2012-06-02 00:13 Textmode has joined #qi-hardware 2012-06-02 01:15 rejon has joined #qi-hardware 2012-06-02 01:37 urandom__ has quit [Remote host closed the connection] 2012-06-02 02:07 xiangfu has joined #qi-hardware 2012-06-02 02:16 qwebirc5779 has joined #qi-hardware 2012-06-02 02:17 heh, now the price hike is out :) let's see what happens 2012-06-02 02:22 qwebirc5779 has quit [Ping timeout: 245 seconds] 2012-06-02 02:34 emeb has quit [Quit: Leaving.] 2012-06-02 02:40 nothing will happen 2012-06-02 02:50 ;-) 2012-06-02 02:50 i guess i should try to organize some angry protests, just to prove you wrong :) 2012-06-02 02:50 xiangfu has quit [Ping timeout: 245 seconds] 2012-06-02 03:04 xiangfu has joined #qi-hardware 2012-06-02 03:34 sucotronic has quit [Ping timeout: 265 seconds] 2012-06-02 03:46 sucotronic has joined #qi-hardware 2012-06-02 04:07 Maroni has quit [Ping timeout: 260 seconds] 2012-06-02 04:11 Maroni has joined #qi-hardware 2012-06-02 04:45 xwalk has quit [Ping timeout: 265 seconds] 2012-06-02 04:46 xwalk has joined #qi-hardware 2012-06-02 04:52 xwalk has quit [Ping timeout: 244 seconds] 2012-06-02 04:55 wolfspraul has joined #qi-hardware 2012-06-02 04:58 wolfspra1l has quit [Ping timeout: 245 seconds] 2012-06-02 05:18 Textmode has quit [Ping timeout: 255 seconds] 2012-06-02 05:18 wolfspra1l has joined #qi-hardware 2012-06-02 05:21 wolfspraul has quit [Ping timeout: 248 seconds] 2012-06-02 05:34 hehe 2012-06-02 05:35 price-hike? ah. 2012-06-02 05:35 well.. i was actually thinking about buying a efika mx from tuxbrain. they seem to be difficult to get over here 2012-06-02 05:42 wolfspra1l: are there no working watches anymore or why does the public mean to give 10mio to these guys?! 2012-06-02 05:44 don't understand 2012-06-02 05:44 it's something people like, obviously 2012-06-02 05:45 I certainly don't ask "why are 10 mio spent on this or that" - if you just look around the world a bit you could ask yourself that question for billions and billions spent every day on total bs 2012-06-02 05:45 I do like how they pulled it off though, will watch whether they can establish strong/new sales channels. 2012-06-02 05:47 wolfspra1l: well.. it doesnt happen that often that one asks for 100k and gets 10mio 2012-06-02 05:47 just too sad that i do not carry watches anymore ;) 2012-06-02 06:00 jekhor has joined #qi-hardware 2012-06-02 06:05 phirsch has quit [Ping timeout: 252 seconds] 2012-06-02 06:05 phirsch has joined #qi-hardware 2012-06-02 06:26 xiangfu has quit [Remote host closed the connection] 2012-06-02 07:07 kristoffer has joined #qi-hardware 2012-06-02 07:17 Ayla has joined #qi-hardware 2012-06-02 07:59 xwalk has joined #qi-hardware 2012-06-02 08:07 The build has FAILED: http://fidelio.qi-hardware.com/~xiangfu/building/Nanonote/Ben/openwrt-xburst.full_system-20120601-0638 2012-06-02 08:48 kilae has joined #qi-hardware 2012-06-02 08:51 rz2k has quit [Quit: ZNC - http://znc.in] 2012-06-02 08:57 [commit] Werner Almesberger: b2/: rename a bit too general "dump" to "dump_param" (master) http://qi-hw.com/p/eda-tools/b723c88 2012-06-02 08:57 [commit] Werner Almesberger: b2/: new option -dCHARS to dump specific db; replaces use of -v (master) http://qi-hw.com/p/eda-tools/3ebac68 2012-06-02 08:57 [commit] Werner Almesberger: b2/boom.c (main): rearrange to reduce indentation depth (master) http://qi-hw.com/p/eda-tools/be1277e 2012-06-02 08:57 [commit] Werner Almesberger: b2/db.c: new function parts_dump to dump the whole parts database (master) http://qi-hw.com/p/eda-tools/2241276 2012-06-02 08:57 [commit] Werner Almesberger: b2/: move parts dumping from lang.y to boom.c and make optional (-dc) (master) http://qi-hw.com/p/eda-tools/f09e4b2 2012-06-02 08:57 [commit] Werner Almesberger: b2/test/Common: support multiple files of the same kind (!