Messages in this thread | | | From | Keith Owens <> | Subject | Re: [Criticism]C++ Flamewar | Date | Tue, 17 Oct 2000 00:43:58 +1100 |
| |
On Mon, 16 Oct 2000 08:50:24 -0400, Mark Salisbury <mbs@mc.com> wrote: >the original-original post was somebody asking why not make the kernel headers >C++ friendly. >all he wanted was the c++ reserved words removed from / kept out of the headers. >that way, if they for some reason want to write, or maybe proto a MODULE in c++ >they could. no reference to putting C++ in the kernel, just writing a module >in it. to me this means that the MODULE would have to be linked w/ libg++ >_NOT_ the kernel.
Interesting concept, linking a module with libg++. Would that be a dynamic or static link?
If it is dynamic then you can absolutely forget about loading the module into the kernel, there is no way that modutils will ever support that. If it is a static link then every module has its own private copy of libg++, that would introduce more than a little kernel bloat. How big is a static copy of libg++ these days? The thought of two or more modules each with a static copy of libg++ but running in the same kernel address space gives me the shivers.
So even if you can compile a module with C++ headers and link against libg++, it is extremely unlikely that you could load it. If you cannot load it, why bother compiling it with C++?
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
| |