DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-20 are pending.
Response to Arguments
Regarding: Prior Art Rejections:
Applicant’s amendments and arguments regarding the rejection of claims 1-20 under 35 U.S.C. 103 have been fully considered but are moot due to new grounds of rejection necessitated by amendment.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3, 5, 6, and 12-20 are rejected under 35 U.S.C. 103 as being unpatentable over Jain et al. US 20180349161 A1 in view of Abe US 7472205 B2 in view of Tsirkin et al. US 20150040124 A1 in view of Kumar et al. US 8429276 B1.
Jain, Tsirkin, and Kumar are cited in a previous office action
Regarding claim 1, Jain teaches the invention substantially as claimed including:
A computing device comprising:
a memory configured to store instructions and a processor coupled to the memory and configured to execute the instructions to cause the computing device to ([0022] Memory 126 may comprise a hard disk, a floppy disk, random access memory (RAM), read only memory (ROM), flash memory, any other type of volatile memory devices or non-volatile memory devices, or combination of the above devices, or any other type of machine medium readable by processor 122 … Memory 126 may store instructions and/or data for performing program execution):
execute a virtual machine manager (VMM) that implements a physical function (PF) driver corresponding to an input/output I/O device ([0014] The PCIe PF is a primary function of a device and advertises the device's SR-IOV capabilities … a PCIe PF may be associated with a hypervisor or virtual machine manager (VMM)) and to a plurality of virtual function (VF) drivers implemented by a plurality of virtual machines (VMs) ([0014] Another PCIe hardware function may include one or more PCIe Virtual Functions (VFs). In various embodiments, a VF may be associated with a device's PF. A VF may share one or more physical resources of the device, such as a memory and a network port, with the PF and other VFs on the device. In some embodiments, a VF may be associated with a VMM (for instance, Hyper-V child partition) in a virtualized environment; [0025] Each of VMs 210a-n may include at least one VF driver 212a-212n));
receive, at the PF driver, at least one first message from a first VF driver of a first VM of the VMs (Fig 4 Adaptive VF 420a -> PF 440a), wherein the at least one first message comprises a dynamic message format that supports carrying at least the first two of a first dynamic indication, wherein the first dynamic indication denotes a first number of a plurality of capabilities ([0038] The adaptive VF driver may send down the capabilities it would like to enable), and wherein the at least one first message comprises a set of requested capabilities supported by the VF driver for enablement on or by the I/O device ([0038] an adaptive VF driver may initiate communication with a PF to request and/or query the resources available to it and the capabilities it can support; [0039] an adaptive VF driver may attempt to negotiate with a PF for advanced capabilities beyond the standard feature set that it can support. In this manner, if the PF is unable to support advanced capability, the adaptive VF driver can still continue to work with the standard feature set. If the PF can support the advanced features then the adaptive VF driver may selectively enable them);
transmit at least one second message from the PF driver to the VF driver, wherein the at least one second message comprises a set of supported capabilities selected from the set of requested capabilities, wherein the set of supported capabilities are capabilities supported by the I/O device and PF driver ([0038] If the adaptive VF driver is an older version and the PF supports additional capabilities, then the adaptive VF driver still gets the standard feature set of capabilities that it requested … If the adaptive VF driver is a newer driver and the underlying hardware can support only a subset of the capabilities the adaptive VF driver can support, the PF may only enable the standard feature set, thereby allowing the adaptive VF driver to run on the older PF and hardware); and
enable the set of supported capabilities for use by the VF driver (Fig 5 508 Activate Standard Feature Set, 512 Activate Advanced Feature Set).
Jain does not explicitly teach wherein the at least one first message comprises a dynamic message format that supports carrying at least the first two of a first dynamic indication, a plurality of second dynamic indications, and a plurality of third dynamic indications, wherein the first dynamic indication denotes a first number of a plurality of capabilities, wherein each second dynamic indication in the plurality of second dynamic indications is associated with one respective capability in the plurality of capabilities, wherein each respective dynamic second indication denotes a size of data stored in the respective message that is associated with the corresponding respective capability.
