign_pointer(*ins, n); - return; - } - } - } - - /* Something went wrong if we are trying to replace a non-existant - * node. Mind as well halt instead of silently failing. - */ - BUG_ON(1); -} - -static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1 = handle & 0xFF; - unsigned int h2 = (handle >> 8) & 0xFF; - - if (h2 > 16) - return 0; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->handle == handle) - return (unsigned long)f; - } - } - return 0; -} - -static int rsvp_init(struct tcf_proto *tp) -{ - struct rsvp_head *data; - - data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL); - if (data) { - rcu_assign_pointer(tp->root, data); - return 0; - } - return -ENOBUFS; -} - -static void rsvp_delete_filter_rcu(struct rcu_head *head) -{ - struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu); - - tcf_exts_destroy(&f->exts); - kfree(f); -} - -static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) -{ - tcf_unbind_filter(tp, &f->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - call_rcu(&f->rcu, rsvp_delete_filter_rcu); -} - -static void rsvp_destroy(struct tcf_proto *tp) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int h1, h2; - - if (data == NULL) - return; - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - - while ((s = rtnl_dereference(data->ht[h1])) != NULL) { - RCU_INIT_POINTER(data->ht[h1], s->next); - - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - while ((f = rtnl_dereference(s->ht[h2])) != NULL) { - rcu_assign_pointer(s->ht[h2], f->next); - rsvp_delete_filter(tp, f); - } - } - kfree_rcu(s, rcu); - } - } - kfree_rcu(data, rcu); -} - -static int rsvp_delete(struct tcf_proto *tp, unsigned long arg, bool *last) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_filter *nfp, *f = (struct rsvp_filter *)arg; - struct rsvp_filter __rcu **fp; - unsigned int h = f->handle; - struct rsvp_session __rcu **sp; - struct rsvp_session *nsp, *s = f->sess; - int i, h1; - - fp = &s->ht[(h >> 8) & 0xFF]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - if (nfp == f) { - RCU_INIT_POINTER(*fp, f->next); - rsvp_delete_filter(tp, f); - - /* Strip tree */ - - for (i = 0; i <= 16; i++) - if (s->ht[i]) - goto out; - - /* OK, session has no flows */ - sp = &head->ht[h & 0xFF]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if (nsp == s) { - RCU_INIT_POINTER(*sp, s->next); - kfree_rcu(s, rcu); - goto out; - } - } - - break; - } - } - -out: - *last = true; - for (h1 = 0; h1 < 256; h1++) { - if (rcu_access_pointer(head->ht[h1])) { - *last = false; - break; - } - } - - return 0; -} - -static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int i = 0xFFFF; - - while (i-- > 0) { - u32 h; - - if ((data->hgenerator += 0x10000) == 0) - data->hgenerator = 0x10000; - h = data->hgenerator|salt; - if (rsvp_get(tp, h) == 0) - return h; - } - return 0; -} - -static int tunnel_bts(struct rsvp_head *data) -{ - int n = data->tgenerator >> 5; - u32 b = 1 << (data->tgenerator & 0x1F); - - if (data->tmap[n] & b) - return 0; - data->tmap[n] |= b; - return 1; -} - -static void tunnel_recycle(struct rsvp_head *data) -{ - struct rsvp_session __rcu **sht = data->ht; - u32 tmap[256/32]; - int h1, h2; - - memset(tmap, 0, sizeof(tmap)); - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - for (s = rtnl_dereference(sht[h1]); s; - s = rtnl_dereference(s->next)) { - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->tunnelhdr == 0) - continue; - data->tgenerator = f->res.classid; - tunnel_bts(data); - } - } - } - } - - memcpy(data->tmap, tmap, sizeof(tmap)); -} - -static u32 gen_tunnel(struct rsvp_head *data) -{ - int i, k; - - for (k = 0; k < 2; k++) { - for (i = 255; i > 0; i--) { - if (++data->tgenerator == 0) - data->tgenerator = 1; - if (tunnel_bts(data)) - return data->tgenerator; - } - tunnel_recycle(data); - } - return 0; -} - -static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { - [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .type = NLA_BINARY, - .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .type = NLA_BINARY, - .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, -}; - -static int rsvp_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, - struct nlattr **tca, - unsigned long *arg, bool ovr) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - struct rsvp_filter *f, *nfp; - struct rsvp_filter __rcu **fp; - struct rsvp_session *nsp, *s; - struct rsvp_session __rcu **sp; - struct tc_rsvp_pinfo *pinfo = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_RSVP_MAX + 1]; - struct tcf_exts e; - unsigned int h1, h2; - __be32 *dst; - int err; - - if (opt == NULL) - return handle ? -EINVAL : 0; - - err = nla_parse_nested(tb, TCA_RSVP_MAX, opt, rsvp_policy, NULL); - if (err < 0) - return err; - - err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); - if (err < 0) - goto errout2; - - f = (struct rsvp_filter *)*arg; - if (f) { - /* Node exists: adjust only classid */ - struct rsvp_filter *n; - - if (f->handle != handle && handle) - goto errout2; - - n = kmemdup(f, sizeof(*f), GFP_KERNEL); - if (!n) { - err = -ENOMEM; - goto errout2; - } - - err = tcf_exts_init(&n->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) { - kfree(n); - goto errout2; - } - - if (tb[TCA_RSVP_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } - - tcf_exts_change(tp, &n->exts, &e); - rsvp_replace(tp, n, handle); - return 0; - } - - /* Now more serious part... */ - err = -EINVAL; - if (handle) - goto errout2; - if (tb[TCA_RSVP_DST] == NULL) - goto errout2; - - err = -ENOBUFS; - f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL); - if (f == NULL) - goto errout2; - - err = tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - goto errout; - h2 = 16; - if (tb[TCA_RSVP_SRC]) { - memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); - h2 = hash_src(f->src); - } - if (tb[TCA_RSVP_PINFO]) { - pinfo = nla_data(tb[TCA_RSVP_PINFO]); - f->spi = pinfo->spi; - f->tunnelhdr = pinfo->tunnelhdr; - } - if (tb[TCA_RSVP_CLASSID]) - f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - - dst = nla_data(tb[TCA_RSVP_DST]); - h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0); - - err = -ENOMEM; - if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0) - goto errout; - - if (f->tunnelhdr) { - err = -EINVAL; - if (f->res.classid > 255) - goto errout; - - err = -ENOMEM; - if (f->res.classid == 0 && - (f->res.classid = gen_tunnel(data)) == 0) - goto errout; - } - - for (sp = &data->ht[h1]; - (s = rtnl_dereference(*sp)) != NULL; - sp = &s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && - pinfo && pinfo->protocol == s->protocol && - memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - pinfo->tunnelid == s->tunnelid) { - -insert: - /* OK, we found appropriate session */ - - fp = &s->ht[h2]; - - f->sess = s; - if (f->tunnelhdr == 0) - tcf_bind_filter(tp, &f->res, base); - - tcf_exts_change(tp, &f->exts, &e); - - fp = &s->ht[h2]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - __u32 mask = nfp->spi.mask & f->spi.mask; - - if (mask != f->spi.mask) - break; - } - RCU_INIT_POINTER(f->next, nfp); - rcu_assign_pointer(*fp, f); - - *arg = (unsigned long)f; - return 0; - } - } - - /* No session found. Create new one. */ - - err = -ENOBUFS; - s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL); - if (s == NULL) - goto errout; - memcpy(s->dst, dst, sizeof(s->dst)); - - if (pinfo) { - s->dpi = pinfo->dpi; - s->protocol = pinfo->protocol; - s->tunnelid = pinfo->tunnelid; - } - sp = &data->ht[h1]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask) - break; - } - RCU_INIT_POINTER(s->next, nsp); - rcu_assign_pointer(*sp, s); - - goto insert; - -errout: - tcf_exts_destroy(&f->exts); - kfree(f); -errout2: - tcf_exts_destroy(&e); - return err; -} - -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - unsigned int h, h1; - - if (arg->stop) - return; - - for (h = 0; h < 256; h++) { - struct rsvp_session *s; - - for (s = rtnl_dereference(head->ht[h]); s; - s = rtnl_dereference(s->next)) { - for (h1 = 0; h1 <= 16; h1++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h1]); f; - f = rtnl_dereference(f->next)) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(tp, (unsigned long)f, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; - } - } - } - } -} - -static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) -{ - struct rsvp_filter *f = (struct rsvp_filter *)fh; - struct rsvp_session *s; - struct nlattr *nest; - struct tc_rsvp_pinfo pinfo; - - if (f == NULL) - return skb->len; - s = f->sess; - - t->tcm_handle = f->handle; - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst)) - goto nla_put_failure; - pinfo.dpi = s->dpi; - pinfo.spi = f->spi; - pinfo.protocol = s->protocol; - pinfo.tunnelid = s->tunnelid; - pinfo.tunnelhdr = f->tunnelhdr; - pinfo.pad = 0; - if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo)) - goto nla_put_failure; - if (f->res.classid && - nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid)) - goto nla_put_failure; - if (((f->handle >> 8) & 0xFF) != 16 && - nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &f->exts) < 0) - goto nla_put_failure; - - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &f->exts) < 0) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static struct tcf_proto_ops RSVP_OPS __read_mostly = { - .kind = RSVP_ID, - .classify = rsvp_classify, - .init = rsvp_init, - .destroy = rsvp_destroy, - .get = rsvp_get, - .change = rsvp_change, - .delete = rsvp_delete, - .walk = rsvp_walk, - .dump = rsvp_dump, - .owner = THIS_MODULE, -}; - -static int __init init_rsvp(void) -{ - return register_tcf_proto_ops(&RSVP_OPS); -} - -static void __exit exit_rsvp(void) -{ - unregister_tcf_proto_ops(&RSVP_OPS); -} - -module_init(init_rsvp) -module_exit(exit_rsvp) diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c deleted file mode 100644 index dd08aea2aee5..000000000000 --- a/net/sched/cls_rsvp6.c +++ /dev/null @@ -1,28 +0,0 @@ -/* - * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/ipv6.h> -#include <linux/skbuff.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> -#include <net/netlink.h> - -#define RSVP_DST_LEN 4 -#define RSVP_ID "rsvp6" -#define RSVP_OPS cls_rsvp6_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c deleted file mode 100644 index 8a8a58357c39..000000000000 --- a/net/sched/cls_tcindex.c +++ /dev/null @@ -1,638 +0,0 @@ -/* - * net/sched/cls_tcindex.c Packet classifier for skb->tc_index - * - * Written 1998,1999 by Werner Almesberger, EPFL ICA - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/skbuff.h> -#include <linux/errno.h> -#include <linux/slab.h> -#include <net/act_api.h> -#include <net/netlink.h> -#include <net/pkt_cls.h> - -/* - * Passing parameters to the root seems to be done more awkwardly than really - * necessary. At least, u32 doesn't seem to use such dirty hacks. To be - * verified. FIXME. - */ - -#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */ -#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ - - -struct tcindex_filter_result { - struct tcf_exts exts; - struct tcf_result res; - struct rcu_head rcu; -}; - -struct tcindex_filter { - u16 key; - struct tcindex_filter_result result; - struct tcindex_filter __rcu *next; - struct rcu_head rcu; -}; - - -struct tcindex_data { - struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */ - struct tcindex_filter __rcu **h; /* imperfect hash; */ - struct tcf_proto *tp; - u16 mask; /* AND key with mask */ - u32 shift; /* shift ANDed key to the right */ - u32 hash; /* hash table size; 0 if undefined */ - u32 alloc_hash; /* allocated size */ - u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_head rcu; -}; - -static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) -{ - return tcf_exts_is_predicative(&r->exts) || r->res.classid; -} - -static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, - u16 key) -{ - if (p->perfect) { - struct tcindex_filter_result *f = p->perfect + key; - - return tcindex_filter_is_set(f) ? f : NULL; - } else if (p->h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *f; - - fp = &p->h[key % p->hash]; - for (f = rcu_dereference_bh_rtnl(*fp); - f; - fp = &f->next, f = rcu_dereference_bh_rtnl(*fp)) - if (f->key == key) - return &f->result; - } - - return NULL; -} - - -static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct tcindex_data *p = rcu_dereference_bh(tp->root); - struct tcindex_filter_result *f; - int key = (skb->tc_index & p->mask) >> p->shift; - - pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n", - skb, tp, res, p); - - f = tcindex_lookup(p, key); - if (!f) { - if (!p->fall_through) - return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(tp->q->handle), key); - res->class = 0; - pr_debug("alg 0x%x\n", res->classid); - return 0; - } - *res = f->res; - pr_debug("map 0x%x\n", res->classid); - - return tcf_exts_exec(skb, &f->exts, res); -} - - -static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r; - - pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); - if (p->perfect && handle >= p->alloc_hash) - return 0; - r = tcindex_lookup(p, handle); - return r && tcindex_filter_is_set(r) ? (unsigned long) r : 0UL; -} - -static int tcindex_init(struct tcf_proto *tp) -{ - struct tcindex_data *p; - - pr_debug("tcindex_init(tp %p)\n", tp); - p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL); - if (!p) - return -ENOMEM; - - p->mask = 0xffff; - p->hash = DEFAULT_HASH_SIZE; - p->fall_through = 1; - - rcu_assign_pointer(tp->root, p); - return 0; -} - -static void tcindex_destroy_rexts(struct rcu_head *head) -{ - struct tcindex_filter_result *r; - - r = container_of(head, struct tcindex_filter_result, rcu); - tcf_exts_destroy(&r->exts); -} - -static void tcindex_destroy_fexts(struct rcu_head *head) -{ - struct tcindex_filter *f = container_of(head, struct tcindex_filter, - rcu); - - tcf_exts_destroy(&f->result.exts); - kfree(f); -} - -static int tcindex_delete(struct tcf_proto *tp, unsigned long arg, bool *last) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg; - struct tcindex_filter __rcu **walk; - struct tcindex_filter *f = NULL; - - pr_debug("tcindex_delete(tp %p,arg 0x%lx),p %p\n", tp, arg, p); - if (p->perfect) { - if (!r->res.class) - return -ENOENT; - } else { - int i; - - for (i = 0; i < p->hash; i++) { - walk = p->h + i; - for (f = rtnl_dereference(*walk); f; - walk = &f->next, f = rtnl_dereference(*walk)) { - if (&f->result == r) - goto found; - } - } - return -ENOENT; - -found: - rcu_assign_pointer(*walk, rtnl_dereference(f->next)); - } - tcf_unbind_filter(tp, &r->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (f) - call_rcu(&f->rcu, tcindex_destroy_fexts); - else - call_rcu(&r->rcu, tcindex_destroy_rexts); - - *last = false; - return 0; -} - -static int tcindex_destroy_element(struct tcf_proto *tp, - unsigned long arg, - struct tcf_walker *walker) -{ - bool last; - - return tcindex_delete(tp, arg, &last); -} - -static void __tcindex_destroy(struct rcu_head *head) -{ - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); - - kfree(p->perfect); - kfree(p->h); - kfree(p); -} - -static inline int -valid_perfect_hash(struct tcindex_data *p) -{ - return p->hash > (p->mask >> p->shift); -} - -static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { - [TCA_TCINDEX_HASH] = { .type = NLA_U32 }, - [TCA_TCINDEX_MASK] = { .type = NLA_U16 }, - [TCA_TCINDEX_SHIFT] = { .type = NLA_U32 }, - [TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 }, - [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, -}; - -static int tcindex_filter_result_init(struct tcindex_filter_result *r) -{ - memset(r, 0, sizeof(*r)); - return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); -} - -static void __tcindex_partial_destroy(struct rcu_head *head) -{ - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); - - kfree(p->perfect); - kfree(p); -} - -static void tcindex_free_perfect_hash(struct tcindex_data *cp) -{ - int i; - - for (i = 0; i < cp->hash; i++) - tcf_exts_destroy(&cp->perfect[i].exts); - kfree(cp->perfect); -} - -static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) -{ - int i, err = 0; - - cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL); - if (!cp->perfect) - return -ENOMEM; - - for (i = 0; i < cp->hash; i++) { - err = tcf_exts_init(&cp->perfect[i].exts, - TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - goto errout; - } - - return 0; - -errout: - tcindex_free_perfect_hash(cp); - return err; -} - -static int -tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, - u32 handle, struct tcindex_data *p, - struct tcindex_filter_result *r, struct nlattr **tb, - struct nlattr *est, bool ovr) -{ - struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_filter_result cr; - struct tcindex_data *cp = NULL, *oldp; - struct tcindex_filter *f = NULL; /* make gcc behave */ - int err, balloc = 0; - struct tcf_exts e; - - err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - - err = -ENOMEM; - /* tcindex_data attributes must look atomic to classifier/lookup so - * allocate new tcindex data and RCU assign it onto root. Keeping - * perfect hash and hash pointers from old data. - */ - cp = kzalloc(sizeof(*cp), GFP_KERNEL); - if (!cp) - goto errout; - - cp->mask = p->mask; - cp->shift = p->shift; - cp->hash = p->hash; - cp->alloc_hash = p->alloc_hash; - cp->fall_through = p->fall_through; - cp->tp = tp; - - if (p->perfect) { - int i; - - if (tcindex_alloc_perfect_hash(cp) < 0) - goto errout; - for (i = 0; i < cp->hash; i++) - cp->perfect[i].res = p->perfect[i].res; - balloc = 1; - } - cp->h = p->h; - - err = tcindex_filter_result_init(&new_filter_result); - if (err < 0) - goto errout1; - err = tcindex_filter_result_init(&cr); - if (err < 0) - goto errout1; - if (old_r) - cr.res = r->res; - - if (tb[TCA_TCINDEX_HASH]) - cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); - - if (tb[TCA_TCINDEX_MASK]) - cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); - - if (tb[TCA_TCINDEX_SHIFT]) - cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); - - err = -EBUSY; - - /* Hash already allocated, make sure that we still meet the - * requirements for the allocated hash. - */ - if (cp->perfect) { - if (!valid_perfect_hash(cp) || - cp->hash > cp->alloc_hash) - goto errout_alloc; - } else if (cp->h && cp->hash != cp->alloc_hash) { - goto errout_alloc; - } - - err = -EINVAL; - if (tb[TCA_TCINDEX_FALL_THROUGH]) - cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - - if (!cp->hash) { - /* Hash not specified, use perfect hash if the upper limit - * of the hashing index is below the threshold. - */ - if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) - cp->hash = (cp->mask >> cp->shift) + 1; - else - cp->hash = DEFAULT_HASH_SIZE; - } - - if (!cp->perfect && !cp->h) - cp->alloc_hash = cp->hash; - - /* Note: this could be as restrictive as if (handle & ~(mask >> shift)) - * but then, we'd fail handles that may become valid after some future - * mask change. While this is extremely unlikely to ever matter, - * the check below is safer (and also more backwards-compatible). - */ - if (cp->perfect || valid_perfect_hash(cp)) - if (handle >= cp->alloc_hash) - goto errout_alloc; - - - err = -ENOMEM; - if (!cp->perfect && !cp->h) { - if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(cp) < 0) - goto errout_alloc; - balloc = 1; - } else { - struct tcindex_filter __rcu **hash; - - hash = kcalloc(cp->hash, - sizeof(struct tcindex_filter *), - GFP_KERNEL); - - if (!hash) - goto errout_alloc; - - cp->h = hash; - balloc = 2; - } - } - - if (cp->perfect) - r = cp->perfect + handle; - else - r = tcindex_lookup(cp, handle) ? : &new_filter_result; - - if (r == &new_filter_result) { - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (!f) - goto errout_alloc; - f->key = handle; - f->next = NULL; - err = tcindex_filter_result_init(&f->result); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - if (tb[TCA_TCINDEX_CLASSID]) { - cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr.res, base); - } - - if (old_r) - tcf_exts_change(tp, &r->exts, &e); - else - tcf_exts_change(tp, &cr.exts, &e); - - if (old_r && old_r != r) { - err = tcindex_filter_result_init(old_r); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - oldp = p; - r->res = cr.res; - rcu_assign_pointer(tp->root, cp); - - if (r == &new_filter_result) { - struct tcindex_filter *nfp; - struct tcindex_filter __rcu **fp; - - tcf_exts_change(tp, &f->result.exts, &r->exts); - - fp = cp->h + (handle % cp->hash); - for (nfp = rtnl_dereference(*fp); - nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) - ; /* nothing */ - - rcu_assign_pointer(*fp, f); - } - - if (oldp) - call_rcu(&oldp->rcu, __tcindex_partial_destroy); - return 0; - -errout_alloc: - if (balloc == 1) - tcindex_free_perfect_hash(cp); - else if (balloc == 2) - kfree(cp->h); -errout1: - tcf_exts_destroy(&cr.exts); - tcf_exts_destroy(&new_filter_result.exts); -errout: - kfree(cp); - tcf_exts_destroy(&e); - return err; -} - -static int -tcindex_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) -{ - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg; - int err; - - pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p," - "p %p,r %p,*arg 0x%lx\n", - tp, handle, tca, arg, opt, p, r, arg ? *arg : 0L); - - if (!opt) - return 0; - - err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL); - if (err < 0) - return err; - - return tcindex_set_parms(net, tp, base, handle, p, r, tb, - tca[TCA_RATE], ovr); -} - -static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter *f, *next; - int i; - - pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p); - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - if (!p->perfect[i].res.class) - continue; - if (walker->count >= walker->skip) { - if (walker->fn(tp, - (unsigned long) (p->perfect+i), walker) - < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } - if (!p->h) - return; - for (i = 0; i < p->hash; i++) { - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - if (walker->count >= walker->skip) { - if (walker->fn(tp, (unsigned long) &f->result, - walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } -} - -static void tcindex_destroy(struct tcf_proto *tp) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcf_walker walker; - - pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - walker.count = 0; - walker.skip = 0; - walker.fn = tcindex_destroy_element; - tcindex_walk(tp, &walker); - - call_rcu(&p->rcu, __tcindex_destroy); -} - - -static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh; - struct nlattr *nest; - - pr_debug("tcindex_dump(tp %p,fh 0x%lx,skb %p,t %p),p %p,r %p\n", - tp, fh, skb, t, p, r); - pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h); - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (!fh) { - t->tcm_handle = ~0; /* whatever ... */ - if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) || - nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) || - nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) || - nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through)) - goto nla_put_failure; - nla_nest_end(skb, nest); - } else { - if (p->perfect) { - t->tcm_handle = r - p->perfect; - } else { - struct tcindex_filter *f; - struct tcindex_filter __rcu **fp; - int i; - - t->tcm_handle = 0; - for (i = 0; !t->tcm_handle && i < p->hash; i++) { - fp = &p->h[i]; - for (f = rtnl_dereference(*fp); - !t->tcm_handle && f; - fp = &f->next, f = rtnl_dereference(*fp)) { - if (&f->result == r) - t->tcm_handle = f->key; - } - } - } - pr_debug("handle = %d\n", t->tcm_handle); - if (r->res.class && - nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &r->exts) < 0) - goto nla_put_failure; - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &r->exts) < 0) - goto nla_put_failure; - } - - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { - .kind = "tcindex", - .classify = tcindex_classify, - .init = tcindex_init, - .destroy = tcindex_destroy, - .get = tcindex_get, - .change = tcindex_change, - .delete = tcindex_delete, - .walk = tcindex_walk, - .dump = tcindex_dump, - .owner = THIS_MODULE, -}; - -static int __init init_tcindex(void) -{ - return register_tcf_proto_ops(&cls_tcindex_ops); -} - -static void __exit exit_tcindex(void) -{ - unregister_tcf_proto_ops(&cls_tcindex_ops); -} - -module_init(init_tcindex) -module_exit(exit_tcindex) -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 2d01195153e6..2a1c00048fd6 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_u32.c Ugly (or Universal) 32bit key Packet Classifier. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * The filters are packed to hash tables of key nodes @@ -24,9 +20,6 @@ * pure RSVP doesn't need such a general approach and can use * much simpler (and faster) schemes, sort of cls_rsvp.c. * - * JHS: We should remove the CONFIG_NET_CLS_IND from here - * eventually when the meta match extension is made available - * * nfmark match added by Catalin(ux aka Dino) BOIE <catab at umbrella.ro> */ @@ -40,19 +33,20 @@ #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/bitmap.h> +#include <linux/netdevice.h> +#include <linux/hash.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> -#include <linux/netdevice.h> +#include <linux/idr.h> +#include <net/tc_wrapper.h> struct tc_u_knode { struct tc_u_knode __rcu *next; u32 handle; struct tc_u_hnode __rcu *ht_up; struct tcf_exts exts; -#ifdef CONFIG_NET_CLS_IND int ifindex; -#endif u8 fshift; struct tcf_result res; struct tc_u_hnode __rcu *ht_down; @@ -60,13 +54,13 @@ struct tc_u_knode { struct tc_u32_pcnt __percpu *pf; #endif u32 flags; + unsigned int in_hw_count; #ifdef CONFIG_CLS_U32_MARK u32 val; u32 mask; u32 __percpu *pcpu_success; #endif - struct tcf_proto *tp; - struct rcu_head rcu; + struct rcu_work rwork; /* The 'sel' field MUST be the last field in structure to allow for * tc_u32_keys allocated at end of structure. */ @@ -77,24 +71,37 @@ struct tc_u_hnode { struct tc_u_hnode __rcu *next; u32 handle; u32 prio; - struct tc_u_common *tp_c; - int refcnt; + refcount_t refcnt; unsigned int divisor; + struct idr handle_idr; + bool is_root; struct rcu_head rcu; + u32 flags; /* The 'ht' field MUST be the last field in structure to allow for * more entries allocated at end of structure. */ - struct tc_u_knode __rcu *ht[1]; + struct tc_u_knode __rcu *ht[]; }; struct tc_u_common { struct tc_u_hnode __rcu *hlist; - struct Qdisc *q; - int refcnt; - u32 hgenerator; - struct rcu_head rcu; + void *ptr; + refcount_t refcnt; + struct idr handle_idr; + struct hlist_node hnode; + long knodes; }; +static u32 handle2id(u32 h) +{ + return ((h & 0x80000000) ? ((h >> 20) & 0x7FF) : h); +} + +static u32 id2handle(u32 id) +{ + return (id | 0x800U) << 20; +} + static inline unsigned int u32_hash_fold(__be32 key, const struct tc_u32_sel *sel, u8 fshift) @@ -104,8 +111,9 @@ static inline unsigned int u32_hash_fold(__be32 key, return h; } -static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +TC_INDIRECT_SCOPE int u32_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res) { struct { struct tc_u_knode *knode; @@ -175,12 +183,10 @@ check_terminal: if (n->sel.flags & TC_U32_TERMINAL) { *res = n->res; -#ifdef CONFIG_NET_CLS_IND if (!tcf_match_indev(skb, n->ifindex)) { n = rcu_dereference_bh(n->next); goto next_knode; } -#endif #ifdef CONFIG_CLS_U32_PERF __this_cpu_inc(n->pf->rhit); #endif @@ -289,7 +295,7 @@ out: } -static unsigned long u32_get(struct tcf_proto *tp, u32 handle) +static void *u32_get(struct tcf_proto *tp, u32 handle) { struct tc_u_hnode *ht; struct tc_u_common *tp_c = tp->data; @@ -300,43 +306,74 @@ static unsigned long u32_get(struct tcf_proto *tp, u32 handle) ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle)); if (!ht) - return 0; + return NULL; if (TC_U32_KEY(handle) == 0) - return (unsigned long)ht; + return ht; + + return u32_lookup_key(ht, handle); +} - return (unsigned long)u32_lookup_key(ht, handle); +/* Protected by rtnl lock */ +static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) +{ + int id = idr_alloc_cyclic(&tp_c->handle_idr, ptr, 1, 0x7FF, GFP_KERNEL); + if (id < 0) + return 0; + return id2handle(id); } -static u32 gen_new_htid(struct tc_u_common *tp_c) +static struct hlist_head *tc_u_common_hash; + +#define U32_HASH_SHIFT 10 +#define U32_HASH_SIZE (1 << U32_HASH_SHIFT) + +static void *tc_u_common_ptr(const struct tcf_proto *tp) { - int i = 0x800; + struct tcf_block *block = tp->chain->block; - /* hgenerator only used inside rtnl lock it is safe to increment - * without read _copy_ update semantics + /* The block sharing is currently supported only + * for classless qdiscs. In that case we use block + * for tc_u_common identification. In case the + * block is not shared, block->q is a valid pointer + * and we can use that. That works for classful qdiscs. */ - do { - if (++tp_c->hgenerator == 0x7FF) - tp_c->hgenerator = 1; - } while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); + if (tcf_block_shared(block)) + return block; + else + return block->q; +} - return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0; +static struct hlist_head *tc_u_hash(void *key) +{ + return tc_u_common_hash + hash_ptr(key, U32_HASH_SHIFT); +} + +static struct tc_u_common *tc_u_common_find(void *key) +{ + struct tc_u_common *tc; + hlist_for_each_entry(tc, tc_u_hash(key), hnode) { + if (tc->ptr == key) + return tc; + } + return NULL; } static int u32_init(struct tcf_proto *tp) { struct tc_u_hnode *root_ht; - struct tc_u_common *tp_c; - - tp_c = tp->q->u32_node; + void *key = tc_u_common_ptr(tp); + struct tc_u_common *tp_c = tc_u_common_find(key); - root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL); + root_ht = kzalloc(struct_size(root_ht, ht, 1), GFP_KERNEL); if (root_ht == NULL) return -ENOBUFS; - root_ht->refcnt++; - root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000; + refcount_set(&root_ht->refcnt, 1); + root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); root_ht->prio = tp->prio; + root_ht->is_root = true; + idr_init(&root_ht->handle_idr); if (tp_c == NULL) { tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL); @@ -344,26 +381,38 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } - tp_c->q = tp->q; - tp->q->u32_node = tp_c; + refcount_set(&tp_c->refcnt, 1); + tp_c->ptr = key; + INIT_HLIST_NODE(&tp_c->hnode); + idr_init(&tp_c->handle_idr); + + hlist_add_head(&tp_c->hnode, tc_u_hash(key)); + } else { + refcount_inc(&tp_c->refcnt); } - tp_c->refcnt++; RCU_INIT_POINTER(root_ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, root_ht); - root_ht->tp_c = tp_c; + /* root_ht must be destroyed when tcf_proto is destroyed */ rcu_assign_pointer(tp->root, root_ht); tp->data = tp_c; return 0; } -static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, - bool free_pf) +static void __u32_destroy_key(struct tc_u_knode *n) { + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); + tcf_exts_destroy(&n->exts); - if (n->ht_down) - n->ht_down->refcnt--; + if (ht && refcount_dec_and_test(&ht->refcnt)) + kfree(ht); + kfree(n); +} + +static void u32_destroy_key(struct tc_u_knode *n, bool free_pf) +{ + tcf_exts_put_net(&n->exts); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -372,8 +421,7 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, if (free_pf) free_percpu(n->pcpu_success); #endif - kfree(n); - return 0; + __u32_destroy_key(n); } /* u32_delete_key_rcu should be called when free'ing a copied @@ -384,11 +432,14 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, * this the u32_delete_key_rcu variant does not free the percpu * statistics. */ -static void u32_delete_key_rcu(struct rcu_head *rcu) +static void u32_delete_key_work(struct work_struct *work) { - struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - - u32_destroy_key(key->tp, key, false); + struct tc_u_knode *key = container_of(to_rcu_work(work), + struct tc_u_knode, + rwork); + rtnl_lock(); + u32_destroy_key(key, false); + rtnl_unlock(); } /* u32_delete_key_freepf_rcu is the rcu callback variant @@ -398,15 +449,19 @@ static void u32_delete_key_rcu(struct rcu_head *rcu) * for the variant that should be used with keys return from * u32_init_knode() */ -static void u32_delete_key_freepf_rcu(struct rcu_head *rcu) +static void u32_delete_key_freepf_work(struct work_struct *work) { - struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - - u32_destroy_key(key->tp, key, true); + struct tc_u_knode *key = container_of(to_rcu_work(work), + struct tc_u_knode, + rwork); + rtnl_lock(); + u32_destroy_key(key, true); + rtnl_unlock(); } static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) { + struct tc_u_common *tp_c = tp->data; struct tc_u_knode __rcu **kp; struct tc_u_knode *pkp; struct tc_u_hnode *ht = rtnl_dereference(key->ht_up); @@ -417,9 +472,12 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) kp = &pkp->next, pkp = rtnl_dereference(*kp)) { if (pkp == key) { RCU_INIT_POINTER(*kp, key->next); + tp_c->knodes--; tcf_unbind_filter(tp, &key->res); - call_rcu(&key->rcu, u32_delete_key_freepf_rcu); + idr_remove(&ht->handle_idr, key->handle); + tcf_exts_get_net(&key->exts); + tcf_queue_work(&key->rwork, u32_delete_key_freepf_work); return 0; } } @@ -428,117 +486,107 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) return 0; } -static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) +static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, + struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; - - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; - - if (tc_should_offload(dev, tp, 0)) { - offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; - offload.cls_u32->knode.handle = handle; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); - } + struct tcf_block *block = tp->chain->block; + struct tc_cls_u32_offload cls_u32 = {}; + + tc_cls_common_offload_init(&cls_u32.common, tp, h->flags, extack); + cls_u32.command = TC_CLSU32_DELETE_HNODE; + cls_u32.hnode.divisor = h->divisor; + cls_u32.hnode.handle = h->handle; + cls_u32.hnode.prio = h->prio; + + tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false, true); } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, - u32 flags) + u32 flags, struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; + struct tcf_block *block = tp->chain->block; + struct tc_cls_u32_offload cls_u32 = {}; + bool skip_sw = tc_skip_sw(flags); + bool offloaded = false; int err; - if (!tc_should_offload(dev, tp, flags)) - return tc_skip_sw(flags) ? -EINVAL : 0; - - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; + tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack); + cls_u32.command = TC_CLSU32_NEW_HNODE; + cls_u32.hnode.divisor = h->divisor; + cls_u32.hnode.handle = h->handle; + cls_u32.hnode.prio = h->prio; - offload.cls_u32->command = TC_CLSU32_NEW_HNODE; - offload.cls_u32->hnode.divisor = h->divisor; - offload.cls_u32->hnode.handle = h->handle; - offload.cls_u32->hnode.prio = h->prio; - - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); - if (tc_skip_sw(flags)) + err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw, true); + if (err < 0) { + u32_clear_hw_hnode(tp, h, NULL); return err; + } else if (err > 0) { + offloaded = true; + } + + if (skip_sw && !offloaded) + return -EINVAL; return 0; } -static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, + struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; - - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; - - if (tc_should_offload(dev, tp, 0)) { - offload.cls_u32->command = TC_CLSU32_DELETE_HNODE; - offload.cls_u32->hnode.divisor = h->divisor; - offload.cls_u32->hnode.handle = h->handle; - offload.cls_u32->hnode.prio = h->prio; - - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); - } + struct tcf_block *block = tp->chain->block; + struct tc_cls_u32_offload cls_u32 = {}; + + tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack); + cls_u32.command = TC_CLSU32_DELETE_KNODE; + cls_u32.knode.handle = n->handle; + + tc_setup_cb_destroy(block, tp, TC_SETUP_CLSU32, &cls_u32, false, + &n->flags, &n->in_hw_count, true); } static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, - u32 flags) + u32 flags, struct netlink_ext_ack *extack) { - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); + struct tcf_block *block = tp->chain->block; + struct tc_cls_u32_offload cls_u32 = {}; + bool skip_sw = tc_skip_sw(flags); int err; - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; - - if (!tc_should_offload(dev, tp, flags)) - return tc_skip_sw(flags) ? -EINVAL : 0; - - offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE; - offload.cls_u32->knode.handle = n->handle; - offload.cls_u32->knode.fshift = n->fshift; + tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack); + cls_u32.command = TC_CLSU32_REPLACE_KNODE; + cls_u32.knode.handle = n->handle; + cls_u32.knode.fshift = n->fshift; #ifdef CONFIG_CLS_U32_MARK - offload.cls_u32->knode.val = n->val; - offload.cls_u32->knode.mask = n->mask; + cls_u32.knode.val = n->val; + cls_u32.knode.mask = n->mask; #else - offload.cls_u32->knode.val = 0; - offload.cls_u32->knode.mask = 0; + cls_u32.knode.val = 0; + cls_u32.knode.mask = 0; #endif - offload.cls_u32->knode.sel = &n->sel; - offload.cls_u32->knode.exts = &n->exts; + cls_u32.knode.sel = &n->sel; + cls_u32.knode.res = &n->res; + cls_u32.knode.exts = &n->exts; if (n->ht_down) - offload.cls_u32->knode.link_handle = n->ht_down->handle; - - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); + cls_u32.knode.link_handle = ht->handle; - if (!err) - n->flags |= TCA_CLS_FLAGS_IN_HW; - - if (tc_skip_sw(flags)) + err = tc_setup_cb_add(block, tp, TC_SETUP_CLSU32, &cls_u32, skip_sw, + &n->flags, &n->in_hw_count, true); + if (err) { + u32_remove_hw_knode(tp, n, NULL); return err; + } + + if (skip_sw && !(n->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; return 0; } -static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) +static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + struct netlink_ext_ack *extack) { + struct tc_u_common *tp_c = tp->data; struct tc_u_knode *n; unsigned int h; @@ -546,29 +594,35 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) while ((n = rtnl_dereference(ht->ht[h])) != NULL) { RCU_INIT_POINTER(ht->ht[h], rtnl_dereference(n->next)); + tp_c->knodes--; tcf_unbind_filter(tp, &n->res); - u32_remove_hw_knode(tp, n->handle); - call_rcu(&n->rcu, u32_delete_key_freepf_rcu); + u32_remove_hw_knode(tp, n, extack); + idr_remove(&ht->handle_idr, n->handle); + if (tcf_exts_get_net(&n->exts)) + tcf_queue_work(&n->rwork, u32_delete_key_freepf_work); + else + u32_destroy_key(n, true); } } } -static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) +static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode __rcu **hn; struct tc_u_hnode *phn; - WARN_ON(ht->refcnt); - - u32_clear_hnode(tp, ht); + u32_clear_hnode(tp, ht, extack); hn = &tp_c->hlist; for (phn = rtnl_dereference(*hn); phn; hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { - u32_clear_hw_hnode(tp, ht); + u32_clear_hw_hnode(tp, ht, extack); + idr_destroy(&ht->handle_idr); + idr_remove(&tp_c->handle_idr, handle2id(ht->handle)); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -578,133 +632,83 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) return -ENOENT; } -static bool ht_empty(struct tc_u_hnode *ht) -{ - unsigned int h; - - for (h = 0; h <= ht->divisor; h++) - if (rcu_access_pointer(ht->ht[h])) - return false; - - return true; -} - -static void u32_destroy(struct tcf_proto *tp) +static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); WARN_ON(root_ht == NULL); - if (root_ht && --root_ht->refcnt == 0) - u32_destroy_hnode(tp, root_ht); + if (root_ht && refcount_dec_and_test(&root_ht->refcnt)) + u32_destroy_hnode(tp, root_ht, extack); - if (--tp_c->refcnt == 0) { + if (refcount_dec_and_test(&tp_c->refcnt)) { struct tc_u_hnode *ht; - tp->q->u32_node = NULL; - - for (ht = rtnl_dereference(tp_c->hlist); - ht; - ht = rtnl_dereference(ht->next)) { - ht->refcnt--; - u32_clear_hnode(tp, ht); - } + hlist_del(&tp_c->hnode); while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) { + u32_clear_hnode(tp, ht, extack); RCU_INIT_POINTER(tp_c->hlist, ht->next); - kfree_rcu(ht, rcu); + + /* u32_destroy_key() will later free ht for us, if it's + * still referenced by some knode + */ + if (refcount_dec_and_test(&ht->refcnt)) + kfree_rcu(ht, rcu); } + idr_destroy(&tp_c->handle_idr); kfree(tp_c); } tp->data = NULL; } -static int u32_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, + bool rtnl_held, struct netlink_ext_ack *extack) { - struct tc_u_hnode *ht = (struct tc_u_hnode *)arg; - struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); + struct tc_u_hnode *ht = arg; struct tc_u_common *tp_c = tp->data; int ret = 0; - if (ht == NULL) - goto out; - if (TC_U32_KEY(ht->handle)) { - u32_remove_hw_knode(tp, ht->handle); + u32_remove_hw_knode(tp, (struct tc_u_knode *)ht, extack); ret = u32_delete_key(tp, (struct tc_u_knode *)ht); goto out; } - if (root_ht == ht) + if (ht->is_root) { + NL_SET_ERR_MSG_MOD(extack, "Not allowed to delete root node"); return -EINVAL; + } - if (ht->refcnt == 1) { - ht->refcnt--; - u32_destroy_hnode(tp, ht); + if (refcount_dec_if_one(&ht->refcnt)) { + u32_destroy_hnode(tp, ht, extack); } else { + NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); return -EBUSY; } out: - *last = true; - if (root_ht) { - if (root_ht->refcnt > 1) { - *last = false; - goto ret; - } - if (root_ht->refcnt == 1) { - if (!ht_empty(root_ht)) { - *last = false; - goto ret; - } - } - } - - if (tp_c->refcnt > 1) { - *last = false; - goto ret; - } - - if (tp_c->refcnt == 1) { - struct tc_u_hnode *ht; - - for (ht = rtnl_dereference(tp_c->hlist); - ht; - ht = rtnl_dereference(ht->next)) - if (!ht_empty(ht)) { - *last = false; - break; - } - } - -ret: + *last = refcount_read(&tp_c->refcnt) == 1 && tp_c->knodes == 0; return ret; } -#define NR_U32_NODE (1<<12) -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) { - struct tc_u_knode *n; - unsigned long i; - unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long), - GFP_KERNEL); - if (!bitmap) - return handle | 0xFFF; - - for (n = rtnl_dereference(ht->ht[TC_U32_HASH(handle)]); - n; - n = rtnl_dereference(n->next)) - set_bit(TC_U32_NODE(n->handle), bitmap); - - i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800); - if (i >= NR_U32_NODE) - i = find_next_zero_bit(bitmap, NR_U32_NODE, 1); + u32 index = htid | 0x800; + u32 max = htid | 0xFFF; + + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { + index = htid + 1; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, + GFP_KERNEL)) + index = max; + } - kfree(bitmap); - return handle | (i >= NR_U32_NODE ? 0xFFF : i); + return index; } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -718,63 +722,74 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; +static void u32_unbind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) + tcf_unbind_filter(tp, &n->res); +} + +static void u32_bind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + unsigned long base, struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) { + n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); + tcf_bind_filter(tp, &n->res, base); + } +} + static int u32_set_parms(struct net *net, struct tcf_proto *tp, - unsigned long base, struct tc_u_hnode *ht, struct tc_u_knode *n, struct nlattr **tb, - struct nlattr *est, bool ovr) + struct nlattr *est, u32 flags, u32 fl_flags, + struct netlink_ext_ack *extack) { - struct tcf_exts e; - int err; + int err, ifindex = -1; - err = tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE); + err = tcf_exts_validate_ex(net, tp, tb, est, &n->exts, flags, + fl_flags, extack); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - err = -EINVAL; + if (tb[TCA_U32_INDEV]) { + ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); + if (ifindex < 0) + return -EINVAL; + } + if (tb[TCA_U32_LINK]) { u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; - if (TC_U32_KEY(handle)) - goto errout; + if (TC_U32_KEY(handle)) { + NL_SET_ERR_MSG_MOD(extack, "u32 Link handle must be a hash table"); + return -EINVAL; + } if (handle) { - ht_down = u32_lookup_ht(ht->tp_c, handle); + ht_down = u32_lookup_ht(tp->data, handle); - if (ht_down == NULL) - goto errout; - ht_down->refcnt++; + if (!ht_down) { + NL_SET_ERR_MSG_MOD(extack, "Link hash table not found"); + return -EINVAL; + } + if (ht_down->is_root) { + NL_SET_ERR_MSG_MOD(extack, "Not linking to root node"); + return -EINVAL; + } + refcount_inc(&ht_down->refcnt); } ht_old = rtnl_dereference(n->ht_down); rcu_assign_pointer(n->ht_down, ht_down); if (ht_old) - ht_old->refcnt--; - } - if (tb[TCA_U32_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); - tcf_bind_filter(tp, &n->res, base); + refcount_dec(&ht_old->refcnt); } -#ifdef CONFIG_NET_CLS_IND - if (tb[TCA_U32_INDEV]) { - int ret; - ret = tcf_change_indev(net, tb[TCA_U32_INDEV]); - if (ret < 0) - goto errout; - n->ifindex = ret; - } -#endif - tcf_exts_change(tp, &n->exts, &e); + if (ifindex >= 0) + n->ifindex = ifindex; return 0; -errout: - tcf_exts_destroy(&e); - return err; } static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, @@ -799,19 +814,19 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, if (pins->handle == n->handle) break; + idr_replace(&ht->handle_idr, n, n->handle); RCU_INIT_POINTER(n->next, pins->next); rcu_assign_pointer(*ins, n); } -static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, +static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, struct tc_u_knode *n) { - struct tc_u_knode *new; + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct tc_u32_sel *s = &n->sel; + struct tc_u_knode *new; - new = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), - GFP_KERNEL); - + new = kzalloc(struct_size(new, sel.keys, s->nkeys), GFP_KERNEL); if (!new) return NULL; @@ -819,17 +834,10 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, new->handle = n->handle; RCU_INIT_POINTER(new->ht_up, n->ht_up); -#ifdef CONFIG_NET_CLS_IND new->ifindex = n->ifindex; -#endif new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; - RCU_INIT_POINTER(new->ht_down, n->ht_down); - - /* bump reference count as long as we hold pointer to structure */ - if (new->ht_down) - new->ht_down->refcnt++; + RCU_INIT_POINTER(new->ht_down, ht); #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update @@ -845,20 +853,24 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, /* Similarly success statistics must be moved as pointers */ new->pcpu_success = n->pcpu_success; #endif - new->tp = tp; - memcpy(&new->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); + memcpy(&new->sel, s, struct_size(s, keys, s->nkeys)); - if (tcf_exts_init(&new->exts, TCA_U32_ACT, TCA_U32_POLICE)) { + if (tcf_exts_init(&new->exts, net, TCA_U32_ACT, TCA_U32_POLICE)) { kfree(new); return NULL; } + /* bump reference count as long as we hold pointer to structure */ + if (ht) + refcount_inc(&ht->refcnt); + return new; } static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) + struct nlattr **tca, void **arg, u32 flags, + struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; @@ -866,93 +878,137 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct tc_u32_sel *s; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; - u32 htid, flags = 0; + u32 htid, userflags = 0; + size_t sel_size; int err; -#ifdef CONFIG_CLS_U32_PERF - size_t size; -#endif - if (opt == NULL) - return handle ? -EINVAL : 0; + if (!opt) { + if (handle) { + NL_SET_ERR_MSG_MOD(extack, "Filter handle requires options"); + return -EINVAL; + } else { + return 0; + } + } - err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_U32_MAX, opt, u32_policy, + extack); if (err < 0) return err; if (tb[TCA_U32_FLAGS]) { - flags = nla_get_u32(tb[TCA_U32_FLAGS]); - if (!tc_flags_valid(flags)) + userflags = nla_get_u32(tb[TCA_U32_FLAGS]); + if (!tc_flags_valid(userflags)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid filter flags"); return -EINVAL; + } } - n = (struct tc_u_knode *)*arg; + n = *arg; if (n) { struct tc_u_knode *new; - if (TC_U32_KEY(n->handle) == 0) + if (TC_U32_KEY(n->handle) == 0) { + NL_SET_ERR_MSG_MOD(extack, "Key node id cannot be zero"); return -EINVAL; + } - if (n->flags != flags) + if ((n->flags ^ userflags) & + ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW)) { + NL_SET_ERR_MSG_MOD(extack, "Key node flags do not match passed flags"); return -EINVAL; + } - new = u32_init_knode(tp, n); + new = u32_init_knode(net, tp, n); if (!new) return -ENOMEM; - err = u32_set_parms(net, tp, base, - rtnl_dereference(n->ht_up), new, tb, - tca[TCA_RATE], ovr); + err = u32_set_parms(net, tp, new, tb, tca[TCA_RATE], + flags, new->flags, extack); if (err) { - u32_destroy_key(tp, new, false); + __u32_destroy_key(new); return err; } - err = u32_replace_hw_knode(tp, new, flags); + u32_bind_filter(tp, new, base, tb); + + err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { - u32_destroy_key(tp, new, false); + u32_unbind_filter(tp, new, tb); + + if (tb[TCA_U32_LINK]) { + struct tc_u_hnode *ht_old; + + ht_old = rtnl_dereference(n->ht_down); + if (ht_old) + refcount_inc(&ht_old->refcnt); + } + __u32_destroy_key(new); return err; } if (!tc_in_hw(new->flags)) new->flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, new->flags); + u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); - call_rcu(&n->rcu, u32_delete_key_rcu); + tcf_exts_get_net(&n->exts); + tcf_queue_work(&n->rwork, u32_delete_key_work); return 0; } if (tb[TCA_U32_DIVISOR]) { unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); - if (--divisor > 0x100) + if (!is_power_of_2(divisor)) { + NL_SET_ERR_MSG_MOD(extack, "Divisor is not a power of 2"); return -EINVAL; - if (TC_U32_KEY(handle)) + } + if (divisor-- > 0x100) { + NL_SET_ERR_MSG_MOD(extack, "Exceeded maximum 256 hash buckets"); return -EINVAL; - if (handle == 0) { - handle = gen_new_htid(tp->data); - if (handle == 0) - return -ENOMEM; } - ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); + if (TC_U32_KEY(handle)) { + NL_SET_ERR_MSG_MOD(extack, "Divisor can only be used on a hash table"); + return -EINVAL; + } + ht = kzalloc(struct_size(ht, ht, divisor + 1), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; - ht->tp_c = tp_c; - ht->refcnt = 1; + if (handle == 0) { + handle = gen_new_htid(tp->data, ht); + if (handle == 0) { + kfree(ht); + return -ENOMEM; + } + } else { + err = idr_alloc_u32(&tp_c->handle_idr, ht, &handle, + handle, GFP_KERNEL); + if (err) { + kfree(ht); + return err; + } + } + refcount_set(&ht->refcnt, 1); ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; + idr_init(&ht->handle_idr); + ht->flags = userflags; - err = u32_replace_hw_hnode(tp, ht, flags); + err = u32_replace_hw_hnode(tp, ht, userflags, extack); if (err) { + idr_remove(&tp_c->handle_idr, handle2id(handle)); kfree(ht); return err; } RCU_INIT_POINTER(ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, ht); - *arg = (unsigned long)ht; + *arg = ht; return 0; } @@ -964,50 +1020,117 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, htid = ht->handle; } else { ht = u32_lookup_ht(tp->data, TC_U32_HTID(htid)); - if (ht == NULL) + if (!ht) { + NL_SET_ERR_MSG_MOD(extack, "Specified hash table not found"); return -EINVAL; + } } } else { ht = rtnl_dereference(tp->root); htid = ht->handle; } - if (ht->divisor < TC_U32_HASH(htid)) + if (ht->divisor < TC_U32_HASH(htid)) { + NL_SET_ERR_MSG_MOD(extack, "Specified hash table buckets exceed configured value"); return -EINVAL; + } + /* At this point, we need to derive the new handle that will be used to + * uniquely map the identity of this table match entry. The + * identity of the entry that we need to construct is 32 bits made of: + * htid(12b):bucketid(8b):node/entryid(12b) + * + * At this point _we have the table(ht)_ in which we will insert this + * entry. We carry the table's id in variable "htid". + * Note that earlier code picked the ht selection either by a) the user + * providing the htid specified via TCA_U32_HASH attribute or b) when + * no such attribute is passed then the root ht, is default to at ID + * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. + * If OTOH the user passed us the htid, they may also pass a bucketid of + * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is + * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be + * passed via the htid, so even if it was non-zero it will be ignored. + * + * We may also have a handle, if the user passed one. The handle also + * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). + * Rule: the bucketid on the handle is ignored even if one was passed; + * rather the value on "htid" is always assumed to be the bucketid. + */ if (handle) { - if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid)) + /* Rule: The htid from handle and tableid from htid must match */ + if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { + NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; - handle = htid | TC_U32_NODE(handle); - } else + } + /* Ok, so far we have a valid htid(12b):bucketid(8b) but we + * need to finalize the table entry identification with the last + * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for + * entries. Rule: nodeid of 0 is reserved only for tables(see + * earlier code which processes TC_U32_DIVISOR attribute). + * Rule: The nodeid can only be derived from the handle (and not + * htid). + * Rule: if the handle specified zero for the node id example + * 0x60000000, then pick a new nodeid from the pool of IDs + * this hash table has been allocating from. + * If OTOH it is specified (i.e for example the user passed a + * handle such as 0x60000123), then we use it generate our final + * handle which is used to uniquely identify the match entry. + */ + if (!TC_U32_NODE(handle)) { + handle = gen_new_kid(ht, htid); + } else { + handle = htid | TC_U32_NODE(handle); + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, + handle, GFP_KERNEL); + if (err) + return err; + } + } else { + /* The user did not give us a handle; lets just generate one + * from the table's pool of nodeids. + */ handle = gen_new_kid(ht, htid); + } - if (tb[TCA_U32_SEL] == NULL) - return -EINVAL; + if (tb[TCA_U32_SEL] == NULL) { + NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); + err = -EINVAL; + goto erridr; + } s = nla_data(tb[TCA_U32_SEL]); + sel_size = struct_size(s, keys, s->nkeys); + if (nla_len(tb[TCA_U32_SEL]) < sel_size) { + err = -EINVAL; + goto erridr; + } - n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); - if (n == NULL) - return -ENOBUFS; + n = kzalloc(struct_size(n, sel.keys, s->nkeys), GFP_KERNEL); + if (n == NULL) { + err = -ENOBUFS; + goto erridr; + } #ifdef CONFIG_CLS_U32_PERF - size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64); - n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt)); + n->pf = __alloc_percpu(struct_size(n->pf, kcnts, s->nkeys), + __alignof__(struct tc_u32_pcnt)); if (!n->pf) { - kfree(n); - return -ENOBUFS; + err = -ENOBUFS; + goto errfree; } #endif - memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); + unsafe_memcpy(&n->sel, s, sel_size, + /* A composite flex-array structure destination, + * which was correctly sized with struct_size(), + * bounds-checked against nla_len(), and allocated + * above. */); RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; - n->flags = flags; - n->tp = tp; + n->flags = userflags; - err = tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); + err = tcf_exts_init(&n->exts, net, TCA_U32_ACT, TCA_U32_POLICE); if (err < 0) goto errout; @@ -1027,18 +1150,24 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr); + err = u32_set_parms(net, tp, n, tb, tca[TCA_RATE], + flags, n->flags, extack); + + u32_bind_filter(tp, n, base, tb); + if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; - err = u32_replace_hw_knode(tp, n, flags); + err = u32_replace_hw_knode(tp, n, flags, extack); if (err) - goto errhw; + goto errunbind; if (!tc_in_hw(n->flags)) n->flags |= TCA_CLS_FLAGS_NOT_IN_HW; + tcf_proto_update_usesw(tp, n->flags); + ins = &ht->ht[TC_U32_HASH(handle)]; for (pins = rtnl_dereference(*ins); pins; ins = &pins->next, pins = rtnl_dereference(*ins)) @@ -1047,11 +1176,14 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); - *arg = (unsigned long)n; + tp_c->knodes++; + *arg = n; return 0; } -errhw: +errunbind: + u32_unbind_filter(tp, n, tb); + #ifdef CONFIG_CLS_U32_MARK free_percpu(n->pcpu_success); #endif @@ -1059,13 +1191,17 @@ errhw: errout: tcf_exts_destroy(&n->exts); #ifdef CONFIG_CLS_U32_PERF +errfree: free_percpu(n->pf); #endif kfree(n); +erridr: + idr_remove(&ht->handle_idr, handle); return err; } -static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; @@ -1080,35 +1216,134 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; - if (arg->count >= arg->skip) { - if (arg->fn(tp, (unsigned long)ht, arg) < 0) { - arg->stop = 1; - return; + + if (!tc_cls_stats_dump(tp, arg, ht)) + return; + + for (h = 0; h <= ht->divisor; h++) { + for (n = rtnl_dereference(ht->ht[h]); + n; + n = rtnl_dereference(n->next)) { + if (!tc_cls_stats_dump(tp, arg, n)) + return; } } - arg->count++; + } +} + +static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + bool add, flow_setup_cb_t *cb, void *cb_priv, + struct netlink_ext_ack *extack) +{ + struct tc_cls_u32_offload cls_u32 = {}; + int err; + + tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, extack); + cls_u32.command = add ? TC_CLSU32_NEW_HNODE : TC_CLSU32_DELETE_HNODE; + cls_u32.hnode.divisor = ht->divisor; + cls_u32.hnode.handle = ht->handle; + cls_u32.hnode.prio = ht->prio; + + err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv); + if (err && add && tc_skip_sw(ht->flags)) + return err; + + return 0; +} + +static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, + bool add, flow_setup_cb_t *cb, void *cb_priv, + struct netlink_ext_ack *extack) +{ + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); + struct tcf_block *block = tp->chain->block; + struct tc_cls_u32_offload cls_u32 = {}; + + tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack); + cls_u32.command = add ? + TC_CLSU32_REPLACE_KNODE : TC_CLSU32_DELETE_KNODE; + cls_u32.knode.handle = n->handle; + + if (add) { + cls_u32.knode.fshift = n->fshift; +#ifdef CONFIG_CLS_U32_MARK + cls_u32.knode.val = n->val; + cls_u32.knode.mask = n->mask; +#else + cls_u32.knode.val = 0; + cls_u32.knode.mask = 0; +#endif + cls_u32.knode.sel = &n->sel; + cls_u32.knode.res = &n->res; + cls_u32.knode.exts = &n->exts; + if (n->ht_down) + cls_u32.knode.link_handle = ht->handle; + } + + return tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSU32, + &cls_u32, cb_priv, &n->flags, + &n->in_hw_count); +} + +static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct tc_u_common *tp_c = tp->data; + struct tc_u_hnode *ht; + struct tc_u_knode *n; + unsigned int h; + int err; + + for (ht = rtnl_dereference(tp_c->hlist); + ht; + ht = rtnl_dereference(ht->next)) { + if (ht->prio != tp->prio) + continue; + + /* When adding filters to a new dev, try to offload the + * hashtable first. When removing, do the filters before the + * hashtable. + */ + if (add && !tc_skip_hw(ht->flags)) { + err = u32_reoffload_hnode(tp, ht, add, cb, cb_priv, + extack); + if (err) + return err; + } + for (h = 0; h <= ht->divisor; h++) { for (n = rtnl_dereference(ht->ht[h]); n; n = rtnl_dereference(n->next)) { - if (arg->count < arg->skip) { - arg->count++; + if (tc_skip_hw(n->flags)) continue; - } - if (arg->fn(tp, (unsigned long)n, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; + + err = u32_reoffload_knode(tp, n, add, cb, + cb_priv, extack); + if (err) + return err; } } + + if (!add && !tc_skip_hw(ht->flags)) + u32_reoffload_hnode(tp, ht, add, cb, cb_priv, extack); } + + return 0; } -static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) +static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { - struct tc_u_knode *n = (struct tc_u_knode *)fh; + struct tc_u_knode *n = fh; + + tc_cls_bind_class(classid, cl, q, &n->res, base); +} + +static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) +{ + struct tc_u_knode *n = fh; struct tc_u_hnode *ht_up, *ht_down; struct nlattr *nest; @@ -1117,12 +1352,12 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, t->tcm_handle = n->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (TC_U32_KEY(n->handle) == 0) { - struct tc_u_hnode *ht = (struct tc_u_hnode *)fh; + struct tc_u_hnode *ht = fh; u32 divisor = ht->divisor + 1; if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor)) @@ -1133,8 +1368,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, int cpu; #endif - if (nla_put(skb, TCA_U32_SEL, - sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key), + if (nla_put(skb, TCA_U32_SEL, struct_size(&n->sel, keys, n->sel.nkeys), &n->sel)) goto nla_put_failure; @@ -1177,18 +1411,14 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (tcf_exts_dump(skb, &n->exts) < 0) goto nla_put_failure; -#ifdef CONFIG_NET_CLS_IND if (n->ifindex) { struct net_device *dev; dev = __dev_get_by_index(net, n->ifindex); if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name)) goto nla_put_failure; } -#endif #ifdef CONFIG_CLS_U32_PERF - gpf = kzalloc(sizeof(struct tc_u32_pcnt) + - n->sel.nkeys * sizeof(u64), - GFP_KERNEL); + gpf = kzalloc(struct_size(gpf, kcnts, n->sel.nkeys), GFP_KERNEL); if (!gpf) goto nla_put_failure; @@ -1202,9 +1432,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, gpf->kcnts[i] += pf->kcnts[i]; } - if (nla_put_64bit(skb, TCA_U32_PCNT, - sizeof(struct tc_u32_pcnt) + - n->sel.nkeys * sizeof(u64), + if (nla_put_64bit(skb, TCA_U32_PCNT, struct_size(gpf, kcnts, n->sel.nkeys), gpf, TCA_U32_PAD)) { kfree(gpf); goto nla_put_failure; @@ -1234,30 +1462,47 @@ static struct tcf_proto_ops cls_u32_ops __read_mostly = { .change = u32_change, .delete = u32_delete, .walk = u32_walk, + .reoffload = u32_reoffload, .dump = u32_dump, + .bind_class = u32_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("u32"); static int __init init_u32(void) { + int i, ret; + pr_info("u32 classifier\n"); #ifdef CONFIG_CLS_U32_PERF pr_info(" Performance counters on\n"); #endif -#ifdef CONFIG_NET_CLS_IND pr_info(" input device check on\n"); -#endif #ifdef CONFIG_NET_CLS_ACT pr_info(" Actions configured\n"); #endif - return register_tcf_proto_ops(&cls_u32_ops); + tc_u_common_hash = kvmalloc_array(U32_HASH_SIZE, + sizeof(struct hlist_head), + GFP_KERNEL); + if (!tc_u_common_hash) + return -ENOMEM; + + for (i = 0; i < U32_HASH_SIZE; i++) + INIT_HLIST_HEAD(&tc_u_common_hash[i]); + + ret = register_tcf_proto_ops(&cls_u32_ops); + if (ret) + kvfree(tc_u_common_hash); + return ret; } static void __exit exit_u32(void) { unregister_tcf_proto_ops(&cls_u32_ops); + kvfree(tc_u_common_hash); } module_init(init_u32) module_exit(exit_u32) +MODULE_DESCRIPTION("Universal 32bit based TC Classifier"); MODULE_LICENSE("GPL"); diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c index ddd883ca55b2..2d27f91d8441 100644 --- a/net/sched/em_canid.c +++ b/net/sched/em_canid.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * em_canid.c Ematch rule to match CAN frames according to their CAN IDs * - * This program is free software; you can distribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Idea: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> * Copyright: (c) 2011 Czech Technical University in Prague * (c) 2011 Volkswagen Group Research @@ -44,6 +40,7 @@ struct canid_match { /** * em_canid_get_id() - Extracts Can ID out of the sk_buff structure. + * @skb: buffer to extract Can ID from */ static canid_t em_canid_get_id(struct sk_buff *skb) { @@ -102,6 +99,9 @@ static int em_canid_match(struct sk_buff *skb, struct tcf_ematch *m, int i; const struct can_filter *lp; + if (!pskb_may_pull(skb, CAN_MTU)) + return 0; + can_id = em_canid_get_id(skb); if (can_id & CAN_EFF_FLAG) { @@ -225,6 +225,7 @@ static void __exit exit_em_canid(void) tcf_em_unregister(&em_canid_ops); } +MODULE_DESCRIPTION("ematch classifier to match CAN IDs embedded in skb CAN frames"); MODULE_LICENSE("GPL"); module_init(init_em_canid); diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index 1c8360a2752a..48c1bce74f49 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_cmp.c Simple packet data comparison ematch * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> */ @@ -14,7 +10,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/tc_ematch/tc_em_cmp.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/pkt_cls.h> static inline int cmp_needs_transformation(struct tcf_em_cmp *cmp) @@ -26,9 +22,12 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { struct tcf_em_cmp *cmp = (struct tcf_em_cmp *) em->data; - unsigned char *ptr = tcf_get_base_ptr(skb, cmp->layer) + cmp->off; + unsigned char *ptr = tcf_get_base_ptr(skb, cmp->layer); u32 val = 0; + if (!ptr) + return 0; + ptr += cmp->off; if (!tcf_valid_offset(skb, ptr, cmp->align)) return 0; @@ -45,7 +44,7 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em, break; case TCF_EM_ALIGN_U32: - /* Worth checking boundries? The branching seems + /* Worth checking boundaries? The branching seems * to get worse. Visit again. */ val = get_unaligned_be32(ptr); @@ -91,6 +90,7 @@ static void __exit exit_em_cmp(void) tcf_em_unregister(&em_cmp_ops); } +MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data"); MODULE_LICENSE("GPL"); module_init(init_em_cmp); diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index c1b23e3060b8..c95cf86fb431 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/em_ipset.c ipset ematch * * Copyright (c) 2012 Florian Westphal <fw@strlen.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. */ #include <linux/gfp.h> @@ -62,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, }; int ret, network_offset; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): state.pf = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c new file mode 100644 index 000000000000..3650117da47f --- /dev/null +++ b/net/sched/em_ipt.c @@ -0,0 +1,297 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * net/sched/em_ipt.c IPtables matches Ematch + * + * (c) 2018 Eyal Birger <eyal.birger@gmail.com> + */ + +#include <linux/gfp.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/tc_ematch/tc_em_ipt.h> +#include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/pkt_cls.h> + +struct em_ipt_match { + const struct xt_match *match; + u32 hook; + u8 nfproto; + u8 match_data[] __aligned(8); +}; + +struct em_ipt_xt_match { + char *match_name; + int (*validate_match_data)(struct nlattr **tb, u8 mrev); +}; + +static const struct nla_policy em_ipt_policy[TCA_EM_IPT_MAX + 1] = { + [TCA_EM_IPT_MATCH_NAME] = { .type = NLA_STRING, + .len = XT_EXTENSION_MAXNAMELEN }, + [TCA_EM_IPT_MATCH_REVISION] = { .type = NLA_U8 }, + [TCA_EM_IPT_HOOK] = { .type = NLA_U32 }, + [TCA_EM_IPT_NFPROTO] = { .type = NLA_U8 }, + [TCA_EM_IPT_MATCH_DATA] = { .type = NLA_UNSPEC }, +}; + +static int check_match(struct net *net, struct em_ipt_match *im, int mdata_len) +{ + struct xt_mtchk_param mtpar = {}; + union { + struct ipt_entry e4; + struct ip6t_entry e6; + } e = {}; + + mtpar.net = net; + mtpar.table = "filter"; + mtpar.hook_mask = 1 << im->hook; + mtpar.family = im->match->family; + mtpar.match = im->match; + mtpar.entryinfo = &e; + mtpar.matchinfo = (void *)im->match_data; + return xt_check_match(&mtpar, mdata_len, 0, 0); +} + +static int policy_validate_match_data(struct nlattr **tb, u8 mrev) +{ + if (mrev != 0) { + pr_err("only policy match revision 0 supported"); + return -EINVAL; + } + + if (nla_get_u32(tb[TCA_EM_IPT_HOOK]) != NF_INET_PRE_ROUTING) { + pr_err("policy can only be matched on NF_INET_PRE_ROUTING"); + return -EINVAL; + } + + return 0; +} + +static int addrtype_validate_match_data(struct nlattr **tb, u8 mrev) +{ + if (mrev != 1) { + pr_err("only addrtype match revision 1 supported"); + return -EINVAL; + } + + return 0; +} + +static const struct em_ipt_xt_match em_ipt_xt_matches[] = { + { + .match_name = "policy", + .validate_match_data = policy_validate_match_data + }, + { + .match_name = "addrtype", + .validate_match_data = addrtype_validate_match_data + }, + {} +}; + +static struct xt_match *get_xt_match(struct nlattr **tb) +{ + const struct em_ipt_xt_match *m; + struct nlattr *mname_attr; + u8 nfproto, mrev = 0; + int ret; + + mname_attr = tb[TCA_EM_IPT_MATCH_NAME]; + for (m = em_ipt_xt_matches; m->match_name; m++) { + if (!nla_strcmp(mname_attr, m->match_name)) + break; + } + + if (!m->match_name) { + pr_err("Unsupported xt match"); + return ERR_PTR(-EINVAL); + } + + if (tb[TCA_EM_IPT_MATCH_REVISION]) + mrev = nla_get_u8(tb[TCA_EM_IPT_MATCH_REVISION]); + + ret = m->validate_match_data(tb, mrev); + if (ret < 0) + return ERR_PTR(ret); + + nfproto = nla_get_u8(tb[TCA_EM_IPT_NFPROTO]); + return xt_request_find_match(nfproto, m->match_name, mrev); +} + +static int em_ipt_change(struct net *net, void *data, int data_len, + struct tcf_ematch *em) +{ + struct nlattr *tb[TCA_EM_IPT_MAX + 1]; + struct em_ipt_match *im = NULL; + struct xt_match *match; + int mdata_len, ret; + u8 nfproto; + + ret = nla_parse_deprecated(tb, TCA_EM_IPT_MAX, data, data_len, + em_ipt_policy, NULL); + if (ret < 0) + return ret; + + if (!tb[TCA_EM_IPT_HOOK] || !tb[TCA_EM_IPT_MATCH_NAME] || + !tb[TCA_EM_IPT_MATCH_DATA] || !tb[TCA_EM_IPT_NFPROTO]) + return -EINVAL; + + nfproto = nla_get_u8(tb[TCA_EM_IPT_NFPROTO]); + switch (nfproto) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + break; + default: + return -EINVAL; + } + + match = get_xt_match(tb); + if (IS_ERR(match)) { + pr_err("unable to load match\n"); + return PTR_ERR(match); + } + + mdata_len = XT_ALIGN(nla_len(tb[TCA_EM_IPT_MATCH_DATA])); + im = kzalloc(sizeof(*im) + mdata_len, GFP_KERNEL); + if (!im) { + ret = -ENOMEM; + goto err; + } + + im->match = match; + im->hook = nla_get_u32(tb[TCA_EM_IPT_HOOK]); + im->nfproto = nfproto; + nla_memcpy(im->match_data, tb[TCA_EM_IPT_MATCH_DATA], mdata_len); + + ret = check_match(net, im, mdata_len); + if (ret) + goto err; + + em->datalen = sizeof(*im) + mdata_len; + em->data = (unsigned long)im; + return 0; + +err: + kfree(im); + module_put(match->me); + return ret; +} + +static void em_ipt_destroy(struct tcf_ematch *em) +{ + struct em_ipt_match *im = (void *)em->data; + + if (!im) + return; + + if (im->match->destroy) { + struct xt_mtdtor_param par = { + .net = em->net, + .match = im->match, + .matchinfo = im->match_data, + .family = im->match->family + }; + im->match->destroy(&par); + } + module_put(im->match->me); + kfree(im); +} + +static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, + struct tcf_pkt_info *info) +{ + const struct em_ipt_match *im = (const void *)em->data; + struct xt_action_param acpar = {}; + struct net_device *indev = NULL; + u8 nfproto = im->match->family; + struct nf_hook_state state; + int ret; + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + return 0; + if (nfproto == NFPROTO_UNSPEC) + nfproto = NFPROTO_IPV4; + break; + case htons(ETH_P_IPV6): + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + return 0; + if (nfproto == NFPROTO_UNSPEC) + nfproto = NFPROTO_IPV6; + break; + default: + return 0; + } + + rcu_read_lock(); + + if (skb->skb_iif) + indev = dev_get_by_index_rcu(em->net, skb->skb_iif); + + nf_hook_state_init(&state, im->hook, nfproto, + indev ?: skb->dev, skb->dev, NULL, em->net, NULL); + + acpar.match = im->match; + acpar.matchinfo = im->match_data; + acpar.state = &state; + + ret = im->match->match(skb, &acpar); + + rcu_read_unlock(); + return ret; +} + +static int em_ipt_dump(struct sk_buff *skb, struct tcf_ematch *em) +{ + struct em_ipt_match *im = (void *)em->data; + + if (nla_put_string(skb, TCA_EM_IPT_MATCH_NAME, im->match->name) < 0) + return -EMSGSIZE; + if (nla_put_u32(skb, TCA_EM_IPT_HOOK, im->hook) < 0) + return -EMSGSIZE; + if (nla_put_u8(skb, TCA_EM_IPT_MATCH_REVISION, im->match->revision) < 0) + return -EMSGSIZE; + if (nla_put_u8(skb, TCA_EM_IPT_NFPROTO, im->nfproto) < 0) + return -EMSGSIZE; + if (nla_put(skb, TCA_EM_IPT_MATCH_DATA, + im->match->usersize ?: im->match->matchsize, + im->match_data) < 0) + return -EMSGSIZE; + + return 0; +} + +static struct tcf_ematch_ops em_ipt_ops = { + .kind = TCF_EM_IPT, + .change = em_ipt_change, + .destroy = em_ipt_destroy, + .match = em_ipt_match, + .dump = em_ipt_dump, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_ipt_ops.link) +}; + +static int __init init_em_ipt(void) +{ + return tcf_em_register(&em_ipt_ops); +} + +static void __exit exit_em_ipt(void) +{ + tcf_em_unregister(&em_ipt_ops); +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Eyal Birger <eyal.birger@gmail.com>"); +MODULE_DESCRIPTION("TC extended match for IPtables matches"); + +module_init(init_em_ipt); +module_exit(exit_em_ipt); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_IPT); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index d6e97115500b..3f2e707a11d1 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_meta.c Metadata ematch * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> * * ========================================================================== @@ -48,7 +44,7 @@ * be provided for non-numeric types. * * Additionally, type dependent modifiers such as shift operators - * or mask may be applied to extend the functionaliy. As of now, + * or mask may be applied to extend the functionality. As of now, * the variable length type supports shifting the byte string to * the right, eating up any number of octets and thus supporting * wildcard interface name comparisons such as "ppp%" matching @@ -199,7 +195,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = tc_skb_protocol(skb); + dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) @@ -315,12 +311,15 @@ META_COLLECTOR(int_sk_bound_if) META_COLLECTOR(var_sk_bound_if) { + int bound_dev_if; + if (skip_nonlocal(skb)) { *err = -1; return; } - if (skb->sk->sk_bound_dev_if == 0) { + bound_dev_if = READ_ONCE(skb->sk->sk_bound_dev_if); + if (bound_dev_if == 0) { dst->value = (unsigned long) "any"; dst->len = 3; } else { @@ -328,7 +327,7 @@ META_COLLECTOR(var_sk_bound_if) rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(skb->sk), - skb->sk->sk_bound_dev_if); + bound_dev_if); *err = var_dev(dev, dst); rcu_read_unlock(); } @@ -450,7 +449,7 @@ META_COLLECTOR(int_sk_wmem_queued) *err = -1; return; } - dst->value = sk->sk_wmem_queued; + dst->value = READ_ONCE(sk->sk_wmem_queued); } META_COLLECTOR(int_sk_fwd_alloc) @@ -461,7 +460,7 @@ META_COLLECTOR(int_sk_fwd_alloc) *err = -1; return; } - dst->value = sk->sk_forward_alloc; + dst->value = READ_ONCE(sk->sk_forward_alloc); } META_COLLECTOR(int_sk_sndbuf) @@ -503,7 +502,7 @@ META_COLLECTOR(int_sk_lingertime) *err = -1; return; } - dst->value = sk->sk_lingertime / HZ; + dst->value = READ_ONCE(sk->sk_lingertime) / HZ; } META_COLLECTOR(int_sk_err_qlen) @@ -525,7 +524,7 @@ META_COLLECTOR(int_sk_ack_bl) *err = -1; return; } - dst->value = sk->sk_ack_backlog; + dst->value = READ_ONCE(sk->sk_ack_backlog); } META_COLLECTOR(int_sk_max_ack_bl) @@ -536,7 +535,7 @@ META_COLLECTOR(int_sk_max_ack_bl) *err = -1; return; } - dst->value = sk->sk_max_ack_backlog; + dst->value = READ_ONCE(sk->sk_max_ack_backlog); } META_COLLECTOR(int_sk_prio) @@ -547,7 +546,7 @@ META_COLLECTOR(int_sk_prio) *err = -1; return; } - dst->value = sk->sk_priority; + dst->value = READ_ONCE(sk->sk_priority); } META_COLLECTOR(int_sk_rcvlowat) @@ -558,7 +557,7 @@ META_COLLECTOR(int_sk_rcvlowat) *err = -1; return; } - dst->value = sk->sk_rcvlowat; + dst->value = READ_ONCE(sk->sk_rcvlowat); } META_COLLECTOR(int_sk_rcvtimeo) @@ -569,7 +568,7 @@ META_COLLECTOR(int_sk_rcvtimeo) *err = -1; return; } - dst->value = sk->sk_rcvtimeo / HZ; + dst->value = READ_ONCE(sk->sk_rcvtimeo) / HZ; } META_COLLECTOR(int_sk_sndtimeo) @@ -580,7 +579,7 @@ META_COLLECTOR(int_sk_sndtimeo) *err = -1; return; } - dst->value = sk->sk_sndtimeo / HZ; + dst->value = READ_ONCE(sk->sk_sndtimeo) / HZ; } META_COLLECTOR(int_sk_sendmsg_off) @@ -912,7 +911,8 @@ static int em_meta_change(struct net *net, void *data, int len, struct tcf_meta_hdr *hdr; struct meta_match *meta = NULL; - err = nla_parse(tb, TCA_EM_META_MAX, data, len, meta_policy, NULL); + err = nla_parse_deprecated(tb, TCA_EM_META_MAX, data, len, + meta_policy, NULL); if (err < 0) goto errout; @@ -1006,6 +1006,7 @@ static void __exit exit_em_meta(void) tcf_em_unregister(&em_meta_ops); } +MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata"); MODULE_LICENSE("GPL"); module_init(init_em_meta); diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index df3110d69585..c65ffa5fff94 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_nbyte.c N-Byte ematch * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> */ @@ -20,7 +16,7 @@ struct nbyte_data { struct tcf_em_nbyte hdr; - char pattern[0]; + char pattern[]; }; static int em_nbyte_change(struct net *net, void *data, int data_len, @@ -35,7 +31,7 @@ static int em_nbyte_change(struct net *net, void *data, int data_len, em->datalen = sizeof(*nbyte) + nbyte->len; em->data = (unsigned long)kmemdup(data, em->datalen, GFP_KERNEL); if (em->data == 0UL) - return -ENOBUFS; + return -ENOMEM; return 0; } @@ -46,12 +42,14 @@ static int em_nbyte_match(struct sk_buff *skb, struct tcf_ematch *em, struct nbyte_data *nbyte = (struct nbyte_data *) em->data; unsigned char *ptr = tcf_get_base_ptr(skb, nbyte->hdr.layer); + if (!ptr) + return 0; ptr += nbyte->hdr.off; if (!tcf_valid_offset(skb, ptr, nbyte->hdr.len)) return 0; - return !memcmp(ptr + nbyte->hdr.off, nbyte->pattern, nbyte->hdr.len); + return !memcmp(ptr, nbyte->pattern, nbyte->hdr.len); } static struct tcf_ematch_ops em_nbyte_ops = { @@ -72,6 +70,7 @@ static void __exit exit_em_nbyte(void) tcf_em_unregister(&em_nbyte_ops); } +MODULE_DESCRIPTION("ematch classifier for arbitrary skb multi-bytes"); MODULE_LICENSE("GPL"); module_init(init_em_nbyte); diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 73e2ed576ceb..692e2be1793e 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_text.c Textsearch ematch * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> */ @@ -33,12 +29,19 @@ static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m, struct tcf_pkt_info *info) { struct text_match *tm = EM_TEXT_PRIV(m); + unsigned char *ptr; int from, to; - from = tcf_get_base_ptr(skb, tm->from_layer) - skb->data; + ptr = tcf_get_base_ptr(skb, tm->from_layer); + if (!ptr) + return 0; + from = ptr - skb->data; from += tm->from_offset; - to = tcf_get_base_ptr(skb, tm->to_layer) - skb->data; + ptr = tcf_get_base_ptr(skb, tm->to_layer); + if (!ptr) + return 0; + to = ptr - skb->data; to += tm->to_offset; return skb_find_text(skb, from, to, tm->config) != UINT_MAX; @@ -101,8 +104,10 @@ retry: static void em_text_destroy(struct tcf_ematch *m) { - if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) { textsearch_destroy(EM_TEXT_PRIV(m)->config); + kfree(EM_TEXT_PRIV(m)); + } } static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) @@ -110,7 +115,7 @@ static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) struct text_match *tm = EM_TEXT_PRIV(m); struct tcf_em_text conf; - strncpy(conf.algo, tm->config->ops->name, sizeof(conf.algo) - 1); + strscpy(conf.algo, tm->config->ops->name); conf.from_offset = tm->from_offset; conf.to_offset = tm->to_offset; conf.from_layer = tm->from_layer; @@ -149,6 +154,7 @@ static void __exit exit_em_text(void) tcf_em_unregister(&em_text_ops); } +MODULE_DESCRIPTION("ematch classifier for embedded text in skbs"); MODULE_LICENSE("GPL"); module_init(init_em_text); diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 797bdb88c010..fdec4db5ec89 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_u32.c U32 Ematch * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * @@ -56,6 +52,7 @@ static void __exit exit_em_u32(void) tcf_em_unregister(&em_u32_ops); } +MODULE_DESCRIPTION("ematch skb classifier using 32 bit chunks of data"); MODULE_LICENSE("GPL"); module_init(init_em_u32); diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 03b677bc0700..5c1235e6076a 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/ematch.c Extended Match API * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> * * ========================================================================== @@ -145,7 +141,7 @@ errout: EXPORT_SYMBOL(tcf_em_register); /** - * tcf_em_unregister - unregster and extended match + * tcf_em_unregister - unregister and extended match * * @ops: ematch operations lookup table * @@ -178,7 +174,7 @@ static int tcf_em_validate(struct tcf_proto *tp, struct tcf_ematch_hdr *em_hdr = nla_data(nla); int data_len = nla_len(nla) - sizeof(*em_hdr); void *data = (void *) em_hdr + sizeof(*em_hdr); - struct net *net = dev_net(qdisc_dev(tp->q)); + struct net *net = tp->chain->block->net; if (!TCF_EM_REL_VALID(em_hdr->flags)) goto errout; @@ -242,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp, goto errout; if (em->ops->change) { + err = -EINVAL; + if (em_hdr->flags & TCF_EM_SIMPLE) + goto errout; err = em->ops->change(net, data, data_len, em); if (err < 0) goto errout; @@ -256,6 +255,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * the value carried. */ if (em_hdr->flags & TCF_EM_SIMPLE) { + if (em->ops->datalen > 0) + goto errout; if (data_len < sizeof(u32)) goto errout; em->data = *(u32 *) data; @@ -267,12 +268,12 @@ static int tcf_em_validate(struct tcf_proto *tp, } em->data = (unsigned long) v; } + em->datalen = data_len; } } em->matchid = em_hdr->matchid; em->flags = em_hdr->flags; - em->datalen = data_len; em->net = net; err = 0; @@ -314,7 +315,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, if (!nla) return 0; - err = nla_parse_nested(tb, TCA_EMATCH_TREE_MAX, nla, em_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_EMATCH_TREE_MAX, nla, + em_policy, NULL); if (err < 0) goto errout; @@ -389,7 +391,6 @@ EXPORT_SYMBOL(tcf_em_tree_validate); /** * tcf_em_tree_destroy - destroy an ematch tree * - * @tp: classifier kind handle * @tree: ematch tree to be deleted * * This functions destroys an ematch tree previously created by @@ -425,7 +426,7 @@ EXPORT_SYMBOL(tcf_em_tree_destroy); * tcf_em_tree_dump - dump ematch tree into a rtnl message * * @skb: skb holding the rtnl message - * @t: ematch tree to be dumped + * @tree: ematch tree to be dumped * @tlv: TLV type to be used to encapsulate the tree * * This function dumps a ematch tree into a rtnl message. It is valid to @@ -440,14 +441,14 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) struct nlattr *top_start; struct nlattr *list_start; - top_start = nla_nest_start(skb, tlv); + top_start = nla_nest_start_noflag(skb, tlv); if (top_start == NULL) goto nla_put_failure; if (nla_put(skb, TCA_EMATCH_TREE_HDR, sizeof(tree->hdr), &tree->hdr)) goto nla_put_failure; - list_start = nla_nest_start(skb, TCA_EMATCH_TREE_LIST); + list_start = nla_nest_start_noflag(skb, TCA_EMATCH_TREE_LIST); if (list_start == NULL) goto nla_put_failure; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bd24a550e0f9..f56b18c8aebf 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_api.c Packet scheduler API. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: @@ -27,21 +23,19 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> -#include <linux/lockdep.h> #include <linux/slab.h> #include <linux/hashtable.h> +#include <linux/bpf.h> +#include <net/netdev_lock.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/tc_wrapper.h> -static int qdisc_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, u32 clid, - struct Qdisc *old, struct Qdisc *new); -static int tclass_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, struct Qdisc *q, - unsigned long cl, int event); +#include <trace/events/qdisc.h> /* @@ -160,7 +154,7 @@ int register_qdisc(struct Qdisc_ops *qops) if (qops->cl_ops) { const struct Qdisc_class_ops *cops = qops->cl_ops; - if (!(cops->get && cops->put && cops->walk && cops->leaf)) + if (!(cops->find && cops->walk && cops->leaf)) goto out_einval; if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf)) @@ -180,7 +174,7 @@ out_einval: } EXPORT_SYMBOL(register_qdisc); -int unregister_qdisc(struct Qdisc_ops *qops) +void unregister_qdisc(struct Qdisc_ops *qops) { struct Qdisc_ops *q, **qp; int err = -ENOENT; @@ -195,7 +189,8 @@ int unregister_qdisc(struct Qdisc_ops *qops) err = 0; } write_unlock(&qdisc_mod_lock); - return err; + + WARN(err, "unregister qdisc(%s) failed\n", qops->id); } EXPORT_SYMBOL(unregister_qdisc); @@ -203,7 +198,7 @@ EXPORT_SYMBOL(unregister_qdisc); void qdisc_get_default(char *name, size_t len) { read_lock(&qdisc_mod_lock); - strlcpy(name, default_qdisc_ops->id, len); + strscpy(name, default_qdisc_ops->id, len); read_unlock(&qdisc_mod_lock); } @@ -213,7 +208,7 @@ static struct Qdisc_ops *qdisc_lookup_default(const char *name) for (q = qdisc_base; q; q = q->next) { if (!strcmp(name, q->id)) { - if (!try_module_get(q->owner)) + if (!bpf_try_module_get(q, q->owner)) q = NULL; break; } @@ -235,7 +230,7 @@ int qdisc_set_default(const char *name) if (!ops) { /* Not found, drop lock and try to load module */ write_unlock(&qdisc_mod_lock); - request_module("sch_%s", name); + request_module(NET_SCH_ALIAS_PREFIX "%s", name); write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); @@ -243,7 +238,7 @@ int qdisc_set_default(const char *name) if (ops) { /* Set new default */ - module_put(default_qdisc_ops->owner); + bpf_module_put(default_qdisc_ops, default_qdisc_ops->owner); default_qdisc_ops = ops; } write_unlock(&qdisc_mod_lock); @@ -276,7 +271,8 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) root->handle == handle) return root; - hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle) { + hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle, + lockdep_rtnl_is_held()) { if (q->handle == handle) return q; } @@ -286,9 +282,6 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { - struct Qdisc *root = qdisc_dev(q)->qdisc; - - WARN_ON_ONCE(root == &noop_qdisc); ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); if (invisible) @@ -310,33 +303,56 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { struct Qdisc *q; - q = qdisc_match_from_root(dev->qdisc, handle); + if (!handle) + return NULL; + q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); if (q) goto out; if (dev_ingress_queue(dev)) q = qdisc_match_from_root( - dev_ingress_queue(dev)->qdisc_sleeping, + rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping), handle); out: return q; } -static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) +{ + struct netdev_queue *nq; + struct Qdisc *q; + + if (!handle) + return NULL; + q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); + if (q) + goto out; + + nq = dev_ingress_queue_rcu(dev); + if (nq) + q = qdisc_match_from_root(rcu_dereference(nq->qdisc_sleeping), + handle); +out: + return q; +} + +static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid, + struct netlink_ext_ack *extack) { unsigned long cl; - struct Qdisc *leaf; const struct Qdisc_class_ops *cops = p->ops->cl_ops; - if (cops == NULL) - return NULL; - cl = cops->get(p, classid); + if (cops == NULL) { + NL_SET_ERR_MSG(extack, "Parent qdisc is not classful"); + return ERR_PTR(-EOPNOTSUPP); + } + cl = cops->find(p, classid); - if (cl == 0) - return NULL; - leaf = cops->leaf(p, cl); - cops->put(p, cl); - return leaf; + if (cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return ERR_PTR(-ENOENT); + } + return cops->leaf(p, cl); } /* Find queueing discipline by name */ @@ -349,7 +365,7 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) read_lock(&qdisc_mod_lock); for (q = qdisc_base; q; q = q->next) { if (nla_strcmp(kind, q->id) == 0) { - if (!try_module_get(q->owner)) + if (!bpf_try_module_get(q, q->owner)) q = NULL; break; } @@ -401,17 +417,21 @@ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, - struct nlattr *tab) + struct nlattr *tab, + struct netlink_ext_ack *extack) { struct qdisc_rate_table *rtab; - if (tab == NULL || r->rate == 0 || r->cell_log == 0 || - nla_len(tab) != TC_RTAB_SIZE) + if (tab == NULL || r->rate == 0 || + r->cell_log == 0 || r->cell_log >= 32 || + nla_len(tab) != TC_RTAB_SIZE) { + NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching"); return NULL; + } for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) { if (!memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) && - !memcmp(&rtab->data, nla_data(tab), 1024)) { + !memcmp(&rtab->data, nla_data(tab), TC_RTAB_SIZE)) { rtab->refcnt++; return rtab; } @@ -421,11 +441,13 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, if (rtab) { rtab->rate = *r; rtab->refcnt = 1; - memcpy(rtab->data, nla_data(tab), 1024); + memcpy(rtab->data, nla_data(tab), TC_RTAB_SIZE); if (r->linklayer == TC_LINKLAYER_UNAWARE) r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; + } else { + NL_SET_ERR_MSG(extack, "Failed to allocate new qdisc rate table"); } return rtab; } @@ -457,7 +479,8 @@ static const struct nla_policy stab_policy[TCA_STAB_MAX + 1] = { [TCA_STAB_DATA] = { .type = NLA_BINARY }, }; -static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) +static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_STAB_MAX + 1]; struct qdisc_size_table *stab; @@ -466,52 +489,61 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) u16 *tab = NULL; int err; - err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_STAB_MAX, opt, stab_policy, + extack); if (err < 0) return ERR_PTR(err); - if (!tb[TCA_STAB_BASE]) + if (!tb[TCA_STAB_BASE]) { + NL_SET_ERR_MSG(extack, "Size table base attribute is missing"); return ERR_PTR(-EINVAL); + } s = nla_data(tb[TCA_STAB_BASE]); if (s->tsize > 0) { - if (!tb[TCA_STAB_DATA]) + if (!tb[TCA_STAB_DATA]) { + NL_SET_ERR_MSG(extack, "Size table data attribute is missing"); return ERR_PTR(-EINVAL); + } tab = nla_data(tb[TCA_STAB_DATA]); tsize = nla_len(tb[TCA_STAB_DATA]) / sizeof(u16); } - if (tsize != s->tsize || (!tab && tsize > 0)) + if (tsize != s->tsize || (!tab && tsize > 0)) { + NL_SET_ERR_MSG(extack, "Invalid size of size table"); return ERR_PTR(-EINVAL); + } list_for_each_entry(stab, &qdisc_stab_list, list) { if (memcmp(&stab->szopts, s, sizeof(*s))) continue; - if (tsize > 0 && memcmp(stab->data, tab, tsize * sizeof(u16))) + if (tsize > 0 && + memcmp(stab->data, tab, flex_array_size(stab, data, tsize))) continue; stab->refcnt++; return stab; } - stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); + if (s->size_log > STAB_SIZE_LOG_MAX || + s->cell_log > STAB_SIZE_LOG_MAX) { + NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); + return ERR_PTR(-EINVAL); + } + + stab = kmalloc(struct_size(stab, data, tsize), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); stab->refcnt = 1; stab->szopts = *s; if (tsize > 0) - memcpy(stab->data, tab, tsize * sizeof(u16)); + memcpy(stab->data, tab, flex_array_size(stab, data, tsize)); list_add_tail(&stab->list, &qdisc_stab_list); return stab; } -static void stab_kfree_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct qdisc_size_table, rcu)); -} - void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) @@ -519,7 +551,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab) if (--tab->refcnt == 0) { list_del(&tab->list); - call_rcu_bh(&tab->rcu, stab_kfree_rcu); + kfree_rcu(tab, rcu); } } EXPORT_SYMBOL(qdisc_put_stab); @@ -528,7 +560,7 @@ static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab) { struct nlattr *nest; - nest = nla_nest_start(skb, TCA_STAB); + nest = nla_nest_start_noflag(skb, TCA_STAB); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts)) @@ -568,17 +600,6 @@ out: pkt_len = 1; qdisc_skb_cb(skb)->pkt_len = pkt_len; } -EXPORT_SYMBOL(__qdisc_calculate_pkt_len); - -void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) -{ - if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { - pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", - txt, qdisc->ops->id, qdisc->handle >> 16); - qdisc->flags |= TCQ_F_WARN_NONWC; - } -} -EXPORT_SYMBOL(qdisc_warn_nonwc); static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { @@ -592,29 +613,49 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) return HRTIMER_NORESTART; } -void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) +void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, + clockid_t clockid) { - hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); - wd->timer.function = qdisc_watchdog; + hrtimer_setup(&wd->timer, qdisc_watchdog, clockid, HRTIMER_MODE_ABS_PINNED); wd->qdisc = qdisc; } +EXPORT_SYMBOL(qdisc_watchdog_init_clockid); + +void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) +{ + qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC); +} EXPORT_SYMBOL(qdisc_watchdog_init); -void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires) +void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, + u64 delta_ns) { - if (test_bit(__QDISC_STATE_DEACTIVATED, - &qdisc_root_sleeping(wd->qdisc)->state)) - return; + bool deactivated; - if (wd->last_expires == expires) + rcu_read_lock(); + deactivated = test_bit(__QDISC_STATE_DEACTIVATED, + &qdisc_root_sleeping(wd->qdisc)->state); + rcu_read_unlock(); + if (deactivated) return; - wd->last_expires = expires; - hrtimer_start(&wd->timer, - ns_to_ktime(expires), - HRTIMER_MODE_ABS_PINNED); + if (hrtimer_is_queued(&wd->timer)) { + u64 softexpires; + + softexpires = ktime_to_ns(hrtimer_get_softexpires(&wd->timer)); + /* If timer is already set in [expires, expires + delta_ns], + * do not reprogram it. + */ + if (softexpires - expires <= delta_ns) + return; + } + + hrtimer_start_range_ns(&wd->timer, + ns_to_ktime(expires), + delta_ns, + HRTIMER_MODE_ABS_PINNED); } -EXPORT_SYMBOL(qdisc_watchdog_schedule_ns); +EXPORT_SYMBOL(qdisc_watchdog_schedule_range_ns); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { @@ -624,14 +665,10 @@ EXPORT_SYMBOL(qdisc_watchdog_cancel); static struct hlist_head *qdisc_class_hash_alloc(unsigned int n) { - unsigned int size = n * sizeof(struct hlist_head), i; struct hlist_head *h; + unsigned int i; - if (size <= PAGE_SIZE) - h = kmalloc(size, GFP_KERNEL); - else - h = (struct hlist_head *) - __get_free_pages(GFP_KERNEL, get_order(size)); + h = kvmalloc_array(n, sizeof(struct hlist_head), GFP_KERNEL); if (h != NULL) { for (i = 0; i < n; i++) @@ -640,16 +677,6 @@ static struct hlist_head *qdisc_class_hash_alloc(unsigned int n) return h; } -static void qdisc_class_hash_free(struct hlist_head *h, unsigned int n) -{ - unsigned int size = n * sizeof(struct hlist_head); - - if (size <= PAGE_SIZE) - kfree(h); - else - free_pages((unsigned long)h, get_order(size)); -} - void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) { struct Qdisc_class_common *cl; @@ -682,7 +709,7 @@ void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) clhash->hashmask = nmask; sch_tree_unlock(sch); - qdisc_class_hash_free(ohash, osize); + kvfree(ohash); } EXPORT_SYMBOL(qdisc_class_hash_grow); @@ -691,7 +718,7 @@ int qdisc_class_hash_init(struct Qdisc_class_hash *clhash) unsigned int size = 4; clhash->hash = qdisc_class_hash_alloc(size); - if (clhash->hash == NULL) + if (!clhash->hash) return -ENOMEM; clhash->hashsize = size; clhash->hashmask = size - 1; @@ -702,7 +729,7 @@ EXPORT_SYMBOL(qdisc_class_hash_init); void qdisc_class_hash_destroy(struct Qdisc_class_hash *clhash) { - qdisc_class_hash_free(clhash->hash, clhash->hashsize); + kvfree(clhash->hash); } EXPORT_SYMBOL(qdisc_class_hash_destroy); @@ -746,35 +773,37 @@ static u32 qdisc_alloc_handle(struct net_device *dev) return 0; } -void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, - unsigned int len) +void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; + bool notify; int drops; - if (n == 0 && len == 0) - return; drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { - if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS)) + if (parentid == TC_H_ROOT) break; if (sch->flags & TCQ_F_NOPARENT) break; + /* Notify parent qdisc only if child qdisc becomes empty. */ + notify = !sch->q.qlen; /* TODO: perform the search on a per txq basis */ - sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); + sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { WARN_ON_ONCE(parentid != TC_H_ROOT); break; } cops = sch->ops->cl_ops; - if (cops->qlen_notify) { - cl = cops->get(sch, parentid); + if (notify && cops->qlen_notify) { + /* Note that qlen_notify must be idempotent as it may get called + * multiple times. + */ + cl = cops->find(sch, parentid); cops->qlen_notify(sch, cl); - cops->put(sch, cl); } sch->q.qlen -= n; sch->qstats.backlog -= len; @@ -784,15 +813,266 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, } EXPORT_SYMBOL(qdisc_tree_reduce_backlog); +int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type, + void *type_data) +{ + struct net_device *dev = qdisc_dev(sch); + int err; + + sch->flags &= ~TCQ_F_OFFLOADED; + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return 0; + + err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); + if (err == -EOPNOTSUPP) + return 0; + + if (!err) + sch->flags |= TCQ_F_OFFLOADED; + + return err; +} +EXPORT_SYMBOL(qdisc_offload_dump_helper); + +void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + enum tc_setup_type type, void *type_data, + struct netlink_ext_ack *extack) +{ + bool any_qdisc_is_offloaded; + int err; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); + + /* Don't report error if the graft is part of destroy operation. */ + if (!err || !new || new == &noop_qdisc) + return; + + /* Don't report error if the parent, the old child and the new + * one are not offloaded. + */ + any_qdisc_is_offloaded = new->flags & TCQ_F_OFFLOADED; + any_qdisc_is_offloaded |= sch && sch->flags & TCQ_F_OFFLOADED; + any_qdisc_is_offloaded |= old && old->flags & TCQ_F_OFFLOADED; + + if (any_qdisc_is_offloaded) + NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); +} +EXPORT_SYMBOL(qdisc_offload_graft_helper); + +void qdisc_offload_query_caps(struct net_device *dev, + enum tc_setup_type type, + void *caps, size_t caps_len) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_query_caps_base base = { + .type = type, + .caps = caps, + }; + + memset(caps, 0, caps_len); + + if (ops->ndo_setup_tc) + ops->ndo_setup_tc(dev, TC_QUERY_CAPS, &base); +} +EXPORT_SYMBOL(qdisc_offload_query_caps); + +static void qdisc_offload_graft_root(struct net_device *dev, + struct Qdisc *new, struct Qdisc *old, + struct netlink_ext_ack *extack) +{ + struct tc_root_qopt_offload graft_offload = { + .command = TC_ROOT_GRAFT, + .handle = new ? new->handle : 0, + .ingress = (new && new->flags & TCQ_F_INGRESS) || + (old && old->flags & TCQ_F_INGRESS), + }; + + qdisc_offload_graft_helper(dev, NULL, new, old, + TC_SETUP_ROOT_QDISC, &graft_offload, extack); +} + +static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, + u32 portid, u32 seq, u16 flags, int event, + struct netlink_ext_ack *extack) +{ + struct gnet_stats_basic_sync __percpu *cpu_bstats = NULL; + struct gnet_stats_queue __percpu *cpu_qstats = NULL; + struct tcmsg *tcm; + struct nlmsghdr *nlh; + unsigned char *b = skb_tail_pointer(skb); + struct gnet_dump d; + struct qdisc_size_table *stab; + u32 block_index; + __u32 qlen; + + cond_resched(); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); + tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = clid; + tcm->tcm_handle = q->handle; + tcm->tcm_info = refcount_read(&q->refcnt); + if (nla_put_string(skb, TCA_KIND, q->ops->id)) + goto nla_put_failure; + if (q->ops->ingress_block_get) { + block_index = q->ops->ingress_block_get(q); + if (block_index && + nla_put_u32(skb, TCA_INGRESS_BLOCK, block_index)) + goto nla_put_failure; + } + if (q->ops->egress_block_get) { + block_index = q->ops->egress_block_get(q); + if (block_index && + nla_put_u32(skb, TCA_EGRESS_BLOCK, block_index)) + goto nla_put_failure; + } + if (q->ops->dump && q->ops->dump(q, skb) < 0) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) + goto nla_put_failure; + qlen = qdisc_qlen_sum(q); + + stab = rtnl_dereference(q->stab); + if (stab && qdisc_dump_stab(skb, stab) < 0) + goto nla_put_failure; + + if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, + NULL, &d, TCA_PAD) < 0) + goto nla_put_failure; + + if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0) + goto nla_put_failure; + + if (qdisc_is_percpu_stats(q)) { + cpu_bstats = q->cpu_bstats; + cpu_qstats = q->cpu_qstats; + } + + if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats, true) < 0 || + gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || + gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) + goto nla_put_failure; + + if (gnet_stats_finish_copy(&d) < 0) + goto nla_put_failure; + + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + + return skb->len; + +out_nlmsg_trim: +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) +{ + if (q->flags & TCQ_F_BUILTIN) + return true; + if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) + return true; + + return false; +} + +static int qdisc_get_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, u32 clid, struct Qdisc *q, + struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (!tc_qdisc_dump_ignore(q, false)) { + if (tc_fill_qdisc(skb, q, clid, portid, n->nlmsg_seq, 0, + RTM_NEWQDISC, extack) < 0) + goto err_out; + } + + if (skb->len) + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + +err_out: + kfree_skb(skb); + return -EINVAL; +} + +static int qdisc_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, u32 clid, + struct Qdisc *old, struct Qdisc *new, + struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (old && !tc_qdisc_dump_ignore(old, false)) { + if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, + 0, RTM_DELQDISC, extack) < 0) + goto err_out; + } + if (new && !tc_qdisc_dump_ignore(new, false)) { + if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, + old ? NLM_F_REPLACE : 0, RTM_NEWQDISC, extack) < 0) + goto err_out; + } + + if (skb->len) + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + +err_out: + kfree_skb(skb); + return -EINVAL; +} + static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, - struct Qdisc *old, struct Qdisc *new) + struct Qdisc *old, struct Qdisc *new, + struct netlink_ext_ack *extack) { if (new || old) - qdisc_notify(net, skb, n, clid, old, new); + qdisc_notify(net, skb, n, clid, old, new, extack); if (old) - qdisc_destroy(old); + qdisc_put(old); +} + +static void qdisc_clear_nolock(struct Qdisc *sch) +{ + sch->flags &= ~TCQ_F_NOLOCK; + if (!