Commit Graph

12518 Commits

Author SHA1 Message Date
Peter Wemm
ba5e60d11c Missing newline at end of file causes syntax error. 1998-11-08 09:57:28 +00:00
Mike Smith
1916cd2927 Enable 686 class optimisations for all 686-class processors, not just the
Pentium Pro.  This resolves the "Dog slow SMP" issue for Pentium II
systems.
1998-11-08 02:26:14 +00:00
Jordan K. Hubbard
37869e957d o Add proper stack checking to all file words
o add fkey and fread
o eliminate fexists now that this can be expressed in HLL forth
  ( : fexists fopen dup -1 <> if fclose 1 else drop 0 then ; ) :-)

Once we get the ability to write files, it should be possible to do
stand-alone rescue work from the 3rd stage boot. :)
1998-11-07 17:38:40 +00:00
Nicolas Souchu
623bdbdb0a Change METHODE (french) to METHOD.
Submitted by: Nick Hibma <nick.hibma@jrc.it>
1998-11-07 14:56:04 +00:00
Nicolas Souchu
376ba00c94 Define DEBUG only if not already defined, avoiding confusions with
opt_global.h
1998-11-07 14:35:41 +00:00
Nicolas Souchu
99a6f52d8f Add iic driver iff the corresponding devclass exists. 1998-11-07 14:33:46 +00:00
Nicolas Souchu
dec0ec9e81 Return to previous check_for_i2c_devices() behaviour.
Cast the cmd parameter to unsigned char in every smbus call.

Submitted by: Roger Hardiman <roger@cs.strath.ac.uk>
1998-11-07 14:30:48 +00:00
Jordan K. Hubbard
335edb957d Eliminate much code cruft by extending simple file I/O API to include
fopen and fclose.
1998-11-07 06:18:06 +00:00
Jordan K. Hubbard
ed82a24960 Eliminate much code cruft by extending simple file I/O API to include
fopen and fclose.  Also look for /boot/boot.4th now and, if found,
load its contents.
1998-11-07 06:18:00 +00:00
Jordan K. Hubbard
d6a0c2b58d Take init out of here - it's a layering violation. 1998-11-07 05:01:25 +00:00
Peter Wemm
7c8faeb31f oops! s/vfs_register/vfs_unregister/ in the unload case..
Mentioned by: dfr
1998-11-07 04:51:36 +00:00
Peter Wemm
5c23153cac Don't define the module glue if building as an LKM, this happens to have
a same symbol name as the LKM glue.
1998-11-07 04:34:02 +00:00
Jordan K. Hubbard
c412a7ae32 Don't have debugging on by default - it makes testing annoying. :) 1998-11-07 03:44:10 +00:00
Jordan K. Hubbard
65e7b066b3 OK, fload/fexec work properly when both compiling and interpreting
now.  Gack.
1998-11-07 01:56:06 +00:00
Jordan K. Hubbard
ebc4b7c4fb switch words to default mode. 1998-11-06 23:50:08 +00:00
Jordan K. Hubbard
e1266cedab Submit better fix to the prompt bug. 1998-11-06 23:22:26 +00:00
Jordan K. Hubbard
f476d38a01 Make fexists/fload work with existing string literals instead. Doing
my own string literal handling is just too wonky.
1998-11-06 23:20:32 +00:00
Mike Smith
ed91f3baaf USERCONFIG_BOOT -> INTRO_USERCONFIG
Submitted by:	des
1998-11-06 20:32:22 +00:00
Jordan K. Hubbard
c6c128e122 Argh, I had this right[er] before. More commits to follow. 1998-11-06 19:17:03 +00:00
David Greenman
bd81f199b5 Added support for non-blocking sockets to sendfile(2). 1998-11-06 19:16:30 +00:00
Peter Wemm
a429d69f4a Remove trailing ';' - use the one supplied by the caller: "VFS_SET(foo);" 1998-11-06 16:36:31 +00:00
Peter Wemm
9fe66b94a2 Make this work now; fixing the kstack overflow allows the dependency to
be added to the symbol search order safely.
1998-11-06 16:02:14 +00:00
Peter Wemm
578c822198 Don't use a glue file for the module; use the one in the kernel. 1998-11-06 16:01:19 +00:00
Peter Wemm
43dfe295b0 Create an 'ibcs2' module so that scripts can tell if it's statically
linked in or needs to be loaded.
1998-11-06 16:00:47 +00:00
Peter Wemm
caab6e909e Don't put aggregate structs 4K large on the kernel stack, especially when
we can recurse when loading dependencies and that the kstack is limited
to something like 6 or 7KB.  Having a single dependency caused an instant
double panic, and I stronly suspect some of the other strange "events"
that I have seen are possibly as a result of taking a couple of interrupts
with a large chunk of the stack already in use.

