How to implement concurrency primitives?

Where can I find information (books, papers, tutorials) on how开发者_Go百科 concurrency primitives are usually implemented? I'm mostly interested in the implementation of inter-process communication, or message-passing (both synchronous and asynchronous): send, receive, select etc.

Where to look depends on the level of abstraction you interested in.

Books I've know which touch this topic, by level of abstraction:

• Hardware: 'Structured Computer Organization' by Tanenbaum;
• OS Level: Several books about Linux kernel and Tanenbaum's 'Operating Systems Design and Implementation';
• OS Level API (not implementation): Books by Richard Stevens -- 'Unix Network Programming' & 'Advanced Programming in the Unix environment';
• In case you interested in distributed systems: again's Tanenbaum 'Distributed Systems: Principles & Paradigms';