(sch->flags & TCQ_F_CPUSTATS)) + return; + + free_percpu(sch->cpu_bstats); + free_percpu(sch->cpu_qstats); + sch->cpu_bstats = NULL; + sch->cpu_qstats = NULL; + sch->flags &= ~TCQ_F_CPUSTATS; } /* Graft qdisc "new" to class "classid" of qdisc "parent" or @@ -806,82 +1086,154 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb, static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, struct sk_buff *skb, struct nlmsghdr *n, u32 classid, - struct Qdisc *new, struct Qdisc *old) + struct Qdisc *new, struct Qdisc *old, + struct netlink_ext_ack *extack) { struct Qdisc *q = old; struct net *net = dev_net(dev); - int err = 0; if (parent == NULL) { unsigned int i, num_q, ingress; + struct netdev_queue *dev_queue; ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { - num_q = 1; ingress = 1; - if (!dev_ingress_queue(dev)) + dev_queue = dev_ingress_queue(dev); + if (!dev_queue) { + NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); return -ENOENT; + } + + q = rtnl_dereference(dev_queue->qdisc_sleeping); + + /* This is the counterpart of that qdisc_refcount_inc_nz() call in + * __tcf_qdisc_find() for filter requests. + */ + if (!qdisc_refcount_dec_if_one(q)) { + NL_SET_ERR_MSG(extack, + "Current ingress or clsact Qdisc has ongoing filter requests"); + return -EBUSY; + } } if (dev->flags & IFF_UP) dev_deactivate(dev); - if (new && new->ops->attach) - goto skip; + qdisc_offload_graft_root(dev, new, old, extack); - for (i = 0; i < num_q; i++) { - struct netdev_queue *dev_queue = dev_ingress_queue(dev); + if (new && new->ops->attach && !ingress) + goto skip; - if (!ingress) + if (!ingress) { + for (i = 0; i < num_q; i++) { dev_queue = netdev_get_tx_queue(dev, i); + old = dev_graft_qdisc(dev_queue, new); + + if (new && i > 0) + qdisc_refcount_inc(new); + qdisc_put(old); + } + } else { + old = dev_graft_qdisc(dev_queue, NULL); - old = dev_graft_qdisc(dev_queue, new); - if (new && i > 0) - refcount_inc(&new->refcnt); + /* {ingress,clsact}_destroy() @old before grafting @new to avoid + * unprotected concurrent accesses to net_device::miniq_{in,e}gress + * pointer(s) in mini_qdisc_pair_swap(). + */ + qdisc_notify(net, skb, n, classid, old, new, extack); + qdisc_destroy(old); - if (!ingress) - qdisc_destroy(old); + dev_graft_qdisc(dev_queue, new); } skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - dev->qdisc, new); + old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) - refcount_inc(&new->refcnt); - dev->qdisc = new ? : &noop_qdisc; + qdisc_refcount_inc(new); + rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + + notify_and_destroy(net, skb, n, classid, old, new, extack); if (new && new->ops->attach) new->ops->attach(new); - } else { - notify_and_destroy(net, skb, n, classid, old, new); } if (dev->flags & IFF_UP) dev_activate(dev); } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; + unsigned long cl; + int err; - err = -EOPNOTSUPP; - if (cops && cops->graft) { - unsigned long cl = cops->get(parent, classid); - if (cl) { - err = cops->graft(parent, cl, new, &old); - cops->put(parent, cl); - } else - err = -ENOENT; + /* Only support running class lockless if parent is lockless */ + if (new && (new->flags & TCQ_F_NOLOCK) && !(parent->flags & TCQ_F_NOLOCK)) + qdisc_clear_nolock(new); + + if (!cops || !cops->graft) + return -EOPNOTSUPP; + + cl = cops->find(parent, classid); + if (!cl) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return -ENOENT; + } + + if (new && new->ops == &noqueue_qdisc_ops) { + NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); + return -EINVAL; + } + + if (new && + !(parent->flags & TCQ_F_MQROOT) && + rcu_access_pointer(new->stab)) { + NL_SET_ERR_MSG(extack, "STAB not supported on a non root"); + return -EINVAL; } - if (!err) - notify_and_destroy(net, skb, n, classid, old, new); + err = cops->graft(parent, cl, new, &old, extack); + if (err) + return err; + notify_and_destroy(net, skb, n, classid, old, new, extack); } - return err; + return 0; } -/* lockdep annotation is needed for ingress; egress gets it only for name */ -static struct lock_class_key qdisc_tx_lock; -static struct lock_class_key qdisc_rx_lock; +static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, + struct netlink_ext_ack *extack) +{ + u32 block_index; + + if (tca[TCA_INGRESS_BLOCK]) { + block_index = nla_get_u32(tca[TCA_INGRESS_BLOCK]); + + if (!block_index) { + NL_SET_ERR_MSG(extack, "Ingress block index cannot be 0"); + return -EINVAL; + } + if (!sch->ops->ingress_block_set) { + NL_SET_ERR_MSG(extack, "Ingress block sharing is not supported"); + return -EOPNOTSUPP; + } + sch->ops->ingress_block_set(sch, block_index); + } + if (tca[TCA_EGRESS_BLOCK]) { + block_index = nla_get_u32(tca[TCA_EGRESS_BLOCK]); + + if (!block_index) { + NL_SET_ERR_MSG(extack, "Egress block index cannot be 0"); + return -EINVAL; + } + if (!sch->ops->egress_block_set) { + NL_SET_ERR_MSG(extack, "Egress block sharing is not supported"); + return -EOPNOTSUPP; + } + sch->ops->egress_block_set(sch, block_index); + } + return 0; +} /* Allocate and initialize new qdisc. @@ -891,8 +1243,9 @@ static struct lock_class_key qdisc_rx_lock; static struct Qdisc *qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, - struct Qdisc *p, u32 parent, u32 handle, - struct nlattr **tca, int *errp) + u32 parent, u32 handle, + struct nlattr **tca, int *errp, + struct netlink_ext_ack *extack) { int err; struct nlattr *kind = tca[TCA_KIND]; @@ -901,39 +1254,13 @@ static struct Qdisc *qdisc_create(struct net_device *dev, struct qdisc_size_table *stab; ops = qdisc_lookup_ops(kind); -#ifdef CONFIG_MODULES - if (ops == NULL && kind != NULL) { - char name[IFNAMSIZ]; - if (nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) { - /* We dropped the RTNL semaphore in order to - * perform the module load. So, even if we - * succeeded in loading the module we have to - * tell the caller to replay the request. We - * indicate this using -EAGAIN. - * We replay the request because the device may - * go away in the mean time. - */ - rtnl_unlock(); - request_module("sch_%s", name); - rtnl_lock(); - ops = qdisc_lookup_ops(kind); - if (ops != NULL) { - /* We will try again qdisc_lookup_ops, - * so don't keep a reference. - */ - module_put(ops->owner); - err = -EAGAIN; - goto err_out; - } - } - } -#endif - - err = -ENOENT; - if (ops == NULL) + if (!ops) { + err = -ENOENT; + NL_SET_ERR_MSG(extack, "Specified qdisc kind is unknown"); goto err_out; + } - sch = qdisc_alloc(dev_queue, ops); + sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { err = PTR_ERR(sch); goto err_out2; @@ -942,17 +1269,22 @@ static struct Qdisc *qdisc_create(struct net_device *dev, sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); - lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); - err = -ENOMEM; - if (handle == 0) + if (handle == 0) { + NL_SET_ERR_MSG(extack, "Maximum number of qdisc handles was exceeded"); + err = -ENOSPC; goto err_out3; + } } - lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } @@ -966,98 +1298,93 @@ static struct Qdisc *qdisc_create(struct net_device *dev, * before again attaching a qdisc. */ if ((dev->priv_flags & IFF_NO_QUEUE) && (dev->tx_queue_len == 0)) { - dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; + WRITE_ONCE(dev->tx_queue_len, DEFAULT_TX_QUEUE_LEN); netdev_info(dev, "Caught tx_queue_len zero misconfig\n"); } - if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) { - if (qdisc_is_percpu_stats(sch)) { - sch->cpu_bstats = - netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); - if (!sch->cpu_bstats) - goto err_out4; + err = qdisc_block_indexes_set(sch, tca, extack); + if (err) + goto err_out3; - sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); - if (!sch->cpu_qstats) - goto err_out4; + if (tca[TCA_STAB]) { + stab = qdisc_get_stab(tca[TCA_STAB], extack); + if (IS_ERR(stab)) { + err = PTR_ERR(stab); + goto err_out3; } + rcu_assign_pointer(sch->stab, stab); + } - if (tca[TCA_STAB]) { - stab = qdisc_get_stab(tca[TCA_STAB]); - if (IS_ERR(stab)) { - err = PTR_ERR(stab); - goto err_out4; - } - rcu_assign_pointer(sch->stab, stab); + if (ops->init) { + err = ops->init(sch, tca[TCA_OPTIONS], extack); + if (err != 0) + goto err_out4; + } + + if (tca[TCA_RATE]) { + err = -EOPNOTSUPP; + if (sch->flags & TCQ_F_MQROOT) { + NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); + goto err_out4; } - if (tca[TCA_RATE]) { - seqcount_t *running; - - err = -EOPNOTSUPP; - if (sch->flags & TCQ_F_MQROOT) - goto err_out4; - - if ((sch->parent != TC_H_ROOT) && - !(sch->flags & TCQ_F_INGRESS) && - (!p || !(p->flags & TCQ_F_MQROOT))) - running = qdisc_root_sleeping_running(sch); - else - running = &sch->running; - - err = gen_new_estimator(&sch->bstats, - sch->cpu_bstats, - &sch->rate_est, - NULL, - running, - tca[TCA_RATE]); - if (err) - goto err_out4; + + err = gen_new_estimator(&sch->bstats, + sch->cpu_bstats, + &sch->rate_est, + NULL, + true, + tca[TCA_RATE]); + if (err) { + NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); + goto err_out4; } + } - qdisc_hash_add(sch, false); + qdisc_hash_add(sch, false); + trace_qdisc_create(ops, dev, parent); - return sch; - } - /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ + return sch; + +err_out4: + /* Even if ops->init() failed, we call ops->destroy() + * like qdisc_create_dflt(). + */ if (ops->destroy) ops->destroy(sch); + qdisc_put_stab(rtnl_dereference(sch->stab)); err_out3: - dev_put(dev); - kfree((char *) sch - sch->padded); + lockdep_unregister_key(&sch->root_lock_key); + netdev_put(dev, &sch->dev_tracker); + qdisc_free(sch); err_out2: - module_put(ops->owner); + bpf_module_put(ops, ops->owner); err_out: *errp = err; return NULL; - -err_out4: - free_percpu(sch->cpu_bstats); - free_percpu(sch->cpu_qstats); - /* - * Any broken qdiscs that would require a ops->reset() here? - * The qdisc was never in action so it shouldn't be necessary. - */ - qdisc_put_stab(rtnl_dereference(sch->stab)); - if (ops->destroy) - ops->destroy(sch); - goto err_out3; } -static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) +static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, + struct netlink_ext_ack *extack) { struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { - if (sch->ops->change == NULL) + if (!sch->ops->change) { + NL_SET_ERR_MSG(extack, "Change operation not supported by specified qdisc"); return -EINVAL; - err = sch->ops->change(sch, tca[TCA_OPTIONS]); + } + if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { + NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); + return -EOPNOTSUPP; + } + err = sch->ops->change(sch, tca[TCA_OPTIONS], extack); if (err) return err; } if (tca[TCA_STAB]) { - stab = qdisc_get_stab(tca[TCA_STAB]); + stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) return PTR_ERR(stab); } @@ -1075,7 +1402,7 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) sch->cpu_bstats, &sch->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); } out: @@ -1122,121 +1449,169 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) return 0; } +const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { + [TCA_KIND] = { .type = NLA_STRING }, + [TCA_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct tc_estimator) }, + [TCA_STAB] = { .type = NLA_NESTED }, + [TCA_DUMP_INVISIBLE] = { .type = NLA_FLAG }, + [TCA_CHAIN] = { .type = NLA_U32 }, + [TCA_INGRESS_BLOCK] = { .type = NLA_U32 }, + [TCA_EGRESS_BLOCK] = { .type = NLA_U32 }, +}; + /* * Delete/get qdisc. */ -static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, - struct netlink_ext_ack *extack) +static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack, + struct net_device *dev, + struct nlattr *tca[TCA_MAX + 1], + struct tcmsg *tcm) { struct net *net = sock_net(skb->sk); - struct tcmsg *tcm = nlmsg_data(n); - struct nlattr *tca[TCA_MAX + 1]; - struct net_device *dev; - u32 clid; struct Qdisc *q = NULL; struct Qdisc *p = NULL; + u32 clid; int err; - if ((n->nlmsg_type != RTM_GETQDISC) && - !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); - if (err < 0) - return err; - - dev = __dev_get_by_index(net, tcm->tcm_ifindex); - if (!dev) - return -ENODEV; - clid = tcm->tcm_parent; if (clid) { if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); - if (!p) + if (!p) { + NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; - q = qdisc_leaf(p, clid); + } + q = qdisc_leaf(p, clid, extack); } else if (dev_ingress_queue(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); } - if (!q) + if (!q) { + NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; + } + if (IS_ERR(q)) + return PTR_ERR(q); - if (tcm->tcm_handle && q->handle != tcm->tcm_handle) + if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { + NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; + } } else { q = qdisc_lookup(dev, tcm->tcm_handle); - if (!q) + if (!q) { + NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified handle"); return -ENOENT; + } } - if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; + } if (n->nlmsg_type == RTM_DELQDISC) { - if (!clid) + if (!clid) { + NL_SET_ERR_MSG(extack, "Classid cannot be zero"); return -EINVAL; - if (q->handle == 0) + } + if (q->handle == 0) { + NL_SET_ERR_MSG(extack, "Cannot delete qdisc with handle of zero"); return -ENOENT; - err = qdisc_graft(dev, p, skb, n, clid, NULL, q); + } + err = qdisc_graft(dev, p, skb, n, clid, NULL, q, extack); if (err != 0) return err; } else { - qdisc_notify(net, skb, n, clid, NULL, q); + qdisc_get_notify(net, skb, n, clid, q, NULL); } return 0; } -/* - * Create/change qdisc. - */ - -static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, - struct netlink_ext_ack *extack) +static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); - struct tcmsg *tcm; + struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; - u32 clid; - struct Qdisc *q, *p; int err; - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - -replay: - /* Reinit, just in case something touches this. */ - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; - tcm = nlmsg_data(n); - clid = tcm->tcm_parent; - q = p = NULL; - dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; + netdev_lock_ops(dev); + err = __tc_get_qdisc(skb, n, extack, dev, tca, tcm); + netdev_unlock_ops(dev); + + return err; +} + +static bool req_create_or_replace(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_REPLACE); +} + +static bool req_create_exclusive(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_EXCL); +} + +static bool req_change(struct nlmsghdr *n) +{ + return (!(n->nlmsg_flags & NLM_F_CREATE) && + !(n->nlmsg_flags & NLM_F_REPLACE) && + !(n->nlmsg_flags & NLM_F_EXCL)); +} + +static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack, + struct net_device *dev, + struct nlattr *tca[TCA_MAX + 1], + struct tcmsg *tcm) +{ + struct Qdisc *q = NULL; + struct Qdisc *p = NULL; + u32 clid; + int err; + + clid = tcm->tcm_parent; if (clid) { if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); - if (!p) + if (!p) { + NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; - q = qdisc_leaf(p, clid); + } + if (p->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot add children to ingress/clsact qdisc"); + return -EOPNOTSUPP; + } + q = qdisc_leaf(p, clid, extack); + if (IS_ERR(q)) + return PTR_ERR(q); } else if (dev_ingress_queue_create(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); } /* It may be default qdisc, ignore it */ @@ -1245,21 +1620,45 @@ replay: if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { - if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) + if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) { + NL_SET_ERR_MSG(extack, "NLM_F_REPLACE needed to override"); return -EEXIST; - if (TC_H_MIN(tcm->tcm_handle)) + } + if (TC_H_MIN(tcm->tcm_handle)) { + NL_SET_ERR_MSG(extack, "Invalid minor handle"); return -EINVAL; + } q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) goto create_n_graft; - if (n->nlmsg_flags & NLM_F_EXCL) + if (q->parent != tcm->tcm_parent) { + NL_SET_ERR_MSG(extack, "Cannot move an existing qdisc to a different parent"); + return -EINVAL; + } + if (n->nlmsg_flags & NLM_F_EXCL) { + NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot override"); return -EEXIST; - if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) + } + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; + } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || - (p && check_loop(q, p, 0))) + (p && check_loop(q, p, 0))) { + NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; - refcount_inc(&q->refcnt); + } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; + } + qdisc_refcount_inc(q); goto graft; } else { if (!q) @@ -1269,57 +1668,78 @@ replay: * * We know, that some child q is already * attached to this parent and have choice: - * either to change it or to create/graft new one. + * 1) change it or 2) create/graft new one. + * If the requested qdisc kind is different + * than the existing one, then we choose graft. + * If they are the same then this is "change" + * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only - * if CREATE and REPLACE flags are set. + * if the request is explicitly stating + * "please create if it doesn't exist". * - * 2. If EXCL is set, requestor wanted to say, - * that qdisc tcm_handle is not expected + * 2. If the request is to exclusive create + * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. + * This will happen when for example tc + * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. - * For now we select create/graft, if - * user gave KIND, which does not match existing. + * For now we select create/graft. */ - if ((n->nlmsg_flags & NLM_F_CREATE) && - (n->nlmsg_flags & NLM_F_REPLACE) && - ((n->nlmsg_flags & NLM_F_EXCL) || - (tca[TCA_KIND] && - nla_strcmp(tca[TCA_KIND], q->ops->id)))) - goto create_n_graft; + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + if (req_create_or_replace(n) || + req_create_exclusive(n)) + goto create_n_graft; + else if (req_change(n)) + goto create_n_graft2; + } } } } else { - if (!tcm->tcm_handle) + if (!tcm->tcm_handle) { + NL_SET_ERR_MSG(extack, "Handle cannot be zero"); return -EINVAL; + } q = qdisc_lookup(dev, tcm->tcm_handle); } /* Change qdisc parameters */ - if (q == NULL) + if (!q) { + NL_SET_ERR_MSG(extack, "Specified qdisc not found"); return -ENOENT; - if (n->nlmsg_flags & NLM_F_EXCL) + } + if (n->nlmsg_flags & NLM_F_EXCL) { + NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot modify"); return -EEXIST; - if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) + } + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; - err = qdisc_change(q, tca); + } + err = qdisc_change(q, tca, extack); if (err == 0) - qdisc_notify(net, skb, n, clid, NULL, q); + qdisc_notify(sock_net(skb->sk), skb, n, clid, NULL, q, extack); return err; create_n_graft: - if (!(n->nlmsg_flags & NLM_F_CREATE)) + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; + } +create_n_graft2: if (clid == TC_H_INGRESS) { - if (dev_ingress_queue(dev)) - q = qdisc_create(dev, dev_ingress_queue(dev), p, + if (dev_ingress_queue(dev)) { + q = qdisc_create(dev, dev_ingress_queue(dev), tcm->tcm_parent, tcm->tcm_parent, - tca, &err); - else + tca, &err, extack); + } else { + NL_SET_ERR_MSG(extack, "Cannot find ingress queue for specified device"); err = -ENOENT; + } } else { struct netdev_queue *dev_queue; @@ -1330,130 +1750,74 @@ create_n_graft: else dev_queue = netdev_get_tx_queue(dev, 0); - q = qdisc_create(dev, dev_queue, p, + q = qdisc_create(dev, dev_queue, tcm->tcm_parent, tcm->tcm_handle, - tca, &err); + tca, &err, extack); } - if (q == NULL) { - if (err == -EAGAIN) - goto replay; + if (!q) return err; - } graft: - err = qdisc_graft(dev, p, skb, n, clid, q, NULL); + err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) - qdisc_destroy(q); + qdisc_put(q); return err; } return 0; } -static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, - u32 portid, u32 seq, u16 flags, int event) +static void request_qdisc_module(struct nlattr *kind) { - struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL; - struct gnet_stats_queue __percpu *cpu_qstats = NULL; - struct tcmsg *tcm; - struct nlmsghdr *nlh; - unsigned char *b = skb_tail_pointer(skb); - struct gnet_dump d; - struct qdisc_size_table *stab; - __u32 qlen; - - cond_resched(); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); - if (!nlh) - goto out_nlmsg_trim; - tcm = nlmsg_data(nlh); - tcm->tcm_family = AF_UNSPEC; - tcm->tcm__pad1 = 0; - tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(q)->ifindex; - tcm->tcm_parent = clid; - tcm->tcm_handle = q->handle; - tcm->tcm_info = refcount_read(&q->refcnt); - if (nla_put_string(skb, TCA_KIND, q->ops->id)) - goto nla_put_failure; - if (q->ops->dump && q->ops->dump(q, skb) < 0) - goto nla_put_failure; - qlen = q->q.qlen; - - stab = rtnl_dereference(q->stab); - if (stab && qdisc_dump_stab(skb, stab) < 0) - goto nla_put_failure; - - if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, - NULL, &d, TCA_PAD) < 0) - goto nla_put_failure; + struct Qdisc_ops *ops; + char name[IFNAMSIZ]; - if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0) - goto nla_put_failure; + if (!kind) + return; - if (qdisc_is_percpu_stats(q)) { - cpu_bstats = q->cpu_bstats; - cpu_qstats = q->cpu_qstats; + ops = qdisc_lookup_ops(kind); + if (ops) { + bpf_module_put(ops, ops->owner); + return; } - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q), - &d, cpu_bstats, &q->bstats) < 0 || - gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || - gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) - goto nla_put_failure; - - if (gnet_stats_finish_copy(&d) < 0) - goto nla_put_failure; - - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; - -out_nlmsg_trim: -nla_put_failure: - nlmsg_trim(skb, b); - return -1; + if (nla_strscpy(name, kind, IFNAMSIZ) >= 0) { + rtnl_unlock(); + request_module(NET_SCH_ALIAS_PREFIX "%s", name); + rtnl_lock(); + } } -static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) +/* + * Create/change qdisc. + */ +static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) { - if (q->flags & TCQ_F_BUILTIN) - return true; - if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) - return true; - - return false; -} + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + struct net_device *dev; + struct tcmsg *tcm; + int err; -static int qdisc_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, u32 clid, - struct Qdisc *old, struct Qdisc *new) -{ - struct sk_buff *skb; - u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, extack); + if (err < 0) + return err; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; + request_qdisc_module(tca[TCA_KIND]); - if (old && !tc_qdisc_dump_ignore(old, false)) { - if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, - 0, RTM_DELQDISC) < 0) - goto err_out; - } - if (new && !tc_qdisc_dump_ignore(new, false)) { - if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, - old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) - goto err_out; - } + tcm = nlmsg_data(n); + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) + return -ENODEV; - if (skb->len) - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + netdev_lock_ops(dev); + err = __tc_modify_qdisc(skb, n, extack, dev, tca, tcm); + netdev_unlock_ops(dev); -err_out: - kfree_skb(skb); - return -EINVAL; + return err; } static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, @@ -1475,7 +1839,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWQDISC) <= 0) + RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } @@ -1497,7 +1861,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWQDISC) <= 0) + RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } @@ -1517,7 +1881,6 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int s_idx, s_q_idx; struct net_device *dev; const struct nlmsghdr *nlh = cb->nlh; - struct tcmsg *tcm = nlmsg_data(nlh); struct nlattr *tca[TCA_MAX + 1]; int err; @@ -1527,7 +1890,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse_deprecated(nlh, sizeof(struct tcmsg), tca, TCA_MAX, + rtm_tca_policy, cb->extack); if (err < 0) return err; @@ -1540,16 +1904,23 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_q_idx = 0; q_idx = 0; - if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, - true, tca[TCA_DUMP_INVISIBLE]) < 0) + netdev_lock_ops(dev); + if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), + skb, cb, &q_idx, s_q_idx, + true, tca[TCA_DUMP_INVISIBLE]) < 0) { + netdev_unlock_ops(dev); goto done; + } dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx, false, - tca[TCA_DUMP_INVISIBLE]) < 0) + tc_dump_qdisc_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, cb, &q_idx, s_q_idx, false, + tca[TCA_DUMP_INVISIBLE]) < 0) { + netdev_unlock_ops(dev); goto done; + } + netdev_unlock_ops(dev); cont: idx++; @@ -1568,17 +1939,233 @@ done: * Traffic classes manipulation. * ************************************************/ +static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, + unsigned long cl, u32 portid, u32 seq, u16 flags, + int event, struct netlink_ext_ack *extack) +{ + struct tcmsg *tcm; + struct nlmsghdr *nlh; + unsigned char *b = skb_tail_pointer(skb); + struct gnet_dump d; + const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; + + cond_resched(); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); + tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = q->handle; + tcm->tcm_handle = q->handle; + tcm->tcm_info = 0; + if (nla_put_string(skb, TCA_KIND, q->ops->id)) + goto nla_put_failure; + if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0) + goto nla_put_failure; + + if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, + NULL, &d, TCA_PAD) < 0) + goto nla_put_failure; + if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0) + goto nla_put_failure; -static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, - struct netlink_ext_ack *extack) + if (gnet_stats_finish_copy(&d) < 0) + goto nla_put_failure; + + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + + return skb->len; + +out_nlmsg_trim: +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static int tclass_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, struct Qdisc *q, + unsigned long cl, int event, struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event, extack) < 0) { + kfree_skb(skb); + return -EINVAL; + } + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); +} + +static int tclass_get_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, struct Qdisc *q, + unsigned long cl, struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, RTM_NEWTCLASS, + extack) < 0) { + kfree_skb(skb); + return -EINVAL; + } + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); +} + +static int tclass_del_notify(struct net *net, + const struct Qdisc_class_ops *cops, + struct sk_buff *oskb, struct nlmsghdr *n, + struct Qdisc *q, unsigned long cl, + struct netlink_ext_ack *extack) +{ + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct sk_buff *skb; + int err = 0; + + if (!cops->delete) + return -EOPNOTSUPP; + + if (rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, + RTM_DELTCLASS, extack) < 0) { + kfree_skb(skb); + return -EINVAL; + } + } else { + skb = NULL; + } + + err = cops->delete(q, cl, extack); + if (err) { + kfree_skb(skb); + return err; + } + + err = rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + return err; +} + +#ifdef CONFIG_NET_CLS + +struct tcf_bind_args { + struct tcf_walker w; + unsigned long base; + unsigned long cl; + u32 classid; +}; + +static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) +{ + struct tcf_bind_args *a = (void *)arg; + + if (n && tp->ops->bind_class) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + + sch_tree_lock(q); + tp->ops->bind_class(n, a->classid, a->cl, q, a->base); + sch_tree_unlock(q); + } + return 0; +} + +struct tc_bind_class_args { + struct qdisc_walker w; + unsigned long new_cl; + u32 portid; + u32 clid; +}; + +static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, + struct qdisc_walker *w) +{ + struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + struct tcf_block *block; + struct tcf_chain *chain; + + block = cops->tcf_block(q, cl, NULL); + if (!block) + return 0; + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { + struct tcf_proto *tp; + + for (tp = tcf_get_next_proto(chain, NULL); + tp; tp = tcf_get_next_proto(chain, tp)) { + struct tcf_bind_args arg = {}; + + arg.w.fn = tcf_node_bind; + arg.classid = a->clid; + arg.base = cl; + arg.cl = a->new_cl; + tp->ops->walk(tp, &arg.w, true); + } + } + + return 0; +} + +static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, + unsigned long new_cl) +{ + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + struct tc_bind_class_args args = {}; + + if (!cops->tcf_block) + return; + args.portid = portid; + args.clid = clid; + args.new_cl = new_cl; + args.w.fn = tc_bind_class_walker; + q->ops->cl_ops->walk(q, &args.w); +} + +#else + +static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, + unsigned long new_cl) +{ +} + +#endif + +static int __tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack, + struct net_device *dev, + struct nlattr *tca[TCA_MAX + 1], + struct tcmsg *tcm) { struct net *net = sock_net(skb->sk); - struct tcmsg *tcm = nlmsg_data(n); - struct nlattr *tca[TCA_MAX + 1]; - struct net_device *dev; - struct Qdisc *q = NULL; const struct Qdisc_class_ops *cops; + struct Qdisc *q = NULL; unsigned long cl = 0; unsigned long new_cl; u32 portid; @@ -1586,18 +2173,6 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, u32 qid; int err; - if ((n->nlmsg_type != RTM_GETTCLASS) && - !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); - if (err < 0) - return err; - - dev = __dev_get_by_index(net, tcm->tcm_ifindex); - if (!dev) - return -ENODEV; - /* parent == TC_H_UNSPEC - unspecified parent. parent == TC_H_ROOT - class is root, which has no parent. @@ -1627,7 +2202,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, } else if (qid1) { qid = qid1; } else if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle; /* Now qid is genuine qdisc handle consistent * both with parent and child. @@ -1638,7 +2213,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle; } /* OK. Locate qdisc */ @@ -1659,7 +2234,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, clid = TC_H_MAKE(qid, clid); if (clid) - cl = cops->get(q, clid); + cl = cops->find(q, clid); if (cl == 0) { err = -ENOENT; @@ -1674,15 +2249,12 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, goto out; break; case RTM_DELTCLASS: - err = -EOPNOTSUPP; - if (cops->delete) - err = cops->delete(q, cl); - if (err == 0) - tclass_notify(net, skb, n, q, cl, - RTM_DELTCLASS); + err = tclass_del_notify(net, cops, skb, n, q, cl, extack); + /* Unbind the class with flilters with 0 */ + tc_bind_tclass(q, portid, clid, 0); goto out; case RTM_GETTCLASS: - err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS); + err = tclass_get_notify(net, skb, n, q, cl, extack); goto out; default: err = -EINVAL; @@ -1690,85 +2262,54 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, } } + if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { + NL_SET_ERR_MSG(extack, "Shared blocks are not supported for classes"); + return -EOPNOTSUPP; + } + + /* Prevent creation of traffic classes with classid TC_H_ROOT */ + if (clid == TC_H_ROOT) { + NL_SET_ERR_MSG(extack, "Cannot create traffic class with classid TC_H_ROOT"); + return -EINVAL; + } + new_cl = cl; err = -EOPNOTSUPP; if (cops->change) - err = cops->change(q, clid, portid, tca, &new_cl); - if (err == 0) - tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS); - + err = cops->change(q, clid, portid, tca, &new_cl, extack); + if (err == 0) { + tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS, extack); + /* We just create a new class, need to do reverse binding. */ + if (cl != new_cl) + tc_bind_tclass(q, portid, clid, new_cl); + } out: - if (cl) - cops->put(q, cl); - return err; } - -static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, - unsigned long cl, - u32 portid, u32 seq, u16 flags, int event) +static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) { - struct tcmsg *tcm; - struct nlmsghdr *nlh; - unsigned char *b = skb_tail_pointer(skb); - struct gnet_dump d; - const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; - - cond_resched(); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); - if (!nlh) - goto out_nlmsg_trim; - tcm = nlmsg_data(nlh); - tcm->tcm_family = AF_UNSPEC; - tcm->tcm__pad1 = 0; - tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(q)->ifindex; - tcm->tcm_parent = q->handle; - tcm->tcm_handle = q->handle; - tcm->tcm_info = 0; - if (nla_put_string(skb, TCA_KIND, q->ops->id)) - goto nla_put_failure; - if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0) - goto nla_put_failure; - - if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, - NULL, &d, TCA_PAD) < 0) - goto nla_put_failure; - - if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0) - goto nla_put_failure; - - if (gnet_stats_finish_copy(&d) < 0) - goto nla_put_failure; - - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; - -out_nlmsg_trim: -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} + struct net *net = sock_net(skb->sk); + struct tcmsg *tcm = nlmsg_data(n); + struct nlattr *tca[TCA_MAX + 1]; + struct net_device *dev; + int err; -static int tclass_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, struct Qdisc *q, - unsigned long cl, int event) -{ - struct sk_buff *skb; - u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, extack); + if (err < 0) + return err; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) + return -ENODEV; - if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event) < 0) { - kfree_skb(skb); - return -EINVAL; - } + netdev_lock_ops(dev); + err = __tc_ctl_tclass(skb, n, extack, dev, tca, tcm); + netdev_unlock_ops(dev); - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + return err; } struct qdisc_dump_args { @@ -1784,7 +2325,7 @@ static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTCLASS); + RTM_NEWTCLASS, NULL); } static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, @@ -1818,7 +2359,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, - int *t_p, int s_t) + int *t_p, int s_t, bool recur) { struct Qdisc *q; int b; @@ -1829,12 +2370,13 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; - if (!qdisc_dev(root)) + if (!qdisc_dev(root) || !recur) return 0; if (tcm->tcm_parent) { q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent)); - if (q && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) + if (q && q != root && + tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; return 0; } @@ -1846,39 +2388,54 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, return 0; } -static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) +static int __tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb, + struct tcmsg *tcm, struct net_device *dev) { - struct tcmsg *tcm = nlmsg_data(cb->nlh); - struct net *net = sock_net(skb->sk); struct netdev_queue *dev_queue; - struct net_device *dev; int t, s_t; - if (nlmsg_len(cb->nlh) < sizeof(*tcm)) - return 0; - dev = dev_get_by_index(net, tcm->tcm_ifindex); - if (!dev) - return 0; - s_t = cb->args[0]; t = 0; - if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), + skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, - &t, s_t) < 0) + tc_dump_tclass_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, tcm, cb, &t, s_t, false) < 0) goto done; done: cb->args[0] = t; - dev_put(dev); return skb->len; } +static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int err; + + if (nlmsg_len(cb->nlh) < sizeof(*tcm)) + return 0; + + dev = dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) + return 0; + + netdev_lock_ops(dev); + err = __tc_dump_tclass(skb, cb, tcm, dev); + netdev_unlock_ops(dev); + + dev_put(dev); + + return err; +} + #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { @@ -1890,24 +2447,11 @@ static int psched_show(struct seq_file *seq, void *v) return 0; } -static int psched_open(struct inode *inode, struct file *file) -{ - return single_open(file, psched_show, NULL); -} - -static const struct file_operations psched_fops = { - .owner = THIS_MODULE, - .open = psched_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __net_init psched_net_init(struct net *net) { struct proc_dir_entry *e; - e = proc_create("psched", 0, net->proc_net, &psched_fops); + e = proc_create_single("psched", 0, net->proc_net, psched_show); if (e == NULL) return -ENOMEM; @@ -1934,6 +2478,21 @@ static struct pernet_operations psched_net_ops = { .exit = psched_net_exit, }; +#if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) +DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); +#endif + +static const struct rtnl_msg_handler psched_rtnl_msg_handlers[] __initconst = { + {.msgtype = RTM_NEWQDISC, .doit = tc_modify_qdisc}, + {.msgtype = RTM_DELQDISC, .doit = tc_get_qdisc}, + {.msgtype = RTM_GETQDISC, .doit = tc_get_qdisc, + .dumpit = tc_dump_qdisc}, + {.msgtype = RTM_NEWTCLASS, .doit = tc_ctl_tclass}, + {.msgtype = RTM_DELTCLASS, .doit = tc_ctl_tclass}, + {.msgtype = RTM_GETTCLASS, .doit = tc_ctl_tclass, + .dumpit = tc_dump_tclass}, +}; + static int __init pktsched_init(void) { int err; @@ -1952,14 +2511,9 @@ static int __init pktsched_init(void) register_qdisc(&mq_qdisc_ops); register_qdisc(&noqueue_qdisc_ops); - rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, - NULL); - rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, - NULL); + rtnl_register_many(psched_rtnl_msg_handlers); + + tc_wrapper_init(); return 0; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c deleted file mode 100644 index 572fe2584e48..000000000000 --- a/net/sched/sch_atm.c +++ /dev/null @@ -1,694 +0,0 @@ -/* net/sched/sch_atm.c - ATM VC selection "queueing discipline" */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/atmdev.h> -#include <linux/atmclip.h> -#include <linux/rtnetlink.h> -#include <linux/file.h> /* for fput */ -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - -/* - * The ATM queuing discipline provides a framework for invoking classifiers - * (aka "filters"), which in turn select classes of this queuing discipline. - * Each class maps the flow(s) it is handling to a given VC. Multiple classes - * may share the same VC. - * - * When creating a class, VCs are specified by passing the number of the open - * socket descriptor by which the calling process references the VC. The kernel - * keeps the VC open at least until all classes using it are removed. - * - * In this file, most functions are named atm_tc_* to avoid confusion with all - * the atm_* in net/atm. This naming convention differs from what's used in the - * rest of net/sched. - * - * Known bugs: - * - sometimes messes up the IP stack - * - any manipulations besides the few operations described in the README, are - * untested and likely to crash the system - * - should lock the flow while there is data in the queue (?) - */ - -#define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - -struct atm_flow_data { - struct Qdisc *q; /* FIFO, TBF, etc. */ - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc, - struct sk_buff *skb); /* chaining */ - struct atm_qdisc_data *parent; /* parent qdisc */ - struct socket *sock; /* for closing */ - u32 classid; /* x:y type ID */ - int ref; /* reference count */ - struct gnet_stats_basic_packed bstats; - struct gnet_stats_queue qstats; - struct list_head list; - struct atm_flow_data *excess; /* flow for excess traffic; - NULL to set CLP instead */ - int hdr_len; - unsigned char hdr[0]; /* header data; MUST BE LAST */ -}; - -struct atm_qdisc_data { - struct atm_flow_data link; /* unclassified skbs go here */ - struct list_head flows; /* NB: "link" is also on this - list */ - struct tasklet_struct task; /* dequeue tasklet */ -}; - -/* ------------------------- Class/flow operations ------------------------- */ - -static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - list_for_each_entry(flow, &p->flows, list) { - if (flow->classid == classid) - return flow; - } - return NULL; -} - -static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", - sch, p, flow, new, old); - if (list_empty(&flow->list)) - return -EINVAL; - if (!new) - new = &noop_qdisc; - *old = flow->q; - flow->q = new; - if (*old) - qdisc_reset(*old); - return 0; -} - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); - return flow ? flow->q : NULL; -} - -static unsigned long atm_tc_get(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_get(sch %p,[qdisc %p],classid %x)\n", sch, p, classid); - flow = lookup_flow(sch, classid); - if (flow) - flow->ref++; - pr_debug("atm_tc_get: flow %p\n", flow); - return (unsigned long)flow; -} - -static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - return atm_tc_get(sch, classid); -} - -/* - * atm_tc_put handles all destructions, including the ones that are explicitly - * requested (atm_tc_destroy, etc.). The assumption here is that we never drop - * anything that still seems to be in use. - */ -static void atm_tc_put(struct Qdisc *sch, unsigned long cl) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (--flow->ref) - return; - pr_debug("atm_tc_put: destroying\n"); - list_del_init(&flow->list); - pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_destroy(flow->q); - tcf_block_put(flow->block); - if (flow->sock) { - pr_debug("atm_tc_put: f_count %ld\n", - file_count(flow->sock->file)); - flow->vcc->pop = flow->old_pop; - sockfd_put(flow->sock); - } - if (flow->excess) - atm_tc_put(sch, (unsigned long)flow->excess); - if (flow != &p->link) - kfree(flow); - /* - * If flow == &p->link, the qdisc no longer works at this point and - * needs to be removed. (By the caller of atm_tc_put.) - */ -} - -static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) -{ - struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - - pr_debug("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); - VCC2FLOW(vcc)->old_pop(vcc, skb); - tasklet_schedule(&p->task); -} - -static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ - 0x00, 0x00, - 0x08, 0x00 -}; /* Ethertype IP (0800) */ - -static const struct nla_policy atm_policy[TCA_ATM_MAX + 1] = { - [TCA_ATM_FD] = { .type = NLA_U32 }, - [TCA_ATM_EXCESS] = { .type = NLA_U32 }, -}; - -static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)*arg; - struct atm_flow_data *excess = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_ATM_MAX + 1]; - struct socket *sock; - int fd, error, hdr_len; - void *hdr; - - pr_debug("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); - /* - * The concept of parents doesn't apply for this qdisc. - */ - if (parent && parent != TC_H_ROOT && parent != sch->handle) - return -EINVAL; - /* - * ATM classes cannot be changed. In order to change properties of the - * ATM connection, that socket needs to be modified directly (via the - * native ATM API. In order to send a flow to a different VC, the old - * class needs to be removed and a new one added. (This may be changed - * later.) - */ - if (flow) - return -EBUSY; - if (opt == NULL) - return -EINVAL; - - error = nla_parse_nested(tb, TCA_ATM_MAX, opt, atm_policy, NULL); - if (error < 0) - return error; - - if (!tb[TCA_ATM_FD]) - return -EINVAL; - fd = nla_get_u32(tb[TCA_ATM_FD]); - pr_debug("atm_tc_change: fd %d\n", fd); - if (tb[TCA_ATM_HDR]) { - hdr_len = nla_len(tb[TCA_ATM_HDR]); - hdr = nla_data(tb[TCA_ATM_HDR]); - } else { - hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ - } - if (!tb[TCA_ATM_EXCESS]) - excess = NULL; - else { - excess = (struct atm_flow_data *) - atm_tc_get(sch, nla_get_u32(tb[TCA_ATM_EXCESS])); - if (!excess) - return -ENOENT; - } - pr_debug("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->nla_type, nla_len(opt), hdr_len); - sock = sockfd_lookup(fd, &error); - if (!sock) - return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); - if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { - error = -EPROTOTYPE; - goto err_out; - } - /* @@@ should check if the socket is really operational or we'll crash - on vcc->send */ - if (classid) { - if (TC_H_MAJ(classid ^ sch->handle)) { - pr_debug("atm_tc_change: classid mismatch\n"); - error = -EINVAL; - goto err_out; - } - } else { - int i; - unsigned long cl; - - for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle, 0x8000 | i); - cl = atm_tc_get(sch, classid); - if (!cl) - break; - atm_tc_put(sch, cl); - } - } - pr_debug("atm_tc_change: new id %x\n", classid); - flow = kzalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); - pr_debug("atm_tc_change: flow %p\n", flow); - if (!flow) { - error = -ENOBUFS; - goto err_out; - } - - error = tcf_block_get(&flow->block, &flow->filter_list); - if (error) { - kfree(flow); - goto err_out; - } - - flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); - if (!flow->q) - flow->q = &noop_qdisc; - pr_debug("atm_tc_change: qdisc %p\n", flow->q); - flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ - flow->vcc->user_back = flow; - pr_debug("atm_tc_change: vcc %p\n", flow->vcc); - flow->old_pop = flow->vcc->pop; - flow->parent = p; - flow->vcc->pop = sch_atm_pop; - flow->classid = classid; - flow->ref = 1; - flow->excess = excess; - list_add(&flow->list, &p->link.list); - flow->hdr_len = hdr_len; - if (hdr) - memcpy(flow->hdr, hdr, hdr_len); - else - memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); - *arg = (unsigned long)flow; - return 0; -err_out: - if (excess) - atm_tc_put(sch, (unsigned long)excess); - sockfd_put(sock); - return error; -} - -static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (list_empty(&flow->list)) - return -EINVAL; - if (rcu_access_pointer(flow->filter_list) || flow == &p->link) - return -EBUSY; - /* - * Reference count must be 2: one for "keepalive" (set at class - * creation), and one for the reference held when calling delete. - */ - if (flow->ref < 2) { - pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); - return -EINVAL; - } - if (flow->ref > 2) - return -EBUSY; /* catch references via excess, etc. */ - atm_tc_put(sch, arg); - return 0; -} - -static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); - if (walker->stop) - return; - list_for_each_entry(flow, &p->flows, list) { - if (walker->count >= walker->skip && - walker->fn(sch, (unsigned long)flow, walker) < 0) { - walker->stop = 1; - break; - } - walker->count++; - } -} - -static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? flow->block : p->link.block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct tcf_result res; - int result; - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - - pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - result = TC_ACT_OK; /* be nice to gcc */ - flow = NULL; - if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) { - struct tcf_proto *fl; - - list_for_each_entry(flow, &p->flows, list) { - fl = rcu_dereference_bh(flow->filter_list); - if (fl) { - result = tcf_classify(skb, fl, &res, true); - if (result < 0) - continue; - flow = (struct atm_flow_data *)res.class; - if (!flow) - flow = lookup_flow(sch, res.classid); - goto done; - } - } - flow = NULL; -done: - ; - } - if (!flow) { - flow = &p->link; - } else { - if (flow->vcc) - ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-) */ -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - __qdisc_drop(skb, to_free); - goto drop; - case TC_ACT_RECLASSIFY: - if (flow->excess) - flow = flow->excess; - else - ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; - break; - } -#endif - } - - ret = qdisc_enqueue(skb, flow->q, to_free); - if (ret != NET_XMIT_SUCCESS) { -drop: __maybe_unused - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - if (flow) - flow->qstats.drops++; - } - return ret; - } - /* - * Okay, this may seem weird. We pretend we've dropped the packet if - * it goes via ATM. The reason for this is that the outer qdisc - * expects to be able to q->dequeue the packet later on if we return - * success at this place. Also, sch->q.qdisc needs to reflect whether - * there is a packet egligible for dequeuing or not. Note that the - * statistics of the outer qdisc are necessarily wrong because of all - * this. There's currently no correct solution for this. - */ - if (flow == &p->link) { - sch->q.qlen++; - return NET_XMIT_SUCCESS; - } - tasklet_schedule(&p->task); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -/* - * Dequeue packets and send them over ATM. Note that we quite deliberately - * avoid checking net_device's flow control here, simply because sch_atm - * uses its own channels, which have nothing to do with any CLIP/LANE/or - * non-ATM interfaces. - */ - -static void sch_atm_dequeue(unsigned long data) -{ - struct Qdisc *sch = (struct Qdisc *)data; - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct sk_buff *skb; - - pr_debug("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - if (flow == &p->link) - continue; - /* - * If traffic is properly shaped, this won't generate nasty - * little bursts. Otherwise, it may ... (but that's okay) - */ - while ((skb = flow->q->ops->peek(flow->q))) { - if (!atm_may_send(flow->vcc, skb->truesize)) - break; - - skb = qdisc_dequeue_peeked(flow->q); - if (unlikely(!skb)) - break; - - qdisc_bstats_update(sch, skb); - bstats_update(&flow->bstats, skb); - pr_debug("atm_tc_dequeue: sending on class %p\n", flow); - /* remove any LL header somebody else has attached */ - skb_pull(skb, skb_network_offset(skb)); - if (skb_headroom(skb) < flow->hdr_len) { - struct sk_buff *new; - - new = skb_realloc_headroom(skb, flow->hdr_len); - dev_kfree_skb(skb); - if (!new) - continue; - skb = new; - } - pr_debug("sch_atm_dequeue: ip %p, data %p\n", - skb_network_header(skb), skb->data); - ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb, flow->hdr_len), flow->hdr, - flow->hdr_len); - refcount_add(skb->truesize, - &sk_atm(flow->vcc)->sk_wmem_alloc); - /* atm.atm_options are already set by atm_tc_enqueue */ - flow->vcc->send(flow->vcc, skb); - } - } -} - -static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - - pr_debug("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); - tasklet_schedule(&p->task); - skb = qdisc_dequeue_peeked(p->link.q); - if (skb) - sch->q.qlen--; - return skb; -} - -static struct sk_buff *atm_tc_peek(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - - pr_debug("atm_tc_peek(sch %p,[qdisc %p])\n", sch, p); - - return p->link.q->ops->peek(p->link.q); -} - -static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); - INIT_LIST_HEAD(&p->flows); - INIT_LIST_HEAD(&p->link.list); - list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, sch->handle); - if (!p->link.q) - p->link.q = &noop_qdisc; - pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - - err = tcf_block_get(&p->link.block, &p->link.filter_list); - if (err) - return err; - - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.classid = sch->handle; - p->link.ref = 1; - tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); - return 0; -} - -static void atm_tc_reset(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) - qdisc_reset(flow->q); - sch->q.qlen = 0; -} - -static void atm_tc_destroy(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow, *tmp; - - pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) - tcf_block_put(flow->block); - - list_for_each_entry_safe(flow, tmp, &p->flows, list) { - if (flow->ref > 1) - pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); - atm_tc_put(sch, (unsigned long)flow); - } - tasklet_kill(&p->task); -} - -static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - struct nlattr *nest; - - pr_debug("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch, p, flow, skb, tcm); - if (list_empty(&flow->list)) - return -EINVAL; - tcm->tcm_handle = flow->classid; - tcm->tcm_info = flow->q->handle; - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr)) - goto nla_put_failure; - if (flow->vcc) { - struct sockaddr_atmpvc pvc; - int state; - - memset(&pvc, 0, sizeof(pvc)); - pvc.sap_family = AF_ATMPVC; - pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; - pvc.sap_addr.vpi = flow->vcc->vpi; - pvc.sap_addr.vci = flow->vcc->vci; - if (nla_put(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc)) - goto nla_put_failure; - state = ATM_VF2VS(flow->vcc->flags); - if (nla_put_u32(skb, TCA_ATM_STATE, state)) - goto nla_put_failure; - } - if (flow->excess) { - if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->classid)) - goto nla_put_failure; - } else { - if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) - goto nla_put_failure; - } - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} -static int -atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &flow->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) - return -1; - - return 0; -} - -static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - return 0; -} - -static const struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .get = atm_tc_get, - .put = atm_tc_put, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_block = atm_tc_tcf_block, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, -}; - -static struct Qdisc_ops atm_qdisc_ops __read_mostly = { - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .peek = atm_tc_peek, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .dump = atm_tc_dump, - .owner = THIS_MODULE, -}; - -static int __init atm_init(void) -{ - return register_qdisc(&atm_qdisc_ops); -} - -static void __exit atm_exit(void) -{ - unregister_qdisc(&atm_qdisc_ops); -} - -module_init(atm_init) -module_exit(atm_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c index c98a61e980ba..a7f7667ae984 100644 --- a/net/sched/sch_blackhole.c +++ b/net/sched/sch_blackhole.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_blackhole.c Black hole queue * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Thomas Graf <tgraf@suug.ch> * * Note: Quantum tunneling is not supported. @@ -21,7 +17,7 @@ static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS; + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } static struct sk_buff *blackhole_dequeue(struct Qdisc *sch) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c new file mode 100644 index 000000000000..4a64d6397b6f --- /dev/null +++ b/net/sched/sch_cake.c @@ -0,0 +1,3153 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* COMMON Applications Kept Enhanced (CAKE) discipline + * + * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com> + * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk> + * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com> + * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de> + * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> + * Copyright (C) 2017-2018 Ryan Mounce <ryan@mounce.com.au> + * + * The CAKE Principles: + * (or, how to have your cake and eat it too) + * + * This is a combination of several shaping, AQM and FQ techniques into one + * easy-to-use package: + * + * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE + * equipment and bloated MACs. This operates in deficit mode (as in sch_fq), + * eliminating the need for any sort of burst parameter (eg. token bucket + * depth). Burst support is limited to that necessary to overcome scheduling + * latency. + * + * - A Diffserv-aware priority queue, giving more priority to certain classes, + * up to a specified fraction of bandwidth. Above that bandwidth threshold, + * the priority is reduced to avoid starving other tins. + * + * - Each priority tin has a separate Flow Queue system, to isolate traffic + * flows from each other. This prevents a burst on one flow from increasing + * the delay to another. Flows are distributed to queues using a + * set-associative hash function. + * + * - Each queue is actively managed by Cobalt, which is a combination of the + * Codel and Blue AQM algorithms. This serves flows fairly, and signals + * congestion early via ECN (if available) and/or packet drops, to keep + * latency low. The codel parameters are auto-tuned based on the bandwidth + * setting, as is necessary at low bandwidths. + * + * The configuration parameters are kept deliberately simple for ease of use. + * Everything has sane defaults. Complete generality of configuration is *not* + * a goal. + * + * The priority queue operates according to a weighted DRR scheme, combined with + * a bandwidth tracker which reuses the shaper logic to detect which side of the + * bandwidth sharing threshold the tin is operating. This determines whether a + * priority-based weight (high) or a bandwidth-based weight (low) is used for + * that tin in the current pass. + * + * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly + * granted us permission to leverage. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/jiffies.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/skbuff.h> +#include <linux/jhash.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/reciprocal_div.h> +#include <net/netlink.h> +#include <linux/if_vlan.h> +#include <net/gso.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/tcp.h> +#include <net/flow_dissector.h> + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack_core.h> +#endif + +#define CAKE_SET_WAYS (8) +#define CAKE_MAX_TINS (8) +#define CAKE_QUEUES (1024) +#define CAKE_FLOW_MASK 63 +#define CAKE_FLOW_NAT_FLAG 64 + +/* struct cobalt_params - contains codel and blue parameters + * @interval: codel initial drop rate + * @target: maximum persistent sojourn time & blue update rate + * @mtu_time: serialisation delay of maximum-size packet + * @p_inc: increment of blue drop probability (0.32 fxp) + * @p_dec: decrement of blue drop probability (0.32 fxp) + */ +struct cobalt_params { + u64 interval; + u64 target; + u64 mtu_time; + u32 p_inc; + u32 p_dec; +}; + +/* struct cobalt_vars - contains codel and blue variables + * @count: codel dropping frequency + * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 + * @drop_next: time to drop next packet, or when we dropped last + * @blue_timer: Blue time to next drop + * @p_drop: BLUE drop probability (0.32 fxp) + * @dropping: set if in dropping state + * @ecn_marked: set if marked + */ +struct cobalt_vars { + u32 count; + u32 rec_inv_sqrt; + ktime_t drop_next; + ktime_t blue_timer; + u32 p_drop; + bool dropping; + bool ecn_marked; +}; + +enum { + CAKE_SET_NONE = 0, + CAKE_SET_SPARSE, + CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */ + CAKE_SET_BULK, + CAKE_SET_DECAYING +}; + +struct cake_flow { + /* this stuff is all needed per-flow at dequeue time */ + struct sk_buff *head; + struct sk_buff *tail; + struct list_head flowchain; + s32 deficit; + u32 dropped; + struct cobalt_vars cvars; + u16 srchost; /* index into cake_host table */ + u16 dsthost; + u8 set; +}; /* please try to keep this structure <= 64 bytes */ + +struct cake_host { + u32 srchost_tag; + u32 dsthost_tag; + u16 srchost_bulk_flow_count; + u16 dsthost_bulk_flow_count; +}; + +struct cake_heap_entry { + u16 t:3, b:10; +}; + +struct cake_tin_data { + struct cake_flow flows[CAKE_QUEUES]; + u32 backlogs[CAKE_QUEUES]; + u32 tags[CAKE_QUEUES]; /* for set association */ + u16 overflow_idx[CAKE_QUEUES]; + struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */ + u16 flow_quantum; + + struct cobalt_params cparams; + u32 drop_overlimit; + u16 bulk_flow_count; + u16 sparse_flow_count; + u16 decaying_flow_count; + u16 unresponsive_flow_count; + + u32 max_skblen; + + struct list_head new_flows; + struct list_head old_flows; + struct list_head decaying_flows; + + /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ + ktime_t time_next_packet; + u64 tin_rate_ns; + u64 tin_rate_bps; + u16 tin_rate_shft; + + u16 tin_quantum; + s32 tin_deficit; + u32 tin_backlog; + u32 tin_dropped; + u32 tin_ecn_mark; + + u32 packets; + u64 bytes; + + u32 ack_drops; + + /* moving averages */ + u64 avge_delay; + u64 peak_delay; + u64 base_delay; + + /* hash function stats */ + u32 way_directs; + u32 way_hits; + u32 way_misses; + u32 way_collisions; +}; /* number of tins is small, so size of this struct doesn't matter much */ + +struct cake_sched_data { + struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; + struct cake_tin_data *tins; + + struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS]; + u16 overflow_timeout; + + u16 tin_cnt; + u8 tin_mode; + u8 flow_mode; + u8 ack_filter; + u8 atm_mode; + + u32 fwmark_mask; + u16 fwmark_shft; + + /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ + u16 rate_shft; + ktime_t time_next_packet; + ktime_t failsafe_next_packet; + u64 rate_ns; + u64 rate_bps; + u16 rate_flags; + s16 rate_overhead; + u16 rate_mpu; + u64 interval; + u64 target; + + /* resource tracking */ + u32 buffer_used; + u32 buffer_max_used; + u32 buffer_limit; + u32 buffer_config_limit; + + /* indices for dequeue */ + u16 cur_tin; + u16 cur_flow; + + struct qdisc_watchdog watchdog; + const u8 *tin_index; + const u8 *tin_order; + + /* bandwidth capacity estimate */ + ktime_t last_packet_time; + ktime_t avg_window_begin; + u64 avg_packet_interval; + u64 avg_window_bytes; + u64 avg_peak_bandwidth; + ktime_t last_reconfig_time; + + /* packet length stats */ + u32 avg_netoff; + u16 max_netlen; + u16 max_adjlen; + u16 min_netlen; + u16 min_adjlen; +}; + +enum { + CAKE_FLAG_OVERHEAD = BIT(0), + CAKE_FLAG_AUTORATE_INGRESS = BIT(1), + CAKE_FLAG_INGRESS = BIT(2), + CAKE_FLAG_WASH = BIT(3), + CAKE_FLAG_SPLIT_GSO = BIT(4) +}; + +/* COBALT operates the Codel and BLUE algorithms in parallel, in order to + * obtain the best features of each. Codel is excellent on flows which + * respond to congestion signals in a TCP-like way. BLUE is more effective on + * unresponsive flows. + */ + +struct cobalt_skb_cb { + ktime_t enqueue_time; + u32 adjusted_len; +}; + +static u64 us_to_ns(u64 us) +{ + return us * NSEC_PER_USEC; +} + +static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb) +{ + qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb)); + return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data; +} + +static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb) +{ + return get_cobalt_cb(skb)->enqueue_time; +} + +static void cobalt_set_enqueue_time(struct sk_buff *skb, + ktime_t now) +{ + get_cobalt_cb(skb)->enqueue_time = now; +} + +static u16 quantum_div[CAKE_QUEUES + 1] = {0}; + +/* Diffserv lookup tables */ + +static const u8 precedence[] = { + 0, 0, 0, 0, 0, 0, 0, 0, + 1, 1, 1, 1, 1, 1, 1, 1, + 2, 2, 2, 2, 2, 2, 2, 2, + 3, 3, 3, 3, 3, 3, 3, 3, + 4, 4, 4, 4, 4, 4, 4, 4, + 5, 5, 5, 5, 5, 5, 5, 5, + 6, 6, 6, 6, 6, 6, 6, 6, + 7, 7, 7, 7, 7, 7, 7, 7, +}; + +static const u8 diffserv8[] = { + 2, 0, 1, 2, 4, 2, 2, 2, + 1, 2, 1, 2, 1, 2, 1, 2, + 5, 2, 4, 2, 4, 2, 4, 2, + 3, 2, 3, 2, 3, 2, 3, 2, + 6, 2, 3, 2, 3, 2, 3, 2, + 6, 2, 2, 2, 6, 2, 6, 2, + 7, 2, 2, 2, 2, 2, 2, 2, + 7, 2, 2, 2, 2, 2, 2, 2, +}; + +static const u8 diffserv4[] = { + 0, 1, 0, 0, 2, 0, 0, 0, + 1, 0, 0, 0, 0, 0, 0, 0, + 2, 0, 2, 0, 2, 0, 2, 0, + 2, 0, 2, 0, 2, 0, 2, 0, + 3, 0, 2, 0, 2, 0, 2, 0, + 3, 0, 0, 0, 3, 0, 3, 0, + 3, 0, 0, 0, 0, 0, 0, 0, + 3, 0, 0, 0, 0, 0, 0, 0, +}; + +static const u8 diffserv3[] = { + 0, 1, 0, 0, 2, 0, 0, 0, + 1, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 2, 0, 2, 0, + 2, 0, 0, 0, 0, 0, 0, 0, + 2, 0, 0, 0, 0, 0, 0, 0, +}; + +static const u8 besteffort[] = { + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, +}; + +/* tin priority order for stats dumping */ + +static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7}; +static const u8 bulk_order[] = {1, 0, 2, 3}; + +/* There is a big difference in timing between the accurate values placed in the + * cache and the approximations given by a single Newton step for small count + * values, particularly when stepping from count 1 to 2 or vice versa. Hence, + * these values are calculated using eight Newton steps, using the + * implementation below. Above 16, a single Newton step gives sufficient + * accuracy in either direction, given the precision stored. + * + * The magnitude of the error when stepping up to count 2 is such as to give the + * value that *should* have been produced at count 4. + */ + +#define REC_INV_SQRT_CACHE (16) +static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { + ~0, ~0, 3037000500, 2479700525, + 2147483647, 1920767767, 1753413056, 1623345051, + 1518500250, 1431655765, 1358187914, 1294981364, + 1239850263, 1191209601, 1147878294, 1108955788 +}; + +/* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots + * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) + * + * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 + */ + +static void cobalt_newton_step(struct cobalt_vars *vars) +{ + u32 invsqrt, invsqrt2; + u64 val; + + invsqrt = vars->rec_inv_sqrt; + invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; + val = (3LL << 32) - ((u64)vars->count * invsqrt2); + + val >>= 2; /* avoid overflow in following multiply */ + val = (val * invsqrt) >> (32 - 2 + 1); + + vars->rec_inv_sqrt = val; +} + +static void cobalt_invsqrt(struct cobalt_vars *vars) +{ + if (vars->count < REC_INV_SQRT_CACHE) + vars->rec_inv_sqrt = inv_sqrt_cache[vars->count]; + else + cobalt_newton_step(vars); +} + +static void cobalt_vars_init(struct cobalt_vars *vars) +{ + memset(vars, 0, sizeof(*vars)); +} + +/* CoDel control_law is t + interval/sqrt(count) + * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid + * both sqrt() and divide operation. + */ +static ktime_t cobalt_control(ktime_t t, + u64 interval, + u32 rec_inv_sqrt) +{ + return ktime_add_ns(t, reciprocal_scale(interval, + rec_inv_sqrt)); +} + +/* Call this when a packet had to be dropped due to queue overflow. Returns + * true if the BLUE state was quiescent before but active after this call. + */ +static bool cobalt_queue_full(struct cobalt_vars *vars, + struct cobalt_params *p, + ktime_t now) +{ + bool up = false; + + if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { + up = !vars->p_drop; + vars->p_drop += p->p_inc; + if (vars->p_drop < p->p_inc) + vars->p_drop = ~0; + vars->blue_timer = now; + } + vars->dropping = true; + vars->drop_next = now; + if (!vars->count) + vars->count = 1; + + return up; +} + +/* Call this when the queue was serviced but turned out to be empty. Returns + * true if the BLUE state was active before but quiescent after this call. + */ +static bool cobalt_queue_empty(struct cobalt_vars *vars, + struct cobalt_params *p, + ktime_t now) +{ + bool down = false; + + if (vars->p_drop && + ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { + if (vars->p_drop < p->p_dec) + vars->p_drop = 0; + else + vars->p_drop -= p->p_dec; + vars->blue_timer = now; + down = !vars->p_drop; + } + vars->dropping = false; + + if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) { + vars->count--; + cobalt_invsqrt(vars); + vars->drop_next = cobalt_control(vars->drop_next, + p->interval, + vars->rec_inv_sqrt); + } + + return down; +} + +/* Call this with a freshly dequeued packet for possible congestion marking. + * Returns true as an instruction to drop the packet, false for delivery. + */ +static enum skb_drop_reason cobalt_should_drop(struct cobalt_vars *vars, + struct cobalt_params *p, + ktime_t now, + struct sk_buff *skb, + u32 bulk_flows) +{ + enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; + bool next_due, over_target; + ktime_t schedule; + u64 sojourn; + +/* The 'schedule' variable records, in its sign, whether 'now' is before or + * after 'drop_next'. This allows 'drop_next' to be updated before the next + * scheduling decision is actually branched, without destroying that + * information. Similarly, the first 'schedule' value calculated is preserved + * in the boolean 'next_due'. + * + * As for 'drop_next', we take advantage of the fact that 'interval' is both + * the delay between first exceeding 'target' and the first signalling event, + * *and* the scaling factor for the signalling frequency. It's therefore very + * natural to use a single mechanism for both purposes, and eliminates a + * significant amount of reference Codel's spaghetti code. To help with this, + * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close + * as possible to 1.0 in fixed-point. + */ + + sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); + schedule = ktime_sub(now, vars->drop_next); + over_target = sojourn > p->target && + sojourn > p->mtu_time * bulk_flows * 2 && + sojourn > p->mtu_time * 4; + next_due = vars->count && ktime_to_ns(schedule) >= 0; + + vars->ecn_marked = false; + + if (over_target) { + if (!vars->dropping) { + vars->dropping = true; + vars->drop_next = cobalt_control(now, + p->interval, + vars->rec_inv_sqrt); + } + if (!vars->count) + vars->count = 1; + } else if (vars->dropping) { + vars->dropping = false; + } + + if (next_due && vars->dropping) { + /* Use ECN mark if possible, otherwise drop */ + if (!(vars->ecn_marked = INET_ECN_set_ce(skb))) + reason = SKB_DROP_REASON_QDISC_CONGESTED; + + vars->count++; + if (!vars->count) + vars->count--; + cobalt_invsqrt(vars); + vars->drop_next = cobalt_control(vars->drop_next, + p->interval, + vars->rec_inv_sqrt); + schedule = ktime_sub(now, vars->drop_next); + } else { + while (next_due) { + vars->count--; + cobalt_invsqrt(vars); + vars->drop_next = cobalt_control(vars->drop_next, + p->interval, + vars->rec_inv_sqrt); + schedule = ktime_sub(now, vars->drop_next); + next_due = vars->count && ktime_to_ns(schedule) >= 0; + } + } + + /* Simple BLUE implementation. Lack of ECN is deliberate. */ + if (vars->p_drop && reason == SKB_NOT_DROPPED_YET && + get_random_u32() < vars->p_drop) + reason = SKB_DROP_REASON_CAKE_FLOOD; + + /* Overload the drop_next field as an activity timeout */ + if (!vars->count) + vars->drop_next = ktime_add_ns(now, p->interval); + else if (ktime_to_ns(schedule) > 0 && reason == SKB_NOT_DROPPED_YET) + vars->drop_next = now; + + return reason; +} + +static bool cake_update_flowkeys(struct flow_keys *keys, + const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + struct nf_conntrack_tuple tuple = {}; + bool rev = !skb->_nfct, upd = false; + __be32 ip; + + if (skb_protocol(skb, true) != htons(ETH_P_IP)) + return false; + + if (!nf_ct_get_tuple_skb(&tuple, skb)) + return false; + + ip = rev ? tuple.dst.u3.ip : tuple.src.u3.ip; + if (ip != keys->addrs.v4addrs.src) { + keys->addrs.v4addrs.src = ip; + upd = true; + } + ip = rev ? tuple.src.u3.ip : tuple.dst.u3.ip; + if (ip != keys->addrs.v4addrs.dst) { + keys->addrs.v4addrs.dst = ip; + upd = true; + } + + if (keys->ports.ports) { + __be16 port; + + port = rev ? tuple.dst.u.all : tuple.src.u.all; + if (port != keys->ports.src) { + keys->ports.src = port; + upd = true; + } + port = rev ? tuple.src.u.all : tuple.dst.u.all; + if (port != keys->ports.dst) { + port = keys->ports.dst; + upd = true; + } + } + return upd; +#else + return false; +#endif +} + +/* Cake has several subtle multiple bit settings. In these cases you + * would be matching triple isolate mode as well. + */ + +static bool cake_dsrc(int flow_mode) +{ + return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC; +} + +static bool cake_ddst(int flow_mode) +{ + return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST; +} + +static void cake_dec_srchost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_dsrc(flow_mode) && + q->hosts[flow->srchost].srchost_bulk_flow_count)) + q->hosts[flow->srchost].srchost_bulk_flow_count--; +} + +static void cake_inc_srchost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_dsrc(flow_mode) && + q->hosts[flow->srchost].srchost_bulk_flow_count < CAKE_QUEUES)) + q->hosts[flow->srchost].srchost_bulk_flow_count++; +} + +static void cake_dec_dsthost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_ddst(flow_mode) && + q->hosts[flow->dsthost].dsthost_bulk_flow_count)) + q->hosts[flow->dsthost].dsthost_bulk_flow_count--; +} + +static void cake_inc_dsthost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_ddst(flow_mode) && + q->hosts[flow->dsthost].dsthost_bulk_flow_count < CAKE_QUEUES)) + q->hosts[flow->dsthost].dsthost_bulk_flow_count++; +} + +static u16 cake_get_flow_quantum(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + u16 host_load = 1; + + if (cake_dsrc(flow_mode)) + host_load = max(host_load, + q->hosts[flow->srchost].srchost_bulk_flow_count); + + if (cake_ddst(flow_mode)) + host_load = max(host_load, + q->hosts[flow->dsthost].dsthost_bulk_flow_count); + + /* The get_random_u16() is a way to apply dithering to avoid + * accumulating roundoff errors + */ + return (q->flow_quantum * quantum_div[host_load] + + get_random_u16()) >> 16; +} + +static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, + int flow_mode, u16 flow_override, u16 host_override) +{ + bool hash_flows = (!flow_override && !!(flow_mode & CAKE_FLOW_FLOWS)); + bool hash_hosts = (!host_override && !!(flow_mode & CAKE_FLOW_HOSTS)); + bool nat_enabled = !!(flow_mode & CAKE_FLOW_NAT_FLAG); + u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0; + u16 reduced_hash, srchost_idx, dsthost_idx; + struct flow_keys keys, host_keys; + bool use_skbhash = skb->l4_hash; + + if (unlikely(flow_mode == CAKE_FLOW_NONE)) + return 0; + + /* If both overrides are set, or we can use the SKB hash and nat mode is + * disabled, we can skip packet dissection entirely. If nat mode is + * enabled there's another check below after doing the conntrack lookup. + */ + if ((!hash_flows || (use_skbhash && !nat_enabled)) && !hash_hosts) + goto skip_hash; + + skb_flow_dissect_flow_keys(skb, &keys, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + /* Don't use the SKB hash if we change the lookup keys from conntrack */ + if (nat_enabled && cake_update_flowkeys(&keys, skb)) + use_skbhash = false; + + /* If we can still use the SKB hash and don't need the host hash, we can + * skip the rest of the hashing procedure + */ + if (use_skbhash && !hash_hosts) + goto skip_hash; + + /* flow_hash_from_keys() sorts the addresses by value, so we have + * to preserve their order in a separate data structure to treat + * src and dst host addresses as independently selectable. + */ + host_keys = keys; + host_keys.ports.ports = 0; + host_keys.basic.ip_proto = 0; + host_keys.keyid.keyid = 0; + host_keys.tags.flow_label = 0; + + switch (host_keys.control.addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + host_keys.addrs.v4addrs.src = 0; + dsthost_hash = flow_hash_from_keys(&host_keys); + host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + host_keys.addrs.v4addrs.dst = 0; + srchost_hash = flow_hash_from_keys(&host_keys); + break; + + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + memset(&host_keys.addrs.v6addrs.src, 0, + sizeof(host_keys.addrs.v6addrs.src)); + dsthost_hash = flow_hash_from_keys(&host_keys); + host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + memset(&host_keys.addrs.v6addrs.dst, 0, + sizeof(host_keys.addrs.v6addrs.dst)); + srchost_hash = flow_hash_from_keys(&host_keys); + break; + + default: + dsthost_hash = 0; + srchost_hash = 0; + } + + /* This *must* be after the above switch, since as a + * side-effect it sorts the src and dst addresses. + */ + if (hash_flows && !use_skbhash) + flow_hash = flow_hash_from_keys(&keys); + +skip_hash: + if (flow_override) + flow_hash = flow_override - 1; + else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS)) + flow_hash = skb->hash; + if (host_override) { + dsthost_hash = host_override - 1; + srchost_hash = host_override - 1; + } + + if (!(flow_mode & CAKE_FLOW_FLOWS)) { + if (flow_mode & CAKE_FLOW_SRC_IP) + flow_hash ^= srchost_hash; + + if (flow_mode & CAKE_FLOW_DST_IP) + flow_hash ^= dsthost_hash; + } + + reduced_hash = flow_hash % CAKE_QUEUES; + + /* set-associative hashing */ + /* fast path if no hash collision (direct lookup succeeds) */ + if (likely(q->tags[reduced_hash] == flow_hash && + q->flows[reduced_hash].set)) { + q->way_directs++; + } else { + u32 inner_hash = reduced_hash % CAKE_SET_WAYS; + u32 outer_hash = reduced_hash - inner_hash; + bool allocate_src = false; + bool allocate_dst = false; + u32 i, k; + + /* check if any active queue in the set is reserved for + * this flow. + */ + for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (q->tags[outer_hash + k] == flow_hash) { + if (i) + q->way_hits++; + + if (!q->flows[outer_hash + k].set) { + /* need to increment host refcnts */ + allocate_src = cake_dsrc(flow_mode); + allocate_dst = cake_ddst(flow_mode); + } + + goto found; + } + } + + /* no queue is reserved for this flow, look for an + * empty one. + */ + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (!q->flows[outer_hash + k].set) { + q->way_misses++; + allocate_src = cake_dsrc(flow_mode); + allocate_dst = cake_ddst(flow_mode); + goto found; + } + } + + /* With no empty queues, default to the original + * queue, accept the collision, update the host tags. + */ + q->way_collisions++; + allocate_src = cake_dsrc(flow_mode); + allocate_dst = cake_ddst(flow_mode); + + if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { + cake_dec_srchost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); + cake_dec_dsthost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); + } +found: + /* reserve queue for future packets in same flow */ + reduced_hash = outer_hash + k; + q->tags[reduced_hash] = flow_hash; + + if (allocate_src) { + srchost_idx = srchost_hash % CAKE_QUEUES; + inner_hash = srchost_idx % CAKE_SET_WAYS; + outer_hash = srchost_idx - inner_hash; + for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (q->hosts[outer_hash + k].srchost_tag == + srchost_hash) + goto found_src; + } + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (!q->hosts[outer_hash + k].srchost_bulk_flow_count) + break; + } + q->hosts[outer_hash + k].srchost_tag = srchost_hash; +found_src: + srchost_idx = outer_hash + k; + q->flows[reduced_hash].srchost = srchost_idx; + + if (q->flows[reduced_hash].set == CAKE_SET_BULK) + cake_inc_srchost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); + } + + if (allocate_dst) { + dsthost_idx = dsthost_hash % CAKE_QUEUES; + inner_hash = dsthost_idx % CAKE_SET_WAYS; + outer_hash = dsthost_idx - inner_hash; + for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (q->hosts[outer_hash + k].dsthost_tag == + dsthost_hash) + goto found_dst; + } + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (!q->hosts[outer_hash + k].dsthost_bulk_flow_count) + break; + } + q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; +found_dst: + dsthost_idx = outer_hash + k; + q->flows[reduced_hash].dsthost = dsthost_idx; + + if (q->flows[reduced_hash].set == CAKE_SET_BULK) + cake_inc_dsthost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); + } + } + + return reduced_hash; +} + +/* helper functions : might be changed when/if skb use a standard list_head */ +/* remove one skb from head of slot queue */ + +static struct sk_buff *dequeue_head(struct cake_flow *flow) +{ + struct sk_buff *skb = flow->head; + + if (skb) { + flow->head = skb->next; + skb_mark_not_on_list(skb); + } + + return skb; +} + +/* add skb to flow queue (tail add) */ + +static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb) +{ + if (!flow->head) + flow->head = skb; + else + flow->tail->next = skb; + flow->tail = skb; + skb->next = NULL; +} + +static struct iphdr *cake_get_iphdr(const struct sk_buff *skb, + struct ipv6hdr *buf) +{ + unsigned int offset = skb_network_offset(skb); + struct iphdr *iph; + + iph = skb_header_pointer(skb, offset, sizeof(struct iphdr), buf); + + if (!iph) + return NULL; + + if (iph->version == 4 && iph->protocol == IPPROTO_IPV6) + return skb_header_pointer(skb, offset + iph->ihl * 4, + sizeof(struct ipv6hdr), buf); + + else if (iph->version == 4) + return iph; + + else if (iph->version == 6) + return skb_header_pointer(skb, offset, sizeof(struct ipv6hdr), + buf); + + return NULL; +} + +static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, + void *buf, unsigned int bufsize) +{ + unsigned int offset = skb_network_offset(skb); + const struct ipv6hdr *ipv6h; + const struct tcphdr *tcph; + const struct iphdr *iph; + struct ipv6hdr _ipv6h; + struct tcphdr _tcph; + + ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); + + if (!ipv6h) + return NULL; + + if (ipv6h->version == 4) { + iph = (struct iphdr *)ipv6h; + offset += iph->ihl * 4; + + /* special-case 6in4 tunnelling, as that is a common way to get + * v6 connectivity in the home + */ + if (iph->protocol == IPPROTO_IPV6) { + ipv6h = skb_header_pointer(skb, offset, + sizeof(_ipv6h), &_ipv6h); + + if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP) + return NULL; + + offset += sizeof(struct ipv6hdr); + + } else if (iph->protocol != IPPROTO_TCP) { + return NULL; + } + + } else if (ipv6h->version == 6) { + if (ipv6h->nexthdr != IPPROTO_TCP) + return NULL; + + offset += sizeof(struct ipv6hdr); + } else { + return NULL; + } + + tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); + if (!tcph || tcph->doff < 5) + return NULL; + + return skb_header_pointer(skb, offset, + min(__tcp_hdrlen(tcph), bufsize), buf); +} + +static const void *cake_get_tcpopt(const struct tcphdr *tcph, + int code, int *oplen) +{ + /* inspired by tcp_parse_options in tcp_input.c */ + int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); + const u8 *ptr = (const u8 *)(tcph + 1); + + while (length > 0) { + int opcode = *ptr++; + int opsize; + + if (opcode == TCPOPT_EOL) + break; + if (opcode == TCPOPT_NOP) { + length--; + continue; + } + if (length < 2) + break; + opsize = *ptr++; + if (opsize < 2 || opsize > length) + break; + + if (opcode == code) { + *oplen = opsize; + return ptr; + } + + ptr += opsize - 2; + length -= opsize; + } + + return NULL; +} + +/* Compare two SACK sequences. A sequence is considered greater if it SACKs more + * bytes than the other. In the case where both sequences ACKs bytes that the + * other doesn't, A is considered greater. DSACKs in A also makes A be + * considered greater. + * + * @return -1, 0 or 1 as normal compare functions + */ +static int cake_tcph_sack_compare(const struct tcphdr *tcph_a, + const struct tcphdr *tcph_b) +{ + const struct tcp_sack_block_wire *sack_a, *sack_b; + u32 ack_seq_a = ntohl(tcph_a->ack_seq); + u32 bytes_a = 0, bytes_b = 0; + int oplen_a, oplen_b; + bool first = true; + + sack_a = cake_get_tcpopt(tcph_a, TCPOPT_SACK, &oplen_a); + sack_b = cake_get_tcpopt(tcph_b, TCPOPT_SACK, &oplen_b); + + /* pointers point to option contents */ + oplen_a -= TCPOLEN_SACK_BASE; + oplen_b -= TCPOLEN_SACK_BASE; + + if (sack_a && oplen_a >= sizeof(*sack_a) && + (!sack_b || oplen_b < sizeof(*sack_b))) + return -1; + else if (sack_b && oplen_b >= sizeof(*sack_b) && + (!sack_a || oplen_a < sizeof(*sack_a))) + return 1; + else if ((!sack_a || oplen_a < sizeof(*sack_a)) && + (!sack_b || oplen_b < sizeof(*sack_b))) + return 0; + + while (oplen_a >= sizeof(*sack_a)) { + const struct tcp_sack_block_wire *sack_tmp = sack_b; + u32 start_a = get_unaligned_be32(&sack_a->start_seq); + u32 end_a = get_unaligned_be32(&sack_a->end_seq); + int oplen_tmp = oplen_b; + bool found = false; + + /* DSACK; always considered greater to prevent dropping */ + if (before(start_a, ack_seq_a)) + return -1; + + bytes_a += end_a - start_a; + + while (oplen_tmp >= sizeof(*sack_tmp)) { + u32 start_b = get_unaligned_be32(&sack_tmp->start_seq); + u32 end_b = get_unaligned_be32(&sack_tmp->end_seq); + + /* first time through we count the total size */ + if (first) + bytes_b += end_b - start_b; + + if (!after(start_b, start_a) && !before(end_b, end_a)) { + found = true; + if (!first) + break; + } + oplen_tmp -= sizeof(*sack_tmp); + sack_tmp++; + } + + if (!found) + return -1; + + oplen_a -= sizeof(*sack_a); + sack_a++; + first = false; + } + + /* If we made it this far, all ranges SACKed by A are covered by B, so + * either the SACKs are equal, or B SACKs more bytes. + */ + return bytes_b > bytes_a ? 1 : 0; +} + +static void cake_tcph_get_tstamp(const struct tcphdr *tcph, + u32 *tsval, u32 *tsecr) +{ + const u8 *ptr; + int opsize; + + ptr = cake_get_tcpopt(tcph, TCPOPT_TIMESTAMP, &opsize); + + if (ptr && opsize == TCPOLEN_TIMESTAMP) { + *tsval = get_unaligned_be32(ptr); + *tsecr = get_unaligned_be32(ptr + 4); + } +} + +static bool cake_tcph_may_drop(const struct tcphdr *tcph, + u32 tstamp_new, u32 tsecr_new) +{ + /* inspired by tcp_parse_options in tcp_input.c */ + int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); + const u8 *ptr = (const u8 *)(tcph + 1); + u32 tstamp, tsecr; + + /* 3 reserved flags must be unset to avoid future breakage + * ACK must be set + * ECE/CWR are handled separately + * All other flags URG/PSH/RST/SYN/FIN must be unset + * 0x0FFF0000 = all TCP flags (confirm ACK=1, others zero) + * 0x00C00000 = CWR/ECE (handled separately) + * 0x0F3F0000 = 0x0FFF0000 & ~0x00C00000 + */ + if (((tcp_flag_word(tcph) & + cpu_to_be32(0x0F3F0000)) != TCP_FLAG_ACK)) + return false; + + while (length > 0) { + int opcode = *ptr++; + int opsize; + + if (opcode == TCPOPT_EOL) + break; + if (opcode == TCPOPT_NOP) { + length--; + continue; + } + if (length < 2) + break; + opsize = *ptr++; + if (opsize < 2 || opsize > length) + break; + + switch (opcode) { + case TCPOPT_MD5SIG: /* doesn't influence state */ + break; + + case TCPOPT_SACK: /* stricter checking performed later */ + if (opsize % 8 != 2) + return false; + break; + + case TCPOPT_TIMESTAMP: + /* only drop timestamps lower than new */ + if (opsize != TCPOLEN_TIMESTAMP) + return false; + tstamp = get_unaligned_be32(ptr); + tsecr = get_unaligned_be32(ptr + 4); + if (after(tstamp, tstamp_new) || + after(tsecr, tsecr_new)) + return false; + break; + + case TCPOPT_MSS: /* these should only be set on SYN */ + case TCPOPT_WINDOW: + case TCPOPT_SACK_PERM: + case TCPOPT_FASTOPEN: + case TCPOPT_EXP: + default: /* don't drop if any unknown options are present */ + return false; + } + + ptr += opsize - 2; + length -= opsize; + } + + return true; +} + +static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, + struct cake_flow *flow) +{ + bool aggressive = q->ack_filter == CAKE_ACK_AGGRESSIVE; + struct sk_buff *elig_ack = NULL, *elig_ack_prev = NULL; + struct sk_buff *skb_check, *skb_prev = NULL; + const struct ipv6hdr *ipv6h, *ipv6h_check; + unsigned char _tcph[64], _tcph_check[64]; + const struct tcphdr *tcph, *tcph_check; + const struct iphdr *iph, *iph_check; + struct ipv6hdr _iph, _iph_check; + const struct sk_buff *skb; + int seglen, num_found = 0; + u32 tstamp = 0, tsecr = 0; + __be32 elig_flags = 0; + int sack_comp; + + /* no other possible ACKs to filter */ + if (flow->head == flow->tail) + return NULL; + + skb = flow->tail; + tcph = cake_get_tcphdr(skb, _tcph, sizeof(_tcph)); + iph = cake_get_iphdr(skb, &_iph); + if (!tcph) + return NULL; + + cake_tcph_get_tstamp(tcph, &tstamp, &tsecr); + + /* the 'triggering' packet need only have the ACK flag set. + * also check that SYN is not set, as there won't be any previous ACKs. + */ + if ((tcp_flag_word(tcph) & + (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK) + return NULL; + + /* the 'triggering' ACK is at the tail of the queue, we have already + * returned if it is the only packet in the flow. loop through the rest + * of the queue looking for pure ACKs with the same 5-tuple as the + * triggering one. + */ + for (skb_check = flow->head; + skb_check && skb_check != skb; + skb_prev = skb_check, skb_check = skb_check->next) { + iph_check = cake_get_iphdr(skb_check, &_iph_check); + tcph_check = cake_get_tcphdr(skb_check, &_tcph_check, + sizeof(_tcph_check)); + + /* only TCP packets with matching 5-tuple are eligible, and only + * drop safe headers + */ + if (!tcph_check || iph->version != iph_check->version || + tcph_check->source != tcph->source || + tcph_check->dest != tcph->dest) + continue; + + if (iph_check->version == 4) { + if (iph_check->saddr != iph->saddr || + iph_check->daddr != iph->daddr) + continue; + + seglen = iph_totlen(skb, iph_check) - + (4 * iph_check->ihl); + } else if (iph_check->version == 6) { + ipv6h = (struct ipv6hdr *)iph; + ipv6h_check = (struct ipv6hdr *)iph_check; + + if (ipv6_addr_cmp(&ipv6h_check->saddr, &ipv6h->saddr) || + ipv6_addr_cmp(&ipv6h_check->daddr, &ipv6h->daddr)) + continue; + + seglen = ntohs(ipv6h_check->payload_len); + } else { + WARN_ON(1); /* shouldn't happen */ + continue; + } + + /* If the ECE/CWR flags changed from the previous eligible + * packet in the same flow, we should no longer be dropping that + * previous packet as this would lose information. + */ + if (elig_ack && (tcp_flag_word(tcph_check) & + (TCP_FLAG_ECE | TCP_FLAG_CWR)) != elig_flags) { + elig_ack = NULL; + elig_ack_prev = NULL; + num_found--; + } + + /* Check TCP options and flags, don't drop ACKs with segment + * data, and don't drop ACKs with a higher cumulative ACK + * counter than the triggering packet. Check ACK seqno here to + * avoid parsing SACK options of packets we are going to exclude + * anyway. + */ + if (!cake_tcph_may_drop(tcph_check, tstamp, tsecr) || + (seglen - __tcp_hdrlen(tcph_check)) != 0 || + after(ntohl(tcph_check->ack_seq), ntohl(tcph->ack_seq))) + continue; + + /* Check SACK options. The triggering packet must SACK more data + * than the ACK under consideration, or SACK the same range but + * have a larger cumulative ACK counter. The latter is a + * pathological case, but is contained in the following check + * anyway, just to be safe. + */ + sack_comp = cake_tcph_sack_compare(tcph_check, tcph); + + if (sack_comp < 0 || + (ntohl(tcph_check->ack_seq) == ntohl(tcph->ack_seq) && + sack_comp == 0)) + continue; + + /* At this point we have found an eligible pure ACK to drop; if + * we are in aggressive mode, we are done. Otherwise, keep + * searching unless this is the second eligible ACK we + * found. + * + * Since we want to drop ACK closest to the head of the queue, + * save the first eligible ACK we find, even if we need to loop + * again. + */ + if (!elig_ack) { + elig_ack = skb_check; + elig_ack_prev = skb_prev; + elig_flags = (tcp_flag_word(tcph_check) + & (TCP_FLAG_ECE | TCP_FLAG_CWR)); + } + + if (num_found++ > 0) + goto found; + } + + /* We made it through the queue without finding two eligible ACKs . If + * we found a single eligible ACK we can drop it in aggressive mode if + * we can guarantee that this does not interfere with ECN flag + * information. We ensure this by dropping it only if the enqueued + * packet is consecutive with the eligible ACK, and their flags match. + */ + if (elig_ack && aggressive && elig_ack->next == skb && + (elig_flags == (tcp_flag_word(tcph) & + (TCP_FLAG_ECE | TCP_FLAG_CWR)))) + goto found; + + return NULL; + +found: + if (elig_ack_prev) + elig_ack_prev->next = elig_ack->next; + else + flow->head = elig_ack->next; + + skb_mark_not_on_list(elig_ack); + + return elig_ack; +} + +static u64 cake_ewma(u64 avg, u64 sample, u32 shift) +{ + avg -= avg >> shift; + avg += sample >> shift; + return avg; +} + +static u32 cake_calc_overhead(struct cake_sched_data *q, u32 len, u32 off) +{ + if (q->rate_flags & CAKE_FLAG_OVERHEAD) + len -= off; + + if (q->max_netlen < len) + q->max_netlen = len; + if (q->min_netlen > len) + q->min_netlen = len; + + len += q->rate_overhead; + + if (len < q->rate_mpu) + len = q->rate_mpu; + + if (q->atm_mode == CAKE_ATM_ATM) { + len += 47; + len /= 48; + len *= 53; + } else if (q->atm_mode == CAKE_ATM_PTM) { + /* Add one byte per 64 bytes or part thereof. + * This is conservative and easier to calculate than the + * precise value. + */ + len += (len + 63) / 64; + } + + if (q->max_adjlen < len) + q->max_adjlen = len; + if (q->min_adjlen > len) + q->min_adjlen = len; + + return len; +} + +static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + unsigned int hdr_len, last_len = 0; + u32 off = skb_network_offset(skb); + u16 segs = qdisc_pkt_segs(skb); + u32 len = qdisc_pkt_len(skb); + + q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8); + + if (segs == 1) + return cake_calc_overhead(q, len, off); + + /* borrowed from qdisc_pkt_len_segs_init() */ + if (!skb->encapsulation) + hdr_len = skb_transport_offset(skb); + else + hdr_len = skb_inner_transport_offset(skb); + + /* + transport layer */ + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | + SKB_GSO_TCPV6))) { + const struct tcphdr *th; + struct tcphdr _tcphdr; + + th = skb_header_pointer(skb, hdr_len, + sizeof(_tcphdr), &_tcphdr); + if (likely(th)) + hdr_len += __tcp_hdrlen(th); + } else { + struct udphdr _udphdr; + + if (skb_header_pointer(skb, hdr_len, + sizeof(_udphdr), &_udphdr)) + hdr_len += sizeof(struct udphdr); + } + + len = shinfo->gso_size + hdr_len; + last_len = skb->len - shinfo->gso_size * (segs - 1); + + return (cake_calc_overhead(q, len, off) * (segs - 1) + + cake_calc_overhead(q, last_len, off)); +} + +static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j) +{ + struct cake_heap_entry ii = q->overflow_heap[i]; + struct cake_heap_entry jj = q->overflow_heap[j]; + + q->overflow_heap[i] = jj; + q->overflow_heap[j] = ii; + + q->tins[ii.t].overflow_idx[ii.b] = j; + q->tins[jj.t].overflow_idx[jj.b] = i; +} + +static u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i) +{ + struct cake_heap_entry ii = q->overflow_heap[i]; + + return q->tins[ii.t].backlogs[ii.b]; +} + +static void cake_heapify(struct cake_sched_data *q, u16 i) +{ + static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES; + u32 mb = cake_heap_get_backlog(q, i); + u32 m = i; + + while (m < a) { + u32 l = m + m + 1; + u32 r = l + 1; + + if (l < a) { + u32 lb = cake_heap_get_backlog(q, l); + + if (lb > mb) { + m = l; + mb = lb; + } + } + + if (r < a) { + u32 rb = cake_heap_get_backlog(q, r); + + if (rb > mb) { + m = r; + mb = rb; + } + } + + if (m != i) { + cake_heap_swap(q, i, m); + i = m; + } else { + break; + } + } +} + +static void cake_heapify_up(struct cake_sched_data *q, u16 i) +{ + while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) { + u16 p = (i - 1) >> 1; + u32 ib = cake_heap_get_backlog(q, i); + u32 pb = cake_heap_get_backlog(q, p); + + if (ib > pb) { + cake_heap_swap(q, i, p); + i = p; + } else { + break; + } + } +} + +static int cake_advance_shaper(struct cake_sched_data *q, + struct cake_tin_data *b, + struct sk_buff *skb, + ktime_t now, bool drop) +{ + u32 len = get_cobalt_cb(skb)->adjusted_len; + + /* charge packet bandwidth to this tin + * and to the global shaper. + */ + if (q->rate_ns) { + u64 tin_dur = (len * b->tin_rate_ns) >> b->tin_rate_shft; + u64 global_dur = (len * q->rate_ns) >> q->rate_shft; + u64 failsafe_dur = global_dur + (global_dur >> 1); + + if (ktime_before(b->time_next_packet, now)) + b->time_next_packet = ktime_add_ns(b->time_next_packet, + tin_dur); + + else if (ktime_before(b->time_next_packet, + ktime_add_ns(now, tin_dur))) + b->time_next_packet = ktime_add_ns(now, tin_dur); + + q->time_next_packet = ktime_add_ns(q->time_next_packet, + global_dur); + if (!drop) + q->failsafe_next_packet = \ + ktime_add_ns(q->failsafe_next_packet, + failsafe_dur); + } + return len; +} + +static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) +{ + struct cake_sched_data *q = qdisc_priv(sch); + ktime_t now = ktime_get(); + u32 idx = 0, tin = 0, len; + struct cake_heap_entry qq; + struct cake_tin_data *b; + struct cake_flow *flow; + struct sk_buff *skb; + + if (!q->overflow_timeout) { + int i; + /* Build fresh max-heap */ + for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2 - 1; i >= 0; i--) + cake_heapify(q, i); + } + q->overflow_timeout = 65535; + + /* select longest queue for pruning */ + qq = q->overflow_heap[0]; + tin = qq.t; + idx = qq.b; + + b = &q->tins[tin]; + flow = &b->flows[idx]; + skb = dequeue_head(flow); + if (unlikely(!skb)) { + /* heap has gone wrong, rebuild it next time */ + q->overflow_timeout = 0; + return idx + (tin << 16); + } + + if (cobalt_queue_full(&flow->cvars, &b->cparams, now)) + b->unresponsive_flow_count++; + + len = qdisc_pkt_len(skb); + q->buffer_used -= skb->truesize; + b->backlogs[idx] -= len; + b->tin_backlog -= len; + sch->qstats.backlog -= len; + + flow->dropped++; + b->tin_dropped++; + + if (q->rate_flags & CAKE_FLAG_INGRESS) + cake_advance_shaper(q, b, skb, now, true); + + qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); + sch->q.qlen--; + + cake_heapify(q, 0); + + return idx + (tin << 16); +} + +static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) +{ + const int offset = skb_network_offset(skb); + u16 *buf, buf_; + u8 dscp; + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) + return 0; + + /* ToS is in the second byte of iphdr */ + dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct iphdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); + } + + return dscp; + + case htons(ETH_P_IPV6): + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) + return 0; + + /* Traffic class is in the first and second bytes of ipv6hdr */ + dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + + ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); + } + + return dscp; + + case htons(ETH_P_ARP): + return 0x38; /* CS7 - Net Control */ + + default: + /* If there is no Diffserv field, treat as best-effort */ + return 0; + } +} + +static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, + struct sk_buff *skb) +{ + struct cake_sched_data *q = qdisc_priv(sch); + u32 tin, mark; + bool wash; + u8 dscp; + + /* Tin selection: Default to diffserv-based selection, allow overriding + * using firewall marks or skb->priority. Call DSCP parsing early if + * wash is enabled, otherwise defer to below to skip unneeded parsing. + */ + mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; + wash = !!