While here, fix a minor logic hiccup in a sanity check.
1998-11-06 15:16:07 +00:00
Peter Wemm
21ce23eb91 Define the kld_debug variable if KLD_DEBUG is enabled 1998-11-06 15:10:17 +00:00
David E. O'Brien
9e22648b54 make lnc0 definition in LINT match GENERIC 1998-11-06 09:37:38 +00:00
David E. O'Brien
9a0931701a add AMD Am7990 & Am79C960 to description of lnc(4) 1998-11-06 09:35:32 +00:00
KATO Takenori
f3284683fb Sync with sys/i386/i386/userconfig.c revision up to 1.115. 1998-11-06 08:08:05 +00:00
KATO Takenori
c70606fd9f Sync with sys/i386/i386/machdep.c revision up to 1.315. 1998-11-06 08:07:32 +00:00
KATO Takenori
48ba888a6a Sync with sys/i386/conf/options.i386 revision 1.91. 1998-11-06 08:07:00 +00:00
KATO Takenori
a0a1e229e8 Sync with sys/i386/conf/Makefile.i386 revision 1.128. 1998-11-06 08:06:32 +00:00
Jordan K. Hubbard
11adc0d65e Use proper literal names. 1998-11-06 04:01:32 +00:00
Mike Smith
8a34f8ba88 Ack. Create parseable command tail properly, and eat args out of the TIB. 1998-11-06 03:50:44 +00:00
Mike Smith
8190a019a5 Don't not print the prompt string; not doing this has funny side-effects.
Make the prompt an empty string instead.
1998-11-06 03:47:08 +00:00
Mike Smith
84924924e1 Don't use the poxy vmGetString interface (who uses counted strings these
days?), get the input buffer ourselves.  Add some debugging code.
1998-11-06 03:45:36 +00:00
Peter Wemm
f9d919e98f put a \n on an error message printf 1998-11-06 02:18:57 +00:00
Peter Wemm
cf3e757633 If this is going to have checks for kernel versions, it might as well
do it so that it works.  This code should run on 2.2.x now.
1998-11-06 02:13:14 +00:00
Peter Wemm
5ebfc07dce Remove machine/cputypes.h - it's an i386 only thing 1998-11-06 01:34:06 +00:00
Robert Nordier
548bf5dd17 Make use of BIOS int 0x13 extensions configurable, and disabled
by default.
1998-11-05 20:52:25 +00:00
David Greenman
9dab07768f Document the new NSFBUFS option. 1998-11-05 14:36:37 +00:00
David Greenman
dd0b2081f4 Implemented zero-copy TCP/IP extensions via sendfile(2) - send a
file to a stream socket. sendfile(2) is similar to implementations in
HP-UX, Linux, and other systems, but the API is more extensive and
addresses many of the complaints that the Apache Group and others have
had with those other implementations. Thanks to Marc Slemko of the
Apache Group for helping me work out the best API for this.
Anyway, this has the "net" result of speeding up sends of files over
TCP/IP sockets by about 10X (that is to say, uses 1/10th of the CPU
cycles) when compared to a traditional read/write loop.
1998-11-05 14:28:26 +00:00
Jordan K. Hubbard
82f35547c9 Remember a bit more of my forth and do:
o Add fexists word to check for the presence of a file
o make fexists and fload immediate words which DTRT both interpreted
  and compiled (doh!)
o add an init word which gets run at bootstrapping time to do extra
  post-coldload initialization (in the default implementation, we
  look for /boot/boot.4th and load it if found).
1998-11-05 08:39:43 +00:00
Jordan K. Hubbard
5eb1c6c169 1. rebuild all elements of testmain properly for safety.
2. add fload and key prims for doing simple file and terminal I/O, respectively
1998-11-05 07:27:55 +00:00
Mike Smith
875e602afe Explicitly invoke perl to run the softwords.pl script in case the
script is not executable.
Submitted by:	Don Lewis <Don.Lewis@tsc.tdk.com>
1998-11-05 04:54:05 +00:00
Peter Wemm
ce6bd34722 Build linux_genassym static, this should help aout-to-elf builds 1998-11-05 04:39:26 +00:00
Peter Wemm
6a1a9040f4 Do not overwrite the lkm versions of the install scripts for now. linux
works but ibcs2 has a load failure and joy doesn't look like it'll work.
1998-11-05 04:22:52 +00:00
Peter Wemm
38266231ef Update to use kldload, no temporary files! 1998-11-05 04:19:26 +00:00
Peter Wemm
92892ca7a5 Do not add ${KMOD} to the CLEANFILES list. We want ${PROG} which is either
${KMOD}.o or ${KMOD}.ko.  Otherwise we can delete the source shell script
for linux, joy and ibcs2.
1998-11-05 04:01:55 +00:00
Nicolas Souchu
d3cf287966 iicbus probe and attach deferred until root_bus_configure() call. 1998-11-04 22:09:17 +00:00