Messages in this thread | | | Date | Tue, 22 Feb 2000 21:49:40 +0100 (CET) | From | Ingo Molnar <> | Subject | [patch] vsyscall feature |
| |
On Tue, 22 Feb 2000, Dean Gaudet wrote:
> out of curiosity, has the fast syscall and fast gettimeofday stuff > with the nifty kernel-supplied code page made it into the > kernel/glibc/etc?
nope, 2.5 stuff. You can check out the 2.3.32 patch (which has a working purely-user-space times() syscall) at:
http://www.redhat.com/~mingo/vsyscall-2.3.32-F4
Documentation/syscall.txt has the design:
+ + 'x86 Virtual System Call Interface', Ingo Molnar <mingo@redhat.com> + + The point is to have an extensible system call interface. The kernel + provides a generic entry point, which is a readonly user-visible page + range. User-space does not know about the internals of this entry + point, it's a simple generic function call. +
there are several 'trampoline pages' (both data and code) which are 'dual-mapped': kernel-space has a read-write mapping to the data page, user-space only has a read-only mapping. This is how sys_times() works.
it's in the prototype stage, but pretty promising IMO, will post a finished patch once the 2.5 is branched off.
-- mingo
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |