US20130246680A1 - Hot plug process in a distributed interconnect bus - Google Patents
Hot plug process in a distributed interconnect bus Download PDFInfo
- Publication number
- US20130246680A1 US20130246680A1 US13/891,861 US201313891861A US2013246680A1 US 20130246680 A1 US20130246680 A1 US 20130246680A1 US 201313891861 A US201313891861 A US 201313891861A US 2013246680 A1 US2013246680 A1 US 2013246680A1
- Authority
- US
- United States
- Prior art keywords
- configuration space
- hot
- plug
- bus unit
- distributed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/40—Bus structure
- G06F13/4063—Device-to-bus coupling
- G06F13/4068—Electrical coupling
- G06F13/4081—Live connection to bus, e.g. hot-plugging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/40—Bus structure
- G06F13/4004—Coupling between buses
- G06F13/4027—Coupling between buses using bus bridges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2213/00—Indexing scheme relating to interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F2213/0026—PCI express
Definitions
- the present invention generally relates to hot-plug processes, and more particularly, for enabling a hot-plug process in a distributed interconnect bus.
- PCI Express Peripheral Component Interconnect Express
- PCIe Peripheral Component Interconnect Express
- PCIe implements a serial, full duplex, multi-lane, point-to-point interconnect, packet-based, and switch based technology.
- Current versions of PCIe buses allow for a transfer rate of 2.5 Giga bit per second (Gbps) or 5 Gbps, per lane, with up to 32 lanes.
- Gbps giga bit per second
- the PCIe bus protocol communication is encapsulated in packets.
- the packetizing and depacketizing data and status-message traffic is handled by the transaction layer of a PCIe port.
- PCIe is used as a motherboard-level interconnect and an expansion board interface for add-in cards.
- a PCIe bus 100 interconnects the card 110 to the motherboard 120 and further connects expansion cards 130 and 140 through a host 160 .
- the host 160 is connected to the motherboard 120 .
- the PCIe bus 100 allows connectivity between the various cards to a CPU sub system 170 of the computing device.
- An expansion card is typically inserted into a slot.
- the host and/or the motherboard are referred to as PCIe roots and the cards are PCIe endpoints.
- An internal memory 180 is also coupled to the motherboard 120 .
- the PCIe is a layered protocol bus, consisting of a transaction layer 210 , a data link layer 220 , and a physical layer 230 .
- the PCIe implements split transactions, i.e., transactions with request and response separated by time, allowing the link to carry other traffic while the target device gathers data for the response.
- the primary function of the transaction layer 210 is to assemble and disassemble transaction layer packets (TLPs). TLPs are used to carry transactions, where each TLP has a unique identifier that enables a response directed at the originator.
- the data link layer 220 acts as an intermediate between the transaction layer 210 and the physical layer 230 and provides a reliable mechanism for exchanging TLPs.
- the data link layer 220 implements error checking (known as “LCRC”) and retransmission mechanisms. LCRC and sequencing are applied on received TLPs and if an error is detected, a data link retry is activated.
- the physical layer 230 consists of an electrical sub-layer 234 and logical sub-layer 232 .
- the logical sub-layer 232 is a transmitter and receiver pair implementing symbol mapping, serialization, and de-serialization of data.
- each lane utilizes two unidirectional low-voltage differential signaling (LVDS) pairs for transmitting and receiving symbols from the logical sub-block 232 .
- LVDS low-voltage differential signaling
- the PCIe bus protocol supports a hot-plug process, i.e., replacing system components without shutting down the power. This feature is highly important in blade servers where cards are frequently removed and inserted without powering on/off the server.
- a hot-plug process is supported in a current implementation of the PCIe buses and controllers.
- the PCIe standard defines a Slot Capabilities Register, Slot Control Register, and Slot Status Register to support the hot-plug process. These registers and the standard hot-plug process are described in detail in the PCI ExpressTM base Specification reversion 1.0a, sections 6.7, 7.8.9, 7.8.10, and 7.8.11 published on Apr. 15, 2003, by the PCI-SIG.
- the Slot Capabilities Register identifies specific capabilities of a PCIe slot.
- the Slot Capabilities Register includes several bits, two of which are: Hot-Plug Surprise bit that indicates that a card in a designated slot can be removed without any prior notification and Hot-Plug Capable bit that indicates that a designated slot is capable of supporting hot-plug operations.
- the Slot Control Register includes bits, that when set, define if a hot-plug interrupt can be asserted, e.g., if a power fault or a presence of card in the slot is detected.
- the Slot Status Register provides information about slot specific parameters, e.g., if a power fault or a presence of the card is detected. These registers will be referred to hereinafter as “Hot-Plug Registers” or “HP R”.
- the hot-plug operation as currently implemented includes generating an interrupt when the slot status changes, i.e., from connected to disconnected and vice versa.
- the operating system captures the interrupt and allocates/reallocates resources to the inserted/removed device.
- OS operating system
- the OS enumerates the card in the order it appears on the PCIe bus.
- a distributed interconnect bus connects the root to endpoints over a distributed medium, e.g., a wireless medium, a computer network, and the like.
- the distributed interconnect bus includes two bridges that implement the PCIe protocol. A first bridge is coupled to the root and a second bridge is connected to an endpoint. The first and second bridge communicate over the distributed medium.
- An example of a distributed bus can be found in US Patent Application Publication No. 2009/0024782, entitled “Distributed Interconnect Bus Apparatus,” assigned to the common assignee, and incorporated herein by reference in its entirety merely for the useful understanding of the background of the invention.
- the connectivity between the endpoints and the root is unreliable.
- the wireless link may frequently be idle for a short period of time, and then operational again.
- Such an event may be treated as a hot-plug event (i.e., a card is removed and inserted).
- the above-referenced standard defines the hot-plug process in a standard PCIe bus where the root and endpoints are physically coupled to the bus, and the connectivity medium is entirely integrated in the computing device (e.g., server or PC).
- the computing device e.g., server or PC
- Data transfers between the root and endpoint(s) are performed by encapsulating the TLPs in data structures compliant with the distributed medium. Further, the signaling definitions and protocol of a standard PCIe do not apply for communication over the distributed medium. Thus, if a bridge coupled to the endpoint generates a hot-plug interrupt signal, the signal cannot be transferred to the root (which informs the OS).
- Certain embodiments disclosed herein include a method for performing a hot-plug removal process in a distributed peripheral component interconnect express (PCIe) bus.
- the method comprises receiving a hot-plug interrupt asserted by a shadow configuration space when a distributed link established over the distributed PCIe is unavailable, wherein the shadow configuration space is a copy of a configuration space of at least one endpoint component wirelessly connected to a host device over the distributed PCIe; reading a hot-plug status from the shadow configuration space; writing to the shadow configuration space to turn off at least one peripheral device connected to the at least one endpoint component; and de-allocating resources allocated to a driver of the at least one peripheral.
- PCIe peripheral component interconnect express
- Certain embodiments disclosed herein also include a method for performing a hot-plug insertion process in a distributed peripheral component interconnect express (PCIe) bus.
- the method comprises receiving a hot-plug interrupt asserted by a shadow configuration space when a distributed link established over the distributed PCIe is available, the hot-plug interrupt informing on detection of a hot-plug insertion event; reading a hot-plug status from a configuration space of at least one endpoint component wirelessly connected to a host device over the distributed PCIe, wherein the configuration space is a copy of the shadow configuration space updated to designate the hot-plug insertion event; writing to the configuration space to turn on at least one peripheral device connected to the at least one endpoint component; and asserting a message indicating that the host device and the at least one peripheral can communicate over the distributed PCIe bus.
- PCIe peripheral component interconnect express
- Certain embodiments disclosed herein also include a wireless communication system.
- the system comprises a root component connected in a host device and directly coupled to an upstream bus unit, wherein the upstream bus unit is configured to maintain a first configuration space and a copy of a second configuration space, the first configuration space bridge includes at least hot-plug registers specifying at least capabilities and status of a slot of the upstream bus unit; and at least one endpoint component connected to at least one peripheral device and directly coupled to a downstream bus unit that communicates with the host bridge over a distributed link established over a distributed peripheral component interconnect express (PCIe) bus, wherein the downstream bus unit is configured to maintain the second configuration space; the second configuration space includes at least hot-plug registers specifying at least capabilities and status of a slot of the downstream bus unit.
- PCIe peripheral component interconnect express
- FIG. 1 is a diagram illustrating a PCIe bus connectivity
- FIG. 2 is a schematic diagram illustrating the operation of a PCIe protocol
- FIG. 3 is a block diagram of a distributed interconnect bus apparatus utilized to describe the embodiments of the invention.
- FIG. 4 is a flowchart illustrating a hot-plug removal method in a distributed PCIe bus in accordance with an embodiment of the invention.
- FIG. 5 a flowchart illustrating a hot-plug insertion method in a distributed PCIe bus in accordance with an embodiment of the invention.
- FIG. 3 shows a non-limiting and exemplary diagram of a distributed interconnect bus apparatus 300 utilized to describe the embodiments of the invention.
- the apparatus 300 comprises an upstream bus unit 305 that includes a first bridge 310 connected to a root component 320 and a second bridge 330 connected to an endpoint component 340 .
- the upstream bus unit 305 and bridge 330 communicate over a link 370 which is the distributed medium used to transfer the data between the components 320 and 340 .
- the medium may be, but is not limited to, a wireless medium, a copper cable, a fiber optic, and so on.
- the interconnect bus apparatus 300 forms a distributed bus for transferring data between remote peripheral devices connected to endpoint component 340 and a motherboard connected to the root component 320 .
- the transport protocol used to carry data over the link 370 is defined according to the type of the medium.
- the transport protocol may be, but is not limited to, IEEE 802.11x (Wi-Fi), Ethernet, Infiniband, and the like.
- the root component 320 may be either a PCIe root or a PCIe switch; the endpoint component 340 is a PCIe endpoint, and the bridges 310 and 330 are PCIe bridges.
- the root component 320 and first bridge 310 communicate by means of the PCIe protocol, and the communication between the endpoint component 340 and the second bridge 330 is similar.
- the communication over the link 370 is not compliant with the PCIe protocol.
- a hot-plug process should be performed when the link 370 transits from an operational state to an idle state (up/down) and vice versa.
- the root component 320 should receive a hot-plug indication on such events to inform the OS of the changes that occurred at the other end of the bus.
- the OS correctly handles the hot-plug events to avoid crashes in the computing device and the software which is associated with it.
- the second bridge 330 implements a configuration space 332 that includes the hot-plug registers (HPR).
- a configuration space includes a setting for performing auto configuration of an endpoint connected to a slot of a bridge.
- Each of bridges 310 and 330 maintains its configuration space that includes at least the HPR described above, i.e., the capabilities and status of the slot. It should be noted that the structure of the configuration space is similar to all bridges, but the content of which may be different.
- the HPR includes Slot Control Register, Slot Status Register, and Slot Capabilities Register described above.
- the configuration space 332 of the second bridge 330 is shadowed in the upstream bus unit 305 . That is, an exact copy of the configuration space 332 is copied and saved in the upstream bus unit 305 .
- the shadow configuration space in the upstream bus unit 305 is labeled as 332-S. Whenever the content of the configuration space 332 -S and more specifically the status of the HPR is changed, a newer version of the shadow configuration space 332 -S is saved in the upstream bus unit 305 .
- the shadow configuration space of 332-S is updated using a configuration write packet generated by the second bridge 330 . This provides the root component 320 , and hence the OS an access the most updated configuration space of a device connected to the endpoint component 340 .
- the first bridge 310 also maintains its configuration space 312 .
- the shadow configuration space 332 -S asserts a hot-plug interrupt indicating the endpoint component 340 has been removed. Further, the root component 320 updates the HPR in configuration space 332 -S on the status of the hot-plug events.
- the OS executed over the CPU accesses the HPR to read the hot-plug events and deallocates resources of a device connected to the endpoint component 340 . For example, the values of the “presence detect status” and “presence detect changed” in the Slot Status Register is read.
- the OS can read status information from the shadowed configuration space 332 -S, actions related to a card removal can be performed without any errors. Further, the OS always has a complete and updated status of the distributed PCIe bus. Without having the shadow configuration space 332 -S, the OS would have tried accessing to the second bridge 330 to write/read to the configuration space. However, as the link 370 is idle such information would not be accessible. This would result in an OS error and a crash of the computing device.
- the upstream bus unit 305 copies the shadow configuration space 332 -S to the bridge 330 , updates the HPR in the configuration space 312 of the first bridge 310 and the shadow configuration space 332 -S.
- the shadow configuration space 332 -S asserts a hot-plug interrupt to the OS. Specifically, a signal is transferred from the configuration space 332 -S to the root component 320 through the upstream bus unit 305 . It should be appreciated that copying the shadow configuration space 332 -S provides coherency between the two bridges and allows the OS to resume communication with the endpoint component 340 without the need to reconfigure the fields of the configuration space 332 of the second bridge 330 .
- FIG. 4 shows an exemplary and non-limiting flowchart 400 illustrating the process of a hot-plug removal in a distributed PCIe bus in accordance with an embodiment of the invention.
- a hot-plug removal is performed when the data cannot be transferred over the link of the distributed medium (e.g., link 370 ).
- a second bridge e.g., bridge 330
- the configuration space of the second bridge is shadowed to an upstream bus unit 305 connected to the root component 320 .
- the configuration space from the second bridge is copied to the upstream bus unit 305 forming a shadow configuration at the upstream bus unit 305 and any subsequent changes are written to the shadow configuration space.
- the configuration space includes HPR that provide at least the bridge's slot status and capabilities.
- a check is made to determine if data can be transferred over the link, i.e., if the link is available. In an embodiment of the invention, this check is performed by the root component. If S 420 results with an affirmative answer, execution returns to S 410 ; otherwise, execution continues with S 430 , where a hot-plug interrupt is asserted by the shadow configuration space 332 -S. The interrupt indicates a hot card removal event.
- the HPR in the shadow configuration space 332 -S is updated with the status of the hot-plug event.
- the OS performs a hot-plug removal process during which, the OS reads and writes to the shadow configuration space 332 -S.
- a hot-plug process performed by Windows based OS includes, in part, reading the hot-plug status bits from the Slot Status Register, requesting a plug-and-play system to eject the device connected to the endpoint, querying drivers for functions of the device, unloading the drivers of the device, writing to the shadow configuration space to turn off the device, and de-allocating resources used by driver(s).
- FIG. 5 shows an exemplary and non-limiting flowchart 500 illustrating the hot-plug insertion method in a distributed PCIe bus in accordance with an embodiment of the invention.
- the hot-plug insertion process is initiated when the data can be transferred over the link of the distributed medium (e.g., link 370 ), and the link is established.
- the second bridge 330 and the endpoint 340 connected thereon are reset.
- execution waits for the initialization of the PCIe PHY and link layers of the second bridge and endpoint.
- the shadow configuration space 332 -S is copied from the upstream bus unit 305 connected to the root to the second bridge 330 .
- each bridge updates the HPR to represent a hot-plug insertion event.
- a hot-plug interrupt is asserted by the shadow configuration space 332 -S informing the OS of the hot-plug event.
- the bridges 310 and 320 wait for the OS to complete the handling of the interrupt.
- the OS performs a hot-plug insertion process during which it reads and writes to the configuration space of the second bridge (i.e., to a recent copy of the shadow configuration space).
- a hot-plug insertion process in a Windows based OS includes, in part, reading hot-plug status bits from the Slot Status Register to determine the type of the hot-plug event, enumerating the PCIe bus to include the endpoint, reading from the configuration space 332 of the second bridge 330 in order to identify the device connected to the endpoint and perform the proper initialization actions (e.g., memory allocation, driver loading, etc.), writing to configuration space at the second bridge to turn on the device, and asserting a message that communication with the device connected to the endpoint can start.
- initialization actions e.g., memory allocation, driver loading, etc.
- the ability to provide an updated copy of the configuration space at the second bridge allows immediately establishing the distributed PCIe bus. Thus, there is no need to re-configure the configuration space at the second bridge according to the device specification. It should be noted that as the process 500 is performed when the distributed link backs up, it is assumed that the device is still connected to the endpoint.
- the various embodiments disclosed herein can be implemented as hardware, firmware, software or any combination thereof.
- the software is preferably implemented as an application program tangibly embodied on a program storage unit, a non-transitory computer readable medium, or a non-transitory machine-readable storage medium that can be in a form of a digital circuit, an analogy circuit, a magnetic medium, or combination thereof.
- the application program may be uploaded to, and executed by, a machine comprising any suitable architecture.
- the machine is implemented on a computer platform having hardware such as one or more central processing units (“CPUs”), a memory, and input/output interfaces.
- CPUs central processing units
- the computer platform may also include an operating system and microinstruction code.
- a non-transitory computer readable medium is any computer readable medium except for a transitory propagating signal.
Abstract
A wireless communication system comprises a root component connected in a host device and directly coupled to an upstream bus unit, wherein the upstream bus unit is configured to maintain a first configuration space and a copy of a second configuration space, the first configuration space bridge includes at least hot-plug registers specifying at least capabilities and status of a slot of the upstream bus unit; and at least one endpoint component connected to at least one peripheral device and directly coupled to a downstream bus unit that communicates with the host bridge over a distributed link established over a distributed peripheral component interconnect express (PCIe) bus, wherein the downstream bus unit is configured to maintain the second configuration space; the second configuration space includes at least hot-plug registers specifying at least capabilities and status of a slot of the downstream bus unit.
Description
- This application is a continuation of a U.S. patent application Ser. No. 12/887,833 filed on Sep. 22, 2010, now allowed as U.S. Pat. No. 8,443,126. The contents of which are herein incorporated by reference.
- The present invention generally relates to hot-plug processes, and more particularly, for enabling a hot-plug process in a distributed interconnect bus.
- Peripheral Component Interconnect Express (PCI Express or PCIe) is a high performance, generic and scalable system interconnect for a wide variety of applications ranging from personal computers to embedded applications. PCIe implements a serial, full duplex, multi-lane, point-to-point interconnect, packet-based, and switch based technology. Current versions of PCIe buses allow for a transfer rate of 2.5 Giga bit per second (Gbps) or 5 Gbps, per lane, with up to 32 lanes. The PCIe bus protocol communication is encapsulated in packets. The packetizing and depacketizing data and status-message traffic is handled by the transaction layer of a PCIe port.
- PCIe is used as a motherboard-level interconnect and an expansion board interface for add-in cards. For example, as illustrated in
FIG. 1 , aPCIe bus 100 interconnects thecard 110 to themotherboard 120 and further connectsexpansion cards host 160. Thehost 160 is connected to themotherboard 120. Thus, thePCIe bus 100 allows connectivity between the various cards to aCPU sub system 170 of the computing device. An expansion card is typically inserted into a slot. Usually, the host and/or the motherboard are referred to as PCIe roots and the cards are PCIe endpoints. Aninternal memory 180 is also coupled to themotherboard 120. - As illustrated in
FIG. 2 , the PCIe is a layered protocol bus, consisting of atransaction layer 210, adata link layer 220, and aphysical layer 230. The PCIe implements split transactions, i.e., transactions with request and response separated by time, allowing the link to carry other traffic while the target device gathers data for the response. With this aim, the primary function of thetransaction layer 210 is to assemble and disassemble transaction layer packets (TLPs). TLPs are used to carry transactions, where each TLP has a unique identifier that enables a response directed at the originator. Thedata link layer 220 acts as an intermediate between thetransaction layer 210 and thephysical layer 230 and provides a reliable mechanism for exchanging TLPs. Thedata link layer 220 implements error checking (known as “LCRC”) and retransmission mechanisms. LCRC and sequencing are applied on received TLPs and if an error is detected, a data link retry is activated. Thephysical layer 230 consists of anelectrical sub-layer 234 andlogical sub-layer 232. Thelogical sub-layer 232 is a transmitter and receiver pair implementing symbol mapping, serialization, and de-serialization of data. At theelectrical sub-layer 234, each lane utilizes two unidirectional low-voltage differential signaling (LVDS) pairs for transmitting and receiving symbols from thelogical sub-block 232. - Although the cards are physically connected to the motherboard, the PCIe bus protocol supports a hot-plug process, i.e., replacing system components without shutting down the power. This feature is highly important in blade servers where cards are frequently removed and inserted without powering on/off the server. A hot-plug process is supported in a current implementation of the PCIe buses and controllers. The PCIe standard defines a Slot Capabilities Register, Slot Control Register, and Slot Status Register to support the hot-plug process. These registers and the standard hot-plug process are described in detail in the PCI Express™ base Specification reversion 1.0a, sections 6.7, 7.8.9, 7.8.10, and 7.8.11 published on Apr. 15, 2003, by the PCI-SIG.
