Commit Graph

204 Commits

Author SHA1 Message Date
Robert Nordier
5103ed619b Drop use of BIOS int 0x14 services in favor of direct port I/O.
Feedback and testing: Adrian Filipi-Martin <adrian@ubergeeks.com>
1998-11-22 07:59:16 +00:00
Archie Cobbs
a8c0f6e542 Fix misallocation of buffer bug (too short) 1998-11-20 02:57:41 +00:00
Paul Richards
9abd5d84ac This fixes a bug in the bcache code whereby false cache hits occur
the first time block 0 is read. This fix initialises the block
numbers to -1 which isn't the most correct thing for a daddr_t but
it isn't likely to cause a problem in the boot blocks and it could
do with a more thought out fix later.

The bug is probably benign on the i386 but on the alpha it can
cause initial file opens to fail. This is the cause of the "can't
open /boot/boot.conf" errors.

It appears on the alpha because of a number of combining factors.
On the alpha the LABELSECTOR is 0 so block 0 needs to be read in
from the media. The first time this happens you get a false hit
because the bc_blkno field is zero initially. Also, the timestamp
check against this cache hit succeeds because on the alpha a hacked
getsecs() function can return 0 when it starts counting so that
the zero initial timestamp + BCACHE_TIMEOUT is greater than the
current time until getsecs() has counted passed BCACHE_TIMEOUT.

The overall effect is that the first open() that occurs gets a
false cache hit and returns garbage to the bd_strategy() function
which then fails the open() call. This false hit then stays in the
cache until BCACHE_TIMEOUT getsecs() ticks have passed; all open()
calls during this time fail.

This explains why you can generally access the media by the time
you get to interp() and start issuing commands but the earlier
attempts to run the boot scripts are failing.

It's possible that this is causing the problem switching to the
mfsroot floppy as well but I haven't confirmed that.
1998-11-19 18:12:03 +00:00
Mike Smith
bcda95d923 Add documentation for $rootdev. 1998-11-13 23:53:02 +00:00
Mike Smith
8f0a6b5b8c Add a new variable $num_ide_disks which is used to offset the unit number
for SCSI disks when converting from BIOS unit numbers to da unit numbers.

Prompted by Kevin Street <street@iname.com>
1998-11-13 23:40:02 +00:00
Jordan K. Hubbard
207fe43d59 bootforth seems to be working well enough for me and others to turn
on by default.  If it causes trouble, it's very easy to switch off again.
1998-11-12 07:40:51 +00:00
Robert Nordier
21ffb6774a Revise error messages. 1998-11-11 08:56:17 +00:00
Robert Nordier
0293eac42c Prevent boot.config being parsed more than once. 1998-11-08 18:37:28 +00:00
Robert Nordier
7ac90f7d65 Drop the familiar 'text=xxxx data=xxxx bss=xxxx ...' display while
loading.  This eliminates noise when loading boot/loader; and when
loading a kernel, they generally flash by too fast to be
intelligible anyway.
1998-11-08 18:29:29 +00:00
Robert Nordier
9888bdcd29 boot1: Eliminate EDD detection and optional use of disk packet
interface.  Do some general consistency fixes and space optimizations.
Use of some freed-up space to defend against possible BIOS misfeatures.

boot2: Revise disk read interface to provide for boot1 changes.  Free
up space for this.
1998-11-08 15:36:35 +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
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
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
Jordan K. Hubbard
c6c128e122 Argh, I had this right[er] before. More commits to follow. 1998-11-06 19:17:03 +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
Robert Nordier
548bf5dd17 Make use of BIOS int 0x13 extensions configurable, and disabled
by default.
1998-11-05 20:52:25 +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
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
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
Jordan K. Hubbard
12b2c0d82e Respect ${.OBJDIR} properly when looking for libficl.a 1998-11-04 02:36:18 +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
631746a171 Include "bootstrap.h" to get a definition for bcache_devdata.
Submitted by:	jkh
1998-11-03 23:44:49 +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
Mike Smith
ddfd18e255 Ok, the entry aging algorithm sucked; 1s time resolution is not enough for
LRU.  Use a 31-bit counter instead.  If we decide to do heavy I/O through
the bootloader this will have to be revisited.
1998-11-02 23:50:59 +00:00
Mike Smith
af1f6e0673 Implement a simple LRU block cache. By default this is initialised to 16k,
and will bypass transfers for more than 8k.  Blocks are invalidated after
2 seconds, so removable media should not confuse the cache.

The 8k threshold is a compromise; all UFS transfers performed by
libstand are 8k or less, so large file reads thrash the cache.
However many filesystem metadata operations are also performed using
8k blocks, so using a lower threshold gives poor performance.

Those of you with an eye for cache algorithms are welcome to tell me
how badly this one sucks; you can start with the 'bcachestats' command
which will print the contents of the cache and access statistics.
1998-11-02 23:28:11 +00:00
Robert Nordier
3d04f230e5 Revise a few comments. 1998-11-02 17:53:08 +00:00
Mike Smith
3c0efe5da1 Standardise on ';' as a component separator; it seems to be a little more
common than ','.
1998-11-02 16:55:57 +00:00
Robert Nordier
3b1bd5ae35 Ignore, rather than emulate, an i386 'hlt' instruction (though for
most practical purposes, this should be indistinguishable from a
more strictly correct approach).

Feedback and testing: msmith
1998-11-01 13:52:52 +00:00
Doug Rabson
06feb69276 * Extend the memory available for the heap from 256k to 512k.
* Embed the stack into the bss section for loader and netboot.  This
  is required for netboot since otherwise the stack would be inside our
  heap.
* Install loader and netboot in /boot by default.
* Fix getbootfile so that it searches for a ',' instead of a ';'
  when terminating the filename.
1998-10-31 17:12:32 +00:00
Mike Smith
dc8be6a8f5 - Add a new command 'lsdev' to list devices which might be likely to host
filesystems.
 - New 'help' command and data in the help.* files (not yet installed),
   provides topic and subtopic help, indexes, etc.
 - Don't crash if the user tries to set an invalid console.  Be helpful
   instead.
 - Expand tabs (badly) on the i386 video console.
 - Some minor cosmetic changes.
1998-10-31 02:53:12 +00:00
Luoqi Chen
36159e3d1e Fix an uninitialized variable in the `dangerously dedicated disk' case. 1998-10-30 07:15:52 +00:00
Mike Smith
4c1a7a5a8f Make the BTX loader much more quiet about what it's doing. This removes
most of the "what the (*^&%(*^ was that?" stuff that normally flies by.
1998-10-30 00:11:35 +00:00
Mike Smith
8879e57b3e Simplify the "is a character ready" test, so that we don't return a false
negative for keypresses with zero ascii values.  This is in line with the
comconsole test, rather than being more ambitious.

Submitted by:	rnordier
1998-10-28 19:24:15 +00:00
Robert Nordier
9244e1a412 Avoid interruptions while talking to keyboard controller. 1998-10-27 20:19:24 +00:00
Robert Nordier
c589107988 biosboot compatibility fix: change behavior of backspace in getstr().
Noticed by: abial

Optimize away a few bytes to make space for the above.
1998-10-27 20:16:36 +00:00