However, Abe teaches wherein the at least one first message comprises a dynamic message format that supports carrying at least the first two of a first dynamic indication, a plurality of second dynamic indications (Fig 3; The descriptors represent the address and size of a receive buffer in the host. Typically, descriptors take the form of a chain. The communication controller follows the descriptor chain to read descriptors to perform communication processing, Col 1 24-29; The descriptor consists of a done bit 200 indicating to the host that the descriptor is consumed, a control code section 201 for setting attributes of the descriptor, a next descriptor address 202 which is the address pointer to the next descriptor in a descriptor chain, and a plurality of pairs of a buffer address indicating an address of a location in which a received packet is stored if this is a receive descriptor, or a location in which data to be sent as a packet is stored if this is a send descriptor, and a buffer size, Col 6 14-22), and a plurality of third dynamic indications, wherein the first dynamic indication denotes a first number of a plurality of capabilities (The host CPU 10 signals a request to send by means of Doorbell. In practice, it writes in send Doorbell register in the I/O bus controller 101 a connection number, the address of a location in the host memory 40.in which the leading descriptor of a descriptor chain is stored, and the number of descriptors in the chain, Col 12 34-39), wherein each second dynamic indication in the plurality of second dynamic indications is associated with one respective capability in the plurality of capabilities, wherein each respective dynamic second indication denotes a size of data stored in the respective message that is associated with the corresponding respective capability (a plurality of pairs of a buffer address indicating an address of a location in which a received packet is stored if this is a receive descriptor, or a location in which data to be sent as a packet is stored if this is a send descriptor, and a buffer size, Col 6 18-22).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to have combined Abe’s DMA descriptor chain messaging structure with the existing system. A person of ordinary skill in the art would have been motivated to make this combination to provide the resulting system with the advantage of efficient messaging between a machine and network (see Abe Col 43-47, An object of the present invention is to provide a communication controller and a communication control method that can reduce descriptor control overhead in a network processor unit by eliminating the need for the network processor unit to scan a chain of descriptors scattered over a host memory).
Jain and Abe do not explicitly teach the dynamic message format comprising a plurality of second dynamic indications, wherein each second dynamic indication in the plurality of second dynamic indications is associated with one respective capability in the plurality of capabilities, wherein each respective dynamic second indication denotes a size of data stored in the respective message that is associated with the corresponding respective capability, and a plurality of third dynamic indications, wherein each respective third dynamic indication denotes a version of the corresponding respective capability.
However, Tsirkin teaches the dynamic message format comprising a plurality of second dynamic indications, wherein each second dynamic indication in the plurality of second dynamic indications is associated with one respective capability in the plurality of capabilities, wherein each respective dynamic second indication denotes a size of data stored in the respective message that is associated with the corresponding respective capability ([0018] capability identifier assigned to the hypervisor may comprise at least one of the size of the capability data structure; Examiner notes: for every capability identifier requested by the guest virtual driver, each capability correlates to a size of its capability data structure), and
a plurality of third dynamic indications, wherein each respective third dynamic indication denotes a version of the corresponding respective capability ([0018] capability identifier assigned to the hypervisor may comprise at least one of … a version of the capability; Examiner notes: for every capability requested by the guest virtual driver, each capability identifier is able to specify a version of the capability to request).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to have combined Tsirkin’s capability message formatting with the system of Jain. A person of ordinary skill in the art would have been motivated to make this combination to provide Jain and Abe’s system with the advantage of establishing a clear communication channel between VM drivers and physical devices reducing overhead associated with virtualization (see Tsirkin [0019] an efficient method and system is provided that enables a hypervisor to have a communication channel with a guest driver associated with the device, while permitting the guest driver direct access to a device for programming of capabilities associated with the device with low overhead).
Jain, Abe, and Tsirkin do not explicitly teach wherein a size of the dynamic message format is adapted to change to any size needed to define any number of supported capabilities.
