On Tue, 26 Jun 2007, Rik van Riel wrote: > Davide Libenzi wrote: > > The following patch implements the sys_brk2() syscall, that nothing is > > other than a sys_brk() with an extra "flags" parameter. This can be used > > to pass the new MAP_NOZERO bit, to ask the kernel to hand over non-zero > > pages if possible. > > Since programs can get back free()d memory after a malloc(), > with the old contents of the memory intact, surely your > MAP_NONZERO behavior could be the default for programs that > can get away with it? > > Maybe we could use some magic ELF header, similar to the > way non-executable stack is handled?
Well, the quick&ugly glibc patch simply uses an environment variable, just because I wanted to bench the kernel build with using the same glibc+gcc. Yes, it can be the default behaviour for the allocator. The patch handles calloc() correctly, by forcibly zeroing memory in such calls. But other software must be taught too, to use MAP_NOZERO when they do not need zeroed memory. I did that for the gcc garbage collector. - Davide - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/