Abstract: A packet is received at a network device, the packet having a header that includes destination information for a first network in a first header portion, and destination information for a second network in a second header portion. The packet is processed, in a first pass, to make a first forwarding decision to forward the packet to a destination in the first network based on information contained in the first header portion. The packet is replicated and the packet, or the replicated packet, is returned for processing in a second pass. The packet, or the replicated packet, is processed in the second pass to make a second forwarding decision to forward at least a portion of the packet or the replicated packet to a destination in the second network based on information contained in the second header portion without relying on information contained in the first header portion.

Abstract: Linked list profiling and updating techniques define subsets of linked list entries that are executed upon various resource calls. The subsets are defined by linked list profiles. The techniques can add/remove linked list entries to/from these profiles in a flexible update manner, in which a profile table is used to store profiles, or in atomic manner, in which each linked list entry itself contains profile data. Implemented in a communication system network device, the techniques are used to define and update profiles of physical or virtual ports used for packet-based egress and ingress communications.

Abstract: Devices, systems, methods, and other embodiments associated with cascaded memory tables for searching are described. In one embodiment, an integrated chip is implemented with two or more address tables. The two or more address tables are implemented with separate memory tables to store addresses. The two or more address tables are comprised of a first address table and a second address table. Connection lines connect the first address table and the second address table to create a cascaded address table. Search logic initiates a search of the first address table for an address. If the address is not found, the search logic initiates a search of the second address table through the connection lines.

Abstract: A network device including a processor having an internet protocol (IP) address, and a processor port configured to communicate exclusively with the processor. The network device also includes a plurality of network ports configured to communicate with network nodes external to the network device. In addition, the network device includes a forwarding engine configured to selectively transfer packets (i) among the plurality of network ports, and (ii) between the processor port and the plurality of network ports; receive a broadcast packet from one of the plurality of network ports, the broadcast packet including a target IP address; and forward the broadcast packet to the processor, via the processor port, only when both (i) the broadcast packet is a control packet, and (ii) the target IP address of the broadcast packet matches the IP address of processor.

Abstract: A multi-stage engine for processing Operations, Administration, and Maintenance (OAM) data units in a network device that includes a memory and an ingress interface from which an OAM data unit is received, includes a first processing stage in a network device, such that the first processing engine is configured to identify a flow of communication traffic to which the OAM data unit belongs, where the flow of communication traffic is identified from among a plurality of flows of communicate traffic received by the network device, and a second processing stage includes an action identification module to identify in the memory an action corresponding to the identified flow using the OAM data unit, and a processing module to process the OAM data unit in accordance with the identified action.

Abstract: A method of detecting address spoofing includes receiving an ARP packet at a network device. The ARP packet includes a first address associated with a first network layer and a second address associated with a second network layer. The method also includes accessing a first memory searchable by the first address to obtain a memory reference and retrieving a third address associated with the second network layer from a second memory using the memory reference. The method further includes comparing the second address with the third address and detecting address spoofing if a match is not present between the second address and the third address.

Abstract: A network device includes a plurality of physical ports configured to be coupled to one or more networks, and a processor device configured to process packets. The processor device includes a processor configured to implement a logical port assignment mechanism to assign source logical port information to a data packet received via a source physical port of the plurality of physical ports. The source logical port information is assigned based on one or more characteristics of the data packet, and the source logical port information corresponds to a logical entity that is different from any physical port. The processor device also includes a forwarding engine processor configured to determine one or more egress logical ports for forwarding the data packet, map the egress logical port(s) to respective egress physical port(s) of the plurality of physical ports, and forward the data packet to the egress physical port(s) based on the mapping.

Abstract: A network device comprises a plurality of physical ports and a packet processing pipeline. The packet processing pipeline is configured to assign a virtual port from a plurality of virtual ports to a packet received via one of the physical ports, wherein a quantity of the virtual ports is larger than a quantity of the physical ports, and wherein, for each of at least some of the physical ports, multiple virtual ports correspond to one physical port. The packet processing pipeline is also configured to assign a virtual domain from a plurality of virtual domains to the packet based on the assigned virtual port, and process the packet based on one or more of i) the assigned virtual port, ii) the assigned virtual domain, and iii) a header field of the packet, including determining zero, one, or more physical ports to which the packet is to be forwarded.

Abstract: A network device includes at least one source physical port configured to be coupled to a network, a plurality of egress ports, and a packet processor. The packet processor includes a processing stage configured to implement a logical port assignment mechanism to assign source logical port information to a data packet received via one of the at least one source physical port, wherein the source logical port information is based on characteristics of the data packet, wherein the source logical port information corresponds to a logical entity that is different from any source physical port, and a forwarding engine to determine one or more egress ports for forwarding the data packet based on at least the assigned source logical port information.

Abstract: A network device comprises a plurality of physical ports, and a packet processing pipeline coupled to the plurality of physical ports. The packet processing pipeline is configured to assign a virtual port from a plurality of virtual ports to a packet received via one of the physical ports, wherein a quantity of the plurality of virtual ports is larger than a quantity of the plurality of physical ports, and wherein, for each of at least some of the physical ports, multiple virtual ports correspond to one physical port. The packet processing pipeline is also configured to assign a virtual domain from a plurality of virtual domains to the packet based on the assigned virtual port, and process the packet based on one or more of i) the assigned virtual port, ii) the assigned virtual domain, and iii) a header field of the packet, including determining zero, one, or more physical ports to which the packet is to be forwarded.