- Generally, the Slot Capabilities Register identifies specific capabilities of a PCIe slot. With regard to a hot-plug, the Slot Capabilities Register includes several bits, two of which are: Hot-Plug Surprise bit that indicates that a card in a designated slot can be removed without any prior notification and Hot-Plug Capable bit that indicates that a designated slot is capable of supporting hot-plug operations. The Slot Control Register includes bits, that when set, define if a hot-plug interrupt can be asserted, e.g., if a power fault or a presence of card in the slot is detected. The Slot Status Register provides information about slot specific parameters, e.g., if a power fault or a presence of the card is detected. These registers will be referred to hereinafter as “Hot-Plug Registers” or “HP R”.
- The hot-plug operation as currently implemented includes generating an interrupt when the slot status changes, i.e., from connected to disconnected and vice versa. The operating system (OS) captures the interrupt and allocates/reallocates resources to the inserted/removed device. Typically, when a card is inserted the OS enumerates the card in the order it appears on the PCIe bus.
- Another type of interconnect bus that recently has been developed is a distributed interconnect bus, for example, a distributed PCIe bus. A distributed interconnect bus connects the root to endpoints over a distributed medium, e.g., a wireless medium, a computer network, and the like. The distributed interconnect bus includes two bridges that implement the PCIe protocol. A first bridge is coupled to the root and a second bridge is connected to an endpoint. The first and second bridge communicate over the distributed medium. An example of a distributed bus can be found in US Patent Application Publication No. 2009/0024782, entitled “Distributed Interconnect Bus Apparatus,” assigned to the common assignee, and incorporated herein by reference in its entirety merely for the useful understanding of the background of the invention.
- Due to the physical nature of the distributed medium, the connectivity between the endpoints and the root is unreliable. For example, the wireless link may frequently be idle for a short period of time, and then operational again. Such an event may be treated as a hot-plug event (i.e., a card is removed and inserted). However, the above-referenced standard defines the hot-plug process in a standard PCIe bus where the root and endpoints are physically coupled to the bus, and the connectivity medium is entirely integrated in the computing device (e.g., server or PC). There is no a solution in the related art that provides a hot-plug process in computing systems that include distributed interconnect buses. Data transfers between the root and endpoint(s) are performed by encapsulating the TLPs in data structures compliant with the distributed medium. Further, the signaling definitions and protocol of a standard PCIe do not apply for communication over the distributed medium. Thus, if a bridge coupled to the endpoint generates a hot-plug interrupt signal, the signal cannot be transferred to the root (which informs the OS).
- Therefore, it would be advantageous to provide a solution to support a hot-plug process in distributed interconnect buses.
- Certain embodiments disclosed herein include a method for performing a hot-plug removal process in a distributed peripheral component interconnect express (PCIe) bus. The method comprises receiving a hot-plug interrupt asserted by a shadow configuration space when a distributed link established over the distributed PCIe is unavailable, wherein the shadow configuration space is a copy of a configuration space of at least one endpoint component wirelessly connected to a host device over the distributed PCIe; reading a hot-plug status from the shadow configuration space; writing to the shadow configuration space to turn off at least one peripheral device connected to the at least one endpoint component; and de-allocating resources allocated to a driver of the at least one peripheral.
- Certain embodiments disclosed herein also include a method for performing a hot-plug insertion process in a distributed peripheral component interconnect express (PCIe) bus. The method comprises receiving a hot-plug interrupt asserted by a shadow configuration space when a distributed link established over the distributed PCIe is available, the hot-plug interrupt informing on detection of a hot-plug insertion event; reading a hot-plug status from a configuration space of at least one endpoint component wirelessly connected to a host device over the distributed PCIe, wherein the configuration space is a copy of the shadow configuration space updated to designate the hot-plug insertion event; writing to the configuration space to turn on at least one peripheral device connected to the at least one endpoint component; and asserting a message indicating that the host device and the at least one peripheral can communicate over the distributed PCIe bus.
- Certain embodiments disclosed herein also include a wireless communication system. The system comprises a root component connected in a host device and directly coupled to an upstream bus unit, wherein the upstream bus unit is configured to maintain a first configuration space and a copy of a second configuration space, the first configuration space bridge includes at least hot-plug registers specifying at least capabilities and status of a slot of the upstream bus unit; and at least one endpoint component connected to at least one peripheral device and directly coupled to a downstream bus unit that communicates with the host bridge over a distributed link established over a distributed peripheral component interconnect express (PCIe) bus, wherein the downstream bus unit is configured to maintain the second configuration space; the second configuration space includes at least hot-plug registers specifying at least capabilities and status of a slot of the downstream bus unit.
- The subject matter that is regarded as the invention is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other objects, features, and advantages of the invention will be apparent from the following detailed description taken in conjunction with the accompanying drawings.
-
FIG. 1 is a diagram illustrating a PCIe bus connectivity; -
FIG. 2 is a schematic diagram illustrating the operation of a PCIe protocol; -
FIG. 3 is a block diagram of a distributed interconnect bus apparatus utilized to describe the embodiments of the invention; -
FIG. 4 is a flowchart illustrating a hot-plug removal method in a distributed PCIe bus in accordance with an embodiment of the invention; and -
FIG. 5 a flowchart illustrating a hot-plug insertion method in a distributed PCIe bus in accordance with an embodiment of the invention. - The embodiments disclosed by the invention are only examples of the many possible advantageous uses and implementations of the innovative teachings presented herein. In general, statements made in the specification of the present application do not necessarily limit any of the various claimed inventions. Moreover, some statements may apply to some inventive features but not to others. In general, unless otherwise indicated, singular elements may be in plural and vice versa with no loss of generality. In the drawings, like numerals refer to like parts through several views.