-c1, !-c2, etc.) (master) http://qi-hw.com/p/eda-tools/69701f4 2012-06-02 08:57 [commit] Werner Almesberger: b2/lang.y (part): show part ID in error message (master) http://qi-hw.com/p/eda-tools/ea57323 2012-06-02 08:57 [commit] Werner Almesberger: b2/test/char: part characteristics database test (master) http://qi-hw.com/p/eda-tools/dd727b1 2012-06-02 08:58 rz2k has joined #qi-hardware 2012-06-02 09:02 Maroni has quit [Ping timeout: 260 seconds] 2012-06-02 09:10 wolfspra1l has quit [Quit: leaving] 2012-06-02 09:11 wolfspraul has joined #qi-hardware 2012-06-02 10:12 rz2k is now known as rz2k_ 2012-06-02 10:13 rz2k has joined #qi-hardware 2012-06-02 10:14 rz2k_ has quit [Quit: ZNC - http://znc.in] 2012-06-02 10:59 B_Lizzard has joined #qi-hardware 2012-06-02 11:16 freespace has quit [Ping timeout: 244 seconds] 2012-06-02 11:22 freespace has joined #qi-hardware 2012-06-02 11:44 http://vincentpetry.net/blog/?p=151 worth for openwrt/nanonote? 2012-06-02 11:54 should run out of the box on the dingoo 2012-06-02 11:57 ah nice :) 2012-06-02 11:57 I even did not care to see if it is packaged already, sorry 2012-06-02 11:58 so in the dingoo you run even python games. nice 2012-06-02 12:01 DocScrutinizer has quit [Ping timeout: 265 seconds] 2012-06-02 12:02 DocScrutinizer has joined #qi-hardware 2012-06-02 12:09 wolfspraul: which nfs version? 2012-06-02 12:42 don't know 2012-06-02 13:38 DocScrutinizer has quit [Ping timeout: 265 seconds] 2012-06-02 13:43 DocScrutinizer has joined #qi-hardware 2012-06-02 14:16 rejon has quit [Ping timeout: 260 seconds] 2012-06-02 14:22 B_Lizzard has quit [Remote host closed the connection] 2012-06-02 14:38 xwalk_ has quit [Quit: Leaving] 2012-06-02 14:43 xwalk_ has joined #qi-hardware 2012-06-02 14:46 compcube has joined #qi-hardware 2012-06-02 14:46 compcube has quit [Changing host] 2012-06-02 14:46 compcube has joined #qi-hardware 2012-06-02 15:45 well, I'm just having fun with copying a complete image of $HOMe (~27GB) from my old laptop to a new one, via scp 2012-06-02 15:46 recovers nicely (when mc is managing that copy via /#sh://) but suuuucks for speed 2012-06-02 15:46 buzzword fishfs it seems 2012-06-02 15:49 the network link is your bottleneck? 2012-06-02 15:50 nah 2012-06-02 15:50 friggin fs operations via ssh are 2012-06-02 15:50 ~20 files/s 2012-06-02 15:51 why don't you use rsync for example? 2012-06-02 15:51 facing another ~12h ETA, plus penalty for each file on source that's not readable by user 2012-06-02 15:52 viric: because I'm a lazy asshole and just realized mc can connect to the ssh of source PC 2012-06-02 15:52 not a bad reason 2012-06-02 15:52 at least mc provides ETA. 2012-06-02 15:52 I don't know any other tool that des 2012-06-02 15:52 does 2012-06-02 15:53 I nevertheless evaluated option a tiny bit before, and concluded rsync via ssh would do exactly the same, but without nice progress indicator and requesters etc 2012-06-02 15:53 I'm more of: ssh pc "tar c /home" | tar x 2012-06-02 15:53 :) 2012-06-02 15:53 well, rsync via ssh would not have a slowdown of fs operations through ssh 2012-06-02 15:54 rsync gives work to the remote rsync. 