However, Kumar teaches wherein a size of the dynamic message format is adapted to change to any size needed to define any number of supported capabilities (while described above with respect to a certain message format, this message format may be expanded to incorporate other fields to accommodate certain functions pertinent to dynamic VM-initiated physical resource reallocation, Col 16 43-47).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to have combined Kumar’s expanding message format with the system of Jain and Tsirkin. A person of ordinary skill in the art would have been motivated to make this combination to provide Jain and Tsirkin’s system with the advantage of adjusting message formats to fit whichever format is required to provision physical capabilities (see Kumar Col 16 this message format may be expanded to incorporate other fields to accommodate certain functions pertinent to dynamic VM-initiated physical resource reallocation).
Regarding claim 2, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain further teaches wherein each one of the plurality of capabilities defined by the dynamic message format is configured to be independently and sequentially processed until the first number of the plurality of capabilities is reached ([0038] If the adaptive VF driver is an older version and the PF supports additional capabilities, then the adaptive VF driver still gets the standard feature set of capabilities that it requested; Examiner notes: the PF needs to check each capability requested by the VF driver to determine if there is support for the capability).
Regarding claim 3, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 2.
Jain further teaches wherein the processor is further configured to execute the instructions to cause the computing device to poll for additional first messages when capabilities defined in received first messages have been processed and a second number of the processed capabilities is less than the first number of capabilities ([0036] With the mailbox mechanism, an adaptive VF driver may be configured for various needs, such as a simple network interface, or a trusted interface that can configure multiple filtering rules and can get access to programming other hardware resources … policies for enabling VF features may be controlled or otherwise managed via the PF and the VMM or hypervisor (for instance, via a hypervisor administrator). In this manner, the adaptive VF driver still remains a dependent driver but can grow to expose an extremely powerful device depending on the policy enforced in the VMM or hypervisor).
Regarding claim 5, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Kumar further teaches wherein the dynamic message format is based on a type-length-value (TLV) format when the dynamic message format of the at least one first message carries just the first dynamic indication and the plurality of second dynamic indications, wherein the type comprises an opcode denoting that the respective message is a capabilities message, wherein the length denotes the first dynamic indication, and wherein the value denotes a second dynamic indication and corresponding capabilities data (This message 80 is formatted in a standard type-length-value (TLV) format. Message 80 may include additional fields not shown in the example of FIG. 5, Col 15 32-35).
Regarding claim 6, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain further teaches wherein the at least one message comprises a plurality of messages, wherein the first indication of the dynamic message format denotes a total number of capabilities included in the plurality of messages, and wherein the dynamic message format further comprises a fourth dynamic indication denoting a second number of capabilities of the total number of capabilities of the first dynamic indication that are included in the respective message ([0038] An advanced feature set may include features in addition to the standard feature set. In some embodiments, features of the advanced feature set may be negotiated with the PF driver specific to the hardware … If the adaptive VF driver is a newer driver and the underlying hardware can support only a subset of the capabilities the adaptive VF driver can support, the PF may only enable the standard feature set, thereby allowing the adaptive VF driver to run on the older PF and hardware; Examiner notes: included in the VF request is a total number of requested capabilities in which a portion of the total number includes advanced feature capabilities).
Regarding claim 12, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain further teaches wherein the dynamic message format further supports carrying a fifth dynamic indication denoting an overall version of a package of the plurality of capabilities included in the at least one first message ([0032] Most I/O devices that expose a virtual function device in a VM typically use a unique device ID to identify the type of hardware from which the virtual device is derived (for example, SR-IOV devices 230a-n). In order to facilitate an adaptive VF driver operating on newer hardware from the same vendor, hardware may advertise the same (or similar) virtual function device ID on current and future versions of these devices).