-
FIG. 3 shows a non-limiting and exemplary diagram of a distributedinterconnect bus apparatus 300 utilized to describe the embodiments of the invention. Theapparatus 300 comprises anupstream bus unit 305 that includes afirst bridge 310 connected to aroot component 320 and asecond bridge 330 connected to anendpoint component 340. Theupstream bus unit 305 and bridge 330 communicate over alink 370 which is the distributed medium used to transfer the data between thecomponents - The
interconnect bus apparatus 300 forms a distributed bus for transferring data between remote peripheral devices connected toendpoint component 340 and a motherboard connected to theroot component 320. The transport protocol used to carry data over thelink 370 is defined according to the type of the medium. For example, the transport protocol may be, but is not limited to, IEEE 802.11x (Wi-Fi), Ethernet, Infiniband, and the like. - In accordance with an embodiment of the invention, the
root component 320 may be either a PCIe root or a PCIe switch; theendpoint component 340 is a PCIe endpoint, and thebridges root component 320 andfirst bridge 310 communicate by means of the PCIe protocol, and the communication between theendpoint component 340 and thesecond bridge 330 is similar. However, as mentioned above the communication over thelink 370 is not compliant with the PCIe protocol. - In accordance with certain disclosed embodiments, a hot-plug process should be performed when the
link 370 transits from an operational state to an idle state (up/down) and vice versa. Theroot component 320 should receive a hot-plug indication on such events to inform the OS of the changes that occurred at the other end of the bus. The OS correctly handles the hot-plug events to avoid crashes in the computing device and the software which is associated with it. - The
second bridge 330 implements aconfiguration space 332 that includes the hot-plug registers (HPR). A configuration space includes a setting for performing auto configuration of an endpoint connected to a slot of a bridge. Each ofbridges - In accordance with an embodiment of the invention, the
configuration space 332 of thesecond bridge 330 is shadowed in theupstream bus unit 305. That is, an exact copy of theconfiguration space 332 is copied and saved in theupstream bus unit 305. The shadow configuration space in theupstream bus unit 305 is labeled as 332-S. Whenever the content of the configuration space 332-S and more specifically the status of the HPR is changed, a newer version of the shadow configuration space 332-S is saved in theupstream bus unit 305. In an embodiment of the invention, the shadow configuration space of 332-S is updated using a configuration write packet generated by thesecond bridge 330. This provides theroot component 320, and hence the OS an access the most updated configuration space of a device connected to theendpoint component 340. Thefirst bridge 310 also maintains itsconfiguration space 312. - When the
link 370 becomes unavailable or unreliable, and transmission over the link 370 (for example, due to high bit error rate) cannot be guaranteed, the shadow configuration space 332-S asserts a hot-plug interrupt indicating theendpoint component 340 has been removed. Further, theroot component 320 updates the HPR in configuration space 332-S on the status of the hot-plug events. The OS executed over the CPU accesses the HPR to read the hot-plug events and deallocates resources of a device connected to theendpoint component 340. For example, the values of the “presence detect status” and “presence detect changed” in the Slot Status Register is read. - It should be appreciated that as the OS can read status information from the shadowed configuration space 332-S, actions related to a card removal can be performed without any errors. Further, the OS always has a complete and updated status of the distributed PCIe bus. Without having the shadow configuration space 332-S, the OS would have tried accessing to the
second bridge 330 to write/read to the configuration space. However, as thelink 370 is idle such information would not be accessible. This would result in an OS error and a crash of the computing device. - When the
link 370 is reconnected and the PCIe connection is reestablished, it is considered a hot-plug event of a hot card insertion. In such an event, theupstream bus unit 305 copies the shadow configuration space 332-S to thebridge 330, updates the HPR in theconfiguration space 312 of thefirst bridge 310 and the shadow configuration space 332-S. In addition, the shadow configuration space 332-S asserts a hot-plug interrupt to the OS. Specifically, a signal is transferred from the configuration space 332-S to theroot component 320 through theupstream bus unit 305. It should be appreciated that copying the shadow configuration space 332-S provides coherency between the two bridges and allows the OS to resume communication with theendpoint component 340 without the need to reconfigure the fields of theconfiguration space 332 of thesecond bridge 330. - It should be noted that for the sake of simplicity and without limiting the scope of the invention, the operation of the hot-plug process has been described with a reference to an embodiment where only one endpoint component is connected to the
second bridge 330. The teachings of the invention are similar when multiple endpoint components are connected. In such an embodiment, the configuration space respective of each bridge that supports each endpoint component is shadowed to the shadow configuration space 332-S. -
FIG. 4 shows an exemplary andnon-limiting flowchart 400 illustrating the process of a hot-plug removal in a distributed PCIe bus in accordance with an embodiment of the invention. A hot-plug removal is performed when the data cannot be transferred over the link of the distributed medium (e.g., link 370). At S410, as long as the link is available, a second bridge (e.g., bridge 330) is connected to an endpoint of the distributed PCIe, and the configuration space of the second bridge is shadowed to anupstream bus unit 305 connected to theroot component 320. That is, the configuration space from the second bridge is copied to theupstream bus unit 305 forming a shadow configuration at theupstream bus unit 305 and any subsequent changes are written to the shadow configuration space. As mentioned above, the configuration space includes HPR that provide at least the bridge's slot status and capabilities. - At S420, a check is made to determine if data can be transferred over the link, i.e., if the link is available. In an embodiment of the invention, this check is performed by the root component. If S420 results with an affirmative answer, execution returns to S410; otherwise, execution continues with S430, where a hot-plug interrupt is asserted by the shadow configuration space 332-S. The interrupt indicates a hot card removal event. At S440, the HPR in the shadow configuration space 332-S is updated with the status of the hot-plug event. At S450, the OS performs a hot-plug removal process during which, the OS reads and writes to the shadow configuration space 332-S. The process executed by the OS is based on the type of the OS. For example, a hot-plug process performed by Windows based OS includes, in part, reading the hot-plug status bits from the Slot Status Register, requesting a plug-and-play system to eject the device connected to the endpoint, querying drivers for functions of the device, unloading the drivers of the device, writing to the shadow configuration space to turn off the device, and de-allocating resources used by driver(s).
- As can be understood from the above example, if the OS cannot access the configuration space of the second bridge, a system error would be generated. Thus, providing an updated shadow configuration space allows performing a hot-plug removal in a distributed PCIe bus.
