summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Simple update to make these work as kld and preload modules.peter1998-11-0413-169/+90
|
* Turn off -g accidentally left in from testing.msmith1998-11-041-3/+3
|
* Fix includes; we were still pulling in <stdlib.h> in some places.msmith1998-11-0410-34/+54
| | | | | Support building a standalone interpreter with 'make testmain', remove win32 and egregious gets() in testmain.c
* Use a smaller default dictionary to waste less space.msmith1998-11-041-2/+2
|
* Typo.jmz1998-11-041-3/+3
|
* General tidy up: remove more unused code, update comments, simplify somepeter1998-11-041-34/+16
| | | | routines a little.
* Respect ${.OBJDIR} properly when looking for libficl.ajkh1998-11-041-1/+5
|
* Don't try to build (nonexistent) Alpha setjmp until we have one.msmith1998-11-041-1/+3
|
* Add required parts for BootForth building (currently disabled andmsmith1998-11-041-5/+10
| | | | | untested). Only suitable for i386 at the moment, as we are missing setjmp/longjmp on the Alpha.
* Make this work in the libstand environment; don't use stdio/stdlib headers.msmith1998-11-047-30/+12
|
* Add BootForth hooks; if BOOT_FORTH is defined, pass every line readmsmith1998-11-044-5/+155
| | | | | | | 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).
* Move setjmp/longjmp implementations here from libc; no signal handlingmsmith1998-11-044-4/+504
| | | | | | | | 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.
* Formatting tweak.jkh1998-11-042-6/+6
|
* Include "bootstrap.h" to get a definition for bcache_devdata.msmith1998-11-031-1/+2
| | | | Submitted by: jkh
* Back out previous commit. The bpfilter -> bpf transition will have to be ades1998-11-0312-34/+31
| | | | flag day unless we can hack config(8) to smooth things over.
* Rename the 'bpfilter' pseudo-device to 'bpf'. The old syntax is still legaldes1998-11-0312-31/+34
| | | | and will stick around for a while.
* USERCONFIG_BOOT -> INTRO_USERCONFIGmsmith1998-11-031-2/+2
|
* Remove USERCONFIG_BOOT, add INTRO_USERCONFIGmsmith1998-11-032-4/+4
|
* Remove the USERCONFIG_BOOT option. Userconfig script data is searchedmsmith1998-11-036-94/+119
| | | | | | | | | | | | | 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.
* A feeble attempt at kld compatability. The mount_* programs assume thatpeter1998-11-031-1/+10
| | | | | | | | | | | 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).
* make mount(2) automatically kldload modules if the requested filesystempeter1998-11-032-6/+64
| | | | isn't present.
* Have the in-kernel linker try a default extension of .ko. This means thatpeter1998-11-031-3/+30
| | | | | "kldload nfs" works. We use the same default extension in the /boot/loader system.
* Initialize the a.out kld loader after elf, so that elf gets first shot atpeter1998-11-031-2/+2
| | | | a kldload attempt.
* Use the kvm space pathname that we copied in, not the one in user space.peter1998-11-031-2/+2
|
* Reactivate coda. Also, KLD isn't just for i386, it will work on allpeter1998-11-031-5/+3
| | | | | 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.
* Support KLD. We register and unregister two modules. "coda" (the vfs)peter1998-11-034-88/+130
| | | | | | | | | 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
* In the cyrix Cx5530, there are null (empty) Base address registers before thejulian1998-11-032-34/+50
| | | | | | | | 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.
* Move the "root" entry up so people can see it.phk1998-11-032-4/+12
|
* Update unionfs comments; It could be made to work but isn't worth thepeter1998-11-031-2/+5
| | | | effort since LKM's will be going away soon.
* The union kld module is now fully functional.peter1998-11-031-5/+2
|
* Change the #ifdef UNION code into a callable hook. Arrange to have thispeter1998-11-036-232/+196
| | | | set up when unionfs is present, either statically or as a kld module.
* Correct name of RAID-5 versiongrog1998-11-031-4/+5
| | | | Add URL for Cybernet
* Update comments on status of modulespeter1998-11-031-2/+3
|
* Build KLD modules, these work for both a.out and elf.peter1998-11-031-1/+4
|
* Correct u_int_64 casting to remove warnings in printf()grog1998-11-031-2/+2
|
* Remove some dead code and commentsgrog1998-11-032-20/+16
|
* Print a warning if we removed a junked drivegrog1998-11-032-2/+14
| | | | Take a drive down if it's not open
* Take drive down if the disk driver tells us it's not theregrog1998-11-032-2/+10
|
* Check for duplicate subdisk namesgrog1998-11-032-18/+18
|
* Add the Ficl (Forth Inspired Command Language) interpreter. If all goes well,msmith1998-11-0323-2/+9740
| | | | | | | | | | | | | | | | | | | 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)
* Deal with both foo.hlp and FOO.TXT files.jkh1998-11-038-34/+52
|
* Copy appropriate docs into help/ directory of boot floppy.jkh1998-11-031-2/+4
|
* Use the new doc locations.jkh1998-11-031-22/+7
|
* Stage 1: Move a bunch of docs out from under sysinstall and otherjkh1998-11-0314-0/+1541
| | | | less than accessible places.
* Don't update the screen while the cursor shape is being changedyokota1998-11-032-2/+10
| | | | | by the user-land program. PR: i386/8344
* Ok, the entry aging algorithm sucked; 1s time resolution is not enough formsmith1998-11-021-7/+16
| | | | | LRU. Use a 31-bit counter instead. If we decide to do heavy I/O through the bootloader this will have to be revisited.
* Implement a simple LRU block cache. By default this is initialised to 16k,msmith1998-11-027-13/+278
| | | | | | | | | | | | | | 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.
* Revise a few comments.rnordier1998-11-022-14/+14
|
* Standardise on ';' as a component separator; it seems to be a little moremsmith1998-11-021-4/+4
| | | | common than ','.
* Include `enigma' into the list of usr.bin programs.joerg1998-11-021-1/+2
|
OpenPOWER on IntegriCloud