Microsoft Technology Licensing, LLC

Karthik Lakshminarayanan

B Anil Kumar

Meher P Malakapalli

Hao Zhang

Parag Chakraborty

Mahesh Sharad Lotlikar

David Michael Robinson

Bradley Post

Tarik Soulami

Vikram Kakumani

Grigor Shirakyan

Kalpesh S Patel

Eric Kai-hau Han

R C Vikram Kakumani

Terrence Lui

A mechanism is described for mitigating the effects of such a DoS attack by detecting a multiple TDR situation within a short duration, identifying the errant virtual machines, and suspending all rendering ability for that virtual machine or set of virtual machines. While the disclosed embodiments are described in the context of virtual machines, the principles may be extended to the general problem of DoS attacks due to TDRs and bugchecks on any physical machine that includes a GPU. For example, DoS attacks can be generated from web sites directly using GPU rendering.

Prevention of DoS attack by a rogue graphics application

A technique for enabling the use of a baseboard management controller in a computer system configured to stream 3D graphical user interfaces to remote clients is described. In an exemplary configuration, a cap driver that is written to conform to a driver model that can interface with a 3D graphics application program interface can be loaded for use with the baseboard management controller instead of a legacy driver that was written to conform to a legacy driver model. This allows a control program to load a graphics driver that can interoperate with the 3D graphics application program interface. In addition to the foregoing, other aspects are described in the text of the summary and detailed description, the claims, and drawings.

Techniques for enabling remote management of servers configured with graphics processors

A method and a processing device are provided for detecting a hardware-based virtual machine environment. An execution time of a privileged instruction may be measured and an execution time of a nonprivileged instruction may be measured. The execution time of the privileged instruction may be compared with the execution time of the nonprivileged instruction. When the execution time of the privileged instruction exceeds the execution time of the nonprivileged instruction by at least a threshold or a threshold factor, then a hardware-based virtual machine environment is detected. In some embodiments, a well-known technique for detecting a software-based virtual machine environment may be used in conjunction with a technique for detecting a hardware-based virtual machine environment. A licensing policy of a software product may be accessed and the software product may be prevented from executing when a detected machine environment is in violation of the licensing policy.

Detection of hardware-based virtual machine environment

Conflicts among programs are detected, and advice is given based on the detected conflicts. A set of conflict rules defines what constitutes a conflict, and a set of advice rules defines what advice is to be given in response to a conflict that has been detected. The conflict rules may be provided by a different party from the action rules, so the decision as to what constitutes a conflict can be made separately from the decision as to what advice should be given when a conflict is detected.

Analysis of software conflicts

Targeted rules and action based support techniques are described, in which, operational data collected from a plurality of clients is used to generate support instructions for troubleshooting operational problems of the clients. Clients are provided targeted access to support instructions based upon information included in the support instructions which matches the support instructions to the clients. In an implementation, clients may be placed in one or more groups based on the analysis of the operational data and may receive support instructions corresponding to the group automatically and without user intervention.

Targeted rules and action based client support

Growing community of inventors

Cupertino, CA, United States of America

Karthik Lakshminarayanan