-
FIG. 5 shows an exemplary andnon-limiting flowchart 500 illustrating the hot-plug insertion method in a distributed PCIe bus in accordance with an embodiment of the invention. The hot-plug insertion process is initiated when the data can be transferred over the link of the distributed medium (e.g., link 370), and the link is established. At S510, upon establishment of the distributed link, thesecond bridge 330 and theendpoint 340 connected thereon are reset. Then, at S520, execution waits for the initialization of the PCIe PHY and link layers of the second bridge and endpoint. - At S530, the shadow configuration space 332-S is copied from the
upstream bus unit 305 connected to the root to thesecond bridge 330. At S540, each bridge updates the HPR to represent a hot-plug insertion event. At S550, a hot-plug interrupt is asserted by the shadow configuration space 332-S informing the OS of the hot-plug event. To start the communication over the distributed PCIe bus, thebridges configuration space 332 of thesecond bridge 330 in order to identify the device connected to the endpoint and perform the proper initialization actions (e.g., memory allocation, driver loading, etc.), writing to configuration space at the second bridge to turn on the device, and asserting a message that communication with the device connected to the endpoint can start. - As can be understood from above example, the ability to provide an updated copy of the configuration space at the second bridge allows immediately establishing the distributed PCIe bus. Thus, there is no need to re-configure the configuration space at the second bridge according to the device specification. It should be noted that as the
process 500 is performed when the distributed link backs up, it is assumed that the device is still connected to the endpoint. - The various embodiments disclosed herein can be implemented as hardware, firmware, software or any combination thereof. Moreover, the software is preferably implemented as an application program tangibly embodied on a program storage unit, a non-transitory computer readable medium, or a non-transitory machine-readable storage medium that can be in a form of a digital circuit, an analogy circuit, a magnetic medium, or combination thereof. The application program may be uploaded to, and executed by, a machine comprising any suitable architecture. Preferably, the machine is implemented on a computer platform having hardware such as one or more central processing units (“CPUs”), a memory, and input/output interfaces. The computer platform may also include an operating system and microinstruction code. The various processes and functions described herein may be either part of the microinstruction code or part of the application program, or any combination thereof, which may be executed by a CPU, whether or not such computer or processor is explicitly shown. In addition, various other peripheral units may be connected to the computer platform such as an additional data storage unit and a printing unit. Furthermore, a non-transitory computer readable medium is any computer readable medium except for a transitory propagating signal.
- The foregoing detailed description has set forth a few of a few of the many forms that different embodiments of the invention can take. It is intended that the foregoing detailed description be understood as an illustration of selected forms that the invention can take and not as a limitation to the definition of the invention. It is only the claims, including all equivalents that are intended to define the scope of this invention.
Claims (22)
1. A method for performing a hot-plug removal process in a distributed peripheral component interconnect express (PCIe) bus, comprising:
receiving a hot-plug interrupt asserted by a shadow configuration space when a distributed link established over the distributed PCIe is unavailable, wherein the shadow configuration space is a copy of a configuration space of at least one endpoint component wirelessly connected to a host device over the distributed PCIe;
reading a hot-plug status from the shadow configuration space;
writing to the shadow configuration space to turn off at least one peripheral device connected to the at least one endpoint component; and
de-allocating resources allocated to a driver of the at least one peripheral.
2. The method of claim 1 , wherein the shadow configuration space is maintained in an upstream bus unit connected to a root component of the host device, wherein the configuration space is maintained in a downstream bus unit coupled to the at least one endpoint component, the upstream bus unit and the downstream bus unit communicate over the distributed link.
3. The method of claim 1 , wherein the configuration space includes at least hot-plug registers (HPR) specifying at least capabilities and status of at least one the downstream bus unit and the at least one endpoint component.
4. The method of claim 3 , wherein the hot-plug registers include at least a slot control register, a slot status register, and a slot capabilities register.
5. The method of claim 3 , wherein writing to the shadow configuration space includes writing to the hot-plug registers using a configuration write packet.
6. The method of claim 2 , wherein a new version of the configuration space is copied to the upstream bus unit upon any change in the configuration space.
7. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute the method of claim 1 .
8. A method for performing a hot-plug insertion process in a distributed peripheral component interconnect express (PCIe) bus, comprising:
receiving a hot-plug interrupt asserted by a shadow configuration space when a distributed link established over the distributed PCIe is available, the hot-plug interrupt informing on detection of a hot-plug insertion event;
reading a hot-plug status from a configuration space of at least one endpoint component wirelessly connected to a host device over the distributed PCIe, wherein the configuration space is a copy of the shadow configuration space updated to designate the hot-plug insertion event;
writing to the configuration space to turn on at least one peripheral device connected to the at least one endpoint component; and
asserting a message indicating that the host device and the at least one peripheral can communicate over the distributed PCIe bus.
9. The method of claim 8 , further comprising:
enumerating the distributed PCIe bus to include the at least one endpoint component.
10. The method of claim 8 , wherein the shadow configuration space is maintained in an upstream bus unit connected to a root component of the host device, wherein the configuration space is maintained in a downstream bus unit coupled to the at least one endpoint component, the upstream bus unit and the downstream bus unit communicate over the distributed link.
11. The method of claim 8 , wherein the configuration space includes at least hot-plug registers (HPR) specifying at least capabilities and status of at least one of the downstream bus unit and the at least one endpoint component.
12. The method of claim 3 , wherein the hot-plug registers include at least a slot control register, a slot status register, and a slot capabilities register.
13. The method of claim 8 , wherein writing to the configuration space includes writing to the hot-plug registers using a configuration write packet.
14. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute the method of claim 8 .
15. A wireless communication system, comprising:
a root component connected in a host device and directly coupled to an upstream bus unit, wherein the upstream bus unit is configured to maintain a first configuration space and a copy of a second configuration space, the first configuration space bridge includes at least hot-plug registers specifying at least capabilities and status of a slot of the upstream bus unit; and
at least one endpoint component connected to at least one peripheral device and directly coupled to a downstream bus unit that communicates with the host bridge over a distributed link established over a distributed peripheral component interconnect express (PCIe) bus, wherein the downstream bus unit is configured to maintain the second configuration space; the second configuration space includes at least hot-plug registers specifying at least capabilities and status of a slot of the downstream bus unit.
16. The wireless communication system of claim 15 , wherein when the distributed link status changes from available to unavailable a hot-plug removal event is triggered.
17. The wireless communication system of claim 16 , wherein the second configuration space is copied to the upstream bus unit when the link is available.
18. The wireless communication system of claim 17 , wherein the second configuration space in the downstream bus unit is updated with the hot-plug removal event.
19. The wireless communication system of claim 18 , wherein an operating system of the host device accesses the copy of the second configuration space in the upstream bus unit during a hot-plug removal process performed by the operating system.
20. The wireless communication system of claim 15 , wherein when the distributed link status changes from unavailable to available a hot-plug insertion event.
21. The wireless communication system of claim 20 , wherein the copy of the second configuration space is copied from the upstream bus unit to the downstream bus unit.
