Abstract: A computer-implemented method, apparatus, and computer program product are disclosed in a data processing environment that includes host computer systems that are coupled to adapters utilizing a switched fabric for routing packets between the host computer systems and the adapters. A unique destination identifier is assigned to one of the host computer systems. A portion of a standard format packet destination address is selected. Within a particular packet, the portion is set equal to the unique identifier that is assigned to the host computer system. The particular packet is then routed through the fabric to the host computer system using the unique destination identifier.

Abstract: A method for generating network traffic includes receiving packet header information and an optional packet payload. The received packet header information is arranged in accordance with a predetermined format. A packet of data including the packet payload and a packet header is formatted in accordance with the arranged header information. The predetermined format specifies a particular order in which packet headers are to be arranged.

Abstract: Mechanisms for migration of a virtual endpoint from one virtual plane to another are provided. With these mechanisms, when a management application requests migration of a virtual endpoint (VE) from one virtual plane (VP) to another, a fabric manager provides an input/output virtualization intermediary (IOVI) with an interrupt to perform a stateless migration. The IOVI quiesces outstanding requests to the virtual functions (VFs) of the VE, causes a function level reset of the VFs, deconfigures addresses in intermediary switches corresponding to the VP, and informs the fabric manager that a destination migration is requested. The fabric manager sends an interrupt to the destination IOVI which performs a function level reset of the destination VFs and reprograms the intermediary switches with the addresses of the destination VP. The destination VFs may then be placed in an active state.

Abstract: Mechanisms for differentiating traffic types per host system blade in a multi-root PCI Express environment are provided. The mechanisms generate a first mapping data structure that, for each single-root virtual hierarchy in the multi-root data processing system, associates a plurality of traffic classes with a plurality of priority groups and maps each traffic class in the plurality of traffic classes to a corresponding virtual channel in a plurality of virtual channels. Moreover, a second mapping data structure is generated that maps each virtual channel in the plurality of virtual channels to corresponding per host system blade virtual links in a plurality of virtual links of the multi-root data processing system. Traffic of a particular priority group is routed from a single-root virtual hierarchy to a particular virtual link in the plurality of the virtual links based on the first mapping data structure and second mapping data structure.

Abstract: A hypervisor, during device discovery, has code which can examine the south-side management data structure in an adapter's configuration space and determine the type of device which is being configured. The hypervisor may copy the south-side management data structure to a hardware management console (HMC) and the HMC can populate the data structure with south-side data and then pass the structure to the hypervisor to replace the data structure on the adapter. In another embodiment the hypervisor may copy the data structure to the HMC and the HMC can instruct the hypervisor to fill-in the data structure, a virtual function at a time, with south-side management data associations. The administrator can assign south-side data, such as a MAC address for a virtual instance of an Ethernet device, to LPARs sharing the adapter. Thus, a standard way to manage the south-side data of virtual functions is provided.

Abstract: In one embodiment, a computer-implemented method for creating redundant system configurations is presented. The computer-implemented method creates a set of virtual function path authorization tables, and receives a request from a requester to provide requested data from a virtual function wherein the virtual function is performed by a single root or a multi-root peripheral component interconnect device. Further a receive buffer is created in a selected address range in a set of addresses ranges as well as a virtual function work queue entry for the virtual function containing an address of the receive buffer in the selected address range. Responsive to a determination that the virtual function is authorized, writing the requested data into the receive buffer of the selected address range in the one or more systems, and responsive to writing the requested data, issuing a notice of completion to the requester.

Abstract: Mechanisms for performing all-to-all comparisons on architectures having limited storage space are provided. The mechanisms determine a number of data elements to be included in each set of data elements to be sent to each processing element of a data processing system, and perform a comparison operation on at least one set of data elements. The comparison operation comprises sending a first request to main memory for transfer of a first set of data elements into a local memory associated with the processing element and sending a second request to main memory for transfer of a second set of data elements into the local memory. A pair wise comparison computation of the all-to-all comparison of data elements operation is performed at approximately a same time as the second set of data elements is being transferred from main memory to the local memory.

Abstract: A computer-implemented method for a high speed peripheral component interconnect input/output virtualization configuration creates a set of virtual function path authorization tables, receives a request including a virtual function, from a requester, to provide requested data, and identifies a source address in the source system and a target address in each target system of the target set of systems. A virtual function work queue entry for the source system is created containing the source and the target address and responsive to determining the virtual function is authorized, write the requested data from the source address of the source system through a firewall of an intermediate device into the target address of each target system, wherein the intermediate device is one of a multi-root peripheral component interconnect device and a single root peripheral component interconnect device, and issuing a notice of completion to the requester.

Abstract: Mechanisms for differentiating traffic types in a multi-root PCI Express environment are provided. The mechanisms generate a first mapping data structure that, for each single-root virtual hierarchy in the multi-root data processing system, associates a plurality of traffic classes with a plurality of priority groups and maps each traffic class in the plurality of traffic classes to a corresponding virtual channel in a plurality of virtual channels. Moreover, a second mapping data structure is generated that maps each virtual channel in the plurality of virtual channels to corresponding virtual link in a plurality of virtual links of the multi-root data processing system. Traffic of a particular priority group is routed from a single-root virtual hierarchy to a particular virtual link in the plurality of the virtual links based on the first mapping data structure and second mapping data structure.

Abstract: A computer-implemented method, apparatus, and computer program product are disclosed for routing error messages in a multiple host computer system environment to only those host computer systems that are affected by the error. The environment includes multiple host computer systems that share multiple devices utilizing a switched fabric. An error is detected in one of the devices. Routing tables that are stored in fabric devices in the fabric are used to identify ones of the host computer systems that are affected by the error. An error message that identifies the error is routed to only the identified ones of the host computer systems.

Abstract: A “LUN Table” enables Logical Unit Number (LUN) mapping/masking within an IOV adapter included in a Serial Attached Small Computer System Interface (“SAS” or “Serial Attached SCSI”). A plurality of System Images (“SI”) share block storage through the SAS. The IOV adapter includes one or more Virtual Functions (VF), a Physical Function (PF), and a LUN Table within the PF. The VF allows each SI to communicate I/0 requests with a storage device through the PF. The LUN Table maps the I/0 requests to unique locations within the storage device. Each SI is isolated from all other SIs. Interference between each SI is avoided. A VIOS or a LUN mapping/masking SAN are not required. I/0 latency, processor overhead and storage cost are improved over prior LUN mapping/masking solutions.

Abstract: Mechanisms for migration stateless virtual functions from one virtual plane to another are provided. When a migration of a source virtual function to a destination virtual function in another virtual plane is to be performed, a source single root PCI manager (SR-PCIM) is first interrupted by a multiple root PCI manager (MR-PCIM). Configuration information that defines the source virtual function is then redefined on the destination virtual function for this stateless migration. A function level reset may then be performed on the source virtual function. The destination SR-PCIM may be interrupted by the MR-PCIM with an interrupt for the destination virtual function. A function level reset may then be performed on the destination virtual function. The destination virtual function state may then be changed to an “active” state such that the migrated virtual function begins processing transactions.

Abstract: In a distributed computer system having multiple root nodes, a challenge protocol is provided, for use in determining or confirming the root node in which a PCI Configuration Manager (PCM) actually resides. This node is referred to as the master node. The challenge procedure is activated whenever the identity of the PCM, which is determined by the root node in which it resides, appears to be uncertain. The challenge procedure resolves this uncertainty, and enables the PCM to continue to configure routings throughout the system. In a useful embodiment, a method is directed to a distributed computer system of the above type which is further provided with PCI switches and with adapters that are available for sharing by different nodes. The method includes the steps of selecting a first one of the root nodes to be master root node, and operating the first root node to query the configuration space of a particular one of the PCI switches.

Abstract: Mechanisms are provided for implementing a multi-root PCI manager (MR-PCIM) in a multi-root I/O virtualization management partition (MR-IMP) to control the shared functionality of an multi-root I/O virtualization (IOV) enabled switch fabric and multi-root IOV enabled I/O adapter (IOA) through the base functions (BF) of the switches and IOAs. A hypervisor provides device-independent facilities to the code running in the I/O Virtualization Management Partition (IMP), Multi-Root (MR)-IMP and client partitions. The MR-IMP may include device specific code without the hypervisor needing to sacrifice its size, robustness, and upgradeability. The hypervisor provides the virtual intermediary functionally for the sharing and control of the switch and IOA's control functions.

Abstract: Mechanisms for enabling both native and non-native input/output virtualization (IOV) in a single I/O adapter are provided. The mechanisms allow a system with a large number of logical partitions (LPARs) and system images to use IOV to share a native IOV enabled I/O adapter or endpoint that does not implement the necessary number of virtual functions (VFs) for each LPAR and system image. A number of VFs supported by the I/O adapter, less one, are assigned to LPARs and system images so that they may make use of native IOV using these VFs. The remaining VF is associated with a virtual intermediary (VI) which handles non-native IOV of the I/O adapter. Any remaining LPARs and system images share the I/O adapter using the non-native IOV via the VI. Thus, any number of LPARs and system images may share the same I/O adapter or endpoint.

Abstract: A hypervisor, during device discovery, has code which can examine the south-side management data structure in an adapter's configuration space and determine the type of device which is being configured. The hypervisor may copy the south-side management data structure to a hardware management console (HMC) and the HMC can populate the data structure with south-side data and then pass the structure to the hypervisor to replace the data structure on the adapter. In another embodiment the hypervisor may copy the data structure to the HMC and the HMC can instruct the hypervisor to fill-in the data structure, a virtual function at a time, with south-side management data associations. The administrator can assign south-side data, such as a MAC address for a virtual instance of an Ethernet device, to LPARs sharing the adapter. Thus, a standard way to manage the south-side data of virtual functions is provided.

Abstract: A computer-implemented method, apparatus, and computer program product are disclosed for bus/device/function (BDF) translation and routing of communications packets through a fabric that utilizes PCI switches. Identifiers are included in communications packets that are routed between a host and an I/O adapter using a PCI fabric to which the host and the I/O adapter are coupled. Destination identifiers that are included in first communications packets that are received by edge switches, which are connected directly to said host or directly connected to said I/O adapter, are translated before routing the communications packets out of the edge switches. Second communications packets that are received by internal switches, which are not directly connected to the host or directly connected to the I/O adapter, are routed without translating destination identifiers that are included in the second communications packets.

Abstract: System and method for managing routing of data in a distributed computing system, such as a distributed computing system that uses PCI Express protocol to communicate over an I/O fabric. A physical tree that is indicative of a physical configuration of the distributed computing system is determined, and a virtual tree is created from the physical tree. The virtual tree is then modified to change an association between at least one source device and at least one target device in the virtual tree. A validation mechanism validates the changed association between the at least one source device and the at least one target device to enable routing of data from the at least one source device to the at least one target device.

Abstract: A PCI Express (PCIe) computer system utilizes address translation services to translate virtual addresses from I/O device adaptors to physical addresses of system memory. A combined memory controller and host bridge uses a translation agent to convert the I/O addresses via translation control entries (TCEs) in a TCE table (also known as an address translation and protection table). Some of the I/O device adaptors have address translation caches for local storage of TCEs. The TCE definition includes a new non-cacheable control bit which is set active in the TCE table when the TCE is in the process of being invalidated. The memory controller prevents further caching of the TCE while the non-cacheable control bit is active. A further implementation utilizes a change-in-progress control bit of the TCE to indicate that the TCE is in the process of being changed to allow simultaneous invalidation of the previously TCE information.

Abstract: The system and method address the situation where an input/output (I/O) fabric is shared by more than one logical partition (LPAR) and where each LPAR can share with the other LPARs an I/O adapter (IOA). In particular, each LPAR is assigned its own separate address space to access a virtual function (VF) assigned to it such that each LPAR's perception is that it has its own independent IOA. Each VF may be shared across multiple LPARs. Facilities are provided for management of the shared resources of the IOA via a Physical Function (PF) of the IOA by assignment of that PF to an I/O Virtualization Management Partition (IMP). The code running in the IMP acts as a virtual intermediary to the VFs for fully managing the VF error handling, VF reset, and configuration operations. The IMP also acts as an interface to the PF for accessing common VF functionality.