GoKawiilOpenBSD stories
When developing software to run in a Unix environment, you will often be able to use the same system features and benefit from good developer tools, regardless of the particular platform you're working on, as most processors will provide a rich instruction set and virtual memory, among other things.
When you're on the other side of the fence, and working in the kernel, all the gory details which will heavily differ across platforms can no longer be ignored, and sometimes, the shortcomings of a given processor architecture can become a real pain in the arse.
For example, if you have read the m88k saga, you might remember that the need, for the operating system exception handler, to perform all the pending load and stores before returning from exception processing, had been a source of problems for years.
The 88100 processor is not the only processor which sometimes makes the kernel developer's life harder than it could have been.
Let me tell you about a processor design choice which turned out to have a significant cost in the kernel (but in a rare situation.)
The VAX architecture, introduced at the end of 1977, is one of the oldest 32-bit architectures. The architecture has a large instruction set, plenty of addressing modes, but nothing fancy: no out-of-order execution, no branch delay slots, no register renaming, no hyper threading, and even no cache memory on the earliest designs, which did not need any as they wouldn't run faster than the memory refresh cycle (back then, processors speeds were expressed as cycle times in micro- or nano-seconds, rather than megahertz: a 5MHz processor would be described as having a 200ns cycle time; in comparison, the memory refresh cycles would be around 120ns, and as progress were made, were slowly decreasing, with 100ns memory being common at the end of the 1980s, 80ns in the first half of the 1990s, 70ns and 60ns later on.)
The exception model of the VAX was also quite simple, with the ``Exceptions and Interrupts'' chapter of the VAX Architecture Reference Manual being only 36 pages long in the first edition (and 43 in the second edition, mostly because of a slightly larger font rather than extra text.)
Quoting from it:
A trap is an exception that occurs at the end of the instruction that caused the exception. Therefore the PC saved on the stack is the address of the next instruction that would normally have been executed.
... continue reading