(q->rate_flags & CAKE_FLAG_WASH); + if (wash) + dscp = cake_handle_diffserv(skb, wash); + + if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) + tin = 0; + + else if (mark && mark <= q->tin_cnt) + tin = q->tin_order[mark - 1]; + + else if (TC_H_MAJ(skb->priority) == sch->handle && + TC_H_MIN(skb->priority) > 0 && + TC_H_MIN(skb->priority) <= q->tin_cnt) + tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; + + else { + if (!wash) + dscp = cake_handle_diffserv(skb, wash); + tin = q->tin_index[dscp]; + + if (unlikely(tin >= q->tin_cnt)) + tin = 0; + } + + return &q->tins[tin]; +} + +static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, + struct sk_buff *skb, int flow_mode, int *qerr) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct tcf_proto *filter; + struct tcf_result res; + u16 flow = 0, host = 0; + int result; + + filter = rcu_dereference_bh(q->filter_list); + if (!filter) + goto hash; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + result = tcf_classify(skb, NULL, filter, &res, false); + + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; + case TC_ACT_SHOT: + return 0; + } +#endif + if (TC_H_MIN(res.classid) <= CAKE_QUEUES) + flow = TC_H_MIN(res.classid); + if (TC_H_MAJ(res.classid) <= (CAKE_QUEUES << 16)) + host = TC_H_MAJ(res.classid) >> 16; + } +hash: + *t = cake_select_tin(sch, skb); + return cake_hash(*t, skb, flow_mode, flow, host) + 1; +} + +static void cake_reconfigure(struct Qdisc *sch); + +static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + u32 idx, tin, prev_qlen, prev_backlog, drop_id; + struct cake_sched_data *q = qdisc_priv(sch); + int len = qdisc_pkt_len(skb), ret; + struct sk_buff *ack = NULL; + ktime_t now = ktime_get(); + struct cake_tin_data *b; + struct cake_flow *flow; + bool same_flow = false; + + /* choose flow to insert into */ + idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); + if (idx == 0) { + if (ret & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return ret; + } + tin = (u32)(b - q->tins); + idx--; + flow = &b->flows[idx]; + + /* ensure shaper state isn't stale */ + if (!b->tin_backlog) { + if (ktime_before(b->time_next_packet, now)) + b->time_next_packet = now; + + if (!sch->q.qlen) { + if (ktime_before(q->time_next_packet, now)) { + q->failsafe_next_packet = now; + q->time_next_packet = now; + } else if (ktime_after(q->time_next_packet, now) && + ktime_after(q->failsafe_next_packet, now)) { + u64 next = \ + min(ktime_to_ns(q->time_next_packet), + ktime_to_ns( + q->failsafe_next_packet)); + sch->qstats.overlimits++; + qdisc_watchdog_schedule_ns(&q->watchdog, next); + } + } + } + + if (unlikely(len > b->max_skblen)) + b->max_skblen = len; + + if (qdisc_pkt_segs(skb) > 1 && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { + struct sk_buff *segs, *nskb; + netdev_features_t features = netif_skb_features(skb); + unsigned int slen = 0, numsegs = 0; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) + return qdisc_drop(skb, sch, to_free); + + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + qdisc_skb_cb(segs)->pkt_len = segs->len; + qdisc_skb_cb(segs)->pkt_segs = 1; + cobalt_set_enqueue_time(segs, now); + get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, + segs); + flow_queue_add(flow, segs); + + sch->q.qlen++; + numsegs++; + slen += segs->len; + q->buffer_used += segs->truesize; + b->packets++; + } + + /* stats */ + b->bytes += slen; + b->backlogs[idx] += slen; + b->tin_backlog += slen; + sch->qstats.backlog += slen; + q->avg_window_bytes += slen; + + qdisc_tree_reduce_backlog(sch, 1-numsegs, len-slen); + consume_skb(skb); + } else { + /* not splitting */ + int ack_pkt_len = 0; + + cobalt_set_enqueue_time(skb, now); + get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb); + flow_queue_add(flow, skb); + + if (q->ack_filter) + ack = cake_ack_filter(q, flow); + + if (ack) { + b->ack_drops++; + sch->qstats.drops++; + ack_pkt_len = qdisc_pkt_len(ack); + b->bytes += ack_pkt_len; + q->buffer_used += skb->truesize - ack->truesize; + if (q->rate_flags & CAKE_FLAG_INGRESS) + cake_advance_shaper(q, b, ack, now, true); + + qdisc_tree_reduce_backlog(sch, 1, ack_pkt_len); + consume_skb(ack); + } else { + sch->q.qlen++; + q->buffer_used += skb->truesize; + } + + /* stats */ + b->packets++; + b->bytes += len - ack_pkt_len; + b->backlogs[idx] += len - ack_pkt_len; + b->tin_backlog += len - ack_pkt_len; + sch->qstats.backlog += len - ack_pkt_len; + q->avg_window_bytes += len - ack_pkt_len; + } + + if (q->overflow_timeout) + cake_heapify_up(q, b->overflow_idx[idx]); + + /* incoming bandwidth capacity estimate */ + if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS) { + u64 packet_interval = \ + ktime_to_ns(ktime_sub(now, q->last_packet_time)); + + if (packet_interval > NSEC_PER_SEC) + packet_interval = NSEC_PER_SEC; + + /* filter out short-term bursts, eg. wifi aggregation */ + q->avg_packet_interval = \ + cake_ewma(q->avg_packet_interval, + packet_interval, + (packet_interval > q->avg_packet_interval ? + 2 : 8)); + + q->last_packet_time = now; + + if (packet_interval > q->avg_packet_interval) { + u64 window_interval = \ + ktime_to_ns(ktime_sub(now, + q->avg_window_begin)); + u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; + + b = div64_u64(b, window_interval); + q->avg_peak_bandwidth = + cake_ewma(q->avg_peak_bandwidth, b, + b > q->avg_peak_bandwidth ? 2 : 8); + q->avg_window_bytes = 0; + q->avg_window_begin = now; + + if (ktime_after(now, + ktime_add_ms(q->last_reconfig_time, + 250))) { + q->rate_bps = (q->avg_peak_bandwidth * 15) >> 4; + cake_reconfigure(sch); + } + } + } else { + q->avg_window_bytes = 0; + q->last_packet_time = now; + } + + /* flowchain */ + if (!flow->set || flow->set == CAKE_SET_DECAYING) { + if (!flow->set) { + list_add_tail(&flow->flowchain, &b->new_flows); + } else { + b->decaying_flow_count--; + list_move_tail(&flow->flowchain, &b->new_flows); + } + flow->set = CAKE_SET_SPARSE; + b->sparse_flow_count++; + + flow->deficit = cake_get_flow_quantum(b, flow, q->flow_mode); + } else if (flow->set == CAKE_SET_SPARSE_WAIT) { + /* this flow was empty, accounted as a sparse flow, but actually + * in the bulk rotation. + */ + flow->set = CAKE_SET_BULK; + b->sparse_flow_count--; + b->bulk_flow_count++; + + cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); + } + + if (q->buffer_used > q->buffer_max_used) + q->buffer_max_used = q->buffer_used; + + if (q->buffer_used <= q->buffer_limit) + return NET_XMIT_SUCCESS; + + prev_qlen = sch->q.qlen; + prev_backlog = sch->qstats.backlog; + + while (q->buffer_used > q->buffer_limit) { + drop_id = cake_drop(sch, to_free); + if ((drop_id >> 16) == tin && + (drop_id & 0xFFFF) == idx) + same_flow = true; + } + + prev_qlen -= sch->q.qlen; + prev_backlog -= sch->qstats.backlog; + b->drop_overlimit += prev_qlen; + + if (same_flow) { + qdisc_tree_reduce_backlog(sch, prev_qlen - 1, + prev_backlog - len); + return NET_XMIT_CN; + } + qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog); + return NET_XMIT_SUCCESS; +} + +static struct sk_buff *cake_dequeue_one(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct cake_tin_data *b = &q->tins[q->cur_tin]; + struct cake_flow *flow = &b->flows[q->cur_flow]; + struct sk_buff *skb = NULL; + u32 len; + + if (flow->head) { + skb = dequeue_head(flow); + len = qdisc_pkt_len(skb); + b->backlogs[q->cur_flow] -= len; + b->tin_backlog -= len; + sch->qstats.backlog -= len; + q->buffer_used -= skb->truesize; + sch->q.qlen--; + + if (q->overflow_timeout) + cake_heapify(q, b->overflow_idx[q->cur_flow]); + } + return skb; +} + +/* Discard leftover packets from a tin no longer in use. */ +static void cake_clear_tin(struct Qdisc *sch, u16 tin) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + + q->cur_tin = tin; + for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++) + while (!!(skb = cake_dequeue_one(sch))) + kfree_skb_reason(skb, SKB_DROP_REASON_QUEUE_PURGE); +} + +static struct sk_buff *cake_dequeue(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct cake_tin_data *b = &q->tins[q->cur_tin]; + enum skb_drop_reason reason; + ktime_t now = ktime_get(); + struct cake_flow *flow; + struct list_head *head; + bool first_flow = true; + struct sk_buff *skb; + u64 delay; + u32 len; + +begin: + if (!sch->q.qlen) + return NULL; + + /* global hard shaper */ + if (ktime_after(q->time_next_packet, now) && + ktime_after(q->failsafe_next_packet, now)) { + u64 next = min(ktime_to_ns(q->time_next_packet), + ktime_to_ns(q->failsafe_next_packet)); + + sch->qstats.overlimits++; + qdisc_watchdog_schedule_ns(&q->watchdog, next); + return NULL; + } + + /* Choose a class to work on. */ + if (!q->rate_ns) { + /* In unlimited mode, can't rely on shaper timings, just balance + * with DRR + */ + bool wrapped = false, empty = true; + + while (b->tin_deficit < 0 || + !(b->sparse_flow_count + b->bulk_flow_count)) { + if (b->tin_deficit <= 0) + b->tin_deficit += b->tin_quantum; + if (b->sparse_flow_count + b->bulk_flow_count) + empty = false; + + q->cur_tin++; + b++; + if (q->cur_tin >= q->tin_cnt) { + q->cur_tin = 0; + b = q->tins; + + if (wrapped) { + /* It's possible for q->qlen to be + * nonzero when we actually have no + * packets anywhere. + */ + if (empty) + return NULL; + } else { + wrapped = true; + } + } + } + } else { + /* In shaped mode, choose: + * - Highest-priority tin with queue and meeting schedule, or + * - The earliest-scheduled tin with queue. + */ + ktime_t best_time = KTIME_MAX; + int tin, best_tin = 0; + + for (tin = 0; tin < q->tin_cnt; tin++) { + b = q->tins + tin; + if ((b->sparse_flow_count + b->bulk_flow_count) > 0) { + ktime_t time_to_pkt = \ + ktime_sub(b->time_next_packet, now); + + if (ktime_to_ns(time_to_pkt) <= 0 || + ktime_compare(time_to_pkt, + best_time) <= 0) { + best_time = time_to_pkt; + best_tin = tin; + } + } + } + + q->cur_tin = best_tin; + b = q->tins + best_tin; + + /* No point in going further if no packets to deliver. */ + if (unlikely(!(b->sparse_flow_count + b->bulk_flow_count))) + return NULL; + } + +retry: + /* service this class */ + head = &b->decaying_flows; + if (!first_flow || list_empty(head)) { + head = &b->new_flows; + if (list_empty(head)) { + head = &b->old_flows; + if (unlikely(list_empty(head))) { + head = &b->decaying_flows; + if (unlikely(list_empty(head))) + goto begin; + } + } + } + flow = list_first_entry(head, struct cake_flow, flowchain); + q->cur_flow = flow - b->flows; + first_flow = false; + + /* flow isolation (DRR++) */ + if (flow->deficit <= 0) { + /* Keep all flows with deficits out of the sparse and decaying + * rotations. No non-empty flow can go into the decaying + * rotation, so they can't get deficits + */ + if (flow->set == CAKE_SET_SPARSE) { + if (flow->head) { + b->sparse_flow_count--; + b->bulk_flow_count++; + + cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); + + flow->set = CAKE_SET_BULK; + } else { + /* we've moved it to the bulk rotation for + * correct deficit accounting but we still want + * to count it as a sparse flow, not a bulk one. + */ + flow->set = CAKE_SET_SPARSE_WAIT; + } + } + + flow->deficit += cake_get_flow_quantum(b, flow, q->flow_mode); + list_move_tail(&flow->flowchain, &b->old_flows); + + goto retry; + } + + /* Retrieve a packet via the AQM */ + while (1) { + skb = cake_dequeue_one(sch); + if (!skb) { + /* this queue was actually empty */ + if (cobalt_queue_empty(&flow->cvars, &b->cparams, now)) + b->unresponsive_flow_count--; + + if (flow->cvars.p_drop || flow->cvars.count || + ktime_before(now, flow->cvars.drop_next)) { + /* keep in the flowchain until the state has + * decayed to rest + */ + list_move_tail(&flow->flowchain, + &b->decaying_flows); + if (flow->set == CAKE_SET_BULK) { + b->bulk_flow_count--; + + cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); + + b->decaying_flow_count++; + } else if (flow->set == CAKE_SET_SPARSE || + flow->set == CAKE_SET_SPARSE_WAIT) { + b->sparse_flow_count--; + b->decaying_flow_count++; + } + flow->set = CAKE_SET_DECAYING; + } else { + /* remove empty queue from the flowchain */ + list_del_init(&flow->flowchain); + if (flow->set == CAKE_SET_SPARSE || + flow->set == CAKE_SET_SPARSE_WAIT) + b->sparse_flow_count--; + else if (flow->set == CAKE_SET_BULK) { + b->bulk_flow_count--; + + cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); + } else + b->decaying_flow_count--; + + flow->set = CAKE_SET_NONE; + } + goto begin; + } + + reason = cobalt_should_drop(&flow->cvars, &b->cparams, now, skb, + (b->bulk_flow_count * + !!(q->rate_flags & + CAKE_FLAG_INGRESS))); + /* Last packet in queue may be marked, shouldn't be dropped */ + if (reason == SKB_NOT_DROPPED_YET || !flow->head) + break; + + /* drop this packet, get another one */ + if (q->rate_flags & CAKE_FLAG_INGRESS) { + len = cake_advance_shaper(q, b, skb, + now, true); + flow->deficit -= len; + b->tin_deficit -= len; + } + flow->dropped++; + b->tin_dropped++; + qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); + qdisc_qstats_drop(sch); + qdisc_dequeue_drop(sch, skb, reason); + if (q->rate_flags & CAKE_FLAG_INGRESS) + goto retry; + } + + b->tin_ecn_mark += !!flow->cvars.ecn_marked; + qdisc_bstats_update(sch, skb); + + /* collect delay stats */ + delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); + b->avge_delay = cake_ewma(b->avge_delay, delay, 8); + b->peak_delay = cake_ewma(b->peak_delay, delay, + delay > b->peak_delay ? 2 : 8); + b->base_delay = cake_ewma(b->base_delay, delay, + delay < b->base_delay ? 2 : 8); + + len = cake_advance_shaper(q, b, skb, now, false); + flow->deficit -= len; + b->tin_deficit -= len; + + if (ktime_after(q->time_next_packet, now) && sch->q.qlen) { + u64 next = min(ktime_to_ns(q->time_next_packet), + ktime_to_ns(q->failsafe_next_packet)); + + qdisc_watchdog_schedule_ns(&q->watchdog, next); + } else if (!sch->q.qlen) { + int i; + + for (i = 0; i < q->tin_cnt; i++) { + if (q->tins[i].decaying_flow_count) { + ktime_t next = \ + ktime_add_ns(now, + q->tins[i].cparams.target); + + qdisc_watchdog_schedule_ns(&q->watchdog, + ktime_to_ns(next)); + break; + } + } + } + + if (q->overflow_timeout) + q->overflow_timeout--; + + return skb; +} + +static void cake_reset(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + u32 c; + + if (!q->tins) + return; + + for (c = 0; c < CAKE_MAX_TINS; c++) + cake_clear_tin(sch, c); +} + +static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { + [TCA_CAKE_BASE_RATE64] = { .type = NLA_U64 }, + [TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 }, + [TCA_CAKE_ATM] = { .type = NLA_U32 }, + [TCA_CAKE_FLOW_MODE] = { .type = NLA_U32 }, + [TCA_CAKE_OVERHEAD] = { .type = NLA_S32 }, + [TCA_CAKE_RTT] = { .type = NLA_U32 }, + [TCA_CAKE_TARGET] = { .type = NLA_U32 }, + [TCA_CAKE_AUTORATE] = { .type = NLA_U32 }, + [TCA_CAKE_MEMORY] = { .type = NLA_U32 }, + [TCA_CAKE_NAT] = { .type = NLA_U32 }, + [TCA_CAKE_RAW] = { .type = NLA_U32 }, + [TCA_CAKE_WASH] = { .type = NLA_U32 }, + [TCA_CAKE_MPU] = { .type = NLA_U32 }, + [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, + [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, + [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, + [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, +}; + +static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, + u64 target_ns, u64 rtt_est_ns) +{ + /* convert byte-rate into time-per-byte + * so it will always unwedge in reasonable time. + */ + static const u64 MIN_RATE = 64; + u32 byte_target = mtu; + u64 byte_target_ns; + u8 rate_shft = 0; + u64 rate_ns = 0; + + b->flow_quantum = 1514; + if (rate) { + b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL); + rate_shft = 34; + rate_ns = ((u64)NSEC_PER_SEC) << rate_shft; + rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate)); + while (!!(rate_ns >> 34)) { + rate_ns >>= 1; + rate_shft--; + } + } /* else unlimited, ie. zero delay */ + + b->tin_rate_bps = rate; + b->tin_rate_ns = rate_ns; + b->tin_rate_shft = rate_shft; + + byte_target_ns = (byte_target * rate_ns) >> rate_shft; + + b->cparams.target = max((byte_target_ns * 3) / 2, target_ns); + b->cparams.interval = max(rtt_est_ns + + b->cparams.target - target_ns, + b->cparams.target * 2); + b->cparams.mtu_time = byte_target_ns; + b->cparams.p_inc = 1 << 24; /* 1/256 */ + b->cparams.p_dec = 1 << 20; /* 1/4096 */ +} + +static int cake_config_besteffort(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct cake_tin_data *b = &q->tins[0]; + u32 mtu = psched_mtu(qdisc_dev(sch)); + u64 rate = q->rate_bps; + + q->tin_cnt = 1; + + q->tin_index = besteffort; + q->tin_order = normal_order; + + cake_set_rate(b, rate, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + b->tin_quantum = 65535; + + return 0; +} + +static int cake_config_precedence(struct Qdisc *sch) +{ + /* convert high-level (user visible) parameters into internal format */ + struct cake_sched_data *q = qdisc_priv(sch); + u32 mtu = psched_mtu(qdisc_dev(sch)); + u64 rate = q->rate_bps; + u32 quantum = 256; + u32 i; + + q->tin_cnt = 8; + q->tin_index = precedence; + q->tin_order = normal_order; + + for (i = 0; i < q->tin_cnt; i++) { + struct cake_tin_data *b = &q->tins[i]; + + cake_set_rate(b, rate, mtu, us_to_ns(q->target), + us_to_ns(q->interval)); + + b->tin_quantum = max_t(u16, 1U, quantum); + + /* calculate next class's parameters */ + rate *= 7; + rate >>= 3; + + quantum *= 7; + quantum >>= 3; + } + + return 0; +} + +/* List of known Diffserv codepoints: + * + * Default Forwarding (DF/CS0) - Best Effort + * Max Throughput (TOS2) + * Min Delay (TOS4) + * LLT "La" (TOS5) + * Assured Forwarding 1 (AF1x) - x3 + * Assured Forwarding 2 (AF2x) - x3 + * Assured Forwarding 3 (AF3x) - x3 + * Assured Forwarding 4 (AF4x) - x3 + * Precedence Class 1 (CS1) + * Precedence Class 2 (CS2) + * Precedence Class 3 (CS3) + * Precedence Class 4 (CS4) + * Precedence Class 5 (CS5) + * Precedence Class 6 (CS6) + * Precedence Class 7 (CS7) + * Voice Admit (VA) + * Expedited Forwarding (EF) + * Lower Effort (LE) + * + * Total 26 codepoints. + */ + +/* List of traffic classes in RFC 4594, updated by RFC 8622: + * (roughly descending order of contended priority) + * (roughly ascending order of uncontended throughput) + * + * Network Control (CS6,CS7) - routing traffic + * Telephony (EF,VA) - aka. VoIP streams + * Signalling (CS5) - VoIP setup + * Multimedia Conferencing (AF4x) - aka. video calls + * Realtime Interactive (CS4) - eg. games + * Multimedia Streaming (AF3x) - eg. YouTube, NetFlix, Twitch + * Broadcast Video (CS3) + * Low-Latency Data (AF2x,TOS4) - eg. database + * Ops, Admin, Management (CS2) - eg. ssh + * Standard Service (DF & unrecognised codepoints) + * High-Throughput Data (AF1x,TOS2) - eg. web traffic + * Low-Priority Data (LE,CS1) - eg. BitTorrent + * + * Total 12 traffic classes. + */ + +static int cake_config_diffserv8(struct Qdisc *sch) +{ +/* Pruned list of traffic classes for typical applications: + * + * Network Control (CS6, CS7) + * Minimum Latency (EF, VA, CS5, CS4) + * Interactive Shell (CS2) + * Low Latency Transactions (AF2x, TOS4) + * Video Streaming (AF4x, AF3x, CS3) + * Bog Standard (DF etc.) + * High Throughput (AF1x, TOS2, CS1) + * Background Traffic (LE) + * + * Total 8 traffic classes. + */ + + struct cake_sched_data *q = qdisc_priv(sch); + u32 mtu = psched_mtu(qdisc_dev(sch)); + u64 rate = q->rate_bps; + u32 quantum = 256; + u32 i; + + q->tin_cnt = 8; + + /* codepoint to class mapping */ + q->tin_index = diffserv8; + q->tin_order = normal_order; + + /* class characteristics */ + for (i = 0; i < q->tin_cnt; i++) { + struct cake_tin_data *b = &q->tins[i]; + + cake_set_rate(b, rate, mtu, us_to_ns(q->target), + us_to_ns(q->interval)); + + b->tin_quantum = max_t(u16, 1U, quantum); + + /* calculate next class's parameters */ + rate *= 7; + rate >>= 3; + + quantum *= 7; + quantum >>= 3; + } + + return 0; +} + +static int cake_config_diffserv4(struct Qdisc *sch) +{ +/* Further pruned list of traffic classes for four-class system: + * + * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) + * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2) + * Best Effort (DF, AF1x, TOS2, and those not specified) + * Background Traffic (LE, CS1) + * + * Total 4 traffic classes. + */ + + struct cake_sched_data *q = qdisc_priv(sch); + u32 mtu = psched_mtu(qdisc_dev(sch)); + u64 rate = q->rate_bps; + u32 quantum = 1024; + + q->tin_cnt = 4; + + /* codepoint to class mapping */ + q->tin_index = diffserv4; + q->tin_order = bulk_order; + + /* class characteristics */ + cake_set_rate(&q->tins[0], rate, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + cake_set_rate(&q->tins[1], rate >> 4, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + cake_set_rate(&q->tins[2], rate >> 1, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + cake_set_rate(&q->tins[3], rate >> 2, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + + /* bandwidth-sharing weights */ + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 1; + q->tins[3].tin_quantum = quantum >> 2; + + return 0; +} + +static int cake_config_diffserv3(struct Qdisc *sch) +{ +/* Simplified Diffserv structure with 3 tins. + * Latency Sensitive (CS7, CS6, EF, VA, TOS4) + * Best Effort + * Low Priority (LE, CS1) + */ + struct cake_sched_data *q = qdisc_priv(sch); + u32 mtu = psched_mtu(qdisc_dev(sch)); + u64 rate = q->rate_bps; + u32 quantum = 1024; + + q->tin_cnt = 3; + + /* codepoint to class mapping */ + q->tin_index = diffserv3; + q->tin_order = bulk_order; + + /* class characteristics */ + cake_set_rate(&q->tins[0], rate, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + cake_set_rate(&q->tins[1], rate >> 4, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + cake_set_rate(&q->tins[2], rate >> 2, mtu, + us_to_ns(q->target), us_to_ns(q->interval)); + + /* bandwidth-sharing weights */ + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 2; + + return 0; +} + +static void cake_reconfigure(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + int c, ft; + + switch (q->tin_mode) { + case CAKE_DIFFSERV_BESTEFFORT: + ft = cake_config_besteffort(sch); + break; + + case CAKE_DIFFSERV_PRECEDENCE: + ft = cake_config_precedence(sch); + break; + + case CAKE_DIFFSERV_DIFFSERV8: + ft = cake_config_diffserv8(sch); + break; + + case CAKE_DIFFSERV_DIFFSERV4: + ft = cake_config_diffserv4(sch); + break; + + case CAKE_DIFFSERV_DIFFSERV3: + default: + ft = cake_config_diffserv3(sch); + break; + } + + for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) { + cake_clear_tin(sch, c); + q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time; + } + + q->rate_ns = q->tins[ft].tin_rate_ns; + q->rate_shft = q->tins[ft].tin_rate_shft; + + if (q->buffer_config_limit) { + q->buffer_limit = q->buffer_config_limit; + } else if (q->rate_bps) { + u64 t = q->rate_bps * q->interval; + + do_div(t, USEC_PER_SEC / 4); + q->buffer_limit = max_t(u32, t, 4U << 20); + } else { + q->buffer_limit = ~0; + } + + sch->flags &= ~TCQ_F_CAN_BYPASS; + + q->buffer_limit = min(q->buffer_limit, + max(sch->limit * psched_mtu(qdisc_dev(sch)), + q->buffer_config_limit)); +} + +static int cake_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_CAKE_MAX + 1]; + u16 rate_flags; + u8 flow_mode; + int err; + + err = nla_parse_nested_deprecated(tb, TCA_CAKE_MAX, opt, cake_policy, + extack); + if (err < 0) + return err; + + flow_mode = q->flow_mode; + if (tb[TCA_CAKE_NAT]) { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + flow_mode &= ~CAKE_FLOW_NAT_FLAG; + flow_mode |= CAKE_FLOW_NAT_FLAG * + !!nla_get_u32(tb[TCA_CAKE_NAT]); +#else + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT], + "No conntrack support in kernel"); + return -EOPNOTSUPP; +#endif + } + + if (tb[TCA_CAKE_BASE_RATE64]) + WRITE_ONCE(q->rate_bps, + nla_get_u64(tb[TCA_CAKE_BASE_RATE64])); + + if (tb[TCA_CAKE_DIFFSERV_MODE]) + WRITE_ONCE(q->tin_mode, + nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE])); + + rate_flags = q->rate_flags; + if (tb[TCA_CAKE_WASH]) { + if (!!nla_get_u32(tb[TCA_CAKE_WASH])) + rate_flags |= CAKE_FLAG_WASH; + else + rate_flags &= ~CAKE_FLAG_WASH; + } + + if (tb[TCA_CAKE_FLOW_MODE]) + flow_mode = ((flow_mode & CAKE_FLOW_NAT_FLAG) | + (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) & + CAKE_FLOW_MASK)); + + if (tb[TCA_CAKE_ATM]) + WRITE_ONCE(q->atm_mode, + nla_get_u32(tb[TCA_CAKE_ATM])); + + if (tb[TCA_CAKE_OVERHEAD]) { + WRITE_ONCE(q->rate_overhead, + nla_get_s32(tb[TCA_CAKE_OVERHEAD])); + rate_flags |= CAKE_FLAG_OVERHEAD; + + q->max_netlen = 0; + q->max_adjlen = 0; + q->min_netlen = ~0; + q->min_adjlen = ~0; + } + + if (tb[TCA_CAKE_RAW]) { + rate_flags &= ~CAKE_FLAG_OVERHEAD; + + q->max_netlen = 0; + q->max_adjlen = 0; + q->min_netlen = ~0; + q->min_adjlen = ~0; + } + + if (tb[TCA_CAKE_MPU]) + WRITE_ONCE(q->rate_mpu, + nla_get_u32(tb[TCA_CAKE_MPU])); + + if (tb[TCA_CAKE_RTT]) { + u32 interval = nla_get_u32(tb[TCA_CAKE_RTT]); + + WRITE_ONCE(q->interval, max(interval, 1U)); + } + + if (tb[TCA_CAKE_TARGET]) { + u32 target = nla_get_u32(tb[TCA_CAKE_TARGET]); + + WRITE_ONCE(q->target, max(target, 1U)); + } + + if (tb[TCA_CAKE_AUTORATE]) { + if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE])) + rate_flags |= CAKE_FLAG_AUTORATE_INGRESS; + else + rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS; + } + + if (tb[TCA_CAKE_INGRESS]) { + if (!!nla_get_u32(tb[TCA_CAKE_INGRESS])) + rate_flags |= CAKE_FLAG_INGRESS; + else + rate_flags &= ~CAKE_FLAG_INGRESS; + } + + if (tb[TCA_CAKE_ACK_FILTER]) + WRITE_ONCE(q->ack_filter, + nla_get_u32(tb[TCA_CAKE_ACK_FILTER])); + + if (tb[TCA_CAKE_MEMORY]) + WRITE_ONCE(q->buffer_config_limit, + nla_get_u32(tb[TCA_CAKE_MEMORY])); + + if (tb[TCA_CAKE_SPLIT_GSO]) { + if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO])) + rate_flags |= CAKE_FLAG_SPLIT_GSO; + else + rate_flags &= ~CAKE_FLAG_SPLIT_GSO; + } + + if (tb[TCA_CAKE_FWMARK]) { + WRITE_ONCE(q->fwmark_mask, nla_get_u32(tb[TCA_CAKE_FWMARK])); + WRITE_ONCE(q->fwmark_shft, + q->fwmark_mask ? __ffs(q->fwmark_mask) : 0); + } + + WRITE_ONCE(q->rate_flags, rate_flags); + WRITE_ONCE(q->flow_mode, flow_mode); + if (q->tins) { + sch_tree_lock(sch); + cake_reconfigure(sch); + sch_tree_unlock(sch); + } + + return 0; +} + +static void cake_destroy(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + + qdisc_watchdog_cancel(&q->watchdog); + tcf_block_put(q->block); + kvfree(q->tins); +} + +static int cake_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct cake_sched_data *q = qdisc_priv(sch); + int i, j, err; + + sch->limit = 10240; + sch->flags |= TCQ_F_DEQUEUE_DROPS; + + q->tin_mode = CAKE_DIFFSERV_DIFFSERV3; + q->flow_mode = CAKE_FLOW_TRIPLE; + + q->rate_bps = 0; /* unlimited by default */ + + q->interval = 100000; /* 100ms default */ + q->target = 5000; /* 5ms: codel RFC argues + * for 5 to 10% of interval + */ + q->rate_flags |= CAKE_FLAG_SPLIT_GSO; + q->cur_tin = 0; + q->cur_flow = 0; + + qdisc_watchdog_init(&q->watchdog, sch); + + if (opt) { + err = cake_change(sch, opt, extack); + + if (err) + return err; + } + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + return err; + + quantum_div[0] = ~0; + for (i = 1; i <= CAKE_QUEUES; i++) + quantum_div[i] = 65535 / i; + + q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), + GFP_KERNEL); + if (!q->tins) + return -ENOMEM; + + for (i = 0; i < CAKE_MAX_TINS; i++) { + struct cake_tin_data *b = q->tins + i; + + INIT_LIST_HEAD(&b->new_flows); + INIT_LIST_HEAD(&b->old_flows); + INIT_LIST_HEAD(&b->decaying_flows); + b->sparse_flow_count = 0; + b->bulk_flow_count = 0; + b->decaying_flow_count = 0; + + for (j = 0; j < CAKE_QUEUES; j++) { + struct cake_flow *flow = b->flows + j; + u32 k = j * CAKE_MAX_TINS + i; + + INIT_LIST_HEAD(&flow->flowchain); + cobalt_vars_init(&flow->cvars); + + q->overflow_heap[k].t = i; + q->overflow_heap[k].b = j; + b->overflow_idx[j] = k; + } + } + + cake_reconfigure(sch); + q->avg_peak_bandwidth = q->rate_bps; + q->min_netlen = ~0; + q->min_adjlen = ~0; + return 0; +} + +static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + u16 rate_flags; + u8 flow_mode; + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, + READ_ONCE(q->rate_bps), TCA_CAKE_PAD)) + goto nla_put_failure; + + flow_mode = READ_ONCE(q->flow_mode); + if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, flow_mode & CAKE_FLOW_MASK)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_RTT, READ_ONCE(q->interval))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_TARGET, READ_ONCE(q->target))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_MEMORY, + READ_ONCE(q->buffer_config_limit))) + goto nla_put_failure; + + rate_flags = READ_ONCE(q->rate_flags); + if (nla_put_u32(skb, TCA_CAKE_AUTORATE, + !!(rate_flags & CAKE_FLAG_AUTORATE_INGRESS))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_INGRESS, + !!(rate_flags & CAKE_FLAG_INGRESS))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, READ_ONCE(q->ack_filter))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_NAT, + !!(flow_mode & CAKE_FLOW_NAT_FLAG))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, READ_ONCE(q->tin_mode))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_WASH, + !!(rate_flags & CAKE_FLAG_WASH))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, READ_ONCE(q->rate_overhead))) + goto nla_put_failure; + + if (!(rate_flags & CAKE_FLAG_OVERHEAD)) + if (nla_put_u32(skb, TCA_CAKE_RAW, 0)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_ATM, READ_ONCE(q->atm_mode))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_MPU, READ_ONCE(q->rate_mpu))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO, + !!(rate_flags & CAKE_FLAG_SPLIT_GSO))) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_FWMARK, READ_ONCE(q->fwmark_mask))) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + return -1; +} + +static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct nlattr *stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); + struct cake_sched_data *q = qdisc_priv(sch); + struct nlattr *tstats, *ts; + int i; + + if (!stats) + return -1; + +#define PUT_STAT_U32(attr, data) do { \ + if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) +#define PUT_STAT_U64(attr, data) do { \ + if (nla_put_u64_64bit(d->skb, TCA_CAKE_STATS_ ## attr, \ + data, TCA_CAKE_STATS_PAD)) \ + goto nla_put_failure; \ + } while (0) + + PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth); + PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit); + PUT_STAT_U32(MEMORY_USED, q->buffer_max_used); + PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16)); + PUT_STAT_U32(MAX_NETLEN, q->max_netlen); + PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen); + PUT_STAT_U32(MIN_NETLEN, q->min_netlen); + PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen); + +#undef PUT_STAT_U32 +#undef PUT_STAT_U64 + + tstats = nla_nest_start_noflag(d->skb, TCA_CAKE_STATS_TIN_STATS); + if (!tstats) + goto nla_put_failure; + +#define PUT_TSTAT_U32(attr, data) do { \ + if (nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) +#define PUT_TSTAT_U64(attr, data) do { \ + if (nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \ + data, TCA_CAKE_TIN_STATS_PAD)) \ + goto nla_put_failure; \ + } while (0) + + for (i = 0; i < q->tin_cnt; i++) { + struct cake_tin_data *b = &q->tins[q->tin_order[i]]; + + ts = nla_nest_start_noflag(d->skb, i + 1); + if (!ts) + goto nla_put_failure; + + PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps); + PUT_TSTAT_U64(SENT_BYTES64, b->bytes); + PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog); + + PUT_TSTAT_U32(TARGET_US, + ktime_to_us(ns_to_ktime(b->cparams.target))); + PUT_TSTAT_U32(INTERVAL_US, + ktime_to_us(ns_to_ktime(b->cparams.interval))); + + PUT_TSTAT_U32(SENT_PACKETS, b->packets); + PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped); + PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark); + PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops); + + PUT_TSTAT_U32(PEAK_DELAY_US, + ktime_to_us(ns_to_ktime(b->peak_delay))); + PUT_TSTAT_U32(AVG_DELAY_US, + ktime_to_us(ns_to_ktime(b->avge_delay))); + PUT_TSTAT_U32(BASE_DELAY_US, + ktime_to_us(ns_to_ktime(b->base_delay))); + + PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits); + PUT_TSTAT_U32(WAY_MISSES, b->way_misses); + PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions); + + PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count + + b->decaying_flow_count); + PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count); + PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count); + PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen); + + PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum); + nla_nest_end(d->skb, ts); + } + +#undef PUT_TSTAT_U32 +#undef PUT_TSTAT_U64 + + nla_nest_end(d->skb, tstats); + return nla_nest_end(d->skb, stats); + +nla_put_failure: + nla_nest_cancel(d->skb, stats); + return -1; +} + +static struct Qdisc *cake_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long cake_find(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static unsigned long cake_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + +static void cake_unbind(struct Qdisc *q, unsigned long cl) +{ +} + +static struct tcf_block *cake_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct cake_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return q->block; +} + +static int cake_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct cake_sched_data *q = qdisc_priv(sch); + const struct cake_flow *flow = NULL; + struct gnet_stats_queue qs = { 0 }; + struct nlattr *stats; + u32 idx = cl - 1; + + if (idx < CAKE_QUEUES * q->tin_cnt) { + const struct cake_tin_data *b = \ + &q->tins[q->tin_order[idx / CAKE_QUEUES]]; + const struct sk_buff *skb; + + flow = &b->flows[idx % CAKE_QUEUES]; + + if (flow->head) { + sch_tree_lock(sch); + skb = flow->head; + while (skb) { + qs.qlen++; + skb = skb->next; + } + sch_tree_unlock(sch); + } + qs.backlog = b->backlogs[idx % CAKE_QUEUES]; + qs.drops = flow->dropped; + } + if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) + return -1; + if (flow) { + ktime_t now = ktime_get(); + + stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); + if (!stats) + return -1; + +#define PUT_STAT_U32(attr, data) do { \ + if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) +#define PUT_STAT_S32(attr, data) do { \ + if (nla_put_s32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) + + PUT_STAT_S32(DEFICIT, flow->deficit); + PUT_STAT_U32(DROPPING, flow->cvars.dropping); + PUT_STAT_U32(COBALT_COUNT, flow->cvars.count); + PUT_STAT_U32(P_DROP, flow->cvars.p_drop); + if (flow->cvars.p_drop) { + PUT_STAT_S32(BLUE_TIMER_US, + ktime_to_us( + ktime_sub(now, + flow->cvars.blue_timer))); + } + if (flow->cvars.dropping) { + PUT_STAT_S32(DROP_NEXT_US, + ktime_to_us( + ktime_sub(now, + flow->cvars.drop_next))); + } + + if (nla_nest_end(d->skb, stats) < 0) + return -1; + } + + return 0; + +nla_put_failure: + nla_nest_cancel(d->skb, stats); + return -1; +} + +static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct cake_sched_data *q = qdisc_priv(sch); + unsigned int i, j; + + if (arg->stop) + return; + + for (i = 0; i < q->tin_cnt; i++) { + struct cake_tin_data *b = &q->tins[q->tin_order[i]]; + + for (j = 0; j < CAKE_QUEUES; j++) { + if (list_empty(&b->flows[j].flowchain)) { + arg->count++; + continue; + } + if (!tc_qdisc_stats_dump(sch, i * CAKE_QUEUES + j + 1, + arg)) + break; + } + } +} + +static const struct Qdisc_class_ops cake_class_ops = { + .leaf = cake_leaf, + .find = cake_find, + .tcf_block = cake_tcf_block, + .bind_tcf = cake_bind, + .unbind_tcf = cake_unbind, + .dump = cake_dump_class, + .dump_stats = cake_dump_class_stats, + .walk = cake_walk, +}; + +static struct Qdisc_ops cake_qdisc_ops __read_mostly = { + .cl_ops = &cake_class_ops, + .id = "cake", + .priv_size = sizeof(struct cake_sched_data), + .enqueue = cake_enqueue, + .dequeue = cake_dequeue, + .peek = qdisc_peek_dequeued, + .init = cake_init, + .reset = cake_reset, + .destroy = cake_destroy, + .change = cake_change, + .dump = cake_dump, + .dump_stats = cake_dump_stats, + .owner = THIS_MODULE, +}; +MODULE_ALIAS_NET_SCH("cake"); + +static int __init cake_module_init(void) +{ + return register_qdisc(&cake_qdisc_ops); +} + +static void __exit cake_module_exit(void) +{ + unregister_qdisc(&cake_qdisc_ops); +} + +module_init(cake_module_init) +module_exit(cake_module_exit) +MODULE_AUTHOR("Jonathan Morton"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("The CAKE shaper."); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c deleted file mode 100644 index 481036f6b54e..000000000000 --- a/net/sched/sch_cbq.c +++ /dev/null @@ -1,1801 +0,0 @@ -/* - * net/sched/sch_cbq.c Class-Based Queueing discipline. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - * - */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - - -/* Class-Based Queueing (CBQ) algorithm. - ======================================= - - Sources: [1] Sally Floyd and Van Jacobson, "Link-sharing and Resource - Management Models for Packet Networks", - IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995 - - [2] Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995 - - [3] Sally Floyd, "Notes on Class-Based Queueing: Setting - Parameters", 1996 - - [4] Sally Floyd and Michael Speer, "Experimental Results - for Class-Based Queueing", 1998, not published. - - ----------------------------------------------------------------------- - - Algorithm skeleton was taken from NS simulator cbq.cc. - If someone wants to check this code against the LBL version, - he should take into account that ONLY the skeleton was borrowed, - the implementation is different. Particularly: - - --- The WRR algorithm is different. Our version looks more - reasonable (I hope) and works when quanta are allowed to be - less than MTU, which is always the case when real time classes - have small rates. Note, that the statement of [3] is - incomplete, delay may actually be estimated even if class - per-round allotment is less than MTU. Namely, if per-round - allotment is W*r_i, and r_1+...+r_k = r < 1 - - delay_i <= ([MTU/(W*r_i)]*W*r + W*r + k*MTU)/B - - In the worst case we have IntServ estimate with D = W*r+k*MTU - and C = MTU*r. The proof (if correct at all) is trivial. - - - --- It seems that cbq-2.0 is not very accurate. At least, I cannot - interpret some places, which look like wrong translations - from NS. Anyone is advised to find these differences - and explain to me, why I am wrong 8). - - --- Linux has no EOI event, so that we cannot estimate true class - idle time. Workaround is to consider the next dequeue event - as sign that previous packet is finished. This is wrong because of - internal device queueing, but on a permanently loaded link it is true. - Moreover, combined with clock integrator, this scheme looks - very close to an ideal solution. */ - -struct cbq_sched_data; - - -struct cbq_class { - struct Qdisc_class_common common; - struct cbq_class *next_alive; /* next class with backlog in this priority band */ - -/* Parameters */ - unsigned char priority; /* class priority */ - unsigned char priority2; /* priority to be used after overlimit */ - unsigned char ewma_log; /* time constant for idle time calculation */ - - u32 defmap; - - /* Link-sharing scheduler parameters */ - long maxidle; /* Class parameters: see below. */ - long offtime; - long minidle; - u32 avpkt; - struct qdisc_rate_table *R_tab; - - /* General scheduler (WRR) parameters */ - long allot; - long quantum; /* Allotment per WRR round */ - long weight; /* Relative allotment: see below */ - - struct Qdisc *qdisc; /* Ptr to CBQ discipline */ - struct cbq_class *split; /* Ptr to split node */ - struct cbq_class *share; /* Ptr to LS parent in the class tree */ - struct cbq_class *tparent; /* Ptr to tree parent in the class tree */ - struct cbq_class *borrow; /* NULL if class is bandwidth limited; - parent otherwise */ - struct cbq_class *sibling; /* Sibling chain */ - struct cbq_class *children; /* Pointer to children chain */ - - struct Qdisc *q; /* Elementary queueing discipline */ - - -/* Variables */ - unsigned char cpriority; /* Effective priority */ - unsigned char delayed; - unsigned char level; /* level of the class in hierarchy: - 0 for leaf classes, and maximal - level of children + 1 for nodes. - */ - - psched_time_t last; /* Last end of service */ - psched_time_t undertime; - long avgidle; - long deficit; /* Saved deficit for WRR */ - psched_time_t penalized; - struct gnet_stats_basic_packed bstats; - struct gnet_stats_queue qstats; - struct net_rate_estimator __rcu *rate_est; - struct tc_cbq_xstats xstats; - - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - - int refcnt; - int filters; - - struct cbq_class *defaults[TC_PRIO_MAX + 1]; -}; - -struct cbq_sched_data { - struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO + 1]; - unsigned int quanta[TC_CBQ_MAXPRIO + 1]; - - struct cbq_class link; - - unsigned int activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes - with backlog */ - -#ifdef CONFIG_NET_CLS_ACT - struct cbq_class *rx_class; -#endif - struct cbq_class *tx_class; - struct cbq_class *tx_borrowed; - int tx_len; - psched_time_t now; /* Cached timestamp */ - unsigned int pmask; - - struct hrtimer delay_timer; - struct qdisc_watchdog watchdog; /* Watchdog timer, - started when CBQ has - backlog, but cannot - transmit just now */ - psched_tdiff_t wd_expires; - int toplevel; - u32 hgenerator; -}; - - -#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) - -static inline struct cbq_class * -cbq_class_lookup(struct cbq_sched_data *q, u32 classid) -{ - struct Qdisc_class_common *clc; - - clc = qdisc_class_find(&q->clhash, classid); - if (clc == NULL) - return NULL; - return container_of(clc, struct cbq_class, common); -} - -#ifdef CONFIG_NET_CLS_ACT - -static struct cbq_class * -cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) -{ - struct cbq_class *cl; - - for (cl = this->tparent; cl; cl = cl->tparent) { - struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; - - if (new != NULL && new != this) - return new; - } - return NULL; -} - -#endif - -/* Classify packet. The procedure is pretty complicated, but - * it allows us to combine link sharing and priority scheduling - * transparently. - * - * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - * so that it resolves to split nodes. Then packets are classified - * by logical priority, or a more specific classifier may be attached - * to the split node. - */ - -static struct cbq_class * -cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *head = &q->link; - struct cbq_class **defmap; - struct cbq_class *cl = NULL; - u32 prio = skb->priority; - struct tcf_proto *fl; - struct tcf_result res; - - /* - * Step 1. If skb->priority points to one of our classes, use it. - */ - if (TC_H_MAJ(prio ^ sch->handle) == 0 && - (cl = cbq_class_lookup(q, prio)) != NULL) - return cl; - - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - for (;;) { - int result = 0; - defmap = head->defaults; - - fl = rcu_dereference_bh(head->filter_list); - /* - * Step 2+n. Apply classifier. - */ - result = tcf_classify(skb, fl, &res, true); - if (!fl || result < 0) - goto fallback; - - cl = (void *)res.class; - if (!cl) { - if (TC_H_MAJ(res.classid)) - cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) - cl = defmap[TC_PRIO_BESTEFFORT]; - - if (cl == NULL) - goto fallback; - } - if (cl->level >= head->level) - goto fallback; -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - return NULL; - case TC_ACT_RECLASSIFY: - return cbq_reclassify(skb, cl); - } -#endif - if (cl->level == 0) - return cl; - - /* - * Step 3+n. If classifier selected a link sharing class, - * apply agency specific classifier. - * Repeat this procdure until we hit a leaf node. - */ - head = cl; - } - -fallback: - cl = head; - - /* - * Step 4. No success... - */ - if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio & TC_PRIO_MAX]) && - !(cl = head->defaults[TC_PRIO_BESTEFFORT])) - return head; - - return cl; -} - -/* - * A packet has just been enqueued on the empty class. - * cbq_activate_class adds it to the tail of active class list - * of its priority band. - */ - -static inline void cbq_activate_class(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - int prio = cl->cpriority; - struct cbq_class *cl_tail; - - cl_tail = q->active[prio]; - q->active[prio] = cl; - - if (cl_tail != NULL) { - cl->next_alive = cl_tail->next_alive; - cl_tail->next_alive = cl; - } else { - cl->next_alive = cl; - q->activemask |= (1<<prio); - } -} - -/* - * Unlink class from active chain. - * Note that this same procedure is done directly in cbq_dequeue* - * during round-robin procedure. - */ - -static void cbq_deactivate_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - int prio = this->cpriority; - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - - do { - cl = cl_prev->next_alive; - if (cl == this) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - return; - } - } - return; - } - } while ((cl_prev = cl) != q->active[prio]); -} - -static void -cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) -{ - int toplevel = q->toplevel; - - if (toplevel > cl->level) { - psched_time_t now = psched_get_time(); - - do { - if (cl->undertime < now) { - q->toplevel = cl->level; - return; - } - } while ((cl = cl->borrow) != NULL && toplevel > cl->level); - } -} - -static int -cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - int uninitialized_var(ret); - struct cbq_class *cl = cbq_classify(skb, sch, &ret); - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = cl; -#endif - if (cl == NULL) { - if (ret & __NET_XMIT_BYPASS) - qdisc_qstats_drop(sch); - __qdisc_drop(skb, to_free); - return ret; - } - - ret = qdisc_enqueue(skb, cl->q, to_free); - if (ret == NET_XMIT_SUCCESS) { - sch->q.qlen++; - cbq_mark_toplevel(q, cl); - if (!cl->next_alive) - cbq_activate_class(cl); - return ret; - } - - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - cbq_mark_toplevel(q, cl); - cl->qstats.drops++; - } - return ret; -} - -/* Overlimit action: penalize leaf class by adding offtime */ -static void cbq_overlimit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - psched_tdiff_t delay = cl->undertime - q->now; - - if (!cl->delayed) { - delay += cl->offtime; - - /* - * Class goes to sleep, so that it will have no - * chance to work avgidle. Let's forgive it 8) - * - * BTW cbq-2.0 has a crap in this - * place, apparently they forgot to shift it by cl->ewma_log. - */ - if (cl->avgidle < 0) - delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); - if (cl->avgidle < cl->minidle) - cl->avgidle = cl->minidle; - if (delay <= 0) - delay = 1; - cl->undertime = q->now + delay; - - cl->xstats.overactions++; - cl->delayed = 1; - } - if (q->wd_expires == 0 || q->wd_expires > delay) - q->wd_expires = delay; - - /* Dirty work! We must schedule wakeups based on - * real available rate, rather than leaf rate, - * which may be tiny (even zero). - */ - if (q->toplevel == TC_CBQ_MAXLEVEL) { - struct cbq_class *b; - psched_tdiff_t base_delay = q->wd_expires; - - for (b = cl->borrow; b; b = b->borrow) { - delay = b->undertime - q->now; - if (delay < base_delay) { - if (delay <= 0) - delay = 1; - base_delay = delay; - } - } - - q->wd_expires = base_delay; - } -} - -static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio, - psched_time_t now) -{ - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - psched_time_t sched = now; - - if (cl_prev == NULL) - return 0; - - do { - cl = cl_prev->next_alive; - if (now - cl->penalized > 0) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - cl->cpriority = cl->priority; - cl->delayed = 0; - cbq_activate_class(cl); - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - return 0; - } - } - - cl = cl_prev->next_alive; - } else if (sched - cl->penalized > 0) - sched = cl->penalized; - } while ((cl_prev = cl) != q->active[prio]); - - return sched - now; -} - -static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) -{ - struct cbq_sched_data *q = container_of(timer, struct cbq_sched_data, - delay_timer); - struct Qdisc *sch = q->watchdog.qdisc; - psched_time_t now; - psched_tdiff_t delay = 0; - unsigned int pmask; - - now = psched_get_time(); - - pmask = q->pmask; - q->pmask = 0; - - while (pmask) { - int prio = ffz(~pmask); - psched_tdiff_t tmp; - - pmask &= ~(1<<prio); - - tmp = cbq_undelay_prio(q, prio, now); - if (tmp > 0) { - q->pmask |= 1<<prio; - if (tmp < delay || delay == 0) - delay = tmp; - } - } - - if (delay) { - ktime_t time; - - time = 0; - time = ktime_add_ns(time, PSCHED_TICKS2NS(now + delay)); - hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS_PINNED); - } - - __netif_schedule(qdisc_root(sch)); - return HRTIMER_NORESTART; -} - -/* - * It is mission critical procedure. - * - * We "regenerate" toplevel cutoff, if transmitting class - * has backlog and it is not regulated. It is not part of - * original CBQ description, but looks more reasonable. - * Probably, it is wrong. This question needs further investigation. - */ - -static inline void -cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, - struct cbq_class *borrowed) -{ - if (cl && q->toplevel >= borrowed->level) { - if (cl->q->q.qlen > 1) { - do { - if (borrowed->undertime == PSCHED_PASTPERFECT) { - q->toplevel = borrowed->level; - return; - } - } while ((borrowed = borrowed->borrow) != NULL); - } -#if 0 - /* It is not necessary now. Uncommenting it - will save CPU cycles, but decrease fairness. - */ - q->toplevel = TC_CBQ_MAXLEVEL; -#endif - } -} - -static void -cbq_update(struct cbq_sched_data *q) -{ - struct cbq_class *this = q->tx_class; - struct cbq_class *cl = this; - int len = q->tx_len; - psched_time_t now; - - q->tx_class = NULL; - /* Time integrator. We calculate EOS time - * by adding expected packet transmission time. - */ - now = q->now + L2T(&q->link, len); - - for ( ; cl; cl = cl->share) { - long avgidle = cl->avgidle; - long idle; - - cl->bstats.packets++; - cl->bstats.bytes += len; - - /* - * (now - last) is total time between packet right edges. - * (last_pktlen/rate) is "virtual" busy time, so that - * - * idle = (now - last) - last_pktlen/rate - */ - - idle = now - cl->last; - if ((unsigned long)idle > 128*1024*1024) { - avgidle = cl->maxidle; - } else { - idle -= L2T(cl, len); - - /* true_avgidle := (1-W)*true_avgidle + W*idle, - * where W=2^{-ewma_log}. But cl->avgidle is scaled: - * cl->avgidle == true_avgidle/W, - * hence: - */ - avgidle += idle - (avgidle>>cl->ewma_log); - } - - if (avgidle <= 0) { - /* Overlimit or at-limit */ - - if (avgidle < cl->minidle) - avgidle = cl->minidle; - - cl->avgidle = avgidle; - - /* Calculate expected time, when this class - * will be allowed to send. - * It will occur, when: - * (1-W)*true_avgidle + W*delay = 0, i.e. - * idle = (1/W - 1)*(-true_avgidle) - * or - * idle = (1 - W)*(-cl->avgidle); - */ - idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); - - /* - * That is not all. - * To maintain the rate allocated to the class, - * we add to undertime virtual clock, - * necessary to complete transmitted packet. - * (len/phys_bandwidth has been already passed - * to the moment of cbq_update) - */ - - idle -= L2T(&q->link, len); - idle += L2T(cl, len); - - cl->undertime = now + idle; - } else { - /* Underlimit */ - - cl->undertime = PSCHED_PASTPERFECT; - if (avgidle > cl->maxidle) - cl->avgidle = cl->maxidle; - else - cl->avgidle = avgidle; - } - if ((s64)(now - cl->last) > 0) - cl->last = now; - } - - cbq_update_toplevel(q, this, q->tx_borrowed); -} - -static inline struct cbq_class * -cbq_under_limit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *this_cl = cl; - - if (cl->tparent == NULL) - return cl; - - if (cl->undertime == PSCHED_PASTPERFECT || q->now >= cl->undertime) { - cl->delayed = 0; - return cl; - } - - do { - /* It is very suspicious place. Now overlimit - * action is generated for not bounded classes - * only if link is completely congested. - * Though it is in agree with ancestor-only paradigm, - * it looks very stupid. Particularly, - * it means that this chunk of code will either - * never be called or result in strong amplification - * of burstiness. Dangerous, silly, and, however, - * no another solution exists. - */ - cl = cl->borrow; - if (!cl) { - this_cl->qstats.overlimits++; - cbq_overlimit(this_cl); - return NULL; - } - if (cl->level > q->toplevel) - return NULL; - } while (cl->undertime != PSCHED_PASTPERFECT && q->now < cl->undertime); - - cl->delayed = 0; - return cl; -} - -static inline struct sk_buff * -cbq_dequeue_prio(struct Qdisc *sch, int prio) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl_tail, *cl_prev, *cl; - struct sk_buff *skb; - int deficit; - - cl_tail = cl_prev = q->active[prio]; - cl = cl_prev->next_alive; - - do { - deficit = 0; - - /* Start round */ - do { - struct cbq_class *borrow = cl; - - if (cl->q->q.qlen && - (borrow = cbq_under_limit(cl)) == NULL) - goto skip_class; - - if (cl->deficit <= 0) { - /* Class exhausted its allotment per - * this round. Switch to the next one. - */ - deficit = 1; - cl->deficit += cl->quantum; - goto next_class; - } - - skb = cl->q->dequeue(cl->q); - - /* Class did not give us any skb :-( - * It could occur even if cl->q->q.qlen != 0 - * f.e. if cl->q == "tbf" - */ - if (skb == NULL) - goto skip_class; - - cl->deficit -= qdisc_pkt_len(skb); - q->tx_class = cl; - q->tx_borrowed = borrow; - if (borrow != cl) { -#ifndef CBQ_XSTATS_BORROWS_BYTES - borrow->xstats.borrows++; - cl->xstats.borrows++; -#else - borrow->xstats.borrows += qdisc_pkt_len(skb); - cl->xstats.borrows += qdisc_pkt_len(skb); -#endif - } - q->tx_len = qdisc_pkt_len(skb); - - if (cl->deficit <= 0) { - q->active[prio] = cl; - cl = cl->next_alive; - cl->deficit += cl->quantum; - } - return skb; - -skip_class: - if (cl->q->q.qlen == 0 || prio != cl->cpriority) { - /* Class is empty or penalized. - * Unlink it from active chain. - */ - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - /* Did cl_tail point to it? */ - if (cl == cl_tail) { - /* Repair it! */ - cl_tail = cl_prev; - - /* Was it the last class in this band? */ - if (cl == cl_tail) { - /* Kill the band! */ - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - if (cl->q->q.qlen) - cbq_activate_class(cl); - return NULL; - } - - q->active[prio] = cl_tail; - } - if (cl->q->q.qlen) - cbq_activate_class(cl); - - cl = cl_prev; - } - -next_class: - cl_prev = cl; - cl = cl->next_alive; - } while (cl_prev != cl_tail); - } while (deficit); - - q->active[prio] = cl_prev; - - return NULL; -} - -static inline struct sk_buff * -cbq_dequeue_1(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct sk_buff *skb; - unsigned int activemask; - - activemask = q->activemask & 0xFF; - while (activemask) { - int prio = ffz(~activemask); - activemask &= ~(1<<prio); - skb = cbq_dequeue_prio(sch, prio); - if (skb) - return skb; - } - return NULL; -} - -static struct sk_buff * -cbq_dequeue(struct Qdisc *sch) -{ - struct sk_buff *skb; - struct cbq_sched_data *q = qdisc_priv(sch); - psched_time_t now; - - now = psched_get_time(); - - if (q->tx_class) - cbq_update(q); - - q->now = now; - - for (;;) { - q->wd_expires = 0; - - skb = cbq_dequeue_1(sch); - if (skb) { - qdisc_bstats_update(sch, skb); - sch->q.qlen--; - return skb; - } - - /* All the classes are overlimit. - * - * It is possible, if: - * - * 1. Scheduler is empty. - * 2. Toplevel cutoff inhibited borrowing. - * 3. Root class is overlimit. - * - * Reset 2d and 3d conditions and retry. - * - * Note, that NS and cbq-2.0 are buggy, peeking - * an arbitrary class is appropriate for ancestor-only - * sharing, but not for toplevel algorithm. - * - * Our version is better, but slower, because it requires - * two passes, but it is unavoidable with top-level sharing. - */ - - if (q->toplevel == TC_CBQ_MAXLEVEL && - q->link.undertime == PSCHED_PASTPERFECT) - break; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->link.undertime = PSCHED_PASTPERFECT; - } - - /* No packets in scheduler or nobody wants to give them to us :-( - * Sigh... start watchdog timer in the last case. - */ - - if (sch->q.qlen) { - qdisc_qstats_overlimit(sch); - if (q->wd_expires) - qdisc_watchdog_schedule(&q->watchdog, - now + q->wd_expires); - } - return NULL; -} - -/* CBQ class maintanance routines */ - -static void cbq_adjust_levels(struct cbq_class *this) -{ - if (this == NULL) - return; - - do { - int level = 0; - struct cbq_class *cl; - - cl = this->children; - if (cl) { - do { - if (cl->level > level) - level = cl->level; - } while ((cl = cl->sibling) != this->children); - } - this->level = level + 1; - } while ((this = this->tparent) != NULL); -} - -static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) -{ - struct cbq_class *cl; - unsigned int h; - - if (q->quanta[prio] == 0) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - /* BUGGGG... Beware! This expression suffer of - * arithmetic overflows! - */ - if (cl->priority == prio) { - cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ - q->quanta[prio]; - } - if (cl->quantum <= 0 || - cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { - pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); - cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; - } - } - } -} - -static void cbq_sync_defmap(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *split = cl->split; - unsigned int h; - int i; - - if (split == NULL) - return; - - for (i = 0; i <= TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) - split->defaults[i] = NULL; - } - - for (i = 0; i <= TC_PRIO_MAX; i++) { - int level = split->level; - - if (split->defaults[i]) - continue; - - for (h = 0; h < q->clhash.hashsize; h++) { - struct cbq_class *c; - - hlist_for_each_entry(c, &q->clhash.hash[h], - common.hnode) { - if (c->split == split && c->level < level && - c->defmap & (1<<i)) { - split->defaults[i] = c; - level = c->level; - } - } - } - } -} - -static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 mask) -{ - struct cbq_class *split = NULL; - - if (splitid == 0) { - split = cl->split; - if (!split) - return; - splitid = split->common.classid; - } - - if (split == NULL || split->common.classid != splitid) { - for (split = cl->tparent; split; split = split->tparent) - if (split->common.classid == splitid) - break; - } - - if (split == NULL) - return; - - if (cl->split != split) { - cl->defmap = 0; - cbq_sync_defmap(cl); - cl->split = split; - cl->defmap = def & mask; - } else - cl->defmap = (cl->defmap & ~mask) | (def & mask); - - cbq_sync_defmap(cl); -} - -static void cbq_unlink_class(struct cbq_class *this) -{ - struct cbq_class *cl, **clp; - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - - qdisc_class_hash_remove(&q->clhash, &this->common); - - if (this->tparent) { - clp = &this->sibling; - cl = *clp; - do { - if (cl == this) { - *clp = cl->sibling; - break; - } - clp = &cl->sibling; - } while ((cl = *clp) != this->sibling); - - if (this->tparent->children == this) { - this->tparent->children = this->sibling; - if (this->sibling == this) - this->tparent->children = NULL; - } - } else { - WARN_ON(this->sibling != this); - } -} - -static void cbq_link_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - struct cbq_class *parent = this->tparent; - - this->sibling = this; - qdisc_class_hash_insert(&q->clhash, &this->common); - - if (parent == NULL) - return; - - if (parent->children == NULL) { - parent->children = this; - } else { - this->sibling = parent->children->sibling; - parent->children->sibling = this; - } -} - -static void -cbq_reset(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - int prio; - unsigned int h; - - q->activemask = 0; - q->pmask = 0; - q->tx_class = NULL; - q->tx_borrowed = NULL; - qdisc_watchdog_cancel(&q->watchdog); - hrtimer_cancel(&q->delay_timer); - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++) - q->active[prio] = NULL; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - qdisc_reset(cl->q); - - cl->next_alive = NULL; - cl->undertime = PSCHED_PASTPERFECT; - cl->avgidle = cl->maxidle; - cl->deficit = cl->quantum; - cl->cpriority = cl->priority; - } - } - sch->q.qlen = 0; -} - - -static int cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) -{ - if (lss->change & TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; - } - if (lss->change & TCF_CBQ_LSS_EWMA) - cl->ewma_log = lss->ewma_log; - if (lss->change & TCF_CBQ_LSS_AVPKT) - cl->avpkt = lss->avpkt; - if (lss->change & TCF_CBQ_LSS_MINIDLE) - cl->minidle = -(long)lss->minidle; - if (lss->change & TCF_CBQ_LSS_MAXIDLE) { - cl->maxidle = lss->maxidle; - cl->avgidle = lss->maxidle; - } - if (lss->change & TCF_CBQ_LSS_OFFTIME) - cl->offtime = lss->offtime; - return 0; -} - -static void cbq_rmprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]--; - q->quanta[cl->priority] -= cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static void cbq_addprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]++; - q->quanta[cl->priority] += cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - - if (wrr->allot) - cl->allot = wrr->allot; - if (wrr->weight) - cl->weight = wrr->weight; - if (wrr->priority) { - cl->priority = wrr->priority - 1; - cl->cpriority = cl->priority; - if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO - 1; - } - - cbq_addprio(q, cl); - return 0; -} - -static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt) -{ - cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange); - return 0; -} - -static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { - [TCA_CBQ_LSSOPT] = { .len = sizeof(struct tc_cbq_lssopt) }, - [TCA_CBQ_WRROPT] = { .len = sizeof(struct tc_cbq_wrropt) }, - [TCA_CBQ_FOPT] = { .len = sizeof(struct tc_cbq_fopt) }, - [TCA_CBQ_OVL_STRATEGY] = { .len = sizeof(struct tc_cbq_ovl) }, - [TCA_CBQ_RATE] = { .len = sizeof(struct tc_ratespec) }, - [TCA_CBQ_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, - [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, -}; - -static int cbq_init(struct Qdisc *sch, struct nlattr *opt) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct tc_ratespec *r; - int err; - - err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, NULL); - if (err < 0) - return err; - - if (tb[TCA_CBQ_RTAB] == NULL || tb[TCA_CBQ_RATE] == NULL) - return -EINVAL; - - r = nla_data(tb[TCA_CBQ_RATE]); - - if ((q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB])) == NULL) - return -EINVAL; - - err = qdisc_class_hash_init(&q->clhash); - if (err < 0) - goto put_rtab; - - q->link.refcnt = 1; - q->link.sibling = &q->link; - q->link.common.classid = sch->handle; - q->link.qdisc = sch; - q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle); - if (!q->link.q) - q->link.q = &noop_qdisc; - else - qdisc_hash_add(q->link.q, true); - - q->link.priority = TC_CBQ_MAXPRIO - 1; - q->link.priority2 = TC_CBQ_MAXPRIO - 1; - q->link.cpriority = TC_CBQ_MAXPRIO - 1; - q->link.allot = psched_mtu(qdisc_dev(sch)); - q->link.quantum = q->link.allot; - q->link.weight = q->link.R_tab->rate.rate; - - q->link.ewma_log = TC_CBQ_DEF_EWMA; - q->link.avpkt = q->link.allot/2; - q->link.minidle = -0x7FFFFFFF; - - qdisc_watchdog_init(&q->watchdog, sch); - hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); - q->delay_timer.function = cbq_undelay; - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - cbq_link_class(&q->link); - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(&q->link, nla_data(tb[TCA_CBQ_LSSOPT])); - - cbq_addprio(q, &q->link); - return 0; - -put_rtab: - qdisc_put_rtab(q->link.R_tab); - return err; -} - -static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - - if (nla_put(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_lssopt opt; - - opt.flags = 0; - if (cl->borrow == NULL) - opt.flags |= TCF_CBQ_LSS_BOUNDED; - if (cl->share == NULL) - opt.flags |= TCF_CBQ_LSS_ISOLATED; - opt.ewma_log = cl->ewma_log; - opt.level = cl->level; - opt.avpkt = cl->avpkt; - opt.maxidle = cl->maxidle; - opt.minidle = (u32)(-cl->minidle); - opt.offtime = cl->offtime; - opt.change = ~0; - if (nla_put(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_wrropt opt; - - memset(&opt, 0, sizeof(opt)); - opt.flags = 0; - opt.allot = cl->allot; - opt.priority = cl->priority + 1; - opt.cpriority = cl->cpriority + 1; - opt.weight = cl->weight; - if (nla_put(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_fopt opt; - - if (cl->split || cl->defmap) { - opt.split = cl->split ? cl->split->common.classid : 0; - opt.defmap = cl->defmap; - opt.defchange = ~0; - if (nla_put(skb, TCA_CBQ_FOPT, sizeof(opt), &opt)) - goto nla_put_failure; - } - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) -{ - if (cbq_dump_lss(skb, cl) < 0 || - cbq_dump_rate(skb, cl) < 0 || - cbq_dump_wrr(skb, cl) < 0 || - cbq_dump_fopt(skb, cl) < 0) - return -1; - return 0; -} - -static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *nest; - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, &q->link) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - q->link.xstats.avgidle = q->link.avgidle; - return gnet_stats_copy_app(d, &q->link.xstats, sizeof(q->link.xstats)); -} - -static int -cbq_dump_class(struct Qdisc *sch, unsigned long arg, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - struct nlattr *nest; - - if (cl->tparent) - tcm->tcm_parent = cl->tparent->common.classid; - else - tcm->tcm_parent = TC_H_ROOT; - tcm->tcm_handle = cl->common.classid; - tcm->tcm_info = cl->q->handle; - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, cl) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - cl->xstats.avgidle = cl->avgidle; - cl->xstats.undertime = 0; - - if (cl->undertime != PSCHED_PASTPERFECT) - cl->xstats.undertime = cl->undertime - q->now; - - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0) - return -1; - - return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); -} - -static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, cl->common.classid); - if (new == NULL) - return -ENOBUFS; - } - - *old = qdisc_replace(sch, new, &cl->q); - return 0; -} - -static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - return cl->q; -} - -static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl->q->q.qlen == 0) - cbq_deactivate_class(cl); -} - -static unsigned long cbq_get(struct Qdisc *sch, u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = cbq_class_lookup(q, classid); - - if (cl) { - cl->refcnt++; - return (unsigned long)cl; - } - return 0; -} - -static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - WARN_ON(cl->filters); - - tcf_block_put(cl->block); - qdisc_destroy(cl->q); - qdisc_put_rtab(cl->R_tab); - gen_kill_estimator(&cl->rate_est); - if (cl != &q->link) - kfree(cl); -} - -static void cbq_destroy(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *next; - struct cbq_class *cl; - unsigned int h; - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = NULL; -#endif - /* - * Filters must be destroyed first because we don't destroy the - * classes from root to leafs which means that filters can still - * be bound to classes which have been destroyed already. --TGR '04 - */ - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) - tcf_block_put(cl->block); - } - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], - common.hnode) - cbq_destroy_class(sch, cl); - } - qdisc_class_hash_destroy(&q->clhash); -} - -static void cbq_put(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (--cl->refcnt == 0) { -#ifdef CONFIG_NET_CLS_ACT - spinlock_t *root_lock = qdisc_root_sleeping_lock(sch); - struct cbq_sched_data *q = qdisc_priv(sch); - - spin_lock_bh(root_lock); - if (q->rx_class == cl) - q->rx_class = NULL; - spin_unlock_bh(root_lock); -#endif - - cbq_destroy_class(sch, cl); - } -} - -static int -cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg) -{ - int err; - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)*arg; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct cbq_class *parent; - struct qdisc_rate_table *rtab = NULL; - - if (opt == NULL) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, NULL); - if (err < 0) - return err; - - if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) - return -EOPNOTSUPP; - - if (cl) { - /* Check parent */ - if (parentid) { - if (cl->tparent && - cl->tparent->common.classid != parentid) - return -EINVAL; - if (!cl->tparent && parentid != TC_H_ROOT) - return -EINVAL; - } - - if (tb[TCA_CBQ_RATE]) { - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), - tb[TCA_CBQ_RTAB]); - if (rtab == NULL) - return -EINVAL; - } - - if (tca[TCA_RATE]) { - err = gen_replace_estimator(&cl->bstats, NULL, - &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); - if (err) { - qdisc_put_rtab(rtab); - return err; - } - } - - /* Change class parameters */ - sch_tree_lock(sch); - - if (cl->next_alive != NULL) - cbq_deactivate_class(cl); - - if (rtab) { - qdisc_put_rtab(cl->R_tab); - cl->R_tab = rtab; - } - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - - if (tb[TCA_CBQ_WRROPT]) { - cbq_rmprio(q, cl); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - } - - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - - if (cl->q->q.qlen) - cbq_activate_class(cl); - - sch_tree_unlock(sch); - - return 0; - } - - if (parentid == TC_H_ROOT) - return -EINVAL; - - if (tb[TCA_CBQ_WRROPT] == NULL || tb[TCA_CBQ_RATE] == NULL || - tb[TCA_CBQ_LSSOPT] == NULL) - return -EINVAL; - - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB]); - if (rtab == NULL) - return -EINVAL; - - if (classid) { - err = -EINVAL; - if (TC_H_MAJ(classid ^ sch->handle) || - cbq_class_lookup(q, classid)) - goto failure; - } else { - int i; - classid = TC_H_MAKE(sch->handle, 0x8000); - - for (i = 0; i < 0x8000; i++) { - if (++q->hgenerator >= 0x8000) - q->hgenerator = 1; - if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) - break; - } - err = -ENOSR; - if (i >= 0x8000) - goto failure; - classid = classid|q->hgenerator; - } - - parent = &q->link; - if (parentid) { - parent = cbq_class_lookup(q, parentid); - err = -EINVAL; - if (parent == NULL) - goto failure; - } - - err = -ENOBUFS; - cl = kzalloc(sizeof(*cl), GFP_KERNEL); - if (cl == NULL) - goto failure; - - err = tcf_block_get(&cl->block, &cl->filter_list); - if (err) { - kfree(cl); - return err; - } - - if (tca[TCA_RATE]) { - err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); - if (err) { - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } - } - - cl->R_tab = rtab; - rtab = NULL; - cl->refcnt = 1; - cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); - if (!cl->q) - cl->q = &noop_qdisc; - else - qdisc_hash_add(cl->q, true); - - cl->common.classid = classid; - cl->tparent = parent; - cl->qdisc = sch; - cl->allot = parent->allot; - cl->quantum = cl->allot; - cl->weight = cl->R_tab->rate.rate; - - sch_tree_lock(sch); - cbq_link_class(cl); - cl->borrow = cl->tparent; - if (cl->tparent != &q->link) - cl->share = cl->tparent; - cbq_adjust_levels(parent); - cl->minidle = -0x7FFFFFFF; - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log == 0) - cl->ewma_log = q->link.ewma_log; - if (cl->maxidle == 0) - cl->maxidle = q->link.maxidle; - if (cl->avpkt == 0) - cl->avpkt = q->link.avpkt; - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); - - *arg = (unsigned long)cl; - return 0; - -failure: - qdisc_put_rtab(rtab); - return err; -} - -static int cbq_delete(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - unsigned int qlen, backlog; - - if (cl->filters || cl->children || cl == &q->link) - return -EBUSY; - - sch_tree_lock(sch); - - qlen = cl->q->q.qlen; - backlog = cl->q->qstats.backlog; - qdisc_reset(cl->q); - qdisc_tree_reduce_backlog(cl->q, qlen, backlog); - - if (cl->next_alive) - cbq_deactivate_class(cl); - - if (q->tx_borrowed == cl) - q->tx_borrowed = q->tx_class; - if (q->tx_class == cl) { - q->tx_class = NULL; - q->tx_borrowed = NULL; - } -#ifdef CONFIG_NET_CLS_ACT - if (q->rx_class == cl) - q->rx_class = NULL; -#endif - - cbq_unlink_class(cl); - cbq_adjust_levels(cl->tparent); - cl->defmap = 0; - cbq_sync_defmap(cl); - - cbq_rmprio(q, cl); - sch_tree_unlock(sch); - - BUG_ON(--cl->refcnt == 0); - /* - * This shouldn't happen: we "hold" one cops->get() when called - * from tc_ctl_tclass; the destroy method is done from cops->put(). - */ - - return 0; -} - -static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl == NULL) - cl = &q->link; - - return cl->block; -} - -static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, - u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class *)parent; - struct cbq_class *cl = cbq_class_lookup(q, classid); - - if (cl) { - if (p && p->level <= cl->level) - return 0; - cl->filters++; - return (unsigned long)cl; - } - return 0; -} - -static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cl->filters--; -} - -static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - unsigned int h; - - if (arg->stop) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, (unsigned long)cl, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; - } - } -} - -static const struct Qdisc_class_ops cbq_class_ops = { - .graft = cbq_graft, - .leaf = cbq_leaf, - .qlen_notify = cbq_qlen_notify, - .get = cbq_get, - .put = cbq_put, - .change = cbq_change_class, - .delete = cbq_delete, - .walk = cbq_walk, - .tcf_block = cbq_tcf_block, - .bind_tcf = cbq_bind_filter, - .unbind_tcf = cbq_unbind_filter, - .dump = cbq_dump_class, - .dump_stats = cbq_dump_class_stats, -}; - -static struct Qdisc_ops cbq_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &cbq_class_ops, - .id = "cbq", - .priv_size = sizeof(struct cbq_sched_data), - .enqueue = cbq_enqueue, - .dequeue = cbq_dequeue, - .peek = qdisc_peek_dequeued, - .init = cbq_init, - .reset = cbq_reset, - .destroy = cbq_destroy, - .change = NULL, - .dump = cbq_dump, - .dump_stats = cbq_dump_stats, - .owner = THIS_MODULE, -}; - -static int __init cbq_module_init(void) -{ - return register_qdisc(&cbq_qdisc_ops); -} -static void __exit cbq_module_exit(void) -{ - unregister_qdisc(&cbq_qdisc_ops); -} -module_init(cbq_module_init) -module_exit(cbq_module_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c new file mode 100644 index 000000000000..8c9a0400c862 --- /dev/null +++ b/net/sched/sch_cbs.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * net/sched/sch_cbs.c Credit Based Shaper + * + * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> + */ + +/* Credit Based Shaper (CBS) + * ========================= + * + * This is a simple rate-limiting shaper aimed at TSN applications on + * systems with known traffic workloads. + * + * Its algorithm is defined by the IEEE 802.1Q-2014 Specification, + * Section 8.6.8.2, and explained in more detail in the Annex L of the + * same specification. + * + * There are four tunables to be considered: + * + * 'idleslope': Idleslope is the rate of credits that is + * accumulated (in kilobits per second) when there is at least + * one packet waiting for transmission. Packets are transmitted + * when the current value of credits is equal or greater than + * zero. When there is no packet to be transmitted the amount of + * credits is set to zero. This is the main tunable of the CBS + * algorithm. + * + * 'sendslope': + * Sendslope is the rate of credits that is depleted (it should be a + * negative number of kilobits per second) when a transmission is + * ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section + * 8.6.8.2 item g): + * + * sendslope = idleslope - port_transmit_rate + * + * 'hicredit': Hicredit defines the maximum amount of credits (in + * bytes) that can be accumulated. Hicredit depends on the + * characteristics of interfering traffic, + * 'max_interference_size' is the maximum size of any burst of + * traffic that can delay the transmission of a frame that is + * available for transmission for this traffic class, (IEEE + * 802.1Q-2014 Annex L, Equation L-3): + * + * hicredit = max_interference_size * (idleslope / port_transmit_rate) + * + * 'locredit': Locredit is the minimum amount of credits that can + * be reached. It is a function of the traffic flowing through + * this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2): + * + * locredit = max_frame_size * (sendslope / port_transmit_rate) + */ + +#include <linux/ethtool.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/units.h> + +#include <net/netevent.h> +#include <net/netlink.h> +#include <net/sch_generic.h> +#include <net/pkt_sched.h> + +static LIST_HEAD(cbs_list); +static DEFINE_SPINLOCK(cbs_list_lock); + +struct cbs_sched_data { + bool offload; + int queue; + atomic64_t port_rate; /* in bytes/s */ + s64 last; /* timestamp in ns */ + s64 credits; /* in bytes */ + s32 locredit; /* in bytes */ + s32 hicredit; /* in bytes */ + s64 sendslope; /* in bytes/s */ + s64 idleslope; /* in bytes/s */ + struct qdisc_watchdog watchdog; + int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free); + struct sk_buff *(*dequeue)(struct Qdisc *sch); + struct Qdisc *qdisc; + struct list_head cbs_list; +}; + +static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, + struct sk_buff **to_free) +{ + unsigned int len = qdisc_pkt_len(skb); + int err; + + err = child->ops->enqueue(skb, child, to_free); + if (err != NET_XMIT_SUCCESS) + return err; + + sch->qstats.backlog += len; + sch->q.qlen++; + + return NET_XMIT_SUCCESS; +} + +static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; + + return cbs_child_enqueue(skb, sch, qdisc, to_free); +} + +static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; + + if (sch->q.qlen == 0 && q->credits > 0) { + /* We need to stop accumulating credits when there's + * no enqueued packets and q->credits is positive. + */ + q->credits = 0; + q->last = ktime_get_ns(); + } + + return cbs_child_enqueue(skb, sch, qdisc, to_free); +} + +static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->enqueue(skb, sch, to_free); +} + +/* timediff is in ns, slope is in bytes/s */ +static s64 timediff_to_credits(s64 timediff, s64 slope) +{ + return div64_s64(timediff * slope, NSEC_PER_SEC); +} + +static s64 delay_from_credits(s64 credits, s64 slope) +{ + if (unlikely(slope == 0)) + return S64_MAX; + + return div64_s64(-credits * NSEC_PER_SEC, slope); +} + +static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate) +{ + if (unlikely(port_rate == 0)) + return S64_MAX; + + return div64_s64(len * slope, port_rate); +} + +static struct sk_buff *cbs_child_dequeue(struct Qdisc *sch, struct Qdisc *child) +{ + struct sk_buff *skb; + + skb = child->ops->dequeue(child); + if (!skb) + return NULL; + + qdisc_qstats_backlog_dec(sch, skb); + qdisc_bstats_update(sch, skb); + sch->q.qlen--; + + return skb; +} + +static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; + s64 now = ktime_get_ns(); + struct sk_buff *skb; + s64 credits; + int len; + + /* The previous packet is still being sent */ + if (now < q->last) { + qdisc_watchdog_schedule_ns(&q->watchdog, q->last); + return NULL; + } + if (q->credits < 0) { + credits = timediff_to_credits(now - q->last, q->idleslope); + + credits = q->credits + credits; + q->credits = min_t(s64, credits, q->hicredit); + + if (q->credits < 0) { + s64 delay; + + delay = delay_from_credits(q->credits, q->idleslope); + qdisc_watchdog_schedule_ns(&q->watchdog, now + delay); + + q->last = now; + + return NULL; + } + } + skb = cbs_child_dequeue(sch, qdisc); + if (!skb) + return NULL; + + len = qdisc_pkt_len(skb); + + /* As sendslope is a negative number, this will decrease the + * amount of q->credits. + */ + credits = credits_from_len(len, q->sendslope, + atomic64_read(&q->port_rate)); + credits += q->credits; + + q->credits = max_t(s64, credits, q->locredit); + /* Estimate of the transmission of the last byte of the packet in ns */ + if (unlikely(atomic64_read(&q->port_rate) == 0)) + q->last = now; + else + q->last = now + div64_s64(len * NSEC_PER_SEC, + atomic64_read(&q->port_rate)); + + return skb; +} + +static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; + + return cbs_child_dequeue(sch, qdisc); +} + +static struct sk_buff *cbs_dequeue(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->dequeue(sch); +} + +static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = { + [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) }, +}; + +static void cbs_disable_offload(struct net_device *dev, + struct cbs_sched_data *q) +{ + struct tc_cbs_qopt_offload cbs = { }; + const struct net_device_ops *ops; + int err; + + if (!q->offload) + return; + + q->enqueue = cbs_enqueue_soft; + q->dequeue = cbs_dequeue_soft; + + ops = dev->netdev_ops; + if (!ops->ndo_setup_tc) + return; + + cbs.queue = q->queue; + cbs.enable = 0; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); + if (err < 0) + pr_warn("Couldn't disable CBS offload for queue %d\n", + cbs.queue); +} + +static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, + const struct tc_cbs_qopt *opt, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_cbs_qopt_offload cbs = { }; + int err; + + if (!ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, "Specified device does not support cbs offload"); + return -EOPNOTSUPP; + } + + cbs.queue = q->queue; + + cbs.enable = 1; + cbs.hicredit = opt->hicredit; + cbs.locredit = opt->locredit; + cbs.idleslope = opt->idleslope; + cbs.sendslope = opt->sendslope; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Specified device failed to setup cbs hardware offload"); + return err; + } + + q->enqueue = cbs_enqueue_offload; + q->dequeue = cbs_dequeue_offload; + + return 0; +} + +static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) +{ + struct ethtool_link_ksettings ecmd; + int speed = SPEED_10; + s64 port_rate; + int err; + + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; + +skip: + port_rate = speed * 1000 * BYTES_PER_KBIT; + + atomic64_set(&q->port_rate, port_rate); + netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n", + dev->name, (long long)atomic64_read(&q->port_rate), + ecmd.base.speed); +} + +static int cbs_dev_notifier(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct cbs_sched_data *q; + struct net_device *qdev; + bool found = false; + + ASSERT_RTNL(); + + if (event != NETDEV_UP && event != NETDEV_CHANGE) + return NOTIFY_DONE; + + spin_lock(&cbs_list_lock); + list_for_each_entry(q, &cbs_list, cbs_list) { + qdev = qdisc_dev(q->qdisc); + if (qdev == dev) { + found = true; + break; + } + } + spin_unlock(&cbs_list_lock); + + if (found) + cbs_set_port_rate(dev, q); + + return NOTIFY_DONE; +} + +static int cbs_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct nlattr *tb[TCA_CBS_MAX + 1]; + struct tc_cbs_qopt *qopt; + int err; + + err = nla_parse_nested_deprecated(tb, TCA_CBS_MAX, opt, cbs_policy, + extack); + if (err < 0) + return err; + + if (!tb[TCA_CBS_PARMS]) { + NL_SET_ERR_MSG(extack, "Missing CBS parameter which are mandatory"); + return -EINVAL; + } + + qopt = nla_data(tb[TCA_CBS_PARMS]); + + if (!qopt->offload) { + cbs_set_port_rate(dev, q); + cbs_disable_offload(dev, q); + } else { + err = cbs_enable_offload(dev, q, qopt, extack); + if (err < 0) + return err; + } + + /* Everything went OK, save the parameters used. */ + WRITE_ONCE(q->hicredit, qopt->hicredit); + WRITE_ONCE(q->locredit, qopt->locredit); + WRITE_ONCE(q->idleslope, qopt->idleslope * BYTES_PER_KBIT); + WRITE_ONCE(q->sendslope, qopt->sendslope * BYTES_PER_KBIT); + WRITE_ONCE(q->offload, qopt->offload); + + return 0; +} + +static int cbs_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + if (!opt) { + NL_SET_ERR_MSG(extack, "Missing CBS qdisc options which are mandatory"); + return -EINVAL; + } + + q->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + sch->handle, extack); + if (!q->qdisc) + return -ENOMEM; + + spin_lock(&cbs_list_lock); + list_add(&q->cbs_list, &cbs_list); + spin_unlock(&cbs_list_lock); + + qdisc_hash_add(q->qdisc, false); + + q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); + + q->enqueue = cbs_enqueue_soft; + q->dequeue = cbs_dequeue_soft; + + qdisc_watchdog_init(&q->watchdog, sch); + + return cbs_change(sch, opt, extack); +} + +static void cbs_destroy(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + /* Nothing to do if we couldn't create the underlying qdisc */ + if (!q->qdisc) + return; + + qdisc_watchdog_cancel(&q->watchdog); + cbs_disable_offload(dev, q); + + spin_lock(&cbs_list_lock); + list_del(&q->cbs_list); + spin_unlock(&cbs_list_lock); + + qdisc_put(q->qdisc); +} + +static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct tc_cbs_qopt opt = { }; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + opt.hicredit = READ_ONCE(q->hicredit); + opt.locredit = READ_ONCE(q->locredit); + opt.sendslope = div64_s64(READ_ONCE(q->sendslope), BYTES_PER_KBIT); + opt.idleslope = div64_s64(READ_ONCE(q->idleslope), BYTES_PER_KBIT); + opt.offload = READ_ONCE(q->offload); + + if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static int cbs_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (cl != 1 || !q->qdisc) /* only one class */ + return -ENOENT; + + tcm->tcm_handle |= TC_H_MIN(1); + tcm->tcm_info = q->qdisc->handle; + + return 0; +} + +static int cbs_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old, struct netlink_ext_ack *extack) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + sch->handle, NULL); + if (!new) + new = &noop_qdisc; + } + + *old = qdisc_replace(sch, new, &q->qdisc); + return 0; +} + +static struct Qdisc *cbs_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->qdisc; +} + +static unsigned long cbs_find(struct Qdisc *sch, u32 classid) +{ + return 1; +} + +static void cbs_walk(struct Qdisc *sch, struct qdisc_walker *walker) +{ + if (!walker->stop) { + tc_qdisc_stats_dump(sch, 1, walker); + } +} + +static const struct Qdisc_class_ops cbs_class_ops = { + .graft = cbs_graft, + .leaf = cbs_leaf, + .find = cbs_find, + .walk = cbs_walk, + .dump = cbs_dump_class, +}; + +static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { + .id = "cbs", + .cl_ops = &cbs_class_ops, + .priv_size = sizeof(struct cbs_sched_data), + .enqueue = cbs_enqueue, + .dequeue = cbs_dequeue, + .peek = qdisc_peek_dequeued, + .init = cbs_init, + .reset = qdisc_reset_queue, + .destroy = cbs_destroy, + .change = cbs_change, + .dump = cbs_dump, + .owner = THIS_MODULE, +}; +MODULE_ALIAS_NET_SCH("cbs"); + +static struct notifier_block cbs_device_notifier = { + .notifier_call = cbs_dev_notifier, +}; + +static int __init cbs_module_init(void) +{ + int err; + + err = register_netdevice_notifier(&cbs_device_notifier); + if (err) + return err; + + err = register_qdisc(&cbs_qdisc_ops); + if (err) + unregister_netdevice_notifier(&cbs_device_notifier); + + return err; +} + +static void __exit cbs_module_exit(void) +{ + unregister_qdisc(&cbs_qdisc_ops); + unregister_netdevice_notifier(&cbs_device_notifier); +} +module_init(cbs_module_init) +module_exit(cbs_module_exit) +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Credit Based shaper"); diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index b30a2c70bd48..59e7bdf5063e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_choke.c CHOKE scheduler * * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com> * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * */ #include <linux/module.h> @@ -64,7 +60,6 @@ struct choke_sched_data { u32 forced_drop; /* Forced drops, qavg > max_thresh */ u32 forced_mark; /* Forced marks, qavg > max_thresh */ u32 pdrop; /* Drops due to queue limits */ - u32 other; /* Drops due to drop() calls */ u32 matched; /* Drops to flow match */ } stats; @@ -128,14 +123,13 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx, if (idx == q->tail) choke_zap_tail_holes(q); + --sch->q.qlen; qdisc_qstats_backlog_dec(sch, skb); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_drop(skb, sch, to_free); - --sch->q.qlen; } struct choke_skb_cb { - u16 classid; u8 keys_valid; struct flow_keys_digest keys; }; @@ -146,11 +140,6 @@ static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; } -static inline void choke_set_classid(struct sk_buff *skb, u16 classid) -{ - choke_skb_cb(skb)->classid = classid; -} - /* * Compare flow of two packets * Returns true only if source and destination address and port match. @@ -194,7 +183,7 @@ static struct sk_buff *choke_peek_random(const struct choke_sched_data *q, int retrys = 3; do { - *pidx = (q->head + prandom_u32_max(choke_len(q))) & q->tab_mask; + *pidx = (q->head + get_random_u32_below(choke_len(q))) & q->tab_mask; skb = q->tab[*pidx]; if (skb) return skb; @@ -325,9 +314,8 @@ static void choke_reset(struct Qdisc *sch) rtnl_qdisc_drop(skb, sch); } - sch->q.qlen = 0; - sch->qstats.backlog = 0; - memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + if (q->tab) + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } @@ -344,7 +332,8 @@ static void choke_free(void *addr) kvfree(addr); } -static int choke_change(struct Qdisc *sch, struct nlattr *opt) +static int choke_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct choke_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CHOKE_MAX + 1]; @@ -353,11 +342,13 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) struct sk_buff **old = NULL; unsigned int mask; u32 max_P; + u8 *stab; if (opt == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_CHOKE_MAX, opt, + choke_policy, NULL); if (err < 0) return err; @@ -365,9 +356,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) tb[TCA_CHOKE_STAB] == NULL) return -EINVAL; - max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; + max_P = nla_get_u32_default(tb[TCA_CHOKE_MAX_P], 0); ctl = nla_data(tb[TCA_CHOKE_PARMS]); + stab = nla_data(tb[TCA_CHOKE_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) + return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) return -EINVAL; @@ -376,7 +370,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) if (mask != q->tab_mask) { struct sk_buff **ntab; - ntab = kvmalloc_array((mask + 1), sizeof(struct sk_buff *), GFP_KERNEL | __GFP_ZERO); + ntab = kvcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL); if (!ntab) return -ENOMEM; @@ -411,12 +405,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) } else sch_tree_lock(sch); - q->flags = ctl->flags; - q->limit = ctl->limit; + WRITE_ONCE(q->flags, ctl->flags); + WRITE_ONCE(q->limit, ctl->limit); red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_CHOKE_STAB]), + stab, max_P); red_set_vars(&q->vars); @@ -428,31 +422,33 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int choke_init(struct Qdisc *sch, struct nlattr *opt) +static int choke_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { - return choke_change(sch, opt); + return choke_change(sch, opt, extack); } static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) { struct choke_sched_data *q = qdisc_priv(sch); + u8 Wlog = READ_ONCE(q->parms.Wlog); struct nlattr *opts = NULL; struct tc_red_qopt opt = { - .limit = q->limit, - .flags = q->flags, - .qth_min = q->parms.qth_min >> q->parms.Wlog, - .qth_max = q->parms.qth_max >> q->parms.Wlog, - .Wlog = q->parms.Wlog, - .Plog = q->parms.Plog, - .Scell_log = q->parms.Scell_log, + .limit = READ_ONCE(q->limit), + .flags = READ_ONCE(q->flags), + .qth_min = READ_ONCE(q->parms.qth_min) >> Wlog, + .qth_max = READ_ONCE(q->parms.qth_max) >> Wlog, + .Wlog = Wlog, + .Plog = READ_ONCE(q->parms.Plog), + .Scell_log = READ_ONCE(q->parms.Scell_log), }; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) || - nla_put_u32(skb, TCA_CHOKE_MAX_P, q->parms.max_P)) + nla_put_u32(skb, TCA_CHOKE_MAX_P, READ_ONCE(q->parms.max_P))) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -468,7 +464,6 @@ static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .early = q->stats.prob_drop + q->stats.forced_drop, .marked = q->stats.prob_mark + q->stats.forced_mark, .pdrop = q->stats.pdrop, - .other = q->stats.other, .matched = q->stats.matched, }; @@ -504,6 +499,7 @@ static struct Qdisc_ops choke_qdisc_ops __read_mostly = { .dump_stats = choke_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("choke"); static int __init choke_module_init(void) { @@ -519,3 +515,4 @@ module_init(choke_module_init) module_exit(choke_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Choose and keep responsive flows scheduler"); diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index c518a1efcb9d..c6551578f1cf 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Codel - The Controlled-Delay Active Queue Management algorithm * @@ -7,37 +8,6 @@ * Implemented on linux by : * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions, and the following disclaimer, - * without modification. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. The names of the authors may not be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * Alternatively, provided that this notice is retained in full, this - * software may be distributed under the terms of the GNU General - * Public License ("GPL") version 2, in which case the provisions of the - * GPL apply INSTEAD OF those given above. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH - * DAMAGE. - * */ #include <linux/module.h> @@ -71,10 +41,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); - if (skb) + if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); - - prefetch(&skb->end); /* we'll need skb_shinfo() */ + prefetch(&skb->end); /* we'll need skb_shinfo() */ + } return skb; } @@ -82,7 +52,7 @@ static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; - kfree_skb(skb); + qdisc_dequeue_drop(sch, skb, SKB_DROP_REASON_QDISC_CONGESTED); qdisc_qstats_drop(sch); } @@ -95,10 +65,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) &q->stats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, - * or HTB crashes. Defer it for next round. - */ - if (q->stats.drop_count && sch->q.qlen) { + if (q->stats.drop_count) { qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; q->stats.drop_len = 0; @@ -119,7 +86,8 @@ static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, } q = qdisc_priv(sch); q->drop_overlimit++; - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_reason(skb, sch, to_free, + SKB_DROP_REASON_QDISC_OVERLIMIT); } static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { @@ -130,17 +98,16 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { [TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 }, }; -static int codel_change(struct Qdisc *sch, struct nlattr *opt) +static int codel_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; - unsigned int qlen, dropped = 0; int err; - if (!opt) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt, + codel_policy, NULL); if (err < 0) return err; @@ -149,42 +116,50 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_CODEL_TARGET]) { u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]); - q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->params.target, + ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_CE_THRESHOLD]) { u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]); - q->params.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->params.ce_threshold, + (val * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_INTERVAL]) { u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]); - q->params.interval = ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->params.interval, + ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_CODEL_LIMIT]); + WRITE_ONCE(sch->limit, + nla_get_u32(tb[TCA_CODEL_LIMIT])); if (tb[TCA_CODEL_ECN]) - q->params.ecn = !!nla_get_u32(tb[TCA_CODEL_ECN]); + WRITE_ONCE(q->params.ecn, + !!nla_get_u32(tb[TCA_CODEL_ECN])); - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; } -static int codel_init(struct Qdisc *sch, struct nlattr *opt) +static int codel_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct codel_sched_data *q = qdisc_priv(sch); @@ -196,7 +171,7 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt) q->params.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { - int err = codel_change(sch, opt); + int err = codel_change(sch, opt, extack); if (err) return err; @@ -207,30 +182,34 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt) else sch->flags &= ~TCQ_F_CAN_BYPASS; + sch->flags |= TCQ_F_DEQUEUE_DROPS; + return 0; } static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) { struct codel_sched_data *q = qdisc_priv(sch); + codel_time_t ce_threshold; struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_CODEL_TARGET, - codel_time_to_us(q->params.target)) || + codel_time_to_us(READ_ONCE(q->params.target))) || nla_put_u32(skb, TCA_CODEL_LIMIT, - sch->limit) || + READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_CODEL_INTERVAL, - codel_time_to_us(q->params.interval)) || + codel_time_to_us(READ_ONCE(q->params.interval))) || nla_put_u32(skb, TCA_CODEL_ECN, - q->params.ecn)) + READ_ONCE(q->params.ecn))) goto nla_put_failure; - if (q->params.ce_threshold != CODEL_DISABLED_THRESHOLD && + ce_threshold = READ_ONCE(q->params.ce_threshold); + if (ce_threshold != CODEL_DISABLED_THRESHOLD && nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD, - codel_time_to_us(q->params.ce_threshold))) + codel_time_to_us(ce_threshold))) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -287,6 +266,7 @@ static struct Qdisc_ops codel_qdisc_ops __read_mostly = { .dump_stats = codel_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("codel"); static int __init codel_module_init(void) { diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index a413dc1c2098..9b6d79bd8737 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_drr.c Deficit Round Robin scheduler * * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. */ #include <linux/module.h> @@ -20,10 +17,8 @@ struct drr_class { struct Qdisc_class_common common; - unsigned int refcnt; - unsigned int filter_cnt; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct list_head alist; @@ -40,6 +35,11 @@ struct drr_sched { struct Qdisc_class_hash clhash; }; +static bool cl_is_active(struct drr_class *cl) +{ + return !list_empty(&cl->alist); +} + static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid) { struct drr_sched *q = qdisc_priv(sch); @@ -51,21 +51,13 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct drr_class, common); } -static void drr_purge_queue(struct drr_class *cl) -{ - unsigned int len = cl->qdisc->q.qlen; - unsigned int backlog = cl->qdisc->qstats.backlog; - - qdisc_reset(cl->qdisc); - qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); -} - static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = { [TCA_DRR_QUANTUM] = { .type = NLA_U32 }, }; static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl = (struct drr_class *)*arg; @@ -74,17 +66,22 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, u32 quantum; int err; - if (!opt) + if (!opt) { + NL_SET_ERR_MSG(extack, "DRR options are required for this operation"); return -EINVAL; + } - err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_DRR_MAX, opt, drr_policy, + extack); if (err < 0) return err; if (tb[TCA_DRR_QUANTUM]) { quantum = nla_get_u32(tb[TCA_DRR_QUANTUM]); - if (quantum == 0) + if (quantum == 0) { + NL_SET_ERR_MSG(extack, "Specified DRR quantum cannot be zero"); return -EINVAL; + } } else quantum = psched_mtu(qdisc_dev(sch)); @@ -92,11 +89,12 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), + NULL, true, tca[TCA_RATE]); - if (err) + if (err) { + NL_SET_ERR_MSG(extack, "Failed to replace estimator"); return err; + } } sch_tree_lock(sch); @@ -111,11 +109,13 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - cl->refcnt = 1; + gnet_stats_basic_sync_init(&cl->bstats); + INIT_LIST_HEAD(&cl->alist); cl->common.classid = classid; cl->quantum = quantum; cl->qdisc = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + &pfifo_qdisc_ops, classid, + NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; else @@ -123,11 +123,10 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { - qdisc_destroy(cl->qdisc); + NL_SET_ERR_MSG(extack, "Failed to replace estimator"); + qdisc_put(cl->qdisc); kfree(cl); return err; } @@ -146,57 +145,46 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl) { gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } -static int drr_delete_class(struct Qdisc *sch, unsigned long arg) +static int drr_delete_class(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl = (struct drr_class *)arg; - if (cl->filter_cnt > 0) + if (qdisc_class_in_use(&cl->common)) { + NL_SET_ERR_MSG(extack, "DRR class is in use"); return -EBUSY; + } sch_tree_lock(sch); - drr_purge_queue(cl); + qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); - BUG_ON(--cl->refcnt == 0); - /* - * This shouldn't happen: we "hold" one cops->get() when called - * from tc_ctl_tclass; the destroy method is done from cops->put(). - */ - sch_tree_unlock(sch); - return 0; -} - -static unsigned long drr_get_class(struct Qdisc *sch, u32 classid) -{ - struct drr_class *cl = drr_find_class(sch, classid); - if (cl != NULL) - cl->refcnt++; - - return (unsigned long)cl; + drr_destroy_class(sch, cl); + return 0; } -static void drr_put_class(struct Qdisc *sch, unsigned long arg) +static unsigned long drr_search_class(struct Qdisc *sch, u32 classid) { - struct drr_class *cl = (struct drr_class *)arg; - - if (--cl->refcnt == 0) - drr_destroy_class(sch, cl); + return (unsigned long)drr_find_class(sch, classid); } -static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); - if (cl) + if (cl) { + NL_SET_ERR_MSG(extack, "DRR classid must be zero"); return NULL; + } return q->block; } @@ -206,8 +194,8 @@ static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent, { struct drr_class *cl = drr_find_class(sch, classid); - if (cl != NULL) - cl->filter_cnt++; + if (cl) + qdisc_class_get(&cl->common); return (unsigned long)cl; } @@ -216,17 +204,18 @@ static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct drr_class *cl = (struct drr_class *)arg; - cl->filter_cnt--; + qdisc_class_put(&cl->common); } static int drr_graft_class(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) { struct drr_class *cl = (struct drr_class *)arg; if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, cl->common.classid); + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + cl->common.classid, NULL); if (new == NULL) new = &noop_qdisc; } @@ -246,8 +235,7 @@ static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg) { struct drr_class *cl = (struct drr_class *)arg; - if (cl->qdisc->q.qlen == 0) - list_del(&cl->alist); + list_del_init(&cl->alist); } static int drr_dump_class(struct Qdisc *sch, unsigned long arg, @@ -260,7 +248,7 @@ static int drr_dump_class(struct Qdisc *sch, unsigned long arg, tcm->tcm_handle = cl->common.classid; tcm->tcm_info = cl->qdisc->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_DRR_QUANTUM, cl->quantum)) @@ -276,17 +264,17 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct drr_class *cl = (struct drr_class *)arg; - __u32 qlen = cl->qdisc->q.qlen; + __u32 qlen = qdisc_qlen_sum(cl->qdisc); + struct Qdisc *cl_q = cl->qdisc; struct tc_drr_stats xstats; memset(&xstats, 0, sizeof(xstats)); if (qlen) xstats.deficit = cl->deficit; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0) + gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); @@ -303,15 +291,8 @@ static void drr_walk(struct Qdisc *sch, struct qdisc_walker *arg) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, (unsigned long)cl, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) return; - } - arg->count++; } } } @@ -333,7 +314,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -341,6 +322,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return NULL; } @@ -356,6 +338,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; int err = 0; @@ -377,12 +360,12 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - if (cl->qdisc->q.qlen == 1) { + if (!cl_is_active(cl)) { list_add_tail(&cl->alist, &q->active); cl->deficit = cl->quantum; } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return err; } @@ -411,7 +394,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) if (unlikely(skb == NULL)) goto out; if (cl->qdisc->q.qlen == 0) - list_del(&cl->alist); + list_del_init(&cl->alist); bstats_update(&cl->bstats, skb); qdisc_bstats_update(sch, skb); @@ -427,12 +410,13 @@ out: return NULL; } -static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) +static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; err = qdisc_class_hash_init(&q->clhash); @@ -451,12 +435,10 @@ static void drr_reset_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->qdisc->q.qlen) - list_del(&cl->alist); + list_del_init(&cl->alist); qdisc_reset(cl->qdisc); } } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void drr_destroy_qdisc(struct Qdisc *sch) @@ -479,8 +461,7 @@ static void drr_destroy_qdisc(struct Qdisc *sch) static const struct Qdisc_class_ops drr_class_ops = { .change = drr_change_class, .delete = drr_delete_class, - .get = drr_get_class, - .put = drr_put_class, + .find = drr_search_class, .tcf_block = drr_tcf_block, .bind_tcf = drr_bind_tcf, .unbind_tcf = drr_unbind_tcf, @@ -504,6 +485,7 @@ static struct Qdisc_ops drr_qdisc_ops __read_mostly = { .destroy = drr_destroy_qdisc, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("drr"); static int __init drr_init(void) { @@ -518,3 +500,4 @@ static void __exit drr_exit(void) module_init(drr_init); module_exit(drr_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Deficit Round Robin scheduler"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c deleted file mode 100644 index 6d94fcc3592a..000000000000 --- a/net/sched/sch_dsmark.c +++ /dev/null @@ -1,512 +0,0 @@ -/* net/sched/sch_dsmark.c - Differentiated Services field marker */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/bitops.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <asm/byteorder.h> - -/* - * classid class marking - * ------- ----- ------- - * n/a 0 n/a - * x:0 1 use entry [0] - * ... ... ... - * x:y y>0 y+1 use entry [y] - * ... ... ... - * x:indices-1 indices use entry [indices-1] - * ... ... ... - * x:y y+1 use entry [y & (indices-1)] - * ... ... ... - * 0xffff 0x10000 use entry [indices-1] - */ - - -#define NO_DEFAULT_INDEX (1 << 16) - -struct mask_value { - u8 mask; - u8 value; -}; - -struct dsmark_qdisc_data { - struct Qdisc *q; - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct mask_value *mv; - u16 indices; - u8 set_tc_index; - u32 default_index; /* index range is 0...0xffff */ -#define DSMARK_EMBEDDED_SZ 16 - struct mask_value embedded[DSMARK_EMBEDDED_SZ]; -}; - -static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) -{ - return index <= p->indices && index > 0; -} - -/* ------------------------- Class/flow operations ------------------------- */ - -static int dsmark_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", - __func__, sch, p, new, old); - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle); - if (new == NULL) - new = &noop_qdisc; - } - - *old = qdisc_replace(sch, new, &p->q); - return 0; -} - -static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - return p->q; -} - -static unsigned long dsmark_get(struct Qdisc *sch, u32 classid) -{ - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", - __func__, sch, qdisc_priv(sch), classid); - - return TC_H_MIN(classid) + 1; -} - -static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - return dsmark_get(sch, classid); -} - -static void dsmark_put(struct Qdisc *sch, unsigned long cl) -{ -} - -static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = { - [TCA_DSMARK_INDICES] = { .type = NLA_U16 }, - [TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 }, - [TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG }, - [TCA_DSMARK_MASK] = { .type = NLA_U8 }, - [TCA_DSMARK_VALUE] = { .type = NLA_U8 }, -}; - -static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - - pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", - __func__, sch, p, classid, parent, *arg); - - if (!dsmark_valid_index(p, *arg)) { - err = -ENOENT; - goto errout; - } - - if (!opt) - goto errout; - - err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL); - if (err < 0) - goto errout; - - if (tb[TCA_DSMARK_VALUE]) - p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]); - - if (tb[TCA_DSMARK_MASK]) - p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]); - - err = 0; - -errout: - return err; -} - -static int dsmark_delete(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - if (!dsmark_valid_index(p, arg)) - return -EINVAL; - - p->mv[arg - 1].mask = 0xff; - p->mv[arg - 1].value = 0; - - return 0; -} - -static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int i; - - pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", - __func__, sch, p, walker); - - if (walker->stop) - return; - - for (i = 0; i < p->indices; i++) { - if (p->mv[i].mask == 0xff && !p->mv[i].value) - goto ignore; - if (walker->count >= walker->skip) { - if (walker->fn(sch, i + 1, walker) < 0) { - walker->stop = 1; - break; - } - } -ignore: - walker->count++; - } -} - -static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - return p->block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); - - if (p->set_tc_index) { - int wlen = skb_network_offset(skb); - - switch (tc_skb_protocol(skb)) { - case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv4_get_dsfield(ip_hdr(skb)) - & ~INET_ECN_MASK; - break; - - case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb)) - & ~INET_ECN_MASK; - break; - default: - skb->tc_index = 0; - break; - } - } - - if (TC_H_MAJ(skb->priority) == sch->handle) - skb->tc_index = TC_H_MIN(skb->priority); - else { - struct tcf_result res; - struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tcf_classify(skb, fl, &res, false); - - pr_debug("result %d class 0x%04x\n", result, res.classid); - - switch (result) { -#ifdef CONFIG_NET_CLS_ACT - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - - case TC_ACT_SHOT: - goto drop; -#endif - case TC_ACT_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; - } - } - - err = qdisc_enqueue(skb, p->q, to_free); - if (err != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(err)) - qdisc_qstats_drop(sch); - return err; - } - - qdisc_qstats_backlog_inc(sch, skb); - sch->q.qlen++; - - return NET_XMIT_SUCCESS; - -drop: - qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - u32 index; - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - skb = qdisc_dequeue_peeked(p->q); - if (skb == NULL) - return NULL; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - index = skb->tc_index & (p->indices - 1); - pr_debug("index %d->%d\n", skb->tc_index, index); - - switch (tc_skb_protocol(skb)) { - case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - default: - /* - * Only complain if a change was actually attempted. - * This way, we can send non-IP traffic through dsmark - * and don't need yet another qdisc as a bypass. - */ - if (p->mv[index].mask != 0xff || p->mv[index].value) - pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(tc_skb_protocol(skb))); - break; - } - - return skb; -} - -static struct sk_buff *dsmark_peek(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - return p->q->ops->peek(p->q); -} - -static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - u32 default_index = NO_DEFAULT_INDEX; - u16 indices; - int i; - - pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); - - if (!opt) - goto errout; - - err = tcf_block_get(&p->block, &p->filter_list); - if (err) - return err; - - err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL); - if (err < 0) - goto errout; - - err = -EINVAL; - indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); - - if (hweight32(indices) != 1) - goto errout; - - if (tb[TCA_DSMARK_DEFAULT_INDEX]) - default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]); - - if (indices <= DSMARK_EMBEDDED_SZ) - p->mv = p->embedded; - else - p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL); - if (!p->mv) { - err = -ENOMEM; - goto errout; - } - for (i = 0; i < indices; i++) { - p->mv[i].mask = 0xff; - p->mv[i].value = 0; - } - p->indices = indices; - p->default_index = default_index; - p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - - p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); - if (p->q == NULL) - p->q = &noop_qdisc; - else - qdisc_hash_add(p->q, true); - - pr_debug("%s: qdisc %p\n", __func__, p->q); - - err = 0; -errout: - return err; -} - -static void dsmark_reset(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - qdisc_reset(p->q); - sch->qstats.backlog = 0; - sch->q.qlen = 0; -} - -static void dsmark_destroy(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - tcf_block_put(p->block); - qdisc_destroy(p->q); - if (p->mv != p->embedded) - kfree(p->mv); -} - -static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); - - if (!dsmark_valid_index(p, cl)) - return -EINVAL; - - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); - tcm->tcm_info = p->q->handle; - - opts = nla_nest_start(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || - nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - opts = nla_nest_start(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) - goto nla_put_failure; - - if (p->default_index != NO_DEFAULT_INDEX && - nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index)) - goto nla_put_failure; - - if (p->set_tc_index && - nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static const struct Qdisc_class_ops dsmark_class_ops = { - .graft = dsmark_graft, - .leaf = dsmark_leaf, - .get = dsmark_get, - .put = dsmark_put, - .change = dsmark_change, - .delete = dsmark_delete, - .walk = dsmark_walk, - .tcf_block = dsmark_tcf_block, - .bind_tcf = dsmark_bind_filter, - .unbind_tcf = dsmark_put, - .dump = dsmark_dump_class, -}; - -static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &dsmark_class_ops, - .id = "dsmark", - .priv_size = sizeof(struct dsmark_qdisc_data), - .enqueue = dsmark_enqueue, - .dequeue = dsmark_dequeue, - .peek = dsmark_peek, - .init = dsmark_init, - .reset = dsmark_reset, - .destroy = dsmark_destroy, - .change = NULL, - .dump = dsmark_dump, - .owner = THIS_MODULE, -}; - -static int __init dsmark_module_init(void) -{ - return register_qdisc(&dsmark_qdisc_ops); -} - -static void __exit dsmark_module_exit(void) -{ - unregister_qdisc(&dsmark_qdisc_ops); -} - -module_init(dsmark_module_init) -module_exit(dsmark_module_exit) - -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c new file mode 100644 index 000000000000..6d7e6389758d --- /dev/null +++ b/net/sched/sch_dualpi2.c @@ -0,0 +1,1177 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +/* Copyright (C) 2024 Nokia + * + * Author: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com> + * Author: Olga Albisser <olga@albisser.org> + * Author: Henrik Steen <henrist@henrist.net> + * Author: Olivier Tilmans <olivier.tilmans@nokia.com> + * Author: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com> + * + * DualPI Improved with a Square (dualpi2): + * - Supports congestion controls that comply with the Prague requirements + * in RFC9331 (e.g. TCP-Prague) + * - Supports coupled dual-queue with PI2 as defined in RFC9332 + * - Supports ECN L4S-identifier (IP.ECN==0b*1) + * + * note: Although DCTCP and BBRv3 can use shallow-threshold ECN marks, + * they do not meet the 'Prague L4S Requirements' listed in RFC 9331 + * Section 4, so they can only be used with DualPI2 in a datacenter + * context. + * + * References: + * - RFC9332: https://datatracker.ietf.org/doc/html/rfc9332 + * - De Schepper, Koen, et al. "PI 2: A linearized AQM for both classic and + * scalable TCP." in proc. ACM CoNEXT'16, 2016. + */ + +#include <linux/errno.h> +#include <linux/hrtimer.h> +#include <linux/if_vlan.h> +#include <linux/kernel.h> +#include <linux/limits.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/types.h> + +#include <net/gso.h> +#include <net/inet_ecn.h> +#include <net/pkt_cls.h> +#include <net/pkt_sched.h> + +/* 32b enable to support flows with windows up to ~8.6 * 1e9 packets + * i.e., twice the maximal snd_cwnd. + * MAX_PROB must be consistent with the RNG in dualpi2_roll(). + */ +#define MAX_PROB U32_MAX + +/* alpha/beta values exchanged over netlink are in units of 256ns */ +#define ALPHA_BETA_SHIFT 8 + +/* Scaled values of alpha/beta must fit in 32b to avoid overflow in later + * computations. Consequently (see and dualpi2_scale_alpha_beta()), their + * netlink-provided values can use at most 31b, i.e. be at most (2^23)-1 + * (~4MHz) as those are given in 1/256th. This enable to tune alpha/beta to + * control flows whose maximal RTTs can be in usec up to few secs. + */ +#define ALPHA_BETA_MAX ((1U << 31) - 1) + +/* Internal alpha/beta are in units of 64ns. + * This enables to use all alpha/beta values in the allowed range without loss + * of precision due to rounding when scaling them internally, e.g., + * scale_alpha_beta(1) will not round down to 0. + */ +#define ALPHA_BETA_GRANULARITY 6 + +#define ALPHA_BETA_SCALING (ALPHA_BETA_SHIFT - ALPHA_BETA_GRANULARITY) + +/* We express the weights (wc, wl) in %, i.e., wc + wl = 100 */ +#define MAX_WC 100 + +struct dualpi2_sched_data { + struct Qdisc *l_queue; /* The L4S Low latency queue (L-queue) */ + struct Qdisc *sch; /* The Classic queue (C-queue) */ + + /* Registered tc filters */ + struct tcf_proto __rcu *tcf_filters; + struct tcf_block *tcf_block; + + /* PI2 parameters */ + u64 pi2_target; /* Target delay in nanoseconds */ + u32 pi2_tupdate; /* Timer frequency in nanoseconds */ + u32 pi2_prob; /* Base PI probability */ + u32 pi2_alpha; /* Gain factor for the integral rate response */ + u32 pi2_beta; /* Gain factor for the proportional response */ + struct hrtimer pi2_timer; /* prob update timer */ + + /* Step AQM (L-queue only) parameters */ + u32 step_thresh; /* Step threshold */ + bool step_in_packets; /* Step thresh in packets (1) or time (0) */ + + /* C-queue starvation protection */ + s32 c_protection_credit; /* Credit (sign indicates which queue) */ + s32 c_protection_init; /* Reset value of the credit */ + u8 c_protection_wc; /* C-queue weight (between 0 and MAX_WC) */ + u8 c_protection_wl; /* L-queue weight (MAX_WC - wc) */ + + /* General dualQ parameters */ + u32 memory_limit; /* Memory limit of both queues */ + u8 coupling_factor;/* Coupling factor (k) between both queues */ + u8 ecn_mask; /* Mask to match packets into L-queue */ + u32 min_qlen_step; /* Minimum queue length to apply step thresh */ + bool drop_early; /* Drop at enqueue (1) instead of dequeue (0) */ + bool drop_overload; /* Drop (1) on overload, or overflow (0) */ + bool split_gso; /* Split aggregated skb (1) or leave as is (0) */ + + /* Statistics */ + u64 c_head_ts; /* Enqueue timestamp of the C-queue head */ + u64 l_head_ts; /* Enqueue timestamp of the L-queue head */ + u64 last_qdelay; /* Q delay val at the last probability update */ + u32 packets_in_c; /* Enqueue packet counter of the C-queue */ + u32 packets_in_l; /* Enqueue packet counter of the L-queue */ + u32 maxq; /* Maximum queue size of the C-queue */ + u32 ecn_mark; /* ECN mark pkt counter due to PI probability */ + u32 step_marks; /* ECN mark pkt counter due to step AQM */ + u32 memory_used; /* Memory used of both queues */ + u32 max_memory_used;/* Maximum used memory */ + + /* Deferred drop statistics */ + u32 deferred_drops_cnt; /* Packets dropped */ + u32 deferred_drops_len; /* Bytes dropped */ +}; + +struct dualpi2_skb_cb { + u64 ts; /* Timestamp at enqueue */ + u8 apply_step:1, /* Can we apply the step threshold */ + classified:2, /* Packet classification results */ + ect:2; /* Packet ECT codepoint */ +}; + +enum dualpi2_classification_results { + DUALPI2_C_CLASSIC = 0, /* C-queue */ + DUALPI2_C_L4S = 1, /* L-queue (scale mark/classic drop) */ + DUALPI2_C_LLLL = 2, /* L-queue (no drops/marks) */ + __DUALPI2_C_MAX /* Keep last*/ +}; + +static struct dualpi2_skb_cb *dualpi2_skb_cb(struct sk_buff *skb) +{ + qdisc_cb_private_validate(skb, sizeof(struct dualpi2_skb_cb)); + return (struct dualpi2_skb_cb *)qdisc_skb_cb(skb)->data; +} + +static u64 dualpi2_sojourn_time(struct sk_buff *skb, u64 reference) +{ + return reference - dualpi2_skb_cb(skb)->ts; +} + +static u64 head_enqueue_time(struct Qdisc *q) +{ + struct sk_buff *skb = qdisc_peek_head(q); + + return skb ? dualpi2_skb_cb(skb)->ts : 0; +} + +static u32 dualpi2_scale_alpha_beta(u32 param) +{ + u64 tmp = ((u64)param * MAX_PROB >> ALPHA_BETA_SCALING); + + do_div(tmp, NSEC_PER_SEC); + return tmp; +} + +static u32 dualpi2_unscale_alpha_beta(u32 param) +{ + u64 tmp = ((u64)param * NSEC_PER_SEC << ALPHA_BETA_SCALING); + + do_div(tmp, MAX_PROB); + return tmp; +} + +static ktime_t next_pi2_timeout(struct dualpi2_sched_data *q) +{ + return ktime_add_ns(ktime_get_ns(), q->pi2_tupdate); +} + +static bool skb_is_l4s(struct sk_buff *skb) +{ + return dualpi2_skb_cb(skb)->classified == DUALPI2_C_L4S; +} + +static bool skb_in_l_queue(struct sk_buff *skb) +{ + return dualpi2_skb_cb(skb)->classified != DUALPI2_C_CLASSIC; +} + +static bool skb_apply_step(struct sk_buff *skb, struct dualpi2_sched_data *q) +{ + return skb_is_l4s(skb) && qdisc_qlen(q->l_queue) >= q->min_qlen_step; +} + +static bool dualpi2_mark(struct dualpi2_sched_data *q, struct sk_buff *skb) +{ + if (INET_ECN_set_ce(skb)) { + q->ecn_mark++; + return true; + } + return false; +} + +static void dualpi2_reset_c_protection(struct dualpi2_sched_data *q) +{ + q->c_protection_credit = q->c_protection_init; +} + +/* This computes the initial credit value and WRR weight for the L queue (wl) + * from the weight of the C queue (wc). + * If wl > wc, the scheduler will start with the L queue when reset. + */ +static void dualpi2_calculate_c_protection(struct Qdisc *sch, + struct dualpi2_sched_data *q, u32 wc) +{ + q->c_protection_wc = wc; + q->c_protection_wl = MAX_WC - wc; + q->c_protection_init = (s32)psched_mtu(qdisc_dev(sch)) * + ((int)q->c_protection_wc - (int)q->c_protection_wl); + dualpi2_reset_c_protection(q); +} + +static bool dualpi2_roll(u32 prob) +{ + return get_random_u32() <= prob; +} + +/* Packets in the C-queue are subject to a marking probability pC, which is the + * square of the internal PI probability (i.e., have an overall lower mark/drop + * probability). If the qdisc is overloaded, ignore ECT values and only drop. + * + * Note that this marking scheme is also applied to L4S packets during overload. + * Return true if packet dropping is required in C queue + */ +static bool dualpi2_classic_marking(struct dualpi2_sched_data *q, + struct sk_buff *skb, u32 prob, + bool overload) +{ + if (dualpi2_roll(prob) && dualpi2_roll(prob)) { + if (overload || dualpi2_skb_cb(skb)->ect == INET_ECN_NOT_ECT) + return true; + dualpi2_mark(q, skb); + } + return false; +} + +/* Packets in the L-queue are subject to a marking probability pL given by the + * internal PI probability scaled by the coupling factor. + * + * On overload (i.e., @local_l_prob is >= 100%): + * - if the qdisc is configured to trade losses to preserve latency (i.e., + * @q->drop_overload), apply classic drops first before marking. + * - otherwise, preserve the "no loss" property of ECN at the cost of queueing + * delay, eventually resulting in taildrop behavior once sch->limit is + * reached. + * Return true if packet dropping is required in L queue + */ +static bool dualpi2_scalable_marking(struct dualpi2_sched_data *q, + struct sk_buff *skb, + u64 local_l_prob, u32 prob, + bool overload) +{ + if (overload) { + /* Apply classic drop */ + if (!q->drop_overload || + !(dualpi2_roll(prob) && dualpi2_roll(prob))) + goto mark; + return true; + } + + /* We can safely cut the upper 32b as overload==false */ + if (dualpi2_roll(local_l_prob)) { + /* Non-ECT packets could have classified as L4S by filters. */ + if (dualpi2_skb_cb(skb)->ect == INET_ECN_NOT_ECT) + return true; +mark: + dualpi2_mark(q, skb); + } + return false; +} + +/* Decide whether a given packet must be dropped (or marked if ECT), according + * to the PI2 probability. + * + * Never mark/drop if we have a standing queue of less than 2 MTUs. + */ +static bool must_drop(struct Qdisc *sch, struct dualpi2_sched_data *q, + struct sk_buff *skb) +{ + u64 local_l_prob; + bool overload; + u32 prob; + + if (sch->qstats.backlog < 2 * psched_mtu(qdisc_dev(sch))) + return false; + + prob = READ_ONCE(q->pi2_prob); + local_l_prob = (u64)prob * q->coupling_factor; + overload = local_l_prob > MAX_PROB; + + switch (dualpi2_skb_cb(skb)->classified) { + case DUALPI2_C_CLASSIC: + return dualpi2_classic_marking(q, skb, prob, overload); + case DUALPI2_C_L4S: + return dualpi2_scalable_marking(q, skb, local_l_prob, prob, + overload); + default: /* DUALPI2_C_LLLL */ + return false; + } +} + +static void dualpi2_read_ect(struct sk_buff *skb) +{ + struct dualpi2_skb_cb *cb = dualpi2_skb_cb(skb); + int wlen = skb_network_offset(skb); + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + goto not_ecn; + + cb->ect = ipv4_get_dsfield(ip_hdr(skb)) & INET_ECN_MASK; + break; + case htons(ETH_P_IPV6): + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + goto not_ecn; + + cb->ect = ipv6_get_dsfield(ipv6_hdr(skb)) & INET_ECN_MASK; + break; + default: + goto not_ecn; + } + return; + +not_ecn: + /* Non pullable/writable packets can only be dropped hence are + * classified as not ECT. + */ + cb->ect = INET_ECN_NOT_ECT; +} + +static int dualpi2_skb_classify(struct dualpi2_sched_data *q, + struct sk_buff *skb) +{ + struct dualpi2_skb_cb *cb = dualpi2_skb_cb(skb); + struct tcf_result res; + struct tcf_proto *fl; + int result; + + dualpi2_read_ect(skb); + if (cb->ect & q->ecn_mask) { + cb->classified = DUALPI2_C_L4S; + return NET_XMIT_SUCCESS; + } + + if (TC_H_MAJ(skb->priority) == q->sch->handle && + TC_H_MIN(skb->priority) < __DUALPI2_C_MAX) { + cb->classified = TC_H_MIN(skb->priority); + return NET_XMIT_SUCCESS; + } + + fl = rcu_dereference_bh(q->tcf_filters); + if (!fl) { + cb->classified = DUALPI2_C_CLASSIC; + return NET_XMIT_SUCCESS; + } + + result = tcf_classify(skb, NULL, fl, &res, false); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + } +#endif + cb->classified = TC_H_MIN(res.classid) < __DUALPI2_C_MAX ? + TC_H_MIN(res.classid) : DUALPI2_C_CLASSIC; + } + return NET_XMIT_SUCCESS; +} + +static int dualpi2_enqueue_skb(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct dualpi2_skb_cb *cb; + + if (unlikely(qdisc_qlen(sch) >= sch->limit) || + unlikely((u64)q->memory_used + skb->truesize > q->memory_limit)) { + qdisc_qstats_overlimit(sch); + if (skb_in_l_queue(skb)) + qdisc_qstats_overlimit(q->l_queue); + return qdisc_drop_reason(skb, sch, to_free, + SKB_DROP_REASON_QDISC_OVERLIMIT); + } + + if (q->drop_early && must_drop(sch, q, skb)) { + qdisc_drop_reason(skb, sch, to_free, + SKB_DROP_REASON_QDISC_CONGESTED); + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + } + + cb = dualpi2_skb_cb(skb); + cb->ts = ktime_get_ns(); + q->memory_used += skb->truesize; + if (q->memory_used > q->max_memory_used) + q->max_memory_used = q->memory_used; + + if (qdisc_qlen(sch) > q->maxq) + q->maxq = qdisc_qlen(sch); + + if (skb_in_l_queue(skb)) { + /* Apply step thresh if skb is L4S && L-queue len >= min_qlen */ + dualpi2_skb_cb(skb)->apply_step = skb_apply_step(skb, q); + + /* Keep the overall qdisc stats consistent */ + ++sch->q.qlen; + qdisc_qstats_backlog_inc(sch, skb); + ++q->packets_in_l; + if (!q->l_head_ts) + q->l_head_ts = cb->ts; + return qdisc_enqueue_tail(skb, q->l_queue); + } + ++q->packets_in_c; + if (!q->c_head_ts) + q->c_head_ts = cb->ts; + return qdisc_enqueue_tail(skb, sch); +} + +/* By default, dualpi2 will split GSO skbs into independent skbs and enqueue + * each of those individually. This yields the following benefits, at the + * expense of CPU usage: + * - Finer-grained AQM actions as the sub-packets of a burst no longer share the + * same fate (e.g., the random mark/drop probability is applied individually) + * - Improved precision of the starvation protection/WRR scheduler at dequeue, + * as the size of the dequeued packets will be smaller. + */ +static int dualpi2_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + int err; + + err = dualpi2_skb_classify(q, skb); + if (err != NET_XMIT_SUCCESS) { + if (err & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return err; + } + + if (q->split_gso && skb_is_gso(skb)) { + netdev_features_t features; + struct sk_buff *nskb, *next; + int cnt, byte_len, orig_len; + int err; + + features = netif_skb_features(skb); + nskb = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(nskb)) + return qdisc_drop(skb, sch, to_free); + + cnt = 1; + byte_len = 0; + orig_len = qdisc_pkt_len(skb); + skb_list_walk_safe(nskb, nskb, next) { + skb_mark_not_on_list(nskb); + + /* Iterate through GSO fragments of an skb: + * (1) Set pkt_len from the single GSO fragments + * (2) Copy classified and ect values of an skb + * (3) Enqueue fragment & set ts in dualpi2_enqueue_skb + */ + qdisc_skb_cb(nskb)->pkt_len = nskb->len; + qdisc_skb_cb(nskb)->pkt_segs = 1; + dualpi2_skb_cb(nskb)->classified = + dualpi2_skb_cb(skb)->classified; + dualpi2_skb_cb(nskb)->ect = dualpi2_skb_cb(skb)->ect; + err = dualpi2_enqueue_skb(nskb, sch, to_free); + + if (err == NET_XMIT_SUCCESS) { + /* Compute the backlog adjustment that needs + * to be propagated in the qdisc tree to reflect + * all new skbs successfully enqueued. + */ + ++cnt; + byte_len += nskb->len; + } + } + if (cnt > 1) { + /* The caller will add the original skb stats to its + * backlog, compensate this if any nskb is enqueued. + */ + --cnt; + byte_len -= orig_len; + } + qdisc_tree_reduce_backlog(sch, -cnt, -byte_len); + consume_skb(skb); + return err; + } + return dualpi2_enqueue_skb(skb, sch, to_free); +} + +/* Select the queue from which the next packet can be dequeued, ensuring that + * neither queue can starve the other with a WRR scheduler. + * + * The sign of the WRR credit determines the next queue, while the size of + * the dequeued packet determines the magnitude of the WRR credit change. If + * either queue is empty, the WRR credit is kept unchanged. + * + * As the dequeued packet can be dropped later, the caller has to perform the + * qdisc_bstats_update() calls. + */ +static struct sk_buff *dequeue_packet(struct Qdisc *sch, + struct dualpi2_sched_data *q, + int *credit_change, + u64 now) +{ + struct sk_buff *skb = NULL; + int c_len; + + *credit_change = 0; + c_len = qdisc_qlen(sch) - qdisc_qlen(q->l_queue); + if (qdisc_qlen(q->l_queue) && (!c_len || q->c_protection_credit <= 0)) { + skb = __qdisc_dequeue_head(&q->l_queue->q); + WRITE_ONCE(q->l_head_ts, head_enqueue_time(q->l_queue)); + if (c_len) + *credit_change = q->c_protection_wc; + qdisc_qstats_backlog_dec(q->l_queue, skb); + + /* Keep the global queue size consistent */ + --sch->q.qlen; + q->memory_used -= skb->truesize; + } else if (c_len) { + skb = __qdisc_dequeue_head(&sch->q); + WRITE_ONCE(q->c_head_ts, head_enqueue_time(sch)); + if (qdisc_qlen(q->l_queue)) + *credit_change = ~((s32)q->c_protection_wl) + 1; + q->memory_used -= skb->truesize; + } else { + dualpi2_reset_c_protection(q); + return NULL; + } + *credit_change *= qdisc_pkt_len(skb); + qdisc_qstats_backlog_dec(sch, skb); + return skb; +} + +static int do_step_aqm(struct dualpi2_sched_data *q, struct sk_buff *skb, + u64 now) +{ + u64 qdelay = 0; + + if (q->step_in_packets) + qdelay = qdisc_qlen(q->l_queue); + else + qdelay = dualpi2_sojourn_time(skb, now); + + if (dualpi2_skb_cb(skb)->apply_step && qdelay > q->step_thresh) { + if (!dualpi2_skb_cb(skb)->ect) { + /* Drop this non-ECT packet */ + return 1; + } + + if (dualpi2_mark(q, skb)) + ++q->step_marks; + } + qdisc_bstats_update(q->l_queue, skb); + return 0; +} + +static void drop_and_retry(struct dualpi2_sched_data *q, struct sk_buff *skb, + struct Qdisc *sch, enum skb_drop_reason reason) +{ + ++q->deferred_drops_cnt; + q->deferred_drops_len += qdisc_pkt_len(skb); + kfree_skb_reason(skb, reason); + qdisc_qstats_drop(sch); +} + +static struct sk_buff *dualpi2_qdisc_dequeue(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + int credit_change; + u64 now; + + now = ktime_get_ns(); + + while ((skb = dequeue_packet(sch, q, &credit_change, now))) { + if (!q->drop_early && must_drop(sch, q, skb)) { + drop_and_retry(q, skb, sch, + SKB_DROP_REASON_QDISC_CONGESTED); + continue; + } + + if (skb_in_l_queue(skb) && do_step_aqm(q, skb, now)) { + qdisc_qstats_drop(q->l_queue); + drop_and_retry(q, skb, sch, + SKB_DROP_REASON_DUALPI2_STEP_DROP); + continue; + } + + q->c_protection_credit += credit_change; + qdisc_bstats_update(sch, skb); + break; + } + + if (q->deferred_drops_cnt) { + qdisc_tree_reduce_backlog(sch, q->deferred_drops_cnt, + q->deferred_drops_len); + q->deferred_drops_cnt = 0; + q->deferred_drops_len = 0; + } + return skb; +} + +static s64 __scale_delta(u64 diff) +{ + do_div(diff, 1 << ALPHA_BETA_GRANULARITY); + return diff; +} + +static void get_queue_delays(struct dualpi2_sched_data *q, u64 *qdelay_c, + u64 *qdelay_l) +{ + u64 now, qc, ql; + + now = ktime_get_ns(); + qc = READ_ONCE(q->c_head_ts); + ql = READ_ONCE(q->l_head_ts); + + *qdelay_c = qc ? now - qc : 0; + *qdelay_l = ql ? now - ql : 0; +} + +static u32 calculate_probability(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + u32 new_prob; + u64 qdelay_c; + u64 qdelay_l; + u64 qdelay; + s64 delta; + + get_queue_delays(q, &qdelay_c, &qdelay_l); + qdelay = max(qdelay_l, qdelay_c); + + /* Alpha and beta take at most 32b, i.e, the delay difference would + * overflow for queuing delay differences > ~4.2sec. + */ + delta = ((s64)qdelay - (s64)q->pi2_target) * q->pi2_alpha; + delta += ((s64)qdelay - (s64)q->last_qdelay) * q->pi2_beta; + q->last_qdelay = qdelay; + + /* Bound new_prob between 0 and MAX_PROB */ + if (delta > 0) { + new_prob = __scale_delta(delta) + q->pi2_prob; + if (new_prob < q->pi2_prob) + new_prob = MAX_PROB; + } else { + new_prob = q->pi2_prob - __scale_delta(~delta + 1); + if (new_prob > q->pi2_prob) + new_prob = 0; + } + + /* If we do not drop on overload, ensure we cap the L4S probability to + * 100% to keep window fairness when overflowing. + */ + if (!q->drop_overload) + return min_t(u32, new_prob, MAX_PROB / q->coupling_factor); + return new_prob; +} + +static u32 get_memory_limit(struct Qdisc *sch, u32 limit) +{ + /* Apply rule of thumb, i.e., doubling the packet length, + * to further include per packet overhead in memory_limit. + */ + u64 memlim = mul_u32_u32(limit, 2 * psched_mtu(qdisc_dev(sch))); + + if (upper_32_bits(memlim)) + return U32_MAX; + else + return lower_32_bits(memlim); +} + +static u32 convert_us_to_nsec(u32 us) +{ + u64 ns = mul_u32_u32(us, NSEC_PER_USEC); + + if (upper_32_bits(ns)) + return U32_MAX; + + return lower_32_bits(ns); +} + +static u32 convert_ns_to_usec(u64 ns) +{ + do_div(ns, NSEC_PER_USEC); + if (upper_32_bits(ns)) + return U32_MAX; + + return lower_32_bits(ns); +} + +static enum hrtimer_restart dualpi2_timer(struct hrtimer *timer) +{ + struct dualpi2_sched_data *q = timer_container_of(q, timer, pi2_timer); + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; /* to lock qdisc for probability calculations */ + + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spin_lock(root_lock); + + WRITE_ONCE(q->pi2_prob, calculate_probability(sch)); + hrtimer_set_expires(&q->pi2_timer, next_pi2_timeout(q)); + + spin_unlock(root_lock); + rcu_read_unlock(); + return HRTIMER_RESTART; +} + +static struct netlink_range_validation dualpi2_alpha_beta_range = { + .min = 1, + .max = ALPHA_BETA_MAX, +}; + +static const struct nla_policy dualpi2_policy[TCA_DUALPI2_MAX + 1] = { + [TCA_DUALPI2_LIMIT] = NLA_POLICY_MIN(NLA_U32, 1), + [TCA_DUALPI2_MEMORY_LIMIT] = NLA_POLICY_MIN(NLA_U32, 1), + [TCA_DUALPI2_TARGET] = { .type = NLA_U32 }, + [TCA_DUALPI2_TUPDATE] = NLA_POLICY_MIN(NLA_U32, 1), + [TCA_DUALPI2_ALPHA] = + NLA_POLICY_FULL_RANGE(NLA_U32, &dualpi2_alpha_beta_range), + [TCA_DUALPI2_BETA] = + NLA_POLICY_FULL_RANGE(NLA_U32, &dualpi2_alpha_beta_range), + [TCA_DUALPI2_STEP_THRESH_PKTS] = { .type = NLA_U32 }, + [TCA_DUALPI2_STEP_THRESH_US] = { .type = NLA_U32 }, + [TCA_DUALPI2_MIN_QLEN_STEP] = { .type = NLA_U32 }, + [TCA_DUALPI2_COUPLING] = NLA_POLICY_MIN(NLA_U8, 1), + [TCA_DUALPI2_DROP_OVERLOAD] = + NLA_POLICY_MAX(NLA_U8, TCA_DUALPI2_DROP_OVERLOAD_MAX), + [TCA_DUALPI2_DROP_EARLY] = + NLA_POLICY_MAX(NLA_U8, TCA_DUALPI2_DROP_EARLY_MAX), + [TCA_DUALPI2_C_PROTECTION] = + NLA_POLICY_RANGE(NLA_U8, 0, MAX_WC), + [TCA_DUALPI2_ECN_MASK] = + NLA_POLICY_RANGE(NLA_U8, TC_DUALPI2_ECN_MASK_L4S_ECT, + TCA_DUALPI2_ECN_MASK_MAX), + [TCA_DUALPI2_SPLIT_GSO] = + NLA_POLICY_MAX(NLA_U8, TCA_DUALPI2_SPLIT_GSO_MAX), +}; + +static int dualpi2_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_DUALPI2_MAX + 1]; + struct dualpi2_sched_data *q; + int old_backlog; + int old_qlen; + int err; + + if (!opt || !nla_len(opt)) { + NL_SET_ERR_MSG_MOD(extack, "Dualpi2 options are required"); + return -EINVAL; + } + err = nla_parse_nested(tb, TCA_DUALPI2_MAX, opt, dualpi2_policy, + extack); + if (err < 0) + return err; + if (tb[TCA_DUALPI2_STEP_THRESH_PKTS] && tb[TCA_DUALPI2_STEP_THRESH_US]) { + NL_SET_ERR_MSG_MOD(extack, "multiple step thresh attributes"); + return -EINVAL; + } + + q = qdisc_priv(sch); + sch_tree_lock(sch); + + if (tb[TCA_DUALPI2_LIMIT]) { + u32 limit = nla_get_u32(tb[TCA_DUALPI2_LIMIT]); + + WRITE_ONCE(sch->limit, limit); + WRITE_ONCE(q->memory_limit, get_memory_limit(sch, limit)); + } + + if (tb[TCA_DUALPI2_MEMORY_LIMIT]) + WRITE_ONCE(q->memory_limit, + nla_get_u32(tb[TCA_DUALPI2_MEMORY_LIMIT])); + + if (tb[TCA_DUALPI2_TARGET]) { + u64 target = nla_get_u32(tb[TCA_DUALPI2_TARGET]); + + WRITE_ONCE(q->pi2_target, target * NSEC_PER_USEC); + } + + if (tb[TCA_DUALPI2_TUPDATE]) { + u64 tupdate = nla_get_u32(tb[TCA_DUALPI2_TUPDATE]); + + WRITE_ONCE(q->pi2_tupdate, convert_us_to_nsec(tupdate)); + } + + if (tb[TCA_DUALPI2_ALPHA]) { + u32 alpha = nla_get_u32(tb[TCA_DUALPI2_ALPHA]); + + WRITE_ONCE(q->pi2_alpha, dualpi2_scale_alpha_beta(alpha)); + } + + if (tb[TCA_DUALPI2_BETA]) { + u32 beta = nla_get_u32(tb[TCA_DUALPI2_BETA]); + + WRITE_ONCE(q->pi2_beta, dualpi2_scale_alpha_beta(beta)); + } + + if (tb[TCA_DUALPI2_STEP_THRESH_PKTS]) { + u32 step_th = nla_get_u32(tb[TCA_DUALPI2_STEP_THRESH_PKTS]); + + WRITE_ONCE(q->step_in_packets, true); + WRITE_ONCE(q->step_thresh, step_th); + } else if (tb[TCA_DUALPI2_STEP_THRESH_US]) { + u32 step_th = nla_get_u32(tb[TCA_DUALPI2_STEP_THRESH_US]); + + WRITE_ONCE(q->step_in_packets, false); + WRITE_ONCE(q->step_thresh, convert_us_to_nsec(step_th)); + } + + if (tb[TCA_DUALPI2_MIN_QLEN_STEP]) + WRITE_ONCE(q->min_qlen_step, + nla_get_u32(tb[TCA_DUALPI2_MIN_QLEN_STEP])); + + if (tb[TCA_DUALPI2_COUPLING]) { + u8 coupling = nla_get_u8(tb[TCA_DUALPI2_COUPLING]); + + WRITE_ONCE(q->coupling_factor, coupling); + } + + if (tb[TCA_DUALPI2_DROP_OVERLOAD]) { + u8 drop_overload = nla_get_u8(tb[TCA_DUALPI2_DROP_OVERLOAD]); + + WRITE_ONCE(q->drop_overload, (bool)drop_overload); + } + + if (tb[TCA_DUALPI2_DROP_EARLY]) { + u8 drop_early = nla_get_u8(tb[TCA_DUALPI2_DROP_EARLY]); + + WRITE_ONCE(q->drop_early, (bool)drop_early); + } + + if (tb[TCA_DUALPI2_C_PROTECTION]) { + u8 wc = nla_get_u8(tb[TCA_DUALPI2_C_PROTECTION]); + + dualpi2_calculate_c_protection(sch, q, wc); + } + + if (tb[TCA_DUALPI2_ECN_MASK]) { + u8 ecn_mask = nla_get_u8(tb[TCA_DUALPI2_ECN_MASK]); + + WRITE_ONCE(q->ecn_mask, ecn_mask); + } + + if (tb[TCA_DUALPI2_SPLIT_GSO]) { + u8 split_gso = nla_get_u8(tb[TCA_DUALPI2_SPLIT_GSO]); + + WRITE_ONCE(q->split_gso, (bool)split_gso); + } + + old_qlen = qdisc_qlen(sch); + old_backlog = sch->qstats.backlog; + while (qdisc_qlen(sch) > sch->limit || + q->memory_used > q->memory_limit) { + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); + + q->memory_used -= skb->truesize; + qdisc_qstats_backlog_dec(sch, skb); + rtnl_qdisc_drop(skb, sch); + } + qdisc_tree_reduce_backlog(sch, old_qlen - qdisc_qlen(sch), + old_backlog - sch->qstats.backlog); + + sch_tree_unlock(sch); + return 0; +} + +/* Default alpha/beta values give a 10dB stability margin with max_rtt=100ms. */ +static void dualpi2_reset_default(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + q->sch->limit = 10000; /* Max 125ms at 1Gbps */ + q->memory_limit = get_memory_limit(sch, q->sch->limit); + + q->pi2_target = 15 * NSEC_PER_MSEC; + q->pi2_tupdate = 16 * NSEC_PER_MSEC; + q->pi2_alpha = dualpi2_scale_alpha_beta(41); /* ~0.16 Hz * 256 */ + q->pi2_beta = dualpi2_scale_alpha_beta(819); /* ~3.20 Hz * 256 */ + + q->step_thresh = 1 * NSEC_PER_MSEC; + q->step_in_packets = false; + + dualpi2_calculate_c_protection(q->sch, q, 10); /* wc=10%, wl=90% */ + + q->ecn_mask = TC_DUALPI2_ECN_MASK_L4S_ECT; /* INET_ECN_ECT_1 */ + q->min_qlen_step = 0; /* Always apply step mark in L-queue */ + q->coupling_factor = 2; /* window fairness for equal RTTs */ + q->drop_overload = TC_DUALPI2_DROP_OVERLOAD_DROP; /* Drop overload */ + q->drop_early = TC_DUALPI2_DROP_EARLY_DROP_DEQUEUE; /* Drop dequeue */ + q->split_gso = TC_DUALPI2_SPLIT_GSO_SPLIT_GSO; /* Split GSO */ +} + +static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + int err; + + q->l_queue = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, 1), extack); + if (!q->l_queue) + return -ENOMEM; + + err = tcf_block_get(&q->tcf_block, &q->tcf_filters, sch, extack); + if (err) + return err; + + q->sch = sch; + dualpi2_reset_default(sch); + hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); + + if (opt && nla_len(opt)) { + err = dualpi2_change(sch, opt, extack); + + if (err) + return err; + } + + hrtimer_start(&q->pi2_timer, next_pi2_timeout(q), + HRTIMER_MODE_ABS_PINNED_SOFT); + return 0; +} + +static int dualpi2_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + bool step_in_pkts; + u32 step_th; + + step_in_pkts = READ_ONCE(q->step_in_packets); + step_th = READ_ONCE(q->step_thresh); + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_put_failure; + + if (step_in_pkts && + (nla_put_u32(skb, TCA_DUALPI2_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_DUALPI2_MEMORY_LIMIT, + READ_ONCE(q->memory_limit)) || + nla_put_u32(skb, TCA_DUALPI2_TARGET, + convert_ns_to_usec(READ_ONCE(q->pi2_target))) || + nla_put_u32(skb, TCA_DUALPI2_TUPDATE, + convert_ns_to_usec(READ_ONCE(q->pi2_tupdate))) || + nla_put_u32(skb, TCA_DUALPI2_ALPHA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_alpha))) || + nla_put_u32(skb, TCA_DUALPI2_BETA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_beta))) || + nla_put_u32(skb, TCA_DUALPI2_STEP_THRESH_PKTS, step_th) || + nla_put_u32(skb, TCA_DUALPI2_MIN_QLEN_STEP, + READ_ONCE(q->min_qlen_step)) || + nla_put_u8(skb, TCA_DUALPI2_COUPLING, + READ_ONCE(q->coupling_factor)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_OVERLOAD, + READ_ONCE(q->drop_overload)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_EARLY, + READ_ONCE(q->drop_early)) || + nla_put_u8(skb, TCA_DUALPI2_C_PROTECTION, + READ_ONCE(q->c_protection_wc)) || + nla_put_u8(skb, TCA_DUALPI2_ECN_MASK, READ_ONCE(q->ecn_mask)) || + nla_put_u8(skb, TCA_DUALPI2_SPLIT_GSO, READ_ONCE(q->split_gso)))) + goto nla_put_failure; + + if (!step_in_pkts && + (nla_put_u32(skb, TCA_DUALPI2_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_DUALPI2_MEMORY_LIMIT, + READ_ONCE(q->memory_limit)) || + nla_put_u32(skb, TCA_DUALPI2_TARGET, + convert_ns_to_usec(READ_ONCE(q->pi2_target))) || + nla_put_u32(skb, TCA_DUALPI2_TUPDATE, + convert_ns_to_usec(READ_ONCE(q->pi2_tupdate))) || + nla_put_u32(skb, TCA_DUALPI2_ALPHA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_alpha))) || + nla_put_u32(skb, TCA_DUALPI2_BETA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_beta))) || + nla_put_u32(skb, TCA_DUALPI2_STEP_THRESH_US, + convert_ns_to_usec(step_th)) || + nla_put_u32(skb, TCA_DUALPI2_MIN_QLEN_STEP, + READ_ONCE(q->min_qlen_step)) || + nla_put_u8(skb, TCA_DUALPI2_COUPLING, + READ_ONCE(q->coupling_factor)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_OVERLOAD, + READ_ONCE(q->drop_overload)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_EARLY, + READ_ONCE(q->drop_early)) || + nla_put_u8(skb, TCA_DUALPI2_C_PROTECTION, + READ_ONCE(q->c_protection_wc)) || + nla_put_u8(skb, TCA_DUALPI2_ECN_MASK, READ_ONCE(q->ecn_mask)) || + nla_put_u8(skb, TCA_DUALPI2_SPLIT_GSO, READ_ONCE(q->split_gso)))) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -1; +} + +static int dualpi2_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct tc_dualpi2_xstats st = { + .prob = READ_ONCE(q->pi2_prob), + .packets_in_c = q->packets_in_c, + .packets_in_l = q->packets_in_l, + .maxq = q->maxq, + .ecn_mark = q->ecn_mark, + .credit = q->c_protection_credit, + .step_marks = q->step_marks, + .memory_used = q->memory_used, + .max_memory_used = q->max_memory_used, + .memory_limit = q->memory_limit, + }; + u64 qc, ql; + + get_queue_delays(q, &qc, &ql); + st.delay_l = convert_ns_to_usec(ql); + st.delay_c = convert_ns_to_usec(qc); + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +/* Reset both L-queue and C-queue, internal packet counters, PI probability, + * C-queue protection credit, and timestamps, while preserving current + * configuration of DUALPI2. + */ +static void dualpi2_reset(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + qdisc_reset_queue(sch); + qdisc_reset_queue(q->l_queue); + q->c_head_ts = 0; + q->l_head_ts = 0; + q->pi2_prob = 0; + q->packets_in_c = 0; + q->packets_in_l = 0; + q->maxq = 0; + q->ecn_mark = 0; + q->step_marks = 0; + q->memory_used = 0; + q->max_memory_used = 0; + dualpi2_reset_c_protection(q); +} + +static void dualpi2_destroy(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + q->pi2_tupdate = 0; + hrtimer_cancel(&q->pi2_timer); + if (q->l_queue) + qdisc_put(q->l_queue); + tcf_block_put(q->tcf_block); +} + +static struct Qdisc *dualpi2_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long dualpi2_find(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static unsigned long dualpi2_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + +static void dualpi2_unbind(struct Qdisc *q, unsigned long cl) +{ +} + +static struct tcf_block *dualpi2_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return q->tcf_block; +} + +static void dualpi2_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + unsigned int i; + + if (arg->stop) + return; + + /* We statically define only 2 queues */ + for (i = 0; i < 2; i++) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +/* Minimal class support to handle tc filters */ +static const struct Qdisc_class_ops dualpi2_class_ops = { + .leaf = dualpi2_leaf, + .find = dualpi2_find, + .tcf_block = dualpi2_tcf_block, + .bind_tcf = dualpi2_bind, + .unbind_tcf = dualpi2_unbind, + .walk = dualpi2_walk, +}; + +static struct Qdisc_ops dualpi2_qdisc_ops __read_mostly = { + .id = "dualpi2", + .cl_ops = &dualpi2_class_ops, + .priv_size = sizeof(struct dualpi2_sched_data), + .enqueue = dualpi2_qdisc_enqueue, + .dequeue = dualpi2_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = dualpi2_init, + .destroy = dualpi2_destroy, + .reset = dualpi2_reset, + .change = dualpi2_change, + .dump = dualpi2_dump, + .dump_stats = dualpi2_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init dualpi2_module_init(void) +{ + return register_qdisc(&dualpi2_qdisc_ops); +} + +static void __exit dualpi2_module_exit(void) +{ + unregister_qdisc(&dualpi2_qdisc_ops); +} + +module_init(dualpi2_module_init); +module_exit(dualpi2_module_exit); + +MODULE_DESCRIPTION("Dual Queue with Proportional Integral controller Improved with a Square (dualpi2) scheduler"); +MODULE_AUTHOR("Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>"); +MODULE_AUTHOR("Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>"); +MODULE_AUTHOR("Olga Albisser <olga@albisser.org>"); +MODULE_AUTHOR("Henrik Steen <henrist@henrist.net>"); +MODULE_AUTHOR("Olivier Tilmans <olivier.tilmans@nokia.com>"); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_VERSION("1.0"); diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c new file mode 100644 index 000000000000..c74d778c32a1 --- /dev/null +++ b/net/sched/sch_etf.c @@ -0,0 +1,517 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* net/sched/sch_etf.c Earliest TxTime First queueing discipline. + * + * Authors: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com> + * Vinicius Costa Gomes <vinicius.gomes@intel.com> + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/errqueue.h> +#include <linux/rbtree.h> +#include <linux/skbuff.h> +#include <linux/posix-timers.h> +#include <net/netlink.h> +#include <net/sch_generic.h> +#include <net/pkt_sched.h> +#include <net/sock.h> + +#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON) +#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON) +#define SKIP_SOCK_CHECK_IS_SET(x) ((x)->flags & TC_ETF_SKIP_SOCK_CHECK) + +struct etf_sched_data { + bool offload; + bool deadline_mode; + bool skip_sock_check; + int clockid; + int queue; + s32 delta; /* in ns */ + ktime_t last; /* The txtime of the last skb sent to the netdevice. */ + struct rb_root_cached head; + struct qdisc_watchdog watchdog; + ktime_t (*get_time)(void); +}; + +static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = { + [TCA_ETF_PARMS] = { .len = sizeof(struct tc_etf_qopt) }, +}; + +static inline int validate_input_params(struct tc_etf_qopt *qopt, + struct netlink_ext_ack *extack) +{ + /* Check if params comply to the following rules: + * * Clockid and delta must be valid. + * + * * Dynamic clockids are not supported. + * + * * Delta must be a positive integer. + * + * Also note that for the HW offload case, we must + * expect that system clocks have been synchronized to PHC. + */ + if (qopt->clockid < 0) { + NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported"); + return -ENOTSUPP; + } + + if (qopt->clockid != CLOCK_TAI) { + NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used"); + return -EINVAL; + } + + if (qopt->delta < 0) { + NL_SET_ERR_MSG(extack, "Delta must be positive"); + return -EINVAL; + } + + return 0; +} + +static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb) +{ + struct etf_sched_data *q = qdisc_priv(sch); + ktime_t txtime = nskb->tstamp; + struct sock *sk = nskb->sk; + ktime_t now; + + if (q->skip_sock_check) + goto skip; + + if (!sk || !sk_fullsock(sk)) + return false; + + if (!sock_flag(sk, SOCK_TXTIME)) + return false; + + /* We don't perform crosstimestamping. + * Drop if packet's clockid differs from qdisc's. + */ + if (sk->sk_clockid != q->clockid) + return false; + + if (sk->sk_txtime_deadline_mode != q->deadline_mode) + return false; + +skip: + now = q->get_time(); + if (ktime_before(txtime, now) || ktime_before(txtime, q->last)) + return false; + + return true; +} + +static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct rb_node *p; + + p = rb_first_cached(&q->head); + if (!p) + return NULL; + + return rb_to_skb(p); +} + +static void reset_watchdog(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = etf_peek_timesortedlist(sch); + ktime_t next; + + if (!skb) { + qdisc_watchdog_cancel(&q->watchdog); + return; + } + + next = ktime_sub_ns(skb->tstamp, q->delta); + qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); +} + +static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) +{ + struct sock_exterr_skb *serr; + struct sk_buff *clone; + ktime_t txtime = skb->tstamp; + struct sock *sk = skb->sk; + + if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors)) + return; + + clone = skb_clone(skb, GFP_ATOMIC); + if (!clone) + return; + + serr = SKB_EXT_ERR(clone); + serr->ee.ee_errno = err; + serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME; + serr->ee.ee_type = 0; + serr->ee.ee_code = code; + serr->ee.ee_pad = 0; + serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */ + serr->ee.ee_info = txtime; /* low part of tstamp */ + + if (sock_queue_err_skb(sk, clone)) + kfree_skb(clone); +} + +static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL; + ktime_t txtime = nskb->tstamp; + bool leftmost = true; + + if (!is_packet_valid(sch, nskb)) { + report_sock_error(nskb, EINVAL, + SO_EE_CODE_TXTIME_INVALID_PARAM); + return qdisc_drop(nskb, sch, to_free); + } + + while (*p) { + struct sk_buff *skb; + + parent = *p; + skb = rb_to_skb(parent); + if (ktime_compare(txtime, skb->tstamp) >= 0) { + p = &parent->rb_right; + leftmost = false; + } else { + p = &parent->rb_left; + } + } + rb_link_node(&nskb->rbnode, parent, p); + rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost); + + qdisc_qstats_backlog_inc(sch, nskb); + sch->q.qlen++; + + /* Now we may need to re-arm the qdisc watchdog for the next packet. */ + reset_watchdog(sch); + + return NET_XMIT_SUCCESS; +} + +static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb, + ktime_t now) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct sk_buff *to_free = NULL; + struct sk_buff *tmp = NULL; + + skb_rbtree_walk_from_safe(skb, tmp) { + if (ktime_after(skb->tstamp, now)) + break; + + rb_erase_cached(&skb->rbnode, &q->head); + + /* The rbnode field in the skb re-uses these fields, now that + * we are done with the rbnode, reset them. + */ + skb->next = NULL; + skb->prev = NULL; + skb->dev = qdisc_dev(sch); + + report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED); + + qdisc_qstats_backlog_dec(sch, skb); + qdisc_drop(skb, sch, &to_free); + qdisc_qstats_overlimit(sch); + sch->q.qlen--; + } + + kfree_skb_list(to_free); +} + +static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb) +{ + struct etf_sched_data *q = qdisc_priv(sch); + + rb_erase_cached(&skb->rbnode, &q->head); + + /* The rbnode field in the skb re-uses these fields, now that + * we are done with the rbnode, reset them. + */ + skb->next = NULL; + skb->prev = NULL; + skb->dev = qdisc_dev(sch); + + qdisc_qstats_backlog_dec(sch, skb); + + qdisc_bstats_update(sch, skb); + + q->last = skb->tstamp; + + sch->q.qlen--; +} + +static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + ktime_t now, next; + + skb = etf_peek_timesortedlist(sch); + if (!skb) + return NULL; + + now = q->get_time(); + + /* Drop if packet has expired while in queue. */ + if (ktime_before(skb->tstamp, now)) { + timesortedlist_drop(sch, skb, now); + skb = NULL; + goto out; + } + + /* When in deadline mode, dequeue as soon as possible and change the + * txtime from deadline to (now + delta). + */ + if (q->deadline_mode) { + timesortedlist_remove(sch, skb); + skb->tstamp = now; + goto out; + } + + next = ktime_sub_ns(skb->tstamp, q->delta); + + /* Dequeue only if now is within the [txtime - delta, txtime] range. */ + if (ktime_after(now, next)) + timesortedlist_remove(sch, skb); + else + skb = NULL; + +out: + /* Now we may need to re-arm the qdisc watchdog for the next packet. */ + reset_watchdog(sch); + + return skb; +} + +static void etf_disable_offload(struct net_device *dev, + struct etf_sched_data *q) +{ + struct tc_etf_qopt_offload etf = { }; + const struct net_device_ops *ops; + int err; + + if (!q->offload) + return; + + ops = dev->netdev_ops; + if (!ops->ndo_setup_tc) + return; + + etf.queue = q->queue; + etf.enable = 0; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); + if (err < 0) + pr_warn("Couldn't disable ETF offload for queue %d\n", + etf.queue); +} + +static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_etf_qopt_offload etf = { }; + int err; + + if (!ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload"); + return -EOPNOTSUPP; + } + + etf.queue = q->queue; + etf.enable = 1; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload"); + return err; + } + + return 0; +} + +static int etf_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct nlattr *tb[TCA_ETF_MAX + 1]; + struct tc_etf_qopt *qopt; + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, + "Missing ETF qdisc options which are mandatory"); + return -EINVAL; + } + + err = nla_parse_nested_deprecated(tb, TCA_ETF_MAX, opt, etf_policy, + extack); + if (err < 0) + return err; + + if (!tb[TCA_ETF_PARMS]) { + NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters"); + return -EINVAL; + } + + qopt = nla_data(tb[TCA_ETF_PARMS]); + + pr_debug("delta %d clockid %d offload %s deadline %s\n", + qopt->delta, qopt->clockid, + OFFLOAD_IS_ON(qopt) ? "on" : "off", + DEADLINE_MODE_IS_ON(qopt) ? "on" : "off"); + + err = validate_input_params(qopt, extack); + if (err < 0) + return err; + + q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); + + if (OFFLOAD_IS_ON(qopt)) { + err = etf_enable_offload(dev, q, extack); + if (err < 0) + return err; + } + + /* Everything went OK, save the parameters used. */ + q->delta = qopt->delta; + q->clockid = qopt->clockid; + q->offload = OFFLOAD_IS_ON(qopt); + q->deadline_mode = DEADLINE_MODE_IS_ON(qopt); + q->skip_sock_check = SKIP_SOCK_CHECK_IS_SET(qopt); + + switch (q->clockid) { + case CLOCK_REALTIME: + q->get_time = ktime_get_real; + break; + case CLOCK_MONOTONIC: + q->get_time = ktime_get; + break; + case CLOCK_BOOTTIME: + q->get_time = ktime_get_boottime; + break; + case CLOCK_TAI: + q->get_time = ktime_get_clocktai; + break; + default: + NL_SET_ERR_MSG(extack, "Clockid is not supported"); + return -ENOTSUPP; + } + + qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid); + + return 0; +} + +static void timesortedlist_clear(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct rb_node *p = rb_first_cached(&q->head); + + while (p) { + struct sk_buff *skb = rb_to_skb(p); + + p = rb_next(p); + + rb_erase_cached(&skb->rbnode, &q->head); + rtnl_kfree_skbs(skb, skb); + sch->q.qlen--; + } +} + +static void etf_reset(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + + /* Only cancel watchdog if it's been initialized. */ + if (q->watchdog.qdisc == sch) + qdisc_watchdog_cancel(&q->watchdog); + + /* No matter which mode we are on, it's safe to clear both lists. */ + timesortedlist_clear(sch); + __qdisc_reset_queue(&sch->q); + + q->last = 0; +} + +static void etf_destroy(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + /* Only cancel watchdog if it's been initialized. */ + if (q->watchdog.qdisc == sch) + qdisc_watchdog_cancel(&q->watchdog); + + etf_disable_offload(dev, q); +} + +static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct tc_etf_qopt opt = { }; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + opt.delta = READ_ONCE(q->delta); + opt.clockid = READ_ONCE(q->clockid); + if (READ_ONCE(q->offload)) + opt.flags |= TC_ETF_OFFLOAD_ON; + + if (READ_ONCE(q->deadline_mode)) + opt.flags |= TC_ETF_DEADLINE_MODE_ON; + + if (READ_ONCE(q->skip_sock_check)) + opt.flags |= TC_ETF_SKIP_SOCK_CHECK; + + if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc_ops etf_qdisc_ops __read_mostly = { + .id = "etf", + .priv_size = sizeof(struct etf_sched_data), + .enqueue = etf_enqueue_timesortedlist, + .dequeue = etf_dequeue_timesortedlist, + .peek = etf_peek_timesortedlist, + .init = etf_init, + .reset = etf_reset, + .destroy = etf_destroy, + .dump = etf_dump, + .owner = THIS_MODULE, +}; +MODULE_ALIAS_NET_SCH("etf"); + +static int __init etf_module_init(void) +{ + return register_qdisc(&etf_qdisc_ops); +} + +static void __exit etf_module_exit(void) +{ + unregister_qdisc(&etf_qdisc_ops); +} +module_init(etf_module_init) +module_exit(etf_module_exit) +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Earliest TxTime First (ETF) qdisc"); diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c new file mode 100644 index 000000000000..82635dd2cfa5 --- /dev/null +++ b/net/sched/sch_ets.c @@ -0,0 +1,839 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * net/sched/sch_ets.c Enhanced Transmission Selection scheduler + * + * Description + * ----------- + * + * The Enhanced Transmission Selection scheduler is a classful queuing + * discipline that merges functionality of PRIO and DRR qdiscs in one scheduler. + * ETS makes it easy to configure a set of strict and bandwidth-sharing bands to + * implement the transmission selection described in 802.1Qaz. + * + * Although ETS is technically classful, it's not possible to add and remove + * classes at will. Instead one specifies number of classes, how many are + * PRIO-like and how many DRR-like, and quanta for the latter. + * + * Algorithm + * --------- + * + * The strict classes, if any, are tried for traffic first: first band 0, if it + * has no traffic then band 1, etc. + * + * When there is no traffic in any of the strict queues, the bandwidth-sharing + * ones are tried next. Each band is assigned a deficit counter, initialized to + * "quantum" of that band. ETS maintains a list of active bandwidth-sharing + * bands whose qdiscs are non-empty. A packet is dequeued from the band at the + * head of the list if the packet size is smaller or equal to the deficit + * counter. If the counter is too small, it is increased by "quantum" and the + * scheduler moves on to the next band in the active list. + */ + +#include <linux/module.h> +#include <net/gen_stats.h> +#include <net/netlink.h> +#include <net/pkt_cls.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> + +struct ets_class { + struct list_head alist; /* In struct ets_sched.active. */ + struct Qdisc *qdisc; + u32 quantum; + u32 deficit; + struct gnet_stats_basic_sync bstats; + struct gnet_stats_queue qstats; +}; + +struct ets_sched { + struct list_head active; + struct tcf_proto __rcu *filter_list; + struct tcf_block *block; + unsigned int nbands; + unsigned int nstrict; + u8 prio2band[TC_PRIO_MAX + 1]; + struct ets_class classes[TCQ_ETS_MAX_BANDS]; +}; + +static const struct nla_policy ets_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_NBANDS] = { .type = NLA_U8 }, + [TCA_ETS_NSTRICT] = { .type = NLA_U8 }, + [TCA_ETS_QUANTA] = { .type = NLA_NESTED }, + [TCA_ETS_PRIOMAP] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ets_priomap_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_PRIOMAP_BAND] = { .type = NLA_U8 }, +}; + +static const struct nla_policy ets_quanta_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static bool cl_is_active(struct ets_class *cl) +{ + return !list_empty(&cl->alist); +} + +static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, + unsigned int *quantum, + struct netlink_ext_ack *extack) +{ + *quantum = nla_get_u32(attr); + if (!*quantum) { + NL_SET_ERR_MSG(extack, "ETS quantum cannot be zero"); + return -EINVAL; + } + return 0; +} + +static struct ets_class * +ets_class_from_arg(struct Qdisc *sch, unsigned long arg) +{ + struct ets_sched *q = qdisc_priv(sch); + + if (arg == 0 || arg > q->nbands) + return NULL; + return &q->classes[arg - 1]; +} + +static u32 ets_class_id(struct Qdisc *sch, const struct ets_class *cl) +{ + struct ets_sched *q = qdisc_priv(sch); + int band = cl - q->classes; + + return TC_H_MAKE(sch->handle, band + 1); +} + +static void ets_offload_change(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct ets_sched *q = qdisc_priv(sch); + struct tc_ets_qopt_offload qopt; + unsigned int w_psum_prev = 0; + unsigned int q_psum = 0; + unsigned int q_sum = 0; + unsigned int quantum; + unsigned int w_psum; + unsigned int weight; + unsigned int i; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.replace_params.bands = q->nbands; + qopt.replace_params.qstats = &sch->qstats; + memcpy(&qopt.replace_params.priomap, + q->prio2band, sizeof(q->prio2band)); + + for (i = 0; i < q->nbands; i++) + q_sum += q->classes[i].quantum; + + for (i = 0; i < q->nbands; i++) { + quantum = q->classes[i].quantum; + q_psum += quantum; + w_psum = quantum ? q_psum * 100 / q_sum : 0; + weight = w_psum - w_psum_prev; + w_psum_prev = w_psum; + + qopt.replace_params.quanta[i] = quantum; + qopt.replace_params.weights[i] = weight; + } + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_graft(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc *old, unsigned long arg, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_GRAFT; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.graft_params.band = arg - 1; + qopt.graft_params.child_handle = new->handle; + + qdisc_offload_graft_helper(dev, sch, new, old, TC_SETUP_QDISC_ETS, + &qopt, extack); +} + +static int ets_offload_dump(struct Qdisc *sch) +{ + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_ETS, &qopt); +} + +static bool ets_class_is_strict(struct ets_sched *q, const struct ets_class *cl) +{ + unsigned int band = cl - q->classes; + + return band < q->nstrict; +} + +static int ets_class_change(struct Qdisc *sch, u32 classid, u32 parentid, + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, *arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opt = tca[TCA_OPTIONS]; + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int quantum; + int err; + + /* Classes can be added and removed only through Qdisc_ops.change + * interface. + */ + if (!cl) { + NL_SET_ERR_MSG(extack, "Fine-grained class addition and removal is not supported"); + return -EOPNOTSUPP; + } + + if (!opt) { + NL_SET_ERR_MSG(extack, "ETS options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_class_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_QUANTA_BAND]) + /* Nothing to configure. */ + return 0; + + if (ets_class_is_strict(q, cl)) { + NL_SET_ERR_MSG(extack, "Strict bands do not have a configurable quantum"); + return -EINVAL; + } + + err = ets_quantum_parse(sch, tb[TCA_ETS_QUANTA_BAND], &quantum, + extack); + if (err) + return err; + + sch_tree_lock(sch); + cl->quantum = quantum; + sch_tree_unlock(sch); + + ets_offload_change(sch); + return 0; +} + +static int ets_class_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, cl), NULL); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } + + *old = qdisc_replace(sch, new, &cl->qdisc); + ets_offload_graft(sch, new, *old, arg, extack); + return 0; +} + +static struct Qdisc *ets_class_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + return cl->qdisc; +} + +static unsigned long ets_class_find(struct Qdisc *sch, u32 classid) +{ + unsigned long band = TC_H_MIN(classid); + struct ets_sched *q = qdisc_priv(sch); + + if (band - 1 >= q->nbands) + return 0; + return band; +} + +static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + + /* We get notified about zero-length child Qdiscs as well if they are + * offloaded. Those aren't on the active list though, so don't attempt + * to remove them. + */ + if (!ets_class_is_strict(q, cl) && sch->q.qlen) + list_del_init(&cl->alist); +} + +static int ets_class_dump(struct Qdisc *sch, unsigned long arg, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *nest; + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle = ets_class_id(sch, cl); + tcm->tcm_info = cl->qdisc->handle; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + if (!ets_class_is_strict(q, cl)) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, cl->quantum)) + goto nla_put_failure; + } + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int ets_class_dump_stats(struct Qdisc *sch, unsigned long arg, + struct gnet_dump *d) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct Qdisc *cl_q = cl->qdisc; + + if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats, true) < 0 || + qdisc_qstats_copy(d, cl_q) < 0) + return -1; + + return 0; +} + +static void ets_qdisc_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct ets_sched *q = qdisc_priv(sch); + int i; + + if (arg->stop) + return; + + for (i = 0; i < q->nbands; i++) { + if (!tc_qdisc_stats_dump(sch, i + 1, arg)) + break; + } +} + +static struct tcf_block * +ets_qdisc_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + + if (cl) { + NL_SET_ERR_MSG(extack, "ETS classid must be zero"); + return NULL; + } + + return q->block; +} + +static unsigned long ets_qdisc_bind_tcf(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return ets_class_find(sch, classid); +} + +static void ets_qdisc_unbind_tcf(struct Qdisc *sch, unsigned long arg) +{ +} + +static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct ets_sched *q = qdisc_priv(sch); + u32 band = skb->priority; + struct tcf_result res; + struct tcf_proto *fl; + int err; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + if (TC_H_MAJ(skb->priority) != sch->handle) { + fl = rcu_dereference_bh(q->filter_list); + err = tcf_classify(skb, NULL, fl, &res, false); +#ifdef CONFIG_NET_CLS_ACT + switch (err) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; + case TC_ACT_SHOT: + return NULL; + } +#endif + if (!fl || err < 0) { + if (TC_H_MAJ(band)) + band = 0; + return &q->classes[q->prio2band[band & TC_PRIO_MAX]]; + } + band = res.classid; + } + band = TC_H_MIN(band) - 1; + if (band >= q->nbands) + return &q->classes[q->prio2band[0]]; + return &q->classes[band]; +} + +static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + unsigned int len = qdisc_pkt_len(skb); + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + int err = 0; + + cl = ets_classify(skb, sch, &err); + if (!cl) { + if (err & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return err; + } + + err = qdisc_enqueue(skb, cl->qdisc, to_free); + if (unlikely(err != NET_XMIT_SUCCESS)) { + if (net_xmit_drop_count(err)) { + cl->qstats.drops++; + qdisc_qstats_drop(sch); + } + return err; + } + + if (!cl_is_active(cl) && !ets_class_is_strict(q, cl)) { + list_add_tail(&cl->alist, &q->active); + cl->deficit = cl->quantum; + } + + sch->qstats.backlog += len; + sch->q.qlen++; + return err; +} + +static struct sk_buff * +ets_qdisc_dequeue_skb(struct Qdisc *sch, struct sk_buff *skb) +{ + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + return skb; +} + +static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + struct sk_buff *skb; + unsigned int band; + unsigned int len; + + while (1) { + for (band = 0; band < q->nstrict; band++) { + cl = &q->classes[band]; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (skb) + return ets_qdisc_dequeue_skb(sch, skb); + } + + if (list_empty(&q->active)) + goto out; + + cl = list_first_entry(&q->active, struct ets_class, alist); + skb = cl->qdisc->ops->peek(cl->qdisc); + if (!skb) { + qdisc_warn_nonwc(__func__, cl->qdisc); + goto out; + } + + len = qdisc_pkt_len(skb); + if (len <= cl->deficit) { + cl->deficit -= len; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (unlikely(!skb)) + goto out; + if (cl->qdisc->q.qlen == 0) + list_del_init(&cl->alist); + return ets_qdisc_dequeue_skb(sch, skb); + } + + cl->deficit += cl->quantum; + list_move_tail(&cl->alist, &q->active); + } +out: + return NULL; +} + +static int ets_qdisc_priomap_parse(struct nlattr *priomap_attr, + unsigned int nbands, u8 *priomap, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int prio = 0; + u8 band; + int rem; + int err; + + err = __nla_validate_nested(priomap_attr, TCA_ETS_MAX, + ets_priomap_policy, NL_VALIDATE_STRICT, + extack); + if (err) + return err; + + nla_for_each_nested(attr, priomap_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_PRIOMAP_BAND: + if (prio > TC_PRIO_MAX) { + NL_SET_ERR_MSG_MOD(extack, "Too many priorities in ETS priomap"); + return -EINVAL; + } + band = nla_get_u8(attr); + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid band number in ETS priomap"); + return -EINVAL; + } + priomap[prio++] = band; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_quanta_parse(struct Qdisc *sch, struct nlattr *quanta_attr, + unsigned int nbands, unsigned int nstrict, + unsigned int *quanta, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int band = nstrict; + int rem; + int err; + + err = __nla_validate_nested(quanta_attr, TCA_ETS_MAX, + ets_quanta_policy, NL_VALIDATE_STRICT, + extack); + if (err < 0) + return err; + + nla_for_each_nested(attr, quanta_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_QUANTA_BAND: + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "ETS quanta has more values than bands"); + return -EINVAL; + } + err = ets_quantum_parse(sch, attr, &quanta[band++], + extack); + if (err) + return err; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + unsigned int quanta[TCQ_ETS_MAX_BANDS] = {0}; + struct Qdisc *queues[TCQ_ETS_MAX_BANDS]; + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int oldbands = q->nbands; + u8 priomap[TC_PRIO_MAX + 1]; + unsigned int nstrict = 0; + unsigned int nbands; + unsigned int i; + int err; + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_NBANDS]) { + NL_SET_ERR_MSG_MOD(extack, "Number of bands is a required argument"); + return -EINVAL; + } + nbands = nla_get_u8(tb[TCA_ETS_NBANDS]); + if (nbands < 1 || nbands > TCQ_ETS_MAX_BANDS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of bands"); + return -EINVAL; + } + /* Unless overridden, traffic goes to the last band. */ + memset(priomap, nbands - 1, sizeof(priomap)); + + if (tb[TCA_ETS_NSTRICT]) { + nstrict = nla_get_u8(tb[TCA_ETS_NSTRICT]); + if (nstrict > nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of strict bands"); + return -EINVAL; + } + } + + if (tb[TCA_ETS_PRIOMAP]) { + err = ets_qdisc_priomap_parse(tb[TCA_ETS_PRIOMAP], + nbands, priomap, extack); + if (err) + return err; + } + + if (tb[TCA_ETS_QUANTA]) { + err = ets_qdisc_quanta_parse(sch, tb[TCA_ETS_QUANTA], + nbands, nstrict, quanta, extack); + if (err) + return err; + } + /* If there are more bands than strict + quanta provided, the remaining + * ones are ETS with quantum of MTU. Initialize the missing values here. + */ + for (i = nstrict; i < nbands; i++) { + if (!quanta[i]) + quanta[i] = psched_mtu(qdisc_dev(sch)); + } + + /* Before commit, make sure we can allocate all new qdiscs */ + for (i = oldbands; i < nbands; i++) { + queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, &q->classes[i]), + extack); + if (!queues[i]) { + while (i > oldbands) + qdisc_put(queues[--i]); + return -ENOMEM; + } + } + + sch_tree_lock(sch); + + for (i = nbands; i < oldbands; i++) { + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + list_del_init(&q->classes[i].alist); + qdisc_purge_queue(q->classes[i].qdisc); + } + + WRITE_ONCE(q->nbands, nbands); + for (i = nstrict; i < q->nstrict; i++) { + if (q->classes[i].qdisc->q.qlen) { + list_add_tail(&q->classes[i].alist, &q->active); + q->classes[i].deficit = quanta[i]; + } + } + WRITE_ONCE(q->nstrict, nstrict); + memcpy(q->prio2band, priomap, sizeof(priomap)); + + for (i = 0; i < q->nbands; i++) + WRITE_ONCE(q->classes[i].quantum, quanta[i]); + + for (i = oldbands; i < q->nbands; i++) { + q->classes[i].qdisc = queues[i]; + if (q->classes[i].qdisc != &noop_qdisc) + qdisc_hash_add(q->classes[i].qdisc, true); + } + + sch_tree_unlock(sch); + + ets_offload_change(sch); + for (i = q->nbands; i < oldbands; i++) { + qdisc_put(q->classes[i].qdisc); + q->classes[i].qdisc = NULL; + WRITE_ONCE(q->classes[i].quantum, 0); + q->classes[i].deficit = 0; + gnet_stats_basic_sync_init(&q->classes[i].bstats); + memset(&q->classes[i].qstats, 0, sizeof(q->classes[i].qstats)); + } + return 0; +} + +static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + int err, i; + + if (!opt) + return -EINVAL; + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + return err; + + INIT_LIST_HEAD(&q->active); + for (i = 0; i < TCQ_ETS_MAX_BANDS; i++) + INIT_LIST_HEAD(&q->classes[i].alist); + + return ets_qdisc_change(sch, opt, extack); +} + +static void ets_qdisc_reset(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + for (band = q->nstrict; band < q->nbands; band++) { + if (q->classes[band].qdisc->q.qlen) + list_del_init(&q->classes[band].alist); + } + for (band = 0; band < q->nbands; band++) + qdisc_reset(q->classes[band].qdisc); +} + +static void ets_qdisc_destroy(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + ets_offload_destroy(sch); + tcf_block_put(q->block); + for (band = 0; band < q->nbands; band++) + qdisc_put(q->classes[band].qdisc); +} + +static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opts; + struct nlattr *nest; + u8 nbands, nstrict; + int band; + int prio; + int err; + + err = ets_offload_dump(sch); + if (err) + return err; + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_err; + + nbands = READ_ONCE(q->nbands); + if (nla_put_u8(skb, TCA_ETS_NBANDS, nbands)) + goto nla_err; + + nstrict = READ_ONCE(q->nstrict); + if (nstrict && nla_put_u8(skb, TCA_ETS_NSTRICT, nstrict)) + goto nla_err; + + if (nbands > nstrict) { + nest = nla_nest_start(skb, TCA_ETS_QUANTA); + if (!nest) + goto nla_err; + + for (band = nstrict; band < nbands; band++) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, + READ_ONCE(q->classes[band].quantum))) + goto nla_err; + } + + nla_nest_end(skb, nest); + } + + nest = nla_nest_start(skb, TCA_ETS_PRIOMAP); + if (!nest) + goto nla_err; + + for (prio = 0; prio <= TC_PRIO_MAX; prio++) { + if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND, + READ_ONCE(q->prio2band[prio]))) + goto nla_err; + } + + nla_nest_end(skb, nest); + + return nla_nest_end(skb, opts); + +nla_err: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static const struct Qdisc_class_ops ets_class_ops = { + .change = ets_class_change, + .graft = ets_class_graft, + .leaf = ets_class_leaf, + .find = ets_class_find, + .qlen_notify = ets_class_qlen_notify, + .dump = ets_class_dump, + .dump_stats = ets_class_dump_stats, + .walk = ets_qdisc_walk, + .tcf_block = ets_qdisc_tcf_block, + .bind_tcf = ets_qdisc_bind_tcf, + .unbind_tcf = ets_qdisc_unbind_tcf, +}; + +static struct Qdisc_ops ets_qdisc_ops __read_mostly = { + .cl_ops = &ets_class_ops, + .id = "ets", + .priv_size = sizeof(struct ets_sched), + .enqueue = ets_qdisc_enqueue, + .dequeue = ets_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .change = ets_qdisc_change, + .init = ets_qdisc_init, + .reset = ets_qdisc_reset, + .destroy = ets_qdisc_destroy, + .dump = ets_qdisc_dump, + .owner = THIS_MODULE, +}; +MODULE_ALIAS_NET_SCH("ets"); + +static int __init ets_init(void) +{ + return register_qdisc(&ets_qdisc_ops); +} + +static void __exit ets_exit(void) +{ + unregister_qdisc(&ets_qdisc_ops); +} + +module_init(ets_init); +module_exit(ets_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Enhanced Transmission Selection(ETS) scheduler"); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 1e37247656f8..e6bfd39ff339 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_fifo.c The simplest FIFO queue. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ @@ -16,13 +12,15 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> /* 1 band FIFO pseudo-"scheduler" */ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) + if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= + READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); @@ -31,7 +29,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - if (likely(sch->q.qlen < sch->limit)) + if (likely(sch->q.qlen < READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); @@ -42,7 +40,10 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, { unsigned int prev_backlog; - if (likely(sch->q.qlen < sch->limit)) + if (unlikely(READ_ONCE(sch->limit) == 0)) + return qdisc_drop(skb, sch, to_free); + + if (likely(sch->q.qlen < READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); prev_backlog = sch->qstats.backlog; @@ -55,7 +56,49 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_CN; } -static int fifo_init(struct Qdisc *sch, struct nlattr *opt) +static void fifo_offload_init(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_fifo_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_FIFO_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt); +} + +static void fifo_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_fifo_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_FIFO_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt); +} + +static int fifo_offload_dump(struct Qdisc *sch) +{ + struct tc_fifo_qopt_offload qopt; + + qopt.command = TC_FIFO_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_FIFO, &qopt); +} + +static int __fifo_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { bool bypass; bool is_bfifo = sch->ops == &bfifo_qdisc_ops; @@ -66,14 +109,14 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt) if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); - sch->limit = limit; + WRITE_ONCE(sch->limit, limit); } else { struct tc_fifo_qopt *ctl = nla_data(opt); if (nla_len(opt) < sizeof(*ctl)) return -EINVAL; - sch->limit = ctl->limit; + WRITE_ONCE(sch->limit, ctl->limit); } if (is_bfifo) @@ -85,12 +128,37 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt) sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; + return 0; } -static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) +static int fifo_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { - struct tc_fifo_qopt opt = { .limit = sch->limit }; + int err; + + err = __fifo_init(sch, opt, extack); + if (err) + return err; + + fifo_offload_init(sch); + return 0; +} + +static int fifo_hd_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + return __fifo_init(sch, opt, extack); +} + +static void fifo_destroy(struct Qdisc *sch) +{ + fifo_offload_destroy(sch); +} + +static int __fifo_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct tc_fifo_qopt opt = { .limit = READ_ONCE(sch->limit) }; if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; @@ -100,6 +168,22 @@ nla_put_failure: return -1; } +static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + int err; + + err = fifo_offload_dump(sch); + if (err) + return err; + + return __fifo_dump(sch, skb); +} + +static int fifo_hd_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + return __fifo_dump(sch, skb); +} + struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .id = "pfifo", .priv_size = 0, @@ -107,6 +191,7 @@ struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, + .destroy = fifo_destroy, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, @@ -121,6 +206,7 @@ struct Qdisc_ops bfifo_qdisc_ops __read_mostly = { .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, + .destroy = fifo_destroy, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, @@ -134,10 +220,10 @@ struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = { .enqueue = pfifo_tail_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, - .init = fifo_init, + .init = fifo_hd_init, .reset = qdisc_reset_queue, - .change = fifo_init, - .dump = fifo_dump, + .change = fifo_hd_init, + .dump = fifo_hd_dump, .owner = THIS_MODULE, }; @@ -151,13 +237,16 @@ int fifo_set_limit(struct Qdisc *q, unsigned int limit) if (strncmp(q->ops->id + 1, "fifo", 4) != 0) return 0; + if (!q->ops->change) + return 0; + nla = kmalloc(nla_attr_size(sizeof(struct tc_fifo_qopt)), GFP_KERNEL); if (nla) { nla->nla_type = RTM_NEWQDISC; nla->nla_len = nla_attr_size(sizeof(struct tc_fifo_qopt)); ((struct tc_fifo_qopt *)nla_data(nla))->limit = limit; - ret = q->ops->change(q, nla); + ret = q->ops->change(q, nla, NULL); kfree(nla); } return ret; @@ -165,16 +254,18 @@ int fifo_set_limit(struct Qdisc *q, unsigned int limit) EXPORT_SYMBOL(fifo_set_limit); struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, - unsigned int limit) + unsigned int limit, + struct netlink_ext_ack *extack) { struct Qdisc *q; int err = -ENOMEM; - q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1)); + q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1), + extack); if (q) { err = fifo_set_limit(q, limit); if (err < 0) { - qdisc_destroy(q); + qdisc_put(q); q = NULL; } } @@ -182,3 +273,4 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, return q ? : ERR_PTR(err); } EXPORT_SYMBOL(fifo_create_dflt); +MODULE_DESCRIPTION("Single queue packet and byte based First In First Out(P/BFIFO) scheduler"); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 263d16e3219e..6e5f2f4f2415 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_fq.c Fair Queue Packet Scheduler (per flow pacing) * - * Copyright (C) 2013-2015 Eric Dumazet <edumazet@google.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. + * Copyright (C) 2013-2023 Eric Dumazet <edumazet@google.com> * * Meant to be mostly used for locally generated traffic : * Fast classification depends on skb->sk being set before reaching us. @@ -54,21 +50,45 @@ #include <net/tcp_states.h> #include <net/tcp.h> +struct fq_skb_cb { + u64 time_to_send; + u8 band; +}; + +static inline struct fq_skb_cb *fq_skb_cb(struct sk_buff *skb) +{ + qdisc_cb_private_validate(skb, sizeof(struct fq_skb_cb)); + return (struct fq_skb_cb *)qdisc_skb_cb(skb)->data; +} + /* - * Per flow structure, dynamically allocated + * Per flow structure, dynamically allocated. + * If packets have monotically increasing time_to_send, they are placed in O(1) + * in linear list (head,tail), otherwise are placed in a rbtree (t_root). */ struct fq_flow { +/* First cache line : used in fq_gc(), fq_enqueue(), fq_dequeue() */ + struct rb_root t_root; struct sk_buff *head; /* list of skbs for this flow : first skb */ union { struct sk_buff *tail; /* last skb in the list */ - unsigned long age; /* jiffies when flow was emptied, for gc */ + unsigned long age; /* (jiffies | 1UL) when flow was emptied, for gc */ + }; + union { + struct rb_node fq_node; /* anchor in fq_root[] trees */ + /* Following field is only used for q->internal, + * because q->internal is not hashed in fq_root[] + */ + u64 stat_fastpath_packets; }; - struct rb_node fq_node; /* anchor in fq_root[] trees */ struct sock *sk; + u32 socket_hash; /* sk_hash */ int qlen; /* number of packets in flow queue */ + +/* Second cache line */ int credit; - u32 socket_hash; /* sk_hash */ - struct fq_flow *next; /* next pointer in RR lists, or &detached */ + int band; + struct fq_flow *next; /* next pointer in RR lists */ struct rb_node rate_node; /* anchor in q->delayed tree */ u64 time_next_packet; @@ -79,53 +99,122 @@ struct fq_flow_head { struct fq_flow *last; }; -struct fq_sched_data { +struct fq_perband_flows { struct fq_flow_head new_flows; - struct fq_flow_head old_flows; + int credit; + int quantum; /* based on band nr : 576KB, 192KB, 64KB */ +}; - struct rb_root delayed; /* for rate limited flows */ - u64 time_next_delayed_flow; - unsigned long unthrottle_latency_ns; +#define FQ_PRIO2BAND_CRUMB_SIZE ((TC_PRIO_MAX + 1) >> 2) + +struct fq_sched_data { +/* Read mostly cache line */ - struct fq_flow internal; /* for non classified or high prio packets */ + u64 offload_horizon; u32 quantum; u32 initial_quantum; u32 flow_refill_delay; - u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ + unsigned long flow_max_rate; /* optional max rate per flow */ + u64 ce_threshold; + u64 horizon; /* horizon in ns */ u32 orphan_mask; /* mask for orphaned skb */ u32 low_rate_threshold; struct rb_root *fq_root; u8 rate_enable; u8 fq_trees_log; + u8 horizon_drop; + u8 prio2band[FQ_PRIO2BAND_CRUMB_SIZE]; + u32 timer_slack; /* hrtimer slack in ns */ +/* Read/Write fields. */ + + unsigned int band_nr; /* band being serviced in fq_dequeue() */ + + struct fq_perband_flows band_flows[FQ_BANDS]; + + struct fq_flow internal; /* fastpath queue. */ + struct rb_root delayed; /* for rate limited flows */ + u64 time_next_delayed_flow; + unsigned long unthrottle_latency_ns; + + u32 band_pkt_count[FQ_BANDS]; u32 flows; - u32 inactive_flows; + u32 inactive_flows; /* Flows with no packet to send. */ u32 throttled_flows; - u64 stat_gc_flows; - u64 stat_internal_packets; - u64 stat_tcp_retrans; u64 stat_throttled; + struct qdisc_watchdog watchdog; + u64 stat_gc_flows; + +/* Seldom used fields. */ + + u64 stat_band_drops[FQ_BANDS]; + u64 stat_ce_mark; + u64 stat_horizon_drops; + u64 stat_horizon_caps; u64 stat_flows_plimit; u64 stat_pkts_too_long; u64 stat_allocation_errors; - struct qdisc_watchdog watchdog; }; -/* special value to mark a detached flow (not on old/new list) */ -static struct fq_flow detached, throttled; +/* return the i-th 2-bit value ("crumb") */ +static u8 fq_prio2band(const u8 *prio2band, unsigned int prio) +{ + return (READ_ONCE(prio2band[prio / 4]) >> (2 * (prio & 0x3))) & 0x3; +} +/* + * f->tail and f->age share the same location. + * We can use the low order bit to differentiate if this location points + * to a sk_buff or contains a jiffies value, if we force this value to be odd. + * This assumes f->tail low order bit must be 0 since alignof(struct sk_buff) >= 2 + */ static void fq_flow_set_detached(struct fq_flow *f) { - f->next = &detached; - f->age = jiffies; + f->age = jiffies | 1UL; } static bool fq_flow_is_detached(const struct fq_flow *f) { - return f->next == &detached; + return !!(f->age & 1UL); +} + +/* special value to mark a throttled flow (not on old/new list) */ +static struct fq_flow throttled; + +static bool fq_flow_is_throttled(const struct fq_flow *f) +{ + return f->next == &throttled; +} + +enum new_flow { + NEW_FLOW, + OLD_FLOW +}; + +static void fq_flow_add_tail(struct fq_sched_data *q, struct fq_flow *flow, + enum new_flow list_sel) +{ + struct fq_perband_flows *pband = &q->band_flows[flow->band]; + struct fq_flow_head *head = (list_sel == NEW_FLOW) ? + &pband->new_flows : + &pband->old_flows; + + if (head->first) + head->last->next = flow; + else + head->first = flow; + head->last = flow; + flow->next = NULL; +} + +static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f) +{ + rb_erase(&f->rate_node, &q->delayed); + q->throttled_flows--; + fq_flow_add_tail(q, f, OLD_FLOW); } static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) @@ -155,15 +244,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) static struct kmem_cache *fq_flow_cachep __read_mostly; -static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) -{ - if (head->first) - head->last->next = flow; - else - head->first = flow; - head->last = flow; - flow->next = NULL; -} /* limit number of collected flows per round */ #define FQ_GC_MAX 8 @@ -179,9 +259,10 @@ static void fq_gc(struct fq_sched_data *q, struct rb_root *root, struct sock *sk) { - struct fq_flow *f, *tofree[FQ_GC_MAX]; struct rb_node **p, *parent; - int fcnt = 0; + void *tofree[FQ_GC_MAX]; + struct fq_flow *f; + int i, fcnt = 0; p = &root->rb_node; parent = NULL; @@ -204,28 +285,81 @@ static void fq_gc(struct fq_sched_data *q, p = &parent->rb_left; } + if (!fcnt) + return; + + for (i = fcnt; i > 0; ) { + f = tofree[--i]; + rb_erase(&f->fq_node, root); + } q->flows -= fcnt; q->inactive_flows -= fcnt; q->stat_gc_flows += fcnt; - while (fcnt) { - struct fq_flow *f = tofree[--fcnt]; - rb_erase(&f->fq_node, root); - kmem_cache_free(fq_flow_cachep, f); + kmem_cache_free_bulk(fq_flow_cachep, fcnt, tofree); +} + +/* Fast path can be used if : + * 1) Packet tstamp is in the past, or within the pacing offload horizon. + * 2) FQ qlen == 0 OR + * (no flow is currently eligible for transmit, + * AND fast path queue has less than 8 packets) + * 3) No SO_MAX_PACING_RATE on the socket (if any). + * 4) No @maxrate attribute on this qdisc, + * + * FQ can not use generic TCQ_F_CAN_BYPASS infrastructure. + */ +static bool fq_fastpath_check(const struct Qdisc *sch, struct sk_buff *skb, + u64 now) +{ + const struct fq_sched_data *q = qdisc_priv(sch); + const struct sock *sk; + + if (fq_skb_cb(skb)->time_to_send > now + q->offload_horizon) + return false; + + if (sch->q.qlen != 0) { + /* Even if some packets are stored in this qdisc, + * we can still enable fast path if all of them are + * scheduled in the future (ie no flows are eligible) + * or in the fast path queue. + */ + if (q->flows != q->inactive_flows + q->throttled_flows) + return false; + + /* Do not allow fast path queue to explode, we want Fair Queue mode + * under pressure. + */ + if (q->internal.qlen >= 8) + return false; + + /* Ordering invariants fall apart if some delayed flows + * are ready but we haven't serviced them, yet. + */ + if (q->time_next_delayed_flow <= now + q->offload_horizon) + return false; } + + sk = skb->sk; + if (sk && sk_fullsock(sk) && !sk_is_tcp(sk) && + sk->sk_max_pacing_rate != ~0UL) + return false; + + if (q->flow_max_rate != ~0UL) + return false; + + return true; } -static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) +static struct fq_flow *fq_classify(struct Qdisc *sch, struct sk_buff *skb, + u64 now) { + struct fq_sched_data *q = qdisc_priv(sch); struct rb_node **p, *parent; struct sock *sk = skb->sk; struct rb_root *root; struct fq_flow *f; - /* warning: no starvation prevention... */ - if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) - return &q->internal; - /* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket * or a listener (SYNCOOKIE mode) * 1) request sockets are not full blown, @@ -234,8 +368,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) * 3) We do not want to rate limit them (eg SYNFLOOD attack), * especially if the listener set SO_MAX_PACING_RATE * 4) We pretend they are orphaned + * TCP can also associate TIME_WAIT sockets with RST or ACK packets. */ - if (!sk || sk_listener(sk)) { + if (!sk || sk_listener_or_tw(sk)) { unsigned long hash = skb_get_hash(skb) & q->orphan_mask; /* By forcing low order bit to 1, we make sure to not @@ -243,13 +378,31 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) */ sk = (struct sock *)((hash << 1) | 1UL); skb_orphan(skb); + } else if (sk->sk_state == TCP_CLOSE) { + unsigned long hash = skb_get_hash(skb) & q->orphan_mask; + /* + * Sockets in TCP_CLOSE are non connected. + * Typical use case is UDP sockets, they can send packets + * with sendto() to many different destinations. + * We probably could use a generic bit advertising + * non connected sockets, instead of sk_state == TCP_CLOSE, + * if we care enough. + */ + sk = (struct sock *)((hash << 1) | 1UL); + } + + if (fq_fastpath_check(sch, skb, now)) { + q->internal.stat_fastpath_packets++; + if (skb->sk == sk && q->rate_enable && + READ_ONCE(sk->sk_pacing_status) != SK_PACING_FQ) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + return &q->internal; } root = &q->fq_root[hash_ptr(sk, q->fq_trees_log)]; - if (q->flows >= (2U << q->fq_trees_log) && - q->inactive_flows > q->flows/2) - fq_gc(q, root, sk); + fq_gc(q, root, sk); p = &root->rb_node; parent = NULL; @@ -263,10 +416,15 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) * It not, we need to refill credit with * initial quantum */ - if (unlikely(skb->sk && + if (unlikely(skb->sk == sk && f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + if (fq_flow_is_throttled(f)) + fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; } return f; @@ -282,10 +440,16 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) q->stat_allocation_errors++; return &q->internal; } + /* f->t_root is already zeroed after kmem_cache_zalloc() */ + fq_flow_set_detached(f); f->sk = sk; - if (skb->sk) + if (skb->sk == sk) { f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); @@ -296,139 +460,171 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) return f; } +static struct sk_buff *fq_peek(struct fq_flow *flow) +{ + struct sk_buff *skb = skb_rb_first(&flow->t_root); + struct sk_buff *head = flow->head; + + if (!skb) + return head; + + if (!head) + return skb; -/* remove one skb from head of flow queue */ -static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) + if (fq_skb_cb(skb)->time_to_send < fq_skb_cb(head)->time_to_send) + return skb; + return head; +} + +static void fq_erase_head(struct Qdisc *sch, struct fq_flow *flow, + struct sk_buff *skb) { - struct sk_buff *skb = flow->head; + if (skb == flow->head) { + struct sk_buff *next = skb->next; - if (skb) { - flow->head = skb->next; - skb->next = NULL; - flow->qlen--; - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; + prefetch(next); + flow->head = next; + } else { + rb_erase(&skb->rbnode, &flow->t_root); + skb->dev = qdisc_dev(sch); } - return skb; } -/* We might add in the future detection of retransmits - * For the time being, just return false - */ -static bool skb_is_retransmit(struct sk_buff *skb) -{ - return false; -} - -/* add skb to flow queue - * flow queue is a linked list, kind of FIFO, except for TCP retransmits - * We special case tcp retransmits to be transmitted before other packets. - * We rely on fact that TCP retransmits are unlikely, so we do not waste - * a separate queue or a pointer. - * head-> [retrans pkt 1] - * [retrans pkt 2] - * [ normal pkt 1] - * [ normal pkt 2] - * [ normal pkt 3] - * tail-> [ normal pkt 4] +/* Remove one skb from flow queue. + * This skb must be the return value of prior fq_peek(). */ +static void fq_dequeue_skb(struct Qdisc *sch, struct fq_flow *flow, + struct sk_buff *skb) +{ + fq_erase_head(sch, flow, skb); + skb_mark_not_on_list(skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + qdisc_bstats_update(sch, skb); +} + static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) { - struct sk_buff *prev, *head = flow->head; + struct rb_node **p, *parent; + struct sk_buff *head, *aux; - skb->next = NULL; - if (!head) { - flow->head = skb; - flow->tail = skb; - return; - } - if (likely(!skb_is_retransmit(skb))) { - flow->tail->next = skb; + head = flow->head; + if (!head || + fq_skb_cb(skb)->time_to_send >= fq_skb_cb(flow->tail)->time_to_send) { + if (!head) + flow->head = skb; + else + flow->tail->next = skb; flow->tail = skb; + skb->next = NULL; return; } - /* This skb is a tcp retransmit, - * find the last retrans packet in the queue - */ - prev = NULL; - while (skb_is_retransmit(head)) { - prev = head; - head = head->next; - if (!head) - break; - } - if (!prev) { /* no rtx packet in queue, become the new head */ - skb->next = flow->head; - flow->head = skb; - } else { - if (prev == flow->tail) - flow->tail = skb; + p = &flow->t_root.rb_node; + parent = NULL; + + while (*p) { + parent = *p; + aux = rb_to_skb(parent); + if (fq_skb_cb(skb)->time_to_send >= fq_skb_cb(aux)->time_to_send) + p = &parent->rb_right; else - skb->next = prev->next; - prev->next = skb; + p = &parent->rb_left; } + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, &flow->t_root); } +static bool fq_packet_beyond_horizon(const struct sk_buff *skb, + const struct fq_sched_data *q, u64 now) +{ + return unlikely((s64)skb->tstamp > (s64)(now + q->horizon)); +} + +#define FQDR(reason) SKB_DROP_REASON_FQ_##reason + static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct fq_sched_data *q = qdisc_priv(sch); struct fq_flow *f; + u64 now; + u8 band; + + band = fq_prio2band(q->prio2band, skb->priority & TC_PRIO_MAX); + if (unlikely(q->band_pkt_count[band] >= sch->limit)) { + q->stat_band_drops[band]++; + return qdisc_drop_reason(skb, sch, to_free, + FQDR(BAND_LIMIT)); + } - if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop(skb, sch, to_free); - - f = fq_classify(skb, q); - if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) { - q->stat_flows_plimit++; - return qdisc_drop(skb, sch, to_free); + now = ktime_get_ns(); + if (!skb->tstamp) { + fq_skb_cb(skb)->time_to_send = now; + } else { + /* Check if packet timestamp is too far in the future. */ + if (fq_packet_beyond_horizon(skb, q, now)) { + if (q->horizon_drop) { + q->stat_horizon_drops++; + return qdisc_drop_reason(skb, sch, to_free, + FQDR(HORIZON_LIMIT)); + } + q->stat_horizon_caps++; + skb->tstamp = now + q->horizon; + } + fq_skb_cb(skb)->time_to_send = skb->tstamp; } - f->qlen++; - if (skb_is_retransmit(skb)) - q->stat_tcp_retrans++; - qdisc_qstats_backlog_inc(sch, skb); - if (fq_flow_is_detached(f)) { - struct sock *sk = skb->sk; - - fq_flow_add_tail(&q->new_flows, f); - if (time_after(jiffies, f->age + q->flow_refill_delay)) - f->credit = max_t(u32, f->credit, q->quantum); - if (sk && q->rate_enable) { - if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != - SK_PACING_FQ)) - smp_store_release(&sk->sk_pacing_status, - SK_PACING_FQ); + f = fq_classify(sch, skb, now); + + if (f != &q->internal) { + if (unlikely(f->qlen >= q->flow_plimit)) { + q->stat_flows_plimit++; + return qdisc_drop_reason(skb, sch, to_free, + FQDR(FLOW_LIMIT)); } - q->inactive_flows--; + + if (fq_flow_is_detached(f)) { + fq_flow_add_tail(q, f, NEW_FLOW); + if (time_after(jiffies, f->age + q->flow_refill_delay)) + f->credit = max_t(u32, f->credit, q->quantum); + } + + f->band = band; + q->band_pkt_count[band]++; + fq_skb_cb(skb)->band = band; + if (f->qlen == 0) + q->inactive_flows--; } + f->qlen++; /* Note: this overwrites f->age */ flow_queue_add(f, skb); - if (unlikely(f == &q->internal)) { - q->stat_internal_packets++; - } + qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; } +#undef FQDR static void fq_check_throttled(struct fq_sched_data *q, u64 now) { unsigned long sample; struct rb_node *p; - if (q->time_next_delayed_flow > now) + if (q->time_next_delayed_flow > now + q->offload_horizon) return; /* Update unthrottle latency EWMA. * This is cheap and can help diagnosing timer/latency problems. */ sample = (unsigned long)(now - q->time_next_delayed_flow); - q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3; - q->unthrottle_latency_ns += sample >> 3; + if ((long)sample > 0) { + q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3; + q->unthrottle_latency_ns += sample >> 3; + } + now += q->offload_horizon; q->time_next_delayed_flow = ~0ULL; while ((p = rb_first(&q->delayed)) != NULL) { @@ -438,92 +634,135 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now) q->time_next_delayed_flow = f->time_next_packet; break; } - rb_erase(p, &q->delayed); - q->throttled_flows--; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_unset_throttled(q, f); } } +static struct fq_flow_head *fq_pband_head_select(struct fq_perband_flows *pband) +{ + if (pband->credit <= 0) + return NULL; + + if (pband->new_flows.first) + return &pband->new_flows; + + return pband->old_flows.first ? &pband->old_flows : NULL; +} + static struct sk_buff *fq_dequeue(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); - u64 now = ktime_get_ns(); + struct fq_perband_flows *pband; struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; - u32 rate, plen; - - skb = fq_dequeue_head(sch, &q->internal); - if (skb) + unsigned long rate; + int retry; + u32 plen; + u64 now; + + if (!sch->q.qlen) + return NULL; + + skb = fq_peek(&q->internal); + if (unlikely(skb)) { + q->internal.qlen--; + fq_dequeue_skb(sch, &q->internal, skb); goto out; + } + + now = ktime_get_ns(); fq_check_throttled(q, now); + retry = 0; + pband = &q->band_flows[q->band_nr]; begin: - head = &q->new_flows; - if (!head->first) { - head = &q->old_flows; - if (!head->first) { - if (q->time_next_delayed_flow != ~0ULL) - qdisc_watchdog_schedule_ns(&q->watchdog, - q->time_next_delayed_flow); - return NULL; + head = fq_pband_head_select(pband); + if (!head) { + while (++retry <= FQ_BANDS) { + if (++q->band_nr == FQ_BANDS) + q->band_nr = 0; + pband = &q->band_flows[q->band_nr]; + pband->credit = min(pband->credit + pband->quantum, + pband->quantum); + if (pband->credit > 0) + goto begin; + retry = 0; } + if (q->time_next_delayed_flow != ~0ULL) + qdisc_watchdog_schedule_range_ns(&q->watchdog, + q->time_next_delayed_flow, + q->timer_slack); + return NULL; } f = head->first; - + retry = 0; if (f->credit <= 0) { f->credit += q->quantum; head->first = f->next; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_add_tail(q, f, OLD_FLOW); goto begin; } - skb = f->head; - if (unlikely(skb && now < f->time_next_packet && - !skb_is_tcp_pure_ack(skb))) { - head->first = f->next; - fq_flow_set_throttled(q, f); - goto begin; - } - - skb = fq_dequeue_head(sch, f); - if (!skb) { + skb = fq_peek(f); + if (skb) { + u64 time_next_packet = max_t(u64, fq_skb_cb(skb)->time_to_send, + f->time_next_packet); + + if (now + q->offload_horizon < time_next_packet) { + head->first = f->next; + f->time_next_packet = time_next_packet; + fq_flow_set_throttled(q, f); + goto begin; + } + prefetch(&skb->end); + fq_dequeue_skb(sch, f, skb); + if ((s64)(now - time_next_packet - q->ce_threshold) > 0) { + INET_ECN_set_ce(skb); + q->stat_ce_mark++; + } + if (--f->qlen == 0) + q->inactive_flows++; + q->band_pkt_count[fq_skb_cb(skb)->band]--; + } else { head->first = f->next; /* force a pass through old_flows to prevent starvation */ - if ((head == &q->new_flows) && q->old_flows.first) { - fq_flow_add_tail(&q->old_flows, f); + if (head == &pband->new_flows) { + fq_flow_add_tail(q, f, OLD_FLOW); } else { fq_flow_set_detached(f); - q->inactive_flows++; } goto begin; } - prefetch(&skb->end); - f->credit -= qdisc_pkt_len(skb); + plen = qdisc_pkt_len(skb); + f->credit -= plen; + pband->credit -= plen; if (!q->rate_enable) goto out; - /* Do not pace locally generated ack packets */ - if (skb_is_tcp_pure_ack(skb)) - goto out; - rate = q->flow_max_rate; - if (skb->sk) - rate = min(skb->sk->sk_pacing_rate, rate); - if (rate <= q->low_rate_threshold) { - f->credit = 0; - plen = qdisc_pkt_len(skb); - } else { - plen = max(qdisc_pkt_len(skb), q->quantum); - if (f->credit > 0) - goto out; + /* If EDT time was provided for this skb, we need to + * update f->time_next_packet only if this qdisc enforces + * a flow max rate. + */ + if (!skb->tstamp) { + if (skb->sk) + rate = min(READ_ONCE(skb->sk->sk_pacing_rate), rate); + + if (rate <= q->low_rate_threshold) { + f->credit = 0; + } else { + plen = max(plen, q->quantum); + if (f->credit > 0) + goto out; + } } - if (rate != ~0U) { + if (rate != ~0UL) { u64 len = (u64)plen * NSEC_PER_SEC; if (likely(rate)) - do_div(len, rate); + len = div64_ul(len, rate); /* Since socket rate can change later, * clamp the delay to 1 second. * Really, providers of too big packets should be fixed ! @@ -541,12 +780,20 @@ begin: f->time_next_packet = now + len; } out: - qdisc_bstats_update(sch, skb); return skb; } static void fq_flow_purge(struct fq_flow *flow) { + struct rb_node *p = rb_first(&flow->t_root); + + while (p) { + struct sk_buff *skb = rb_to_skb(p); + + p = rb_next(p); + rb_erase(&skb->rbnode, &flow->t_root); + rtnl_kfree_skbs(skb, skb); + } rtnl_kfree_skbs(flow->head, flow->tail); flow->head = NULL; flow->qlen = 0; @@ -579,8 +826,10 @@ static void fq_reset(struct Qdisc *sch) kmem_cache_free(fq_flow_cachep, f); } } - q->new_flows.first = NULL; - q->old_flows.first = NULL; + for (idx = 0; idx < FQ_BANDS; idx++) { + q->band_flows[idx].new_flows.first = NULL; + q->band_flows[idx].old_flows.first = NULL; + } q->delayed = RB_ROOT; q->flows = 0; q->inactive_flows = 0; @@ -663,7 +912,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) fq_rehash(q, old_fq_root, q->fq_trees_log, array, log); q->fq_root = array; - q->fq_trees_log = log; + WRITE_ONCE(q->fq_trees_log, log); sch_tree_unlock(sch); @@ -672,31 +921,109 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; } +static const struct netlink_range_validation iq_range = { + .max = INT_MAX, +}; + static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { + [TCA_FQ_UNSPEC] = { .strict_start_type = TCA_FQ_TIMER_SLACK }, + [TCA_FQ_PLIMIT] = { .type = NLA_U32 }, [TCA_FQ_FLOW_PLIMIT] = { .type = NLA_U32 }, [TCA_FQ_QUANTUM] = { .type = NLA_U32 }, - [TCA_FQ_INITIAL_QUANTUM] = { .type = NLA_U32 }, + [TCA_FQ_INITIAL_QUANTUM] = NLA_POLICY_FULL_RANGE(NLA_U32, &iq_range), [TCA_FQ_RATE_ENABLE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_DEFAULT_RATE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 }, [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, + [TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 }, + [TCA_FQ_TIMER_SLACK] = { .type = NLA_U32 }, + [TCA_FQ_HORIZON] = { .type = NLA_U32 }, + [TCA_FQ_HORIZON_DROP] = { .type = NLA_U8 }, + [TCA_FQ_PRIOMAP] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_prio_qopt)), + [TCA_FQ_WEIGHTS] = NLA_POLICY_EXACT_LEN(FQ_BANDS * sizeof(s32)), + [TCA_FQ_OFFLOAD_HORIZON] = { .type = NLA_U32 }, }; -static int fq_change(struct Qdisc *sch, struct nlattr *opt) +/* compress a u8 array with all elems <= 3 to an array of 2-bit fields */ +static void fq_prio2band_compress_crumb(const u8 *in, u8 *out) +{ + const int num_elems = TC_PRIO_MAX + 1; + u8 tmp[FQ_PRIO2BAND_CRUMB_SIZE]; + int i; + + memset(tmp, 0, sizeof(tmp)); + for (i = 0; i < num_elems; i++) + tmp[i / 4] |= in[i] << (2 * (i & 0x3)); + + for (i = 0; i < FQ_PRIO2BAND_CRUMB_SIZE; i++) + WRITE_ONCE(out[i], tmp[i]); +} + +static void fq_prio2band_decompress_crumb(const u8 *in, u8 *out) +{ + const int num_elems = TC_PRIO_MAX + 1; + int i; + + for (i = 0; i < num_elems; i++) + out[i] = fq_prio2band(in, i); +} + +static int fq_load_weights(struct fq_sched_data *q, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + s32 *weights = nla_data(attr); + int i; + + for (i = 0; i < FQ_BANDS; i++) { + if (weights[i] < FQ_MIN_WEIGHT) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Weight %d less that minimum allowed %d", + weights[i], FQ_MIN_WEIGHT); + return -EINVAL; + } + } + for (i = 0; i < FQ_BANDS; i++) + WRITE_ONCE(q->band_flows[i].quantum, weights[i]); + return 0; +} + +static int fq_load_priomap(struct fq_sched_data *q, + const struct nlattr *attr, + struct netlink_ext_ack *extack) { + const struct tc_prio_qopt *map = nla_data(attr); + int i; + + if (map->bands != FQ_BANDS) { + NL_SET_ERR_MSG_MOD(extack, "FQ only supports 3 bands"); + return -EINVAL; + } + for (i = 0; i < TC_PRIO_MAX + 1; i++) { + if (map->priomap[i] >= FQ_BANDS) { + NL_SET_ERR_MSG_FMT_MOD(extack, "FQ priomap field %d maps to a too high band %d", + i, map->priomap[i]); + return -EINVAL; + } + } + fq_prio2band_compress_crumb(map->priomap, q->prio2band); + return 0; +} + +static int fq_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; - int err, drop_count = 0; - unsigned drop_len = 0; u32 fq_log; + int err; - if (!opt) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_FQ_MAX, opt, fq_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy, + NULL); if (err < 0) return err; @@ -713,39 +1040,48 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) err = -EINVAL; } if (tb[TCA_FQ_PLIMIT]) - sch->limit = nla_get_u32(tb[TCA_FQ_PLIMIT]); + WRITE_ONCE(sch->limit, + nla_get_u32(tb[TCA_FQ_PLIMIT])); if (tb[TCA_FQ_FLOW_PLIMIT]) - q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]); + WRITE_ONCE(q->flow_plimit, + nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT])); if (tb[TCA_FQ_QUANTUM]) { u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); - if (quantum > 0) - q->quantum = quantum; - else + if (quantum > 0 && quantum <= (1 << 20)) { + WRITE_ONCE(q->quantum, quantum); + } else { + NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); err = -EINVAL; + } } if (tb[TCA_FQ_INITIAL_QUANTUM]) - q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); + WRITE_ONCE(q->initial_quantum, + nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM])); if (tb[TCA_FQ_FLOW_DEFAULT_RATE]) pr_warn_ratelimited("sch_fq: defrate %u ignored.\n", nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE])); - if (tb[TCA_FQ_FLOW_MAX_RATE]) - q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + if (tb[TCA_FQ_FLOW_MAX_RATE]) { + u32 rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + WRITE_ONCE(q->flow_max_rate, + (rate == ~0U) ? ~0UL : rate); + } if (tb[TCA_FQ_LOW_RATE_THRESHOLD]) - q->low_rate_threshold = - nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD]); + WRITE_ONCE(q->low_rate_threshold, + nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD])); if (tb[TCA_FQ_RATE_ENABLE]) { u32 enable = nla_get_u32(tb[TCA_FQ_RATE_ENABLE]); if (enable <= 1) - q->rate_enable = enable; + WRITE_ONCE(q->rate_enable, + enable); else err = -EINVAL; } @@ -753,27 +1089,67 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_FQ_FLOW_REFILL_DELAY]) { u32 usecs_delay = nla_get_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]) ; - q->flow_refill_delay = usecs_to_jiffies(usecs_delay); + WRITE_ONCE(q->flow_refill_delay, + usecs_to_jiffies(usecs_delay)); } + if (!err && tb[TCA_FQ_PRIOMAP]) + err = fq_load_priomap(q, tb[TCA_FQ_PRIOMAP], extack); + + if (!err && tb[TCA_FQ_WEIGHTS]) + err = fq_load_weights(q, tb[TCA_FQ_WEIGHTS], extack); + if (tb[TCA_FQ_ORPHAN_MASK]) - q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]); + WRITE_ONCE(q->orphan_mask, + nla_get_u32(tb[TCA_FQ_ORPHAN_MASK])); + + if (tb[TCA_FQ_CE_THRESHOLD]) + WRITE_ONCE(q->ce_threshold, + (u64)NSEC_PER_USEC * + nla_get_u32(tb[TCA_FQ_CE_THRESHOLD])); + + if (tb[TCA_FQ_TIMER_SLACK]) + WRITE_ONCE(q->timer_slack, + nla_get_u32(tb[TCA_FQ_TIMER_SLACK])); + + if (tb[TCA_FQ_HORIZON]) + WRITE_ONCE(q->horizon, + (u64)NSEC_PER_USEC * + nla_get_u32(tb[TCA_FQ_HORIZON])); + if (tb[TCA_FQ_HORIZON_DROP]) + WRITE_ONCE(q->horizon_drop, + nla_get_u8(tb[TCA_FQ_HORIZON_DROP])); + + if (tb[TCA_FQ_OFFLOAD_HORIZON]) { + u64 offload_horizon = (u64)NSEC_PER_USEC * + nla_get_u32(tb[TCA_FQ_OFFLOAD_HORIZON]); + + if (offload_horizon <= qdisc_dev(sch)->max_pacing_offload_horizon) { + WRITE_ONCE(q->offload_horizon, offload_horizon); + } else { + NL_SET_ERR_MSG_MOD(extack, "invalid offload_horizon"); + err = -EINVAL; + } + } if (!err) { + sch_tree_unlock(sch); err = fq_resize(sch, fq_log); sch_tree_lock(sch); } + while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; - drop_len += qdisc_pkt_len(skb); + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - drop_count++; } - qdisc_tree_reduce_backlog(sch, drop_count, drop_len); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return err; @@ -788,30 +1164,46 @@ static void fq_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); } -static int fq_init(struct Qdisc *sch, struct nlattr *opt) +static int fq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct fq_sched_data *q = qdisc_priv(sch); - int err; + int i, err; sch->limit = 10000; q->flow_plimit = 100; q->quantum = 2 * psched_mtu(qdisc_dev(sch)); q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); q->flow_refill_delay = msecs_to_jiffies(40); - q->flow_max_rate = ~0U; + q->flow_max_rate = ~0UL; q->time_next_delayed_flow = ~0ULL; q->rate_enable = 1; - q->new_flows.first = NULL; - q->old_flows.first = NULL; + for (i = 0; i < FQ_BANDS; i++) { + q->band_flows[i].new_flows.first = NULL; + q->band_flows[i].old_flows.first = NULL; + } + q->band_flows[0].quantum = 9 << 16; + q->band_flows[1].quantum = 3 << 16; + q->band_flows[2].quantum = 1 << 16; q->delayed = RB_ROOT; q->fq_root = NULL; q->fq_trees_log = ilog2(1024); q->orphan_mask = 1024 - 1; q->low_rate_threshold = 550000 / 8; - qdisc_watchdog_init(&q->watchdog, sch); + + q->timer_slack = 10 * NSEC_PER_USEC; /* 10 usec of hrtimer slack */ + + q->horizon = 10ULL * NSEC_PER_SEC; /* 10 seconds */ + q->horizon_drop = 1; /* by default, drop packets beyond horizon */ + + /* Default ce_threshold of 4294 seconds */ + q->ce_threshold = (u64)NSEC_PER_USEC * ~0U; + + fq_prio2band_compress_crumb(sch_default_prio2band, q->prio2band); + qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_MONOTONIC); if (opt) - err = fq_change(sch, opt); + err = fq_change(sch, opt, extack); else err = fq_resize(sch, q->fq_trees_log); @@ -821,26 +1213,68 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_sched_data *q = qdisc_priv(sch); + struct tc_prio_qopt prio = { + .bands = FQ_BANDS, + }; struct nlattr *opts; + u64 offload_horizon; + u64 ce_threshold; + s32 weights[3]; + u64 horizon; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */ - if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || - nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || - nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) || - nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) || - nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) || - nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) || + ce_threshold = READ_ONCE(q->ce_threshold); + do_div(ce_threshold, NSEC_PER_USEC); + + horizon = READ_ONCE(q->horizon); + do_div(horizon, NSEC_PER_USEC); + + offload_horizon = READ_ONCE(q->offload_horizon); + do_div(offload_horizon, NSEC_PER_USEC); + + if (nla_put_u32(skb, TCA_FQ_PLIMIT, + READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, + READ_ONCE(q->flow_plimit)) || + nla_put_u32(skb, TCA_FQ_QUANTUM, + READ_ONCE(q->quantum)) || + nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, + READ_ONCE(q->initial_quantum)) || + nla_put_u32(skb, TCA_FQ_RATE_ENABLE, + READ_ONCE(q->rate_enable)) || + nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, + min_t(unsigned long, + READ_ONCE(q->flow_max_rate), ~0U)) || nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, - jiffies_to_usecs(q->flow_refill_delay)) || - nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) || + jiffies_to_usecs(READ_ONCE(q->flow_refill_delay))) || + nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, + READ_ONCE(q->orphan_mask)) || nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD, - q->low_rate_threshold) || - nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) + READ_ONCE(q->low_rate_threshold)) || + nla_put_u32(skb, TCA_FQ_CE_THRESHOLD, (u32)ce_threshold) || + nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, + READ_ONCE(q->fq_trees_log)) || + nla_put_u32(skb, TCA_FQ_TIMER_SLACK, + READ_ONCE(q->timer_slack)) || + nla_put_u32(skb, TCA_FQ_HORIZON, (u32)horizon) || + nla_put_u32(skb, TCA_FQ_OFFLOAD_HORIZON, (u32)offload_horizon) || + nla_put_u8(skb, TCA_FQ_HORIZON_DROP, + READ_ONCE(q->horizon_drop))) + goto nla_put_failure; + + fq_prio2band_decompress_crumb(q->prio2band, prio.priomap); + if (nla_put(skb, TCA_FQ_PRIOMAP, sizeof(prio), &prio)) + goto nla_put_failure; + + weights[0] = READ_ONCE(q->band_flows[0].quantum); + weights[1] = READ_ONCE(q->band_flows[1].quantum); + weights[2] = READ_ONCE(q->band_flows[2].quantum); + if (nla_put(skb, TCA_FQ_WEIGHTS, sizeof(weights), &weights)) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -853,22 +1287,34 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct fq_sched_data *q = qdisc_priv(sch); struct tc_fq_qd_stats st; + int i; + + st.pad = 0; sch_tree_lock(sch); st.gc_flows = q->stat_gc_flows; - st.highprio_packets = q->stat_internal_packets; - st.tcp_retrans = q->stat_tcp_retrans; + st.highprio_packets = 0; + st.fastpath_packets = q->internal.stat_fastpath_packets; + st.tcp_retrans = 0; st.throttled = q->stat_throttled; st.flows_plimit = q->stat_flows_plimit; st.pkts_too_long = q->stat_pkts_too_long; st.allocation_errors = q->stat_allocation_errors; - st.time_next_delayed_flow = q->time_next_delayed_flow - ktime_get_ns(); + st.time_next_delayed_flow = q->time_next_delayed_flow + q->timer_slack - + ktime_get_ns(); st.flows = q->flows; st.inactive_flows = q->inactive_flows; st.throttled_flows = q->throttled_flows; st.unthrottle_latency_ns = min_t(unsigned long, q->unthrottle_latency_ns, ~0U); + st.ce_mark = q->stat_ce_mark; + st.horizon_drops = q->stat_horizon_drops; + st.horizon_caps = q->stat_horizon_caps; + for (i = 0; i < FQ_BANDS; i++) { + st.band_drops[i] = q->stat_band_drops[i]; + st.band_pkt_count[i] = q->band_pkt_count[i]; + } sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); @@ -889,6 +1335,7 @@ static struct Qdisc_ops fq_qdisc_ops __read_mostly = { .dump_stats = fq_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("fq"); static int __init fq_module_init(void) { @@ -896,7 +1343,7 @@ static int __init fq_module_init(void) fq_flow_cachep = kmem_cache_create("fq_flow_cache", sizeof(struct fq_flow), - 0, 0, NULL); + 0, SLAB_HWCACHE_ALIGN, NULL); if (!fq_flow_cachep) return -ENOMEM; @@ -916,3 +1363,4 @@ module_init(fq_module_init) module_exit(fq_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue Packet Scheduler"); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 337f2d6d81e4..dc187c7f06b1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Fair Queue CoDel discipline * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> */ @@ -18,7 +14,6 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> -#include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/netlink.h> @@ -49,7 +44,6 @@ struct fq_codel_flow { struct sk_buff *tail; struct list_head flowchain; int deficit; - u32 dropped; /* number of drops (or ECN marks) on this flow */ struct codel_vars cvars; }; /* please try to keep this structure <= 64 bytes */ @@ -97,7 +91,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, filter, &res, false); + result = tcf_classify(skb, NULL, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -105,6 +99,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return 0; } @@ -123,7 +118,7 @@ static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) struct sk_buff *skb = flow->head; flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } @@ -173,10 +168,12 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, skb = dequeue_head(flow); len += qdisc_pkt_len(skb); mem += get_codel_cb(skb)->mem_usage; + tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_OVERLIMIT); __qdisc_drop(skb, to_free); } while (++i < max_packets && len < threshold); - flow->dropped += i; + /* Tell codel to increase its signal strength also */ + flow->cvars.count += i; q->backlogs[idx] -= len; q->memory_usage -= mem; sch->qstats.drops += i; @@ -191,7 +188,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct fq_codel_sched_data *q = qdisc_priv(sch); unsigned int idx, prev_backlog, prev_qlen; struct fq_codel_flow *flow; - int uninitialized_var(ret); + int ret; unsigned int pkt_len; bool memory_limited; @@ -214,7 +211,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_add_tail(&flow->flowchain, &q->new_flows); q->new_flow_count++; flow->deficit = q->quantum; - flow->dropped = 0; } get_codel_cb(skb)->mem_usage = skb->truesize; q->memory_usage += get_codel_cb(skb)->mem_usage; @@ -279,7 +275,7 @@ static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; - kfree_skb(skb); + qdisc_dequeue_drop(sch, skb, SKB_DROP_REASON_QDISC_CONGESTED); qdisc_qstats_drop(sch); } @@ -289,7 +285,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct sk_buff *skb; struct fq_codel_flow *flow; struct list_head *head; - u32 prev_drop_count, prev_ecn_mark; begin: head = &q->new_flows; @@ -306,16 +301,10 @@ begin: goto begin; } - prev_drop_count = q->cstats.drop_count; - prev_ecn_mark = q->cstats.ecn_mark; - skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - flow->dropped += q->cstats.drop_count - prev_drop_count; - flow->dropped += q->cstats.ecn_mark - prev_ecn_mark; - if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &q->new_flows) && !list_empty(&q->old_flows)) @@ -326,10 +315,8 @@ begin: } qdisc_bstats_update(sch, skb); flow->deficit -= qdisc_pkt_len(skb); - /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, - * or HTB crashes. Defer it for next round. - */ - if (q->cstats.drop_count && sch->q.qlen) { + + if (q->cstats.drop_count) { qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); q->cstats.drop_count = 0; @@ -359,8 +346,6 @@ static void fq_codel_reset(struct Qdisc *sch) codel_vars_init(&flow->cvars); } memset(q->backlogs, 0, q->flows_cnt * sizeof(u32)); - sch->q.qlen = 0; - sch->qstats.backlog = 0; q->memory_usage = 0; } @@ -374,19 +359,21 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR] = { .type = NLA_U8 }, + [TCA_FQ_CODEL_CE_THRESHOLD_MASK] = { .type = NLA_U8 }, }; -static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) +static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; + u32 quantum = 0; int err; - if (!opt) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_FQ_CODEL_MAX, opt, fq_codel_policy, - NULL); + err = nla_parse_nested_deprecated(tb, TCA_FQ_CODEL_MAX, opt, + fq_codel_policy, NULL); if (err < 0) return err; if (tb[TCA_FQ_CODEL_FLOWS]) { @@ -397,52 +384,74 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) q->flows_cnt > 65536) return -EINVAL; } + if (tb[TCA_FQ_CODEL_QUANTUM]) { + quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); + if (quantum > FQ_CODEL_QUANTUM_MAX) { + NL_SET_ERR_MSG(extack, "Invalid quantum"); + return -EINVAL; + } + } sch_tree_lock(sch); if (tb[TCA_FQ_CODEL_TARGET]) { u64 target = nla_get_u32(tb[TCA_FQ_CODEL_TARGET]); - q->cparams.target = (target * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->cparams.target, + (target * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_FQ_CODEL_CE_THRESHOLD]) { u64 val = nla_get_u32(tb[TCA_FQ_CODEL_CE_THRESHOLD]); - q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->cparams.ce_threshold, + (val * NSEC_PER_USEC) >> CODEL_SHIFT); } + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]) + WRITE_ONCE(q->cparams.ce_threshold_selector, + nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR])); + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]) + WRITE_ONCE(q->cparams.ce_threshold_mask, + nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK])); + if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); - q->cparams.interval = (interval * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->cparams.interval, + (interval * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_FQ_CODEL_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_FQ_CODEL_LIMIT]); + WRITE_ONCE(sch->limit, + nla_get_u32(tb[TCA_FQ_CODEL_LIMIT])); if (tb[TCA_FQ_CODEL_ECN]) - q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]); + WRITE_ONCE(q->cparams.ecn, + !!nla_get_u32(tb[TCA_FQ_CODEL_ECN])); - if (tb[TCA_FQ_CODEL_QUANTUM]) - q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); + if (quantum) + WRITE_ONCE(q->quantum, quantum); if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + WRITE_ONCE(q->drop_batch_size, + max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]))); if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) - q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); + WRITE_ONCE(q->memory_limit, + min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]))); while (sch->q.qlen > sch->limit || q->memory_usage > q->memory_limit) { - struct sk_buff *skb = fq_codel_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - q->cstats.drop_len += qdisc_pkt_len(skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - q->cstats.drop_count++; } - qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); - q->cstats.drop_count = 0; - q->cstats.drop_len = 0; + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; @@ -457,7 +466,8 @@ static void fq_codel_destroy(struct Qdisc *sch) kvfree(q->flows); } -static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) +static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct fq_codel_sched_data *q = qdisc_priv(sch); int i; @@ -476,24 +486,27 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) q->cparams.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { - int err = fq_codel_change(sch, opt); + err = fq_codel_change(sch, opt, extack); if (err) - return err; + goto init_failure; } - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) - return err; + goto init_failure; if (!q->flows) { - q->flows = kvzalloc(q->flows_cnt * - sizeof(struct fq_codel_flow), GFP_KERNEL); - if (!q->flows) - return -ENOMEM; - q->backlogs = kvzalloc(q->flows_cnt * sizeof(u32), GFP_KERNEL); + q->flows = kvcalloc(q->flows_cnt, + sizeof(struct fq_codel_flow), + GFP_KERNEL); + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } + q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL); if (!q->backlogs) { - kvfree(q->flows); - return -ENOMEM; + err = -ENOMEM; + goto alloc_failure; } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; @@ -506,40 +519,59 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; + + sch->flags |= TCQ_F_DEQUEUE_DROPS; + return 0; + +alloc_failure: + kvfree(q->flows); + q->flows = NULL; +init_failure: + q->flows_cnt = 0; + return err; } static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_codel_sched_data *q = qdisc_priv(sch); + codel_time_t ce_threshold; struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_FQ_CODEL_TARGET, - codel_time_to_us(q->cparams.target)) || + codel_time_to_us(READ_ONCE(q->cparams.target))) || nla_put_u32(skb, TCA_FQ_CODEL_LIMIT, - sch->limit) || + READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_FQ_CODEL_INTERVAL, - codel_time_to_us(q->cparams.interval)) || + codel_time_to_us(READ_ONCE(q->cparams.interval))) || nla_put_u32(skb, TCA_FQ_CODEL_ECN, - q->cparams.ecn) || + READ_ONCE(q->cparams.ecn)) || nla_put_u32(skb, TCA_FQ_CODEL_QUANTUM, - q->quantum) || + READ_ONCE(q->quantum)) || nla_put_u32(skb, TCA_FQ_CODEL_DROP_BATCH_SIZE, - q->drop_batch_size) || + READ_ONCE(q->drop_batch_size)) || nla_put_u32(skb, TCA_FQ_CODEL_MEMORY_LIMIT, - q->memory_limit) || + READ_ONCE(q->memory_limit)) || nla_put_u32(skb, TCA_FQ_CODEL_FLOWS, - q->flows_cnt)) + READ_ONCE(q->flows_cnt))) goto nla_put_failure; - if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD && - nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, - codel_time_to_us(q->cparams.ce_threshold))) - goto nla_put_failure; + ce_threshold = READ_ONCE(q->cparams.ce_threshold); + if (ce_threshold != CODEL_DISABLED_THRESHOLD) { + if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, + codel_time_to_us(ce_threshold))) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, + READ_ONCE(q->cparams.ce_threshold_selector))) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_MASK, + READ_ONCE(q->cparams.ce_threshold_mask))) + goto nla_put_failure; + } return nla_nest_end(skb, opts); @@ -579,7 +611,7 @@ static struct Qdisc *fq_codel_leaf(struct Qdisc *sch, unsigned long arg) return NULL; } -static unsigned long fq_codel_get(struct Qdisc *sch, u32 classid) +static unsigned long fq_codel_find(struct Qdisc *sch, u32 classid) { return 0; } @@ -587,16 +619,15 @@ static unsigned long fq_codel_get(struct Qdisc *sch, u32 classid) static unsigned long fq_codel_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { - /* we cannot bypass queue discipline anymore */ - sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } -static void fq_codel_put(struct Qdisc *q, unsigned long cl) +static void fq_codel_unbind(struct Qdisc *q, unsigned long cl) { } -static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct fq_codel_sched_data *q = qdisc_priv(sch); @@ -650,7 +681,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch_tree_unlock(sch); } qs.backlog = q->backlogs[idx]; - qs.drops = flow->dropped; + qs.drops = 0; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; @@ -668,26 +699,21 @@ static void fq_codel_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (i = 0; i < q->flows_cnt; i++) { - if (list_empty(&q->flows[i].flowchain) || - arg->count < arg->skip) { + if (list_empty(&q->flows[i].flowchain)) { arg->count++; continue; } - if (arg->fn(sch, i + 1, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, i + 1, arg)) break; - } - arg->count++; } } static const struct Qdisc_class_ops fq_codel_class_ops = { .leaf = fq_codel_leaf, - .get = fq_codel_get, - .put = fq_codel_put, + .find = fq_codel_find, .tcf_block = fq_codel_tcf_block, .bind_tcf = fq_codel_bind, - .unbind_tcf = fq_codel_put, + .unbind_tcf = fq_codel_unbind, .dump = fq_codel_dump_class, .dump_stats = fq_codel_dump_class_stats, .walk = fq_codel_walk, @@ -708,6 +734,7 @@ static struct Qdisc_ops fq_codel_qdisc_ops __read_mostly = { .dump_stats = fq_codel_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("fq_codel"); static int __init fq_codel_module_init(void) { @@ -723,3 +750,4 @@ module_init(fq_codel_module_init) module_exit(fq_codel_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue CoDel discipline"); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c new file mode 100644 index 000000000000..7b96bc3ff891 --- /dev/null +++ b/net/sched/sch_fq_pie.c @@ -0,0 +1,595 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Flow Queue PIE discipline + * + * Copyright (C) 2019 Mohit P. Tahiliani <tahiliani@nitk.edu.in> + * Copyright (C) 2019 Sachin D. Patil <sdp.sachin@gmail.com> + * Copyright (C) 2019 V. Saicharan <vsaicharan1998@gmail.com> + * Copyright (C) 2019 Mohit Bhasi <mohitbhasi1998@gmail.com> + * Copyright (C) 2019 Leslie Monis <lesliemonis@gmail.com> + * Copyright (C) 2019 Gautam Ramakrishnan <gautamramk@gmail.com> + */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/sizes.h> +#include <linux/vmalloc.h> +#include <net/pkt_cls.h> +#include <net/pie.h> + +/* Flow Queue PIE + * + * Principles: + * - Packets are classified on flows. + * - This is a Stochastic model (as we use a hash, several flows might + * be hashed to the same slot) + * - Each flow has a PIE managed queue. + * - Flows are linked onto two (Round Robin) lists, + * so that new flows have priority on old ones. + * - For a given flow, packets are not reordered. + * - Drops during enqueue only. + * - ECN capability is off by default. + * - ECN threshold (if ECN is enabled) is at 10% by default. + * - Uses timestamps to calculate queue delay by default. + */ + +/** + * struct fq_pie_flow - contains data for each flow + * @vars: pie vars associated with the flow + * @deficit: number of remaining byte credits + * @backlog: size of data in the flow + * @qlen: number of packets in the flow + * @flowchain: flowchain for the flow + * @head: first packet in the flow + * @tail: last packet in the flow + */ +struct fq_pie_flow { + struct pie_vars vars; + s32 deficit; + u32 backlog; + u32 qlen; + struct list_head flowchain; + struct sk_buff *head; + struct sk_buff *tail; +}; + +struct fq_pie_sched_data { + struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; + struct fq_pie_flow *flows; + struct Qdisc *sch; + struct list_head old_flows; + struct list_head new_flows; + struct pie_params p_params; + u32 ecn_prob; + u32 flows_cnt; + u32 flows_cursor; + u32 quantum; + u32 memory_limit; + u32 new_flow_count; + u32 memory_usage; + u32 overmemory; + struct pie_stats stats; + struct timer_list adapt_timer; +}; + +static unsigned int fq_pie_hash(const struct fq_pie_sched_data *q, + struct sk_buff *skb) +{ + return reciprocal_scale(skb_get_hash(skb), q->flows_cnt); +} + +static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct tcf_proto *filter; + struct tcf_result res; + int result; + + if (TC_H_MAJ(skb->priority) == sch->handle && + TC_H_MIN(skb->priority) > 0 && + TC_H_MIN(skb->priority) <= q->flows_cnt) + return TC_H_MIN(skb->priority); + + filter = rcu_dereference_bh(q->filter_list); + if (!filter) + return fq_pie_hash(q, skb) + 1; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + result = tcf_classify(skb, NULL, filter, &res, false); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; + case TC_ACT_SHOT: + return 0; + } +#endif + if (TC_H_MIN(res.classid) <= q->flows_cnt) + return TC_H_MIN(res.classid); + } + return 0; +} + +/* add skb to flow queue (tail add) */ +static inline void flow_queue_add(struct fq_pie_flow *flow, + struct sk_buff *skb) +{ + if (!flow->head) + flow->head = skb; + else + flow->tail->next = skb; + flow->tail = skb; + skb->next = NULL; +} + +static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct fq_pie_flow *sel_flow; + int ret; + u8 memory_limited = false; + u8 enqueue = false; + u32 pkt_len; + u32 idx; + + /* Classifies packet into corresponding flow */ + idx = fq_pie_classify(skb, sch, &ret); + if (idx == 0) { + if (ret & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return ret; + } + idx--; + + sel_flow = &q->flows[idx]; + /* Checks whether adding a new packet would exceed memory limit */ + get_pie_cb(skb)->mem_usage = skb->truesize; + memory_limited = q->memory_usage > q->memory_limit + skb->truesize; + + /* Checks if the qdisc is full */ + if (unlikely(qdisc_qlen(sch) >= sch->limit)) { + q->stats.overlimit++; + goto out; + } else if (unlikely(memory_limited)) { + q->overmemory++; + } + + reason = SKB_DROP_REASON_QDISC_CONGESTED; + + if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars, + sel_flow->backlog, skb->len)) { + enqueue = true; + } else if (q->p_params.ecn && + sel_flow->vars.prob <= (MAX_PROB / 100) * q->ecn_prob && + INET_ECN_set_ce(skb)) { + /* If packet is ecn capable, mark it if drop probability + * is lower than the parameter ecn_prob, else drop it. + */ + q->stats.ecn_mark++; + enqueue = true; + } + if (enqueue) { + /* Set enqueue time only when dq_rate_estimator is disabled. */ + if (!q->p_params.dq_rate_estimator) + pie_set_enqueue_time(skb); + + pkt_len = qdisc_pkt_len(skb); + q->stats.packets_in++; + q->memory_usage += skb->truesize; + sch->qstats.backlog += pkt_len; + sch->q.qlen++; + flow_queue_add(sel_flow, skb); + if (list_empty(&sel_flow->flowchain)) { + list_add_tail(&sel_flow->flowchain, &q->new_flows); + q->new_flow_count++; + sel_flow->deficit = q->quantum; + sel_flow->qlen = 0; + sel_flow->backlog = 0; + } + sel_flow->qlen++; + sel_flow->backlog += pkt_len; + return NET_XMIT_SUCCESS; + } +out: + q->stats.dropped++; + sel_flow->vars.accu_prob = 0; + qdisc_drop_reason(skb, sch, to_free, reason); + return NET_XMIT_CN; +} + +static const struct netlink_range_validation fq_pie_q_range = { + .min = 1, + .max = 1 << 20, +}; + +static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { + [TCA_FQ_PIE_LIMIT] = {.type = NLA_U32}, + [TCA_FQ_PIE_FLOWS] = {.type = NLA_U32}, + [TCA_FQ_PIE_TARGET] = {.type = NLA_U32}, + [TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32}, + [TCA_FQ_PIE_ALPHA] = {.type = NLA_U32}, + [TCA_FQ_PIE_BETA] = {.type = NLA_U32}, + [TCA_FQ_PIE_QUANTUM] = + NLA_POLICY_FULL_RANGE(NLA_U32, &fq_pie_q_range), + [TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32}, + [TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32}, + [TCA_FQ_PIE_ECN] = {.type = NLA_U32}, + [TCA_FQ_PIE_BYTEMODE] = {.type = NLA_U32}, + [TCA_FQ_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, +}; + +static inline struct sk_buff *dequeue_head(struct fq_pie_flow *flow) +{ + struct sk_buff *skb = flow->head; + + flow->head = skb->next; + skb->next = NULL; + return skb; +} + +static struct sk_buff *fq_pie_qdisc_dequeue(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = NULL; + struct fq_pie_flow *flow; + struct list_head *head; + u32 pkt_len; + +begin: + head = &q->new_flows; + if (list_empty(head)) { + head = &q->old_flows; + if (list_empty(head)) + return NULL; + } + + flow = list_first_entry(head, struct fq_pie_flow, flowchain); + /* Flow has exhausted all its credits */ + if (flow->deficit <= 0) { + flow->deficit += q->quantum; + list_move_tail(&flow->flowchain, &q->old_flows); + goto begin; + } + + if (flow->head) { + skb = dequeue_head(flow); + pkt_len = qdisc_pkt_len(skb); + sch->qstats.backlog -= pkt_len; + sch->q.qlen--; + qdisc_bstats_update(sch, skb); + } + + if (!skb) { + /* force a pass through old_flows to prevent starvation */ + if (head == &q->new_flows && !list_empty(&q->old_flows)) + list_move_tail(&flow->flowchain, &q->old_flows); + else + list_del_init(&flow->flowchain); + goto begin; + } + + flow->qlen--; + flow->deficit -= pkt_len; + flow->backlog -= pkt_len; + q->memory_usage -= get_pie_cb(skb)->mem_usage; + pie_process_dequeue(skb, &q->p_params, &flow->vars, flow->backlog); + return skb; +} + +static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + unsigned int dropped_pkts = 0, dropped_bytes = 0; + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_FQ_PIE_MAX + 1]; + int err; + + err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack); + if (err < 0) + return err; + + sch_tree_lock(sch); + if (tb[TCA_FQ_PIE_LIMIT]) { + u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]); + + WRITE_ONCE(q->p_params.limit, limit); + WRITE_ONCE(sch->limit, limit); + } + if (tb[TCA_FQ_PIE_FLOWS]) { + if (q->flows) { + NL_SET_ERR_MSG_MOD(extack, + "Number of flows cannot be changed"); + goto flow_error; + } + q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]); + if (!q->flows_cnt || q->flows_cnt > 65536) { + NL_SET_ERR_MSG_MOD(extack, + "Number of flows must range in [1..65536]"); + goto flow_error; + } + } + + /* convert from microseconds to pschedtime */ + if (tb[TCA_FQ_PIE_TARGET]) { + /* target is in us */ + u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]); + + /* convert to pschedtime */ + WRITE_ONCE(q->p_params.target, + PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC)); + } + + /* tupdate is in jiffies */ + if (tb[TCA_FQ_PIE_TUPDATE]) + WRITE_ONCE(q->p_params.tupdate, + usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE]))); + + if (tb[TCA_FQ_PIE_ALPHA]) + WRITE_ONCE(q->p_params.alpha, + nla_get_u32(tb[TCA_FQ_PIE_ALPHA])); + + if (tb[TCA_FQ_PIE_BETA]) + WRITE_ONCE(q->p_params.beta, + nla_get_u32(tb[TCA_FQ_PIE_BETA])); + + if (tb[TCA_FQ_PIE_QUANTUM]) + WRITE_ONCE(q->quantum, nla_get_u32(tb[TCA_FQ_PIE_QUANTUM])); + + if (tb[TCA_FQ_PIE_MEMORY_LIMIT]) + WRITE_ONCE(q->memory_limit, + nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT])); + + if (tb[TCA_FQ_PIE_ECN_PROB]) + WRITE_ONCE(q->ecn_prob, + nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB])); + + if (tb[TCA_FQ_PIE_ECN]) + WRITE_ONCE(q->p_params.ecn, + nla_get_u32(tb[TCA_FQ_PIE_ECN])); + + if (tb[TCA_FQ_PIE_BYTEMODE]) + WRITE_ONCE(q->p_params.bytemode, + nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE])); + + if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]) + WRITE_ONCE(q->p_params.dq_rate_estimator, + nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR])); + + /* Drop excess packets if new limit is lower */ + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); + + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); + rtnl_kfree_skbs(skb, skb); + } + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); + + sch_tree_unlock(sch); + return 0; + +flow_error: + sch_tree_unlock(sch); + return -EINVAL; +} + +static void fq_pie_timer(struct timer_list *t) +{ + struct fq_pie_sched_data *q = timer_container_of(q, t, adapt_timer); + unsigned long next, tupdate; + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; /* to lock qdisc for probability calculations */ + int max_cnt, i; + + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spin_lock(root_lock); + + /* Limit this expensive loop to 2048 flows per round. */ + max_cnt = min_t(int, q->flows_cnt - q->flows_cursor, 2048); + for (i = 0; i < max_cnt; i++) { + pie_calculate_probability(&q->p_params, + &q->flows[q->flows_cursor].vars, + q->flows[q->flows_cursor].backlog); + q->flows_cursor++; + } + + tupdate = q->p_params.tupdate; + next = 0; + if (q->flows_cursor >= q->flows_cnt) { + q->flows_cursor = 0; + next = tupdate; + } + if (tupdate) + mod_timer(&q->adapt_timer, jiffies + next); + spin_unlock(root_lock); + rcu_read_unlock(); +} + +static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + int err; + u32 idx; + + pie_params_init(&q->p_params); + sch->limit = 10 * 1024; + q->p_params.limit = sch->limit; + q->quantum = psched_mtu(qdisc_dev(sch)); + q->sch = sch; + q->ecn_prob = 10; + q->flows_cnt = 1024; + q->memory_limit = SZ_32M; + + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + timer_setup(&q->adapt_timer, fq_pie_timer, 0); + + if (opt) { + err = fq_pie_change(sch, opt, extack); + + if (err) + return err; + } + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + goto init_failure; + + q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_pie_flow), + GFP_KERNEL); + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } + for (idx = 0; idx < q->flows_cnt; idx++) { + struct fq_pie_flow *flow = q->flows + idx; + + INIT_LIST_HEAD(&flow->flowchain); + pie_vars_init(&flow->vars); + } + + mod_timer(&q->adapt_timer, jiffies + HZ / 2); + + return 0; + +init_failure: + q->flows_cnt = 0; + + return err; +} + +static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (!opts) + return -EMSGSIZE; + + /* convert target from pschedtime to us */ + if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_FQ_PIE_FLOWS, READ_ONCE(q->flows_cnt)) || + nla_put_u32(skb, TCA_FQ_PIE_TARGET, + ((u32)PSCHED_TICKS2NS(READ_ONCE(q->p_params.target))) / + NSEC_PER_USEC) || + nla_put_u32(skb, TCA_FQ_PIE_TUPDATE, + jiffies_to_usecs(READ_ONCE(q->p_params.tupdate))) || + nla_put_u32(skb, TCA_FQ_PIE_ALPHA, READ_ONCE(q->p_params.alpha)) || + nla_put_u32(skb, TCA_FQ_PIE_BETA, READ_ONCE(q->p_params.beta)) || + nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, READ_ONCE(q->quantum)) || + nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, + READ_ONCE(q->memory_limit)) || + nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, READ_ONCE(q->ecn_prob)) || + nla_put_u32(skb, TCA_FQ_PIE_ECN, READ_ONCE(q->p_params.ecn)) || + nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, READ_ONCE(q->p_params.bytemode)) || + nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR, + READ_ONCE(q->p_params.dq_rate_estimator))) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct tc_fq_pie_xstats st = { + .packets_in = q->stats.packets_in, + .overlimit = q->stats.overlimit, + .overmemory = q->overmemory, + .dropped = q->stats.dropped, + .ecn_mark = q->stats.ecn_mark, + .new_flow_count = q->new_flow_count, + .memory_usage = q->memory_usage, + }; + struct list_head *pos; + + sch_tree_lock(sch); + list_for_each(pos, &q->new_flows) + st.new_flows_len++; + + list_for_each(pos, &q->old_flows) + st.old_flows_len++; + sch_tree_unlock(sch); + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static void fq_pie_reset(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + u32 idx; + + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + for (idx = 0; idx < q->flows_cnt; idx++) { + struct fq_pie_flow *flow = q->flows + idx; + + /* Removes all packets from flow */ + rtnl_kfree_skbs(flow->head, flow->tail); + flow->head = NULL; + + INIT_LIST_HEAD(&flow->flowchain); + pie_vars_init(&flow->vars); + } +} + +static void fq_pie_destroy(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + + tcf_block_put(q->block); + q->p_params.tupdate = 0; + timer_delete_sync(&q->adapt_timer); + kvfree(q->flows); +} + +static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = { + .id = "fq_pie", + .priv_size = sizeof(struct fq_pie_sched_data), + .enqueue = fq_pie_qdisc_enqueue, + .dequeue = fq_pie_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = fq_pie_init, + .destroy = fq_pie_destroy, + .reset = fq_pie_reset, + .change = fq_pie_change, + .dump = fq_pie_dump, + .dump_stats = fq_pie_dump_stats, + .owner = THIS_MODULE, +}; +MODULE_ALIAS_NET_SCH("fq_pie"); + +static int __init fq_pie_module_init(void) +{ + return register_qdisc(&fq_pie_qdisc_ops); +} + +static void __exit fq_pie_module_exit(void) +{ + unregister_qdisc(&fq_pie_qdisc_ops); +} + +module_init(fq_pie_module_init); +module_exit(fq_pie_module_exit); + +MODULE_DESCRIPTION("Flow Queue Proportional Integral controller Enhanced (FQ-PIE)"); +MODULE_AUTHOR("Mohit P. Tahiliani"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c new file mode 100644 index 000000000000..d1d87dce7f3f --- /dev/null +++ b/net/sched/sch_frag.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +#include <linux/if_vlan.h> +#include <net/netlink.h> +#include <net/sch_generic.h> +#include <net/pkt_sched.h> +#include <net/dst.h> +#include <net/ip.h> +#include <net/ip6_fib.h> + +struct sch_frag_data { + unsigned long dst; + struct qdisc_skb_cb cb; + __be16 inner_protocol; + u16 vlan_tci; + __be16 vlan_proto; + unsigned int l2_len; + u8 l2_data[VLAN_ETH_HLEN]; + int (*xmit)(struct sk_buff *skb); + local_lock_t bh_lock; +}; + +static DEFINE_PER_CPU(struct sch_frag_data, sch_frag_data_storage) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; + +static int sch_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct sch_frag_data *data = this_cpu_ptr(&sch_frag_data_storage); + + lockdep_assert_held(&data->bh_lock); + if (skb_cow_head(skb, data->l2_len) < 0) { + kfree_skb(skb); + return -ENOMEM; + } + + __skb_dst_copy(skb, data->dst); + *qdisc_skb_cb(skb) = data->cb; + skb->inner_protocol = data->inner_protocol; + if (data->vlan_tci & VLAN_CFI_MASK) + __vlan_hwaccel_put_tag(skb, data->vlan_proto, + data->vlan_tci & ~VLAN_CFI_MASK); + else + __vlan_hwaccel_clear_tag(skb); + + /* Reconstruct the MAC header. */ + skb_push(skb, data->l2_len); + memcpy(skb->data, &data->l2_data, data->l2_len); + skb_postpush_rcsum(skb, skb->data, data->l2_len); + skb_reset_mac_header(skb); + + return data->xmit(skb); +} + +static void sch_frag_prepare_frag(struct sk_buff *skb, + int (*xmit)(struct sk_buff *skb)) +{ + unsigned int hlen = skb_network_offset(skb); + struct sch_frag_data *data; + + data = this_cpu_ptr(&sch_frag_data_storage); + data->dst = skb->_skb_refdst; + data->cb = *qdisc_skb_cb(skb); + data->xmit = xmit; + data->inner_protocol = skb->inner_protocol; + if (skb_vlan_tag_present(skb)) + data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK; + else + data->vlan_tci = 0; + data->vlan_proto = skb->vlan_proto; + data->l2_len = hlen; + memcpy(&data->l2_data, skb->data, hlen); + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + skb_pull(skb, hlen); +} + +static unsigned int +sch_frag_dst_get_mtu(const struct dst_entry *dst) +{ + return dst->dev->mtu; +} + +static struct dst_ops sch_frag_dst_ops = { + .family = AF_UNSPEC, + .mtu = sch_frag_dst_get_mtu, +}; + +static int sch_fragment(struct net *net, struct sk_buff *skb, + u16 mru, int (*xmit)(struct sk_buff *skb)) +{ + int ret = -1; + + if (skb_network_offset(skb) > VLAN_ETH_HLEN) { + net_warn_ratelimited("L2 header too long to fragment\n"); + goto err; + } + + if (skb_protocol(skb, true) == htons(ETH_P_IP)) { + struct rtable sch_frag_rt = { 0 }; + unsigned long orig_dst; + + local_lock_nested_bh(&sch_frag_data_storage.bh_lock); + sch_frag_prepare_frag(skb, xmit); + dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, + DST_OBSOLETE_NONE, DST_NOCOUNT); + sch_frag_rt.dst.dev = skb->dev; + + orig_dst = skb->_skb_refdst; + skb_dst_set_noref(skb, &sch_frag_rt.dst); + IPCB(skb)->frag_max_size = mru; + + ret = ip_do_fragment(net, skb->sk, skb, sch_frag_xmit); + local_unlock_nested_bh(&sch_frag_data_storage.bh_lock); + refdst_drop(orig_dst); + } else if (skb_protocol(skb, true) == htons(ETH_P_IPV6)) { + unsigned long orig_dst; + struct rt6_info sch_frag_rt; + + local_lock_nested_bh(&sch_frag_data_storage.bh_lock); + sch_frag_prepare_frag(skb, xmit); + memset(&sch_frag_rt, 0, sizeof(sch_frag_rt)); + dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, + DST_OBSOLETE_NONE, DST_NOCOUNT); + sch_frag_rt.dst.dev = skb->dev; + + orig_dst = skb->_skb_refdst; + skb_dst_set_noref(skb, &sch_frag_rt.dst); + IP6CB(skb)->frag_max_size = mru; + + ret = ipv6_stub->ipv6_fragment(net, skb->sk, skb, + sch_frag_xmit); + local_unlock_nested_bh(&sch_frag_data_storage.bh_lock); + refdst_drop(orig_dst); + } else { + net_warn_ratelimited("Fail frag %s: eth=%x, MRU=%d, MTU=%d\n", + netdev_name(skb->dev), + ntohs(skb_protocol(skb, true)), mru, + skb->dev->mtu); + goto err; + } + + return ret; +err: + kfree_skb(skb); + return ret; +} + +int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)) +{ + u16 mru = tc_skb_cb(skb)->mru; + int err; + + if (mru && skb->len > mru + skb->dev->hard_header_len) + err = sch_fragment(dev_net(skb->dev), skb, mru, xmit); + else + err = xmit(skb); + + return err; +} +EXPORT_SYMBOL_GPL(sch_frag_xmit_hook); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 57ba406f1437..852e603c1755 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_generic.c Generic packet scheduler routines. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Jamal Hadi Salim, <hadi@cyberus.ca> 990601 * - Ingress support @@ -26,14 +22,42 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/if_vlan.h> +#include <linux/skb_array.h> +#include <linux/if_macvlan.h> +#include <linux/bpf.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> +#include <net/hotdata.h> +#include <trace/events/qdisc.h> +#include <trace/events/net.h> +#include <net/xfrm.h> /* Qdisc to use by default */ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; EXPORT_SYMBOL(default_qdisc_ops); +static void qdisc_maybe_clear_missed(struct Qdisc *q, + const struct netdev_queue *txq) +{ + clear_bit(__QDISC_STATE_MISSED, &q->state); + + /* Make sure the below netif_xmit_frozen_or_stopped() + * checking happens after clearing STATE_MISSED. + */ + smp_mb__after_atomic(); + + /* Checking netif_xmit_frozen_or_stopped() again to + * make sure STATE_MISSED is set if the STATE_MISSED + * set by netif_tx_wake_queue()'s rescheduling of + * net_tx_action() is cleared by the above clear_bit(). + */ + if (!netif_xmit_frozen_or_stopped(txq)) + set_bit(__QDISC_STATE_MISSED, &q->state); + else + set_bit(__QDISC_STATE_DRAINING, &q->state); +} + /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with @@ -45,23 +69,121 @@ EXPORT_SYMBOL(default_qdisc_ops); * - updates to tree and tree walking are only done under the rtnl mutex. */ -static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) +#define SKB_XOFF_MAGIC ((struct sk_buff *)1UL) + +static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) { - q->gso_skb = skb; - q->qstats.requeues++; - qdisc_qstats_backlog_inc(q, skb); - q->q.qlen++; /* it's still part of the queue */ - __netif_schedule(q); + const struct netdev_queue *txq = q->dev_queue; + spinlock_t *lock = NULL; + struct sk_buff *skb; - return 0; + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); + } + + skb = skb_peek(&q->skb_bad_txq); + if (skb) { + /* check the reason of requeuing without tx lock first */ + txq = skb_get_tx_queue(txq->dev, skb); + if (!netif_xmit_frozen_or_stopped(txq)) { + skb = __skb_dequeue(&q->skb_bad_txq); + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_dec(q, skb); + qdisc_qstats_cpu_qlen_dec(q); + } else { + qdisc_qstats_backlog_dec(q, skb); + q->q.qlen--; + } + } else { + skb = SKB_XOFF_MAGIC; + qdisc_maybe_clear_missed(q, txq); + } + } + + if (lock) + spin_unlock(lock); + + return skb; +} + +static inline struct sk_buff *qdisc_dequeue_skb_bad_txq(struct Qdisc *q) +{ + struct sk_buff *skb = skb_peek(&q->skb_bad_txq); + + if (unlikely(skb)) + skb = __skb_dequeue_bad_txq(q); + + return skb; +} + +static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, + struct sk_buff *skb) +{ + spinlock_t *lock = NULL; + + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); + } + + __skb_queue_tail(&q->skb_bad_txq, skb); + + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_inc(q, skb); + qdisc_qstats_cpu_qlen_inc(q); + } else { + qdisc_qstats_backlog_inc(q, skb); + q->q.qlen++; + } + + if (lock) + spin_unlock(lock); +} + +static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) +{ + spinlock_t *lock = NULL; + + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); + } + + while (skb) { + struct sk_buff *next = skb->next; + + __skb_queue_tail(&q->gso_skb, skb); + + /* it's still part of the queue */ + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_requeues_inc(q); + qdisc_qstats_cpu_backlog_inc(q, skb); + qdisc_qstats_cpu_qlen_inc(q); + } else { + q->qstats.requeues++; + qdisc_qstats_backlog_inc(q, skb); + q->q.qlen++; + } + + skb = next; + } + + if (lock) { + spin_unlock(lock); + set_bit(__QDISC_STATE_MISSED, &q->state); + } else { + __netif_schedule(q); + } } static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, - int *packets) + int *packets, int budget) { int bytelimit = qdisc_avail_bulklimit(txq) - skb->len; + int cnt = 0; while (bytelimit > 0) { struct sk_buff *nskb = q->dequeue(q); @@ -72,9 +194,11 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, bytelimit -= nskb->len; /* covers GSO len */ skb->next = nskb; skb = nskb; - (*packets)++; /* GSO counts as one pkt */ + if (++cnt >= budget) + break; } - skb->next = NULL; + (*packets) += cnt; + skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure @@ -93,117 +217,158 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, if (!nskb) break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { - q->skb_bad_txq = nskb; - qdisc_qstats_backlog_inc(q, nskb); - q->q.qlen++; + qdisc_enqueue_skb_bad_txq(q, nskb); break; } skb->next = nskb; skb = nskb; } while (++cnt < 8); (*packets) += cnt; - skb->next = NULL; + skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). * A requeued skb (via q->gso_skb) can also be a SKB list. */ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, - int *packets) + int *packets, int budget) { - struct sk_buff *skb = q->gso_skb; const struct netdev_queue *txq = q->dev_queue; + struct sk_buff *skb = NULL; *packets = 1; - if (unlikely(skb)) { + if (unlikely(!skb_queue_empty(&q->gso_skb))) { + spinlock_t *lock = NULL; + + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); + } + + skb = skb_peek(&q->gso_skb); + + /* skb may be null if another cpu pulls gso_skb off in between + * empty check and lock. + */ + if (!skb) { + if (lock) + spin_unlock(lock); + goto validate; + } + /* skb in gso_skb were already validated */ *validate = false; + if (xfrm_offload(skb)) + *validate = true; /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { - q->gso_skb = NULL; - qdisc_qstats_backlog_dec(q, skb); - q->q.qlen--; - } else + skb = __skb_dequeue(&q->gso_skb); + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_dec(q, skb); + qdisc_qstats_cpu_qlen_dec(q); + } else { + qdisc_qstats_backlog_dec(q, skb); + q->q.qlen--; + } + } else { skb = NULL; - return skb; + qdisc_maybe_clear_missed(q, txq); + } + if (lock) + spin_unlock(lock); + goto trace; } +validate: *validate = true; - skb = q->skb_bad_txq; + + if ((q->flags & TCQ_F_ONETXQUEUE) && + netif_xmit_frozen_or_stopped(txq)) { + qdisc_maybe_clear_missed(q, txq); + return skb; + } + + skb = qdisc_dequeue_skb_bad_txq(q); if (unlikely(skb)) { - /* check the reason of requeuing without tx lock first */ - txq = skb_get_tx_queue(txq->dev, skb); - if (!netif_xmit_frozen_or_stopped(txq)) { - q->skb_bad_txq = NULL; - qdisc_qstats_backlog_dec(q, skb); - q->q.qlen--; - goto bulk; - } - return NULL; + if (skb == SKB_XOFF_MAGIC) + return NULL; + goto bulk; } - if (!(q->flags & TCQ_F_ONETXQUEUE) || - !netif_xmit_frozen_or_stopped(txq)) - skb = q->dequeue(q); + skb = q->dequeue(q); if (skb) { bulk: if (qdisc_may_bulk(q)) - try_bulk_dequeue_skb(q, skb, txq, packets); + try_bulk_dequeue_skb(q, skb, txq, packets, budget); else try_bulk_dequeue_skb_slow(q, skb, packets); } +trace: + trace_qdisc_dequeue(q, txq, *packets, skb); return skb; } /* * Transmit possibly several skbs, and handle the return status as - * required. Owning running seqcount bit guarantees that - * only one CPU can execute this function. + * required. Owning qdisc running bit guarantees that only one CPU + * can execute this function. * * Returns to the caller: - * 0 - queue is empty or throttled. - * >0 - queue is not empty. + * false - hardware queue frozen backoff + * true - feel free to send more pkts */ -int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, - struct net_device *dev, struct netdev_queue *txq, - spinlock_t *root_lock, bool validate) +bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, struct netdev_queue *txq, + spinlock_t *root_lock, bool validate) { int ret = NETDEV_TX_BUSY; + bool again = false; /* And release qdisc */ - spin_unlock(root_lock); + if (root_lock) + spin_unlock(root_lock); /* Note that we validate skb (GSO, checksum, ...) outside of locks */ if (validate) - skb = validate_xmit_skb_list(skb, dev); + skb = validate_xmit_skb_list(skb, dev, &again); + +#ifdef CONFIG_XFRM_OFFLOAD + if (unlikely(again)) { + if (root_lock) + spin_lock(root_lock); + + dev_requeue_skb(skb, q); + return false; + } +#endif if (likely(skb)) { HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); + else + qdisc_maybe_clear_missed(q, txq); HARD_TX_UNLOCK(dev, txq); } else { - spin_lock(root_lock); - return qdisc_qlen(q); + if (root_lock) + spin_lock(root_lock); + return true; } - spin_lock(root_lock); - if (dev_xmit_complete(ret)) { - /* Driver sent out skb successfully or skb was consumed */ - ret = qdisc_qlen(q); - } else { + if (root_lock) + spin_lock(root_lock); + + if (!dev_xmit_complete(ret)) { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely(ret != NETDEV_TX_BUSY)) net_warn_ratelimited("BUG %s code %d qlen %d\n", dev->name, ret, q->q.qlen); - ret = dev_requeue_skb(skb, q); + dev_requeue_skb(skb, q); + return false; } - if (ret && netif_xmit_frozen_or_stopped(txq)) - ret = 0; - - return ret; + return true; } /* @@ -225,20 +390,22 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, * >0 - queue is not empty. * */ -static inline int qdisc_restart(struct Qdisc *q, int *packets) +static inline bool qdisc_restart(struct Qdisc *q, int *packets, int budget) { + spinlock_t *root_lock = NULL; struct netdev_queue *txq; struct net_device *dev; - spinlock_t *root_lock; struct sk_buff *skb; bool validate; /* Dequeue packet */ - skb = dequeue_skb(q, &validate, packets); + skb = dequeue_skb(q, &validate, packets, budget); if (unlikely(!skb)) - return 0; + return false; + + if (!(q->flags & TCQ_F_NOLOCK)) + root_lock = qdisc_lock(q); - root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = skb_get_tx_queue(dev, skb); @@ -247,35 +414,30 @@ static inline int qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = dev_tx_weight; + int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; - while (qdisc_restart(q, &packets)) { - /* - * Ordered by possible occurrence: Postpone processing if - * 1. we've exceeded packet quota - * 2. another process needs the CPU; - */ + while (qdisc_restart(q, &packets, quota)) { quota -= packets; - if (quota <= 0 || need_resched()) { - __netif_schedule(q); + if (quota <= 0) { + if (q->flags & TCQ_F_NOLOCK) + set_bit(__QDISC_STATE_MISSED, &q->state); + else + __netif_schedule(q); + break; } } - - qdisc_run_end(q); } unsigned long dev_trans_start(struct net_device *dev) { - unsigned long val, res; + unsigned long res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start); + unsigned long val; unsigned int i; - if (is_vlan_dev(dev)) - dev = vlan_dev_real_dev(dev); - res = netdev_get_tx_queue(dev, 0)->trans_start; for (i = 1; i < dev->num_tx_queues; i++) { - val = netdev_get_tx_queue(dev, i)->trans_start; + val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start); if (val && time_after(val, res)) res = val; } @@ -284,70 +446,133 @@ unsigned long dev_trans_start(struct net_device *dev) } EXPORT_SYMBOL(dev_trans_start); -static void dev_watchdog(unsigned long arg) +static void netif_freeze_queues(struct net_device *dev) +{ + unsigned int i; + int cpu; + + cpu = smp_processor_id(); + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + /* We are the only thread of execution doing a + * freeze, but we have to grab the _xmit_lock in + * order to synchronize with threads which are in + * the ->hard_start_xmit() handler and already + * checked the frozen bit. + */ + __netif_tx_lock(txq, cpu); + set_bit(__QUEUE_STATE_FROZEN, &txq->state); + __netif_tx_unlock(txq); + } +} + +void netif_tx_lock(struct net_device *dev) +{ + spin_lock(&dev->tx_global_lock); + netif_freeze_queues(dev); +} +EXPORT_SYMBOL(netif_tx_lock); + +static void netif_unfreeze_queues(struct net_device *dev) +{ + unsigned int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + /* No need to grab the _xmit_lock here. If the + * queue is not stopped for another reason, we + * force a schedule. + */ + clear_bit(__QUEUE_STATE_FROZEN, &txq->state); + netif_schedule_queue(txq); + } +} + +void netif_tx_unlock(struct net_device *dev) +{ + netif_unfreeze_queues(dev); + spin_unlock(&dev->tx_global_lock); +} +EXPORT_SYMBOL(netif_tx_unlock); + +static void dev_watchdog(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; + struct net_device *dev = timer_container_of(dev, t, watchdog_timer); + bool release = true; - netif_tx_lock(dev); + spin_lock(&dev->tx_global_lock); if (!qdisc_tx_is_noop(dev)) { if (netif_device_present(dev) && netif_running(dev) && netif_carrier_ok(dev)) { - int some_queue_timedout = 0; + unsigned int timedout_ms = 0; unsigned int i; unsigned long trans_start; + unsigned long oldest_start = jiffies; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); - trans_start = txq->trans_start; - if (netif_xmit_stopped(txq) && - time_after(jiffies, (trans_start + - dev->watchdog_timeo))) { - some_queue_timedout = 1; - txq->trans_timeout++; + if (!netif_xmit_stopped(txq)) + continue; + + /* Paired with WRITE_ONCE() + smp_mb...() in + * netdev_tx_sent_queue() and netif_tx_stop_queue(). + */ + smp_mb(); + trans_start = READ_ONCE(txq->trans_start); + + if (time_after(jiffies, trans_start + dev->watchdog_timeo)) { + timedout_ms = jiffies_to_msecs(jiffies - trans_start); + atomic_long_inc(&txq->trans_timeout); break; } + if (time_after(oldest_start, trans_start)) + oldest_start = trans_start; } - if (some_queue_timedout) { - WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", - dev->name, netdev_drivername(dev), i); - dev->netdev_ops->ndo_tx_timeout(dev); + if (unlikely(timedout_ms)) { + trace_net_dev_xmit_timeout(dev, i); + netdev_crit(dev, "NETDEV WATCHDOG: CPU: %d: transmit queue %u timed out %u ms\n", + raw_smp_processor_id(), + i, timedout_ms); + netif_freeze_queues(dev); + dev->netdev_ops->ndo_tx_timeout(dev, i); + netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, - round_jiffies(jiffies + + round_jiffies(oldest_start + dev->watchdog_timeo))) - dev_hold(dev); + release = false; } } - netif_tx_unlock(dev); + spin_unlock(&dev->tx_global_lock); - dev_put(dev); + if (release) + netdev_put(dev, &dev->watchdog_dev_tracker); } -void __netdev_watchdog_up(struct net_device *dev) +void netdev_watchdog_up(struct net_device *dev) { - if (dev->netdev_ops->ndo_tx_timeout) { - if (dev->watchdog_timeo <= 0) - dev->watchdog_timeo = 5*HZ; - if (!mod_timer(&dev->watchdog_timer, - round_jiffies(jiffies + dev->watchdog_timeo))) - dev_hold(dev); - } -} - -static void dev_watchdog_up(struct net_device *dev) -{ - __netdev_watchdog_up(dev); + if (!dev->netdev_ops->ndo_tx_timeout) + return; + if (dev->watchdog_timeo <= 0) + dev->watchdog_timeo = 5*HZ; + if (!mod_timer(&dev->watchdog_timer, + round_jiffies(jiffies + dev->watchdog_timeo))) + netdev_hold(dev, &dev->watchdog_dev_tracker, + GFP_ATOMIC); } +EXPORT_SYMBOL_GPL(netdev_watchdog_up); -static void dev_watchdog_down(struct net_device *dev) +static void netdev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); - if (del_timer(&dev->watchdog_timer)) - dev_put(dev); + if (timer_delete(&dev->watchdog_timer)) + netdev_put(dev, &dev->watchdog_dev_tracker); netif_tx_unlock_bh(dev); } @@ -355,17 +580,17 @@ static void dev_watchdog_down(struct net_device *dev) * netif_carrier_on - set carrier * @dev: network device * - * Device has detected that carrier. + * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; - atomic_inc(&dev->carrier_changes); + atomic_inc(&dev->carrier_up_count); linkwatch_fire_event(dev); if (netif_running(dev)) - __netdev_watchdog_up(dev); + netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_carrier_on); @@ -381,12 +606,30 @@ void netif_carrier_off(struct net_device *dev) if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; - atomic_inc(&dev->carrier_changes); + atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } } EXPORT_SYMBOL(netif_carrier_off); +/** + * netif_carrier_event - report carrier state event + * @dev: network device + * + * Device has detected a carrier event but the carrier state wasn't changed. + * Use in drivers when querying carrier state asynchronously, to avoid missing + * events (link flaps) if link recovers before it's queried. + */ +void netif_carrier_event(struct net_device *dev) +{ + if (dev->reg_state == NETREG_UNINITIALIZED) + return; + atomic_inc(&dev->carrier_up_count); + atomic_inc(&dev->carrier_down_count); + linkwatch_fire_event(dev); +} +EXPORT_SYMBOL_GPL(netif_carrier_event); + /* "NOOP" scheduler: the best scheduler, recommended for all interfaces under all circumstances. It is difficult to invent anything faster or cheaper. @@ -395,6 +638,7 @@ EXPORT_SYMBOL(netif_carrier_off); static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { + dev_core_stats_tx_dropped_inc(skb->dev); __qdisc_drop(skb, to_free); return NET_XMIT_CN; } @@ -414,8 +658,8 @@ struct Qdisc_ops noop_qdisc_ops __read_mostly = { }; static struct netdev_queue noop_netdev_queue = { - .qdisc = &noop_qdisc, - .qdisc_sleeping = &noop_qdisc, + RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), + RCU_POINTER_INITIALIZER(qdisc_sleeping, &noop_qdisc), }; struct Qdisc noop_qdisc = { @@ -425,12 +669,23 @@ struct Qdisc noop_qdisc = { .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, - .running = SEQCNT_ZERO(noop_qdisc.running), - .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), + .gso_skb = { + .next = (struct sk_buff *)&noop_qdisc.gso_skb, + .prev = (struct sk_buff *)&noop_qdisc.gso_skb, + .qlen = 0, + .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock), + }, + .skb_bad_txq = { + .next = (struct sk_buff *)&noop_qdisc.skb_bad_txq, + .prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq, + .qlen = 0, + .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), + }, }; EXPORT_SYMBOL(noop_qdisc); -static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt) +static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt, + struct netlink_ext_ack *extack) { /* register_qdisc() assigns a default of noop_enqueue if unset, * but __dev_queue_xmit() treats noqueue only as such @@ -449,9 +704,10 @@ struct Qdisc_ops noqueue_qdisc_ops __read_mostly = { .owner = THIS_MODULE, }; -static const u8 prio2band[TC_PRIO_MAX + 1] = { - 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 +const u8 sch_default_prio2band[TC_PRIO_MAX + 1] = { + 1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1 }; +EXPORT_SYMBOL(sch_default_prio2band); /* 3-band FIFO queue: old style, but should be a bit faster than generic prio+fifo combination. @@ -461,100 +717,133 @@ static const u8 prio2band[TC_PRIO_MAX + 1] = { /* * Private data for a pfifo_fast scheduler containing: - * - queues for the three band - * - bitmap indicating which of the bands contain skbs + * - rings for priority bands */ struct pfifo_fast_priv { - u32 bitmap; - struct qdisc_skb_head q[PFIFO_FAST_BANDS]; + struct skb_array q[PFIFO_FAST_BANDS]; }; -/* - * Convert a bitmap to the first band number where an skb is queued, where: - * bitmap=0 means there are no skbs on any band. - * bitmap=1 means there is an skb on band 0. - * bitmap=7 means there are skbs on all 3 bands, etc. - */ -static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0}; - -static inline struct qdisc_skb_head *band2list(struct pfifo_fast_priv *priv, - int band) +static inline struct skb_array *band2list(struct pfifo_fast_priv *priv, + int band) { - return priv->q + band; + return &priv->q[band]; } static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { - if (qdisc->q.qlen < qdisc_dev(qdisc)->tx_queue_len) { - int band = prio2band[skb->priority & TC_PRIO_MAX]; - struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - struct qdisc_skb_head *list = band2list(priv, band); + int band = sch_default_prio2band[skb->priority & TC_PRIO_MAX]; + struct pfifo_fast_priv *priv = qdisc_priv(qdisc); + struct skb_array *q = band2list(priv, band); + unsigned int pkt_len = qdisc_pkt_len(skb); + int err; - priv->bitmap |= (1 << band); - qdisc->q.qlen++; - return __qdisc_enqueue_tail(skb, qdisc, list); + err = skb_array_produce(q, skb); + + if (unlikely(err)) { + tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_OVERLIMIT); + + if (qdisc_is_percpu_stats(qdisc)) + return qdisc_drop_cpu(skb, qdisc, to_free); + else + return qdisc_drop(skb, qdisc, to_free); } - return qdisc_drop(skb, qdisc, to_free); + qdisc_update_stats_at_enqueue(qdisc, pkt_len); + return NET_XMIT_SUCCESS; } static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - int band = bitmap2band[priv->bitmap]; + struct sk_buff *skb = NULL; + bool need_retry = true; + int band; - if (likely(band >= 0)) { - struct qdisc_skb_head *qh = band2list(priv, band); - struct sk_buff *skb = __qdisc_dequeue_head(qh); +retry: + for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { + struct skb_array *q = band2list(priv, band); - if (likely(skb != NULL)) { - qdisc_qstats_backlog_dec(qdisc, skb); - qdisc_bstats_update(qdisc, skb); - } + if (__skb_array_empty(q)) + continue; + + skb = __skb_array_consume(q); + } + if (likely(skb)) { + qdisc_update_stats_at_dequeue(qdisc, skb); + } else if (need_retry && + READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) { + /* Delay clearing the STATE_MISSED here to reduce + * the overhead of the second spin_trylock() in + * qdisc_run_begin() and __netif_schedule() calling + * in qdisc_run_end(). + */ + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); + + /* Make sure dequeuing happens after clearing + * STATE_MISSED. + */ + smp_mb__after_atomic(); - qdisc->q.qlen--; - if (qh->qlen == 0) - priv->bitmap &= ~(1 << band); + need_retry = false; - return skb; + goto retry; } - return NULL; + return skb; } static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - int band = bitmap2band[priv->bitmap]; + struct sk_buff *skb = NULL; + int band; - if (band >= 0) { - struct qdisc_skb_head *qh = band2list(priv, band); + for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { + struct skb_array *q = band2list(priv, band); - return qh->head; + skb = __skb_array_peek(q); } - return NULL; + return skb; } static void pfifo_fast_reset(struct Qdisc *qdisc) { - int prio; + int i, band; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) - __qdisc_reset_queue(band2list(priv, prio)); + for (band = 0; band < PFIFO_FAST_BANDS; band++) { + struct skb_array *q = band2list(priv, band); + struct sk_buff *skb; - priv->bitmap = 0; - qdisc->qstats.backlog = 0; - qdisc->q.qlen = 0; + /* NULL ring is possible if destroy path is due to a failed + * skb_array_init() in pfifo_fast_init() case. + */ + if (!q->ring.queue) + continue; + + while ((skb = __skb_array_consume(q)) != NULL) + kfree_skb(skb); + } + + if (qdisc_is_percpu_stats(qdisc)) { + for_each_possible_cpu(i) { + struct gnet_stats_queue *q; + + q = per_cpu_ptr(qdisc->cpu_qstats, i); + q->backlog = 0; + q->qlen = 0; + } + } } static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; - memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1); + memcpy(&opt.priomap, sch_default_prio2band, TC_PRIO_MAX + 1); if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; return skb->len; @@ -563,19 +852,68 @@ nla_put_failure: return -1; } -static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) +static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt, + struct netlink_ext_ack *extack) { - int prio; + unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); + int prio; + + /* guard against zero length rings */ + if (!qlen) + return -EINVAL; - for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) - qdisc_skb_head_init(band2list(priv, prio)); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + struct skb_array *q = band2list(priv, prio); + int err; + + err = skb_array_init(q, qlen, GFP_KERNEL); + if (err) + return -ENOMEM; + } /* Can by-pass the queue discipline */ qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } +static void pfifo_fast_destroy(struct Qdisc *sch) +{ + struct pfifo_fast_priv *priv = qdisc_priv(sch); + int prio; + + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + struct skb_array *q = band2list(priv, prio); + + /* NULL ring is possible if destroy path is due to a failed + * skb_array_init() in pfifo_fast_init() case. + */ + if (!q->ring.queue) + continue; + /* Destroy ring but no need to kfree_skb because a call to + * pfifo_fast_reset() has already done that work. + */ + ptr_ring_cleanup(&q->ring, NULL); + } +} + +static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch, + unsigned int new_len) +{ + struct pfifo_fast_priv *priv = qdisc_priv(sch); + struct skb_array *bands[PFIFO_FAST_BANDS]; + int prio; + + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + struct skb_array *q = band2list(priv, prio); + + bands[prio] = q; + } + + return skb_array_resize_multiple_bh(bands, PFIFO_FAST_BANDS, new_len, + GFP_KERNEL); +} + struct Qdisc_ops pfifo_fast_ops __read_mostly = { .id = "pfifo_fast", .priv_size = sizeof(struct pfifo_fast_priv), @@ -583,83 +921,103 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { .dequeue = pfifo_fast_dequeue, .peek = pfifo_fast_peek, .init = pfifo_fast_init, + .destroy = pfifo_fast_destroy, .reset = pfifo_fast_reset, .dump = pfifo_fast_dump, + .change_tx_queue_len = pfifo_fast_change_tx_queue_len, .owner = THIS_MODULE, + .static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS, }; EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, - const struct Qdisc_ops *ops) + const struct Qdisc_ops *ops, + struct netlink_ext_ack *extack) { - void *p; struct Qdisc *sch; - unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size; + unsigned int size = sizeof(*sch) + ops->priv_size; int err = -ENOBUFS; - struct net_device *dev = dev_queue->dev; + struct net_device *dev; + + if (!dev_queue) { + NL_SET_ERR_MSG(extack, "No device queue given"); + err = -EINVAL; + goto errout; + } - p = kzalloc_node(size, GFP_KERNEL, - netdev_queue_numa_node_read(dev_queue)); + dev = dev_queue->dev; + sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); - if (!p) + if (!sch) goto errout; - sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); - /* if we got non aligned memory, ask more and do alignment ourself */ - if (sch != p) { - kfree(p); - p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL, - netdev_queue_numa_node_read(dev_queue)); - if (!p) - goto errout; - sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); - sch->padded = (char *) sch - (char *) p; - } - qdisc_skb_head_init(&sch->q); + __skb_queue_head_init(&sch->gso_skb); + __skb_queue_head_init(&sch->skb_bad_txq); + gnet_stats_basic_sync_init(&sch->bstats); + lockdep_register_key(&sch->root_lock_key); spin_lock_init(&sch->q.lock); + lockdep_set_class(&sch->q.lock, &sch->root_lock_key); + + if (ops->static_flags & TCQ_F_CPUSTATS) { + sch->cpu_bstats = + netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); + if (!sch->cpu_bstats) + goto errout1; + + sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!sch->cpu_qstats) { + free_percpu(sch->cpu_bstats); + goto errout1; + } + } - spin_lock_init(&sch->busylock); - lockdep_set_class(&sch->busylock, + /* seqlock has the same scope of busylock, for NOLOCK qdisc */ + spin_lock_init(&sch->seqlock); + lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); - sch->ops = ops; + sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; - dev_hold(dev); + netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); return sch; +errout1: + lockdep_unregister_key(&sch->root_lock_key); + kfree(sch); errout: return ERR_PTR(err); } struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, - unsigned int parentid) + unsigned int parentid, + struct netlink_ext_ack *extack) { struct Qdisc *sch; - if (!try_module_get(ops->owner)) + if (!bpf_try_module_get(ops, ops->owner)) { + NL_SET_ERR_MSG(extack, "Failed to increase module reference counter"); return NULL; + } - sch = qdisc_alloc(dev_queue, ops); + sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { - module_put(ops->owner); + bpf_module_put(ops, ops->owner); return NULL; } sch->parent = parentid; - if (!ops->init || ops->init(sch, NULL) == 0) + if (!ops->init || ops->init(sch, NULL, extack) == 0) { + trace_qdisc_create(ops, dev_queue->dev, parentid); return sch; + } - qdisc_destroy(sch); + qdisc_put(sch); return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); @@ -670,39 +1028,40 @@ void qdisc_reset(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; + trace_qdisc_reset(qdisc); + if (ops->reset) ops->reset(qdisc); - kfree_skb(qdisc->skb_bad_txq); - qdisc->skb_bad_txq = NULL; + __skb_queue_purge(&qdisc->gso_skb); + __skb_queue_purge(&qdisc->skb_bad_txq); - if (qdisc->gso_skb) { - kfree_skb_list(qdisc->gso_skb); - qdisc->gso_skb = NULL; - } qdisc->q.qlen = 0; + qdisc->qstats.backlog = 0; } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_rcu_free(struct rcu_head *head) +void qdisc_free(struct Qdisc *qdisc) { - struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); - if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); free_percpu(qdisc->cpu_qstats); } - kfree((char *) qdisc - qdisc->padded); + kfree(qdisc); } -void qdisc_destroy(struct Qdisc *qdisc) +static void qdisc_free_cb(struct rcu_head *head) { - const struct Qdisc_ops *ops = qdisc->ops; + struct Qdisc *q = container_of(head, struct Qdisc, rcu); - if (qdisc->flags & TCQ_F_BUILTIN || - !refcount_dec_and_test(&qdisc->refcnt)) - return; + qdisc_free(q); +} + +static void __qdisc_destroy(struct Qdisc *qdisc) +{ + const struct Qdisc_ops *ops = qdisc->ops; + struct net_device *dev = qdisc_dev(qdisc); #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); @@ -710,42 +1069,73 @@ void qdisc_destroy(struct Qdisc *qdisc) qdisc_put_stab(rtnl_dereference(qdisc->stab)); #endif gen_kill_estimator(&qdisc->rate_est); - if (ops->reset) - ops->reset(qdisc); + + qdisc_reset(qdisc); + + if (ops->destroy) ops->destroy(qdisc); - module_put(ops->owner); - dev_put(qdisc_dev(qdisc)); + lockdep_unregister_key(&qdisc->root_lock_key); + bpf_module_put(ops, ops->owner); + netdev_put(dev, &qdisc->dev_tracker); - kfree_skb_list(qdisc->gso_skb); - kfree_skb(qdisc->skb_bad_txq); - /* - * gen_estimator est_timer() might access qdisc->q.lock, - * wait a RCU grace period before freeing qdisc. - */ - call_rcu(&qdisc->rcu_head, qdisc_rcu_free); + trace_qdisc_destroy(qdisc); + + call_rcu(&qdisc->rcu, qdisc_free_cb); +} + +void qdisc_destroy(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return; + + __qdisc_destroy(qdisc); +} + +void qdisc_put(struct Qdisc *qdisc) +{ + if (!qdisc) + return; + + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_test(&qdisc->refcnt)) + return; + + __qdisc_destroy(qdisc); } -EXPORT_SYMBOL(qdisc_destroy); +EXPORT_SYMBOL(qdisc_put); + +/* Version of qdisc_put() that is called with rtnl mutex unlocked. + * Intended to be used as optimization, this function only takes rtnl lock if + * qdisc reference counter reached zero. + */ + +void qdisc_put_unlocked(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) + return; + + __qdisc_destroy(qdisc); + rtnl_unlock(); +} +EXPORT_SYMBOL(qdisc_put_unlocked); /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { - struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; + struct Qdisc *oqdisc = rtnl_dereference(dev_queue->qdisc_sleeping); spinlock_t *root_lock; root_lock = qdisc_lock(oqdisc); spin_lock_bh(root_lock); - /* Prune old scheduler */ - if (oqdisc && refcount_read(&oqdisc->refcnt) <= 1) - qdisc_reset(oqdisc); - /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); spin_unlock_bh(root_lock); @@ -754,6 +1144,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, } EXPORT_SYMBOL(dev_graft_qdisc); +static void shutdown_scheduler_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_qdisc_default) +{ + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); + struct Qdisc *qdisc_default = _qdisc_default; + + if (qdisc) { + rcu_assign_pointer(dev_queue->qdisc, qdisc_default); + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc_default); + + qdisc_put(qdisc); + } +} + static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) @@ -763,15 +1168,16 @@ static void attach_one_default_qdisc(struct net_device *dev, if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; + else if(dev->type == ARPHRD_CAN) + ops = &pfifo_fast_ops; - qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT); - if (!qdisc) { - netdev_info(dev, "activation failed\n"); + qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); + if (!qdisc) return; - } + if (!netif_is_multiqueue(dev)) qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } static void attach_default_qdiscs(struct net_device *dev) @@ -784,18 +1190,34 @@ static void attach_default_qdiscs(struct net_device *dev) if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - dev->qdisc = txq->qdisc_sleeping; - refcount_inc(&dev->qdisc->refcnt); + qdisc = rtnl_dereference(txq->qdisc_sleeping); + rcu_assign_pointer(dev->qdisc, qdisc); + qdisc_refcount_inc(qdisc); } else { - qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); + qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); if (qdisc) { - dev->qdisc = qdisc; + rcu_assign_pointer(dev->qdisc, qdisc); qdisc->ops->attach(qdisc); } } + qdisc = rtnl_dereference(dev->qdisc); + + /* Detect default qdisc setup/init failed and fallback to "noqueue" */ + if (qdisc == &noop_qdisc) { + netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n", + default_qdisc_ops->id, noqueue_qdisc_ops.id); + netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); + dev->priv_flags |= IFF_NO_QUEUE; + netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); + qdisc = rtnl_dereference(txq->qdisc_sleeping); + rcu_assign_pointer(dev->qdisc, qdisc); + qdisc_refcount_inc(qdisc); + dev->priv_flags ^= IFF_NO_QUEUE; + } + #ifdef CONFIG_NET_SCHED - if (dev->qdisc != &noop_qdisc) - qdisc_hash_add(dev->qdisc, false); + if (qdisc != &noop_qdisc) + qdisc_hash_add(qdisc, false); #endif } @@ -803,7 +1225,7 @@ static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) { - struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *new_qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); int *need_watchdog_p = _need_watchdog; if (!(new_qdisc->flags & TCQ_F_BUILTIN)) @@ -811,7 +1233,7 @@ static void transition_one_qdisc(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p) { - dev_queue->trans_start = 0; + WRITE_ONCE(dev_queue->trans_start, 0); *need_watchdog_p = 1; } } @@ -825,7 +1247,7 @@ void dev_activate(struct net_device *dev) * and noqueue_qdisc for virtual interfaces */ - if (dev->qdisc == &noop_qdisc) + if (rtnl_dereference(dev->qdisc) == &noop_qdisc) attach_default_qdiscs(dev); if (!netif_carrier_ok(dev)) @@ -839,29 +1261,59 @@ void dev_activate(struct net_device *dev) if (need_watchdog) { netif_trans_update(dev); - dev_watchdog_up(dev); + netdev_watchdog_up(dev); } } EXPORT_SYMBOL(dev_activate); +static void qdisc_deactivate(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return; + + set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); +} + static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, - void *_qdisc_default) + void *_sync_needed) { - struct Qdisc *qdisc_default = _qdisc_default; + bool *sync_needed = _sync_needed; struct Qdisc *qdisc; qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { - spin_lock_bh(qdisc_lock(qdisc)); + if (qdisc->enqueue) + *sync_needed = true; + qdisc_deactivate(qdisc); + rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); + } +} - if (!(qdisc->flags & TCQ_F_BUILTIN)) - set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); +static void dev_reset_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_unused) +{ + struct Qdisc *qdisc; + bool nolock; - rcu_assign_pointer(dev_queue->qdisc, qdisc_default); - qdisc_reset(qdisc); + qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); + if (!qdisc) + return; + + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); + spin_lock_bh(qdisc_lock(qdisc)); + + qdisc_reset(qdisc); - spin_unlock_bh(qdisc_lock(qdisc)); + spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); + spin_unlock_bh(&qdisc->seqlock); } } @@ -876,9 +1328,9 @@ static bool some_qdisc_is_busy(struct net_device *dev) int val; dev_queue = netdev_get_tx_queue(dev, i); - q = dev_queue->qdisc_sleeping; - root_lock = qdisc_lock(q); + q = rtnl_dereference(dev_queue->qdisc_sleeping); + root_lock = qdisc_lock(q); spin_lock_bh(root_lock); val = (qdisc_is_running(q) || @@ -901,31 +1353,40 @@ static bool some_qdisc_is_busy(struct net_device *dev) */ void dev_deactivate_many(struct list_head *head) { - struct net_device *dev; bool sync_needed = false; + struct net_device *dev; list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, - &noop_qdisc); + &sync_needed); if (dev_ingress_queue(dev)) dev_deactivate_queue(dev, dev_ingress_queue(dev), - &noop_qdisc); + &sync_needed); - dev_watchdog_down(dev); - sync_needed |= !dev->dismantle; + netdev_watchdog_down(dev); } - /* Wait for outstanding qdisc-less dev_queue_xmit calls. - * This is avoided if all devices are in dismantle phase : - * Caller will call synchronize_net() for us - */ + /* Wait for outstanding qdisc enqueuing calls. */ if (sync_needed) synchronize_net(); + list_for_each_entry(dev, head, close_list) { + netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); + + if (dev_ingress_queue(dev)) + dev_reset_queue(dev, dev_ingress_queue(dev), NULL); + } + /* Wait for outstanding qdisc_run calls. */ - list_for_each_entry(dev, head, close_list) - while (some_qdisc_is_busy(dev)) - yield(); + list_for_each_entry(dev, head, close_list) { + while (some_qdisc_is_busy(dev)) { + /* wait_event() would avoid this sleep-loop but would + * require expensive checks in the fast paths of packet + * processing which isn't worth it. + */ + schedule_timeout_uninterruptible(1); + } + } } void dev_deactivate(struct net_device *dev) @@ -938,6 +1399,72 @@ void dev_deactivate(struct net_device *dev) } EXPORT_SYMBOL(dev_deactivate); +static int qdisc_change_tx_queue_len(struct net_device *dev, + struct netdev_queue *dev_queue) +{ + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); + const struct Qdisc_ops *ops = qdisc->ops; + + if (ops->change_tx_queue_len) + return ops->change_tx_queue_len(qdisc, dev->tx_queue_len); + return 0; +} + +void dev_qdisc_change_real_num_tx(struct net_device *dev, + unsigned int new_real_tx) +{ + struct Qdisc *qdisc = rtnl_dereference(dev->qdisc); + + if (qdisc->ops->change_real_num_tx) + qdisc->ops->change_real_num_tx(qdisc, new_real_tx); +} + +void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) +{ +#ifdef CONFIG_NET_SCHED + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *qdisc; + unsigned int i; + + for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); + /* Only update the default qdiscs we created, + * qdiscs with handles are always hashed. + */ + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_del(qdisc); + } + for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_add(qdisc, false); + } +#endif +} +EXPORT_SYMBOL(mq_change_real_num_tx); + +int dev_qdisc_change_tx_queue_len(struct net_device *dev) +{ + bool up = dev->flags & IFF_UP; + unsigned int i; + int ret = 0; + + if (up) + dev_deactivate(dev); + + for (i = 0; i < dev->num_tx_queues; i++) { + ret = qdisc_change_tx_queue_len(dev, &dev->_tx[i]); + + /* TODO: revert changes on a partial failure */ + if (ret) + break; + } + + if (up) + dev_activate(dev); + return ret; +} + static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc) @@ -945,32 +1472,17 @@ static void dev_init_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc = _qdisc; rcu_assign_pointer(dev_queue->qdisc, qdisc); - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } void dev_init_scheduler(struct net_device *dev) { - dev->qdisc = &noop_qdisc; + rcu_assign_pointer(dev->qdisc, &noop_qdisc); netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); -} - -static void shutdown_scheduler_queue(struct net_device *dev, - struct netdev_queue *dev_queue, - void *_qdisc_default) -{ - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; - struct Qdisc *qdisc_default = _qdisc_default; - - if (qdisc) { - rcu_assign_pointer(dev_queue->qdisc, qdisc_default); - dev_queue->qdisc_sleeping = qdisc_default; - - qdisc_destroy(qdisc); - } + timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } void dev_shutdown(struct net_device *dev) @@ -978,44 +1490,130 @@ void dev_shutdown(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - qdisc_destroy(dev->qdisc); - dev->qdisc = &noop_qdisc; + qdisc_put(rtnl_dereference(dev->qdisc)); + rcu_assign_pointer(dev->qdisc, &noop_qdisc); WARN_ON(timer_pending(&dev->watchdog_timer)); } +/** + * psched_ratecfg_precompute__() - Pre-compute values for reciprocal division + * @rate: Rate to compute reciprocal division values of + * @mult: Multiplier for reciprocal division + * @shift: Shift for reciprocal division + * + * The multiplier and shift for reciprocal division by rate are stored + * in mult and shift. + * + * The deal here is to replace a divide by a reciprocal one + * in fast path (a reciprocal divide is a multiply and a shift) + * + * Normal formula would be : + * time_in_ns = (NSEC_PER_SEC * len) / rate_bps + * + * We compute mult/shift to use instead : + * time_in_ns = (len * mult) >> shift; + * + * We try to get the highest possible mult value for accuracy, + * but have to make sure no overflows will ever happen. + * + * reciprocal_value() is not used here it doesn't handle 64-bit values. + */ +static void psched_ratecfg_precompute__(u64 rate, u32 *mult, u8 *shift) +{ + u64 factor = NSEC_PER_SEC; + + *mult = 1; + *shift = 0; + + if (rate <= 0) + return; + + for (;;) { + *mult = div64_u64(factor, rate); + if (*mult & (1U << 31) || factor & (1ULL << 63)) + break; + factor <<= 1; + (*shift)++; + } +} + void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64) { memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; + r->mpu = conf->mpu; r->rate_bytes_ps = max_t(u64, conf->rate, rate64); r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); - r->mult = 1; - /* - * The deal here is to replace a divide by a reciprocal one - * in fast path (a reciprocal divide is a multiply and a shift) - * - * Normal formula would be : - * time_in_ns = (NSEC_PER_SEC * len) / rate_bps - * - * We compute mult/shift to use instead : - * time_in_ns = (len * mult) >> shift; - * - * We try to get the highest possible mult value for accuracy, - * but have to make sure no overflows will ever happen. + psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift); +} +EXPORT_SYMBOL(psched_ratecfg_precompute); + +void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64) +{ + r->rate_pkts_ps = pktrate64; + psched_ratecfg_precompute__(r->rate_pkts_ps, &r->mult, &r->shift); +} +EXPORT_SYMBOL(psched_ppscfg_precompute); + +void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, + struct tcf_proto *tp_head) +{ + /* Protected with chain0->filter_chain_lock. + * Can't access chain directly because tp_head can be NULL. */ - if (r->rate_bytes_ps > 0) { - u64 factor = NSEC_PER_SEC; - - for (;;) { - r->mult = div64_u64(factor, r->rate_bytes_ps); - if (r->mult & (1U << 31) || factor & (1ULL << 63)) - break; - factor <<= 1; - r->shift++; - } + struct mini_Qdisc *miniq_old = + rcu_dereference_protected(*miniqp->p_miniq, 1); + struct mini_Qdisc *miniq; + + if (!tp_head) { + RCU_INIT_POINTER(*miniqp->p_miniq, NULL); + } else { + miniq = miniq_old != &miniqp->miniq1 ? + &miniqp->miniq1 : &miniqp->miniq2; + + /* We need to make sure that readers won't see the miniq + * we are about to modify. So ensure that at least one RCU + * grace period has elapsed since the miniq was made + * inactive. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + cond_synchronize_rcu(miniq->rcu_state); + else if (!poll_state_synchronize_rcu(miniq->rcu_state)) + synchronize_rcu_expedited(); + + miniq->filter_list = tp_head; + rcu_assign_pointer(*miniqp->p_miniq, miniq); } + + if (miniq_old) + /* This is counterpart of the rcu sync above. We need to + * block potential new user of miniq_old until all readers + * are not seeing it. + */ + miniq_old->rcu_state = start_poll_synchronize_rcu(); } -EXPORT_SYMBOL(psched_ratecfg_precompute); +EXPORT_SYMBOL(mini_qdisc_pair_swap); + +void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, + struct tcf_block *block) +{ + miniqp->miniq1.block = block; + miniqp->miniq2.block = block; +} +EXPORT_SYMBOL(mini_qdisc_pair_block_init); + +void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, + struct mini_Qdisc __rcu **p_miniq) +{ + miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats; + miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats; + miniqp->miniq1.rcu_state = get_state_synchronize_rcu(); + miniqp->miniq2.rcu_state = miniqp->miniq1.rcu_state; + miniqp->p_miniq = p_miniq; +} +EXPORT_SYMBOL(mini_qdisc_pair_init); diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 17c7130454bd..532fde548b88 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -1,17 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_gred.c Generic Random Early Detection queue. * - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: J Hadi Salim (hadi@cyberus.ca) 1998-2002 * * 991129: - Bug fix with grio mode * - a better sing. AvgQ mode with Grio(WRED) - * - A finer grained VQ dequeue based on sugestion + * - A finer grained VQ dequeue based on suggestion * from Ren Liu * - More error checks * @@ -23,19 +18,23 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> +#include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/red.h> #define GRED_DEF_PRIO (MAX_DPs / 2) #define GRED_VQ_MASK (MAX_DPs - 1) +#define GRED_VQ_RED_FLAGS (TC_RED_ECN | TC_RED_HARDDROP) + struct gred_sched_data; struct gred_sched; struct gred_sched_data { u32 limit; /* HARD maximal queue length */ u32 DP; /* the drop parameters */ - u32 bytesin; /* bytes seen on virtualQ so far*/ + u32 red_flags; /* virtualQ version of red_flags */ + u64 bytesin; /* bytes seen on virtualQ so far*/ u32 packetsin; /* packets seen on virtualQ so far*/ u32 backlog; /* bytes on the virtualQ */ u8 prio; /* the prio of this vq */ @@ -57,6 +56,7 @@ struct gred_sched { u32 DPs; u32 def; struct red_vars wred_set; + struct tc_gred_qopt_offload *opt; }; static inline int gred_wred_mode(struct gred_sched *table) @@ -139,14 +139,27 @@ static inline void gred_store_wred_set(struct gred_sched *table, table->wred_set.qidlestart = q->vars.qidlestart; } -static inline int gred_use_ecn(struct gred_sched *t) +static int gred_use_ecn(struct gred_sched_data *q) { - return t->red_flags & TC_RED_ECN; + return q->red_flags & TC_RED_ECN; } -static inline int gred_use_harddrop(struct gred_sched *t) +static int gred_use_harddrop(struct gred_sched_data *q) { - return t->red_flags & TC_RED_HARDDROP; + return q->red_flags & TC_RED_HARDDROP; +} + +static bool gred_per_vq_red_flags_used(struct gred_sched *table) +{ + unsigned int i; + + /* Local per-vq flags couldn't have been set unless global are 0 */ + if (table->red_flags) + return false; + for (i = 0; i < MAX_DPs; i++) + if (table->tab[i] && table->tab[i]->red_flags) + return true; + return false; } static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -212,7 +225,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, case RED_PROB_MARK: qdisc_qstats_overlimit(sch); - if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { + if (!gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.prob_drop++; goto congestion_drop; } @@ -222,7 +235,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, case RED_HARD_MARK: qdisc_qstats_overlimit(sch); - if (gred_use_harddrop(t) || !gred_use_ecn(t) || + if (gred_use_harddrop(q) || !gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.forced_drop++; goto congestion_drop; @@ -238,10 +251,10 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->stats.pdrop++; drop: - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); congestion_drop: - qdisc_drop(skb, sch, to_free); + qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_CONGESTED); return NET_XMIT_CN; } @@ -295,28 +308,138 @@ static void gred_reset(struct Qdisc *sch) } } +static void gred_offload(struct Qdisc *sch, enum tc_gred_command command) +{ + struct gred_sched *table = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_gred_qopt_offload *opt = table->opt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + memset(opt, 0, sizeof(*opt)); + opt->command = command; + opt->handle = sch->handle; + opt->parent = sch->parent; + + if (command == TC_GRED_REPLACE) { + unsigned int i; + + opt->set.grio_on = gred_rio_mode(table); + opt->set.wred_on = gred_wred_mode(table); + opt->set.dp_cnt = table->DPs; + opt->set.dp_def = table->def; + + for (i = 0; i < table->DPs; i++) { + struct gred_sched_data *q = table->tab[i]; + + if (!q) + continue; + opt->set.tab[i].present = true; + opt->set.tab[i].limit = q->limit; + opt->set.tab[i].prio = q->prio; + opt->set.tab[i].min = q->parms.qth_min >> q->parms.Wlog; + opt->set.tab[i].max = q->parms.qth_max >> q->parms.Wlog; + opt->set.tab[i].is_ecn = gred_use_ecn(q); + opt->set.tab[i].is_harddrop = gred_use_harddrop(q); + opt->set.tab[i].probability = q->parms.max_P; + opt->set.tab[i].backlog = &q->backlog; + } + opt->set.qstats = &sch->qstats; + } + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_GRED, opt); +} + +static int gred_offload_dump_stats(struct Qdisc *sch) +{ + struct gred_sched *table = qdisc_priv(sch); + struct tc_gred_qopt_offload *hw_stats; + u64 bytes = 0, packets = 0; + unsigned int i; + int ret; + + hw_stats = kzalloc(sizeof(*hw_stats), GFP_KERNEL); + if (!hw_stats) + return -ENOMEM; + + hw_stats->command = TC_GRED_STATS; + hw_stats->handle = sch->handle; + hw_stats->parent = sch->parent; + + for (i = 0; i < MAX_DPs; i++) { + gnet_stats_basic_sync_init(&hw_stats->stats.bstats[i]); + if (table->tab[i]) + hw_stats->stats.xstats[i] = &table->tab[i]->stats; + } + + ret = qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_GRED, hw_stats); + /* Even if driver returns failure adjust the stats - in case offload + * ended but driver still wants to adjust the values. + */ + sch_tree_lock(sch); + for (i = 0; i < MAX_DPs; i++) { + if (!table->tab[i]) + continue; + table->tab[i]->packetsin += u64_stats_read(&hw_stats->stats.bstats[i].packets); + table->tab[i]->bytesin += u64_stats_read(&hw_stats->stats.bstats[i].bytes); + table->tab[i]->backlog += hw_stats->stats.qstats[i].backlog; + + bytes += u64_stats_read(&hw_stats->stats.bstats[i].bytes); + packets += u64_stats_read(&hw_stats->stats.bstats[i].packets); + sch->qstats.qlen += hw_stats->stats.qstats[i].qlen; + sch->qstats.backlog += hw_stats->stats.qstats[i].backlog; + sch->qstats.drops += hw_stats->stats.qstats[i].drops; + sch->qstats.requeues += hw_stats->stats.qstats[i].requeues; + sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits; + } + _bstats_update(&sch->bstats, bytes, packets); + sch_tree_unlock(sch); + + kfree(hw_stats); + return ret; +} + static inline void gred_destroy_vq(struct gred_sched_data *q) { kfree(q); } -static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) +static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps, + struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_sopt *sopt; + bool red_flags_changed; int i; - if (dps == NULL) + if (!dps) return -EINVAL; sopt = nla_data(dps); - if (sopt->DPs > MAX_DPs || sopt->DPs == 0 || sopt->def_DP >= sopt->DPs) + if (sopt->DPs > MAX_DPs) { + NL_SET_ERR_MSG_MOD(extack, "number of virtual queues too high"); return -EINVAL; + } + if (sopt->DPs == 0) { + NL_SET_ERR_MSG_MOD(extack, + "number of virtual queues can't be 0"); + return -EINVAL; + } + if (sopt->def_DP >= sopt->DPs) { + NL_SET_ERR_MSG_MOD(extack, "default virtual queue above virtual queue count"); + return -EINVAL; + } + if (sopt->flags && gred_per_vq_red_flags_used(table)) { + NL_SET_ERR_MSG_MOD(extack, "can't set per-Qdisc RED flags when per-virtual queue flags are used"); + return -EINVAL; + } sch_tree_lock(sch); table->DPs = sopt->DPs; table->def = sopt->def_DP; + red_flags_changed = table->red_flags != sopt->flags; table->red_flags = sopt->flags; /* @@ -336,6 +459,12 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) gred_disable_wred_mode(table); } + if (red_flags_changed) + for (i = 0; i < table->DPs; i++) + if (table->tab[i]) + table->tab[i]->red_flags = + table->red_flags & GRED_VQ_RED_FLAGS; + for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n", @@ -345,22 +474,30 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) } } + gred_offload(sch, TC_GRED_REPLACE); return 0; } static inline int gred_change_vq(struct Qdisc *sch, int dp, struct tc_gred_qopt *ctl, int prio, u8 *stab, u32 max_P, - struct gred_sched_data **prealloc) + struct gred_sched_data **prealloc, + struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) { + NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); + return -EINVAL; + } + if (!q) { table->tab[dp] = q = *prealloc; *prealloc = NULL; if (!q) return -ENOMEM; + q->red_flags = table->red_flags & GRED_VQ_RED_FLAGS; } q->DP = dp; @@ -380,15 +517,130 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, return 0; } +static const struct nla_policy gred_vq_policy[TCA_GRED_VQ_MAX + 1] = { + [TCA_GRED_VQ_DP] = { .type = NLA_U32 }, + [TCA_GRED_VQ_FLAGS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy gred_vqe_policy[TCA_GRED_VQ_ENTRY_MAX + 1] = { + [TCA_GRED_VQ_ENTRY] = { .type = NLA_NESTED }, +}; + static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = { [TCA_GRED_PARMS] = { .len = sizeof(struct tc_gred_qopt) }, [TCA_GRED_STAB] = { .len = 256 }, [TCA_GRED_DPS] = { .len = sizeof(struct tc_gred_sopt) }, [TCA_GRED_MAX_P] = { .type = NLA_U32 }, [TCA_GRED_LIMIT] = { .type = NLA_U32 }, + [TCA_GRED_VQ_LIST] = { .type = NLA_NESTED }, }; -static int gred_change(struct Qdisc *sch, struct nlattr *opt) +static void gred_vq_apply(struct gred_sched *table, const struct nlattr *entry) +{ + struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; + u32 dp; + + nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry, + gred_vq_policy, NULL); + + dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); + + if (tb[TCA_GRED_VQ_FLAGS]) + table->tab[dp]->red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); +} + +static void gred_vqs_apply(struct gred_sched *table, struct nlattr *vqs) +{ + const struct nlattr *attr; + int rem; + + nla_for_each_nested(attr, vqs, rem) { + switch (nla_type(attr)) { + case TCA_GRED_VQ_ENTRY: + gred_vq_apply(table, attr); + break; + } + } +} + +static int gred_vq_validate(struct gred_sched *table, u32 cdp, + const struct nlattr *entry, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; + int err; + u32 dp; + + err = nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry, + gred_vq_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_GRED_VQ_DP]) { + NL_SET_ERR_MSG_MOD(extack, "Virtual queue with no index specified"); + return -EINVAL; + } + dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); + if (dp >= table->DPs) { + NL_SET_ERR_MSG_MOD(extack, "Virtual queue with index out of bounds"); + return -EINVAL; + } + if (dp != cdp && !table->tab[dp]) { + NL_SET_ERR_MSG_MOD(extack, "Virtual queue not yet instantiated"); + return -EINVAL; + } + + if (tb[TCA_GRED_VQ_FLAGS]) { + u32 red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); + + if (table->red_flags && table->red_flags != red_flags) { + NL_SET_ERR_MSG_MOD(extack, "can't change per-virtual queue RED flags when per-Qdisc flags are used"); + return -EINVAL; + } + if (red_flags & ~GRED_VQ_RED_FLAGS) { + NL_SET_ERR_MSG_MOD(extack, + "invalid RED flags specified"); + return -EINVAL; + } + } + + return 0; +} + +static int gred_vqs_validate(struct gred_sched *table, u32 cdp, + struct nlattr *vqs, struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int rem, err; + + err = nla_validate_nested_deprecated(vqs, TCA_GRED_VQ_ENTRY_MAX, + gred_vqe_policy, extack); + if (err < 0) + return err; + + nla_for_each_nested(attr, vqs, rem) { + switch (nla_type(attr)) { + case TCA_GRED_VQ_ENTRY: + err = gred_vq_validate(table, cdp, attr, extack); + if (err) + return err; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "GRED_VQ_LIST can contain only entry attributes"); + return -EINVAL; + } + } + + if (rem > 0) { + NL_SET_ERR_MSG_MOD(extack, "Trailing data after parsing virtual queue list"); + return -EINVAL; + } + + return 0; +} + +static int gred_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt *ctl; @@ -398,32 +650,40 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt) u32 max_P; struct gred_sched_data *prealloc; - if (opt == NULL) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy, + extack); if (err < 0) return err; if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) { if (tb[TCA_GRED_LIMIT] != NULL) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); - return gred_change_table_def(sch, opt); + return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } if (tb[TCA_GRED_PARMS] == NULL || tb[TCA_GRED_STAB] == NULL || - tb[TCA_GRED_LIMIT] != NULL) + tb[TCA_GRED_LIMIT] != NULL) { + NL_SET_ERR_MSG_MOD(extack, "can't configure Qdisc and virtual queue at the same time"); return -EINVAL; + } - max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0; + max_P = nla_get_u32_default(tb[TCA_GRED_MAX_P], 0); - err = -EINVAL; ctl = nla_data(tb[TCA_GRED_PARMS]); stab = nla_data(tb[TCA_GRED_STAB]); - if (ctl->DP >= table->DPs) - goto errout; + if (ctl->DP >= table->DPs) { + NL_SET_ERR_MSG_MOD(extack, "virtual queue index above virtual queue count"); + return -EINVAL; + } + + if (tb[TCA_GRED_VQ_LIST]) { + err = gred_vqs_validate(table, ctl->DP, tb[TCA_GRED_VQ_LIST], + extack); + if (err) + return err; + } if (gred_rio_mode(table)) { if (ctl->prio == 0) { @@ -443,9 +703,13 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt) prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); sch_tree_lock(sch); - err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc); + err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc, + extack); if (err < 0) - goto errout_locked; + goto err_unlock_free; + + if (tb[TCA_GRED_VQ_LIST]) + gred_vqs_apply(table, tb[TCA_GRED_VQ_LIST]); if (gred_rio_mode(table)) { gred_disable_wred_mode(table); @@ -453,29 +717,38 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt) gred_enable_wred_mode(table); } - err = 0; + sch_tree_unlock(sch); + kfree(prealloc); + + gred_offload(sch, TC_GRED_REPLACE); + return 0; -errout_locked: +err_unlock_free: sch_tree_unlock(sch); kfree(prealloc); -errout: return err; } -static int gred_init(struct Qdisc *sch, struct nlattr *opt) +static int gred_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { + struct gred_sched *table = qdisc_priv(sch); struct nlattr *tb[TCA_GRED_MAX + 1]; int err; - if (opt == NULL) + if (!opt) return -EINVAL; - err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy, + extack); if (err < 0) return err; - if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) + if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) { + NL_SET_ERR_MSG_MOD(extack, + "virtual queue configuration can't be specified at initialization time"); return -EINVAL; + } if (tb[TCA_GRED_LIMIT]) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); @@ -483,13 +756,19 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = qdisc_dev(sch)->tx_queue_len * psched_mtu(qdisc_dev(sch)); - return gred_change_table_def(sch, tb[TCA_GRED_DPS]); + if (qdisc_dev(sch)->netdev_ops->ndo_setup_tc) { + table->opt = kzalloc(sizeof(*table->opt), GFP_KERNEL); + if (!table->opt) + return -ENOMEM; + } + + return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) { struct gred_sched *table = qdisc_priv(sch); - struct nlattr *parms, *opts = NULL; + struct nlattr *parms, *vqs, *opts = NULL; int i; u32 max_p[MAX_DPs]; struct tc_gred_sopt sopt = { @@ -499,7 +778,10 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) .flags = table->red_flags, }; - opts = nla_nest_start(skb, TCA_OPTIONS); + if (gred_offload_dump_stats(sch)) + goto nla_put_failure; + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_GRED_DPS, sizeof(sopt), &sopt)) @@ -516,7 +798,8 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put_u32(skb, TCA_GRED_LIMIT, sch->limit)) goto nla_put_failure; - parms = nla_nest_start(skb, TCA_GRED_PARMS); + /* Old style all-in-one dump of VQs */ + parms = nla_nest_start_noflag(skb, TCA_GRED_PARMS); if (parms == NULL) goto nla_put_failure; @@ -545,7 +828,6 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) opt.Wlog = q->parms.Wlog; opt.Plog = q->parms.Plog; opt.Scell_log = q->parms.Scell_log; - opt.other = q->stats.other; opt.early = q->stats.prob_drop; opt.forced = q->stats.forced_drop; opt.pdrop = q->stats.pdrop; @@ -566,6 +848,56 @@ append_opt: nla_nest_end(skb, parms); + /* Dump the VQs again, in more structured way */ + vqs = nla_nest_start_noflag(skb, TCA_GRED_VQ_LIST); + if (!vqs) + goto nla_put_failure; + + for (i = 0; i < MAX_DPs; i++) { + struct gred_sched_data *q = table->tab[i]; + struct nlattr *vq; + + if (!q) + continue; + + vq = nla_nest_start_noflag(skb, TCA_GRED_VQ_ENTRY); + if (!vq) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GRED_VQ_DP, q->DP)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GRED_VQ_FLAGS, q->red_flags)) + goto nla_put_failure; + + /* Stats */ + if (nla_put_u64_64bit(skb, TCA_GRED_VQ_STAT_BYTES, q->bytesin, + TCA_GRED_VQ_PAD)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PACKETS, q->packetsin)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_BACKLOG, + gred_backlog(table, q, sch))) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_DROP, + q->stats.prob_drop)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_MARK, + q->stats.prob_mark)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_DROP, + q->stats.forced_drop)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_MARK, + q->stats.forced_mark)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PDROP, q->stats.pdrop)) + goto nla_put_failure; + + nla_nest_end(skb, vq); + } + nla_nest_end(skb, vqs); + return nla_nest_end(skb, opts); nla_put_failure: @@ -578,10 +910,12 @@ static void gred_destroy(struct Qdisc *sch) struct gred_sched *table = qdisc_priv(sch); int i; - for (i = 0; i < table->DPs; i++) { - if (table->tab[i]) - gred_destroy_vq(table->tab[i]); - } + for (i = 0; i < table->DPs; i++) + gred_destroy_vq(table->tab[i]); + + if (table->opt) + gred_offload(sch, TC_GRED_DESTROY); + kfree(table->opt); } static struct Qdisc_ops gred_qdisc_ops __read_mostly = { @@ -597,6 +931,7 @@ static struct Qdisc_ops gred_qdisc_ops __read_mostly = { .dump = gred_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("gred"); static int __init gred_module_init(void) { @@ -612,3 +947,4 @@ module_init(gred_module_init) module_exit(gred_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Generic Random Early Detection qdisc"); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b52f74610dc7..d8fd35da32a7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -110,14 +110,12 @@ enum hfsc_class_flags { struct hfsc_class { struct Qdisc_class_common cl_common; - unsigned int refcnt; /* usage count */ - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ struct tcf_block *block; - unsigned int filter_cnt; /* filter count */ unsigned int level; /* class level in hierarchy */ struct hfsc_sched *sched; /* scheduler data */ @@ -177,6 +175,11 @@ struct hfsc_sched { #define HT_INFINITY 0xffffffffffffffffULL /* infinite time value */ +static bool cl_in_el_or_vttree(struct hfsc_class *cl) +{ + return ((cl->cl_flags & HFSC_FSC) && cl->cl_nactive) || + ((cl->cl_flags & HFSC_RSC) && !RB_EMPTY_NODE(&cl->el_node)); +} /* * eligible tree holds backlogged classes being sorted by their eligible times. @@ -205,7 +208,10 @@ eltree_insert(struct hfsc_class *cl) static inline void eltree_remove(struct hfsc_class *cl) { - rb_erase(&cl->el_node, &cl->sched->eligible); + if (!RB_EMPTY_NODE(&cl->el_node)) { + rb_erase(&cl->el_node, &cl->sched->eligible); + RB_CLEAR_NODE(&cl->el_node); + } } static inline void @@ -830,54 +836,6 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time) } static void -set_active(struct hfsc_class *cl, unsigned int len) -{ - if (cl->cl_flags & HFSC_RSC) - init_ed(cl, len); - if (cl->cl_flags & HFSC_FSC) - init_vf(cl, len); - -} - -static void -set_passive(struct hfsc_class *cl) -{ - if (cl->cl_flags & HFSC_RSC) - eltree_remove(cl); - - /* - * vttree is now handled in update_vf() so that update_vf(cl, 0, 0) - * needs to be called explicitly to remove a class from vttree. - */ -} - -static unsigned int -qdisc_peek_len(struct Qdisc *sch) -{ - struct sk_buff *skb; - unsigned int len; - - skb = sch->ops->peek(sch); - if (unlikely(skb == NULL)) { - qdisc_warn_nonwc("qdisc_peek_len", sch); - return 0; - } - len = qdisc_pkt_len(skb); - - return len; -} - -static void -hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl) -{ - unsigned int len = cl->qdisc->q.qlen; - unsigned int backlog = cl->qdisc->qstats.backlog; - - qdisc_reset(cl->qdisc); - qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); -} - -static void hfsc_adjust_levels(struct hfsc_class *cl) { struct hfsc_class *p; @@ -936,6 +894,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc, cl->cl_flags |= HFSC_USC; } +static void +hfsc_upgrade_rt(struct hfsc_class *cl) +{ + cl->cl_fsc = cl->cl_rsc; + rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); + cl->cl_flags |= HFSC_FSC; +} + static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { [TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) }, @@ -944,7 +910,8 @@ static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { static int hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)*arg; @@ -958,7 +925,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (opt == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_HFSC_MAX, opt, hfsc_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_HFSC_MAX, opt, hfsc_policy, + NULL); if (err < 0) return err; @@ -981,6 +949,9 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } if (cl != NULL) { + int old_flags; + int len = 0; + if (parentid) { if (cl->cl_parent && cl->cl_parent->cl_common.classid != parentid) @@ -994,13 +965,15 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; } sch_tree_lock(sch); + old_flags = cl->cl_flags; + if (rsc != NULL) hfsc_change_rsc(cl, rsc, cur_time); if (fsc != NULL) @@ -1008,11 +981,26 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (usc != NULL) hfsc_change_usc(cl, usc, cur_time); + if (cl->qdisc->q.qlen != 0) + len = qdisc_peek_len(cl->qdisc); + /* Check queue length again since some qdisc implementations + * (e.g., netem/codel) might empty the queue during the peek + * operation. + */ if (cl->qdisc->q.qlen != 0) { - if (cl->cl_flags & HFSC_RSC) - update_ed(cl, qdisc_peek_len(cl->qdisc)); - if (cl->cl_flags & HFSC_FSC) - update_vf(cl, 0, cur_time); + if (cl->cl_flags & HFSC_RSC) { + if (old_flags & HFSC_RSC) + update_ed(cl, len); + else + init_ed(cl, len); + } + + if (cl->cl_flags & HFSC_FSC) { + if (old_flags & HFSC_FSC) + update_vf(cl, 0, cur_time); + else + init_vf(cl, len); + } } sch_tree_unlock(sch); @@ -1041,7 +1029,9 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - err = tcf_block_get(&cl->block, &cl->filter_list); + RB_CLEAR_NODE(&cl->el_node); + + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); return err; @@ -1049,9 +1039,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { tcf_block_put(cl->block); kfree(cl); @@ -1067,11 +1055,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, hfsc_change_usc(cl, usc, 0); cl->cl_common.classid = classid; - cl->refcnt = 1; cl->sched = q; cl->cl_parent = parent; - cl->qdisc = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + classid, NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; else @@ -1081,10 +1068,16 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->cf_tree = RB_ROOT; sch_tree_lock(sch); + /* Check if the inner class is a misconfigured 'rt' */ + if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { + NL_SET_ERR_MSG(extack, + "Forced curve change on parent 'rt' to 'sc'"); + hfsc_upgrade_rt(parent); + } qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) - hfsc_purge_queue(sch, parent); + qdisc_purge_queue(parent->qdisc); hfsc_adjust_levels(parent); sch_tree_unlock(sch); @@ -1100,36 +1093,36 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) struct hfsc_sched *q = qdisc_priv(sch); tcf_block_put(cl->block); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) kfree(cl); } static int -hfsc_delete_class(struct Qdisc *sch, unsigned long arg) +hfsc_delete_class(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; - if (cl->level > 0 || cl->filter_cnt > 0 || cl == &q->root) + if (cl->level > 0 || qdisc_class_in_use(&cl->cl_common) || + cl == &q->root) { + NL_SET_ERR_MSG(extack, "HFSC class in use"); return -EBUSY; + } sch_tree_lock(sch); list_del(&cl->siblings); hfsc_adjust_levels(cl->cl_parent); - hfsc_purge_queue(sch, cl); + qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->cl_common); - BUG_ON(--cl->refcnt == 0); - /* - * This shouldn't happen: we "hold" one cops->get() when called - * from tc_ctl_tclass; the destroy method is done from cops->put(). - */ - sch_tree_unlock(sch); + + hfsc_destroy_class(sch, cl); return 0; } @@ -1150,13 +1143,14 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); - while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return NULL; } @@ -1179,7 +1173,8 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) } /* classification failed, try default class */ - cl = hfsc_find_class(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch); + cl = hfsc_find_class(TC_H_MAKE(TC_H_MAJ(sch->handle), + READ_ONCE(q->defcls)), sch); if (cl == NULL || cl->level > 0) return NULL; @@ -1188,7 +1183,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) static int hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct hfsc_class *cl = (struct hfsc_class *)arg; @@ -1196,7 +1191,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, return -EINVAL; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->cl_common.classid); + cl->cl_common.classid, NULL); if (new == NULL) new = &noop_qdisc; } @@ -1221,30 +1216,19 @@ hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; - if (cl->qdisc->q.qlen == 0) { + /* vttree is now handled in update_vf() so that update_vf(cl, 0, 0) + * needs to be called explicitly to remove a class from vttree. + */ + if (cl->cl_nactive) update_vf(cl, 0, 0); - set_passive(cl); - } + if (cl->cl_flags & HFSC_RSC) + eltree_remove(cl); } static unsigned long -hfsc_get_class(struct Qdisc *sch, u32 classid) +hfsc_search_class(struct Qdisc *sch, u32 classid) { - struct hfsc_class *cl = hfsc_find_class(classid, sch); - - if (cl != NULL) - cl->refcnt++; - - return (unsigned long)cl; -} - -static void -hfsc_put_class(struct Qdisc *sch, unsigned long arg) -{ - struct hfsc_class *cl = (struct hfsc_class *)arg; - - if (--cl->refcnt == 0) - hfsc_destroy_class(sch, cl); + return (unsigned long)hfsc_find_class(classid, sch); } static unsigned long @@ -1256,7 +1240,7 @@ hfsc_bind_tcf(struct Qdisc *sch, unsigned long parent, u32 classid) if (cl != NULL) { if (p != NULL && p->level <= cl->level) return 0; - cl->filter_cnt++; + qdisc_class_get(&cl->cl_common); } return (unsigned long)cl; @@ -1267,10 +1251,11 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; - cl->filter_cnt--; + qdisc_class_put(&cl->cl_common); } -static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; @@ -1332,7 +1317,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, if (cl->level == 0) tcm->tcm_info = cl->qdisc->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (hfsc_dump_curves(skb, cl) < 0) @@ -1350,16 +1335,17 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, { struct hfsc_class *cl = (struct hfsc_class *)arg; struct tc_hfsc_stats xstats; + __u32 qlen; - cl->qstats.backlog = cl->qdisc->qstats.backlog; + qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &cl->qstats.backlog); xstats.level = cl->level; xstats.period = cl->cl_vtperiod; xstats.work = cl->cl_total; xstats.rtwork = cl->cl_cumul; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0) + gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); @@ -1380,15 +1366,8 @@ hfsc_walk(struct Qdisc *sch, struct qdisc_walker *arg) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, (unsigned long)cl, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) return; - } - arg->count++; } } } @@ -1407,18 +1386,21 @@ hfsc_schedule_watchdog(struct Qdisc *sch) if (next_time == 0 || next_time > q->root.cl_cfmin) next_time = q->root.cl_cfmin; } - WARN_ON(next_time == 0); - qdisc_watchdog_schedule(&q->watchdog, next_time); + if (next_time) + qdisc_watchdog_schedule(&q->watchdog, next_time); } static int -hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) +hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; int err; - if (opt == NULL || nla_len(opt) < sizeof(*qopt)) + qdisc_watchdog_init(&q->watchdog, sch); + + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); @@ -1428,11 +1410,15 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; + err = tcf_block_get(&q->root.block, &q->root.filter_list, sch, extack); + if (err) + return err; + + gnet_stats_basic_sync_init(&q->root.bstats); q->root.cl_common.classid = sch->handle; - q->root.refcnt = 1; q->root.sched = q; q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle); + sch->handle, NULL); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; else @@ -1444,24 +1430,21 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) qdisc_class_hash_insert(&q->clhash, &q->root.cl_common); qdisc_class_hash_grow(sch, &q->clhash); - qdisc_watchdog_init(&q->watchdog, sch); - return 0; } static int -hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt) +hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; - if (opt == NULL || nla_len(opt) < sizeof(*qopt)) + if (nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); - sch_tree_lock(sch); - q->defcls = qopt->defcls; - sch_tree_unlock(sch); + WRITE_ONCE(q->defcls, qopt->defcls); return 0; } @@ -1509,8 +1492,6 @@ hfsc_reset_qdisc(struct Qdisc *sch) } q->eligible = RB_ROOT; qdisc_watchdog_cancel(&q->watchdog); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void @@ -1522,8 +1503,10 @@ hfsc_destroy_qdisc(struct Qdisc *sch) unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { tcf_block_put(cl->block); + cl->block = NULL; + } } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1541,7 +1524,7 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) unsigned char *b = skb_tail_pointer(skb); struct tc_hfsc_qopt qopt; - qopt.defcls = q->defcls; + qopt.defcls = READ_ONCE(q->defcls); if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; return skb->len; @@ -1554,8 +1537,10 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); struct hfsc_class *cl; - int uninitialized_var(err); + int err; + bool first; cl = hfsc_classify(skb, sch, &err); if (cl == NULL) { @@ -1565,6 +1550,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } + first = !cl->qdisc->q.qlen; err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { @@ -1574,8 +1560,14 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } - if (cl->qdisc->q.qlen == 1) { - set_active(cl, qdisc_pkt_len(skb)); + sch->qstats.backlog += len; + sch->q.qlen++; + + if (first && !cl_in_el_or_vttree(cl)) { + if (cl->cl_flags & HFSC_RSC) + init_ed(cl, len); + if (cl->cl_flags & HFSC_FSC) + init_vf(cl, len); /* * If this is the first packet, isolate the head so an eventual * head drop before the first dequeue operation has no chance @@ -1586,9 +1578,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } - qdisc_qstats_backlog_inc(sch, skb); - sch->q.qlen++; - return NET_XMIT_SUCCESS; } @@ -1639,18 +1628,24 @@ hfsc_dequeue(struct Qdisc *sch) if (realtime) cl->cl_cumul += qdisc_pkt_len(skb); - if (cl->qdisc->q.qlen != 0) { - if (cl->cl_flags & HFSC_RSC) { + if (cl->cl_flags & HFSC_RSC) { + if (cl->qdisc->q.qlen != 0) { /* update ed */ next_len = qdisc_peek_len(cl->qdisc); - if (realtime) - update_ed(cl, next_len); - else - update_d(cl, next_len); + /* Check queue length again since some qdisc implementations + * (e.g., netem/codel) might empty the queue during the peek + * operation. + */ + if (cl->qdisc->q.qlen != 0) { + if (realtime) + update_ed(cl, next_len); + else + update_d(cl, next_len); + } + } else { + /* the class becomes passive */ + eltree_remove(cl); } - } else { - /* the class becomes passive */ - set_passive(cl); } qdisc_bstats_update(sch, skb); @@ -1666,8 +1661,7 @@ static const struct Qdisc_class_ops hfsc_class_ops = { .graft = hfsc_graft_class, .leaf = hfsc_class_leaf, .qlen_notify = hfsc_qlen_notify, - .get = hfsc_get_class, - .put = hfsc_put_class, + .find = hfsc_search_class, .bind_tcf = hfsc_bind_tcf, .unbind_tcf = hfsc_unbind_tcf, .tcf_block = hfsc_tcf_block, @@ -1690,6 +1684,7 @@ static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = { .priv_size = sizeof(struct hfsc_sched), .owner = THIS_MODULE }; +MODULE_ALIAS_NET_SCH("hfsc"); static int __init hfsc_init(void) @@ -1704,5 +1699,6 @@ hfsc_cleanup(void) } MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Hierarchical Fair Service Curve scheduler"); module_init(hfsc_init); module_exit(hfsc_cleanup); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 51d3ba682af9..2d4855e28a28 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -1,14 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0-only /* net/sched/sch_hhf.c Heavy-Hitter Filter (HHF) * * Copyright (C) 2013 Terry Lam <vtlam@google.com> * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com> */ -#include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> +#include <linux/siphash.h> #include <net/pkt_sched.h> #include <net/sock.h> @@ -125,7 +126,7 @@ struct wdrr_bucket { struct hhf_sched_data { struct wdrr_bucket buckets[WDRR_BUCKET_CNT]; - u32 perturbation; /* hash perturbation */ + siphash_key_t perturbation; /* hash perturbation */ u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ u32 drop_overlimit; /* number of times max qdisc packet * limit was hit @@ -263,7 +264,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) } /* Get hashed flow-id of the skb. */ - hash = skb_get_hash_perturb(skb, q->perturbation); + hash = skb_get_hash_perturb(skb, &q->perturbation); /* Check if this packet belongs to an already established HH flow. */ flow_pos = hash & HHF_BIT_MASK; @@ -330,7 +331,7 @@ static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket) struct sk_buff *skb = bucket->head; bucket->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } @@ -477,6 +478,9 @@ static void hhf_destroy(struct Qdisc *sch) kvfree(q->hhf_valid_bits[i]); } + if (!q->hh_flows) + return; + for (i = 0; i < HH_FLOWS_CNT; i++) { struct hh_flow_state *flow, *next; struct list_head *head = &q->hh_flows[i]; @@ -501,20 +505,19 @@ static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { [TCA_HHF_NON_HH_WEIGHT] = { .type = NLA_U32 }, }; -static int hhf_change(struct Qdisc *sch, struct nlattr *opt) +static int hhf_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; - unsigned int qlen, prev_backlog; int err; u64 non_hh_quantum; u32 new_quantum = q->quantum; u32 new_hhf_non_hh_weight = q->hhf_non_hh_weight; - if (!opt) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_HHF_MAX, opt, hhf_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_HHF_MAX, opt, hhf_policy, + NULL); if (err < 0) return err; @@ -525,57 +528,64 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]); non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight; - if (non_hh_quantum > INT_MAX) + if (non_hh_quantum == 0 || non_hh_quantum > INT_MAX) return -EINVAL; sch_tree_lock(sch); if (tb[TCA_HHF_BACKLOG_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]); + WRITE_ONCE(sch->limit, nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT])); - q->quantum = new_quantum; - q->hhf_non_hh_weight = new_hhf_non_hh_weight; + WRITE_ONCE(q->quantum, new_quantum); + WRITE_ONCE(q->hhf_non_hh_weight, new_hhf_non_hh_weight); if (tb[TCA_HHF_HH_FLOWS_LIMIT]) - q->hh_flows_limit = nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]); + WRITE_ONCE(q->hh_flows_limit, + nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT])); if (tb[TCA_HHF_RESET_TIMEOUT]) { u32 us = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]); - q->hhf_reset_timeout = usecs_to_jiffies(us); + WRITE_ONCE(q->hhf_reset_timeout, + usecs_to_jiffies(us)); } if (tb[TCA_HHF_ADMIT_BYTES]) - q->hhf_admit_bytes = nla_get_u32(tb[TCA_HHF_ADMIT_BYTES]); + WRITE_ONCE(q->hhf_admit_bytes, + nla_get_u32(tb[TCA_HHF_ADMIT_BYTES])); if (tb[TCA_HHF_EVICT_TIMEOUT]) { u32 us = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]); - q->hhf_evict_timeout = usecs_to_jiffies(us); + WRITE_ONCE(q->hhf_evict_timeout, + usecs_to_jiffies(us)); } - qlen = sch->q.qlen; - prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = hhf_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); + + if (!skb) + break; + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, - prev_backlog - sch->qstats.backlog); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; } -static int hhf_init(struct Qdisc *sch, struct nlattr *opt) +static int hhf_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct hhf_sched_data *q = qdisc_priv(sch); int i; sch->limit = 1000; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); @@ -586,7 +596,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) q->hhf_non_hh_weight = 2; if (opt) { - int err = hhf_change(sch, opt); + int err = hhf_change(sch, opt, extack); if (err) return err; @@ -594,8 +604,8 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) if (!q->hh_flows) { /* Initialize heavy-hitter flow table. */ - q->hh_flows = kvzalloc(HH_FLOWS_CNT * - sizeof(struct list_head), GFP_KERNEL); + q->hh_flows = kvcalloc(HH_FLOWS_CNT, sizeof(struct list_head), + GFP_KERNEL); if (!q->hh_flows) return -ENOMEM; for (i = 0; i < HH_FLOWS_CNT; i++) @@ -609,8 +619,9 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) /* Initialize heavy-hitter filter arrays. */ for (i = 0; i < HHF_ARRAYS_CNT; i++) { - q->hhf_arrays[i] = kvzalloc(HHF_ARRAYS_LEN * - sizeof(u32), GFP_KERNEL); + q->hhf_arrays[i] = kvcalloc(HHF_ARRAYS_LEN, + sizeof(u32), + GFP_KERNEL); if (!q->hhf_arrays[i]) { /* Note: hhf_destroy() will be called * by our caller. @@ -648,19 +659,22 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_HHF_BACKLOG_LIMIT, sch->limit) || - nla_put_u32(skb, TCA_HHF_QUANTUM, q->quantum) || - nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, q->hh_flows_limit) || + if (nla_put_u32(skb, TCA_HHF_BACKLOG_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_HHF_QUANTUM, READ_ONCE(q->quantum)) || + nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, + READ_ONCE(q->hh_flows_limit)) || nla_put_u32(skb, TCA_HHF_RESET_TIMEOUT, - jiffies_to_usecs(q->hhf_reset_timeout)) || - nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, q->hhf_admit_bytes) || + jiffies_to_usecs(READ_ONCE(q->hhf_reset_timeout))) || + nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, + READ_ONCE(q->hhf_admit_bytes)) || nla_put_u32(skb, TCA_HHF_EVICT_TIMEOUT, - jiffies_to_usecs(q->hhf_evict_timeout)) || - nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight)) + jiffies_to_usecs(READ_ONCE(q->hhf_evict_timeout))) || + nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, + READ_ONCE(q->hhf_non_hh_weight))) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -697,6 +711,7 @@ static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .dump_stats = hhf_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("hhf"); static int __init hhf_module_init(void) { @@ -713,3 +728,4 @@ module_exit(hhf_module_exit) MODULE_AUTHOR("Terry Lam"); MODULE_AUTHOR("Nandita Dukkipati"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Heavy-Hitter Filter (HHF)"); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 203286ab4427..b5e40c51655a 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_htb.c Hierarchical token bucket, feed tree version * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Martin Devera, <devik@cdi.cz> * * Credits (in time order) for older HTB versions: @@ -56,7 +52,7 @@ */ static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */ -#define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ +#define HTB_VER 0x30011 /* major must be matched with number supplied by TC as version */ #if HTB_VER >> 16 != TC_HTB_PROTOVER #error "Mismatched sch_htb.c and pkt_sch.h" @@ -106,8 +102,6 @@ struct htb_class { struct tcf_proto __rcu *filter_list; /* class attached filters */ struct tcf_block *block; - int filter_cnt; - int refcnt; /* usage count of this class */ int level; /* our level (see above) */ unsigned int children; @@ -118,7 +112,8 @@ struct htb_class { /* * Written often fields */ - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; + struct gnet_stats_basic_sync bstats_bias; struct tc_htb_xstats xstats; /* our special stats */ /* token bucket parameters */ @@ -127,14 +122,14 @@ struct htb_class { union { struct htb_class_leaf { - struct list_head drop_list; int deficit[TC_HTB_MAXDEPTH]; struct Qdisc *q; + struct netdev_queue *offload_queue; } leaf; struct htb_class_inner { struct htb_prio clprio[TC_HTB_NUMPRIO]; } inner; - } un; + }; s64 pq_key; int prio_activity; /* for which prios are we active */ @@ -143,6 +138,7 @@ struct htb_class { struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */ unsigned int drops ____cacheline_aligned_in_smp; + unsigned int overlimits; }; struct htb_level { @@ -166,12 +162,12 @@ struct htb_sched { /* non shaped skbs; let them go directly thru */ struct qdisc_skb_head direct_queue; - long direct_pkts; + u32 direct_pkts; + u32 overlimits; struct qdisc_watchdog watchdog; s64 now; /* cached dequeue time */ - struct list_head drops[TC_HTB_NUMPRIO];/* active leaves (for drops) */ /* time of nearest event per level (row) */ s64 near_ev_cache[TC_HTB_MAXDEPTH]; @@ -179,6 +175,11 @@ struct htb_sched { int row_mask[TC_HTB_MAXDEPTH]; struct htb_level hlevel[TC_HTB_MAXDEPTH]; + + struct Qdisc **direct_qdiscs; + unsigned int num_direct_qdiscs; + + bool offload; }; /* find class in global hash table using given handle */ @@ -193,8 +194,18 @@ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) return container_of(clc, struct htb_class, common); } +static unsigned long htb_search(struct Qdisc *sch, u32 handle) +{ + return (unsigned long)htb_find(handle, sch); +} + +#define HTB_DIRECT ((struct htb_class *)-1L) + /** * htb_classify - classify a packet into class + * @skb: the socket buffer + * @sch: the active queue discipline + * @qerr: pointer for returned status code * * It returns NULL if the packet should be dropped or -1 if the packet * should be passed directly thru. In all other cases leaf class is returned. @@ -205,8 +216,6 @@ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful * then finish and return direct queue. */ -#define HTB_DIRECT ((struct htb_class *)-1L) - static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) { @@ -233,13 +242,14 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return NULL; } @@ -267,6 +277,9 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, /** * htb_add_to_id_tree - adds class to the round robin list + * @root: the root of the tree + * @cl: the class to add + * @prio: the give prio in class * * Routine adds class to the list (actually tree) sorted by classid. * Make sure that class is not already on such list for given prio. @@ -292,6 +305,9 @@ static void htb_add_to_id_tree(struct rb_root *root, /** * htb_add_to_wait_tree - adds class to the event queue with delay + * @q: the priority event queue + * @cl: the class to add + * @delay: delay in microseconds * * The class is added to priority event queue to indicate that class will * change its mode in cl->pq_key microseconds. Make sure that class is not @@ -325,17 +341,22 @@ static void htb_add_to_wait_tree(struct htb_sched *q, /** * htb_next_rb_node - finds next node in binary tree + * @n: the current node in binary tree * * When we are past last key we return NULL. * Average complexity is 2 steps per call. */ static inline void htb_next_rb_node(struct rb_node **n) { - *n = rb_next(*n); + if (*n) + *n = rb_next(*n); } /** * htb_add_class_to_row - add class to its row + * @q: the priority event queue + * @cl: the class to add + * @mask: the given priorities in class in bitmap * * The class is added to row at priorities marked in mask. * It does nothing if mask == 0. @@ -365,6 +386,9 @@ static void htb_safe_rb_erase(struct rb_node *rb, struct rb_root *root) /** * htb_remove_class_from_row - removes class from its row + * @q: the priority event queue + * @cl: the class to add + * @mask: the given priorities in class in bitmap * * The class is removed from row at priorities marked in mask. * It does nothing if mask == 0. @@ -392,6 +416,8 @@ static inline void htb_remove_class_from_row(struct htb_sched *q, /** * htb_activate_prios - creates active classe's feed chain + * @q: the priority event queue + * @cl: the class to activate * * The class is connected to ancestors and/or appropriate rows * for priorities it is participating on. cl->cmode must be new @@ -405,16 +431,19 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (cl->cmode == HTB_MAY_BORROW && p && mask) { m = mask; while (m) { - int prio = ffz(~m); + unsigned int prio = ffz(~m); + + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) + break; m &= ~(1 << prio); - if (p->un.inner.clprio[prio].feed.rb_node) + if (p->inner.clprio[prio].feed.rb_node) /* parent already has its feed in use so that * reset bit in mask as parent is already ok */ mask &= ~(1 << prio); - htb_add_to_id_tree(&p->un.inner.clprio[prio].feed, cl, prio); + htb_add_to_id_tree(&p->inner.clprio[prio].feed, cl, prio); } p->prio_activity |= mask; cl = p; @@ -427,6 +456,8 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) /** * htb_deactivate_prios - remove class from feed chain + * @q: the priority event queue + * @cl: the class to deactivate * * cl->cmode must represent old mode (before deactivation). It does * nothing if cl->prio_activity == 0. Class is removed from all feed @@ -444,19 +475,19 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].ptr == cl->node + prio) { + if (p->inner.clprio[prio].ptr == cl->node + prio) { /* we are removing child which is pointed to from * parent feed - forget the pointer but remember * classid */ - p->un.inner.clprio[prio].last_ptr_id = cl->common.classid; - p->un.inner.clprio[prio].ptr = NULL; + p->inner.clprio[prio].last_ptr_id = cl->common.classid; + p->inner.clprio[prio].ptr = NULL; } htb_safe_rb_erase(cl->node + prio, - &p->un.inner.clprio[prio].feed); + &p->inner.clprio[prio].feed); - if (!p->un.inner.clprio[prio].feed.rb_node) + if (!p->inner.clprio[prio].feed.rb_node) mask |= 1 << prio; } @@ -487,6 +518,8 @@ static inline s64 htb_hiwater(const struct htb_class *cl) /** * htb_class_mode - computes and returns current class mode + * @cl: the target class + * @diff: diff time in microseconds * * It computes cl's mode at time cl->t_c+diff and returns it. If mode * is not HTB_CAN_SEND then cl->pq_key is updated to time difference @@ -515,9 +548,12 @@ htb_class_mode(struct htb_class *cl, s64 *diff) /** * htb_change_class_mode - changes classe's mode + * @q: the priority event queue + * @cl: the target class + * @diff: diff time in microseconds * * This should be the only way how to change classe's mode under normal - * cirsumstances. Routine will update feed lists linkage, change mode + * circumstances. Routine will update feed lists linkage, change mode * and add class to the wait event queue if appropriate. New mode should * be different from old one and cl->pq_key has to be valid if changing * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree). @@ -530,6 +566,11 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) if (new_mode == cl->cmode) return; + if (new_mode == HTB_CANT_SEND) { + cl->overlimits++; + q->overlimits++; + } + if (cl->prio_activity) { /* not necessary: speed optimization */ if (cl->cmode != HTB_CANT_SEND) htb_deactivate_prios(q, cl); @@ -542,6 +583,8 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) /** * htb_activate - inserts leaf cl into appropriate active feeds + * @q: the priority event queue + * @cl: the target class * * Routine learns (new) priority of leaf and activates feed chain * for the prio. It can be called on already active leaf safely. @@ -549,58 +592,42 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->un.leaf.q || !cl->un.leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; htb_activate_prios(q, cl); - list_add_tail(&cl->un.leaf.drop_list, - q->drops + cl->prio); } } /** * htb_deactivate - remove leaf cl from active feeds + * @q: the priority event queue + * @cl: the target class * * Make sure that leaf is active. In the other words it can't be called * with non-active leaf. It also removes class from the drop list. */ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(!cl->prio_activity); - + if (!cl->prio_activity) + return; htb_deactivate_prios(q, cl); cl->prio_activity = 0; - list_del_init(&cl->un.leaf.drop_list); -} - -static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) -{ - struct sk_buff *last = qh->tail; - - if (last) { - skb->next = NULL; - last->next = skb; - qh->tail = skb; - } else { - qh->tail = skb; - qh->head = skb; - } - qh->qlen++; } static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - int uninitialized_var(ret); + int ret; + unsigned int len = qdisc_pkt_len(skb); struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = htb_classify(skb, sch, &ret); if (cl == HTB_DIRECT) { /* enqueue to helper queue */ if (q->direct_queue.qlen < q->direct_qlen) { - htb_enqueue_tail(skb, sch, &q->direct_queue); + __qdisc_enqueue_tail(skb, &q->direct_queue); q->direct_pkts++; } else { return qdisc_drop(skb, sch, to_free); @@ -612,7 +639,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; #endif - } else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q, + } else if ((ret = qdisc_enqueue(skb, cl->leaf.q, to_free)) != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) { qdisc_qstats_drop(sch); @@ -623,7 +650,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, htb_activate(q, cl); } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -656,6 +683,10 @@ static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff) /** * htb_charge_class - charges amount "bytes" to leaf and ancestors + * @q: the priority event queue + * @cl: the class to start iterate + * @level: the minimum level to account + * @skb: the socket buffer * * Routine assumes that packet "bytes" long was dequeued from leaf cl * borrowing from "level". It accounts bytes to ceil leaky bucket for @@ -705,6 +736,9 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, /** * htb_do_events - make mode changes to classes at the level + * @q: the priority event queue + * @level: which wait_pq in 'q->hlevel' + * @start: start jiffies * * Scans event queue for pending events and applies them. Returns time of * next pending event (0 for no event in pq, q->now for too many events). @@ -773,6 +807,8 @@ static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n, /** * htb_lookup_leaf - returns next leaf class in DRR order + * @hprio: the current one + * @prio: which prio in class * * Find leaf where current feed pointers points to. */ @@ -785,7 +821,9 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) u32 *pid; } stk[TC_HTB_MAXDEPTH], *sp = stk; - BUG_ON(!hprio->row.rb_node); + if (unlikely(!hprio->row.rb_node)) + return NULL; + sp->root = hprio->row.rb_node; sp->pptr = &hprio->ptr; sp->pid = &hprio->last_ptr_id; @@ -820,7 +858,7 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) cl = rb_entry(*sp->pptr, struct htb_class, node[prio]); if (!cl->level) return cl; - clp = &cl->un.inner.clprio[prio]; + clp = &cl->inner.clprio[prio]; (++sp)->root = clp->feed.rb_node; sp->pptr = &clp->ptr; sp->pid = &clp->last_ptr_id; @@ -854,7 +892,7 @@ next: * graft operation on the leaf since last dequeue; * simply deactivate and skip such class */ - if (unlikely(cl->un.leaf.q->q.qlen == 0)) { + if (unlikely(cl->leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -870,12 +908,12 @@ next: goto next; } - skb = cl->un.leaf.q->dequeue(cl->un.leaf.q); + skb = cl->leaf.q->dequeue(cl->leaf.q); if (likely(skb != NULL)) break; - qdisc_warn_nonwc("htb", cl->un.leaf.q); - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr: + qdisc_warn_nonwc("htb", cl->leaf.q); + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr: &q->hlevel[0].hprio[prio].ptr); cl = htb_lookup_leaf(hprio, prio); @@ -883,16 +921,16 @@ next: if (likely(skb != NULL)) { bstats_update(&cl->bstats, skb); - cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb); - if (cl->un.leaf.deficit[level] < 0) { - cl->un.leaf.deficit[level] += cl->quantum; - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr : + cl->leaf.deficit[level] -= qdisc_pkt_len(skb); + if (cl->leaf.deficit[level] < 0) { + cl->leaf.deficit[level] += cl->quantum; + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr : &q->hlevel[0].hprio[prio].ptr); } /* this used to be after charge_class but this constelation * gives us slightly better performance */ - if (!cl->un.leaf.q->q.qlen) + if (!cl->leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); } @@ -949,7 +987,6 @@ ok: goto ok; } } - qdisc_qstats_overlimit(sch); if (likely(next_event > q->now)) qdisc_watchdog_schedule_ns(&q->watchdog, next_event); else @@ -969,11 +1006,10 @@ static void htb_reset(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->level) - memset(&cl->un.inner, 0, sizeof(cl->un.inner)); + memset(&cl->inner, 0, sizeof(cl->inner)); else { - if (cl->un.leaf.q) - qdisc_reset(cl->un.leaf.q); - INIT_LIST_HEAD(&cl->un.leaf.drop_list); + if (cl->leaf.q && !q->offload) + qdisc_reset(cl->leaf.q); } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; @@ -981,12 +1017,8 @@ static void htb_reset(struct Qdisc *sch) } qdisc_watchdog_cancel(&q->watchdog); __qdisc_reset_queue(&q->direct_queue); - sch->q.qlen = 0; - sch->qstats.backlog = 0; memset(q->hlevel, 0, sizeof(q->hlevel)); memset(q->row_mask, 0, sizeof(q->row_mask)); - for (i = 0; i < TC_HTB_NUMPRIO; i++) - INIT_LIST_HEAD(q->drops + i); } static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = { @@ -997,6 +1029,7 @@ static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = { [TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 }, [TCA_HTB_RATE64] = { .type = NLA_U64 }, [TCA_HTB_CEIL64] = { .type = NLA_U64 }, + [TCA_HTB_OFFLOAD] = { .type = NLA_FLAG }, }; static void htb_work_func(struct work_struct *work) @@ -1009,22 +1042,35 @@ static void htb_work_func(struct work_struct *work) rcu_read_unlock(); } -static int htb_init(struct Qdisc *sch, struct nlattr *opt) +static int htb_offload(struct net_device *dev, struct tc_htb_qopt_offload *opt) +{ + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_HTB, opt); +} + +static int htb_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; struct htb_sched *q = qdisc_priv(sch); struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_glob *gopt; + unsigned int ntx; + bool offload; int err; - int i; + + qdisc_watchdog_init(&q->watchdog, sch); + INIT_WORK(&q->work, htb_work_func); if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; - err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_HTB_MAX, opt, htb_policy, + NULL); if (err < 0) return err; @@ -1035,15 +1081,30 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (gopt->version != HTB_VER >> 16) return -EINVAL; + offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]); + + if (offload) { + if (sch->parent != TC_H_ROOT) { + NL_SET_ERR_MSG(extack, "HTB must be the root qdisc to use offload"); + return -EOPNOTSUPP; + } + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, "hw-tc-offload ethtool feature flag must be on"); + return -EOPNOTSUPP; + } + + q->num_direct_qdiscs = dev->real_num_tx_queues; + q->direct_qdiscs = kcalloc(q->num_direct_qdiscs, + sizeof(*q->direct_qdiscs), + GFP_KERNEL); + if (!q->direct_qdiscs) + return -ENOMEM; + } + err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; - for (i = 0; i < TC_HTB_NUMPRIO; i++) - INIT_LIST_HEAD(q->drops + i); - - qdisc_watchdog_init(&q->watchdog, sch); - INIT_WORK(&q->work, htb_work_func); - qdisc_skb_head_init(&q->direct_queue); if (tb[TCA_HTB_DIRECT_QLEN]) q->direct_qlen = nla_get_u32(tb[TCA_HTB_DIRECT_QLEN]); @@ -1054,15 +1115,105 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) q->rate2quantum = 1; q->defcls = gopt->defcls; + if (!offload) + return 0; + + for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *qdisc; + + qdisc = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, 0), extack); + if (!qdisc) { + return -ENOMEM; + } + + q->direct_qdiscs[ntx] = qdisc; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + } + + sch->flags |= TCQ_F_MQROOT; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_CREATE, + .parent_classid = TC_H_MAJ(sch->handle) >> 16, + .classid = TC_H_MIN(q->defcls), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) + return err; + + /* Defer this assignment, so that htb_destroy skips offload-related + * parts (especially calling ndo_setup_tc) on errors. + */ + q->offload = true; + return 0; } +static void htb_attach_offload(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct htb_sched *q = qdisc_priv(sch); + unsigned int ntx; + + for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { + struct Qdisc *old, *qdisc = q->direct_qdiscs[ntx]; + + old = dev_graft_qdisc(qdisc->dev_queue, qdisc); + qdisc_put(old); + qdisc_hash_add(qdisc, false); + } + for (ntx = q->num_direct_qdiscs; ntx < dev->num_tx_queues; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *old = dev_graft_qdisc(dev_queue, NULL); + + qdisc_put(old); + } + + kfree(q->direct_qdiscs); + q->direct_qdiscs = NULL; +} + +static void htb_attach_software(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx; + + /* Resemble qdisc_graft behavior. */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *old = dev_graft_qdisc(dev_queue, sch); + + qdisc_refcount_inc(sch); + + qdisc_put(old); + } +} + +static void htb_attach(struct Qdisc *sch) +{ + struct htb_sched *q = qdisc_priv(sch); + + if (q->offload) + htb_attach_offload(sch); + else + htb_attach_software(sch); +} + static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) { struct htb_sched *q = qdisc_priv(sch); struct nlattr *nest; struct tc_htb_glob gopt; + if (q->offload) + sch->flags |= TCQ_F_OFFLOADED; + else + sch->flags &= ~TCQ_F_OFFLOADED; + + sch->qstats.overlimits = q->overlimits; /* Its safe to not acquire qdisc lock. As we hold RTNL, * no change can happen on the qdisc parameters. */ @@ -1073,12 +1224,14 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) gopt.defcls = q->defcls; gopt.debug = 0; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) || nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen)) goto nla_put_failure; + if (q->offload && nla_put_flag(skb, TCA_HTB_OFFLOAD)) + goto nla_put_failure; return nla_nest_end(skb, nest); @@ -1091,6 +1244,7 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct htb_class *cl = (struct htb_class *)arg; + struct htb_sched *q = qdisc_priv(sch); struct nlattr *nest; struct tc_htb_opt opt; @@ -1099,10 +1253,10 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; - if (!cl->level && cl->un.leaf.q) - tcm->tcm_info = cl->un.leaf.q->handle; + if (!cl->level && cl->leaf.q) + tcm->tcm_info = cl->leaf.q->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -1117,6 +1271,8 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, opt.level = cl->level; if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt)) goto nla_put_failure; + if (q->offload && nla_put_flag(skb, TCA_HTB_OFFLOAD)) + goto nla_put_failure; if ((cl->rate.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_HTB_RATE64, cl->rate.rate_bytes_ps, TCA_HTB_PAD)) @@ -1133,26 +1289,70 @@ nla_put_failure: return -1; } +static void htb_offload_aggregate_stats(struct htb_sched *q, + struct htb_class *cl) +{ + u64 bytes = 0, packets = 0; + struct htb_class *c; + unsigned int i; + + gnet_stats_basic_sync_init(&cl->bstats); + + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry(c, &q->clhash.hash[i], common.hnode) { + struct htb_class *p = c; + + while (p && p->level < cl->level) + p = p->parent; + + if (p != cl) + continue; + + bytes += u64_stats_read(&c->bstats_bias.bytes); + packets += u64_stats_read(&c->bstats_bias.packets); + if (c->level == 0) { + bytes += u64_stats_read(&c->leaf.q->bstats.bytes); + packets += u64_stats_read(&c->leaf.q->bstats.packets); + } + } + } + _bstats_update(&cl->bstats, bytes, packets); +} + static int htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct htb_class *cl = (struct htb_class *)arg; + struct htb_sched *q = qdisc_priv(sch); struct gnet_stats_queue qs = { .drops = cl->drops, + .overlimits = cl->overlimits, }; __u32 qlen = 0; - if (!cl->level && cl->un.leaf.q) { - qlen = cl->un.leaf.q->q.qlen; - qs.backlog = cl->un.leaf.q->qstats.backlog; - } + if (!cl->level && cl->leaf.q) + qdisc_qstats_qlen_backlog(cl->leaf.q, &qlen, &qs.backlog); + cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), INT_MIN, INT_MAX); cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens), INT_MIN, INT_MAX); - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (q->offload) { + if (!cl->level) { + if (cl->leaf.q) + cl->bstats = cl->leaf.q->bstats; + else + gnet_stats_basic_sync_init(&cl->bstats); + _bstats_update(&cl->bstats, + u64_stats_read(&cl->bstats_bias.bytes), + u64_stats_read(&cl->bstats_bias.packets)); + } else { + htb_offload_aggregate_stats(q, cl); + } + } + + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &qs, qlen) < 0) return -1; @@ -1160,42 +1360,135 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); } +static struct netdev_queue * +htb_select_queue(struct Qdisc *sch, struct tcmsg *tcm) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; + struct htb_sched *q = qdisc_priv(sch); + int err; + + if (!q->offload) + return sch->dev_queue; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_QUERY_QUEUE, + .classid = TC_H_MIN(tcm->tcm_parent), + }; + err = htb_offload(dev, &offload_opt); + if (err || offload_opt.qid >= dev->num_tx_queues) + return NULL; + return netdev_get_tx_queue(dev, offload_opt.qid); +} + +static struct Qdisc * +htb_graft_helper(struct netdev_queue *dev_queue, struct Qdisc *new_q) +{ + struct net_device *dev = dev_queue->dev; + struct Qdisc *old_q; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + old_q = dev_graft_qdisc(dev_queue, new_q); + if (new_q) + new_q->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + if (dev->flags & IFF_UP) + dev_activate(dev); + + return old_q; +} + +static struct netdev_queue *htb_offload_get_queue(struct htb_class *cl) +{ + struct netdev_queue *queue; + + queue = cl->leaf.offload_queue; + if (!(cl->leaf.q->flags & TCQ_F_BUILTIN)) + WARN_ON(cl->leaf.q->dev_queue != queue); + + return queue; +} + +static void htb_offload_move_qdisc(struct Qdisc *sch, struct htb_class *cl_old, + struct htb_class *cl_new, bool destroying) +{ + struct netdev_queue *queue_old, *queue_new; + struct net_device *dev = qdisc_dev(sch); + + queue_old = htb_offload_get_queue(cl_old); + queue_new = htb_offload_get_queue(cl_new); + + if (!destroying) { + struct Qdisc *qdisc; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + qdisc = dev_graft_qdisc(queue_old, NULL); + WARN_ON(qdisc != cl_old->leaf.q); + } + + if (!(cl_old->leaf.q->flags & TCQ_F_BUILTIN)) + cl_old->leaf.q->dev_queue = queue_new; + cl_old->leaf.offload_queue = queue_new; + + if (!destroying) { + struct Qdisc *qdisc; + + qdisc = dev_graft_qdisc(queue_new, cl_old->leaf.q); + if (dev->flags & IFF_UP) + dev_activate(dev); + WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN)); + } +} + static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { + struct netdev_queue *dev_queue = sch->dev_queue; struct htb_class *cl = (struct htb_class *)arg; + struct htb_sched *q = qdisc_priv(sch); + struct Qdisc *old_q; if (cl->level) return -EINVAL; - if (new == NULL && - (new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid)) == NULL) - return -ENOBUFS; - *old = qdisc_replace(sch, new, &cl->un.leaf.q); + if (q->offload) + dev_queue = htb_offload_get_queue(cl); + + if (!new) { + new = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + cl->common.classid, extack); + if (!new) + return -ENOBUFS; + } + + if (q->offload) { + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + qdisc_refcount_inc(new); + old_q = htb_graft_helper(dev_queue, new); + } + + *old = qdisc_replace(sch, new, &cl->leaf.q); + + if (q->offload) { + WARN_ON(old_q != *old); + qdisc_put(old_q); + } + return 0; } static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - return !cl->level ? cl->un.leaf.q : NULL; + return !cl->level ? cl->leaf.q : NULL; } static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - if (cl->un.leaf.q->q.qlen == 0) - htb_deactivate(qdisc_priv(sch), cl); -} - -static unsigned long htb_get(struct Qdisc *sch, u32 classid) -{ - struct htb_class *cl = htb_find(classid, sch); - if (cl) - cl->refcnt++; - return (unsigned long)cl; + htb_deactivate(qdisc_priv(sch), cl); } static inline int htb_parent_last_child(struct htb_class *cl) @@ -1209,32 +1502,110 @@ static inline int htb_parent_last_child(struct htb_class *cl) return 1; } -static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, +static void htb_parent_to_leaf(struct Qdisc *sch, struct htb_class *cl, struct Qdisc *new_q) { + struct htb_sched *q = qdisc_priv(sch); struct htb_class *parent = cl->parent; - WARN_ON(cl->level || !cl->un.leaf.q || cl->prio_activity); + WARN_ON(cl->level || !cl->leaf.q || cl->prio_activity); if (parent->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&parent->pq_node, &q->hlevel[parent->level].wait_pq); parent->level = 0; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); - INIT_LIST_HEAD(&parent->un.leaf.drop_list); - parent->un.leaf.q = new_q ? new_q : &noop_qdisc; + memset(&parent->inner, 0, sizeof(parent->inner)); + parent->leaf.q = new_q ? new_q : &noop_qdisc; parent->tokens = parent->buffer; parent->ctokens = parent->cbuffer; parent->t_c = ktime_get_ns(); parent->cmode = HTB_CAN_SEND; + if (q->offload) + parent->leaf.offload_queue = cl->leaf.offload_queue; +} + +static void htb_parent_to_leaf_offload(struct Qdisc *sch, + struct netdev_queue *dev_queue, + struct Qdisc *new_q) +{ + struct Qdisc *old_q; + + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + if (new_q) + qdisc_refcount_inc(new_q); + old_q = htb_graft_helper(dev_queue, new_q); + WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); +} + +static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, + bool last_child, bool destroying, + struct netlink_ext_ack *extack) +{ + struct tc_htb_qopt_offload offload_opt; + struct netdev_queue *dev_queue; + struct Qdisc *q = cl->leaf.q; + struct Qdisc *old; + int err; + + if (cl->level) + return -EINVAL; + + WARN_ON(!q); + dev_queue = htb_offload_get_queue(cl); + /* When destroying, caller qdisc_graft grafts the new qdisc and invokes + * qdisc_put for the qdisc being destroyed. htb_destroy_class_offload + * does not need to graft or qdisc_put the qdisc being destroyed. + */ + if (!destroying) { + old = htb_graft_helper(dev_queue, NULL); + /* Last qdisc grafted should be the same as cl->leaf.q when + * calling htb_delete. + */ + WARN_ON(old != q); + } + + if (cl->parent) { + _bstats_update(&cl->parent->bstats_bias, + u64_stats_read(&q->bstats.bytes), + u64_stats_read(&q->bstats.packets)); + } + + offload_opt = (struct tc_htb_qopt_offload) { + .command = !last_child ? TC_HTB_LEAF_DEL : + destroying ? TC_HTB_LEAF_DEL_LAST_FORCE : + TC_HTB_LEAF_DEL_LAST, + .classid = cl->common.classid, + .extack = extack, + }; + err = htb_offload(qdisc_dev(sch), &offload_opt); + + if (!destroying) { + if (!err) + qdisc_put(old); + else + htb_graft_helper(dev_queue, old); + } + + if (last_child) + return err; + + if (!err && offload_opt.classid != TC_H_MIN(cl->common.classid)) { + u32 classid = TC_H_MAJ(sch->handle) | + TC_H_MIN(offload_opt.classid); + struct htb_class *moved_cl = htb_find(classid, sch); + + htb_offload_move_qdisc(sch, moved_cl, cl, destroying); + } + + return err; } static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { - WARN_ON(!cl->un.leaf.q); - qdisc_destroy(cl->un.leaf.q); + WARN_ON(!cl->leaf.q); + qdisc_put(cl->leaf.q); } gen_kill_estimator(&cl->rate_est); tcf_block_put(cl->block); @@ -1243,8 +1614,11 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) static void htb_destroy(struct Qdisc *sch) { + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; struct htb_sched *q = qdisc_priv(sch); struct hlist_node *next; + bool nonempty, changed; struct htb_class *cl; unsigned int i; @@ -1258,98 +1632,152 @@ static void htb_destroy(struct Qdisc *sch) tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { tcf_block_put(cl->block); + cl->block = NULL; + } } - for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], - common.hnode) - htb_destroy_class(sch, cl); - } + + do { + nonempty = false; + changed = false; + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], + common.hnode) { + bool last_child; + + if (!q->offload) { + htb_destroy_class(sch, cl); + continue; + } + + nonempty = true; + + if (cl->level) + continue; + + changed = true; + + last_child = htb_parent_last_child(cl); + htb_destroy_class_offload(sch, cl, last_child, + true, NULL); + qdisc_class_hash_remove(&q->clhash, + &cl->common); + if (cl->parent) + cl->parent->children--; + if (last_child) + htb_parent_to_leaf(sch, cl, NULL); + htb_destroy_class(sch, cl); + } + } + } while (changed); + WARN_ON(nonempty); + qdisc_class_hash_destroy(&q->clhash); __qdisc_reset_queue(&q->direct_queue); + + if (q->offload) { + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_DESTROY, + }; + htb_offload(dev, &offload_opt); + } + + if (!q->direct_qdiscs) + return; + for (i = 0; i < q->num_direct_qdiscs && q->direct_qdiscs[i]; i++) + qdisc_put(q->direct_qdiscs[i]); + kfree(q->direct_qdiscs); } -static int htb_delete(struct Qdisc *sch, unsigned long arg) +static int htb_delete(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; struct Qdisc *new_q = NULL; int last_child = 0; + int err; /* TODO: why don't allow to delete subtree ? references ? does * tc subsys guarantee us that in htb_destroy it holds no class * refs so that we can remove children safely there ? */ - if (cl->children || cl->filter_cnt) + if (cl->children || qdisc_class_in_use(&cl->common)) { + NL_SET_ERR_MSG(extack, "HTB class in use"); return -EBUSY; + } - if (!cl->level && htb_parent_last_child(cl)) { - new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->parent->common.classid); + if (!cl->level && htb_parent_last_child(cl)) last_child = 1; + + if (q->offload) { + err = htb_destroy_class_offload(sch, cl, last_child, false, + extack); + if (err) + return err; } - sch_tree_lock(sch); + if (last_child) { + struct netdev_queue *dev_queue = sch->dev_queue; - if (!cl->level) { - unsigned int qlen = cl->un.leaf.q->q.qlen; - unsigned int backlog = cl->un.leaf.q->qstats.backlog; + if (q->offload) + dev_queue = htb_offload_get_queue(cl); - qdisc_reset(cl->un.leaf.q); - qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog); + new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + cl->parent->common.classid, + NULL); + if (q->offload) + htb_parent_to_leaf_offload(sch, dev_queue, new_q); } + sch_tree_lock(sch); + + if (!cl->level) + qdisc_purge_queue(cl->leaf.q); + /* delete from hash and active; remainder in destroy_class */ qdisc_class_hash_remove(&q->clhash, &cl->common); if (cl->parent) cl->parent->children--; - if (cl->prio_activity) - htb_deactivate(q, cl); + htb_deactivate(q, cl); if (cl->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&cl->pq_node, &q->hlevel[cl->level].wait_pq); if (last_child) - htb_parent_to_leaf(q, cl, new_q); - - BUG_ON(--cl->refcnt == 0); - /* - * This shouldn't happen: we "hold" one cops->get() when called - * from tc_ctl_tclass; the destroy method is done from cops->put(). - */ + htb_parent_to_leaf(sch, cl, new_q); sch_tree_unlock(sch); - return 0; -} - -static void htb_put(struct Qdisc *sch, unsigned long arg) -{ - struct htb_class *cl = (struct htb_class *)arg; - if (--cl->refcnt == 0) - htb_destroy_class(sch, cl); + htb_destroy_class(sch, cl); + return 0; } static int htb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg) + unsigned long *arg, struct netlink_ext_ack *extack) { int err = -EINVAL; struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; + struct tc_htb_qopt_offload offload_opt; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HTB_MAX + 1]; + struct Qdisc *parent_qdisc = NULL; + struct netdev_queue *dev_queue; struct tc_htb_opt *hopt; u64 rate64, ceil64; + int warn = 0; /* extract all subattrs from opt attr */ if (!opt) goto failure; - err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_HTB_MAX, opt, htb_policy, + extack); if (err < 0) goto failure; @@ -1363,15 +1791,33 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!hopt->rate.rate || !hopt->ceil.rate) goto failure; + if (q->offload) { + /* Options not supported by the offload. */ + if (hopt->rate.overhead || hopt->ceil.overhead) { + NL_SET_ERR_MSG(extack, "HTB offload doesn't support the overhead parameter"); + goto failure; + } + if (hopt->rate.mpu || hopt->ceil.mpu) { + NL_SET_ERR_MSG(extack, "HTB offload doesn't support the mpu parameter"); + goto failure; + } + } + /* Keeping backward compatible with rate_table based iproute2 tc */ if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) - qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB])); + qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB], + NULL)); if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) - qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB])); + qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB], + NULL)); + + rate64 = nla_get_u64_default(tb[TCA_HTB_RATE64], 0); + ceil64 = nla_get_u64_default(tb[TCA_HTB_CEIL64], 0); if (!cl) { /* new class */ - struct Qdisc *new_q; + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *new_q, *old_q; int prio; struct { struct nlattr nla; @@ -1395,7 +1841,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* check maximal depth */ if (parent && parent->parent && parent->parent->level < 2) { - pr_err("htb: tree is too deep\n"); + NL_SET_ERR_MSG_MOD(extack, "tree is too deep"); goto failure; } err = -ENOBUFS; @@ -1403,7 +1849,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + gnet_stats_basic_sync_init(&cl->bstats); + gnet_stats_basic_sync_init(&cl->bstats_bias); + + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); goto failure; @@ -1412,40 +1861,95 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE] ? : &est.nla); - if (err) { - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } + if (err) + goto err_block_put; } - cl->refcnt = 1; cl->children = 0; - INIT_LIST_HEAD(&cl->un.leaf.drop_list); RB_CLEAR_NODE(&cl->pq_node); for (prio = 0; prio < TC_HTB_NUMPRIO; prio++) RB_CLEAR_NODE(&cl->node[prio]); + cl->common.classid = classid; + + /* Make sure nothing interrupts us in between of two + * ndo_setup_tc calls. + */ + ASSERT_RTNL(); + /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) * so that can't be used inside of sch_tree_lock * -- thanks to Karlis Peisenieks */ - new_q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + if (!q->offload) { + dev_queue = sch->dev_queue; + } else if (!(parent && !parent->level)) { + /* Assign a dev_queue to this classid. */ + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_ALLOC_QUEUE, + .classid = cl->common.classid, + .parent_classid = parent ? + TC_H_MIN(parent->common.classid) : + TC_HTB_CLASSID_ROOT, + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .prio = hopt->prio, + .quantum = hopt->quantum, + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) { + NL_SET_ERR_MSG_WEAK(extack, + "Failed to offload TC_HTB_LEAF_ALLOC_QUEUE"); + goto err_kill_estimator; + } + dev_queue = netdev_get_tx_queue(dev, offload_opt.qid); + } else { /* First child. */ + dev_queue = htb_offload_get_queue(parent); + old_q = htb_graft_helper(dev_queue, NULL); + WARN_ON(old_q != parent->leaf.q); + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_TO_INNER, + .classid = cl->common.classid, + .parent_classid = + TC_H_MIN(parent->common.classid), + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .prio = hopt->prio, + .quantum = hopt->quantum, + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) { + NL_SET_ERR_MSG_WEAK(extack, + "Failed to offload TC_HTB_LEAF_TO_INNER"); + htb_graft_helper(dev_queue, old_q); + goto err_kill_estimator; + } + _bstats_update(&parent->bstats_bias, + u64_stats_read(&old_q->bstats.bytes), + u64_stats_read(&old_q->bstats.packets)); + qdisc_put(old_q); + } + new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + classid, NULL); + if (q->offload) { + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + if (new_q) + qdisc_refcount_inc(new_q); + old_q = htb_graft_helper(dev_queue, new_q); + /* No qdisc_put needed. */ + WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); + } sch_tree_lock(sch); if (parent && !parent->level) { - unsigned int qlen = parent->un.leaf.q->q.qlen; - unsigned int backlog = parent->un.leaf.q->qstats.backlog; - /* turn parent into inner node */ - qdisc_reset(parent->un.leaf.q); - qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); - qdisc_destroy(parent->un.leaf.q); - if (parent->prio_activity) - htb_deactivate(q, parent); + qdisc_purge_queue(parent->leaf.q); + parent_qdisc = parent->leaf.q; + htb_deactivate(q, parent); /* remove from evt list because of level change */ if (parent->cmode != HTB_CAN_SEND) { @@ -1454,12 +1958,14 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } parent->level = (parent->parent ? parent->parent->level : TC_HTB_MAXDEPTH) - 1; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); + memset(&parent->inner, 0, sizeof(parent->inner)); } + /* leaf (we) needs elementary qdisc */ - cl->un.leaf.q = new_q ? new_q : &noop_qdisc; + cl->leaf.q = new_q ? new_q : &noop_qdisc; + if (q->offload) + cl->leaf.offload_queue = dev_queue; - cl->common.classid = classid; cl->parent = parent; /* set class to be in HTB_CAN_SEND state */ @@ -1473,30 +1979,50 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; - if (cl->un.leaf.q != &noop_qdisc) - qdisc_hash_add(cl->un.leaf.q, true); + if (cl->leaf.q != &noop_qdisc) + qdisc_hash_add(cl->leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; } - sch_tree_lock(sch); - } - rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; + if (q->offload) { + struct net_device *dev = qdisc_dev(sch); + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_NODE_MODIFY, + .classid = cl->common.classid, + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .prio = hopt->prio, + .quantum = hopt->quantum, + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) + /* Estimator was replaced, and rollback may fail + * as well, so we don't try to recover it, and + * the estimator won't work property with the + * offload anyway, because bstats are updated + * only when the stats are queried. + */ + return err; + } - ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; + sch_tree_lock(sch); + } psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64); psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); /* it used to be a nasty bug here, we have to check that node - * is really leaf before changing cl->un.leaf ! + * is really leaf before changing cl->leaf ! */ if (!cl->level) { u64 quantum = cl->rate.rate_bytes_ps; @@ -1505,13 +2031,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->quantum = min_t(u64, quantum, INT_MAX); if (!hopt->quantum && cl->quantum < 1000) { - pr_warn("HTB: quantum of class %X is small. Consider r2q change.\n", - cl->common.classid); + warn = -1; cl->quantum = 1000; } if (!hopt->quantum && cl->quantum > 200000) { - pr_warn("HTB: quantum of class %X is big. Consider r2q change.\n", - cl->common.classid); + warn = 1; cl->quantum = 200000; } if (hopt->quantum) @@ -1524,17 +2048,29 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer); sch_tree_unlock(sch); + qdisc_put(parent_qdisc); + + if (warn) + NL_SET_ERR_MSG_FMT_MOD(extack, + "quantum of class %X is %s. Consider r2q change.", + cl->common.classid, (warn == -1 ? "small" : "big")); qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; +err_kill_estimator: + gen_kill_estimator(&cl->rate_est); +err_block_put: + tcf_block_put(cl->block); + kfree(cl); failure: return err; } -static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; @@ -1557,7 +2093,7 @@ static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, * be broken by class during destroy IIUC. */ if (cl) - cl->filter_cnt++; + qdisc_class_get(&cl->common); return (unsigned long)cl; } @@ -1565,8 +2101,7 @@ static void htb_unbind_filter(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - if (cl) - cl->filter_cnt--; + qdisc_class_put(&cl->common); } static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) @@ -1580,25 +2115,18 @@ static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, (unsigned long)cl, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) return; - } - arg->count++; } } } static const struct Qdisc_class_ops htb_class_ops = { + .select_queue = htb_select_queue, .graft = htb_graft, .leaf = htb_leaf, .qlen_notify = htb_qlen_notify, - .get = htb_get, - .put = htb_put, + .find = htb_search, .change = htb_change_class, .delete = htb_delete, .walk = htb_walk, @@ -1617,11 +2145,13 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = { .dequeue = htb_dequeue, .peek = qdisc_peek_dequeued, .init = htb_init, + .attach = htb_attach, .reset = htb_reset, .destroy = htb_destroy, .dump = htb_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("htb"); static int __init htb_module_init(void) { @@ -1635,3 +2165,4 @@ static void __exit htb_module_exit(void) module_init(htb_module_init) module_exit(htb_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Hierarchical Token Bucket scheduler"); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index d8a9bebcab90..cc6051d4f2ef 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -1,10 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* net/sched/sch_ingress.c - Ingress and clsact qdisc * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Jamal Hadi Salim 1999 */ @@ -17,9 +13,12 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> +#include <net/tcx.h> struct ingress_sched_data { struct tcf_block *block; + struct tcf_block_ext_info block_info; + struct mini_Qdisc_pair miniqp; }; static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) @@ -27,23 +26,18 @@ static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) return NULL; } -static unsigned long ingress_get(struct Qdisc *sch, u32 classid) +static unsigned long ingress_find(struct Qdisc *sch, u32 classid) { return TC_H_MIN(classid) + 1; } -static bool ingress_cl_offload(u32 classid) -{ - return true; -} - static unsigned long ingress_bind_filter(struct Qdisc *sch, unsigned long parent, u32 classid) { - return ingress_get(sch, classid); + return ingress_find(sch, classid); } -static void ingress_put(struct Qdisc *sch, unsigned long cl) +static void ingress_unbind_filter(struct Qdisc *sch, unsigned long cl) { } @@ -51,25 +45,66 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) { } -static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct ingress_sched_data *q = qdisc_priv(sch); return q->block; } -static int ingress_init(struct Qdisc *sch, struct nlattr *opt) +static void clsact_chain_head_change(struct tcf_proto *tp_head, void *priv) +{ + struct mini_Qdisc_pair *miniqp = priv; + + mini_qdisc_pair_swap(miniqp, tp_head); +}; + +static void ingress_ingress_block_set(struct Qdisc *sch, u32 block_index) +{ + struct ingress_sched_data *q = qdisc_priv(sch); + + q->block_info.block_index = block_index; +} + +static u32 ingress_ingress_block_get(struct Qdisc *sch) +{ + struct ingress_sched_data *q = qdisc_priv(sch); + + return q->block_info.block_index; +} + +static int ingress_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *entry; + bool created; int err; - err = tcf_block_get(&q->block, &dev->ingress_cl_list); + if (sch->parent != TC_H_INGRESS) + return -EOPNOTSUPP; + + net_inc_ingress_queue(); + + entry = tcx_entry_fetch_or_create(dev, true, &created); + if (!entry) + return -ENOMEM; + tcx_miniq_inc(entry); + mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq); + if (created) + tcx_entry_update(dev, entry, true); + + q->block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + q->block_info.chain_head_change = clsact_chain_head_change; + q->block_info.chain_head_change_priv = &q->miniqp; + + err = tcf_block_get_ext(&q->block, sch, &q->block_info, extack); if (err) return err; - net_inc_ingress_queue(); - sch->flags |= TCQ_F_CPUSTATS; + mini_qdisc_pair_block_init(&q->miniqp, q->block); return 0; } @@ -77,8 +112,22 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *entry = rtnl_dereference(dev->tcx_ingress); + + if (sch->parent != TC_H_INGRESS) + return; + + tcf_block_put_ext(q->block, sch, &q->block_info); + + if (entry) { + tcx_miniq_dec(entry); + if (!tcx_entry_is_active(entry)) { + tcx_entry_update(dev, NULL, true); + tcx_entry_free(entry); + } + } - tcf_block_put(q->block); net_dec_ingress_queue(); } @@ -86,7 +135,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb) { struct nlattr *nest; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -98,32 +147,39 @@ nla_put_failure: } static const struct Qdisc_class_ops ingress_class_ops = { + .flags = QDISC_CLASS_OPS_DOIT_UNLOCKED, .leaf = ingress_leaf, - .get = ingress_get, - .put = ingress_put, + .find = ingress_find, .walk = ingress_walk, .tcf_block = ingress_tcf_block, - .tcf_cl_offload = ingress_cl_offload, .bind_tcf = ingress_bind_filter, - .unbind_tcf = ingress_put, + .unbind_tcf = ingress_unbind_filter, }; static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { - .cl_ops = &ingress_class_ops, - .id = "ingress", - .priv_size = sizeof(struct ingress_sched_data), - .init = ingress_init, - .destroy = ingress_destroy, - .dump = ingress_dump, - .owner = THIS_MODULE, + .cl_ops = &ingress_class_ops, + .id = "ingress", + .priv_size = sizeof(struct ingress_sched_data), + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, + .init = ingress_init, + .destroy = ingress_destroy, + .dump = ingress_dump, + .ingress_block_set = ingress_ingress_block_set, + .ingress_block_get = ingress_ingress_block_get, + .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("ingress"); struct clsact_sched_data { struct tcf_block *ingress_block; struct tcf_block *egress_block; + struct tcf_block_ext_info ingress_block_info; + struct tcf_block_ext_info egress_block_info; + struct mini_Qdisc_pair miniqp_ingress; + struct mini_Qdisc_pair miniqp_egress; }; -static unsigned long clsact_get(struct Qdisc *sch, u32 classid) +static unsigned long clsact_find(struct Qdisc *sch, u32 classid) { switch (TC_H_MIN(classid)) { case TC_H_MIN(TC_H_MIN_INGRESS): @@ -134,18 +190,14 @@ static unsigned long clsact_get(struct Qdisc *sch, u32 classid) } } -static bool clsact_cl_offload(u32 classid) -{ - return TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS); -} - static unsigned long clsact_bind_filter(struct Qdisc *sch, unsigned long parent, u32 classid) { - return clsact_get(sch, classid); + return clsact_find(sch, classid); } -static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct clsact_sched_data *q = qdisc_priv(sch); @@ -159,59 +211,141 @@ static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl) } } -static int clsact_init(struct Qdisc *sch, struct nlattr *opt) +static void clsact_ingress_block_set(struct Qdisc *sch, u32 block_index) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + q->ingress_block_info.block_index = block_index; +} + +static void clsact_egress_block_set(struct Qdisc *sch, u32 block_index) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + q->egress_block_info.block_index = block_index; +} + +static u32 clsact_ingress_block_get(struct Qdisc *sch) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + return q->ingress_block_info.block_index; +} + +static u32 clsact_egress_block_get(struct Qdisc *sch) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + return q->egress_block_info.block_index; +} + +static int clsact_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct clsact_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *entry; + bool created; int err; - err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); - if (err) - return err; + if (sch->parent != TC_H_CLSACT) + return -EOPNOTSUPP; + + net_inc_ingress_queue(); + net_inc_egress_queue(); - err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + entry = tcx_entry_fetch_or_create(dev, true, &created); + if (!entry) + return -ENOMEM; + tcx_miniq_inc(entry); + mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq); + if (created) + tcx_entry_update(dev, entry, true); + + q->ingress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + q->ingress_block_info.chain_head_change = clsact_chain_head_change; + q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress; + + err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info, + extack); if (err) return err; - net_inc_ingress_queue(); - net_inc_egress_queue(); + mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block); - sch->flags |= TCQ_F_CPUSTATS; + entry = tcx_entry_fetch_or_create(dev, false, &created); + if (!entry) + return -ENOMEM; + tcx_miniq_inc(entry); + mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq); + if (created) + tcx_entry_update(dev, entry, false); - return 0; + q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS; + q->egress_block_info.chain_head_change = clsact_chain_head_change; + q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; + + return tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info, extack); } static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *ingress_entry = rtnl_dereference(dev->tcx_ingress); + struct bpf_mprog_entry *egress_entry = rtnl_dereference(dev->tcx_egress); + + if (sch->parent != TC_H_CLSACT) + return; - tcf_block_put(q->egress_block); - tcf_block_put(q->ingress_block); + tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); + + if (ingress_entry) { + tcx_miniq_dec(ingress_entry); + if (!tcx_entry_is_active(ingress_entry)) { + tcx_entry_update(dev, NULL, true); + tcx_entry_free(ingress_entry); + } + } + + if (egress_entry) { + tcx_miniq_dec(egress_entry); + if (!tcx_entry_is_active(egress_entry)) { + tcx_entry_update(dev, NULL, false); + tcx_entry_free(egress_entry); + } + } net_dec_ingress_queue(); net_dec_egress_queue(); } static const struct Qdisc_class_ops clsact_class_ops = { + .flags = QDISC_CLASS_OPS_DOIT_UNLOCKED, .leaf = ingress_leaf, - .get = clsact_get, - .put = ingress_put, + .find = clsact_find, .walk = ingress_walk, .tcf_block = clsact_tcf_block, - .tcf_cl_offload = clsact_cl_offload, .bind_tcf = clsact_bind_filter, - .unbind_tcf = ingress_put, + .unbind_tcf = ingress_unbind_filter, }; static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { - .cl_ops = &clsact_class_ops, - .id = "clsact", - .priv_size = sizeof(struct clsact_sched_data), - .init = clsact_init, - .destroy = clsact_destroy, - .dump = ingress_dump, - .owner = THIS_MODULE, + .cl_ops = &clsact_class_ops, + .id = "clsact", + .priv_size = sizeof(struct clsact_sched_data), + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, + .init = clsact_init, + .destroy = clsact_destroy, + .dump = ingress_dump, + .ingress_block_set = clsact_ingress_block_set, + .egress_block_set = clsact_egress_block_set, + .ingress_block_get = clsact_ingress_block_get, + .egress_block_get = clsact_egress_block_get, + .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("clsact"); static int __init ingress_module_init(void) { @@ -236,5 +370,5 @@ static void __exit ingress_module_exit(void) module_init(ingress_module_init); module_exit(ingress_module_exit); -MODULE_ALIAS("sch_clsact"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Ingress and clsact based ingress and egress qdiscs"); diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index cadfdd4f1e52..c860119a8f09 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_mq.c Classful multiqueue dummy scheduler * * Copyright (c) 2009 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. */ #include <linux/types.h> @@ -16,26 +13,59 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <net/netlink.h> +#include <net/pkt_cls.h> #include <net/pkt_sched.h> +#include <net/sch_generic.h> struct mq_sched { struct Qdisc **qdiscs; }; +static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_mq_qopt_offload opt = { + .command = cmd, + .handle = sch->handle, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); +} + +static int mq_offload_stats(struct Qdisc *sch) +{ + struct tc_mq_qopt_offload opt = { + .command = TC_MQ_STATS, + .handle = sch->handle, + .stats = { + .bstats = &sch->bstats, + .qstats = &sch->qstats, + }, + }; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt); +} + static void mq_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); unsigned int ntx; + mq_offload(sch, TC_MQ_DESTROY); + if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } -static int mq_init(struct Qdisc *sch, struct nlattr *opt) +static int mq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); @@ -59,7 +89,8 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) dev_queue = netdev_get_tx_queue(dev, ntx); qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx), TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(ntx + 1))); + TC_H_MIN(ntx + 1)), + extack); if (!qdisc) return -ENOMEM; priv->qdiscs[ntx] = qdisc; @@ -67,6 +98,8 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) } sch->flags |= TCQ_F_MQROOT; + + mq_offload(sch, TC_MQ_CREATE); return 0; } @@ -81,7 +114,7 @@ static void mq_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); @@ -99,22 +132,28 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) unsigned int ntx; sch->q.qlen = 0; - memset(&sch->bstats, 0, sizeof(sch->bstats)); + gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); + /* MQ supports lockless qdiscs. However, statistics accounting needs + * to account for all, none, or a mix of locked and unlocked child + * qdiscs. Percpu stats are added to counters in-band and locking + * qdisc totals are added at end. + */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { - qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; + + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); + spin_unlock_bh(qdisc_lock(qdisc)); } - return 0; + + return mq_offload_stats(sch); } static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) @@ -130,21 +169,14 @@ static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) static struct netdev_queue *mq_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { - unsigned int ntx = TC_H_MIN(tcm->tcm_parent); - struct netdev_queue *dev_queue = mq_queue_get(sch, ntx); - - if (!dev_queue) { - struct net_device *dev = qdisc_dev(sch); - - return netdev_get_tx_queue(dev, 0); - } - return dev_queue; + return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); + struct tc_mq_qopt_offload graft_offload; struct net_device *dev = qdisc_dev(sch); if (dev->flags & IFF_UP) @@ -155,6 +187,14 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); + + graft_offload.handle = sch->handle; + graft_offload.graft_params.queue = cl - 1; + graft_offload.graft_params.child_handle = new ? new->handle : 0; + graft_offload.command = TC_MQ_GRAFT; + + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old, + TC_SETUP_QDISC_MQ, &graft_offload, extack); return 0; } @@ -162,10 +202,10 @@ static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } -static unsigned long mq_get(struct Qdisc *sch, u32 classid) +static unsigned long mq_find(struct Qdisc *sch, u32 classid) { unsigned int ntx = TC_H_MIN(classid); @@ -174,10 +214,6 @@ static unsigned long mq_get(struct Qdisc *sch, u32 classid) return ntx; } -static void mq_put(struct Qdisc *sch, unsigned long cl) -{ -} - static int mq_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { @@ -185,7 +221,7 @@ static int mq_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } @@ -194,9 +230,9 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) + sch = rtnl_dereference(dev_queue->qdisc_sleeping); + if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || + qdisc_qstats_copy(d, sch) < 0) return -1; return 0; } @@ -211,11 +247,8 @@ static void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg) arg->count = arg->skip; for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { - if (arg->fn(sch, ntx + 1, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, ntx + 1, arg)) break; - } - arg->count++; } } @@ -223,8 +256,7 @@ static const struct Qdisc_class_ops mq_class_ops = { .select_queue = mq_select_queue, .graft = mq_graft, .leaf = mq_leaf, - .get = mq_get, - .put = mq_put, + .find = mq_find, .walk = mq_walk, .dump = mq_dump_class, .dump_stats = mq_dump_class_stats, @@ -237,6 +269,7 @@ struct Qdisc_ops mq_qdisc_ops __read_mostly = { .init = mq_init, .destroy = mq_destroy, .attach = mq_attach, + .change_real_num_tx = mq_change_real_num_tx, .dump = mq_dump, .owner = THIS_MODULE, }; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index e0c02725cd48..f3e5ef9a9592 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -1,13 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_mqprio.c * * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. */ +#include <linux/ethtool_netlink.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/kernel.h> @@ -18,12 +16,82 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> +#include <net/pkt_cls.h> + +#include "sch_mqprio_lib.h" struct mqprio_sched { struct Qdisc **qdiscs; + u16 mode; + u16 shaper; int hw_offload; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; + u32 fp[TC_QOPT_MAX_QUEUE]; }; +static int mqprio_enable_offload(struct Qdisc *sch, + const struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack) +{ + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt_offload mqprio = { + .qopt = *qopt, + .extack = extack, + }; + int err, i; + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + + mqprio_fp_to_offload(priv->fp, &mqprio); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + if (err) + return err; + + priv->hw_offload = mqprio.qopt.hw; + + return 0; +} + +static void mqprio_disable_offload(struct Qdisc *sch) +{ + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + break; + } +} + static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); @@ -34,34 +102,21 @@ static void mqprio_destroy(struct Qdisc *sch) for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } - if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt offload = { 0 }; - struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, - { .mqprio = &offload } }; - - dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, 0, &tc); - } else { + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) + mqprio_disable_offload(sch); + else netdev_set_num_tc(dev, 0); - } } -static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) +static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + const struct tc_mqprio_caps *caps, + struct netlink_ext_ack *extack) { - int i, j; - - /* Verify num_tc is not out of max range */ - if (qopt->num_tc > TC_MAX_QUEUE) - return -EINVAL; - - /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { - if (qopt->prio_tc_map[i] >= qopt->num_tc) - return -EINVAL; - } + int err; /* Limit qopt->hw to maximum supported offload value. Drivers have * the option of overriding this later if they don't support the a @@ -70,36 +125,225 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX) qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX; - /* If hardware offload is requested we will leave it to the device - * to either populate the queue counts itself or to validate the - * provided queue counts. If ndo_setup_tc is not present then - * hardware doesn't support offload and we should return an error. + /* If hardware offload is requested, we will leave 3 options to the + * device driver: + * - populate the queue counts itself (and ignore what was requested) + * - validate the provided queue counts by itself (and apply them) + * - request queue count validation here (and apply them) + */ + err = mqprio_validate_qopt(dev, qopt, + !qopt->hw || caps->validate_queue_counts, + false, extack); + if (err) + return err; + + /* If ndo_setup_tc is not present then hardware doesn't support offload + * and we should return an error. */ - if (qopt->hw) - return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL; + if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, + "Device does not support hardware offload"); + return -EINVAL; + } - for (i = 0; i < qopt->num_tc; i++) { - unsigned int last = qopt->offset[i] + qopt->count[i]; + return 0; +} - /* Verify the queue count is in tx range being equal to the - * real_num_tx_queues indicates the last queue is in use. - */ - if (qopt->offset[i] >= dev->real_num_tx_queues || - !qopt->count[i] || - last > dev->real_num_tx_queues) +static const struct +nla_policy mqprio_tc_entry_policy[TCA_MQPRIO_TC_ENTRY_MAX + 1] = { + [TCA_MQPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, + TC_QOPT_MAX_QUEUE - 1), + [TCA_MQPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32, + TC_FP_EXPRESS, + TC_FP_PREEMPTIBLE), +}; + +static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = { + [TCA_MQPRIO_MODE] = { .len = sizeof(u16) }, + [TCA_MQPRIO_SHAPER] = { .len = sizeof(u16) }, + [TCA_MQPRIO_MIN_RATE64] = { .type = NLA_NESTED }, + [TCA_MQPRIO_MAX_RATE64] = { .type = NLA_NESTED }, + [TCA_MQPRIO_TC_ENTRY] = { .type = NLA_NESTED }, +}; + +static int mqprio_parse_tc_entry(u32 fp[TC_QOPT_MAX_QUEUE], + struct nlattr *opt, + unsigned long *seen_tcs, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_MQPRIO_TC_ENTRY_MAX + 1]; + int err, tc; + + err = nla_parse_nested(tb, TCA_MQPRIO_TC_ENTRY_MAX, opt, + mqprio_tc_entry_policy, extack); + if (err < 0) + return err; + + if (NL_REQ_ATTR_CHECK(extack, opt, tb, TCA_MQPRIO_TC_ENTRY_INDEX)) { + NL_SET_ERR_MSG(extack, "TC entry index missing"); + return -EINVAL; + } + + tc = nla_get_u32(tb[TCA_MQPRIO_TC_ENTRY_INDEX]); + if (*seen_tcs & BIT(tc)) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_TC_ENTRY_INDEX], + "Duplicate tc entry"); + return -EINVAL; + } + + *seen_tcs |= BIT(tc); + + if (tb[TCA_MQPRIO_TC_ENTRY_FP]) + fp[tc] = nla_get_u32(tb[TCA_MQPRIO_TC_ENTRY_FP]); + + return 0; +} + +static int mqprio_parse_tc_entries(struct Qdisc *sch, struct nlattr *nlattr_opt, + int nlattr_opt_len, + struct netlink_ext_ack *extack) +{ + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + bool have_preemption = false; + unsigned long seen_tcs = 0; + u32 fp[TC_QOPT_MAX_QUEUE]; + struct nlattr *n; + int tc, rem; + int err = 0; + + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) + fp[tc] = priv->fp[tc]; + + nla_for_each_attr_type(n, TCA_MQPRIO_TC_ENTRY, nlattr_opt, + nlattr_opt_len, rem) { + err = mqprio_parse_tc_entry(fp, n, &seen_tcs, extack); + if (err) + goto out; + } + + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { + priv->fp[tc] = fp[tc]; + if (fp[tc] == TC_FP_PREEMPTIBLE) + have_preemption = true; + } + + if (have_preemption && !ethtool_dev_mm_supported(dev)) { + NL_SET_ERR_MSG(extack, "Device does not support preemption"); + return -EOPNOTSUPP; + } +out: + return err; +} + +/* Parse the other netlink attributes that represent the payload of + * TCA_OPTIONS, which are appended right after struct tc_mqprio_qopt. + */ +static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt, + struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct nlattr *nlattr_opt = nla_data(opt) + NLA_ALIGN(sizeof(*qopt)); + int nlattr_opt_len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); + struct mqprio_sched *priv = qdisc_priv(sch); + struct nlattr *tb[TCA_MQPRIO_MAX + 1] = {}; + struct nlattr *attr; + int i, rem, err; + + if (nlattr_opt_len >= nla_attr_size(0)) { + err = nla_parse_deprecated(tb, TCA_MQPRIO_MAX, nlattr_opt, + nlattr_opt_len, mqprio_policy, + NULL); + if (err < 0) + return err; + } + + if (!qopt->hw) { + NL_SET_ERR_MSG(extack, + "mqprio TCA_OPTIONS can only contain netlink attributes in hardware mode"); + return -EINVAL; + } + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = nla_get_u16(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = nla_get_u16(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MIN_RATE64], + "min_rate accepted only when shaper is in bw_rlimit mode"); + return -EINVAL; + } + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute type expected to be TCA_MQPRIO_MIN_RATE64"); + return -EINVAL; + } + + if (nla_len(attr) != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute TCA_MQPRIO_MIN_RATE64 expected to have 8 bytes length"); + return -EINVAL; + } + + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = nla_get_u64(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MAX_RATE64], + "max_rate accepted only when shaper is in bw_rlimit mode"); return -EINVAL; + } + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute type expected to be TCA_MQPRIO_MAX_RATE64"); + return -EINVAL; + } - /* Verify that the offset and counts do not overlap */ - for (j = i + 1; j < qopt->num_tc; j++) { - if (last > qopt->offset[j]) + if (nla_len(attr) != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute TCA_MQPRIO_MAX_RATE64 expected to have 8 bytes length"); return -EINVAL; + } + + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = nla_get_u64(attr); + i++; } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + + if (tb[TCA_MQPRIO_TC_ENTRY]) { + err = mqprio_parse_tc_entries(sch, nlattr_opt, nlattr_opt_len, + extack); + if (err) + return err; } return 0; } -static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) +static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); @@ -107,6 +351,8 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; + struct tc_mqprio_caps caps; + int len, tc; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); @@ -117,13 +363,30 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; + /* make certain can allocate enough classids to handle queues */ + if (dev->num_tx_queues >= TC_H_MIN_PRIORITY) + return -ENOMEM; + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) + priv->fp[tc] = TC_FP_EXPRESS; + + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_MQPRIO, + &caps, sizeof(caps)); + qopt = nla_data(opt); - if (mqprio_parse_opt(dev, qopt)) + if (mqprio_parse_opt(dev, qopt, &caps, extack)) return -EINVAL; + len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); + if (len > 0) { + err = mqprio_parse_nlattr(sch, qopt, opt, extack); + if (err) + return err; + } + /* pre-allocate qdisc, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); @@ -135,7 +398,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, i), TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1))); + TC_H_MIN(i + 1)), extack); if (!qdisc) return -ENOMEM; @@ -148,16 +411,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt offload = *qopt; - struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, - { .mqprio = &offload } }; - - err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, - 0, 0, &tc); + err = mqprio_enable_offload(sch, qopt, extack); if (err) return err; - - priv->hw_offload = offload.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -185,7 +441,7 @@ static void mqprio_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); } @@ -197,7 +453,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); - unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; @@ -205,7 +461,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, } static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); @@ -227,47 +483,129 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, return 0; } +static int dump_rates(struct mqprio_sched *priv, + struct tc_mqprio_qopt *opt, struct sk_buff *skb) +{ + struct nlattr *nest; + int i; + + if (priv->flags & TC_MQPRIO_F_MIN_RATE) { + nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MIN_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MIN_RATE64, + sizeof(priv->min_rate[i]), + &priv->min_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + + if (priv->flags & TC_MQPRIO_F_MAX_RATE) { + nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MAX_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MAX_RATE64, + sizeof(priv->max_rate[i]), + &priv->max_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static int mqprio_dump_tc_entries(struct mqprio_sched *priv, + struct sk_buff *skb) +{ + struct nlattr *n; + int tc; + + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { + n = nla_nest_start(skb, TCA_MQPRIO_TC_ENTRY); + if (!n) + return -EMSGSIZE; + + if (nla_put_u32(skb, TCA_MQPRIO_TC_ENTRY_INDEX, tc)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_MQPRIO_TC_ENTRY_FP, priv->fp[tc])) + goto nla_put_failure; + + nla_nest_end(skb, n); + } + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, n); + return -EMSGSIZE; +} + static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; - unsigned int i; + unsigned int ntx; sch->q.qlen = 0; - memset(&sch->bstats, 0, sizeof(sch->bstats)); + gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); - for (i = 0; i < dev->num_tx_queues; i++) { - qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); + /* MQ supports lockless qdiscs. However, statistics accounting needs + * to account for all, none, or a mix of locked and unlocked child + * qdiscs. Percpu stats are added to counters in-band and locking + * qdisc totals are added at end. + */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; + + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); + spin_unlock_bh(qdisc_lock(qdisc)); } - opt.num_tc = netdev_get_num_tc(dev); - memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + mqprio_qopt_reconstruct(dev, &opt); opt.hw = priv->hw_offload; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - opt.count[i] = dev->tc_to_txq[i].count; - opt.offset[i] = dev->tc_to_txq[i].offset; - } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; - return skb->len; + if ((priv->flags & TC_MQPRIO_F_MODE) && + nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_SHAPER) && + nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MIN_RATE || + priv->flags & TC_MQPRIO_F_MAX_RATE) && + (dump_rates(priv, &opt, skb) != 0)) + goto nla_put_failure; + + if (mqprio_dump_tc_entries(priv, skb)) + goto nla_put_failure; + + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } @@ -278,50 +616,43 @@ static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl) if (!dev_queue) return NULL; - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } -static unsigned long mqprio_get(struct Qdisc *sch, u32 classid) +static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) { struct net_device *dev = qdisc_dev(sch); unsigned int ntx = TC_H_MIN(classid); - if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) - return 0; - return ntx; -} + /* There are essentially two regions here that have valid classid + * values. The first region will have a classid value of 1 through + * num_tx_queues. All of these are backed by actual Qdiscs. + */ + if (ntx < TC_H_MIN_PRIORITY) + return (ntx <= dev->num_tx_queues) ? ntx : 0; -static void mqprio_put(struct Qdisc *sch, unsigned long cl) -{ + /* The second region represents the hardware traffic classes. These + * are represented by classid values of TC_H_MIN_PRIORITY through + * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1 + */ + return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0; } static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { - struct net_device *dev = qdisc_dev(sch); + if (cl < TC_H_MIN_PRIORITY) { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + struct net_device *dev = qdisc_dev(sch); + int tc = netdev_txq_to_tc(dev, cl - 1); - if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = (tc < 0) ? 