Abstract: An apparatus for forwarding packets includes a packet processing pipeline having a processing unit that processes packets compliant with a recognized communication protocol. A first port coupled to the packet processing pipeline is configured to receive a packet that does not comply with the recognized communication protocol and has a header that conforms to a second communication protocol. A data extraction unit extracts first destination information from the header of the packet and, based on the first destination information, generates second destination information that conforms to the recognized communication protocol. The processing unit determines, based on the second destination information, an egress interface to which the packet is to be forwarded.

Abstract: A packet processing pipeline is configured to classify packets received via a network based on information in the received packets: (1) as belonging to one of a plurality of identified flows, or (2) as not belonging to any of the plurality of identified flows. For each received packet determined not to belong to one of the previously identified flows, the pipeline sends at least a portion of the packet or a corresponding packet descriptor to a processing unit. For each received packet determined not to belong to one of the previously identified flows, the processing unit defines a new flow corresponding to the packet based on an analysis of the portion corresponding packet descriptor, and configures the packet processing pipeline to handle the new flow.

Abstract: A network switch includes a memory to store associations between at least one flooding domain and a plurality of network interfaces. A classifier assigns a processor code to selected packets received at one or more of the network interfaces. The processor code includes a flag indicating if a packet is to be processed by a processor. A transfer circuit transfers packets among the network interfaces based on the associations and transfers the selected packets to the processor based on the processor code independently of transfer of packets to at least one flooding domain.

Abstract: A network switch including a port, a memory, and a controller. The port has a port identifier and receives a packet (including an address of the source device) transmitted from a source device to the network switch. The memory is configured to store entries, each entry including (i) an identifier of a port of the network switch and (ii) an address of a network device. The controller is configured to (i) determine whether the address of the source device and the port identifier of the packet are stored in the memory and (ii) send a message to a processor requesting approval of the packet. The controller is configured to send the message when (i) the address of the source device is not stored in the memory or (ii) the port identifier of the packet is not stored with the address of the source device as one of the entries.

Abstract: A method for forwarding FCoE packets in a network switching device includes receiving a first packet at the network switching device via an Ethernet link, determining, in the network switching device, an FC destination identifier included in the first packet, updating, in the network switching device, an Ethernet address based on the FC destination identifier, generating, in the network switching device, a first TRILL destination identifier based on the updated Ethernet address, and causing, in the network switching device, the first packet to be forwarded to a different device based on the first TRILL destination identifier.

Abstract: A method for processing packets, in a network device including at least one processing engine that i) is not configured to process destination information that conforms to a first protocol and ii) is configured to process destination information that conforms to a second protocol, includes receiving a packet at the network device, and determining, in the network device, first destination information included in the packet. The first destination information conforms to the first protocol. The method also includes generating, in the network device, second destination information conforming to a third protocol based on the first destination information. The method also includes generating, in the network device, third destination information conforming to the second protocol based on the second destination information. The method also includes processing the packet with the at least one processing engine included in the network device using the third destination information.

Abstract: Devices, systems, methods, and other embodiments associated with cascaded memory tables for searching are described. In one embodiment, an integrated chip is implemented with two or more address tables. The two or more address tables are implemented with separate memory tables to store addresses. The two or more address tables are comprised of a first address table and a second address table. Connection lines connect the first address table and the second address table to create a cascaded address table. Search logic initiates a search of the first address table for an address. If the address is not found, the search logic initiates a search of the second address table through the connection lines.

Abstract: A packet is received from a network via an ingress port, wherein the packet includes at least first and second headers. A first set of one or more egress ports via which the packet is to be forwarded is determined based on one of the first header or the second header, and the packet is forwarded to the first set of one or more egress ports. At least a subset of the packet is forwarded to an upstream location in a packet processing pipeline, and a second set of one or more egress ports via which the at least a portion of the packet is to be forwarded is determined in response to forwarding the at least the subset of the packet to the upstream location in the packet processing pipeline and based on at least one of the first header or the second header. The at least the portion of the packet is forwarded to the second set of one or more egress ports.

Abstract: A network device for use in a networking system. The network device includes a packet processor adapted to receive control packets at a network port of the network device. The packet processor is also adapted to assign a CPU code to the control packets. The network device also includes a CPU in communication with the packet processor and a lookup table indexed by the CPU code and in communication with the packet processor. According to embodiments of the present invention, one or more entries in the lookup table define a rate limit in accordance with which packets characterized by the CPU code are delivered from the packet processor to the CPU.

Abstract: Devices, systems, methods, and other embodiments associated with cascaded memory tables for searching are described. In one embodiment, an integrated chip is implemented with two or more address tables. The two or more address tables are implemented with separate memory tables to store addresses. The two or more address tables are comprised of a first address table and a second address table. Connection lines connect the first address table and the second address table to create a cascaded address table. Search logic initiates a search of the first address table for an address. If the address is not found, the search logic initiates a search of the second address table through the connection lines.