# US 2022/0035673 A1 · Memory allocator for i/o operations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0035673 A1 - Document ID: US20220035673A1 - Status: Published application - Kind: A1 - Application number: 17/085,893 - Filed: 2020-10-30 - Published: 2022-02-03 - Earliest claimed: 2020-07-30 - Assignees: VMware, Inc. - Applicants: VMware, Inc. - Inventors: Alex Markuze; Chen Dar; Aran Bergman; Igor Golikov; Israel Cidon; Eyal Zohar - Web page: https://patentgrep.com/patent/US20220035673A1 ## CPC - G06F 9/5016: {the resource being the memory} - G06F 9/544: {Buffers; Shared memory; Pipes} - G06F 12/10: Address translation - H04L 47/193: at the transport layer, e.g. TCP related - H04L 47/30: in combination with information about buffer occupancy at either end or at transit nodes - H04L 49/30: {Peripheral units, e.g. input or output ports} - H04L 49/9089: {replacing packets in a storage arrangement, e.g. pushout} - H04L 69/162: {involving adaptations of sockets based mechanisms (secure socket layer H04L63/168)} - G06F 2209/5011: Pool - G06F 2212/657: Virtual address space management - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Some embodiments provide a novel method for sharing data between user-space processes and kernel-space processes without copying the data. The method dedicates, by a driver of a network interface controller (NIC), a memory address space for a user-space process. The method allocates a virtual region of the memory address space for zero-copy operations. The method maps the virtual region to a memory address space of the kernel. The method allows access to the virtual region by both the user-space process and a kernel-space process. ## Claims ### Claim 1 A method of sharing data between user-space processes and kernel-space processes without copying the data, the method comprising: dedicating, by a driver of a network interface controller (NIC), a memory address space for a user-space process; allocating a virtual region of the memory address space of the user-space process for zero-copy operations; mapping the virtual region to a memory address space of the kernel; and allowing access to the virtual region by both the user-space process and a kernel-space process. ### Claim 2 (depends on 1) The method of claim 1, wherein access to the virtual region is limited to a single user. ### Claim 3 (depends on 1) The method of claim 1, wherein the allocated virtual region implements a dedicated receiving (RX) ring accessible by the network interface controller (NIC). ### Claim 4 (depends on 3) The method of claim 3, wherein the dedicated RX ring is limited to a single tuple. ### Claim 5 (depends on 3) The method of claim 3, wherein the dedicated RX ring is limited to a defined group of tuples. ### Claim 6 (depends on 1) The method of claim 1, wherein the allocated virtual region implements a dedicated transmission (TX) ring accessible by network interface controller (NIC). ### Claim 7 (depends on 6) The method of claim 6, wherein the dedicated TX ring is limited to a single tuple. ### Claim 8 (depends on 6) The method of claim 6, wherein the dedicated TX ring is limited to a defined group of tuples. ### Claim 9 (depends on 1) The method of claim 1 further comprising, the user-space process identifying virtual memory allocated to zero-copy operations to be deallocated. ### Claim 10 (depends on 1) The method of claim 1, wherein, when the amount of memory allocated by the user-space process is more than a threshold amount, the kernel-space process deallocates at least part of the memory allocated by the user-space process. ### Claim 11 (depends on 1) The method of claim 1, wherein, when the amount of memory allocated by the user-space process is more than a threshold amount, the kernel-space process prevents the user-space process from allocating more memory. ### Claim 12 (depends on 1) The method of claim 1, wherein the kernel-space process is a guest kernel-space process on a guest virtual machine operating on a host machine, the method further comprising additionally allowing access to the virtual region by a user-space process of the host machine. ### Claim 13 (depends on 1) The method of claim 1, wherein the kernel-space process is a guest kernel-space process on a guest virtual machine operating on a host machine, the method further comprising additionally allowing access to the virtual region by a kernel-space process of the host. ### Claim 14 (depends on 1) The method of claim 1, wherein the NIC driver dedicates the memory using an application device queue (ADQ). ### Claim 15 A non-transitory machine readable medium storing a program which when executed by at least one processing unit implements sharing of data between user-space processes and kernel-space processes without copying the data, the program comprising sets of instructions for: dedicating, by a driver of a network interface controller (NIC), a memory address space for a user-space process; allocating a virtual region of the memory address space for zero-copy operations; mapping the virtual region to a memory address space of the kernel; and allowing access to the virtual region by both the user-space process and a kernel-space process. ### Claim 16 (depends on 15) The non-transitory machine readable medium of claim 15, wherein access to the virtual region is limited to a single user. ### Claim 17 (depends on 15) The non-transitory machine readable medium of claim 15, wherein the allocated virtual region implements a dedicated receiving (RX) ring accessible by the network interface controller (NIC). ### Claim 18 (depends on 17) The non-transitory machine readable medium of claim 17, wherein the dedicated RX ring is limited to a defined group of tuples. ### Claim 19 (depends on 15) The non-transitory machine readable medium of claim 15, wherein the allocated virtual region implements a dedicated transmission (TX) ring accessible by network interface controller (NIC). ### Claim 20 (depends on 19) The non-transitory machine readable medium of claim 19, wherein the dedicated TX ring is limited to a defined group of tuples.