0 : + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(tc + TC_H_MIN_PRIORITY)); + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; + } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; - } else { - int i; - struct netdev_queue *dev_queue; - - dev_queue = mqprio_queue_get(sch, cl); - tcm->tcm_parent = 0; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - struct netdev_tc_txq tc = dev->tc_to_txq[i]; - int q_idx = cl - netdev_get_num_tc(dev); - - if (q_idx > tc.offset && - q_idx <= tc.offset + tc.count) { - tcm->tcm_parent = - TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1)); - break; - } - } - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; } tcm->tcm_handle |= TC_H_MIN(cl); return 0; @@ -332,16 +663,15 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, __releases(d->lock) __acquires(d->lock) { - struct net_device *dev = qdisc_dev(sch); - - if (cl <= netdev_get_num_tc(dev)) { + if (cl >= TC_H_MIN_PRIORITY) { int i; - __u32 qlen = 0; - struct Qdisc *qdisc; + __u32 qlen; struct gnet_stats_queue qstats = {0}; - struct gnet_stats_basic_packed bstats = {0}; - struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + struct gnet_stats_basic_sync bstats; + struct net_device *dev = qdisc_dev(sch); + struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; + gnet_stats_basic_sync_init(&bstats); /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we * hold here is the look on dev_queue->qdisc_sleeping @@ -352,32 +682,33 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, for (i = tc.offset; i < tc.offset + tc.count; i++) { struct netdev_queue *q = netdev_get_tx_queue(dev, i); + struct Qdisc *qdisc = rtnl_dereference(q->qdisc); - qdisc = rtnl_dereference(q->qdisc); spin_lock_bh(qdisc_lock(qdisc)); - qlen += qdisc->q.qlen; - bstats.bytes += qdisc->bstats.bytes; - bstats.packets += qdisc->bstats.packets; - qstats.backlog += qdisc->qstats.backlog; - qstats.drops += qdisc->qstats.drops; - qstats.requeues += qdisc->qstats.requeues; - qstats.overlimits += qdisc->qstats.overlimits; + + gnet_stats_add_basic(&bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); + spin_unlock_bh(qdisc_lock(qdisc)); } + qlen = qdisc_qlen(sch) + qstats.qlen; + /* Reclaim root sleeping lock before completing stats */ if (d->lock) spin_lock_bh(d->lock); - if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &bstats, false) < 0 || gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0) return -1; } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &sch->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, - &sch->qstats, sch->q.qlen) < 0) + sch = rtnl_dereference(dev_queue->qdisc_sleeping); + if (gnet_stats_copy_basic(d, sch->cpu_bstats, + &sch->bstats, true) < 0 || + qdisc_qstats_copy(d, sch) < 0) return -1; } return 0; @@ -393,25 +724,41 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) /* Walk hierarchy with a virtual class per tc */ arg->count = arg->skip; - for (ntx = arg->skip; - ntx < dev->num_tx_queues + netdev_get_num_tc(dev); - ntx++) { + for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) { + if (!tc_qdisc_stats_dump(sch, ntx + TC_H_MIN_PRIORITY, arg)) + return; + } + + /* Pad the values and skip over unused traffic classes */ + if (ntx < TC_MAX_QUEUE) { + arg->count = TC_MAX_QUEUE; + ntx = TC_MAX_QUEUE; + } + + /* Reset offset, sort out remaining per-queue qdiscs */ + for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) { if (arg->fn(sch, ntx + 1, arg) < 0) { arg->stop = 1; - break; + return; } arg->count++; } } +static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); +} + static const struct Qdisc_class_ops mqprio_class_ops = { .graft = mqprio_graft, .leaf = mqprio_leaf, - .get = mqprio_get, - .put = mqprio_put, + .find = mqprio_find, .walk = mqprio_walk, .dump = mqprio_dump_class, .dump_stats = mqprio_dump_class_stats, + .select_queue = mqprio_select_queue, }; static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { @@ -421,9 +768,11 @@ static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { .init = mqprio_init, .destroy = mqprio_destroy, .attach = mqprio_attach, + .change_real_num_tx = mq_change_real_num_tx, .dump = mqprio_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("mqprio"); static int __init mqprio_module_init(void) { @@ -439,3 +788,4 @@ module_init(mqprio_module_init); module_exit(mqprio_module_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Classful multiqueue prio qdisc"); diff --git a/net/sched/sch_mqprio_lib.c b/net/sched/sch_mqprio_lib.c new file mode 100644 index 000000000000..b3a5572c167b --- /dev/null +++ b/net/sched/sch_mqprio_lib.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/netlink.h> +#include <linux/types.h> +#include <net/pkt_sched.h> + +#include "sch_mqprio_lib.h" + +/* Returns true if the intervals [a, b) and [c, d) overlap. */ +static bool intervals_overlap(int a, int b, int c, int d) +{ + int left = max(a, c), right = min(b, d); + + return left < right; +} + +static int mqprio_validate_queue_counts(struct net_device *dev, + const struct tc_mqprio_qopt *qopt, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, j; + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + if (!qopt->count[i]) { + NL_SET_ERR_MSG_FMT_MOD(extack, "No queues for TC %d", + i); + return -EINVAL; + } + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->real_num_tx_queues || + last > dev->real_num_tx_queues) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Queues %d:%d for TC %d exceed the %d TX queues available", + qopt->count[i], qopt->offset[i], + i, dev->real_num_tx_queues); + return -EINVAL; + } + + if (allow_overlapping_txqs) + continue; + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (intervals_overlap(qopt->offset[i], last, + qopt->offset[j], + qopt->offset[j] + + qopt->count[j])) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "TC %d queues %d@%d overlap with TC %d queues %d@%d", + i, qopt->count[i], qopt->offset[i], + j, qopt->count[j], qopt->offset[j]); + return -EINVAL; + } + } + } + + return 0; +} + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, err; + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) { + NL_SET_ERR_MSG(extack, + "Number of traffic classes is outside valid range"); + return -EINVAL; + } + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i <= TC_BITMASK; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) { + NL_SET_ERR_MSG(extack, + "Invalid traffic class in priority to traffic class mapping"); + return -EINVAL; + } + } + + if (validate_queue_counts) { + err = mqprio_validate_queue_counts(dev, qopt, + allow_overlapping_txqs, + extack); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mqprio_validate_qopt); + +void mqprio_qopt_reconstruct(struct net_device *dev, struct tc_mqprio_qopt *qopt) +{ + int tc, num_tc = netdev_get_num_tc(dev); + + qopt->num_tc = num_tc; + memcpy(qopt->prio_tc_map, dev->prio_tc_map, sizeof(qopt->prio_tc_map)); + + for (tc = 0; tc < num_tc; tc++) { + qopt->count[tc] = dev->tc_to_txq[tc].count; + qopt->offset[tc] = dev->tc_to_txq[tc].offset; + } +} +EXPORT_SYMBOL_GPL(mqprio_qopt_reconstruct); + +void mqprio_fp_to_offload(u32 fp[TC_QOPT_MAX_QUEUE], + struct tc_mqprio_qopt_offload *mqprio) +{ + unsigned long preemptible_tcs = 0; + int tc; + + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) + if (fp[tc] == TC_FP_PREEMPTIBLE) + preemptible_tcs |= BIT(tc); + + mqprio->preemptible_tcs = preemptible_tcs; +} +EXPORT_SYMBOL_GPL(mqprio_fp_to_offload); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Shared mqprio qdisc code currently between taprio and mqprio"); diff --git a/net/sched/sch_mqprio_lib.h b/net/sched/sch_mqprio_lib.h new file mode 100644 index 000000000000..079f597072e3 --- /dev/null +++ b/net/sched/sch_mqprio_lib.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SCH_MQPRIO_LIB_H +#define __SCH_MQPRIO_LIB_H + +#include <linux/types.h> + +struct net_device; +struct netlink_ext_ack; +struct tc_mqprio_qopt; + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack); +void mqprio_qopt_reconstruct(struct net_device *dev, + struct tc_mqprio_qopt *qopt); +void mqprio_fp_to_offload(u32 fp[TC_QOPT_MAX_QUEUE], + struct tc_mqprio_qopt_offload *mqprio); + +#endif diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index f143b7bbaa0d..06e03f5cd7ce 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -1,18 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, Intel Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ @@ -47,13 +36,14 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tcf_classify(skb, fl, &res, false); + err = tcf_classify(skb, NULL, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return NULL; } @@ -162,7 +152,6 @@ multiq_reset(struct Qdisc *sch) for (band = 0; band < q->bands; band++) qdisc_reset(q->queues[band]); - sch->q.qlen = 0; q->curband = 0; } @@ -174,16 +163,18 @@ multiq_destroy(struct Qdisc *sch) tcf_block_put(q->block); for (band = 0; band < q->bands; band++) - qdisc_destroy(q->queues[band]); + qdisc_put(q->queues[band]); kfree(q->queues); } -static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) +static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); struct tc_multiq_qopt *qopt; - int i; + struct Qdisc **removed; + int i, n_removed = 0; if (!netif_is_multiqueue(qdisc_dev(sch))) return -EOPNOTSUPP; @@ -194,27 +185,36 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) qopt->bands = qdisc_dev(sch)->real_num_tx_queues; + removed = kmalloc(sizeof(*removed) * (q->max_bands - qopt->bands), + GFP_KERNEL); + if (!removed) + return -ENOMEM; + sch_tree_lock(sch); q->bands = qopt->bands; for (i = q->bands; i < q->max_bands; i++) { if (q->queues[i] != &noop_qdisc) { struct Qdisc *child = q->queues[i]; + q->queues[i] = &noop_qdisc; - qdisc_tree_reduce_backlog(child, child->q.qlen, - child->qstats.backlog); - qdisc_destroy(child); + qdisc_purge_queue(child); + removed[n_removed++] = child; } } sch_tree_unlock(sch); + for (i = 0; i < n_removed; i++) + qdisc_put(removed[i]); + kfree(removed); + for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, - i + 1)); + i + 1), extack); if (child) { sch_tree_lock(sch); old = q->queues[i]; @@ -222,30 +222,28 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) if (child != &noop_qdisc) qdisc_hash_add(child, true); - if (old != &noop_qdisc) { - qdisc_tree_reduce_backlog(old, - old->q.qlen, - old->qstats.backlog); - qdisc_destroy(old); - } + if (old != &noop_qdisc) + qdisc_purge_queue(old); sch_tree_unlock(sch); + qdisc_put(old); } } } return 0; } -static int multiq_init(struct Qdisc *sch, struct nlattr *opt) +static int multiq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); int i, err; q->queues = NULL; - if (opt == NULL) + if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; @@ -257,12 +255,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->max_bands; i++) q->queues[i] = &noop_qdisc; - err = multiq_tune(sch, opt); - - if (err) - kfree(q->queues); - - return err; + return multiq_tune(sch, opt, extack); } static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -285,7 +278,7 @@ nla_put_failure: } static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; @@ -306,7 +299,7 @@ multiq_leaf(struct Qdisc *sch, unsigned long arg) return q->queues[band]; } -static unsigned long multiq_get(struct Qdisc *sch, u32 classid) +static unsigned long multiq_find(struct Qdisc *sch, u32 classid) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = TC_H_MIN(classid); @@ -319,11 +312,11 @@ static unsigned long multiq_get(struct Qdisc *sch, u32 classid) static unsigned long multiq_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { - return multiq_get(sch, classid); + return multiq_find(sch, classid); } -static void multiq_put(struct Qdisc *q, unsigned long cl) +static void multiq_unbind(struct Qdisc *q, unsigned long cl) { } @@ -344,9 +337,8 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0) + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, &cl_q->bstats, true) < 0 || + qdisc_qstats_copy(d, cl_q) < 0) return -1; return 0; @@ -361,19 +353,13 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (band = 0; band < q->bands; band++) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, band + 1, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, band + 1, arg)) break; - } - arg->count++; } } -static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); @@ -385,12 +371,11 @@ static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl) static const struct Qdisc_class_ops multiq_class_ops = { .graft = multiq_graft, .leaf = multiq_leaf, - .get = multiq_get, - .put = multiq_put, + .find = multiq_find, .walk = multiq_walk, .tcf_block = multiq_tcf_block, .bind_tcf = multiq_bind, - .unbind_tcf = multiq_put, + .unbind_tcf = multiq_unbind, .dump = multiq_dump_class, .dump_stats = multiq_dump_class_stats, }; @@ -410,6 +395,7 @@ static struct Qdisc_ops multiq_qdisc_ops __read_mostly = { .dump = multiq_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("multiq"); static int __init multiq_module_init(void) { @@ -425,3 +411,4 @@ module_init(multiq_module_init) module_exit(multiq_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Multi queue to hardware queue mapping qdisc"); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 1b3dd6190e93..32a5f3304046 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_netem.c Network emulator * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License. - * * Many of the algorithms and ideas for this came from * NIST Net which is not copyrighted. * @@ -21,10 +17,12 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> +#include <linux/prandom.h> #include <linux/rtnetlink.h> #include <linux/reciprocal_div.h> #include <linux/rbtree.h> +#include <net/gso.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> @@ -68,17 +66,28 @@ Fabio Ludovici <fabio.ludovici at yahoo.it> */ +struct disttable { + u32 size; + s16 table[] __counted_by(size); +}; + struct netem_sched_data { /* internal t(ime)fifo qdisc uses t_root and sch->limit */ struct rb_root t_root; + /* a linear queue; reduces rbtree rebalancing when jitter is low */ + struct sk_buff *t_head; + struct sk_buff *t_tail; + + u32 t_len; + /* optional qdisc for classful handling (NULL at netem init) */ struct Qdisc *qdisc; struct qdisc_watchdog watchdog; - psched_tdiff_t latency; - psched_tdiff_t jitter; + s64 latency; + s64 jitter; u32 loss; u32 ecn; @@ -99,10 +108,12 @@ struct netem_sched_data { u32 rho; } delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor; - struct disttable { - u32 size; - s16 table[0]; - } *delay_dist; + struct prng { + u64 seed; + struct rnd_state prng_state; + } prng; + + struct disttable *delay_dist; enum { CLG_RANDOM, @@ -135,6 +146,14 @@ struct netem_sched_data { u32 a5; /* p23 used only in 4-states */ } clg; + struct tc_netem_slot slot_config; + struct slotstate { + u64 slot_next; + s32 packets_left; + s32 bytes_left; + } slot; + + struct disttable *slot_dist; }; /* Time stamp put into socket buffer control block @@ -145,16 +164,9 @@ struct netem_sched_data { * we save skb->tstamp value in skb->cb[] before destroying it. */ struct netem_skb_cb { - psched_time_t time_to_send; - ktime_t tstamp_save; + u64 time_to_send; }; - -static struct sk_buff *netem_rb_to_skb(struct rb_node *rb) -{ - return rb_entry(rb, struct sk_buff, rbnode); -} - static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ @@ -168,22 +180,23 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; - state->last = prandom_u32(); + state->last = get_random_u32(); } /* get_crandom - correlated random number generator * Next number depends on last value. * rho is scaled to avoid floating point. */ -static u32 get_crandom(struct crndstate *state) +static u32 get_crandom(struct crndstate *state, struct prng *p) { u64 value, rho; unsigned long answer; + struct rnd_state *s = &p->prng_state; - if (state->rho == 0) /* no correlation */ - return prandom_u32(); + if (!state || state->rho == 0) /* no correlation */ + return prandom_u32_state(s); - value = prandom_u32(); + value = prandom_u32_state(s); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; @@ -197,7 +210,7 @@ static u32 get_crandom(struct crndstate *state) static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; - u32 rnd = prandom_u32(); + u32 rnd = prandom_u32_state(&q->prng.prng_state); /* * Makes a comparison between rnd and the transition @@ -205,17 +218,17 @@ static bool loss_4state(struct netem_sched_data *q) * next state and if the next packet has to be transmitted or lost. * The four states correspond to: * TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period - * LOST_IN_BURST_PERIOD => isolated losses within a gap period - * LOST_IN_GAP_PERIOD => lost packets within a burst period - * TX_IN_GAP_PERIOD => successfully transmitted packets within a burst period + * LOST_IN_GAP_PERIOD => isolated losses within a gap period + * LOST_IN_BURST_PERIOD => lost packets within a burst period + * TX_IN_BURST_PERIOD => successfully transmitted packets within a burst period */ switch (clg->state) { case TX_IN_GAP_PERIOD: if (rnd < clg->a4) { - clg->state = LOST_IN_BURST_PERIOD; + clg->state = LOST_IN_GAP_PERIOD; return true; } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { - clg->state = LOST_IN_GAP_PERIOD; + clg->state = LOST_IN_BURST_PERIOD; return true; } else if (clg->a1 + clg->a4 < rnd) { clg->state = TX_IN_GAP_PERIOD; @@ -224,24 +237,24 @@ static bool loss_4state(struct netem_sched_data *q) break; case TX_IN_BURST_PERIOD: if (rnd < clg->a5) { - clg->state = LOST_IN_GAP_PERIOD; + clg->state = LOST_IN_BURST_PERIOD; return true; } else { clg->state = TX_IN_BURST_PERIOD; } break; - case LOST_IN_GAP_PERIOD: + case LOST_IN_BURST_PERIOD: if (rnd < clg->a3) clg->state = TX_IN_BURST_PERIOD; else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { clg->state = TX_IN_GAP_PERIOD; } else if (clg->a2 + clg->a3 < rnd) { - clg->state = LOST_IN_GAP_PERIOD; + clg->state = LOST_IN_BURST_PERIOD; return true; } break; - case LOST_IN_BURST_PERIOD: + case LOST_IN_GAP_PERIOD: clg->state = TX_IN_GAP_PERIOD; break; } @@ -262,18 +275,19 @@ static bool loss_4state(struct netem_sched_data *q) static bool loss_gilb_ell(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; + struct rnd_state *s = &q->prng.prng_state; switch (clg->state) { case GOOD_STATE: - if (prandom_u32() < clg->a1) + if (prandom_u32_state(s) < clg->a1) clg->state = BAD_STATE; - if (prandom_u32() < clg->a4) + if (prandom_u32_state(s) < clg->a4) return true; break; case BAD_STATE: - if (prandom_u32() < clg->a2) + if (prandom_u32_state(s) < clg->a2) clg->state = GOOD_STATE; - if (prandom_u32() > clg->a3) + if (prandom_u32_state(s) > clg->a3) return true; } @@ -285,7 +299,7 @@ static bool loss_event(struct netem_sched_data *q) switch (q->loss_model) { case CLG_RANDOM: /* Random packet drop 0 => none, ~0 => all */ - return q->loss && q->loss >= get_crandom(&q->loss_cor); + return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng); case CLG_4_STATES: /* 4state loss model algorithm (used also for GI model) @@ -312,22 +326,23 @@ static bool loss_event(struct netem_sched_data *q) * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. */ -static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, - struct crndstate *state, - const struct disttable *dist) +static s64 tabledist(s64 mu, s32 sigma, + struct crndstate *state, + struct prng *prng, + const struct disttable *dist) { - psched_tdiff_t x; + s64 x; long t; u32 rnd; if (sigma == 0) return mu; - rnd = get_crandom(state); + rnd = get_crandom(state, prng); /* default uniform distribution */ if (dist == NULL) - return (rnd % (2*sigma)) - sigma + mu; + return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; @@ -339,10 +354,8 @@ static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, return x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu; } -static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sched_data *q) +static u64 packet_time_ns(u64 len, const struct netem_sched_data *q) { - u64 ticks; - len += q->packet_overhead; if (q->cell_size) { @@ -353,43 +366,56 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche len = cells * (q->cell_size + q->cell_overhead); } - ticks = (u64)len * NSEC_PER_SEC; - - do_div(ticks, q->rate); - return PSCHED_NS2TICKS(ticks); + return div64_u64(len * NSEC_PER_SEC, q->rate); } static void tfifo_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); - struct rb_node *p; + struct rb_node *p = rb_first(&q->t_root); - while ((p = rb_first(&q->t_root))) { - struct sk_buff *skb = netem_rb_to_skb(p); + while (p) { + struct sk_buff *skb = rb_to_skb(p); - rb_erase(p, &q->t_root); + p = rb_next(p); + rb_erase(&skb->rbnode, &q->t_root); rtnl_kfree_skbs(skb, skb); } + + rtnl_kfree_skbs(q->t_head, q->t_tail); + q->t_head = NULL; + q->t_tail = NULL; + q->t_len = 0; } static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); - psched_time_t tnext = netem_skb_cb(nskb)->time_to_send; - struct rb_node **p = &q->t_root.rb_node, *parent = NULL; - - while (*p) { - struct sk_buff *skb; + u64 tnext = netem_skb_cb(nskb)->time_to_send; - parent = *p; - skb = netem_rb_to_skb(parent); - if (tnext >= netem_skb_cb(skb)->time_to_send) - p = &parent->rb_right; + if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) { + if (q->t_tail) + q->t_tail->next = nskb; else - p = &parent->rb_left; + q->t_head = nskb; + q->t_tail = nskb; + } else { + struct rb_node **p = &q->t_root.rb_node, *parent = NULL; + + while (*p) { + struct sk_buff *skb; + + parent = *p; + skb = rb_to_skb(parent); + if (tnext >= netem_skb_cb(skb)->time_to_send) + p = &parent->rb_right; + else + p = &parent->rb_left; + } + rb_link_node(&nskb->rbnode, parent, p); + rb_insert_color(&nskb->rbnode, &q->t_root); } - rb_link_node(&nskb->rbnode, parent, p); - rb_insert_color(&nskb->rbnode, &q->t_root); + q->t_len++; sch->q.qlen++; } @@ -403,6 +429,7 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff *segs; netdev_features_t features = netif_skb_features(skb); + qdisc_skb_cb(skb)->pkt_segs = 1; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { @@ -413,16 +440,6 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, return segs; } -static void netem_enqueue_skb_head(struct qdisc_skb_head *qh, struct sk_buff *skb) -{ - skb->next = qh->head; - - if (!qh->head) - qh->tail = skb; - qh->head = skb; - qh->qlen++; -} - /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -435,15 +452,16 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; - unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb); - int nb = 0; + unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; + + /* Do not fool qdisc_drop_all() */ + skb->prev = NULL; /* Random duplication */ - if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) + if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng)) ++count; /* Drop packet? */ @@ -466,18 +484,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb); /* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. @@ -485,17 +496,16 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * If packet is going to be hardware checksummed, then * do it now in software before we mangle it. */ - if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { + if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) { if (skb_is_gso(skb)) { - segs = netem_segment(skb, sch, to_free); - if (!segs) - return NET_XMIT_DROP; - } else { - segs = skb; - } + skb = netem_segment(skb, sch, to_free); + if (!skb) + goto finish_segs; - skb = segs; - segs = segs->next; + segs = skb->next; + skb_mark_not_on_list(skb); + qdisc_skb_cb(skb)->pkt_len = skb->len; + } skb = skb_unshare(skb, GFP_ATOMIC); if (unlikely(!skb)) { @@ -505,29 +515,51 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) { qdisc_drop(skb, sch, to_free); + skb = NULL; goto finish_segs; } - skb->data[prandom_u32() % skb_headlen(skb)] ^= - 1<<(prandom_u32() % 8); + skb->data[get_random_u32_below(skb_headlen(skb))] ^= + 1<<get_random_u32_below(8); } - if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop(skb, sch, to_free); + if (unlikely(q->t_len >= sch->limit)) { + /* re-link segs, so that qdisc_drop_all() frees them all */ + skb->next = segs; + qdisc_drop_all(skb, sch, to_free); + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; + } qdisc_qstats_backlog_inc(sch, skb); cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ - q->reorder < get_crandom(&q->reorder_cor)) { - psched_time_t now; - psched_tdiff_t delay; + q->reorder < get_crandom(&q->reorder_cor, &q->prng)) { + u64 now; + s64 delay; delay = tabledist(q->latency, q->jitter, - &q->delay_cor, q->delay_dist); + &q->delay_cor, &q->prng, q->delay_dist); - now = psched_get_time(); + now = ktime_get_ns(); if (q->rate) { struct netem_skb_cb *last = NULL; @@ -538,12 +570,19 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff *t_skb; struct netem_skb_cb *t_last; - t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || - t_last->time_to_send > last->time_to_send) { + t_last->time_to_send > last->time_to_send) + last = t_last; + } + if (q->t_tail) { + struct netem_skb_cb *t_last = + netem_skb_cb(q->t_tail); + + if (!last || + t_last->time_to_send > last->time_to_send) last = t_last; - } } if (last) { @@ -553,15 +592,14 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * from delay. */ delay -= last->time_to_send - now; - delay = max_t(psched_tdiff_t, 0, delay); + delay = max_t(s64, 0, delay); now = last->time_to_send; } - delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); + delay += packet_time_ns(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; - cb->tstamp_save = skb->tstamp; ++q->counter; tfifo_enqueue(skb, sch); } else { @@ -569,18 +607,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * Do re-ordering by putting one out of N packets at the front * of the queue. */ - cb->time_to_send = psched_get_time(); + cb->time_to_send = ktime_get_ns(); q->counter = 0; - netem_enqueue_skb_head(&sch->q, skb); + __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { + unsigned int len, last_len; + int rc, nb; + + len = skb ? skb->len : 0; + nb = skb ? 1 : 0; + while (segs) { skb2 = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); @@ -593,52 +640,105 @@ finish_segs: } segs = skb2; } - sch->q.qlen += nb; - if (nb > 1) - qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); + /* Parent qdiscs accounted for 1 skb of size @prev_len */ + qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); + } else if (!skb) { + return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } +/* Delay the next round with a new future slot with a + * correct number of bytes and packets. + */ + +static void get_slot_next(struct netem_sched_data *q, u64 now) +{ + s64 next_delay; + + if (!q->slot_dist) + next_delay = q->slot_config.min_delay + + (get_random_u32() * + (q->slot_config.max_delay - + q->slot_config.min_delay) >> 32); + else + next_delay = tabledist(q->slot_config.dist_delay, + (s32)(q->slot_config.dist_jitter), + NULL, &q->prng, q->slot_dist); + + q->slot.slot_next = now + next_delay; + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; +} + +static struct sk_buff *netem_peek(struct netem_sched_data *q) +{ + struct sk_buff *skb = skb_rb_first(&q->t_root); + u64 t1, t2; + + if (!skb) + return q->t_head; + if (!q->t_head) + return skb; + + t1 = netem_skb_cb(skb)->time_to_send; + t2 = netem_skb_cb(q->t_head)->time_to_send; + if (t1 < t2) + return skb; + return q->t_head; +} + +static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb) +{ + if (skb == q->t_head) { + q->t_head = skb->next; + if (!q->t_head) + q->t_tail = NULL; + } else { + rb_erase(&skb->rbnode, &q->t_root); + } +} + static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - struct rb_node *p; tfifo_dequeue: skb = __qdisc_dequeue_head(&sch->q); if (skb) { - qdisc_qstats_backlog_dec(sch, skb); deliver: + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); return skb; } - p = rb_first(&q->t_root); - if (p) { - psched_time_t time_to_send; - - skb = netem_rb_to_skb(p); + skb = netem_peek(q); + if (skb) { + u64 time_to_send; + u64 now = ktime_get_ns(); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; - if (time_to_send <= psched_get_time()) { - rb_erase(p, &q->t_root); + if (q->slot.slot_next && q->slot.slot_next < time_to_send) + get_slot_next(q, now); - sch->q.qlen--; - qdisc_qstats_backlog_dec(sch, skb); + if (time_to_send <= now && q->slot.slot_next <= now) { + netem_erase_head(q, skb); + q->t_len--; skb->next = NULL; skb->prev = NULL; - skb->tstamp = netem_skb_cb(skb)->tstamp_save; - -#ifdef CONFIG_NET_CLS_ACT - /* - * If it's at ingress let's pretend the delay is - * from the network (tstamp will be updated). + /* skb->dev shares skb->rbnode area, + * we need to restore its value. */ - if (skb->tc_redirected && skb->tc_from_ingress) - skb->tstamp = 0; -#endif + skb->dev = qdisc_dev(sch); + + if (q->slot.slot_next) { + q->slot.packets_left--; + q->slot.bytes_left -= qdisc_pkt_len(skb); + if (q->slot.packets_left <= 0 || + q->slot.bytes_left <= 0) + get_slot_next(q, now); + } if (q->qdisc) { unsigned int pkt_len = qdisc_pkt_len(skb); @@ -647,29 +747,38 @@ deliver: err = qdisc_enqueue(skb, q->qdisc, &to_free); kfree_skb_list(to_free); - if (err != NET_XMIT_SUCCESS && - net_xmit_drop_count(err)) { - qdisc_qstats_drop(sch); - qdisc_tree_reduce_backlog(sch, 1, - pkt_len); + if (err != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(err)) + qdisc_qstats_drop(sch); + sch->qstats.backlog -= pkt_len; + sch->q.qlen--; + qdisc_tree_reduce_backlog(sch, 1, pkt_len); } goto tfifo_dequeue; } + sch->q.qlen--; goto deliver; } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) + if (skb) { + sch->q.qlen--; goto deliver; + } } - qdisc_watchdog_schedule(&q->watchdog, time_to_send); + + qdisc_watchdog_schedule_ns(&q->watchdog, + max(time_to_send, + q->slot.slot_next)); } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) + if (skb) { + sch->q.qlen--; goto deliver; + } } return NULL; } @@ -694,19 +803,18 @@ static void dist_free(struct disttable *d) * Distribution data is a variable size payload containing * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) + +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; - if (n > NETEM_DIST_MAX) + if (!n || n > NETEM_DIST_MAX) return -EINVAL; - d = kvmalloc(sizeof(struct disttable) + n * sizeof(s16), GFP_KERNEL); + d = kvmalloc(struct_size(d, table, n), GFP_KERNEL); if (!d) return -ENOMEM; @@ -714,16 +822,32 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(q->delay_dist, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } +static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) +{ + const struct tc_netem_slot *c = nla_data(attr); + + q->slot_config = *c; + if (q->slot_config.max_packets == 0) + q->slot_config.max_packets = INT_MAX; + if (q->slot_config.max_bytes == 0) + q->slot_config.max_bytes = INT_MAX; + + /* capping dist_jitter to the range acceptable by tabledist() */ + q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); + + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; + if (q->slot_config.min_delay | q->slot_config.max_delay | + q->slot_config.dist_jitter) + q->slot.slot_next = ktime_get_ns(); + else + q->slot.slot_next = 0; +} + static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corr *c = nla_data(attr); @@ -825,6 +949,10 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, [TCA_NETEM_RATE64] = { .type = NLA_U64 }, + [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, + [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, + [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, + [TCA_NETEM_PRNG_SEED] = { .type = NLA_U64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -838,31 +966,80 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, } if (nested_len >= nla_attr_size(0)) - return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), - nested_len, policy, NULL); + return nla_parse_deprecated(tb, maxtype, + nla_data(nla) + NLA_ALIGN(len), + nested_len, policy, NULL); memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); return 0; } +static const struct Qdisc_class_ops netem_class_ops; + +static int check_netem_in_tree(struct Qdisc *sch, bool duplicates, + struct netlink_ext_ack *extack) +{ + struct Qdisc *root, *q; + unsigned int i; + + root = qdisc_root_sleeping(sch); + + if (sch != root && root->ops->cl_ops == &netem_class_ops) { + if (duplicates || + ((struct netem_sched_data *)qdisc_priv(root))->duplicate) + goto err; + } + + if (!qdisc_dev(root)) + return 0; + + hash_for_each(qdisc_dev(root)->qdisc_hash, i, q, hash) { + if (sch != q && q->ops->cl_ops == &netem_class_ops) { + if (duplicates || + ((struct netem_sched_data *)qdisc_priv(q))->duplicate) + goto err; + } + } + + return 0; + +err: + NL_SET_ERR_MSG(extack, + "netem: cannot mix duplicating netems with other netems in tree"); + return -EINVAL; +} + /* Parse netlink message to set options */ -static int netem_change(struct Qdisc *sch, struct nlattr *opt) +static int netem_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; int ret; - if (opt == NULL) - return -EINVAL; - qopt = nla_data(opt); ret = parse_attr(tb, TCA_NETEM_MAX, opt, netem_policy, sizeof(*qopt)); if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; old_loss_model = q->loss_model; @@ -871,33 +1048,30 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; - return ret; + q->clg = old_clg; + goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]); - if (ret) { - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - return ret; - } - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; - q->latency = qopt->latency; - q->jitter = qopt->jitter; + q->latency = PSCHED_TICKS2NS(qopt->latency); + q->jitter = PSCHED_TICKS2NS(qopt->jitter); q->limit = qopt->limit; q->gap = qopt->gap; q->counter = 0; q->loss = qopt->loss; + + ret = check_netem_in_tree(sch, qopt->duplicate, extack); + if (ret) + goto unlock; + q->duplicate = qopt->duplicate; /* for compatibility with earlier versions. @@ -922,24 +1096,49 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) q->rate = max_t(u64, q->rate, nla_get_u64(tb[TCA_NETEM_RATE64])); + if (tb[TCA_NETEM_LATENCY64]) + q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]); + + if (tb[TCA_NETEM_JITTER64]) + q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]); + if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); + if (tb[TCA_NETEM_SLOT]) + get_slot(q, tb[TCA_NETEM_SLOT]); + + /* capping jitter to the range acceptable by tabledist() */ + q->jitter = min_t(s64, abs(q->jitter), INT_MAX); + + if (tb[TCA_NETEM_PRNG_SEED]) + q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]); + else + q->prng.seed = get_random_u64(); + prandom_seed_state(&q->prng.prng_state, q->prng.seed); + +unlock: + sch_tree_unlock(sch); + +table_free: + dist_free(delay_dist); + dist_free(slot_dist); return ret; } -static int netem_init(struct Qdisc *sch, struct nlattr *opt) +static int netem_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); int ret; + qdisc_watchdog_init(&q->watchdog, sch); + if (!opt) return -EINVAL; - qdisc_watchdog_init(&q->watchdog, sch); - q->loss_model = CLG_RANDOM; - ret = netem_change(sch, opt); + ret = netem_change(sch, opt, extack); if (ret) pr_info("netem: change failed\n"); return ret; @@ -951,8 +1150,9 @@ static void netem_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); if (q->qdisc) - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); dist_free(q->delay_dist); + dist_free(q->slot_dist); } static int dump_loss_model(const struct netem_sched_data *q, @@ -960,7 +1160,7 @@ static int dump_loss_model(const struct netem_sched_data *q, { struct nlattr *nest; - nest = nla_nest_start(skb, TCA_NETEM_LOSS); + nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS); if (nest == NULL) goto nla_put_failure; @@ -1014,9 +1214,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_netem_reorder reorder; struct tc_netem_corrupt corrupt; struct tc_netem_rate rate; + struct tc_netem_slot slot; - qopt.latency = q->latency; - qopt.jitter = q->jitter; + qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency), + UINT_MAX); + qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter), + UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; qopt.gap = q->gap; @@ -1024,6 +1227,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; + if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency)) + goto nla_put_failure; + + if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter)) + goto nla_put_failure; + cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; @@ -1060,6 +1269,21 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (dump_loss_model(q, skb) != 0) goto nla_put_failure; + if (q->slot_config.min_delay | q->slot_config.max_delay | + q->slot_config.dist_jitter) { + slot = q->slot_config; + if (slot.max_packets == INT_MAX) + slot.max_packets = 0; + if (slot.max_bytes == INT_MAX) + slot.max_bytes = 0; + if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot)) + goto nla_put_failure; + } + + if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed, + TCA_NETEM_PAD)) + goto nla_put_failure; + return nla_nest_end(skb, nla); nla_put_failure: @@ -1082,7 +1306,7 @@ static int netem_dump_class(struct Qdisc *sch, unsigned long cl, } static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); @@ -1096,32 +1320,23 @@ static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg) return q->qdisc; } -static unsigned long netem_get(struct Qdisc *sch, u32 classid) +static unsigned long netem_find(struct Qdisc *sch, u32 classid) { return 1; } -static void netem_put(struct Qdisc *sch, unsigned long arg) -{ -} - static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { - if (walker->count >= walker->skip) - if (walker->fn(sch, 1, walker) < 0) { - walker->stop = 1; - return; - } - walker->count++; + if (!tc_qdisc_stats_dump(sch, 1, walker)) + return; } } static const struct Qdisc_class_ops netem_class_ops = { .graft = netem_graft, .leaf = netem_leaf, - .get = netem_get, - .put = netem_put, + .find = netem_find, .walk = netem_walk, .dump = netem_dump_class, }; @@ -1140,6 +1355,7 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .dump = netem_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("netem"); static int __init netem_module_init(void) @@ -1154,3 +1370,4 @@ static void __exit netem_module_exit(void) module_init(netem_module_init) module_exit(netem_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Network characteristics emulator qdisc"); diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 6c2791d6102d..0a377313b6a9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -1,15 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2013 Cisco Systems, Inc, 2013. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Author: Vijay Subramanian <vijaynsu@cisco.com> * Author: Mythili Prabhu <mysuryan@cisco.com> * @@ -17,9 +8,7 @@ * University of Oslo, Norway. * * References: - * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00 - * IEEE Conference on High Performance Switching and Routing 2013 : - * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem" + * RFC 8033: https://tools.ietf.org/html/rfc8033 */ #include <linux/module.h> @@ -30,113 +19,73 @@ #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> - -#define QUEUE_THRESHOLD 10000 -#define DQCOUNT_INVALID -1 -#define MAX_PROB 0xffffffff -#define PIE_SCALE 8 - -/* parameters used */ -struct pie_params { - psched_time_t target; /* user specified target delay in pschedtime */ - u32 tupdate; /* timer frequency (in jiffies) */ - u32 limit; /* number of packets that can be enqueued */ - u32 alpha; /* alpha and beta are between 0 and 32 */ - u32 beta; /* and are used for shift relative to 1 */ - bool ecn; /* true if ecn is enabled */ - bool bytemode; /* to scale drop early prob based on pkt size */ -}; - -/* variables used */ -struct pie_vars { - u32 prob; /* probability but scaled by u32 limit. */ - psched_time_t burst_time; - psched_time_t qdelay; - psched_time_t qdelay_old; - u64 dq_count; /* measured in bytes */ - psched_time_t dq_tstamp; /* drain rate */ - u32 avg_dq_rate; /* bytes per pschedtime tick,scaled */ - u32 qlen_old; /* in bytes */ -}; - -/* statistics gathering */ -struct pie_stats { - u32 packets_in; /* total number of packets enqueued */ - u32 dropped; /* packets dropped due to pie_action */ - u32 overlimit; /* dropped due to lack of space in queue */ - u32 maxq; /* maximum queue size */ - u32 ecn_mark; /* packets marked with ECN */ -}; +#include <net/pie.h> /* private data for the Qdisc */ struct pie_sched_data { - struct pie_params params; struct pie_vars vars; + struct pie_params params; struct pie_stats stats; struct timer_list adapt_timer; + struct Qdisc *sch; }; -static void pie_params_init(struct pie_params *params) -{ - params->alpha = 2; - params->beta = 20; - params->tupdate = usecs_to_jiffies(30 * USEC_PER_MSEC); /* 30 ms */ - params->limit = 1000; /* default of 1000 packets */ - params->target = PSCHED_NS2TICKS(20 * NSEC_PER_MSEC); /* 20 ms */ - params->ecn = false; - params->bytemode = false; -} - -static void pie_vars_init(struct pie_vars *vars) -{ - vars->dq_count = DQCOUNT_INVALID; - vars->avg_dq_rate = 0; - /* default of 100 ms in pschedtime */ - vars->burst_time = PSCHED_NS2TICKS(100 * NSEC_PER_MSEC); -} - -static bool drop_early(struct Qdisc *sch, u32 packet_size) +bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, + struct pie_vars *vars, u32 backlog, u32 packet_size) { - struct pie_sched_data *q = qdisc_priv(sch); - u32 rnd; - u32 local_prob = q->vars.prob; + u64 rnd; + u64 local_prob = vars->prob; u32 mtu = psched_mtu(qdisc_dev(sch)); /* If there is still burst allowance left skip random early drop */ - if (q->vars.burst_time > 0) + if (vars->burst_time > 0) return false; /* If current delay is less than half of target, and * if drop prob is low already, disable early_drop */ - if ((q->vars.qdelay < q->params.target / 2) - && (q->vars.prob < MAX_PROB / 5)) + if ((vars->qdelay < params->target / 2) && + (vars->prob < MAX_PROB / 5)) return false; - /* If we have fewer than 2 mtu-sized packets, disable drop_early, + /* If we have fewer than 2 mtu-sized packets, disable pie_drop_early, * similar to min_th in RED */ - if (sch->qstats.backlog < 2 * mtu) + if (backlog < 2 * mtu) return false; /* If bytemode is turned on, use packet size to compute new * probablity. Smaller packets will have lower drop prob in this case */ - if (q->params.bytemode && packet_size <= mtu) - local_prob = (local_prob / mtu) * packet_size; + if (params->bytemode && packet_size <= mtu) + local_prob = (u64)packet_size * div_u64(local_prob, mtu); + else + local_prob = vars->prob; + + if (local_prob == 0) + vars->accu_prob = 0; else - local_prob = q->vars.prob; + vars->accu_prob += local_prob; - rnd = prandom_u32(); - if (rnd < local_prob) + if (vars->accu_prob < (MAX_PROB / 100) * 85) + return false; + if (vars->accu_prob >= (MAX_PROB / 2) * 17) + return true; + + get_random_bytes(&rnd, 8); + if ((rnd >> BITS_PER_BYTE) < local_prob) { + vars->accu_prob = 0; return true; + } return false; } +EXPORT_SYMBOL_GPL(pie_drop_early); static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; struct pie_sched_data *q = qdisc_priv(sch); bool enqueue = false; @@ -145,7 +94,10 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto out; } - if (!drop_early(sch, skb->len)) { + reason = SKB_DROP_REASON_QDISC_CONGESTED; + + if (!pie_drop_early(sch, &q->params, &q->vars, sch->qstats.backlog, + skb->len)) { enqueue = true; } else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) && INET_ECN_set_ce(skb)) { @@ -158,6 +110,10 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* we can enqueue the packet */ if (enqueue) { + /* Set enqueue time only when dq_rate_estimator is disabled. */ + if (!q->params.dq_rate_estimator) + pie_set_enqueue_time(skb); + q->stats.packets_in++; if (qdisc_qlen(sch) > q->stats.maxq) q->stats.maxq = qdisc_qlen(sch); @@ -167,30 +123,31 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, out: q->stats.dropped++; - return qdisc_drop(skb, sch, to_free); + q->vars.accu_prob = 0; + return qdisc_drop_reason(skb, sch, to_free, reason); } static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { - [TCA_PIE_TARGET] = {.type = NLA_U32}, - [TCA_PIE_LIMIT] = {.type = NLA_U32}, - [TCA_PIE_TUPDATE] = {.type = NLA_U32}, - [TCA_PIE_ALPHA] = {.type = NLA_U32}, - [TCA_PIE_BETA] = {.type = NLA_U32}, - [TCA_PIE_ECN] = {.type = NLA_U32}, - [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, + [TCA_PIE_TARGET] = {.type = NLA_U32}, + [TCA_PIE_LIMIT] = {.type = NLA_U32}, + [TCA_PIE_TUPDATE] = {.type = NLA_U32}, + [TCA_PIE_ALPHA] = {.type = NLA_U32}, + [TCA_PIE_BETA] = {.type = NLA_U32}, + [TCA_PIE_ECN] = {.type = NLA_U32}, + [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, + [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, }; -static int pie_change(struct Qdisc *sch, struct nlattr *opt) +static int pie_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; - unsigned int qlen, dropped = 0; int err; - if (!opt) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy, + NULL); if (err < 0) return err; @@ -202,174 +159,213 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt) u32 target = nla_get_u32(tb[TCA_PIE_TARGET]); /* convert to pschedtime */ - q->params.target = PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC); + WRITE_ONCE(q->params.target, + PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC)); } /* tupdate is in jiffies */ if (tb[TCA_PIE_TUPDATE]) - q->params.tupdate = usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE])); + WRITE_ONCE(q->params.tupdate, + usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE]))); if (tb[TCA_PIE_LIMIT]) { u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]); - q->params.limit = limit; - sch->limit = limit; + WRITE_ONCE(q->params.limit, limit); + WRITE_ONCE(sch->limit, limit); } if (tb[TCA_PIE_ALPHA]) - q->params.alpha = nla_get_u32(tb[TCA_PIE_ALPHA]); + WRITE_ONCE(q->params.alpha, nla_get_u32(tb[TCA_PIE_ALPHA])); if (tb[TCA_PIE_BETA]) - q->params.beta = nla_get_u32(tb[TCA_PIE_BETA]); + WRITE_ONCE(q->params.beta, nla_get_u32(tb[TCA_PIE_BETA])); if (tb[TCA_PIE_ECN]) - q->params.ecn = nla_get_u32(tb[TCA_PIE_ECN]); + WRITE_ONCE(q->params.ecn, nla_get_u32(tb[TCA_PIE_ECN])); if (tb[TCA_PIE_BYTEMODE]) - q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]); + WRITE_ONCE(q->params.bytemode, + nla_get_u32(tb[TCA_PIE_BYTEMODE])); + + if (tb[TCA_PIE_DQ_RATE_ESTIMATOR]) + WRITE_ONCE(q->params.dq_rate_estimator, + nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; } -static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) +void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, + struct pie_vars *vars, u32 backlog) { + psched_time_t now = psched_get_time(); + u32 dtime = 0; - struct pie_sched_data *q = qdisc_priv(sch); - int qlen = sch->qstats.backlog; /* current queue size in bytes */ + /* If dq_rate_estimator is disabled, calculate qdelay using the + * packet timestamp. + */ + if (!params->dq_rate_estimator) { + vars->qdelay = now - pie_get_enqueue_time(skb); + + if (vars->dq_tstamp != DTIME_INVALID) + dtime = now - vars->dq_tstamp; + + vars->dq_tstamp = now; + + if (backlog == 0) + vars->qdelay = 0; + + if (dtime == 0) + return; + + goto burst_allowance_reduction; + } /* If current queue is about 10 packets or more and dq_count is unset * we have enough packets to calculate the drain rate. Save * current time as dq_tstamp and start measurement cycle. */ - if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) { - q->vars.dq_tstamp = psched_get_time(); - q->vars.dq_count = 0; + if (backlog >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) { + vars->dq_tstamp = psched_get_time(); + vars->dq_count = 0; } - /* Calculate the average drain rate from this value. If queue length - * has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset + /* Calculate the average drain rate from this value. If queue length + * has receded to a small value viz., <= QUEUE_THRESHOLD bytes, reset * the dq_count to -1 as we don't have enough packets to calculate the - * drain rate anymore The following if block is entered only when we + * drain rate anymore. The following if block is entered only when we * have a substantial queue built up (QUEUE_THRESHOLD bytes or more) * and we calculate the drain rate for the threshold here. dq_count is * in bytes, time difference in psched_time, hence rate is in * bytes/psched_time. */ - if (q->vars.dq_count != DQCOUNT_INVALID) { - q->vars.dq_count += skb->len; + if (vars->dq_count != DQCOUNT_INVALID) { + vars->dq_count += skb->len; - if (q->vars.dq_count >= QUEUE_THRESHOLD) { - psched_time_t now = psched_get_time(); - u32 dtime = now - q->vars.dq_tstamp; - u32 count = q->vars.dq_count << PIE_SCALE; + if (vars->dq_count >= QUEUE_THRESHOLD) { + u32 count = vars->dq_count << PIE_SCALE; + + dtime = now - vars->dq_tstamp; if (dtime == 0) return; count = count / dtime; - if (q->vars.avg_dq_rate == 0) - q->vars.avg_dq_rate = count; + if (vars->avg_dq_rate == 0) + vars->avg_dq_rate = count; else - q->vars.avg_dq_rate = - (q->vars.avg_dq_rate - - (q->vars.avg_dq_rate >> 3)) + (count >> 3); + vars->avg_dq_rate = + (vars->avg_dq_rate - + (vars->avg_dq_rate >> 3)) + (count >> 3); /* If the queue has receded below the threshold, we hold * on to the last drain rate calculated, else we reset * dq_count to 0 to re-enter the if block when the next * packet is dequeued */ - if (qlen < QUEUE_THRESHOLD) - q->vars.dq_count = DQCOUNT_INVALID; - else { - q->vars.dq_count = 0; - q->vars.dq_tstamp = psched_get_time(); + if (backlog < QUEUE_THRESHOLD) { + vars->dq_count = DQCOUNT_INVALID; + } else { + vars->dq_count = 0; + vars->dq_tstamp = psched_get_time(); } - if (q->vars.burst_time > 0) { - if (q->vars.burst_time > dtime) - q->vars.burst_time -= dtime; - else - q->vars.burst_time = 0; - } + goto burst_allowance_reduction; } } + + return; + +burst_allowance_reduction: + if (vars->burst_time > 0) { + if (vars->burst_time > dtime) + vars->burst_time -= dtime; + else + vars->burst_time = 0; + } } +EXPORT_SYMBOL_GPL(pie_process_dequeue); -static void calculate_probability(struct Qdisc *sch) +void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, + u32 backlog) { - struct pie_sched_data *q = qdisc_priv(sch); - u32 qlen = sch->qstats.backlog; /* queue size in bytes */ psched_time_t qdelay = 0; /* in pschedtime */ - psched_time_t qdelay_old = q->vars.qdelay; /* in pschedtime */ - s32 delta = 0; /* determines the change in probability */ - u32 oldprob; - u32 alpha, beta; + psched_time_t qdelay_old = 0; /* in pschedtime */ + s64 delta = 0; /* determines the change in probability */ + u64 oldprob; + u64 alpha, beta; + u32 power; bool update_prob = true; - q->vars.qdelay_old = q->vars.qdelay; + if (params->dq_rate_estimator) { + qdelay_old = vars->qdelay; + vars->qdelay_old = vars->qdelay; - if (q->vars.avg_dq_rate > 0) - qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate; - else - qdelay = 0; + if (vars->avg_dq_rate > 0) + qdelay = (backlog << PIE_SCALE) / vars->avg_dq_rate; + else + qdelay = 0; + } else { + qdelay = vars->qdelay; + qdelay_old = vars->qdelay_old; + } - /* If qdelay is zero and qlen is not, it means qlen is very small, less - * than dequeue_rate, so we do not update probabilty in this round + /* If qdelay is zero and backlog is not, it means backlog is very small, + * so we do not update probability in this round. */ - if (qdelay == 0 && qlen != 0) + if (qdelay == 0 && backlog != 0) update_prob = false; /* In the algorithm, alpha and beta are between 0 and 2 with typical * value for alpha as 0.125. In this implementation, we use values 0-32 * passed from user space to represent this. Also, alpha and beta have * unit of HZ and need to be scaled before they can used to update - * probability. alpha/beta are updated locally below by 1) scaling them - * appropriately 2) scaling down by 16 to come to 0-2 range. - * Please see paper for details. - * - * We scale alpha and beta differently depending on whether we are in - * light, medium or high dropping mode. + * probability. alpha/beta are updated locally below by scaling down + * by 16 to come to 0-2 range. */ - if (q->vars.prob < MAX_PROB / 100) { - alpha = - (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7; - beta = - (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7; - } else if (q->vars.prob < MAX_PROB / 10) { - alpha = - (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5; - beta = - (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5; - } else { - alpha = - (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; - beta = - (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + alpha = ((u64)params->alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + beta = ((u64)params->beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + + /* We scale alpha and beta differently depending on how heavy the + * congestion is. Please see RFC 8033 for details. + */ + if (vars->prob < MAX_PROB / 10) { + alpha >>= 1; + beta >>= 1; + + power = 100; + while (vars->prob < div_u64(MAX_PROB, power) && + power <= 1000000) { + alpha >>= 2; + beta >>= 2; + power *= 10; + } } /* alpha and beta should be between 0 and 32, in multiples of 1/16 */ - delta += alpha * ((qdelay - q->params.target)); - delta += beta * ((qdelay - qdelay_old)); + delta += alpha * (qdelay - params->target); + delta += beta * (qdelay - qdelay_old); - oldprob = q->vars.prob; + oldprob = vars->prob; /* to ensure we increase probability in steps of no more than 2% */ - if (delta > (s32) (MAX_PROB / (100 / 2)) && - q->vars.prob >= MAX_PROB / 10) + if (delta > (s64)(MAX_PROB / (100 / 2)) && + vars->prob >= MAX_PROB / 10) delta = (MAX_PROB / 100) * 2; /* Non-linear drop: @@ -380,12 +376,12 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) delta += MAX_PROB / (100 / 2); - q->vars.prob += delta; + vars->prob += delta; if (delta > 0) { /* prevent overflow */ - if (q->vars.prob < oldprob) { - q->vars.prob = MAX_PROB; + if (vars->prob < oldprob) { + vars->prob = MAX_PROB; /* Prevent normalization error. If probability is at * maximum value already, we normalize it here, and * skip the check to do a non-linear drop in the next @@ -395,50 +391,59 @@ static void calculate_probability(struct Qdisc *sch) } } else { /* prevent underflow */ - if (q->vars.prob > oldprob) - q->vars.prob = 0; + if (vars->prob > oldprob) + vars->prob = 0; } /* Non-linear drop in probability: Reduce drop probability quickly if * delay is 0 for 2 consecutive Tupdate periods. */ - if ((qdelay == 0) && (qdelay_old == 0) && update_prob) - q->vars.prob = (q->vars.prob * 98) / 100; + if (qdelay == 0 && qdelay_old == 0 && update_prob) + /* Reduce drop probability to 98.4% */ + vars->prob -= vars->prob / 64; - q->vars.qdelay = qdelay; - q->vars.qlen_old = qlen; + vars->qdelay = qdelay; + vars->backlog_old = backlog; /* We restart the measurement cycle if the following conditions are met * 1. If the delay has been low for 2 consecutive Tupdate periods * 2. Calculated drop probability is zero - * 3. We have atleast one estimate for the avg_dq_rate ie., - * is a non-zero value + * 3. If average dq_rate_estimator is enabled, we have at least one + * estimate for the avg_dq_rate ie., is a non-zero value */ - if ((q->vars.qdelay < q->params.target / 2) && - (q->vars.qdelay_old < q->params.target / 2) && - (q->vars.prob == 0) && - (q->vars.avg_dq_rate > 0)) - pie_vars_init(&q->vars); + if ((vars->qdelay < params->target / 2) && + (vars->qdelay_old < params->target / 2) && + vars->prob == 0 && + (!params->dq_rate_estimator || vars->avg_dq_rate > 0)) { + pie_vars_init(vars); + } + + if (!params->dq_rate_estimator) + vars->qdelay_old = qdelay; } +EXPORT_SYMBOL_GPL(pie_calculate_probability); -static void pie_timer(unsigned long arg) +static void pie_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct pie_sched_data *q = qdisc_priv(sch); - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + struct pie_sched_data *q = timer_container_of(q, t, adapt_timer); + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - calculate_probability(sch); + pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog); /* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */ if (q->params.tupdate) mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); spin_unlock(root_lock); - + rcu_read_unlock(); } -static int pie_init(struct Qdisc *sch, struct nlattr *opt) +static int pie_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct pie_sched_data *q = qdisc_priv(sch); @@ -446,10 +451,11 @@ static int pie_init(struct Qdisc *sch, struct nlattr *opt) pie_vars_init(&q->vars); sch->limit = q->params.limit; - setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, pie_timer, 0); if (opt) { - int err = pie_change(sch, opt); + int err = pie_change(sch, opt, extack); if (err) return err; @@ -464,20 +470,24 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *opts; - opts = nla_nest_start(skb, TCA_OPTIONS); - if (opts == NULL) + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) goto nla_put_failure; /* convert target from pschedtime to us */ if (nla_put_u32(skb, TCA_PIE_TARGET, - ((u32) PSCHED_TICKS2NS(q->params.target)) / + ((u32)PSCHED_TICKS2NS(READ_ONCE(q->params.target))) / NSEC_PER_USEC) || - nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) || - nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(q->params.tupdate)) || - nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) || - nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) || + nla_put_u32(skb, TCA_PIE_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_PIE_TUPDATE, + jiffies_to_usecs(READ_ONCE(q->params.tupdate))) || + nla_put_u32(skb, TCA_PIE_ALPHA, READ_ONCE(q->params.alpha)) || + nla_put_u32(skb, TCA_PIE_BETA, READ_ONCE(q->params.beta)) || nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) || - nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode)) + nla_put_u32(skb, TCA_PIE_BYTEMODE, + READ_ONCE(q->params.bytemode)) || + nla_put_u32(skb, TCA_PIE_DQ_RATE_ESTIMATOR, + READ_ONCE(q->params.dq_rate_estimator))) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -485,19 +495,15 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_failure: nla_nest_cancel(skb, opts); return -1; - } static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct pie_sched_data *q = qdisc_priv(sch); struct tc_pie_xstats st = { - .prob = q->vars.prob, - .delay = ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) / + .prob = q->vars.prob << BITS_PER_BYTE, + .delay = ((u32)PSCHED_TICKS2NS(q->vars.qdelay)) / NSEC_PER_USEC, - /* unscale and return dq_rate in bytes per sec */ - .avg_dq_rate = q->vars.avg_dq_rate * - (PSCHED_TICKS_PER_SEC) >> PIE_SCALE, .packets_in = q->stats.packets_in, .overlimit = q->stats.overlimit, .maxq = q->stats.maxq, @@ -505,24 +511,33 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .ecn_mark = q->stats.ecn_mark, }; + /* avg_dq_rate is only valid if dq_rate_estimator is enabled */ + st.dq_rate_estimating = q->params.dq_rate_estimator; + + /* unscale and return dq_rate in bytes per sec */ + if (q->params.dq_rate_estimator) + st.avg_dq_rate = q->vars.avg_dq_rate * + (PSCHED_TICKS_PER_SEC) >> PIE_SCALE; + return gnet_stats_copy_app(d, &st, sizeof(st)); } static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) { - struct sk_buff *skb; - skb = qdisc_dequeue_head(sch); + struct pie_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = qdisc_dequeue_head(sch); if (!skb) return NULL; - pie_process_dequeue(sch, skb); + pie_process_dequeue(skb, &q->params, &q->vars, sch->qstats.backlog); return skb; } static void pie_reset(struct Qdisc *sch) { struct pie_sched_data *q = qdisc_priv(sch); + qdisc_reset_queue(sch); pie_vars_init(&q->vars); } @@ -530,12 +545,13 @@ static void pie_reset(struct Qdisc *sch) static void pie_destroy(struct Qdisc *sch) { struct pie_sched_data *q = qdisc_priv(sch); + q->params.tupdate = 0; - del_timer_sync(&q->adapt_timer); + timer_delete_sync(&q->adapt_timer); } static struct Qdisc_ops pie_qdisc_ops __read_mostly = { - .id = "pie", + .id = "pie", .priv_size = sizeof(struct pie_sched_data), .enqueue = pie_qdisc_enqueue, .dequeue = pie_qdisc_dequeue, @@ -548,6 +564,7 @@ static struct Qdisc_ops pie_qdisc_ops __read_mostly = { .dump_stats = pie_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("pie"); static int __init pie_module_init(void) { diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 1c6cbab3e7b9..cefb65201e17 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * sch_plug.c Queue traffic until an explicit release command * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * There are two ways to use this qdisc: * 1. A simple "instantaneous" plug/unplug operation, by issuing an alternating * sequence of TCQ_PLUG_BUFFER & TCQ_PLUG_RELEASE_INDEFINITE commands. @@ -123,7 +119,8 @@ static struct sk_buff *plug_dequeue(struct Qdisc *sch) return qdisc_dequeue_head(sch); } -static int plug_init(struct Qdisc *sch, struct nlattr *opt) +static int plug_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct plug_sched_data *q = qdisc_priv(sch); @@ -158,14 +155,12 @@ static int plug_init(struct Qdisc *sch, struct nlattr *opt) * command is received (just act as a pass-thru queue). * TCQ_PLUG_LIMIT: Increase/decrease queue size */ -static int plug_change(struct Qdisc *sch, struct nlattr *opt) +static int plug_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct plug_sched_data *q = qdisc_priv(sch); struct tc_plug_qopt *msg; - if (opt == NULL) - return -EINVAL; - msg = nla_data(opt); if (nla_len(opt) < sizeof(*msg)) return -EINVAL; @@ -212,12 +207,13 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .priv_size = sizeof(struct plug_sched_data), .enqueue = plug_enqueue, .dequeue = plug_dequeue, - .peek = qdisc_peek_head, + .peek = qdisc_peek_dequeued, .init = plug_init, .change = plug_change, .reset = qdisc_reset_queue, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("plug"); static int __init plug_module_init(void) { @@ -231,3 +227,4 @@ static void __exit plug_module_exit(void) module_init(plug_module_init) module_exit(plug_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Qdisc to plug and unplug traffic via netlink control"); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index e3e364cc9a70..9e2b9a490db2 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_prio.c Simple 3-band priority "scheduler". * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Fixes: 19990609: J Hadi Salim <hadi@nortelnetworks.com>: * Init -- EINVAL when opt undefined @@ -43,13 +39,14 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tcf_classify(skb, fl, &res, false); + err = tcf_classify(skb, NULL, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return NULL; } @@ -71,6 +68,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) static int prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); struct Qdisc *qdisc; int ret; @@ -80,14 +78,14 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) if (ret & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); - kfree_skb(skb); + __qdisc_drop(skb, to_free); return ret; } #endif ret = qdisc_enqueue(skb, qdisc, to_free); if (ret == NET_XMIT_SUCCESS) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -137,8 +135,30 @@ prio_reset(struct Qdisc *sch) for (prio = 0; prio < q->bands; prio++) qdisc_reset(q->queues[prio]); - sch->qstats.backlog = 0; - sch->q.qlen = 0; +} + +static int prio_offload(struct Qdisc *sch, struct tc_prio_qopt *qopt) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_prio_qopt_offload opt = { + .handle = sch->handle, + .parent = sch->parent, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + if (qopt) { + opt.command = TC_PRIO_REPLACE; + opt.replace_params.bands = qopt->bands; + memcpy(&opt.replace_params.priomap, qopt->priomap, + TC_PRIO_MAX + 1); + opt.replace_params.qstats = &sch->qstats; + } else { + opt.command = TC_PRIO_DESTROY; + } + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO, &opt); } static void @@ -148,11 +168,13 @@ prio_destroy(struct Qdisc *sch) struct prio_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); + prio_offload(sch, NULL); for (prio = 0; prio < q->bands; prio++) - qdisc_destroy(q->queues[prio]); + qdisc_put(q->queues[prio]); } -static int prio_tune(struct Qdisc *sch, struct nlattr *opt) +static int prio_tune(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); struct Qdisc *queues[TCQ_PRIO_BANDS]; @@ -163,7 +185,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) return -EINVAL; qopt = nla_data(opt); - if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2) + if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < TCQ_MIN_PRIO_BANDS) return -EINVAL; for (i = 0; i <= TC_PRIO_MAX; i++) { @@ -174,25 +196,22 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) /* Before commit, make sure we can allocate all new qdiscs */ for (i = oldbands; i < qopt->bands; i++) { queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - TC_H_MAKE(sch->handle, i + 1)); + TC_H_MAKE(sch->handle, i + 1), + extack); if (!queues[i]) { while (i > oldbands) - qdisc_destroy(queues[--i]); + qdisc_put(queues[--i]); return -ENOMEM; } } + prio_offload(sch, qopt); sch_tree_lock(sch); q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); - for (i = q->bands; i < oldbands; i++) { - struct Qdisc *child = q->queues[i]; - - qdisc_tree_reduce_backlog(child, child->q.qlen, - child->qstats.backlog); - qdisc_destroy(child); - } + for (i = q->bands; i < oldbands; i++) + qdisc_purge_queue(q->queues[i]); for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; @@ -201,10 +220,14 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) } sch_tree_unlock(sch); + + for (i = q->bands; i < oldbands; i++) + qdisc_put(q->queues[i]); return 0; } -static int prio_init(struct Qdisc *sch, struct nlattr *opt) +static int prio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); int err; @@ -212,11 +235,28 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; - return prio_tune(sch, opt); + return prio_tune(sch, opt, extack); +} + +static int prio_dump_offload(struct Qdisc *sch) +{ + struct tc_prio_qopt_offload hw_stats = { + .command = TC_PRIO_STATS, + .handle = sch->handle, + .parent = sch->parent, + { + .stats = { + .bstats = &sch->bstats, + .qstats = &sch->qstats, + }, + }, + }; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_PRIO, &hw_stats); } static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -224,10 +264,15 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) struct prio_sched_data *q = qdisc_priv(sch); unsigned char *b = skb_tail_pointer(skb); struct tc_prio_qopt opt; + int err; opt.bands = q->bands; memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1); + err = prio_dump_offload(sch); + if (err) + goto nla_put_failure; + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; @@ -239,15 +284,32 @@ nla_put_failure: } static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); + struct tc_prio_qopt_offload graft_offload; unsigned long band = arg - 1; - if (new == NULL) - new = &noop_qdisc; + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, arg), extack); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } *old = qdisc_replace(sch, new, &q->queues[band]); + + graft_offload.handle = sch->handle; + graft_offload.parent = sch->parent; + graft_offload.graft_params.band = band; + graft_offload.graft_params.child_handle = new->handle; + graft_offload.command = TC_PRIO_GRAFT; + + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old, + TC_SETUP_QDISC_PRIO, &graft_offload, + extack); return 0; } @@ -260,7 +322,7 @@ prio_leaf(struct Qdisc *sch, unsigned long arg) return q->queues[band]; } -static unsigned long prio_get(struct Qdisc *sch, u32 classid) +static unsigned long prio_find(struct Qdisc *sch, u32 classid) { struct prio_sched_data *q = qdisc_priv(sch); unsigned long band = TC_H_MIN(classid); @@ -272,11 +334,11 @@ static unsigned long prio_get(struct Qdisc *sch, u32 classid) static unsigned long prio_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { - return prio_get(sch, classid); + return prio_find(sch, classid); } -static void prio_put(struct Qdisc *q, unsigned long cl) +static void prio_unbind(struct Qdisc *q, unsigned long cl) { } @@ -297,9 +359,9 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0) + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, + &cl_q->bstats, true) < 0 || + qdisc_qstats_copy(d, cl_q) < 0) return -1; return 0; @@ -314,19 +376,13 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (prio = 0; prio < q->bands; prio++) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, prio + 1, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, prio + 1, arg)) break; - } - arg->count++; } } -static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); @@ -338,12 +394,11 @@ static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl) static const struct Qdisc_class_ops prio_class_ops = { .graft = prio_graft, .leaf = prio_leaf, - .get = prio_get, - .put = prio_put, + .find = prio_find, .walk = prio_walk, .tcf_block = prio_tcf_block, .bind_tcf = prio_bind, - .unbind_tcf = prio_put, + .unbind_tcf = prio_unbind, .dump = prio_dump_class, .dump_stats = prio_dump_class_stats, }; @@ -363,6 +418,7 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = { .dump = prio_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("prio"); static int __init prio_module_init(void) { @@ -378,3 +434,4 @@ module_init(prio_module_init) module_exit(prio_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Simple 3-band priority qdisc"); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 0e16dfda0bd7..d920f57dc6d7 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_qfq.c Quick Fair Queueing Plus Scheduler. * * Copyright (c) 2009 Fabio Checconi, Luigi Rizzo, and Paolo Valente. * Copyright (c) 2012 Paolo Valente. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. */ #include <linux/module.h> @@ -116,6 +113,7 @@ #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ +#define QFQ_MAX_LMAX (1UL << QFQ_MTU_SHIFT) #define QFQ_MAX_AGG_CLASSES 8 /* max num classes per aggregate allowed */ @@ -132,10 +130,7 @@ struct qfq_aggregate; struct qfq_class { struct Qdisc_class_common common; - unsigned int refcnt; - unsigned int filter_cnt; - - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct Qdisc *qdisc; @@ -207,6 +202,11 @@ struct qfq_sched { */ enum update_reason {enqueue, requeue}; +static bool cl_is_active(struct qfq_class *cl) +{ + return !list_empty(&cl->alist); +} + static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) { struct qfq_sched *q = qdisc_priv(sch); @@ -218,18 +218,14 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct qfq_class, common); } -static void qfq_purge_queue(struct qfq_class *cl) -{ - unsigned int len = cl->qdisc->q.qlen; - unsigned int backlog = cl->qdisc->qstats.backlog; - - qdisc_reset(cl->qdisc); - qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); -} +static const struct netlink_range_validation lmax_range = { + .min = QFQ_MIN_LMAX, + .max = QFQ_MAX_LMAX, +}; static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { - [TCA_QFQ_WEIGHT] = { .type = NLA_U32 }, - [TCA_QFQ_LMAX] = { .type = NLA_U32 }, + [TCA_QFQ_WEIGHT] = NLA_POLICY_RANGE(NLA_U32, 1, QFQ_MAX_WEIGHT), + [TCA_QFQ_LMAX] = NLA_POLICY_FULL_RANGE(NLA_U32, &lmax_range), }; /* @@ -356,7 +352,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) struct qfq_aggregate *agg = cl->agg; - list_del(&cl->alist); /* remove from RR queue of the aggregate */ + list_del_init(&cl->alist); /* remove from RR queue of the aggregate */ if (list_empty(&agg->active)) /* agg is now inactive */ qfq_deactivate_agg(q, agg); } @@ -388,8 +384,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, u32 lmax) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight); + struct qfq_aggregate *new_agg; + /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */ + if (lmax > QFQ_MAX_LMAX) + return -EINVAL; + + new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC); if (new_agg == NULL) @@ -403,58 +404,60 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, } static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)*arg; bool existing = false; struct nlattr *tb[TCA_QFQ_MAX + 1]; struct qfq_aggregate *new_agg = NULL; - u32 weight, lmax, inv_w; + u32 weight, lmax, inv_w, old_weight, old_lmax; int err; int delta_w; - if (tca[TCA_OPTIONS] == NULL) { - pr_notice("qfq: no options\n"); + if (NL_REQ_ATTR_CHECK(extack, NULL, tca, TCA_OPTIONS)) { + NL_SET_ERR_MSG_MOD(extack, "missing options"); return -EINVAL; } - err = nla_parse_nested(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy, - NULL); + err = nla_parse_nested_deprecated(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], + qfq_policy, extack); if (err < 0) return err; - if (tb[TCA_QFQ_WEIGHT]) { - weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]); - if (!weight || weight > (1UL << QFQ_MAX_WSHIFT)) { - pr_notice("qfq: invalid weight %u\n", weight); - return -EINVAL; - } - } else - weight = 1; + weight = nla_get_u32_default(tb[TCA_QFQ_WEIGHT], 1); if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); + } else { + /* MTU size is user controlled */ + lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > QFQ_MAX_LMAX) { + NL_SET_ERR_MSG_MOD(extack, + "MTU size out of bounds for qfq"); return -EINVAL; } - } else - lmax = psched_mtu(qdisc_dev(sch)); + } inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; - if (cl != NULL && - lmax == cl->agg->lmax && - weight == cl->agg->class_weight) - return 0; /* nothing to change */ + if (cl != NULL) { + sch_tree_lock(sch); + old_weight = cl->agg->class_weight; + old_lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (lmax == old_lmax && weight == old_weight) + return 0; /* nothing to change */ + } - delta_w = weight - (cl ? cl->agg->class_weight : 0); + delta_w = weight - (cl ? old_weight : 0); if (q->wsum + delta_w > QFQ_MAX_WSUM) { - pr_notice("qfq: total weight out of range (%d + %u)\n", - delta_w, q->wsum); + NL_SET_ERR_MSG_FMT_MOD(extack, + "total weight out of range (%d + %u)", + delta_w, q->wsum); return -EINVAL; } @@ -463,7 +466,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; @@ -477,12 +480,13 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - cl->refcnt = 1; + gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->deficit = lmax; + INIT_LIST_HEAD(&cl->alist); - cl->qdisc = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + classid, NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; @@ -490,7 +494,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) goto destroy_class; @@ -498,11 +502,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl->qdisc != &noop_qdisc) qdisc_hash_add(cl->qdisc, true); - sch_tree_lock(sch); - qdisc_class_hash_insert(&q->clhash, &cl->common); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); set_change_agg: sch_tree_lock(sch); @@ -520,70 +519,58 @@ set_change_agg: } if (existing) qfq_deact_rm_from_agg(q, cl); + else + qdisc_class_hash_insert(&q->clhash, &cl->common); qfq_add_to_agg(q, new_agg, cl); sch_tree_unlock(sch); + qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; destroy_class: - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); return err; } static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { - struct qfq_sched *q = qdisc_priv(sch); - - qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } -static int qfq_delete_class(struct Qdisc *sch, unsigned long arg) +static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; - if (cl->filter_cnt > 0) + if (qdisc_class_in_use(&cl->common)) { + NL_SET_ERR_MSG_MOD(extack, "QFQ class in use"); return -EBUSY; + } sch_tree_lock(sch); - qfq_purge_queue(cl); + qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); - - BUG_ON(--cl->refcnt == 0); - /* - * This shouldn't happen: we "hold" one cops->get() when called - * from tc_ctl_tclass; the destroy method is done from cops->put(). - */ + qfq_rm_from_agg(q, cl); sch_tree_unlock(sch); + + qfq_destroy_class(sch, cl); return 0; } -static unsigned long qfq_get_class(struct Qdisc *sch, u32 classid) +static unsigned long qfq_search_class(struct Qdisc *sch, u32 classid) { - struct qfq_class *cl = qfq_find_class(sch, classid); - - if (cl != NULL) - cl->refcnt++; - - return (unsigned long)cl; + return (unsigned long)qfq_find_class(sch, classid); } -static void qfq_put_class(struct Qdisc *sch, unsigned long arg) -{ - struct qfq_class *cl = (struct qfq_class *)arg; - - if (--cl->refcnt == 0) - qfq_destroy_class(sch, cl); -} - -static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); @@ -598,8 +585,8 @@ static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent, { struct qfq_class *cl = qfq_find_class(sch, classid); - if (cl != NULL) - cl->filter_cnt++; + if (cl) + qdisc_class_get(&cl->common); return (unsigned long)cl; } @@ -608,17 +595,18 @@ static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct qfq_class *cl = (struct qfq_class *)arg; - cl->filter_cnt--; + qdisc_class_put(&cl->common); } static int qfq_graft_class(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) { struct qfq_class *cl = (struct qfq_class *)arg; if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, cl->common.classid); + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + cl->common.classid, NULL); if (new == NULL) new = &noop_qdisc; } @@ -639,16 +627,22 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, { struct qfq_class *cl = (struct qfq_class *)arg; struct nlattr *nest; + u32 class_weight, lmax; tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle = cl->common.classid; tcm->tcm_info = cl->qdisc->handle; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) || - nla_put_u32(skb, TCA_QFQ_LMAX, cl->agg->lmax)) + + sch_tree_lock(sch); + class_weight = cl->agg->class_weight; + lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (nla_put_u32(skb, TCA_QFQ_WEIGHT, class_weight) || + nla_put_u32(skb, TCA_QFQ_LMAX, lmax)) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -665,14 +659,14 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, memset(&xstats, 0, sizeof(xstats)); + sch_tree_lock(sch); xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; + sch_tree_unlock(sch); - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, - &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0) + qdisc_qstats_copy(d, cl->qdisc) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); @@ -689,15 +683,8 @@ static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, (unsigned long)cl, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) return; - } - arg->count++; } } } @@ -720,7 +707,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -728,6 +715,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return NULL; } @@ -999,19 +987,24 @@ static void qfq_update_eligible(struct qfq_sched *q) } /* Dequeue head packet of the head class in the DRR queue of the aggregate. */ -static void agg_dequeue(struct qfq_aggregate *agg, - struct qfq_class *cl, unsigned int len) +static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, + struct qfq_class *cl, unsigned int len) { - qdisc_dequeue_peeked(cl->qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc); + + if (!skb) + return NULL; cl->deficit -= (int) len; if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */ - list_del(&cl->alist); - else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) { + list_del_init(&cl->alist); + else if (cl->deficit < qdisc_peek_len(cl->qdisc)) { cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } + + return skb; } static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, @@ -1023,7 +1016,7 @@ static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, *cl = list_first_entry(&agg->active, struct qfq_class, alist); skb = (*cl)->qdisc->ops->peek((*cl)->qdisc); if (skb == NULL) - WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n"); + qdisc_warn_nonwc("qfq_dequeue", (*cl)->qdisc); else *len = qdisc_pkt_len(skb); @@ -1157,11 +1150,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) if (!skb) return NULL; - qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; + + skb = agg_dequeue(in_serv_agg, cl, len); + + if (!skb) { + sch->q.qlen++; + return NULL; + } + + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); - agg_dequeue(in_serv_agg, cl, len); /* If lmax is lowered, through qfq_change_class, for a class * owning pending packets with larger size than the new value * of lmax, then the following condition may hold. @@ -1225,6 +1225,7 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q) static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb), gso_segs; struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; struct qfq_aggregate *agg; @@ -1234,22 +1235,22 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (cl == NULL) { if (err & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); - kfree_skb(skb); + __qdisc_drop(skb, to_free); return err; } pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); - if (unlikely(cl->agg->lmax < qdisc_pkt_len(skb))) { + if (unlikely(cl->agg->lmax < len)) { pr_debug("qfq: increasing maxpkt from %u to %u for class %u", - cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid); - err = qfq_change_agg(sch, cl, cl->agg->class_weight, - qdisc_pkt_len(skb)); + cl->agg->lmax, len, cl->common.classid); + err = qfq_change_agg(sch, cl, cl->agg->class_weight, len); if (err) { cl->qstats.drops++; return qdisc_drop(skb, sch, to_free); } } + gso_segs = qdisc_pkt_segs(skb); err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); @@ -1260,16 +1261,16 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - bstats_update(&cl->bstats, skb); - qdisc_qstats_backlog_inc(sch, skb); + _bstats_update(&cl->bstats, len, gso_segs); + sch->qstats.backlog += len; ++sch->q.qlen; agg = cl->agg; - /* if the queue was not empty, then done here */ - if (cl->qdisc->q.qlen != 1) { + /* if the class is active, then done here */ + if (cl_is_active(cl)) { if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) && list_first_entry(&agg->active, struct qfq_class, alist) - == cl && cl->deficit < qdisc_pkt_len(skb)) + == cl && cl->deficit < len) list_move_tail(&cl->alist, &agg->active); return err; @@ -1428,18 +1429,20 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; - if (cl->qdisc->q.qlen == 0) - qfq_deactivate_class(q, cl); + if (list_empty(&cl->alist)) + return; + qfq_deactivate_class(q, cl); } -static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) +static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_group *grp; int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; @@ -1447,10 +1450,8 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) if (err < 0) return err; - if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES) - max_classes = QFQ_MAX_AGG_CLASSES; - else - max_classes = qdisc_dev(sch)->tx_queue_len + 1; + max_classes = min_t(u64, (u64)qdisc_dev(sch)->tx_queue_len + 1, + QFQ_MAX_AGG_CLASSES); /* max_cl_shift = floor(log_2(max_classes)) */ max_cl_shift = __fls(max_classes); q->max_agg_classes = 1<<max_cl_shift; @@ -1486,8 +1487,6 @@ static void qfq_reset_qdisc(struct Qdisc *sch) qdisc_reset(cl->qdisc); } } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void qfq_destroy_qdisc(struct Qdisc *sch) @@ -1502,6 +1501,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { + qfq_rm_from_agg(q, cl); qfq_destroy_class(sch, cl); } } @@ -1511,8 +1511,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) static const struct Qdisc_class_ops qfq_class_ops = { .change = qfq_change_class, .delete = qfq_delete_class, - .get = qfq_get_class, - .put = qfq_put_class, + .find = qfq_search_class, .tcf_block = qfq_tcf_block, .bind_tcf = qfq_bind_tcf, .unbind_tcf = qfq_unbind_tcf, @@ -1536,6 +1535,7 @@ static struct Qdisc_ops qfq_qdisc_ops __read_mostly = { .destroy = qfq_destroy_qdisc, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("qfq"); static int __init qfq_init(void) { @@ -1550,3 +1550,4 @@ static void __exit qfq_exit(void) module_init(qfq_init); module_exit(qfq_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Quick Fair Queueing Plus qdisc"); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 11292adce412..479c42d11083 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_red.c Random Early Detection queue. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: @@ -19,6 +15,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <net/inet_ecn.h> #include <net/red.h> @@ -38,14 +35,23 @@ struct red_sched_data { u32 limit; /* HARD maximal queue length */ + unsigned char flags; + /* Non-flags in tc_red_qopt.flags. */ + unsigned char userbits; + struct timer_list adapt_timer; + struct Qdisc *sch; struct red_parms parms; struct red_vars vars; struct red_stats stats; struct Qdisc *qdisc; + struct tcf_qevent qe_early_drop; + struct tcf_qevent qe_mark; }; +#define TC_RED_SUPPORTED_FLAGS (TC_RED_HISTORIC_FLAGS | TC_RED_NODROP) + static inline int red_use_ecn(struct red_sched_data *q) { return q->flags & TC_RED_ECN; @@ -56,11 +62,18 @@ static inline int red_use_harddrop(struct red_sched_data *q) return q->flags & TC_RED_HARDDROP; } +static int red_use_nodrop(struct red_sched_data *q) +{ + return q->flags & TC_RED_NODROP; +} + static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_CONGESTED; struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; + unsigned int len; int ret; q->vars.qavg = red_calc_qavg(&q->parms, @@ -76,29 +89,50 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, case RED_PROB_MARK: qdisc_qstats_overlimit(sch); - if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { + if (!red_use_ecn(q)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + if (INET_ECN_set_ce(skb)) { + q->stats.prob_mark++; + skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret); + if (!skb) + return NET_XMIT_CN | ret; + } else if (!red_use_nodrop(q)) { q->stats.prob_drop++; goto congestion_drop; } - q->stats.prob_mark++; + /* Non-ECT packet in ECN nodrop mode: queue it. */ break; case RED_HARD_MARK: + reason = SKB_DROP_REASON_QDISC_OVERLIMIT; qdisc_qstats_overlimit(sch); - if (red_use_harddrop(q) || !red_use_ecn(q) || - !INET_ECN_set_ce(skb)) { + if (red_use_harddrop(q) || !red_use_ecn(q)) { q->stats.forced_drop++; goto congestion_drop; } - q->stats.forced_mark++; + if (INET_ECN_set_ce(skb)) { + q->stats.forced_mark++; + skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret); + if (!skb) + return NET_XMIT_CN | ret; + } else if (!red_use_nodrop(q)) { + q->stats.forced_drop++; + goto congestion_drop; + } + + /* Non-ECT packet in ECN nodrop mode: queue it. */ break; } + len = qdisc_pkt_len(skb); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; @@ -107,7 +141,11 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, return ret; congestion_drop: - qdisc_drop(skb, sch, to_free); + skb = tcf_qevent_handle(&q->qe_early_drop, sch, skb, to_free, &ret); + if (!skb) + return NET_XMIT_CN | ret; + + qdisc_drop_reason(skb, sch, to_free, reason); return NET_XMIT_CN; } @@ -142,75 +180,124 @@ static void red_reset(struct Qdisc *sch) struct red_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; red_restart(&q->vars); } +static int red_offload(struct Qdisc *sch, bool enable) +{ + struct red_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_red_qopt_offload opt = { + .handle = sch->handle, + .parent = sch->parent, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + if (enable) { + opt.command = TC_RED_REPLACE; + opt.set.min = q->parms.qth_min >> q->parms.Wlog; + opt.set.max = q->parms.qth_max >> q->parms.Wlog; + opt.set.probability = q->parms.max_P; + opt.set.limit = q->limit; + opt.set.is_ecn = red_use_ecn(q); + opt.set.is_harddrop = red_use_harddrop(q); + opt.set.is_nodrop = red_use_nodrop(q); + opt.set.qstats = &sch->qstats; + } else { + opt.command = TC_RED_DESTROY; + } + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); +} + static void red_destroy(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); - del_timer_sync(&q->adapt_timer); - qdisc_destroy(q->qdisc); + tcf_qevent_destroy(&q->qe_mark, sch); + tcf_qevent_destroy(&q->qe_early_drop, sch); + timer_delete_sync(&q->adapt_timer); + red_offload(sch, false); + qdisc_put(q->qdisc); } static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { + [TCA_RED_UNSPEC] = { .strict_start_type = TCA_RED_FLAGS }, [TCA_RED_PARMS] = { .len = sizeof(struct tc_red_qopt) }, [TCA_RED_STAB] = { .len = RED_STAB_SIZE }, [TCA_RED_MAX_P] = { .type = NLA_U32 }, + [TCA_RED_FLAGS] = NLA_POLICY_BITFIELD32(TC_RED_SUPPORTED_FLAGS), + [TCA_RED_EARLY_DROP_BLOCK] = { .type = NLA_U32 }, + [TCA_RED_MARK_BLOCK] = { .type = NLA_U32 }, }; -static int red_change(struct Qdisc *sch, struct nlattr *opt) +static int __red_change(struct Qdisc *sch, struct nlattr **tb, + struct netlink_ext_ack *extack) { + struct Qdisc *old_child = NULL, *child = NULL; struct red_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_RED_MAX + 1]; + struct nla_bitfield32 flags_bf; struct tc_red_qopt *ctl; - struct Qdisc *child = NULL; + unsigned char userbits; + unsigned char flags; int err; u32 max_P; - - if (opt == NULL) - return -EINVAL; - - err = nla_parse_nested(tb, TCA_RED_MAX, opt, red_policy, NULL); - if (err < 0) - return err; + u8 *stab; if (tb[TCA_RED_PARMS] == NULL || tb[TCA_RED_STAB] == NULL) return -EINVAL; - max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; + max_P = nla_get_u32_default(tb[TCA_RED_MAX_P], 0); ctl = nla_data(tb[TCA_RED_PARMS]); + stab = nla_data(tb[TCA_RED_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Scell_log, stab)) + return -EINVAL; + + err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS, + tb[TCA_RED_FLAGS], TC_RED_SUPPORTED_FLAGS, + &flags_bf, &userbits, extack); + if (err) + return err; if (ctl->limit > 0) { - child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit); + child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit, + extack); if (IS_ERR(child)) return PTR_ERR(child); - } - if (child != &noop_qdisc) + /* child is fifo, no need to check for noop_qdisc */ qdisc_hash_add(child, true); + } + sch_tree_lock(sch); - q->flags = ctl->flags; + + flags = (q->flags & ~flags_bf.selector) | flags_bf.value; + err = red_validate_flags(flags, extack); + if (err) + goto unlock_out; + + q->flags = flags; + q->userbits = userbits; q->limit = ctl->limit; if (child) { - qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, - q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_purge_queue(q->qdisc); + old_child = q->qdisc; q->qdisc = child; } red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_RED_STAB]), + stab, max_P); red_set_vars(&q->vars); - del_timer(&q->adapt_timer); + timer_delete(&q->adapt_timer); if (ctl->flags & TC_RED_ADAPTATIVE) mod_timer(&q->adapt_timer, jiffies + HZ/2); @@ -218,28 +305,107 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) red_start_of_idle_period(&q->vars); sch_tree_unlock(sch); + + red_offload(sch, true); + + if (old_child) + qdisc_put(old_child); return 0; + +unlock_out: + sch_tree_unlock(sch); + if (child) + qdisc_put(child); + return err; } -static inline void red_adaptative_timer(unsigned long arg) +static inline void red_adaptative_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct red_sched_data *q = qdisc_priv(sch); - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + struct red_sched_data *q = timer_container_of(q, t, adapt_timer); + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); red_adaptative_algo(&q->parms, &q->vars); mod_timer(&q->adapt_timer, jiffies + HZ/2); spin_unlock(root_lock); + rcu_read_unlock(); } -static int red_init(struct Qdisc *sch, struct nlattr *opt) +static int red_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_RED_MAX + 1]; + int err; q->qdisc = &noop_qdisc; - setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch); - return red_change(sch, opt); + q->sch = sch; + timer_setup(&q->adapt_timer, red_adaptative_timer, 0); + + if (!opt) + return -EINVAL; + + err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy, + extack); + if (err < 0) + return err; + + err = __red_change(sch, tb, extack); + if (err) + return err; + + err = tcf_qevent_init(&q->qe_early_drop, sch, + FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, + tb[TCA_RED_EARLY_DROP_BLOCK], extack); + if (err) + return err; + + return tcf_qevent_init(&q->qe_mark, sch, + FLOW_BLOCK_BINDER_TYPE_RED_MARK, + tb[TCA_RED_MARK_BLOCK], extack); +} + +static int red_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct red_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_RED_MAX + 1]; + int err; + + err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy, + extack); + if (err < 0) + return err; + + err = tcf_qevent_validate_change(&q->qe_early_drop, + tb[TCA_RED_EARLY_DROP_BLOCK], extack); + if (err) + return err; + + err = tcf_qevent_validate_change(&q->qe_mark, + tb[TCA_RED_MARK_BLOCK], extack); + if (err) + return err; + + return __red_change(sch, tb, extack); +} + +static int red_dump_offload_stats(struct Qdisc *sch) +{ + struct tc_red_qopt_offload hw_stats = { + .command = TC_RED_STATS, + .handle = sch->handle, + .parent = sch->parent, + { + .stats.bstats = &sch->bstats, + .stats.qstats = &sch->qstats, + }, + }; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_RED, &hw_stats); } static int red_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -248,20 +414,29 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *opts = NULL; struct tc_red_qopt opt = { .limit = q->limit, - .flags = q->flags, + .flags = (q->flags & TC_RED_HISTORIC_FLAGS) | + q->userbits, .qth_min = q->parms.qth_min >> q->parms.Wlog, .qth_max = q->parms.qth_max >> q->parms.Wlog, .Wlog = q->parms.Wlog, .Plog = q->parms.Plog, .Scell_log = q->parms.Scell_log, }; + int err; + + err = red_dump_offload_stats(sch); + if (err) + goto nla_put_failure; - sch->qstats.backlog = q->qdisc->qstats.backlog; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) || - nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P)) + nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P) || + nla_put_bitfield32(skb, TCA_RED_FLAGS, + q->flags, TC_RED_SUPPORTED_FLAGS) || + tcf_qevent_dump(skb, TCA_RED_MARK_BLOCK, &q->qe_mark) || + tcf_qevent_dump(skb, TCA_RED_EARLY_DROP_BLOCK, &q->qe_early_drop)) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -273,12 +448,24 @@ nla_put_failure: static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct red_sched_data *q = qdisc_priv(sch); - struct tc_red_xstats st = { - .early = q->stats.prob_drop + q->stats.forced_drop, - .pdrop = q->stats.pdrop, - .other = q->stats.other, - .marked = q->stats.prob_mark + q->stats.forced_mark, - }; + struct net_device *dev = qdisc_dev(sch); + struct tc_red_xstats st = {0}; + + if (sch->flags & TCQ_F_OFFLOADED) { + struct tc_red_qopt_offload hw_stats_request = { + .command = TC_RED_XSTATS, + .handle = sch->handle, + .parent = sch->parent, + { + .xstats = &q->stats, + }, + }; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, + &hw_stats_request); + } + st.early = q->stats.prob_drop + q->stats.forced_drop; + st.pdrop = q->stats.pdrop; + st.marked = q->stats.prob_mark + q->stats.forced_mark; return gnet_stats_copy_app(d, &st, sizeof(st)); } @@ -293,8 +480,23 @@ static int red_dump_class(struct Qdisc *sch, unsigned long cl, return 0; } +static void red_graft_offload(struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + struct netlink_ext_ack *extack) +{ + struct tc_red_qopt_offload graft_offload = { + .handle = sch->handle, + .parent = sch->parent, + .child_handle = new->handle, + .command = TC_RED_GRAFT, + }; + + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, old, + TC_SETUP_QDISC_RED, &graft_offload, extack); +} + static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); @@ -302,6 +504,8 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->qdisc); + + red_graft_offload(sch, new, *old, extack); return 0; } @@ -311,32 +515,22 @@ static struct Qdisc *red_leaf(struct Qdisc *sch, unsigned long arg) return q->qdisc; } -static unsigned long red_get(struct Qdisc *sch, u32 classid) +static unsigned long red_find(struct Qdisc *sch, u32 classid) { return 1; } -static void red_put(struct Qdisc *sch, unsigned long arg) -{ -} - static void red_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { - if (walker->count >= walker->skip) - if (walker->fn(sch, 1, walker) < 0) { - walker->stop = 1; - return; - } - walker->count++; + tc_qdisc_stats_dump(sch, 1, walker); } } static const struct Qdisc_class_ops red_class_ops = { .graft = red_graft, .leaf = red_leaf, - .get = red_get, - .put = red_put, + .find = red_find, .walk = red_walk, .dump = red_dump_class, }; @@ -356,6 +550,7 @@ static struct Qdisc_ops red_qdisc_ops __read_mostly = { .dump_stats = red_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("red"); static int __init red_module_init(void) { @@ -371,3 +566,4 @@ module_init(red_module_init) module_exit(red_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Random Early Detection qdisc"); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 11fb6ec878d6..d2835f1168e1 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -1,19 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_sfb.c Stochastic Fair Blue * * Copyright (c) 2008-2011 Juliusz Chroboczek <jch@pps.jussieu.fr> * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * * W. Feng, D. Kandlur, D. Saha, K. Shin. Blue: * A New Class of Active Queue Management Algorithms. * U. Michigan CSE-TR-387-99, April 1999. * * http://www.thefengs.com/wuchang/blue/CSE-TR-387-99.pdf - * */ #include <linux/module.h> @@ -22,7 +18,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/random.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <net/ip.