| To: | "Maciej W. Rozycki" <macro@ds2.pg.gda.pl> |
|---|---|
| Subject: | Re: MIPS_ATOMIC_SET in sys_sysmips() |
| From: | Harald Koerfgen <Harald.Koerfgen@home.ivm.de> |
| Date: | Tue, 19 Dec 2000 18:03:01 +0100 (CET) |
| Cc: | linux-mips@oss.sgi.com, Ralf Baechle <ralf@uni-koblenz.de>, Jun Sun <jsun@mvista.com> |
| In-reply-to: | <Pine.GSO.3.96.1001219140739.10024F-100000@delta.ds2.pg.gda.pl> |
| Organization: | none |
| Reply-to: | Harald Koerfgen <Harald.Koerfgen@home.ivm.de> |
| Sender: | owner-linux-mips@oss.sgi.com |
On 19-Dec-00 Maciej W. Rozycki wrote: > On Mon, 18 Dec 2000, Jun Sun wrote: >> What do we offer to machines without ll/sc? > > I asked Ralf for a clarification of the sysmips(MIPS_ATOMIC_SET, ...) > call before I write better code. No response so far. I'm now really > cosidering implementing the Ultrix atomic_op() syscall -- at least it has > a well-known defined behaviour. Another possibility would be to rely on the userland ll/sc emulation in the kernel. The one in the linux-vr tree seems to be working well and can easily be backported to Linux/MIPS. Advantage: userland binary compatibility. Disadvantage: possibility for a lot of context switches for userland atomic operations. Having a sysmips(MIPS_ATOMIC_SET, ...) or atomic_op() solution would probably a lot faster. Maybe we should implement both :) -- Regards, Harald |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Kernel Oops when booting on DECstation, Harald Koerfgen |
|---|---|
| Next by Date: | Re: Kernel Oops when booting on DECstation, Karel van Houten |
| Previous by Thread: | Re: MIPS_ATOMIC_SET in sys_sysmips(), Maciej W. Rozycki |
| Next by Thread: | Re: MIPS_ATOMIC_SET in sys_sysmips(), Maciej W. Rozycki |
| Indexes: | [Date] [Thread] [Top] [All Lists] |