Regarding claim 13, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain further teaches wherein the VF driver is implemented as an adaptive VF (AVF) and/or assignable device interface (ADI) ([0028] an adaptive VF driver, such as one or more of VF drivers 212a-n, may be operative to facilitate forward compatibility with hardware and/or software upgrades), wherein a plurality of instances of the AVF and/or ADI are implemented on the plurality of VMs (Fig 4 VM’s 410, AVF’s 420), wherein the plurality of instances of the AVF and/or ADI are mapped to a single common PF driver, and wherein the plurality of instances of the AVF and/or ADI are concurrently adapted (Fig 2 PF Drivers 222 controlling Physical Functions 240 corresponding to VF Functions 232; [0025] Each of VMs 210a-n may include at least one VF driver 212a-212n that interact with respective virtual functions 232a-232n that are implemented, for instance, in SR-IOV devices 230a-n. In some embodiments, at least a portion of VF drivers 212a-n may include adaptive VF drivers. Physical functions (PF) may be implemented using PF drivers 222a-n in VMM 220, which interact with PFs 240a-n in SR-IOV devices 230a-n).
Regarding claim 14, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain further teaches wherein the processor is further configured to execute the instructions to cause the computing device to: enable a base mode including a set of basic capabilities on the PF driver and the I/O device for use by the VF driver (; and receive, in response to the enabled base mode, the at least one first message for enablement of advanced capabilities ([0039] an adaptive VF driver may attempt to negotiate with a PF for advanced capabilities beyond the standard feature set that it can support. In this manner, if the PF is unable to support advanced capability, the adaptive VF driver can still continue to work with the standard feature set. If the PF can support the advanced features then the adaptive VF driver may selectively enable them).
Regarding claim 15, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain teaches wherein the processor is further configured to execute the instructions to cause the computing device to receive, at the PF driver, at least one third message from the VF driver, wherein the at least one third message is formatted according to the dynamic message format, and wherein the at least one third message comprises a set of enabled capabilities selected from the set of supported capabilities for enablement by the I/O device and the PF driver ([0042] a virtual channel may be supported with capability negotiation between PF and VF driver on top of the hardware mailbox. This can be expanded with more capabilities depending on use-case and to preserve the base capabilities that all PFs and VFs must support such as single layer checksum, TSO, RSS, and/or the like; [0051] an adaptive VF driver may initiate communication with a PF to request and/or query the resources available to it and the capabilities it can support; Examiner notes: negotiation between VF driver and PF driver indicates elections are made on both ends, VF driver queries the PF driver for supported capabilities, PF driver responds by providing supported capabilities, VF driver makes selection out of supported capabilities. All negotiation can be done using the same message format).
Regarding claim 16, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain further teaches wherein the at least one second message is formatted according to the dynamic message format (Examiner notes: it would be trivial for the PF driver to respond to the VF driver’s query using the same format as the response message would merely include the capabilities that are supported by the PF driver and associated I/O device.
Regarding claims 17 and 18, they are the methods of claims 1 and 12 respectively. Therefore, they are rejected for the same reasons as claims 1 and 12 respectively.
Regarding claim 19, it is the computer program product of claim 1 without limitation: execute a virtual machine manager (VMM) that implements a physical function (PF) driver corresponding to an input/output 1/O device and to a plurality of virtual function (VF) drivers implemented by a plurality of virtual machines (VMs). Therefore, it is rejected for the same reasons as claim 1.
Jain further teaches a computer program product comprising a non-transitory storage medium storing program code, the program code comprising instructions, which when executed using a processor of a computer cause the computer to ([0062] instructions stored on a machine-readable medium which represents various logic within the processor, which when read by a machine causes the machine to fabricate logic to perform the techniques described herein).
Regarding claim 20, it is the computer program product of claim 1. Therefore, it is rejected for the same reasons as claim 1.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Jain et al. US 20180349161 A1 in view of Abe US 7472205 B2 in view of Tsirkin et al. US 20150040124 A1 in view of Kumar et al. US 8429276 B1 in further view of Batman (open-mesh NPL).
Batman is cited in a previous office action
Regarding claim 4, Jain, Abe, Tsirkin, and Kumar teach the computing device of claim 1.
Jain, Tsirkin, and Kumar do not explicitly teach wherein the dynamic message format is based on a type-version- length-value (TVLV) format, wherein the type comprises an opcode denoting that the respective message is a capabilities message, wherein the version denotes a third dynamic indication, wherein the length denotes the first dynamic indication, and wherein the value denotes a second dynamic indication and corresponding capabilities data.
However, Batman teaches wherein the dynamic message format is based on a type-version- length-value (TVLV) format when the dynamic message format of the at least one first message carries the first dynamic indication, the plurality of second dynamic indications, and the plurality of third dynamic indications, wherein the type comprises an opcode denoting that the respective message is a capabilities message, wherein the version denotes a third dynamic indication, wherein the length denotes the first dynamic indication, and wherein the value denotes a second dynamic indication and corresponding capabilities data.
PNG
media_image1.png
496
728
media_image1.png
Greyscale
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to have combined Batman’s TVLV message format with the system of Jain, Abe, Tsirkin, and Kumar. A person of ordinary skill in the art would have been motivated to make this combination to provide Jain, Tsirkin, and Kumar’s system with the advantage of standardizing requests fields over a network (see Batman TVLV Concept: provide the infrastructure for sending, receiving and parsing information 'containers' while preserving backward compatibility. TVLV (based on the commonly known Type Length Value technique) was chosen as the format for those containers).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Jain et al. US 20180349161 A1 in view of Abe US 7472205 B2 Tsirkin et al. US 20150040124 A1 in view of Kumar et al. US 8429276 B1 in further view of Heideman et al. US 7873868 B1.
Heideman is cited in a previous office action
Regarding claim 9, Jain, Tsirkin, and Kumar teach the computing device of claim 1.
Tsirkin teaches wherein the dynamic message format further comprises an opcode denoting a capabilities message (Fig 1 Capability ID)
Jain, Tsirkin, and Kumar do not explicitly teach an indication selected from a group consisting of a first message, a middle message, a last message, and an only message .
However, Heideman teaches an indication selected from a group consisting of an initial message of the at least one first message, a middle message of the at least one first message, a last message of the at least one first message, and an only message of the at least one first message (Because PRP Packet 204 is the first packet in the list, Previous PRP is set to null, Col 10 63-64; The last 32-bit word of the fixed length SRR header 88 contains Last Packet Flag 102, which indicates that the current packet is the last packet of an audit sequence and Packet Number 104. If Last Packet Flag 102 is set and Packet Number 104 is equal to 1, the current SRR packet is the only packet in the audit sequence, Col 9 12-17; Examiner notes: if there is no previous PRP then the packet is the first packet, else if there is a previous PRP and last packet flag is 0 then the packet is a middle packet, else if last packet flag is 1, then the packet is the last packet, else if last packet flag is 1 and packet number is 1, then the packet is an only packet).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to have combined Pan’s with the system of Jain, Tsirkin, and Kumar. A person of ordinary skill in the art would have been motivated to make this combination to provide Jain, Tsirkin, and Kumar’s system with the advantage of providing a system auditor insight on packet ordering in an auditing sequence (see Heideman Col 8 62 Though the SRR packets are primarily used to convey audit data from master to slave, they are also used to implement the master/slave control functions. The first 48 words contain Descriptor 86. This is followed by Header 88. A number of control entries (i.e., Control Entry #1 90, Control Entry #2 92, Control Entry #3 93, and Control Entry #4 94) provide the actual control information. Each of the control entries has a variable length depending upon the function to be performed, as explained below).
Allowable Subject Matter
Claims 7, 8, 10, and 11 objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the
examiner should be directed to HARRISON LI whose telephone number is (703) 756-1469. The
examiner can normally be reached Monday-Friday 9:00am-5:30pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing
using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is
encouraged to use the USPTO Automated Interview Request (AIR) at
http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s
supervisor, Aimee Li can be reached on (571) 272-4169. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/H.L./
Examiner, Art Unit 2195
/Aimee Li/Supervisory Patent Examiner, Art Unit 2195
Prosecution Insights