Commit Graph

33046 Commits

Author SHA1 Message Date
Robert Nordier
7fb5f2bae4 Handle a zero elements argument.
PR:		8566
Submitted by:	Archie Cobbs <archie@whistle.com>
1998-11-04 08:55:34 +00:00
Mike Smith
c194030b86 Typo curnwid -> currnwid
Submitted by:	Randy Bush <rbush@bainbridge.verio.net>
1998-11-04 08:33:32 +00:00
Mike Smith
400a056059 Don't need this one anymore. 1998-11-04 07:40:05 +00:00
Mike Smith
b8ffd2a51c Well I never. Seems like _setjmp()/_longjmp() are just what the doctor
ordered.  This brings the Alpha back to parity, and should bring us
BootForth on both platforms.

Submitted by:	John Birrell (jb@freebsd.org)
1998-11-04 07:39:53 +00:00
Mike Smith
2cd5cac4ec Improve the assertion testing for successful softword compilation.
The excessive use of assert() vs. robust error checking is annoying.
1998-11-04 07:07:18 +00:00
Mike Smith
1add1a81da Improve the quality of isspace() to match expectations. This should make
the Ficl interpreter read its softwords array OK.
1998-11-04 07:04:00 +00:00
Peter Wemm
0640d357f2 Simple update to make these work as kld and preload modules. 1998-11-04 03:49:39 +00:00
Mike Smith
95bd40d634 Turn off -g accidentally left in from testing. 1998-11-04 03:42:36 +00:00
Mike Smith
4ce140ae69 Fix includes; we were still pulling in <stdlib.h> in some places.
Support building a standalone interpreter with 'make testmain', remove
win32 and egregious gets() in testmain.c
1998-11-04 03:42:16 +00:00
Mike Smith
66683792a4 Use a smaller default dictionary to waste less space. 1998-11-04 03:41:09 +00:00
Jean-Marc Zucconi
56b1692a2c Typo. 1998-11-04 03:21:21 +00:00
Peter Wemm
ee9d248c5f General tidy up: remove more unused code, update comments, simplify some
routines a little.
1998-11-04 03:18:10 +00:00
Jordan K. Hubbard
12b2c0d82e Respect ${.OBJDIR} properly when looking for libficl.a 1998-11-04 02:36:18 +00:00
Mike Smith
797ed6379a Don't try to build (nonexistent) Alpha setjmp until we have one. 1998-11-04 00:32:08 +00:00
Mike Smith
48fe834fda Add required parts for BootForth building (currently disabled and
untested).  Only suitable for i386 at the moment, as we are missing
setjmp/longjmp on the Alpha.
1998-11-04 00:30:47 +00:00
Mike Smith
cbb5c0dd58 Make this work in the libstand environment; don't use stdio/stdlib headers. 1998-11-04 00:29:33 +00:00
Mike Smith
c7db92c026 Add BootForth hooks; if BOOT_FORTH is defined, pass every line read
to the Forth interpreter.  Instantiate all of our inbuilt commands
as Forth words, and handle them being called from there.

Add my copyright to the bcache module (oops).
1998-11-04 00:29:01 +00:00
Mike Smith
25c3957dfd Move setjmp/longjmp implementations here from libc; no signal handling
in libstand, only for i386 until I locate an alpha setjmp/longjmp.

Minimal 64-bit gcc integer support for i386.  This is kinda nasty, and
should be revisited once we decide whether the bootblocks need
quad arithmetic.
1998-11-04 00:23:18 +00:00
Jordan K. Hubbard
e470578761 Formatting tweak. 1998-11-04 00:06:41 +00:00
Mike Smith
631746a171 Include "bootstrap.h" to get a definition for bcache_devdata.
Submitted by:	jkh
1998-11-03 23:44:49 +00:00
Dag-Erling Smørgrav
fb46af4f6c Back out previous commit. The bpfilter -> bpf transition will have to be a
flag day unless we can hack config(8) to smooth things over.
1998-11-03 22:01:22 +00:00
Dag-Erling Smørgrav
10b4ab477f Rename the 'bpfilter' pseudo-device to 'bpf'. The old syntax is still legal
and will stick around for a while.
1998-11-03 21:12:20 +00:00
Mike Smith
174033faec USERCONFIG_BOOT -> INTRO_USERCONFIG 1998-11-03 21:09:11 +00:00
Mike Smith
5aa27731b7 Remove USERCONFIG_BOOT, add INTRO_USERCONFIG 1998-11-03 21:08:49 +00:00
Mike Smith
ec2a20b046 Remove the USERCONFIG_BOOT option. Userconfig script data is searched
for in a loaded module of type "userconfig_script".  The RB_CONFIG
flag will always result in the user being left inside userconfig at
the end of the script's execution, regardless of 'quit' commands in
the script.  If the RB_CONFIG flag is not specified, the user will
never be left inside userconfig, even if the script does not have an
explicit exit command.

Add the INTRO_USERCONFIG option.  This option forces the userconfig 'intro'
screen (after a script has optionally been executed).  There is no longer
a need to queue an 'intro' command.
1998-11-03 21:07:51 +00:00
Peter Wemm
86854f0360 A feeble attempt at kld compatability. The mount_* programs assume that
they cannot mount a filesystem that they cannot see in getvfsbyname().
Part 1 of this is a hack, make vfsisloadable() always return true - the
ultimate decider of whether it's loadable or not is kldload() or mount().
Part 2 of this is to have vfsload() call kldload(2) and return success if
it works.  This means that we will use a viable kld module in preference
to an LKM!
Ultimately, the thing to do is remove the hacks to do a vfsload in all the
mount_* commands and let the kernel do it by itself in mount(2).
1998-11-03 15:02:29 +00:00
Peter Wemm
02fc72dbe5 make mount(2) automatically kldload modules if the requested filesystem
isn't present.
1998-11-03 14:29:09 +00:00
Peter Wemm
7837745438 Have the in-kernel linker try a default extension of .ko. This means that
"kldload nfs" works.  We use the same default extension in the /boot/loader
system.
1998-11-03 14:27:05 +00:00
Peter Wemm
e91a7f30cf Initialize the a.out kld loader after elf, so that elf gets first shot at
a kldload attempt.
1998-11-03 14:25:21 +00:00
Peter Wemm
b913711e0c Use the kvm space pathname that we copied in, not the one in user space. 1998-11-03 13:09:31 +00:00
Peter Wemm
cabb29ecf0 Reactivate coda. Also, KLD isn't just for i386, it will work on all
architectures since it is a key part of the configuration mechanism. The
exact same code runs in the kernel as it does in a kld module.
1998-11-03 08:58:27 +00:00
Peter Wemm
7b91328a39 Support KLD. We register and unregister two modules. "coda" (the vfs)
via VFS_SET(), and "codadev" for the cdevsw entry.  From kldstat -v:
 3    1 0xf02c5000 115d8    coda.ko
        Contains modules:
                Id Name
                 2 codadev
                 3 coda
1998-11-03 08:55:06 +00:00
Julian Elischer
cd8ab93c90 In the cyrix Cx5530, there are null (empty) Base address registers before the
base register that controls Ultra-DMA, so we need to examine all possible
base registers instead of just giving up at the first empty one.
Also, looking at the source code to the BIOS, I see that they are also
checking for 0xffffffff as an invalid value so do the same. Stefan may like
to clean this up, but at least now I can find my PCI IDE registers.
1998-11-03 08:47:29 +00:00
Poul-Henning Kamp
5707e03c5f Move the "root" entry up so people can see it. 1998-11-03 08:14:38 +00:00
Peter Wemm
8bec73f82d Update unionfs comments; It could be made to work but isn't worth the
effort since LKM's will be going away soon.
1998-11-03 08:07:08 +00:00
Peter Wemm
3b49cbc625 The union kld module is now fully functional. 1998-11-03 08:03:04 +00:00
Peter Wemm
8c14bf40a1 Change the #ifdef UNION code into a callable hook. Arrange to have this
set up when unionfs is present, either statically or as a kld module.
1998-11-03 08:01:48 +00:00
Greg Lehey
28045e8444 Correct name of RAID-5 version
Add URL for Cybernet
1998-11-03 07:02:58 +00:00
Peter Wemm
d679319f61 Update comments on status of modules 1998-11-03 06:51:48 +00:00
Peter Wemm
600f97da28 Build KLD modules, these work for both a.out and elf. 1998-11-03 06:50:58 +00:00
Greg Lehey
07e7cd96c5 Correct u_int_64 casting to remove warnings in printf() 1998-11-03 06:39:39 +00:00
Greg Lehey
0b492c2b06 Remove some dead code and comments 1998-11-03 06:38:58 +00:00
Greg Lehey
44043daefc Print a warning if we removed a junked drive
Take a drive down if it's not open
1998-11-03 06:38:26 +00:00
Greg Lehey
8ef3d686c9 Take drive down if the disk driver tells us it's not there 1998-11-03 06:37:57 +00:00
Greg Lehey
62ae0ffa95 Check for duplicate subdisk names 1998-11-03 06:37:14 +00:00
Mike Smith
780ebb4b00 Add the Ficl (Forth Inspired Command Language) interpreter. If all goes well,
this will allow us to manage bloat in the loader by using a bytecoded HLL
rather than lots of C code.  It also offers an opportunity for vendors
or others with special applications to significantly customise the boot
process without having to commit to a divergent code branch.

This early commit is to allow others to experiment with the most effective
mechanisms for integrating FICL with the loader as it currently stands.

Ficl is distributed with the following license conditions:

"Ficl is freeware.  Use it in any way that you like, with the understanding
 that the code is not supported."

All source files contain authorship attributions.

Obtained from:	John Sadler (john_sadler@alum.mit.edu)
1998-11-03 06:11:35 +00:00
Jordan K. Hubbard
aa9f92fbdb Deal with both foo.hlp and FOO.TXT files. 1998-11-03 03:38:56 +00:00
Jordan K. Hubbard
93713c9d5f Copy appropriate docs into help/ directory of boot floppy. 1998-11-03 03:36:34 +00:00
Jordan K. Hubbard
ed51787467 Use the new doc locations. 1998-11-03 03:31:22 +00:00
Jordan K. Hubbard
d7d6f7335d Stage 1: Move a bunch of docs out from under sysinstall and other
less than accessible places.
1998-11-03 03:21:09 +00:00