Linux Plumbers Conf 2009

Some would say that Linux has been successful in the embedded space in spite of itself, as there has been relatively little communication between the embedded Linux community and the larger Linux community. Although this has been changing over the past few years, continued progress would be beneficial.

Given his success in bringing many device manufacturers into the Linux community, we can think of no one better than Greg Kroah-Hartman to lead up Linux Plumber Conference’s Embedded microconference. Greg has duly assembled a very impressive lineup.

Greg starts with a real live embedded-Linux developer, Mike Rapoport, who will present “Embedded Linux Development: a Glance From Inside.” Mike works for a small embedded company, so is in a good position to describe the process of embedded-device development and the constraints that this process imposes on embedded developers. He will use this information to analyze the reasons for the relatively low number of contributions to the Linux kernel from the embedded community.

Greg then moves to a real embedded project with “Lessons Learned Designing an Open Source UMPC” by Ben Goska, Tim Harder, and Carlos Jensen. This project produced both the hardware and software for an ultra-mobile personal computer (UMPC) named OSWALD (for Oregon State Wireless Active Learning Device). The purpose of OSWALD is to encourage students to learn about every aspect of computing by permitting experimentation at any level from hardware through firmware and kernel to applications. Every aspect of OSWALD is therefore open, from the hardware to the applications. This presentation gives a quick overview of OSWALD’s architecture and the challenges faced in bringing it to reality.

Greg’s next topic is a real hardware problem that is affecting even embedded systems, “Asymmetric Multiprocessing Issues” by Hollis Blanchard. Yes, multicore CPUs have arrived even in the embedded arena. But embedded system designers want to take things one step further, creating asymmetric systems that run multiple instances of Linux with different capabilities (e.g., real-time and not) on a multicore system. However, such systems do not always have the hardware virtualization capabilities, so these Linux instances must cooperate, leaving hardware resources for each other and sharing hardware as needed. Hollis describes how to use existing solutions to make these systems a reality.

Greg’s final topic is a proposed solution for a real problem, “Flattened Device Tree for All Architectures”, by Grant Likely. This proposal provides the benefits of OpenFirmware’s device tree to PowerPC systems that do not provide OpenFirmware. This approach has also been used for some systems in other architectures, including Microblaze, ARM, and MIPS. Grant will propose this flattened device tree for other architectures in order to consolidate code and ease porting Linux to new architectures.