* [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? @ 2001-11-19 15:38 Terje Eggestad 2001-11-21 21:54 ` Pavel Machek 2001-11-22 14:41 ` Terje Eggestad 0 siblings, 2 replies; 6+ messages in thread From: Terje Eggestad @ 2001-11-19 15:38 UTC (permalink / raw) To: linux-kernel subject says it all.... I remember there was a discussion and a patch floating around that implemented SYSCALL/SYSRET, just want to know what happened to it.... TJ -- _________________________________________________________________________ Terje Eggestad terje.eggestad@scali.no Scali Scalable Linux Systems http://www.scali.com Olaf Helsets Vei 6 tel: +47 22 62 89 61 (OFFICE) P.O.Box 70 Bogerud +47 975 31 574 (MOBILE) N-0621 Oslo fax: +47 22 62 89 51 NORWAY _________________________________________________________________________ ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? 2001-11-19 15:38 [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? Terje Eggestad @ 2001-11-21 21:54 ` Pavel Machek 2001-11-22 14:41 ` Terje Eggestad 1 sibling, 0 replies; 6+ messages in thread From: Pavel Machek @ 2001-11-21 21:54 UTC (permalink / raw) To: Terje Eggestad; +Cc: linux-kernel On Mon 19-11-01 16:38:45, Terje Eggestad wrote: > subject says it all.... > > I remember there was a discussion and a patch floating around that > implemented SYSCALL/SYSRET, just want to know what happened to it.... discarded -- <sig in construction> ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? 2001-11-19 15:38 [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? Terje Eggestad 2001-11-21 21:54 ` Pavel Machek @ 2001-11-22 14:41 ` Terje Eggestad 1 sibling, 0 replies; 6+ messages in thread From: Terje Eggestad @ 2001-11-22 14:41 UTC (permalink / raw) To: Pavel Machek; +Cc: linux-kernel ons, 2001-11-21 kl. 22:54 skrev Pavel Machek: > > On Mon 19-11-01 16:38:45, Terje Eggestad wrote: > > subject says it all.... > > > > I remember there was a discussion and a patch floating around that > > implemented SYSCALL/SYSRET, just want to know what happened to it.... > > discarded Because there was no perf benefit or because the patch was in poor quality? > > -- > <sig in construction> -- _________________________________________________________________________ Terje Eggestad terje.eggestad@scali.no Scali Scalable Linux Systems http://www.scali.com Olaf Helsets Vei 6 tel: +47 22 62 89 61 (OFFICE) P.O.Box 70 Bogerud +47 975 31 574 (MOBILE) N-0621 Oslo fax: +47 22 62 89 51 NORWAY _________________________________________________________________________ ^ permalink raw reply [flat|nested] 6+ messages in thread
[parent not found: <1006184327.19902.2.camel@pc-16.office.scali.no.suse.lists.linux.kernel>]
[parent not found: <20011121225402.A175@elf.ucw.cz.suse.lists.linux.kernel>]
[parent not found: <1006440069.22598.4.camel@pc-16.office.scali.no.suse.lists.linux.kernel>]
* Re: [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? [not found] ` <1006440069.22598.4.camel@pc-16.office.scali.no.suse.lists.linux.kernel> @ 2001-11-22 15:26 ` Andi Kleen 2001-11-23 13:54 ` Terje Eggestad 1 sibling, 0 replies; 6+ messages in thread From: Andi Kleen @ 2001-11-22 15:26 UTC (permalink / raw) To: Terje Eggestad; +Cc: linux-kernel Terje Eggestad <terje.eggestad@scali.no> writes: > ons, 2001-11-21 kl. 22:54 skrev Pavel Machek: > > > > On Mon 19-11-01 16:38:45, Terje Eggestad wrote: > > > subject says it all.... > > > > > > I remember there was a discussion and a patch floating around that > > > implemented SYSCALL/SYSRET, just want to know what happened to it.... > > > > discarded > > Because there was no perf benefit or because the patch was in poor > quality? The x86-64 port uses SYSCALL/SYSRET as the native call method for 64bit programs. Before x86-64 it turned out that SYSCALL is not really usable because of some builtin limitations (which are fixed in x86-64). This is only a problem for the K6, K7 should have support for SYSENTER/SYSEXIT (the Intel equivalent), which seems to be better designed. There is a patch to use SYSENTER/SYSEXIT. -Andi ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? [not found] ` <1006440069.22598.4.camel@pc-16.office.scali.no.suse.lists.linux.kernel> 2001-11-22 15:26 ` Andi Kleen @ 2001-11-23 13:54 ` Terje Eggestad 2001-11-23 13:57 ` Andi Kleen 1 sibling, 1 reply; 6+ messages in thread From: Terje Eggestad @ 2001-11-23 13:54 UTC (permalink / raw) To: Andi Kleen; +Cc: linux-kernel Cool, do you happen top know where the patch is? On e that I can apply to stock 2.4.1x?? TJ tor, 2001-11-22 kl. 16:26 skrev Andi Kleen: > Terje Eggestad <terje.eggestad@scali.no> writes: > > > ons, 2001-11-21 kl. 22:54 skrev Pavel Machek: > > > > > > On Mon 19-11-01 16:38:45, Terje Eggestad wrote: > > > > subject says it all.... > > > > > > > > I remember there was a discussion and a patch floating around that > > > > implemented SYSCALL/SYSRET, just want to know what happened to it.... > > > > > > discarded > > > > Because there was no perf benefit or because the patch was in poor > > quality? > > The x86-64 port uses SYSCALL/SYSRET as the native call method for 64bit > programs. > > Before x86-64 it turned out that SYSCALL is not really usable because > of some builtin limitations (which are fixed in x86-64). This is only > a problem for the K6, K7 should have support for SYSENTER/SYSEXIT (the > Intel equivalent), which seems to be better designed. There is a patch > to use SYSENTER/SYSEXIT. > > > -Andi -- _________________________________________________________________________ Terje Eggestad terje.eggestad@scali.no Scali Scalable Linux Systems http://www.scali.com Olaf Helsets Vei 6 tel: +47 22 62 89 61 (OFFICE) P.O.Box 70 Bogerud +47 975 31 574 (MOBILE) N-0621 Oslo fax: +47 22 62 89 51 NORWAY _________________________________________________________________________ ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? 2001-11-23 13:54 ` Terje Eggestad @ 2001-11-23 13:57 ` Andi Kleen 0 siblings, 0 replies; 6+ messages in thread From: Andi Kleen @ 2001-11-23 13:57 UTC (permalink / raw) To: Terje Eggestad; +Cc: Andi Kleen, linux-kernel On Fri, Nov 23, 2001 at 02:54:02PM +0100, Terje Eggestad wrote: > Cool, > > do you happen top know where the patch is? On e that I can apply to > stock 2.4.1x?? x86-64 is on ftp.x86-64.org If you mean SYSENTER/SYSEXIT IIRC there were two indepdent patches for that from Manfred Spraul and from Ingo Molnar. You have to ask them if they kept any of them uptodate. -Andi ^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2001-11-23 13:58 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2001-11-19 15:38 [Q] was the SYSENTER/SYSCALL fast system calls completed or discared in the end?? Terje Eggestad
2001-11-21 21:54 ` Pavel Machek
2001-11-22 14:41 ` Terje Eggestad
[not found] <1006184327.19902.2.camel@pc-16.office.scali.no.suse.lists.linux.kernel>
[not found] ` <20011121225402.A175@elf.ucw.cz.suse.lists.linux.kernel>
[not found] ` <1006440069.22598.4.camel@pc-16.office.scali.no.suse.lists.linux.kernel>
2001-11-22 15:26 ` Andi Kleen
2001-11-23 13:54 ` Terje Eggestad
2001-11-23 13:57 ` Andi Kleen
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®