22. The wireless communication system of claim 21 , wherein the operating system accesses the second configuration space in the downstream bus unit during a hot-plug insertion process performed by the operating system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/891,861 US20130246680A1 (en) | 2010-09-22 | 2013-05-10 | Hot plug process in a distributed interconnect bus |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/887,833 US8443126B2 (en) | 2010-09-22 | 2010-09-22 | Hot plug process in a distributed interconnect bus |
US13/891,861 US20130246680A1 (en) | 2010-09-22 | 2013-05-10 | Hot plug process in a distributed interconnect bus |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/887,833 Continuation US8443126B2 (en) | 2010-09-22 | 2010-09-22 | Hot plug process in a distributed interconnect bus |
Publications (1)
Publication Number | Publication Date |
---|---|
US20130246680A1 true US20130246680A1 (en) | 2013-09-19 |
Family
ID=45818755
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/887,833 Active 2031-05-07 US8443126B2 (en) | 2010-09-22 | 2010-09-22 | Hot plug process in a distributed interconnect bus |
US13/891,861 Abandoned US20130246680A1 (en) | 2010-09-22 | 2013-05-10 | Hot plug process in a distributed interconnect bus |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/887,833 Active 2031-05-07 US8443126B2 (en) | 2010-09-22 | 2010-09-22 | Hot plug process in a distributed interconnect bus |
Country Status (1)
Country | Link |
---|---|
US (2) | US8443126B2 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017172195A1 (en) * | 2016-04-01 | 2017-10-05 | Intel Corporation | Method, apparatus, and system for plugin mechanism of computer extension bus |
CN107678994A (en) * | 2017-09-15 | 2018-02-09 | 华为技术有限公司 | PCIe device hot drawing method and device |
US10331605B2 (en) | 2016-08-30 | 2019-06-25 | International Business Machines Corporation | Dynamic re-allocation of signal lanes |
US20220276976A1 (en) * | 2013-06-28 | 2022-09-01 | Futurewei Technologies, Inc. | System and Method for Extended Peripheral Component Interconnect Express Fabrics |
Families Citing this family (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6718415B1 (en) | 1999-05-14 | 2004-04-06 | Acqis Technology, Inc. | Computer system and method including console housing multiple computer modules having independent processing units, mass storage devices, and graphics controllers |
US6643777B1 (en) | 1999-05-14 | 2003-11-04 | Acquis Technology, Inc. | Data security method and device for computer modules |
US8671153B1 (en) * | 2010-08-20 | 2014-03-11 | Acqis Llc | Low cost, high performance and high data throughput server blade |
US8782463B1 (en) | 2011-10-27 | 2014-07-15 | Seagate Technology Llc | Restoring a failed storage volume after removal of a storage device from an array |
US9665521B2 (en) | 2012-05-18 | 2017-05-30 | Dell Products, Lp | System and method for providing a processing node with input/output functionality by an I/O complex switch |
JP6089835B2 (en) * | 2013-03-19 | 2017-03-08 | 富士通株式会社 | Information processing apparatus and control method |
WO2014186938A1 (en) | 2013-05-20 | 2014-11-27 | 华为技术有限公司 | Computer system, access method and apparatus for peripheral component interconnect express endpoint devices |
US9582366B2 (en) | 2014-11-21 | 2017-02-28 | International Business Machines Corporation | Detecting and sparing of optical PCIE cable channel attached IO drawer |
US9697155B2 (en) | 2014-11-21 | 2017-07-04 | International Business Machines Corporation | Detecting and configuring of external IO enclosure |
US10229085B2 (en) | 2015-01-23 | 2019-03-12 | Hewlett Packard Enterprise Development Lp | Fibre channel hardware card port assignment and management method for port names |
WO2017007388A1 (en) * | 2015-07-09 | 2017-01-12 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and host node for configuring a remote node and a host node |
US10212754B2 (en) | 2015-08-12 | 2019-02-19 | Nxp Usa, Inc. | System and method for radio base station device hot reconnection (hot plugging) |
US10158525B2 (en) | 2015-08-12 | 2018-12-18 | Nxp Usa, Inc. | System and method for radio base station device hot switching and hot swapping |
US10394586B2 (en) * | 2015-08-13 | 2019-08-27 | Red Hat Israel, Ltd. | Using capability indicators to indicate support for guest driven surprise removal of virtual PCI devices |
US10122386B2 (en) | 2015-12-15 | 2018-11-06 | Nxp Usa, Inc. | System and method for on-the-fly modification of the properties on an active antenna carrier in radio base station communication operation |
US9979600B2 (en) | 2015-12-15 | 2018-05-22 | Nxp Usa, Inc. | System and method for automatic load adaptive antenna carrier bandwidth dynamic reconfiguration in radio base station system |
US10178641B2 (en) | 2016-01-04 | 2019-01-08 | Nxp Usa, Inc. | System and method for automatic delay compensation in a radio base station system |
CN105701051B (en) * | 2016-01-15 | 2019-10-15 | 华为技术有限公司 | A kind of hot-plug method, host controller, host and PCIe bridge device |
CN107038137B (en) | 2016-02-04 | 2020-04-28 | 华为技术有限公司 | Hot-plug equipment and method |
US10223318B2 (en) | 2017-05-31 | 2019-03-05 | Hewlett Packard Enterprise Development Lp | Hot plugging peripheral connected interface express (PCIe) cards |
US10254821B2 (en) * | 2017-08-01 | 2019-04-09 | Intel Corporation | Managing surprise hot plug in low power state |
US10853299B2 (en) * | 2017-09-15 | 2020-12-01 | Dell Products L.P. | Hot-plugged PCIe device configuration system |
CN108345566A (en) * | 2018-01-31 | 2018-07-31 | 郑州云海信息技术有限公司 | A kind of makeup of ponds PCIE is set and its design method |
US10445279B1 (en) | 2018-07-19 | 2019-10-15 | Mellanox Technologies, Ltd. | Automatic PCIe operating mode configuration |
US10503682B1 (en) | 2018-12-19 | 2019-12-10 | Mellanox Technologies, Ltd. | Accessing PCIe configuration data through network |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7058738B2 (en) * | 2004-04-28 | 2006-06-06 | Microsoft Corporation | Configurable PCI express switch which allows multiple CPUs to be connected to multiple I/O devices |
US7257659B2 (en) * | 2003-12-31 | 2007-08-14 | Intel Corporation | Method for signaling PCI/PCI-X standard hot-plug controller (SHPC) command status |
US7535254B1 (en) * | 2007-05-14 | 2009-05-19 | Xilinx, Inc. | Reconfiguration of a hard macro via configuration registers |
US7552242B2 (en) * | 2004-12-03 | 2009-06-23 | Intel Corporation | Integrated circuit having processor and switch capabilities |
US20090292854A1 (en) * | 2008-05-22 | 2009-11-26 | Khoo Ken | Use of bond option to alternate between pci configuration space |
US7689751B2 (en) * | 2008-02-15 | 2010-03-30 | Sun Microsystems, Inc. | PCI-express system |
US20100257400A1 (en) * | 2009-03-18 | 2010-10-07 | Colin Whitby-Strevens | Network loop healing apparatus and methods |