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -49,7 +45,7 @@ struct sfb_bucket { * (Section 4.4 of SFB reference : moving hash functions) */ struct sfb_bins { - u32 perturbation; /* jhash perturbation */ + siphash_key_t perturbation; /* siphash key */ struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; }; @@ -139,15 +135,15 @@ static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) } } -static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) +static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q) { u32 sfbhash; - sfbhash = sfb_hash(skb, 0); + sfbhash = cb->hashes[0]; if (sfbhash) increment_one_qlen(sfbhash, 0, q); - sfbhash = sfb_hash(skb, 1); + sfbhash = cb->hashes[1]; if (sfbhash) increment_one_qlen(sfbhash, 1, q); } @@ -221,7 +217,8 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = prandom_u32(); + get_random_bytes(&q->bins[slot].perturbation, + sizeof(q->bins[slot].perturbation)); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -260,7 +257,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, struct tcf_result res; int result; - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -268,6 +265,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return false; } @@ -282,9 +280,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; struct sfb_sched_data *q = qdisc_priv(sch); + unsigned int len = qdisc_pkt_len(skb); struct Qdisc *child = q->qdisc; struct tcf_proto *fl; + struct sfb_skb_cb cb; int i; u32 p_min = ~0; u32 minqlen = ~0; @@ -317,9 +318,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If using external classifiers, get result and record it. */ if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; - sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation); } else { - sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation); + sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation); } @@ -355,7 +356,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Inelastic flow */ if (q->double_buffering) { sfbhash = skb_get_hash_perturb(skb, - q->bins[slot].perturbation); + &q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; @@ -379,7 +380,8 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto enqueue; } - r = prandom_u32() & SFB_MAX_PROB; + r = get_random_u16() & SFB_MAX_PROB; + reason = SKB_DROP_REASON_QDISC_CONGESTED; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { @@ -401,11 +403,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, } enqueue: + memcpy(&cb, sfb_skb_cb(skb), sizeof(cb)); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; - increment_qlen(skb, q); + increment_qlen(&cb, q); } else if (net_xmit_drop_count(ret)) { q->stats.childdrop++; qdisc_qstats_drop(sch); @@ -413,7 +416,7 @@ enqueue: return ret; drop: - qdisc_drop(skb, sch, to_free); + qdisc_drop_reason(skb, sch, to_free, reason); return NET_XMIT_CN; other_drop: if (ret & __NET_XMIT_BYPASS) @@ -454,9 +457,8 @@ static void sfb_reset(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; + if (likely(q->qdisc)) + qdisc_reset(q->qdisc); q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); @@ -468,7 +470,7 @@ static void sfb_destroy(struct Qdisc *sch) struct sfb_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = { @@ -487,17 +489,19 @@ static const struct tc_sfb_qopt sfb_default_ops = { .penalty_burst = 20, }; -static int sfb_change(struct Qdisc *sch, struct nlattr *opt) +static int sfb_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); - struct Qdisc *child; + struct Qdisc *child, *old; struct nlattr *tb[TCA_SFB_MAX + 1]; const struct tc_sfb_qopt *ctl = &sfb_default_ops; u32 limit; int err; if (opt) { - err = nla_parse_nested(tb, TCA_SFB_MAX, opt, sfb_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_SFB_MAX, opt, + sfb_policy, NULL); if (err < 0) return -EINVAL; @@ -511,7 +515,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) if (limit == 0) limit = qdisc_dev(sch)->tx_queue_len; - child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit); + child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit, extack); if (IS_ERR(child)) return PTR_ERR(child); @@ -519,9 +523,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) qdisc_hash_add(child, true); sch_tree_lock(sch); - qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, - q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_purge_queue(q->qdisc); + old = q->qdisc; q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); @@ -544,21 +547,23 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) sfb_init_perturbation(1, q); sch_tree_unlock(sch); + qdisc_put(old); return 0; } -static int sfb_init(struct Qdisc *sch, struct nlattr *opt) +static int sfb_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; q->qdisc = &noop_qdisc; - return sfb_change(sch, opt); + return sfb_change(sch, opt, extack); } static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -578,7 +583,7 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) }; sch->qstats.backlog = q->qdisc->qstats.backlog; - opts = nla_nest_start(skb, TCA_OPTIONS); + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt)) @@ -614,7 +619,7 @@ static int sfb_dump_class(struct Qdisc *sch, unsigned long cl, } static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); @@ -632,22 +637,24 @@ static struct Qdisc *sfb_leaf(struct Qdisc *sch, unsigned long arg) return q->qdisc; } -static unsigned long sfb_get(struct Qdisc *sch, u32 classid) +static unsigned long sfb_find(struct Qdisc *sch, u32 classid) { return 1; } -static void sfb_put(struct Qdisc *sch, unsigned long arg) +static void sfb_unbind(struct Qdisc *sch, unsigned long arg) { } static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { return -ENOSYS; } -static int sfb_delete(struct Qdisc *sch, unsigned long cl) +static int sfb_delete(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { return -ENOSYS; } @@ -655,16 +662,12 @@ static int sfb_delete(struct Qdisc *sch, unsigned long cl) static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { - if (walker->count >= walker->skip) - if (walker->fn(sch, 1, walker) < 0) { - walker->stop = 1; - return; - } - walker->count++; + tc_qdisc_stats_dump(sch, 1, walker); } } -static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); @@ -683,14 +686,13 @@ static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent, static const struct Qdisc_class_ops sfb_class_ops = { .graft = sfb_graft, .leaf = sfb_leaf, - .get = sfb_get, - .put = sfb_put, + .find = sfb_find, .change = sfb_change_class, .delete = sfb_delete, .walk = sfb_walk, .tcf_block = sfb_tcf_block, .bind_tcf = sfb_bind, - .unbind_tcf = sfb_put, + .unbind_tcf = sfb_unbind, .dump = sfb_dump_class, }; @@ -709,6 +711,7 @@ static struct Qdisc_ops sfb_qdisc_ops __read_mostly = { .dump_stats = sfb_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("sfb"); static int __init sfb_module_init(void) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index f80ea2cc5f1f..96eb2f122973 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_sfq.c Stochastic Fairness Queueing discipline. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ @@ -18,7 +14,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/netlink.h> @@ -81,12 +77,6 @@ #define SFQ_EMPTY_SLOT 0xffff #define SFQ_DEFAULT_HASH_DIVISOR 1024 -/* We use 16 bits to store allot, and want to handle packets up to 64K - * Scale allot by 8 (1<<3) so that no overflow occurs. - */ -#define SFQ_ALLOT_SHIFT 3 -#define SFQ_ALLOT_SIZE(X) DIV_ROUND_UP(X, 1 << SFQ_ALLOT_SHIFT) - /* This type should contain at least SFQ_MAX_DEPTH + 1 + SFQ_MAX_FLOWS values */ typedef u16 sfq_index; @@ -108,7 +98,7 @@ struct sfq_slot { sfq_index next; /* next slot in sfq RR chain */ struct sfq_head dep; /* anchor in dep[] chains */ unsigned short hash; /* hash value (index in ht[]) */ - short allot; /* credit for this slot */ + int allot; /* credit for this slot */ unsigned int backlog; struct red_vars vars; @@ -121,10 +111,9 @@ struct sfq_sched_data { u8 headdrop; u8 maxdepth; /* limit of packets per flow */ - u32 perturbation; + siphash_key_t perturbation; u8 cur_depth; /* depth of longest slot */ u8 flags; - unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ struct tcf_proto __rcu *filter_list; struct tcf_block *block; sfq_index *ht; /* Hash table ('divisor' slots) */ @@ -145,6 +134,7 @@ struct sfq_sched_data { int perturb_period; unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ struct timer_list perturb_timer; + struct Qdisc *sch; }; /* @@ -160,7 +150,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index static unsigned int sfq_hash(const struct sfq_sched_data *q, const struct sk_buff *skb) { - return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1); + return skb_get_hash_perturb(skb, &q->perturbation) & (q->divisor - 1); } static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, @@ -181,7 +171,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return sfq_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -189,6 +179,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + fallthrough; case TC_ACT_SHOT: return 0; } @@ -292,7 +283,7 @@ static inline void slot_queue_add(struct sfq_slot *slot, struct sk_buff *skb) slot->skblist_prev = skb; } -static unsigned int sfq_drop(struct Qdisc *sch) +static unsigned int sfq_drop(struct Qdisc *sch, struct sk_buff **to_free) { struct sfq_sched_data *q = qdisc_priv(sch); sfq_index x, d = q->cur_depth; @@ -310,9 +301,8 @@ drop: slot->backlog -= len; sfq_dec(q, x); sch->q.qlen--; - qdisc_qstats_drop(sch); qdisc_qstats_backlog_dec(sch, skb); - kfree_skb(skb); + qdisc_drop(skb, sch, to_free); return len; } @@ -320,7 +310,10 @@ drop: /* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */ x = q->tail->next; slot = &q->slots[x]; - q->tail->next = slot->next; + if (slot->next == x) + q->tail = NULL; /* no more active slots */ + else + q->tail->next = slot->next; q->ht[slot->hash] = SFQ_EMPTY_SLOT; goto drop; } @@ -352,7 +345,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) unsigned int hash, dropped; sfq_index x, qlen; struct sfq_slot *slot; - int uninitialized_var(ret); + int ret; struct sk_buff *head; int delta; @@ -360,7 +353,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) if (hash == 0) { if (ret & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); - kfree_skb(skb); + __qdisc_drop(skb, to_free); return ret; } hash--; @@ -437,6 +430,7 @@ congestion_drop: qdisc_drop(head, sch, to_free); slot_queue_add(slot, skb); + qdisc_tree_reduce_backlog(sch, 0, delta); return NET_XMIT_CN; } @@ -458,18 +452,20 @@ enqueue: */ q->tail = slot; /* We could use a bigger initial quantum for new flows */ - slot->allot = q->scaled_quantum; + slot->allot = q->quantum; } if (++sch->q.qlen <= q->limit) return NET_XMIT_SUCCESS; qlen = slot->qlen; - dropped = sfq_drop(sch); + dropped = sfq_drop(sch, to_free); /* Return Congestion Notification only if we dropped a packet * from this flow. */ - if (qlen != slot->qlen) + if (qlen != slot->qlen) { + qdisc_tree_reduce_backlog(sch, 0, dropped - qdisc_pkt_len(skb)); return NET_XMIT_CN; + } /* As we dropped a packet, better let upper stack know this */ qdisc_tree_reduce_backlog(sch, 1, dropped); @@ -493,7 +489,7 @@ next_slot: slot = &q->slots[a]; if (slot->allot <= 0) { q->tail = slot; - slot->allot += q->scaled_quantum; + slot->allot += q->quantum; goto next_slot; } skb = slot_dequeue_head(slot); @@ -512,7 +508,7 @@ next_slot: } q->tail->next = next_a; } else { - slot->allot -= SFQ_ALLOT_SIZE(qdisc_pkt_len(skb)); + slot->allot -= qdisc_pkt_len(skb); } return skb; } @@ -595,36 +591,58 @@ drop: q->tail->next = x; } q->tail = slot; - slot->allot = q->scaled_quantum; + slot->allot = q->quantum; } } sch->q.qlen -= dropped; qdisc_tree_reduce_backlog(sch, dropped, drop_len); } -static void sfq_perturbation(unsigned long arg) +static void sfq_perturbation(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct sfq_sched_data *q = qdisc_priv(sch); - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + struct sfq_sched_data *q = timer_container_of(q, t, perturb_timer); + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; + siphash_key_t nkey; + int period; + get_random_bytes(&nkey, sizeof(nkey)); + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - q->perturbation = prandom_u32(); + q->perturbation = nkey; if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); - if (q->perturb_period) - mod_timer(&q->perturb_timer, jiffies + q->perturb_period); + /* q->perturb_period can change under us from + * sfq_change() and sfq_destroy(). + */ + period = READ_ONCE(q->perturb_period); + if (period) + mod_timer(&q->perturb_timer, jiffies + period); + rcu_read_unlock(); } -static int sfq_change(struct Qdisc *sch, struct nlattr *opt) +static int sfq_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct sfq_sched_data *q = qdisc_priv(sch); struct tc_sfq_qopt *ctl = nla_data(opt); struct tc_sfq_qopt_v1 *ctl_v1 = NULL; unsigned int qlen, dropped = 0; struct red_parms *p = NULL; + struct sk_buff *to_free = NULL; + struct sk_buff *tail = NULL; + unsigned int maxflows; + unsigned int quantum; + unsigned int divisor; + int perturb_period; + u8 headdrop; + u8 maxdepth; + int limit; + u8 flags; + if (opt->nla_len < nla_attr_size(sizeof(*ctl))) return -EINVAL; @@ -633,52 +651,98 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; + + if ((int)ctl->quantum < 0) { + NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); + return -EINVAL; + } + + if (ctl->perturb_period < 0 || + ctl->perturb_period > INT_MAX / HZ) { + NL_SET_ERR_MSG_MOD(extack, "invalid perturb period"); + return -EINVAL; + } + perturb_period = ctl->perturb_period * HZ; + + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, + ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) + return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL); if (!p) return -ENOMEM; } + sch_tree_lock(sch); - if (ctl->quantum) { - q->quantum = ctl->quantum; - q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); - } - q->perturb_period = ctl->perturb_period * HZ; + + limit = q->limit; + divisor = q->divisor; + headdrop = q->headdrop; + maxdepth = q->maxdepth; + maxflows = q->maxflows; + quantum = q->quantum; + flags = q->flags; + + /* update and validate configuration */ + if (ctl->quantum) + quantum = ctl->quantum; if (ctl->flows) - q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); + maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) { - q->divisor = ctl->divisor; - q->maxflows = min_t(u32, q->maxflows, q->divisor); + divisor = ctl->divisor; + maxflows = min_t(u32, maxflows, divisor); } if (ctl_v1) { if (ctl_v1->depth) - q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH); + maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH); if (p) { - swap(q->red_parms, p); - red_set_parms(q->red_parms, + red_set_parms(p, ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog, ctl_v1->Plog, ctl_v1->Scell_log, NULL, ctl_v1->max_P); } - q->flags = ctl_v1->flags; - q->headdrop = ctl_v1->headdrop; + flags = ctl_v1->flags; + headdrop = ctl_v1->headdrop; } if (ctl->limit) { - q->limit = min_t(u32, ctl->limit, q->maxdepth * q->maxflows); - q->maxflows = min_t(u32, q->maxflows, q->limit); + limit = min_t(u32, ctl->limit, maxdepth * maxflows); + maxflows = min_t(u32, maxflows, limit); + } + if (limit == 1) { + sch_tree_unlock(sch); + kfree(p); + NL_SET_ERR_MSG_MOD(extack, "invalid limit"); + return -EINVAL; } + /* commit configuration */ + q->limit = limit; + q->divisor = divisor; + q->headdrop = headdrop; + q->maxdepth = maxdepth; + q->maxflows = maxflows; + WRITE_ONCE(q->perturb_period, perturb_period); + q->quantum = quantum; + q->flags = flags; + if (p) + swap(q->red_parms, p); + qlen = sch->q.qlen; - while (sch->q.qlen > q->limit) - dropped += sfq_drop(sch); + while (sch->q.qlen > q->limit) { + dropped += sfq_drop(sch, &to_free); + if (!tail) + tail = to_free; + } + + rtnl_kfree_skbs(to_free, tail); qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); - del_timer(&q->perturb_timer); + timer_delete(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); } sch_tree_unlock(sch); kfree(p); @@ -700,26 +764,27 @@ static void sfq_destroy(struct Qdisc *sch) struct sfq_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); - q->perturb_period = 0; - del_timer_sync(&q->perturb_timer); + WRITE_ONCE(q->perturb_period, 0); + timer_delete_sync(&q->perturb_timer); sfq_free(q->ht); sfq_free(q->slots); kfree(q->red_parms); } -static int sfq_init(struct Qdisc *sch, struct nlattr *opt) +static int sfq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct sfq_sched_data *q = qdisc_priv(sch); int i; int err; - err = tcf_block_get(&q->block, &q->filter_list); + q->sch = sch; + timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE); + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; - setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, - (unsigned long)sch); - for (i = 0; i < SFQ_MAX_DEPTH + 1; i++) { q->dep[i].next = i + SFQ_MAX_FLOWS; q->dep[i].prev = i + SFQ_MAX_FLOWS; @@ -732,12 +797,11 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->divisor = SFQ_DEFAULT_HASH_DIVISOR; q->maxflows = SFQ_DEFAULT_FLOWS; q->quantum = psched_mtu(qdisc_dev(sch)); - q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); if (opt) { - int err = sfq_change(sch, opt); + int err = sfq_change(sch, opt, extack); if (err) return err; } @@ -805,7 +869,7 @@ static struct Qdisc *sfq_leaf(struct Qdisc *sch, unsigned long arg) return NULL; } -static unsigned long sfq_get(struct Qdisc *sch, u32 classid) +static unsigned long sfq_find(struct Qdisc *sch, u32 classid) { return 0; } @@ -813,16 +877,15 @@ static unsigned long sfq_get(struct Qdisc *sch, u32 classid) static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { - /* we cannot bypass queue discipline anymore */ - sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } -static void sfq_put(struct Qdisc *q, unsigned long cl) +static void sfq_unbind(struct Qdisc *q, unsigned long cl) { } -static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct sfq_sched_data *q = qdisc_priv(sch); @@ -849,7 +912,7 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl, if (idx != SFQ_EMPTY_SLOT) { const struct sfq_slot *slot = &q->slots[idx]; - xstats.allot = slot->allot << SFQ_ALLOT_SHIFT; + xstats.allot = slot->allot; qs.qlen = slot->qlen; qs.backlog = slot->backlog; } @@ -867,26 +930,21 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (i = 0; i < q->divisor; i++) { - if (q->ht[i] == SFQ_EMPTY_SLOT || - arg->count < arg->skip) { + if (q->ht[i] == SFQ_EMPTY_SLOT) { arg->count++; continue; } - if (arg->fn(sch, i + 1, arg) < 0) { - arg->stop = 1; + if (!tc_qdisc_stats_dump(sch, i + 1, arg)) break; - } - arg->count++; } } static const struct Qdisc_class_ops sfq_class_ops = { .leaf = sfq_leaf, - .get = sfq_get, - .put = sfq_put, + .find = sfq_find, .tcf_block = sfq_tcf_block, .bind_tcf = sfq_bind, - .unbind_tcf = sfq_put, + .unbind_tcf = sfq_unbind, .dump = sfq_dump_class, .dump_stats = sfq_dump_class_stats, .walk = sfq_walk, @@ -906,6 +964,7 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = { .dump = sfq_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("sfq"); static int __init sfq_module_init(void) { @@ -918,3 +977,4 @@ static void __exit sfq_module_exit(void) module_init(sfq_module_init) module_exit(sfq_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Stochastic Fairness qdisc"); diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c new file mode 100644 index 000000000000..f485f62ab721 --- /dev/null +++ b/net/sched/sch_skbprio.c @@ -0,0 +1,310 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * net/sched/sch_skbprio.c SKB Priority Queue. + * + * Authors: Nishanth Devarajan, <ndev2021@gmail.com> + * Cody Doucette, <doucette@bu.edu> + * original idea by Michel Machado, Cody Doucette, and Qiaobin Fu + */ + +#include <linux/string.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> +#include <net/inet_ecn.h> + +/* SKB Priority Queue + * ================================= + * + * Skbprio (SKB Priority Queue) is a queueing discipline that prioritizes + * packets according to their skb->priority field. Under congestion, + * Skbprio drops already-enqueued lower priority packets to make space + * available for higher priority packets; it was conceived as a solution + * for denial-of-service defenses that need to route packets with different + * priorities as a mean to overcome DoS attacks. + */ + +struct skbprio_sched_data { + /* Queue state. */ + struct sk_buff_head qdiscs[SKBPRIO_MAX_PRIORITY]; + struct gnet_stats_queue qstats[SKBPRIO_MAX_PRIORITY]; + u16 highest_prio; + u16 lowest_prio; +}; + +static u16 calc_new_high_prio(const struct skbprio_sched_data *q) +{ + int prio; + + for (prio = q->highest_prio - 1; prio >= q->lowest_prio; prio--) { + if (!skb_queue_empty(&q->qdiscs[prio])) + return prio; + } + + /* SKB queue is empty, return 0 (default highest priority setting). */ + return 0; +} + +static u16 calc_new_low_prio(const struct skbprio_sched_data *q) +{ + int prio; + + for (prio = q->lowest_prio + 1; prio <= q->highest_prio; prio++) { + if (!skb_queue_empty(&q->qdiscs[prio])) + return prio; + } + + /* SKB queue is empty, return SKBPRIO_MAX_PRIORITY - 1 + * (default lowest priority setting). + */ + return SKBPRIO_MAX_PRIORITY - 1; +} + +static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1; + struct skbprio_sched_data *q = qdisc_priv(sch); + struct sk_buff_head *qdisc; + struct sk_buff_head *lp_qdisc; + struct sk_buff *to_drop; + u16 prio, lp; + + /* Obtain the priority of @skb. */ + prio = min(skb->priority, max_priority); + + qdisc = &q->qdiscs[prio]; + + /* sch->limit can change under us from skbprio_change() */ + if (sch->q.qlen < READ_ONCE(sch->limit)) { + __skb_queue_tail(qdisc, skb); + qdisc_qstats_backlog_inc(sch, skb); + q->qstats[prio].backlog += qdisc_pkt_len(skb); + + /* Check to update highest and lowest priorities. */ + if (prio > q->highest_prio) + q->highest_prio = prio; + + if (prio < q->lowest_prio) + q->lowest_prio = prio; + + sch->q.qlen++; + return NET_XMIT_SUCCESS; + } + + /* If this packet has the lowest priority, drop it. */ + lp = q->lowest_prio; + if (prio <= lp) { + q->qstats[prio].drops++; + q->qstats[prio].overlimits++; + return qdisc_drop(skb, sch, to_free); + } + + __skb_queue_tail(qdisc, skb); + qdisc_qstats_backlog_inc(sch, skb); + q->qstats[prio].backlog += qdisc_pkt_len(skb); + + /* Drop the packet at the tail of the lowest priority qdisc. */ + lp_qdisc = &q->qdiscs[lp]; + to_drop = __skb_dequeue_tail(lp_qdisc); + BUG_ON(!to_drop); + qdisc_qstats_backlog_dec(sch, to_drop); + qdisc_drop(to_drop, sch, to_free); + + q->qstats[lp].backlog -= qdisc_pkt_len(to_drop); + q->qstats[lp].drops++; + q->qstats[lp].overlimits++; + + /* Check to update highest and lowest priorities. */ + if (skb_queue_empty(lp_qdisc)) { + if (q->lowest_prio == q->highest_prio) { + q->lowest_prio = prio; + q->highest_prio = prio; + } else { + q->lowest_prio = calc_new_low_prio(q); + } + } + + if (prio > q->highest_prio) + q->highest_prio = prio; + + return NET_XMIT_CN; +} + +static struct sk_buff *skbprio_dequeue(struct Qdisc *sch) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + struct sk_buff_head *hpq = &q->qdiscs[q->highest_prio]; + struct sk_buff *skb = __skb_dequeue(hpq); + + if (unlikely(!skb)) + return NULL; + + sch->q.qlen--; + qdisc_qstats_backlog_dec(sch, skb); + qdisc_bstats_update(sch, skb); + + q->qstats[q->highest_prio].backlog -= qdisc_pkt_len(skb); + + /* Update highest priority field. */ + if (skb_queue_empty(hpq)) { + if (q->lowest_prio == q->highest_prio) { + q->highest_prio = 0; + q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; + } else { + q->highest_prio = calc_new_high_prio(q); + } + } + return skb; +} + +static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct tc_skbprio_qopt *ctl = nla_data(opt); + + if (opt->nla_len != nla_attr_size(sizeof(*ctl))) + return -EINVAL; + + WRITE_ONCE(sch->limit, ctl->limit); + return 0; +} + +static int skbprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + int prio; + + /* Initialise all queues, one for each possible priority. */ + for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) + __skb_queue_head_init(&q->qdiscs[prio]); + + memset(&q->qstats, 0, sizeof(q->qstats)); + q->highest_prio = 0; + q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; + sch->limit = 64; + if (!opt) + return 0; + + return skbprio_change(sch, opt, extack); +} + +static int skbprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct tc_skbprio_qopt opt; + + opt.limit = READ_ONCE(sch->limit); + + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + return -1; + + return skb->len; +} + +static void skbprio_reset(struct Qdisc *sch) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + int prio; + + for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) + __skb_queue_purge(&q->qdiscs[prio]); + + memset(&q->qstats, 0, sizeof(q->qstats)); + q->highest_prio = 0; + q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; +} + +static void skbprio_destroy(struct Qdisc *sch) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + int prio; + + for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) + __skb_queue_purge(&q->qdiscs[prio]); +} + +static struct Qdisc *skbprio_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long skbprio_find(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static int skbprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int skbprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + if (gnet_stats_copy_queue(d, NULL, &q->qstats[cl - 1], + q->qstats[cl - 1].qlen) < 0) + return -1; + return 0; +} + +static void skbprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + unsigned int i; + + if (arg->stop) + return; + + for (i = 0; i < SKBPRIO_MAX_PRIORITY; i++) { + if (!tc_qdisc_stats_dump(sch, i + 1, arg)) + break; + } +} + +static const struct Qdisc_class_ops skbprio_class_ops = { + .leaf = skbprio_leaf, + .find = skbprio_find, + .dump = skbprio_dump_class, + .dump_stats = skbprio_dump_class_stats, + .walk = skbprio_walk, +}; + +static struct Qdisc_ops skbprio_qdisc_ops __read_mostly = { + .cl_ops = &skbprio_class_ops, + .id = "skbprio", + .priv_size = sizeof(struct skbprio_sched_data), + .enqueue = skbprio_enqueue, + .dequeue = skbprio_dequeue, + .peek = qdisc_peek_dequeued, + .init = skbprio_init, + .reset = skbprio_reset, + .change = skbprio_change, + .dump = skbprio_dump, + .destroy = skbprio_destroy, + .owner = THIS_MODULE, +}; +MODULE_ALIAS_NET_SCH("skbprio"); + +static int __init skbprio_module_init(void) +{ + return register_qdisc(&skbprio_qdisc_ops); +} + +static void __exit skbprio_module_exit(void) +{ + unregister_qdisc(&skbprio_qdisc_ops); +} + +module_init(skbprio_module_init) +module_exit(skbprio_module_exit) + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SKB priority based scheduling qdisc"); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c new file mode 100644 index 000000000000..300d577b3286 --- /dev/null +++ b/net/sched/sch_taprio.c @@ -0,0 +1,2574 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* net/sched/sch_taprio.c Time Aware Priority Scheduler + * + * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> + * + */ + +#include <linux/ethtool.h> +#include <linux/ethtool_netlink.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/list.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/math64.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/rcupdate.h> +#include <linux/time.h> +#include <net/gso.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/sch_generic.h> +#include <net/sock.h> +#include <net/tcp.h> + +#define TAPRIO_STAT_NOT_SET (~0ULL) + +#include "sch_mqprio_lib.h" + +static LIST_HEAD(taprio_list); +static struct static_key_false taprio_have_broken_mqprio; +static struct static_key_false taprio_have_working_mqprio; + +#define TAPRIO_ALL_GATES_OPEN -1 + +#define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) +#define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) +#define TAPRIO_SUPPORTED_FLAGS \ + (TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) +#define TAPRIO_FLAGS_INVALID U32_MAX +/* Minimum value for picos_per_byte to ensure non-zero duration + * for minimum-sized Ethernet frames (ETH_ZLEN = 60). + * 60 * 17 > PSEC_PER_NSEC (1000) + */ +#define TAPRIO_PICOS_PER_BYTE_MIN 17 + +struct sched_entry { + /* Durations between this GCL entry and the GCL entry where the + * respective traffic class gate closes + */ + u64 gate_duration[TC_MAX_QUEUE]; + atomic_t budget[TC_MAX_QUEUE]; + /* The qdisc makes some effort so that no packet leaves + * after this time + */ + ktime_t gate_close_time[TC_MAX_QUEUE]; + struct list_head list; + /* Used to calculate when to advance the schedule */ + ktime_t end_time; + ktime_t next_txtime; + int index; + u32 gate_mask; + u32 interval; + u8 command; +}; + +struct sched_gate_list { + /* Longest non-zero contiguous gate durations per traffic class, + * or 0 if a traffic class gate never opens during the schedule. + */ + u64 max_open_gate_duration[TC_MAX_QUEUE]; + u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ + u32 max_sdu[TC_MAX_QUEUE]; /* for dump */ + struct rcu_head rcu; + struct list_head entries; + size_t num_entries; + ktime_t cycle_end_time; + s64 cycle_time; + s64 cycle_time_extension; + s64 base_time; +}; + +struct taprio_sched { + struct Qdisc **qdiscs; + struct Qdisc *root; + u32 flags; + enum tk_offsets tk_offset; + int clockid; + bool offloaded; + bool detected_mqprio; + bool broken_mqprio; + atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ + * speeds it's sub-nanoseconds per byte + */ + + /* Protects the update side of the RCU protected current_entry */ + spinlock_t current_entry_lock; + struct sched_entry __rcu *current_entry; + struct sched_gate_list __rcu *oper_sched; + struct sched_gate_list __rcu *admin_sched; + struct hrtimer advance_timer; + struct list_head taprio_list; + int cur_txq[TC_MAX_QUEUE]; + u32 max_sdu[TC_MAX_QUEUE]; /* save info from the user */ + u32 fp[TC_QOPT_MAX_QUEUE]; /* only for dump and offloading */ + u32 txtime_delay; +}; + +struct __tc_taprio_qopt_offload { + refcount_t users; + struct tc_taprio_qopt_offload offload; +}; + +static void taprio_calculate_gate_durations(struct taprio_sched *q, + struct sched_gate_list *sched) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + struct sched_entry *entry, *cur; + int tc; + + list_for_each_entry(entry, &sched->entries, list) { + u32 gates_still_open = entry->gate_mask; + + /* For each traffic class, calculate each open gate duration, + * starting at this schedule entry and ending at the schedule + * entry containing a gate close event for that TC. + */ + cur = entry; + + do { + if (!gates_still_open) + break; + + for (tc = 0; tc < num_tc; tc++) { + if (!(gates_still_open & BIT(tc))) + continue; + + if (cur->gate_mask & BIT(tc)) + entry->gate_duration[tc] += cur->interval; + else + gates_still_open &= ~BIT(tc); + } + + cur = list_next_entry_circular(cur, &sched->entries, list); + } while (cur != entry); + + /* Keep track of the maximum gate duration for each traffic + * class, taking care to not confuse a traffic class which is + * temporarily closed with one that is always closed. + */ + for (tc = 0; tc < num_tc; tc++) + if (entry->gate_duration[tc] && + sched->max_open_gate_duration[tc] < entry->gate_duration[tc]) + sched->max_open_gate_duration[tc] = entry->gate_duration[tc]; + } +} + +static bool taprio_entry_allows_tx(ktime_t skb_end_time, + struct sched_entry *entry, int tc) +{ + return ktime_before(skb_end_time, entry->gate_close_time[tc]); +} + +static ktime_t sched_base_time(const struct sched_gate_list *sched) +{ + if (!sched) + return KTIME_MAX; + + return ns_to_ktime(sched->base_time); +} + +static ktime_t taprio_mono_to_any(const struct taprio_sched *q, ktime_t mono) +{ + /* This pairs with WRITE_ONCE() in taprio_parse_clockid() */ + enum tk_offsets tk_offset = READ_ONCE(q->tk_offset); + + switch (tk_offset) { + case TK_OFFS_MAX: + return mono; + default: + return ktime_mono_to_any(mono, tk_offset); + } +} + +static ktime_t taprio_get_time(const struct taprio_sched *q) +{ + return taprio_mono_to_any(q, ktime_get()); +} + +static void taprio_free_sched_cb(struct rcu_head *head) +{ + struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu); + struct sched_entry *entry, *n; + + list_for_each_entry_safe(entry, n, &sched->entries, list) { + list_del(&entry->list); + kfree(entry); + } + + kfree(sched); +} + +static void switch_schedules(struct taprio_sched *q, + struct sched_gate_list **admin, + struct sched_gate_list **oper) +{ + rcu_assign_pointer(q->oper_sched, *admin); + rcu_assign_pointer(q->admin_sched, NULL); + + if (*oper) + call_rcu(&(*oper)->rcu, taprio_free_sched_cb); + + *oper = *admin; + *admin = NULL; +} + +/* Get how much time has been already elapsed in the current cycle. */ +static s32 get_cycle_time_elapsed(struct sched_gate_list *sched, ktime_t time) +{ + ktime_t time_since_sched_start; + s32 time_elapsed; + + time_since_sched_start = ktime_sub(time, sched->base_time); + div_s64_rem(time_since_sched_start, sched->cycle_time, &time_elapsed); + + return time_elapsed; +} + +static ktime_t get_interval_end_time(struct sched_gate_list *sched, + struct sched_gate_list *admin, + struct sched_entry *entry, + ktime_t intv_start) +{ + s32 cycle_elapsed = get_cycle_time_elapsed(sched, intv_start); + ktime_t intv_end, cycle_ext_end, cycle_end; + + cycle_end = ktime_add_ns(intv_start, sched->cycle_time - cycle_elapsed); + intv_end = ktime_add_ns(intv_start, entry->interval); + cycle_ext_end = ktime_add(cycle_end, sched->cycle_time_extension); + + if (ktime_before(intv_end, cycle_end)) + return intv_end; + else if (admin && admin != sched && + ktime_after(admin->base_time, cycle_end) && + ktime_before(admin->base_time, cycle_ext_end)) + return admin->base_time; + else + return cycle_end; +} + +static int length_to_duration(struct taprio_sched *q, int len) +{ + return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC); +} + +static int duration_to_length(struct taprio_sched *q, u64 duration) +{ + return div_u64(duration * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); +} + +/* Sets sched->max_sdu[] and sched->max_frm_len[] to the minimum between the + * q->max_sdu[] requested by the user and the max_sdu dynamically determined by + * the maximum open gate durations at the given link speed. + */ +static void taprio_update_queue_max_sdu(struct taprio_sched *q, + struct sched_gate_list *sched, + struct qdisc_size_table *stab) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + u32 max_sdu_from_user; + u32 max_sdu_dynamic; + u32 max_sdu; + int tc; + + for (tc = 0; tc < num_tc; tc++) { + max_sdu_from_user = q->max_sdu[tc] ?: U32_MAX; + + /* TC gate never closes => keep the queueMaxSDU + * selected by the user + */ + if (sched->max_open_gate_duration[tc] == sched->cycle_time) { + max_sdu_dynamic = U32_MAX; + } else { + u32 max_frm_len; + + max_frm_len = duration_to_length(q, sched->max_open_gate_duration[tc]); + /* Compensate for L1 overhead from size table, + * but don't let the frame size go negative + */ + if (stab) { + max_frm_len -= stab->szopts.overhead; + max_frm_len = max_t(int, max_frm_len, + dev->hard_header_len + 1); + } + max_sdu_dynamic = max_frm_len - dev->hard_header_len; + if (max_sdu_dynamic > dev->max_mtu) + max_sdu_dynamic = U32_MAX; + } + + max_sdu = min(max_sdu_dynamic, max_sdu_from_user); + + if (max_sdu != U32_MAX) { + sched->max_frm_len[tc] = max_sdu + dev->hard_header_len; + sched->max_sdu[tc] = max_sdu; + } else { + sched->max_frm_len[tc] = U32_MAX; /* never oversized */ + sched->max_sdu[tc] = 0; + } + } +} + +/* Returns the entry corresponding to next available interval. If + * validate_interval is set, it only validates whether the timestamp occurs + * when the gate corresponding to the skb's traffic class is open. + */ +static struct sched_entry *find_entry_to_transmit(struct sk_buff *skb, + struct Qdisc *sch, + struct sched_gate_list *sched, + struct sched_gate_list *admin, + ktime_t time, + ktime_t *interval_start, + ktime_t *interval_end, + bool validate_interval) +{ + ktime_t curr_intv_start, curr_intv_end, cycle_end, packet_transmit_time; + ktime_t earliest_txtime = KTIME_MAX, txtime, cycle, transmit_end_time; + struct sched_entry *entry = NULL, *entry_found = NULL; + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + bool entry_available = false; + s32 cycle_elapsed; + int tc, n; + + tc = netdev_get_prio_tc_map(dev, skb->priority); + packet_transmit_time = length_to_duration(q, qdisc_pkt_len(skb)); + + *interval_start = 0; + *interval_end = 0; + + if (!sched) + return NULL; + + cycle = sched->cycle_time; + cycle_elapsed = get_cycle_time_elapsed(sched, time); + curr_intv_end = ktime_sub_ns(time, cycle_elapsed); + cycle_end = ktime_add_ns(curr_intv_end, cycle); + + list_for_each_entry(entry, &sched->entries, list) { + curr_intv_start = curr_intv_end; + curr_intv_end = get_interval_end_time(sched, admin, entry, + curr_intv_start); + + if (ktime_after(curr_intv_start, cycle_end)) + break; + + if (!(entry->gate_mask & BIT(tc)) || + packet_transmit_time > entry->interval) + continue; + + txtime = entry->next_txtime; + + if (ktime_before(txtime, time) || validate_interval) { + transmit_end_time = ktime_add_ns(time, packet_transmit_time); + if ((ktime_before(curr_intv_start, time) && + ktime_before(transmit_end_time, curr_intv_end)) || + (ktime_after(curr_intv_start, time) && !validate_interval)) { + entry_found = entry; + *interval_start = curr_intv_start; + *interval_end = curr_intv_end; + break; + } else if (!entry_available && !validate_interval) { + /* Here, we are just trying to find out the + * first available interval in the next cycle. + */ + entry_available = true; + entry_found = entry; + *interval_start = ktime_add_ns(curr_intv_start, cycle); + *interval_end = ktime_add_ns(curr_intv_end, cycle); + } + } else if (ktime_before(txtime, earliest_txtime) && + !entry_available) { + earliest_txtime = txtime; + entry_found = entry; + n = div_s64(ktime_sub(txtime, curr_intv_start), cycle); + *interval_start = ktime_add(curr_intv_start, n * cycle); + *interval_end = ktime_add(curr_intv_end, n * cycle); + } + } + + return entry_found; +} + +static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sched_gate_list *sched, *admin; + ktime_t interval_start, interval_end; + struct sched_entry *entry; + + rcu_read_lock(); + sched = rcu_dereference(q->oper_sched); + admin = rcu_dereference(q->admin_sched); + + entry = find_entry_to_transmit(skb, sch, sched, admin, skb->tstamp, + &interval_start, &interval_end, true); + rcu_read_unlock(); + + return entry; +} + +/* This returns the tstamp value set by TCP in terms of the set clock. */ +static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb) +{ + unsigned int offset = skb_network_offset(skb); + const struct ipv6hdr *ipv6h; + const struct iphdr *iph; + struct ipv6hdr _ipv6h; + + ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); + if (!ipv6h) + return 0; + + if (ipv6h->version == 4) { + iph = (struct iphdr *)ipv6h; + offset += iph->ihl * 4; + + /* special-case 6in4 tunnelling, as that is a common way to get + * v6 connectivity in the home + */ + if (iph->protocol == IPPROTO_IPV6) { + ipv6h = skb_header_pointer(skb, offset, + sizeof(_ipv6h), &_ipv6h); + + if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP) + return 0; + } else if (iph->protocol != IPPROTO_TCP) { + return 0; + } + } else if (ipv6h->version == 6 && ipv6h->nexthdr != IPPROTO_TCP) { + return 0; + } + + return taprio_mono_to_any(q, skb->skb_mstamp_ns); +} + +/* There are a few scenarios where we will have to modify the txtime from + * what is read from next_txtime in sched_entry. They are: + * 1. If txtime is in the past, + * a. The gate for the traffic class is currently open and packet can be + * transmitted before it closes, schedule the packet right away. + * b. If the gate corresponding to the traffic class is going to open later + * in the cycle, set the txtime of packet to the interval start. + * 2. If txtime is in the future, there are packets corresponding to the + * current traffic class waiting to be transmitted. So, the following + * possibilities exist: + * a. We can transmit the packet before the window containing the txtime + * closes. + * b. The window might close before the transmission can be completed + * successfully. So, schedule the packet in the next open window. + */ +static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch) +{ + ktime_t transmit_end_time, interval_end, interval_start, tcp_tstamp; + struct taprio_sched *q = qdisc_priv(sch); + struct sched_gate_list *sched, *admin; + ktime_t minimum_time, now, txtime; + int len, packet_transmit_time; + struct sched_entry *entry; + bool sched_changed; + + now = taprio_get_time(q); + minimum_time = ktime_add_ns(now, q->txtime_delay); + + tcp_tstamp = get_tcp_tstamp(q, skb); + minimum_time = max_t(ktime_t, minimum_time, tcp_tstamp); + + rcu_read_lock(); + admin = rcu_dereference(q->admin_sched); + sched = rcu_dereference(q->oper_sched); + if (admin && ktime_after(minimum_time, admin->base_time)) + switch_schedules(q, &admin, &sched); + + /* Until the schedule starts, all the queues are open */ + if (!sched || ktime_before(minimum_time, sched->base_time)) { + txtime = minimum_time; + goto done; + } + + len = qdisc_pkt_len(skb); + packet_transmit_time = length_to_duration(q, len); + + do { + sched_changed = false; + + entry = find_entry_to_transmit(skb, sch, sched, admin, + minimum_time, + &interval_start, &interval_end, + false); + if (!entry) { + txtime = 0; + goto done; + } + + txtime = entry->next_txtime; + txtime = max_t(ktime_t, txtime, minimum_time); + txtime = max_t(ktime_t, txtime, interval_start); + + if (admin && admin != sched && + ktime_after(txtime, admin->base_time)) { + sched = admin; + sched_changed = true; + continue; + } + + transmit_end_time = ktime_add(txtime, packet_transmit_time); + minimum_time = transmit_end_time; + + /* Update the txtime of current entry to the next time it's + * interval starts. + */ + if (ktime_after(transmit_end_time, interval_end)) + entry->next_txtime = ktime_add(interval_start, sched->cycle_time); + } while (sched_changed || ktime_after(transmit_end_time, interval_end)); + + entry->next_txtime = transmit_end_time; + +done: + rcu_read_unlock(); + return txtime; +} + +/* Devices with full offload are expected to honor this in hardware */ +static bool taprio_skb_exceeds_queue_max_sdu(struct Qdisc *sch, + struct sk_buff *skb) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_gate_list *sched; + int prio = skb->priority; + bool exceeds = false; + u8 tc; + + tc = netdev_get_prio_tc_map(dev, prio); + + rcu_read_lock(); + sched = rcu_dereference(q->oper_sched); + if (sched && skb->len > sched->max_frm_len[tc]) + exceeds = true; + rcu_read_unlock(); + + return exceeds; +} + +static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + + /* sk_flags are only safe to use on full sockets. */ + if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { + if (!is_valid_interval(skb, sch)) + return qdisc_drop(skb, sch, to_free); + } else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { + skb->tstamp = get_packet_txtime(skb, sch); + if (!skb->tstamp) + return qdisc_drop(skb, sch, to_free); + } + + qdisc_qstats_backlog_inc(sch, skb); + sch->q.qlen++; + + return qdisc_enqueue(skb, child, to_free); +} + +static int taprio_enqueue_segmented(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, + struct sk_buff **to_free) +{ + unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); + netdev_features_t features = netif_skb_features(skb); + struct sk_buff *segs, *nskb; + int ret; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) + return qdisc_drop(skb, sch, to_free); + + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + qdisc_skb_cb(segs)->pkt_len = segs->len; + qdisc_skb_cb(segs)->pkt_segs = 1; + slen += segs->len; + + /* FIXME: we should be segmenting to a smaller size + * rather than dropping these + */ + if (taprio_skb_exceeds_queue_max_sdu(sch, segs)) + ret = qdisc_drop(segs, sch, to_free); + else + ret = taprio_enqueue_one(segs, sch, child, to_free); + + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) + qdisc_qstats_drop(sch); + } else { + numsegs++; + } + } + + if (numsegs > 1) + qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); + consume_skb(skb); + + return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; +} + +/* Will not be called in the full offload case, since the TX queues are + * attached to the Qdisc created using qdisc_create_dflt() + */ +static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct Qdisc *child; + int queue; + + queue = skb_get_queue_mapping(skb); + + child = q->qdiscs[queue]; + if (unlikely(!child)) + return qdisc_drop(skb, sch, to_free); + + if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { + /* Large packets might not be transmitted when the transmission + * duration exceeds any configured interval. Therefore, segment + * the skb into smaller chunks. Drivers with full offload are + * expected to handle this in hardware. + */ + if (skb_is_gso(skb)) + return taprio_enqueue_segmented(skb, sch, child, + to_free); + + return qdisc_drop(skb, sch, to_free); + } + + return taprio_enqueue_one(skb, sch, child, to_free); +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + WARN_ONCE(1, "taprio only supports operating as root qdisc, peek() not implemented"); + return NULL; +} + +static void taprio_set_budgets(struct taprio_sched *q, + struct sched_gate_list *sched, + struct sched_entry *entry) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + int tc, budget; + + for (tc = 0; tc < num_tc; tc++) { + /* Traffic classes which never close have infinite budget */ + if (entry->gate_duration[tc] == sched->cycle_time) + budget = INT_MAX; + else + budget = div64_u64((u64)entry->gate_duration[tc] * PSEC_PER_NSEC, + atomic64_read(&q->picos_per_byte)); + + atomic_set(&entry->budget[tc], budget); + } +} + +/* When an skb is sent, it consumes from the budget of all traffic classes */ +static int taprio_update_budgets(struct sched_entry *entry, size_t len, + int tc_consumed, int num_tc) +{ + int tc, budget, new_budget = 0; + + for (tc = 0; tc < num_tc; tc++) { + budget = atomic_read(&entry->budget[tc]); + /* Don't consume from infinite budget */ + if (budget == INT_MAX) { + if (tc == tc_consumed) + new_budget = budget; + continue; + } + + if (tc == tc_consumed) + new_budget = atomic_sub_return(len, &entry->budget[tc]); + else + atomic_sub(len, &entry->budget[tc]); + } + + return new_budget; +} + +static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, + struct sched_entry *entry, + u32 gate_mask) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *child = q->qdiscs[txq]; + int num_tc = netdev_get_num_tc(dev); + struct sk_buff *skb; + ktime_t guard; + int prio; + int len; + u8 tc; + + if (unlikely(!child)) + return NULL; + + if (TXTIME_ASSIST_IS_ENABLED(q->flags)) + goto skip_peek_checks; + + skb = child->ops->peek(child); + if (!skb) + return NULL; + + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); + + if (!(gate_mask & BIT(tc))) + return NULL; + + len = qdisc_pkt_len(skb); + guard = ktime_add_ns(taprio_get_time(q), length_to_duration(q, len)); + + /* In the case that there's no gate entry, there's no + * guard band ... + */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + !taprio_entry_allows_tx(guard, entry, tc)) + return NULL; + + /* ... and no budget. */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + taprio_update_budgets(entry, len, tc, num_tc) < 0) + return NULL; + +skip_peek_checks: + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + return NULL; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; +} + +static void taprio_next_tc_txq(struct net_device *dev, int tc, int *txq) +{ + int offset = dev->tc_to_txq[tc].offset; + int count = dev->tc_to_txq[tc].count; + + (*txq)++; + if (*txq == offset + count) + *txq = offset; +} + +/* Prioritize higher traffic classes, and select among TXQs belonging to the + * same TC using round robin + */ +static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int num_tc = netdev_get_num_tc(dev); + struct sk_buff *skb; + int tc; + + for (tc = num_tc - 1; tc >= 0; tc--) { + int first_txq = q->cur_txq[tc]; + + if (!(gate_mask & BIT(tc))) + continue; + + do { + skb = taprio_dequeue_from_txq(sch, q->cur_txq[tc], + entry, gate_mask); + + taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]); + + if (q->cur_txq[tc] >= dev->num_tx_queues) + q->cur_txq[tc] = first_txq; + + if (skb) + return skb; + } while (q->cur_txq[tc] != first_txq); + } + + return NULL; +} + +/* Broken way of prioritizing smaller TXQ indices and ignoring the traffic + * class other than to determine whether the gate is open or not + */ +static struct sk_buff *taprio_dequeue_txq_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) +{ + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + skb = taprio_dequeue_from_txq(sch, i, entry, gate_mask); + if (skb) + return skb; + } + + return NULL; +} + +/* Will not be called in the full offload case, since the TX queues are + * attached to the Qdisc created using qdisc_create_dflt() + */ +static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sk_buff *skb = NULL; + struct sched_entry *entry; + u32 gate_mask; + + rcu_read_lock(); + entry = rcu_dereference(q->current_entry); + /* if there's no entry, it means that the schedule didn't + * start yet, so force all gates to be open, this is in + * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 + * "AdminGateStates" + */ + gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; + if (!gate_mask) + goto done; + + if (static_branch_unlikely(&taprio_have_broken_mqprio) && + !static_branch_likely(&taprio_have_working_mqprio)) { + /* Single NIC kind which is broken */ + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + } else if (static_branch_likely(&taprio_have_working_mqprio) && + !static_branch_unlikely(&taprio_have_broken_mqprio)) { + /* Single NIC kind which prioritizes properly */ + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); + } else { + /* Mixed NIC kinds present in system, need dynamic testing */ + if (q->broken_mqprio) + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + else + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); + } + +done: + rcu_read_unlock(); + + return skb; +} + +static bool should_restart_cycle(const struct sched_gate_list *oper, + const struct sched_entry *entry) +{ + if (list_is_last(&entry->list, &oper->entries)) + return true; + + if (ktime_compare(entry->end_time, oper->cycle_end_time) == 0) + return true; + + return false; +} + +static bool should_change_schedules(const struct sched_gate_list *admin, + const struct sched_gate_list *oper, + ktime_t end_time) +{ + ktime_t next_base_time, extension_time; + + if (!admin) + return false; + + next_base_time = sched_base_time(admin); + + /* This is the simple case, the end_time would fall after + * the next schedule base_time. + */ + if (ktime_compare(next_base_time, end_time) <= 0) + return true; + + /* This is the cycle_time_extension case, if the end_time + * plus the amount that can be extended would fall after the + * next schedule base_time, we can extend the current schedule + * for that amount. + */ + extension_time = ktime_add_ns(end_time, oper->cycle_time_extension); + + /* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about + * how precisely the extension should be made. So after + * conformance testing, this logic may change. + */ + if (ktime_compare(next_base_time, extension_time) <= 0) + return true; + + return false; +} + +static enum hrtimer_restart advance_sched(struct hrtimer *timer) +{ + struct taprio_sched *q = container_of(timer, struct taprio_sched, + advance_timer); + struct net_device *dev = qdisc_dev(q->root); + struct sched_gate_list *oper, *admin; + int num_tc = netdev_get_num_tc(dev); + struct sched_entry *entry, *next; + struct Qdisc *sch = q->root; + ktime_t end_time; + int tc; + + spin_lock(&q->current_entry_lock); + entry = rcu_dereference_protected(q->current_entry, + lockdep_is_held(&q->current_entry_lock)); + oper = rcu_dereference_protected(q->oper_sched, + lockdep_is_held(&q->current_entry_lock)); + admin = rcu_dereference_protected(q->admin_sched, + lockdep_is_held(&q->current_entry_lock)); + + if (!oper) + switch_schedules(q, &admin, &oper); + + /* This can happen in two cases: 1. this is the very first run + * of this function (i.e. we weren't running any schedule + * previously); 2. The previous schedule just ended. The first + * entry of all schedules are pre-calculated during the + * schedule initialization. + */ + if (unlikely(!entry || entry->end_time == oper->base_time)) { + next = list_first_entry(&oper->entries, struct sched_entry, + list); + end_time = next->end_time; + goto first_run; + } + + if (should_restart_cycle(oper, entry)) { + next = list_first_entry(&oper->entries, struct sched_entry, + list); + oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time, + oper->cycle_time); + } else { + next = list_next_entry(entry, list); + } + + end_time = ktime_add_ns(entry->end_time, next->interval); + end_time = min_t(ktime_t, end_time, oper->cycle_end_time); + + for (tc = 0; tc < num_tc; tc++) { + if (next->gate_duration[tc] == oper->cycle_time) + next->gate_close_time[tc] = KTIME_MAX; + else + next->gate_close_time[tc] = ktime_add_ns(entry->end_time, + next->gate_duration[tc]); + } + + if (should_change_schedules(admin, oper, end_time)) { + /* Set things so the next time this runs, the new + * schedule runs. + */ + end_time = sched_base_time(admin); + switch_schedules(q, &admin, &oper); + } + + next->end_time = end_time; + taprio_set_budgets(q, oper, next); + +first_run: + rcu_assign_pointer(q->current_entry, next); + spin_unlock(&q->current_entry_lock); + + hrtimer_set_expires(&q->advance_timer, end_time); + + rcu_read_lock(); + __netif_schedule(sch); + rcu_read_unlock(); + + return HRTIMER_RESTART; +} + +static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { + [TCA_TAPRIO_SCHED_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_CMD] = { .type = NLA_U8 }, + [TCA_TAPRIO_SCHED_ENTRY_GATE_MASK] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, +}; + +static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { + [TCA_TAPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, + TC_QOPT_MAX_QUEUE - 1), + [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, + [TCA_TAPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32, + TC_FP_EXPRESS, + TC_FP_PREEMPTIBLE), +}; + +static const struct netlink_range_validation_signed taprio_cycle_time_range = { + .min = 0, + .max = INT_MAX, +}; + +static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { + [TCA_TAPRIO_ATTR_PRIOMAP] = { + .len = sizeof(struct tc_mqprio_qopt) + }, + [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, + [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = + NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), + [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_FLAGS] = + NLA_POLICY_MASK(NLA_U32, TAPRIO_SUPPORTED_FLAGS), + [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, + [TCA_TAPRIO_ATTR_TC_ENTRY] = { .type = NLA_NESTED }, +}; + +static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb, + struct sched_entry *entry, + struct netlink_ext_ack *extack) +{ + int min_duration = length_to_duration(q, ETH_ZLEN); + u32 interval = 0; + + if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) + entry->command = nla_get_u8( + tb[TCA_TAPRIO_SCHED_ENTRY_CMD]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]) + entry->gate_mask = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]) + interval = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); + + /* The interval should allow at least the minimum ethernet + * frame to go out. + */ + if (interval < min_duration) { + NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); + return -EINVAL; + } + + entry->interval = interval; + + return 0; +} + +static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n, + struct sched_entry *entry, int index, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; + int err; + + err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n, + entry_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + entry->index = index; + + return fill_sched_entry(q, tb, entry, extack); +} + +static int parse_sched_list(struct taprio_sched *q, struct nlattr *list, + struct sched_gate_list *sched, + struct netlink_ext_ack *extack) +{ + struct nlattr *n; + int err, rem; + int i = 0; + + if (!list) + return -EINVAL; + + nla_for_each_nested(n, list, rem) { + struct sched_entry *entry; + + if (nla_type(n) != TCA_TAPRIO_SCHED_ENTRY) { + NL_SET_ERR_MSG(extack, "Attribute is not of type 'entry'"); + continue; + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + err = parse_sched_entry(q, n, entry, i, extack); + if (err < 0) { + kfree(entry); + return err; + } + + list_add_tail(&entry->list, &sched->entries); + i++; + } + + sched->num_entries = i; + + return i; +} + +static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, + struct sched_gate_list *new, + struct netlink_ext_ack *extack) +{ + int err = 0; + + if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) { + NL_SET_ERR_MSG(extack, "Adding a single entry is not supported"); + return -ENOTSUPP; + } + + if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]) + new->base_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]); + + if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION]) + new->cycle_time_extension = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION]); + + if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]) + new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]); + + if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) + err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], + new, extack); + if (err < 0) + return err; + + if (!new->cycle_time) { + struct sched_entry *entry; + ktime_t cycle = 0; + + list_for_each_entry(entry, &new->entries, list) + cycle = ktime_add_ns(cycle, entry->interval); + + if (cycle < 0 || cycle > INT_MAX) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); + return -EINVAL; + } + + new->cycle_time = cycle; + } + + if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too small"); + return -EINVAL; + } + + taprio_calculate_gate_durations(q, new); + + return 0; +} + +static int taprio_parse_mqprio_opt(struct net_device *dev, + struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack, + u32 taprio_flags) +{ + bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); + + if (!qopt) { + if (!dev->num_tc) { + NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); + return -EINVAL; + } + return 0; + } + + /* taprio imposes that traffic classes map 1:n to tx queues */ + if (qopt->num_tc > dev->num_tx_queues) { + NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); + return -EINVAL; + } + + /* For some reason, in txtime-assist mode, we allow TXQ ranges for + * different TCs to overlap, and just validate the TXQ ranges. + */ + return mqprio_validate_qopt(dev, qopt, true, allow_overlapping_txqs, + extack); +} + +static int taprio_get_start_time(struct Qdisc *sch, + struct sched_gate_list *sched, + ktime_t *start) +{ + struct taprio_sched *q = qdisc_priv(sch); + ktime_t now, base, cycle; + s64 n; + + base = sched_base_time(sched); + now = taprio_get_time(q); + + if (ktime_after(base, now)) { + *start = base; + return 0; + } + + cycle = sched->cycle_time; + + /* The qdisc is expected to have at least one sched_entry. Moreover, + * any entry must have 'interval' > 0. Thus if the cycle time is zero, + * something went really wrong. In that case, we should warn about this + * inconsistent state and return error. + */ + if (WARN_ON(!cycle)) + return -EFAULT; + + /* Schedule the start time for the beginning of the next + * cycle. + */ + n = div64_s64(ktime_sub_ns(now, base), cycle); + *start = ktime_add_ns(base, (n + 1) * cycle); + return 0; +} + +static void setup_first_end_time(struct taprio_sched *q, + struct sched_gate_list *sched, ktime_t base) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + struct sched_entry *first; + ktime_t cycle; + int tc; + + first = list_first_entry(&sched->entries, + struct sched_entry, list); + + cycle = sched->cycle_time; + + /* FIXME: find a better place to do this */ + sched->cycle_end_time = ktime_add_ns(base, cycle); + + first->end_time = ktime_add_ns(base, first->interval); + taprio_set_budgets(q, sched, first); + + for (tc = 0; tc < num_tc; tc++) { + if (first->gate_duration[tc] == sched->cycle_time) + first->gate_close_time[tc] = KTIME_MAX; + else + first->gate_close_time[tc] = ktime_add_ns(base, first->gate_duration[tc]); + } + + rcu_assign_pointer(q->current_entry, NULL); +} + +static void taprio_start_sched(struct Qdisc *sch, + ktime_t start, struct sched_gate_list *new) +{ + struct taprio_sched *q = qdisc_priv(sch); + ktime_t expires; + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) + return; + + expires = hrtimer_get_expires(&q->advance_timer); + if (expires == 0) + expires = KTIME_MAX; + + /* If the new schedule starts before the next expiration, we + * reprogram it to the earliest one, so we change the admin + * schedule to the operational one at the right time. + */ + start = min_t(ktime_t, start, expires); + + hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS); +} + +static void taprio_set_picos_per_byte(struct net_device *dev, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + struct ethtool_link_ksettings ecmd; + int speed = SPEED_10; + int picos_per_byte; + int err; + + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; + +skip: + picos_per_byte = (USEC_PER_SEC * 8) / speed; + if (picos_per_byte < TAPRIO_PICOS_PER_BYTE_MIN) { + if (!extack) + pr_warn("Link speed %d is too high. Schedule may be inaccurate.\n", + speed); + NL_SET_ERR_MSG_FMT_MOD(extack, + "Link speed %d is too high. Schedule may be inaccurate.", + speed); + picos_per_byte = TAPRIO_PICOS_PER_BYTE_MIN; + } + + atomic64_set(&q->picos_per_byte, picos_per_byte); + netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", + dev->name, (long long)atomic64_read(&q->picos_per_byte), + ecmd.base.speed); +} + +static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct sched_gate_list *oper, *admin; + struct qdisc_size_table *stab; + struct taprio_sched *q; + + ASSERT_RTNL(); + + if (event != NETDEV_UP && event != NETDEV_CHANGE) + return NOTIFY_DONE; + + list_for_each_entry(q, &taprio_list, taprio_list) { + if (dev != qdisc_dev(q->root)) + continue; + + taprio_set_picos_per_byte(dev, q, NULL); + + stab = rtnl_dereference(q->root->stab); + + rcu_read_lock(); + oper = rcu_dereference(q->oper_sched); + if (oper) + taprio_update_queue_max_sdu(q, oper, stab); + + admin = rcu_dereference(q->admin_sched); + if (admin) + taprio_update_queue_max_sdu(q, admin, stab); + rcu_read_unlock(); + + break; + } + + return NOTIFY_DONE; +} + +static void setup_txtime(struct taprio_sched *q, + struct sched_gate_list *sched, ktime_t base) +{ + struct sched_entry *entry; + u64 interval = 0; + + list_for_each_entry(entry, &sched->entries, list) { + entry->next_txtime = ktime_add_ns(base, interval); + interval += entry->interval; + } +} + +static struct tc_taprio_qopt_offload *taprio_offload_alloc(int num_entries) +{ + struct __tc_taprio_qopt_offload *__offload; + + __offload = kzalloc(struct_size(__offload, offload.entries, num_entries), + GFP_KERNEL); + if (!__offload) + return NULL; + + refcount_set(&__offload->users, 1); + + return &__offload->offload; +} + +struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload + *offload) +{ + struct __tc_taprio_qopt_offload *__offload; + + __offload = container_of(offload, struct __tc_taprio_qopt_offload, + offload); + + refcount_inc(&__offload->users); + + return offload; +} +EXPORT_SYMBOL_GPL(taprio_offload_get); + +void taprio_offload_free(struct tc_taprio_qopt_offload *offload) +{ + struct __tc_taprio_qopt_offload *__offload; + + __offload = container_of(offload, struct __tc_taprio_qopt_offload, + offload); + + if (!refcount_dec_and_test(&__offload->users)) + return; + + kfree(__offload); +} +EXPORT_SYMBOL_GPL(taprio_offload_free); + +/* The function will only serve to keep the pointers to the "oper" and "admin" + * schedules valid in relation to their base times, so when calling dump() the + * users looks at the right schedules. + * When using full offload, the admin configuration is promoted to oper at the + * base_time in the PHC time domain. But because the system time is not + * necessarily in sync with that, we can't just trigger a hrtimer to call + * switch_schedules at the right hardware time. + * At the moment we call this by hand right away from taprio, but in the future + * it will be useful to create a mechanism for drivers to notify taprio of the + * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). + * This is left as TODO. + */ +static void taprio_offload_config_changed(struct taprio_sched *q) +{ + struct sched_gate_list *oper, *admin; + + oper = rtnl_dereference(q->oper_sched); + admin = rtnl_dereference(q->admin_sched); + + switch_schedules(q, &admin, &oper); +} + +static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) +{ + u32 i, queue_mask = 0; + + for (i = 0; i < dev->num_tc; i++) { + u32 offset, count; + + if (!(tc_mask & BIT(i))) + continue; + + offset = dev->tc_to_txq[i].offset; + count = dev->tc_to_txq[i].count; + + queue_mask |= GENMASK(offset + count - 1, offset); + } + + return queue_mask; +} + +static void taprio_sched_to_offload(struct net_device *dev, + struct sched_gate_list *sched, + struct tc_taprio_qopt_offload *offload, + const struct tc_taprio_caps *caps) +{ + struct sched_entry *entry; + int i = 0; + + offload->base_time = sched->base_time; + offload->cycle_time = sched->cycle_time; + offload->cycle_time_extension = sched->cycle_time_extension; + + list_for_each_entry(entry, &sched->entries, list) { + struct tc_taprio_sched_entry *e = &offload->entries[i]; + + e->command = entry->command; + e->interval = entry->interval; + if (caps->gate_mask_per_txq) + e->gate_mask = tc_map_to_queue_mask(dev, + entry->gate_mask); + else + e->gate_mask = entry->gate_mask; + + i++; + } + + offload->num_entries = i; +} + +static void taprio_detect_broken_mqprio(struct taprio_sched *q) +{ + struct net_device *dev = qdisc_dev(q->root); + struct tc_taprio_caps caps; + + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, + &caps, sizeof(caps)); + + q->broken_mqprio = caps.broken_mqprio; + if (q->broken_mqprio) + static_branch_inc(&taprio_have_broken_mqprio); + else + static_branch_inc(&taprio_have_working_mqprio); + + q->detected_mqprio = true; +} + +static void taprio_cleanup_broken_mqprio(struct taprio_sched *q) +{ + if (!q->detected_mqprio) + return; + + if (q->broken_mqprio) + static_branch_dec(&taprio_have_broken_mqprio); + else + static_branch_dec(&taprio_have_working_mqprio); +} + +static int taprio_enable_offload(struct net_device *dev, + struct taprio_sched *q, + struct sched_gate_list *sched, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_taprio_qopt_offload *offload; + struct tc_taprio_caps caps; + int tc, err = 0; + + if (!ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, + "Device does not support taprio offload"); + return -EOPNOTSUPP; + } + + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, + &caps, sizeof(caps)); + + if (!caps.supports_queue_max_sdu) { + for (tc = 0; tc < TC_MAX_QUEUE; tc++) { + if (q->max_sdu[tc]) { + NL_SET_ERR_MSG_MOD(extack, + "Device does not handle queueMaxSDU"); + return -EOPNOTSUPP; + } + } + } + + offload = taprio_offload_alloc(sched->num_entries); + if (!offload) { + NL_SET_ERR_MSG(extack, + "Not enough memory for enabling offload mode"); + return -ENOMEM; + } + offload->cmd = TAPRIO_CMD_REPLACE; + offload->extack = extack; + mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt); + offload->mqprio.extack = extack; + taprio_sched_to_offload(dev, sched, offload, &caps); + mqprio_fp_to_offload(q->fp, &offload->mqprio); + + for (tc = 0; tc < TC_MAX_QUEUE; tc++) + offload->max_sdu[tc] = q->max_sdu[tc]; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err < 0) { + NL_SET_ERR_MSG_WEAK(extack, + "Device failed to setup taprio offload"); + goto done; + } + + q->offloaded = true; + +done: + /* The offload structure may linger around via a reference taken by the + * device driver, so clear up the netlink extack pointer so that the + * driver isn't tempted to dereference data which stopped being valid + */ + offload->extack = NULL; + offload->mqprio.extack = NULL; + taprio_offload_free(offload); + + return err; +} + +static int taprio_disable_offload(struct net_device *dev, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_taprio_qopt_offload *offload; + int err; + + if (!q->offloaded) + return 0; + + offload = taprio_offload_alloc(0); + if (!offload) { + NL_SET_ERR_MSG(extack, + "Not enough memory to disable offload mode"); + return -ENOMEM; + } + offload->cmd = TAPRIO_CMD_DESTROY; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err < 0) { + NL_SET_ERR_MSG(extack, + "Device failed to disable offload"); + goto out; + } + + q->offloaded = false; + +out: + taprio_offload_free(offload); + + return err; +} + +/* If full offload is enabled, the only possible clockid is the net device's + * PHC. For that reason, specifying a clockid through netlink is incorrect. + * For txtime-assist, it is implicitly assumed that the device's PHC is kept + * in sync with the specified clockid via a user space daemon such as phc2sys. + * For both software taprio and txtime-assist, the clockid is used for the + * hrtimer that advances the schedule and hence mandatory. + */ +static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err = -EINVAL; + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + const struct ethtool_ops *ops = dev->ethtool_ops; + struct kernel_ethtool_ts_info info = { + .cmd = ETHTOOL_GET_TS_INFO, + .phc_index = -1, + }; + + if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + NL_SET_ERR_MSG(extack, + "The 'clockid' cannot be specified for full offload"); + goto out; + } + + if (ops && ops->get_ts_info) + err = ops->get_ts_info(dev, &info); + + if (err || info.phc_index < 0) { + NL_SET_ERR_MSG(extack, + "Device does not have a PTP clock"); + err = -ENOTSUPP; + goto out; + } + } else if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + int clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + enum tk_offsets tk_offset; + + /* We only support static clockids and we don't allow + * for it to be modified after the first init. + */ + if (clockid < 0 || + (q->clockid != -1 && q->clockid != clockid)) { + NL_SET_ERR_MSG(extack, + "Changing the 'clockid' of a running schedule is not supported"); + err = -ENOTSUPP; + goto out; + } + + switch (clockid) { + case CLOCK_REALTIME: + tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + err = -EINVAL; + goto out; + } + /* This pairs with READ_ONCE() in taprio_mono_to_any */ + WRITE_ONCE(q->tk_offset, tk_offset); + + q->clockid = clockid; + } else { + NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); + goto out; + } + + /* Everything went ok, return success. */ + err = 0; + +out: + return err; +} + +static int taprio_parse_tc_entry(struct Qdisc *sch, + struct nlattr *opt, + u32 max_sdu[TC_QOPT_MAX_QUEUE], + u32 fp[TC_QOPT_MAX_QUEUE], + unsigned long *seen_tcs, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { }; + struct net_device *dev = qdisc_dev(sch); + int err, tc; + u32 val; + + err = nla_parse_nested(tb, TCA_TAPRIO_TC_ENTRY_MAX, opt, + taprio_tc_policy, extack); + if (err < 0) + return err; + + if (NL_REQ_ATTR_CHECK(extack, opt, tb, TCA_TAPRIO_TC_ENTRY_INDEX)) { + NL_SET_ERR_MSG_MOD(extack, "TC entry index missing"); + return -EINVAL; + } + + tc = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_INDEX]); + if (*seen_tcs & BIT(tc)) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_TAPRIO_TC_ENTRY_INDEX], + "Duplicate tc entry"); + return -EINVAL; + } + + *seen_tcs |= BIT(tc); + + if (tb[TCA_TAPRIO_TC_ENTRY_MAX_SDU]) { + val = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_MAX_SDU]); + if (val > dev->max_mtu) { + NL_SET_ERR_MSG_MOD(extack, "TC max SDU exceeds device max MTU"); + return -ERANGE; + } + + max_sdu[tc] = val; + } + + if (tb[TCA_TAPRIO_TC_ENTRY_FP]) + fp[tc] = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_FP]); + + return 0; +} + +static int taprio_parse_tc_entries(struct Qdisc *sch, + struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + u32 max_sdu[TC_QOPT_MAX_QUEUE]; + bool have_preemption = false; + unsigned long seen_tcs = 0; + u32 fp[TC_QOPT_MAX_QUEUE]; + struct nlattr *n; + int tc, rem; + int err = 0; + + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { + max_sdu[tc] = q->max_sdu[tc]; + fp[tc] = q->fp[tc]; + } + + nla_for_each_nested_type(n, TCA_TAPRIO_ATTR_TC_ENTRY, opt, rem) { + err = taprio_parse_tc_entry(sch, n, max_sdu, fp, &seen_tcs, + extack); + if (err) + return err; + } + + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { + q->max_sdu[tc] = max_sdu[tc]; + q->fp[tc] = fp[tc]; + if (fp[tc] != TC_FP_EXPRESS) + have_preemption = true; + } + + if (have_preemption) { + if (!FULL_OFFLOAD_IS_ENABLED(q->flags)) { + NL_SET_ERR_MSG(extack, + "Preemption only supported with full offload"); + return -EOPNOTSUPP; + } + + if (!ethtool_dev_mm_supported(dev)) { + NL_SET_ERR_MSG(extack, + "Device does not support preemption"); + return -EOPNOTSUPP; + } + } + + return err; +} + +static int taprio_mqprio_cmp(const struct net_device *dev, + const struct tc_mqprio_qopt *mqprio) +{ + int i; + + if (!mqprio || mqprio->num_tc != dev->num_tc) + return -1; + + for (i = 0; i < mqprio->num_tc; i++) + if (dev->tc_to_txq[i].count != mqprio->count[i] || + dev->tc_to_txq[i].offset != mqprio->offset[i]) + return -1; + + for (i = 0; i <= TC_BITMASK; i++) + if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i]) + return -1; + + return 0; +} + +static int taprio_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct qdisc_size_table *stab = rtnl_dereference(sch->stab); + struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; + struct sched_gate_list *oper, *admin, *new_admin; + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt *mqprio = NULL; + unsigned long flags; + u32 taprio_flags; + ktime_t start; + int i, err; + + err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_ATTR_MAX, opt, + taprio_policy, extack); + if (err < 0) + return err; + + if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) + mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); + + /* The semantics of the 'flags' argument in relation to 'change()' + * requests, are interpreted following two rules (which are applied in + * this order): (1) an omitted 'flags' argument is interpreted as + * zero; (2) the 'flags' of a "running" taprio instance cannot be + * changed. + */ + taprio_flags = nla_get_u32_default(tb[TCA_TAPRIO_ATTR_FLAGS], 0); + + /* txtime-assist and full offload are mutually exclusive */ + if ((taprio_flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && + (taprio_flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_TAPRIO_ATTR_FLAGS], + "TXTIME_ASSIST and FULL_OFFLOAD are mutually exclusive"); + return -EINVAL; + } + + if (q->flags != TAPRIO_FLAGS_INVALID && q->flags != taprio_flags) { + NL_SET_ERR_MSG_MOD(extack, + "Changing 'flags' of a running schedule is not supported"); + return -EOPNOTSUPP; + } + q->flags = taprio_flags; + + /* Needed for length_to_duration() during netlink attribute parsing */ + taprio_set_picos_per_byte(dev, q, extack); + + err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); + if (err < 0) + return err; + + err = taprio_parse_tc_entries(sch, opt, extack); + if (err) + return err; + + new_admin = kzalloc(sizeof(*new_admin), GFP_KERNEL); + if (!new_admin) { + NL_SET_ERR_MSG(extack, "Not enough memory for a new schedule"); + return -ENOMEM; + } + INIT_LIST_HEAD(&new_admin->entries); + + oper = rtnl_dereference(q->oper_sched); + admin = rtnl_dereference(q->admin_sched); + + /* no changes - no new mqprio settings */ + if (!taprio_mqprio_cmp(dev, mqprio)) + mqprio = NULL; + + if (mqprio && (oper || admin)) { + NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported"); + err = -ENOTSUPP; + goto free_sched; + } + + if (mqprio) { + err = netdev_set_num_tc(dev, mqprio->num_tc); + if (err) + goto free_sched; + for (i = 0; i < mqprio->num_tc; i++) { + netdev_set_tc_queue(dev, i, + mqprio->count[i], + mqprio->offset[i]); + q->cur_txq[i] = mqprio->offset[i]; + } + + /* Always use supplied priority mappings */ + for (i = 0; i <= TC_BITMASK; i++) + netdev_set_prio_tc_map(dev, i, + mqprio->prio_tc_map[i]); + } + + err = parse_taprio_schedule(q, tb, new_admin, extack); + if (err < 0) + goto free_sched; + + if (new_admin->num_entries == 0) { + NL_SET_ERR_MSG(extack, "There should be at least one entry in the schedule"); + err = -EINVAL; + goto free_sched; + } + + err = taprio_parse_clockid(sch, tb, extack); + if (err < 0) + goto free_sched; + + taprio_update_queue_max_sdu(q, new_admin, stab); + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) + err = taprio_enable_offload(dev, q, new_admin, extack); + else + err = taprio_disable_offload(dev, q, extack); + if (err) + goto free_sched; + + /* Protects against enqueue()/dequeue() */ + spin_lock_bh(qdisc_lock(sch)); + + if (tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]) { + if (!TXTIME_ASSIST_IS_ENABLED(q->flags)) { + NL_SET_ERR_MSG_MOD(extack, "txtime-delay can only be set when txtime-assist mode is enabled"); + err = -EINVAL; + goto unlock; + } + + q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]); + } + + if (!TXTIME_ASSIST_IS_ENABLED(q->flags) && + !FULL_OFFLOAD_IS_ENABLED(q->flags) && + !hrtimer_active(&q->advance_timer)) { + hrtimer_setup(&q->advance_timer, advance_sched, q->clockid, HRTIMER_MODE_ABS); + } + + err = taprio_get_start_time(sch, new_admin, &start); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Internal error: failed get start time"); + goto unlock; + } + + setup_txtime(q, new_admin, start); + + if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { + if (!oper) { + rcu_assign_pointer(q->oper_sched, new_admin); + err = 0; + new_admin = NULL; + goto unlock; + } + + /* Not going to race against advance_sched(), but still */ + admin = rcu_replace_pointer(q->admin_sched, new_admin, + lockdep_rtnl_is_held()); + if (admin) + call_rcu(&admin->rcu, taprio_free_sched_cb); + } else { + setup_first_end_time(q, new_admin, start); + + /* Protects against advance_sched() */ + spin_lock_irqsave(&q->current_entry_lock, flags); + + taprio_start_sched(sch, start, new_admin); + + admin = rcu_replace_pointer(q->admin_sched, new_admin, + lockdep_rtnl_is_held()); + if (admin) + call_rcu(&admin->rcu, taprio_free_sched_cb); + + spin_unlock_irqrestore(&q->current_entry_lock, flags); + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) + taprio_offload_config_changed(q); + } + + new_admin = NULL; + err = 0; + + if (!stab) + NL_SET_ERR_MSG_MOD(extack, + "Size table not specified, frame length estimations may be inaccurate"); + +unlock: + spin_unlock_bh(qdisc_lock(sch)); + +free_sched: + if (new_admin) + call_rcu(&new_admin->rcu, taprio_free_sched_cb); + + return err; +} + +static void taprio_reset(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int i; + + hrtimer_cancel(&q->advance_timer); + + if (q->qdiscs) { + for (i = 0; i < dev->num_tx_queues; i++) + if (q->qdiscs[i]) + qdisc_reset(q->qdiscs[i]); + } +} + +static void taprio_destroy(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_gate_list *oper, *admin; + unsigned int i; + + list_del(&q->taprio_list); + + /* Note that taprio_reset() might not be called if an error + * happens in qdisc_create(), after taprio_init() has been called. + */ + hrtimer_cancel(&q->advance_timer); + qdisc_synchronize(sch); + + taprio_disable_offload(dev, q, NULL); + + if (q->qdiscs) { + for (i = 0; i < dev->num_tx_queues; i++) + qdisc_put(q->qdiscs[i]); + + kfree(q->qdiscs); + } + q->qdiscs = NULL; + + netdev_reset_tc(dev); + + oper = rtnl_dereference(q->oper_sched); + admin = rtnl_dereference(q->admin_sched); + + if (oper) + call_rcu(&oper->rcu, taprio_free_sched_cb); + + if (admin) + call_rcu(&admin->rcu, taprio_free_sched_cb); + + taprio_cleanup_broken_mqprio(q); +} + +static int taprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int i, tc; + + spin_lock_init(&q->current_entry_lock); + + hrtimer_setup(&q->advance_timer, advance_sched, CLOCK_TAI, HRTIMER_MODE_ABS); + + q->root = sch; + + /* We only support static clockids. Use an invalid value as default + * and get the valid one on taprio_change(). + */ + q->clockid = -1; + q->flags = TAPRIO_FLAGS_INVALID; + + list_add(&q->taprio_list, &taprio_list); + + if (sch->parent != TC_H_ROOT) { + NL_SET_ERR_MSG_MOD(extack, "Can only be attached as root qdisc"); + return -EOPNOTSUPP; + } + + if (!netif_is_multiqueue(dev)) { + NL_SET_ERR_MSG_MOD(extack, "Multi-queue device is required"); + return -EOPNOTSUPP; + } + + q->qdiscs = kcalloc(dev->num_tx_queues, sizeof(q->qdiscs[0]), + GFP_KERNEL); + if (!q->qdiscs) + return -ENOMEM; + + if (!opt) + return -EINVAL; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + + dev_queue = netdev_get_tx_queue(dev, i); + qdisc = qdisc_create_dflt(dev_queue, + &pfifo_qdisc_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1)), + extack); + if (!qdisc) + return -ENOMEM; + + if (i < dev->real_num_tx_queues) + qdisc_hash_add(qdisc, false); + + q->qdiscs[i] = qdisc; + } + + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) + q->fp[tc] = TC_FP_EXPRESS; + + taprio_detect_broken_mqprio(q); + + return taprio_change(sch, opt, extack); +} + +static void taprio_attach(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx; + + /* Attach underlying qdisc */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *old, *dev_queue_qdisc; + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + struct Qdisc *qdisc = q->qdiscs[ntx]; + + /* In offload mode, the root taprio qdisc is bypassed + * and the netdev TX queues see the children directly + */ + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + dev_queue_qdisc = qdisc; + } else { + /* In software mode, attach the root taprio qdisc + * to all netdev TX queues, so that dev_qdisc_enqueue() + * goes through taprio_enqueue(). + */ + dev_queue_qdisc = sch; + } + old = dev_graft_qdisc(dev_queue, dev_queue_qdisc); + /* The qdisc's refcount requires to be elevated once + * for each netdev TX queue it is grafted onto + */ + qdisc_refcount_inc(dev_queue_qdisc); + if (old) + qdisc_put(old); + } +} + +static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, + unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1; + + if (ntx >= dev->num_tx_queues) + return NULL; + + return netdev_get_tx_queue(dev, ntx); +} + +static int taprio_graft(struct Qdisc *sch, unsigned long cl, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + if (!dev_queue) + return -EINVAL; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + /* In offload mode, the child Qdisc is directly attached to the netdev + * TX queue, and thus, we need to keep its refcount elevated in order + * to counteract qdisc_graft()'s call to qdisc_put() once per TX queue. + * However, save the reference to the new qdisc in the private array in + * both software and offload cases, to have an up-to-date reference to + * our children. + */ + *old = q->qdiscs[cl - 1]; + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old); + if (new) + qdisc_refcount_inc(new); + if (*old) + qdisc_put(*old); + } + + q->qdiscs[cl - 1] = new; + if (new) + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + + if (dev->flags & IFF_UP) + dev_activate(dev); + + return 0; +} + +static int dump_entry(struct sk_buff *msg, + const struct sched_entry *entry) +{ + struct nlattr *item; + + item = nla_nest_start_noflag(msg, TCA_TAPRIO_SCHED_ENTRY); + if (!item) + return -ENOSPC; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INDEX, entry->index)) + goto nla_put_failure; + + if (nla_put_u8(msg, TCA_TAPRIO_SCHED_ENTRY_CMD, entry->command)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, + entry->gate_mask)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INTERVAL, + entry->interval)) + goto nla_put_failure; + + return nla_nest_end(msg, item); + +nla_put_failure: + nla_nest_cancel(msg, item); + return -1; +} + +static int dump_schedule(struct sk_buff *msg, + const struct sched_gate_list *root) +{ + struct nlattr *entry_list; + struct sched_entry *entry; + + if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_BASE_TIME, + root->base_time, TCA_TAPRIO_PAD)) + return -1; + + if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, + root->cycle_time, TCA_TAPRIO_PAD)) + return -1; + + if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, + root->cycle_time_extension, TCA_TAPRIO_PAD)) + return -1; + + entry_list = nla_nest_start_noflag(msg, + TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); + if (!entry_list) + goto error_nest; + + list_for_each_entry(entry, &root->entries, list) { + if (dump_entry(msg, entry) < 0) + goto error_nest; + } + + nla_nest_end(msg, entry_list); + return 0; + +error_nest: + nla_nest_cancel(msg, entry_list); + return -1; +} + +static int taprio_dump_tc_entries(struct sk_buff *skb, + struct taprio_sched *q, + struct sched_gate_list *sched) +{ + struct nlattr *n; + int tc; + + for (tc = 0; tc < TC_MAX_QUEUE; tc++) { + n = nla_nest_start(skb, TCA_TAPRIO_ATTR_TC_ENTRY); + if (!n) + return -EMSGSIZE; + + if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_INDEX, tc)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_MAX_SDU, + sched->max_sdu[tc])) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_FP, q->fp[tc])) + goto nla_put_failure; + + nla_nest_end(skb, n); + } + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, n); + return -EMSGSIZE; +} + +static int taprio_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) +{ + if (val == TAPRIO_STAT_NOT_SET) + return 0; + if (nla_put_u64_64bit(skb, attrtype, val, TCA_TAPRIO_OFFLOAD_STATS_PAD)) + return -EMSGSIZE; + return 0; +} + +static int taprio_dump_xstats(struct Qdisc *sch, struct gnet_dump *d, + struct tc_taprio_qopt_offload *offload, + struct tc_taprio_qopt_stats *stats) +{ + struct net_device *dev = qdisc_dev(sch); + const struct net_device_ops *ops; + struct sk_buff *skb = d->skb; + struct nlattr *xstats; + int err; + + ops = qdisc_dev(sch)->netdev_ops; + + /* FIXME I could use qdisc_offload_dump_helper(), but that messes + * with sch->flags depending on whether the device reports taprio + * stats, and I'm not sure whether that's a good idea, considering + * that stats are optional to the offload itself + */ + if (!ops->ndo_setup_tc) + return 0; + + memset(stats, 0xff, sizeof(*stats)); + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err == -EOPNOTSUPP) + return 0; + if (err) + return err; + + xstats = nla_nest_start(skb, TCA_STATS_APP); + if (!xstats) + goto err; + + if (taprio_put_stat(skb, stats->window_drops, + TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS) || + taprio_put_stat(skb, stats->tx_overruns, + TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS)) + goto err_cancel; + + nla_nest_end(skb, xstats); + + return 0; + +err_cancel: + nla_nest_cancel(skb, xstats); +err: + return -EMSGSIZE; +} + +static int taprio_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct tc_taprio_qopt_offload offload = { + .cmd = TAPRIO_CMD_STATS, + }; + + return taprio_dump_xstats(sch, d, &offload, &offload.stats); +} + +static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_gate_list *oper, *admin; + struct tc_mqprio_qopt opt = { 0 }; + struct nlattr *nest, *sched_nest; + + mqprio_qopt_reconstruct(dev, &opt); + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto start_error; + + if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) + goto options_error; + + if (!FULL_OFFLOAD_IS_ENABLED(q->flags) && + nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) + goto options_error; + + if (q->flags && nla_put_u32(skb, TCA_TAPRIO_ATTR_FLAGS, q->flags)) + goto options_error; + + if (q->txtime_delay && + nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) + goto options_error; + + rcu_read_lock(); + + oper = rtnl_dereference(q->oper_sched); + admin = rtnl_dereference(q->admin_sched); + + if (oper && taprio_dump_tc_entries(skb, q, oper)) + goto options_error_rcu; + + if (oper && dump_schedule(skb, oper)) + goto options_error_rcu; + + if (!admin) + goto done; + + sched_nest = nla_nest_start_noflag(skb, TCA_TAPRIO_ATTR_ADMIN_SCHED); + if (!sched_nest) + goto options_error_rcu; + + if (dump_schedule(skb, admin)) + goto admin_error; + + nla_nest_end(skb, sched_nest); + +done: + rcu_read_unlock(); + return nla_nest_end(skb, nest); + +admin_error: + nla_nest_cancel(skb, sched_nest); + +options_error_rcu: + rcu_read_unlock(); + +options_error: + nla_nest_cancel(skb, nest); + +start_error: + return -ENOSPC; +} + +static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx = cl - 1; + + if (ntx >= dev->num_tx_queues) + return NULL; + + return q->qdiscs[ntx]; +} + +static unsigned long taprio_find(struct Qdisc *sch, u32 classid) +{ + unsigned int ntx = TC_H_MIN(classid); + + if (!taprio_queue_get(sch, ntx)) + return 0; + return ntx; +} + +static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct Qdisc *child = taprio_leaf(sch, cl); + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle |= TC_H_MIN(cl); + tcm->tcm_info = child->handle; + + return 0; +} + +static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) + __releases(d->lock) + __acquires(d->lock) +{ + struct Qdisc *child = taprio_leaf(sch, cl); + struct tc_taprio_qopt_offload offload = { + .cmd = TAPRIO_CMD_QUEUE_STATS, + .queue_stats = { + .queue = cl - 1, + }, + }; + + if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 || + qdisc_qstats_copy(d, child) < 0) + return -1; + + return taprio_dump_xstats(sch, d, &offload, &offload.queue_stats.stats); +} + +static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx; + + if (arg->stop) + return; + + arg->count = arg->skip; + for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { + if (!tc_qdisc_stats_dump(sch, ntx + 1, arg)) + break; + } +} + +static struct netdev_queue *taprio_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + return taprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); +} + +static const struct Qdisc_class_ops taprio_class_ops = { + .graft = taprio_graft, + .leaf = taprio_leaf, + .find = taprio_find, + .walk = taprio_walk, + .dump = taprio_dump_class, + .dump_stats = taprio_dump_class_stats, + .select_queue = taprio_select_queue, +}; + +static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { + .cl_ops = &taprio_class_ops, + .id = "taprio", + .priv_size = sizeof(struct taprio_sched), + .init = taprio_init, + .change = taprio_change, + .destroy = taprio_destroy, + .reset = taprio_reset, + .attach = taprio_attach, + .peek = taprio_peek, + .dequeue = taprio_dequeue, + .enqueue = taprio_enqueue, + .dump = taprio_dump, + .dump_stats = taprio_dump_stats, + .owner = THIS_MODULE, +}; +MODULE_ALIAS_NET_SCH("taprio"); + +static struct notifier_block taprio_device_notifier = { + .notifier_call = taprio_dev_notifier, +}; + +static int __init taprio_module_init(void) +{ + int err = register_netdevice_notifier(&taprio_device_notifier); + + if (err) + return err; + + return register_qdisc(&taprio_qdisc_ops); +} + +static void __exit taprio_module_exit(void) +{ + unregister_qdisc(&taprio_qdisc_ops); + unregister_netdevice_notifier(&taprio_device_notifier); +} + +module_init(taprio_module_init); +module_exit(taprio_module_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Time Aware Priority qdisc"); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index b2e4b6ad241a..f2340164f579 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -1,15 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_tbf.c Token Bucket Filter queue. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Dmitry Torokhov <dtor@mail.ru> - allow attaching inner qdiscs - * original idea by Martin Devera - * */ #include <linux/module.h> @@ -18,8 +13,10 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> +#include <net/gso.h> #include <net/netlink.h> #include <net/sch_generic.h> +#include <net/pkt_cls.h> #include <net/pkt_sched.h> @@ -142,14 +139,64 @@ static u64 psched_ns_t2l(const struct psched_ratecfg *r, return len; } -/* - * Return length of individual segments of a gso packet, - * including all headers (MAC, IP, TCP/UDP) - */ -static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) +static void tbf_offload_change(struct Qdisc *sch) { - unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - return hdr_len + skb_gso_transport_seglen(skb); + struct tbf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_tbf_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_TBF_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.replace_params.rate = q->rate; + qopt.replace_params.max_size = q->max_size; + qopt.replace_params.qstats = &sch->qstats; + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt); +} + +static void tbf_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_tbf_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_TBF_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt); +} + +static int tbf_offload_dump(struct Qdisc *sch) +{ + struct tc_tbf_qopt_offload qopt; + + qopt.command = TC_TBF_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_TBF, &qopt); +} + +static void tbf_offload_graft(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc *old, struct netlink_ext_ack *extack) +{ + struct tc_tbf_qopt_offload graft_offload = { + .handle = sch->handle, + .parent = sch->parent, + .child_handle = new->handle, + .command = TC_TBF_GRAFT, + }; + + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, old, + TC_SETUP_QDISC_TBF, &graft_offload, extack); } /* GSO packet is too big, segment it so that tbf can transmit @@ -161,7 +208,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, struct tbf_sched_data *q = qdisc_priv(sch); struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); - unsigned int len = 0, prev_len = qdisc_pkt_len(skb); + unsigned int len = 0, prev_len = qdisc_pkt_len(skb), seg_len; int ret, nb; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); @@ -170,35 +217,42 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); nb = 0; - while (segs) { - nskb = segs->next; - segs->next = NULL; - qdisc_skb_cb(segs)->pkt_len = segs->len; - len += segs->len; + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + seg_len = segs->len; + qdisc_skb_cb(segs)->pkt_len = seg_len; + qdisc_skb_cb(segs)->pkt_segs = 1; ret = qdisc_enqueue(segs, q->qdisc, to_free); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) qdisc_qstats_drop(sch); } else { nb++; + len += seg_len; } - segs = nskb; } sch->q.qlen += nb; - if (nb > 1) + sch->qstats.backlog += len; + if (nb > 0) { qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); - consume_skb(skb); - return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; + consume_skb(skb); + return NET_XMIT_SUCCESS; + } + + kfree_skb(skb); + return NET_XMIT_DROP; } static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct tbf_sched_data *q = qdisc_priv(sch); + unsigned int len = qdisc_pkt_len(skb); int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) + if (skb_is_gso(skb) && + skb_gso_validate_mac_len(skb, q->max_size)) return tbf_segment(skb, sch, to_free); return qdisc_drop(skb, sch, to_free); } @@ -209,7 +263,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, return ret; } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -284,8 +338,6 @@ static void tbf_reset(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; q->t_c = ktime_get_ns(); q->tokens = q->buffer; q->ptokens = q->mtu; @@ -302,20 +354,23 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = { [TCA_TBF_PBURST] = { .type = NLA_U32 }, }; -static int tbf_change(struct Qdisc *sch, struct nlattr *opt) +static int tbf_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { int err; struct tbf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_TBF_MAX + 1]; struct tc_tbf_qopt *qopt; struct Qdisc *child = NULL; + struct Qdisc *old = NULL; struct psched_ratecfg rate; struct psched_ratecfg peak; u64 max_size; s64 buffer, mtu; u64 rate64 = 0, prate64 = 0; - err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy, NULL); + err = nla_parse_nested_deprecated(tb, TCA_TBF_MAX, opt, tbf_policy, + NULL); if (err < 0) return err; @@ -326,11 +381,13 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) qopt = nla_data(tb[TCA_TBF_PARMS]); if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE) qdisc_put_rtab(qdisc_get_rtab(&qopt->rate, - tb[TCA_TBF_RTAB])); + tb[TCA_TBF_RTAB], + NULL)); if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE) qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate, - tb[TCA_TBF_PTAB])); + tb[TCA_TBF_PTAB], + NULL)); buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U); mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U); @@ -383,21 +440,22 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) if (err) goto done; } else if (qopt->limit > 0) { - child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); + child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit, + extack); if (IS_ERR(child)) { err = PTR_ERR(child); goto done; } + + /* child is fifo, no need to check for noop_qdisc */ + qdisc_hash_add(child, true); } sch_tree_lock(sch); if (child) { - qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, - q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_purge_queue(q->qdisc); + old = q->qdisc; q->qdisc = child; - if (child != &noop_qdisc) - qdisc_hash_add(child, true); } q->limit = qopt->limit; if (tb[TCA_TBF_PBURST]) @@ -416,23 +474,28 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg)); sch_tree_unlock(sch); + qdisc_put(old); err = 0; + + tbf_offload_change(sch); done: return err; } -static int tbf_init(struct Qdisc *sch, struct nlattr *opt) +static int tbf_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct tbf_sched_data *q = qdisc_priv(sch); - if (opt == NULL) + qdisc_watchdog_init(&q->watchdog, sch); + q->qdisc = &noop_qdisc; + + if (!opt) return -EINVAL; q->t_c = ktime_get_ns(); - qdisc_watchdog_init(&q->watchdog, sch); - q->qdisc = &noop_qdisc; - return tbf_change(sch, opt); + return tbf_change(sch, opt, extack); } static void tbf_destroy(struct Qdisc *sch) @@ -440,7 +503,8 @@ static void tbf_destroy(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); - qdisc_destroy(q->qdisc); + tbf_offload_destroy(sch); + qdisc_put(q->qdisc); } static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -448,9 +512,13 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) struct tbf_sched_data *q = qdisc_priv(sch); struct nlattr *nest; struct tc_tbf_qopt opt; + int err; + + err = tbf_offload_dump(sch); + if (err) + return err; - sch->qstats.backlog = q->qdisc->qstats.backlog; - nest = nla_nest_start(skb, TCA_OPTIONS); + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -493,7 +561,7 @@ static int tbf_dump_class(struct Qdisc *sch, unsigned long cl, } static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -501,6 +569,8 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->qdisc); + + tbf_offload_graft(sch, new, *old, extack); return 0; } @@ -510,32 +580,22 @@ static struct Qdisc *tbf_leaf(struct Qdisc *sch, unsigned long arg) return q->qdisc; } -static unsigned long tbf_get(struct Qdisc *sch, u32 classid) +static unsigned long tbf_find(struct Qdisc *sch, u32 classid) { return 1; } -static void tbf_put(struct Qdisc *sch, unsigned long arg) -{ -} - static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { - if (walker->count >= walker->skip) - if (walker->fn(sch, 1, walker) < 0) { - walker->stop = 1; - return; - } - walker->count++; + tc_qdisc_stats_dump(sch, 1, walker); } } static const struct Qdisc_class_ops tbf_class_ops = { .graft = tbf_graft, .leaf = tbf_leaf, - .get = tbf_get, - .put = tbf_put, + .find = tbf_find, .walk = tbf_walk, .dump = tbf_dump_class, }; @@ -555,6 +615,7 @@ static struct Qdisc_ops tbf_qdisc_ops __read_mostly = { .dump = tbf_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("tbf"); static int __init tbf_module_init(void) { @@ -568,3 +629,4 @@ static void __exit tbf_module_exit(void) module_init(tbf_module_init) module_exit(tbf_module_exit) MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Token Bucket Filter qdisc"); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 9fe6b427afed..8badec6d82a2 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -1,10 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* net/sched/sch_teql.c "True" (or "trivial") link equalizer. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ @@ -82,7 +78,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) struct net_device *dev = qdisc_dev(sch); struct teql_sched_data *q = qdisc_priv(sch); - if (q->q.qlen < dev->tx_queue_len) { + if (q->q.qlen < READ_ONCE(dev->tx_queue_len)) { __skb_queue_tail(&q->q, skb); return NET_XMIT_SUCCESS; } @@ -128,7 +124,6 @@ teql_reset(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); skb_queue_purge(&dat->q); - sch->q.qlen = 0; } static void @@ -138,6 +133,9 @@ teql_destroy(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); struct teql_master *master = dat->m; + if (!master) + return; + prev = master->slaves; if (prev) { do { @@ -167,7 +165,8 @@ teql_destroy(struct Qdisc *sch) } } -static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) +static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct teql_master *m = (struct teql_master *)sch->ops; @@ -242,7 +241,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)), haddr, NULL, skb->len); if (err < 0) @@ -298,7 +297,7 @@ restart: struct net_device *slave = qdisc_dev(q); struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0); - if (slave_txq->qdisc_sleeping != q) + if (rcu_access_pointer(slave_txq->qdisc_sleeping) != q) continue; if (netif_xmit_stopped(netdev_get_tx_queue(slave, subq)) || !netif_running(slave)) { @@ -425,7 +424,7 @@ static int teql_master_mtu(struct net_device *dev, int new_mtu) } while ((q = NEXT_SLAVE(q)) != m->slaves); } - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); return 0; } @@ -492,7 +491,7 @@ static int __init teql_init(void) master = netdev_priv(dev); - strlcpy(master->qops.id, dev->name, IFNAMSIZ); + strscpy(master->qops.id, dev->name, IFNAMSIZ); err = register_qdisc(&master->qops); if (err) { @@ -524,3 +523,4 @@ module_init(teql_init); module_exit(teql_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("True (or trivial) link equalizer qdisc"); |