Fast Pentium memcpy update

Robert L Krawitz (rlk@tiac.net)
Tue, 2 Apr 1996 15:53:50 -0500

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Doug Ledford: "Time spent on interrupt handling"
Previous message: Steven L Baur: "[1.3.82] NFS: too small read memory size (0 bytes)"

A bug has been found (and a patch submitted) for another sporadic
memory corruption problem. I have not reissued the patch as I have
not had an opportunity to test it yet. I will reissue it (probably
against 1.3.82) as soon as I have a chance to test it (possibly
tonight).

The problem in question manifests itself when the fast memcpy routine
is used both in user space and in the kernel. I don't have the report
in front of me (my ISP system is down right now), but the upshot is
that it is due to a conflict with the FPU save routine. Presumably it
will cause a problem with any user program that uses the FPU. I will
post a more complete report as soon as it is available.

-- Robert Krawitz <rlk@tiac.net> http://www.tiac.net/users/rlk/

Member of the League for Programming Freedom -- mail lpf@uunet.uu.net Tall Clubs International -- tci-request@aptinc.com or 1-800-521-2512

Next message: Doug Ledford: "Time spent on interrupt handling"
Previous message: Steven L Baur: "[1.3.82] NFS: too small read memory size (0 bytes)"