US8050290B2 (en) * | 2007-05-16 | 2011-11-01 | Wilocity, Ltd. | Wireless peripheral interconnect bus |
US8374157B2 (en) * | 2007-02-12 | 2013-02-12 | Wilocity, Ltd. | Wireless docking station |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7447822B2 (en) | 2005-12-12 | 2008-11-04 | Inventec Corporation | Hot-plug control system and method |
US20070271404A1 (en) * | 2006-05-16 | 2007-11-22 | Sun Microsystems, Inc. | Realtime multithreaded hot-plug control |
TW200801952A (en) * | 2006-06-02 | 2008-01-01 | Via Tech Inc | Method for setting up a peripheral component interconnect express (PCIE) |
US7475178B2 (en) * | 2006-08-18 | 2009-01-06 | Sun Microsystems, Inc. | Hot-plug link apparatus and method using a direction line to indicate presence of a hot-plug device |
CN101211323B (en) * | 2006-12-28 | 2011-06-22 | 联想(北京)有限公司 | Hardware interruption processing method and processing unit |
JP4429331B2 (en) * | 2007-03-08 | 2010-03-10 | エヌイーシーコンピュータテクノ株式会社 | Mode setting method in hot plug of PCI device and system having PCI bus |
US20080307143A1 (en) | 2007-06-11 | 2008-12-11 | Sunix Co., Ltd. | Modularized (block) channel technology with expansion of different to output interfaces |
US9075926B2 (en) | 2007-07-19 | 2015-07-07 | Qualcomm Incorporated | Distributed interconnect bus apparatus |
US7603500B2 (en) * | 2007-08-10 | 2009-10-13 | Dell Products L.P. | System and method for allowing coexistence of multiple PCI managers in a PCI express system |
JP5645014B2 (en) * | 2008-05-28 | 2014-12-24 | 日本電気株式会社 | I / O connection system, method and program |
US20110072168A1 (en) * | 2009-09-24 | 2011-03-24 | Hongxiao Zhao | Data transfer system with different operating modes |
US20110145655A1 (en) * | 2009-12-11 | 2011-06-16 | Mike Erickson | Input/output hub to input/output device communication |
-
2010
- 2010-09-22 US US12/887,833 patent/US8443126B2/en active Active
-
2013
- 2013-05-10 US US13/891,861 patent/US20130246680A1/en not_active Abandoned
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7257659B2 (en) * | 2003-12-31 | 2007-08-14 | Intel Corporation | Method for signaling PCI/PCI-X standard hot-plug controller (SHPC) command status |
US7058738B2 (en) * | 2004-04-28 | 2006-06-06 | Microsoft Corporation | Configurable PCI express switch which allows multiple CPUs to be connected to multiple I/O devices |
US7552242B2 (en) * | 2004-12-03 | 2009-06-23 | Intel Corporation | Integrated circuit having processor and switch capabilities |
US8374157B2 (en) * | 2007-02-12 | 2013-02-12 | Wilocity, Ltd. | Wireless docking station |
US7535254B1 (en) * | 2007-05-14 | 2009-05-19 | Xilinx, Inc. | Reconfiguration of a hard macro via configuration registers |
US8050290B2 (en) * | 2007-05-16 | 2011-11-01 | Wilocity, Ltd. | Wireless peripheral interconnect bus |
US7689751B2 (en) * | 2008-02-15 | 2010-03-30 | Sun Microsystems, Inc. | PCI-express system |
US20090292854A1 (en) * | 2008-05-22 | 2009-11-26 | Khoo Ken | Use of bond option to alternate between pci configuration space |
US20100257400A1 (en) * | 2009-03-18 | 2010-10-07 | Colin Whitby-Strevens | Network loop healing apparatus and methods |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220276976A1 (en) * | 2013-06-28 | 2022-09-01 | Futurewei Technologies, Inc. | System and Method for Extended Peripheral Component Interconnect Express Fabrics |
US11954058B2 (en) * | 2013-06-28 | 2024-04-09 | Futurewei Technologies, Inc. | System and method for extended peripheral component interconnect express fabrics |
WO2017172195A1 (en) * | 2016-04-01 | 2017-10-05 | Intel Corporation | Method, apparatus, and system for plugin mechanism of computer extension bus |
US9953001B2 (en) | 2016-04-01 | 2018-04-24 | Intel Corporation | Method, apparatus, and system for plugin mechanism of computer extension bus |
US10331605B2 (en) | 2016-08-30 | 2019-06-25 | International Business Machines Corporation | Dynamic re-allocation of signal lanes |
CN107678994A (en) * | 2017-09-15 | 2018-02-09 | 华为技术有限公司 | PCIe device hot drawing method and device |
Also Published As
Publication number | Publication date |
---|---|
US8443126B2 (en) | 2013-05-14 |
US20120072633A1 (en) | 2012-03-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8443126B2 (en) | Hot plug process in a distributed interconnect bus | |
US7945721B1 (en) | Flexible control and/or status register configuration | |
US8135873B2 (en) | Information processing device for performing information exchange between a PCI express bus and a non-PCI express bus interface | |
CN106209695B (en) | Providing low power physical units for load/store communication protocols | |
US9396152B2 (en) | Device, system and method for communication with heterogenous physical layers | |
US7610431B1 (en) | Configuration space compaction | |
US20140108697A1 (en) | Controlling A Physical Link Of A First Protocol Using An Extended Capability Structure Of A Second Protocol | |
US7752376B1 (en) | Flexible configuration space | |
US20080005311A1 (en) | Disk initiated asynchronous event notification | |
Bhatt | Creating a third generation I/O interconnect | |
JP4837659B2 (en) | Bus controller for processing split transactions | |
US8291146B2 (en) | System and method for accessing resources of a PCI express compliant device | |
KR102420530B1 (en) | Alternative protocol selection | |
CN112639753B (en) | Aggregated inband interruption | |
EP3722963B1 (en) | System, apparatus and method for bulk register accesses in a processor | |
US10853289B2 (en) | System, apparatus and method for hardware-based bi-directional communication via reliable high performance half-duplex link | |
US20150269109A1 (en) | Method, apparatus and system for single-ended communication of transaction layer packets | |
WO2005060688A2 (en) | Serial communication device configurable to operate in root mode or endpoint mode | |
WO2017160397A1 (en) | A method, apparatus and system to send transactions without tracking | |
EP3087454A1 (en) | Input output data alignment | |
US9639076B2 (en) | Switch device, information processing device, and control method of information processing device | |
US11797468B2 (en) | Peripheral component interconnect express device and computing system including the same | |
Verma et al. | Pcie bus: A state-of-the-art-review | |
US7577877B2 (en) | Mechanisms to prevent undesirable bus behavior | |
US20230315591A1 (en) | PCIe DEVICE AND COMPUTING SYSTEM INCLUDING THE SAME |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: QUALCOMM ATHEROS, INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:WILOCITY LTD.;REEL/FRAME:033521/0593 Effective date: 20140707 Owner name: QUALCOMM INCORPORATED, CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:QUALCOMM ATHEROS, INC.;REEL/FRAME:033521/0834 Effective date: 20140801 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |