Red Hat Israel, Ltd.

Red Hat, Inc.

Gal Hammer

Marcel Apfelbaum

Michael Tsirkin

Yuval Kashtan

A device attachment request to attach a device to a container within a virtual machine is received. The virtual machine is monitored to determine whether the virtual machine is ready for a hot-plug of the device. An indication that the virtual machine is ready for the hot-plug of the device is received from the virtual machine. A device hot-plug operation is issued to cause the device to be hot-plugged to the virtual machine.

Reliable device assignment for virtual machine based containers

The technology disclosed herein enables an operating system kernel to schedule and perform load balancing of latency-sensitive tasks on processors that are otherwise excluded from a scope of load balancing performed by the kernel scheduler. An example method may include identifying, in an operating system of a computing device, one or more first tasks and one or more second tasks, where the second tasks are characterized by one or more latency constraints, identifying a first set of processors that are available for load balancing by a kernel scheduler of the operating system, scheduling execution of the first tasks on the first set of processors, identifying a second set of processors that are excluded from a scope of load balancing performed by the kernel scheduler, and scheduling execution of the second tasks on the second set of processors.

Latency sensitive workload balancing

Disclosed is a method of managing memory of a virtual machine (VM), including providing a physical IOMMU device on a host, and performing a memory translation using the physical IOMMU device on the host.

Hardware offloading for an emulated IOMMU device

Providing clock times to virtual devices. In one embodiment, a method includes identifying a real-time clock device of a host computing device. The host computing device comprises a hypervisor and a virtual machine. The method also includes determining that a virtual device used by the virtual machine will use clock times obtained from the real-time clock device. The method further includes obtaining, by a processing device of the host computing device, a current clock time from the real-time clock device of the host computing device. The method further includes providing the current clock time to the virtual device.

Providing virtual devices direct access to clock times in memory locations managed by a hypervisor

Disclosed is a method of managing memory of a virtual machine (VM), including receiving, at a physical input-output memory management unit (IOMMU) of a processing device operating the VM, a request from a VM IOMMU for VM memory address translation for a VM peripheral component interconnect (PCI) device created on the VM; determining, by the physical IOMMU, a corresponding VM memory address translation result based on the request as received and a memory translation table; and transmitting, by the physical IOMMU to the VM IOMMU, the corresponding VM memory address translation result for servicing the request for VM memory address translation of the VM PCI device.

A system and method of emulated input-output memory management units includes a management software associating a first device with a first input-output memory management unit having a first security designation, and associating a second device with a second input-output memory management unit having a second security designation different from the first security designation. A hypervisor constructs a table that describes associations between the plurality of devices and the plurality of input-output memory management units. The hypervisor provides the table to a guest virtual machine having a plurality of guest addresses including a first guest address and a second guest address. The first device accesses the first guest address through the first input-output memory management unit and the second device accesses the second guest address through the second input-output memory management unit.

Multiple input-output memory management units with fine grained device scopes for virtual machines

Various examples are directed to systems and methods for utilizing a memory-mapped I/O channel. A first application may request that a message be sent to a channel counterparty. A message driver may receive from the first application the request to send the message, where the request comprises payload data from the message. The message driver may write a work request to a send queue of a first queue pair at the first memory location. An emulated channel adapter may poll a physical address at a memory device corresponding to the first memory location; determine that the work request is present at the send queue, and send the payload data to the channel counterparty.

Memory-mapped input/output (I/O) channel

An example method of providing a crash dump file upon a crash of a guest OS includes receiving, by a hypervisor, a notification that a guest OS running on a virtual machine has crashed. The notification is from the guest OS, and the virtual machine and the hypervisor run on a host machine. The method also includes in response to receiving the notification, writing, by the hypervisor, a crash dump file associated with the guest OS crash to a host file system of the host machine.

Crash dump extraction of guest failure

Some examples can enable virtual bridges to be hot plugged into a virtual Peripheral Component Interconnect (vPCI) system. For example, a number of subordinate buses that are connected to a vPCI bridge in the vPCI system can be determined. The vPCI system can be for a virtual machine. A parameter value can then be generated by adding an integer to the number of subordinate buses that are connected to the vPCI bridge. The integer can be a predefined number of additional subordinate buses to enable to be connected to the vPCI bridge. The parameter value can then be assigned to the vPCI bridge. This may enable additional virtual bridges to be hot plugged into the vPCI system at a later time. For example, a new virtual bridge can be added to the vPCI system using the parameter value for the vPCI bridge.

Hot plugging of virtual bridges in a virtual PCI system

Inter-process data transfer on a host computing device is disclosed. A kernel module executing on the host computing device receives, from a first process, buffer registration information that identifies a virtual address of a receive buffer and a length of the receive buffer. The kernel module determines a first physical memory address that corresponds to the virtual address of the receive buffer. The kernel module receives, from a second process, a send request to send data to the first process, the send request including a virtual address of a send buffer, a length of the data, and a destination identifier that is associated with the receive buffer. The kernel module determines a second physical memory address that corresponds to the virtual address of the send buffer and transfers the data directly from the second physical memory address to the first physical memory address.

Kernel-assisted inter-process data transfer

An example method of updating a virtual machine (VM) identifier (ID) stored in a memory buffer allocated from guest memory includes supplying firmware to a guest running on a VM that is executable on a host machine. The firmware includes instructions to allocate a memory buffer. The method also includes obtaining a buffer address of the memory buffer. The memory buffer is in guest memory and stores a VM ID that identifies a first instance of the VM. The method further includes storing the buffer address into hypervisor memory. The method also includes receiving an indication that the VM ID has been updated. The method further includes using the buffer address stored in hypervisor memory to update the VM ID.

Growing community of inventors

Kfar Saba, Israel

Gal Hammer