2012-06-02 15:54 you *might* be right actually 2012-06-02 15:54 initially I thought "whatever time it takes, I'm not in a hurry" 2012-06-02 15:55 now I realize I have to observe this process for 12h, to eventually hit return to make a warning requester go away, whenever there's a file owned by root and not user, and not readable by user 2012-06-02 15:57 ha. :) 2012-06-02 15:57 if you know the size of the data... use 'pv' 2012-06-02 15:58 ssh pc "tar cp /home" | pv -S 23g | tar xp 2012-06-02 15:58 and you'll get an ETA. :) 2012-06-02 15:58 ssh pc "tar cp /home" | pv -a -S 23g | tar xp 2012-06-02 15:58 the averaging may work better for ETA. 2012-06-02 15:59 store the 'tar' stderr, and you'll have a list of the errors. 2012-06-02 15:59 ssh pc "tar cp /home" 2> tarc-errors.txt | pv -a -S 23g | tar xp 2012-06-02 16:07 valhalla has quit [Ping timeout: 252 seconds] 2012-06-02 16:56 lekernel has joined #qi-hardware 2012-06-02 17:20 jekhor has quit [Ping timeout: 252 seconds] 2012-06-02 17:23 I used sftp from console now, logging in to source PC as root --- rocks! 2012-06-02 17:24 jekhor has joined #qi-hardware 2012-06-02 17:25 from scroll spreed in xterm I estimate I'm up from ~20fileops/s to >500 now 2012-06-02 17:27 well, this might have been the part where dest files already been existing 2012-06-02 17:27 suddenly it dropped significantly 2012-06-02 17:34 kuribas has joined #qi-hardware 2012-06-02 17:36 still, I'm confident it won't take longer than 2 hours now 2012-06-02 17:40 Ayla has quit [Ping timeout: 248 seconds] 2012-06-02 17:40 Ayla has joined #qi-hardware 2012-06-02 17:56 mhm, 2 minutes for qi ML 2012-06-02 17:56 /home/jr/.kde/share/apps/kmail/mail/.lists.directory/qi/cur/1292839187.22703.sSFlI 100% 5131 5.0KB/s 00:00 2012-06-02 18:00 those 130,000 mails suck for sftp, even at an estimated rate of 100/s 2012-06-02 18:02 it depends on your filesystem too 2012-06-02 18:03 if it seeks once per letter... on a 7200rpm disk it will do little more than 100/s 2012-06-02 18:03 with sftp you still have each file requested remotely, one by one. 2012-06-02 18:07 sure 2012-06-02 18:07 /home/jr/.kde/share/apps/kmail/mail/.lists.directory/.openmoko.directory/.public.directory/cmty/cur/1326897176.26507.33lRp 100% 7094 6.9KB/s 00:00 2012-06-02 18:08 good luck. 2012-06-02 18:08 I hope it'll be thru with mail eventually 2012-06-02 18:09 I don't think sftp will respect symlinks, dates, ... 2012-06-02 18:11 -pr will 2012-06-02 18:12 bottleneck CPU still, not HDD: Avg: 25.1% sy: 5.1% ni: 0.0% hi: 0.0% si: 0.6% wa: 35.4% 2012-06-02 18:13 which makes a total of 100% on one of both cores, plus a bit on other one 2012-06-02 18:13 wa is it 2012-06-02 18:14 device reads SDA (8.0): ~80/s max 2012-06-02 18:15 usually way ,ower 2012-06-02 18:15 lower* 2012-06-02 18:15 well, no, that's actually average. max is 500 2012-06-02 18:17 those 80 though could actually be the msg files read one by one 2012-06-02 18:21 *yawn* 2012-06-02 18:21 watching make runs is more fun ;-) 2012-06-02 18:24 *yaaaawn* /home/jr/.kde/share/apps/kmail/mail/.lists.directory/.openmoko.directory/.public.directory/cmty/cur/1221116234.3915.HLS8k:2,S 100% 3816 3.7KB/s 00:00 2012-06-02 18:25 * DocScrutinizer51 sobs for all the inodes 2012-06-02 18:26 if you delete all the files, your inodes will enjoy freedom again :) 2012-06-02 18:27 jr@halley:~> find /home/jr/.kde/share/apps/kmail/mail/ |wc -l 2012-06-02 18:27 154729 2012-06-02 18:28 took an amazing ~5s to complete, despite this sftp monster running concurently 2012-06-02 18:29 YAY OM-kernel ML 2012-06-02 18:29 through with community 2012-06-02 18:30 anyway mail takes >30% of the files to copy 2012-06-02 18:30 number of, not volume 2012-06-02 18:32 \o/ internal 2012-06-02 18:38 DocScrutinizer has quit [Ping timeout: 260 seconds] 2012-06-02 18:43 [commit] Werner Almesberger: fisl2011/Makefile (DL): Atben_atusb_prod_03.jpg was missing (master) http://qi-hw.com/p/wernermisc/8418a19 2012-06-02 18:43 and stalled >:-( 2012-06-02 18:47 phirsch has quit [Ping timeout: 252 seconds] 2012-06-02 18:48 fsck that d-link dir615, which obviously has problems with occasionally dropping ARP table or whatever 2012-06-02 18:49 or firewall/NAT hangups 2012-06-02 18:49 phirsch has joined #qi-hardware 2012-06-02 18:57 DocScrutinizer has joined #qi-hardware 2012-06-02 19:24 kilae_ has joined #qi-hardware 2012-06-02 19:26 kilae has quit [Ping timeout: 260 seconds] 2012-06-02 19:43 fuuuuuck, sftp won't resume, I.E. will start from very first file again, ignoring all the stuff already copied. Worse: rsync does that too :-o 2012-06-02 19:44 seems rsync hold a local file where it keeps a list of files already synced, and it doesn't care at all about actually existing real files on destination 2012-06-02 19:47 or maybe not 2012-06-02 19:47 already at "xfer#25322" 2012-06-02 19:55 44k done 61k left 2012-06-02 20:02 Maroni has joined #qi-hardware 2012-06-02 20:23 left 1900 of 171000 2012-06-02 20:24 and friggin rsync is way slower than sftp: while sftp maxed out a ~11MB/s on large files, rsync gets to 3.xMB/s when lucky 2012-06-02 20:25 and the WTF: it's not been dir615 but the sis190 kernel module of source machine. Had to modprobe-cycle it to make the NIC work again 2012-06-02 20:25 "it"=the lockup 2012-06-02 20:56 Ayla has quit [Quit: Lost terminal] 2012-06-02 20:57 Ayla has joined #qi-hardware 2012-06-02 21:00 compcube has quit [Quit: Leaving] 2012-06-02 21:19 jekhor has quit [Ping timeout: 248 seconds] 2012-06-02 21:25 hypermodern_ has joined #qi-hardware 2012-06-02 21:26 hypermodern_ has left #qi-hardware [#qi-hardware] 2012-06-02 21:35 kilae_ has quit [Quit: ChatZilla 0.9.88.2 [Firefox 12.0/20120420145725]] 2012-06-02 22:21 sigh 2012-06-02 22:21 sent 8096479 bytes received 19742271984 bytes 2132984.34 bytes/sec 2012-06-02 22:21 total size is 28602138243 speedup is 1.45 2012-06-02 22:21 rsync error: some files/attrs were not transferred (see previous errors) (code 23) at main.c(1530) [generator=3.0.9] 2012-06-02 22:23 make a tar and scp it ? or would that be too easy ? :) 2012-06-02 22:24 extra points for rsyncing the tar, since this will let you restart 2012-06-02 22:24 make a tar of 28GB, on a disk that has 300MB free? 2012-06-02 22:24 suuure 2012-06-02 22:24 delete all the porn first :) 2012-06-02 22:28 well, seems it's thru now. but now I have a dir /home/jr/halley with lots of stuff in it. And a dir /home/jr/halley/home/jr, with all the stuff in it again :-S 2012-06-02 22:29 that's called a "backup" :) 2012-06-02 22:29 could you tell from the cmdline >> rsync -vaRzxP --fake-super root@192.168.1.30:/home/jr/ ~/halley/jr/ << which is the real stuff now? 2012-06-02 22:30 my bet would be on the subdirectory 2012-06-02 22:31 but you can just move it out. then do a du -sh to compare size 2012-06-02 22:31 indeed 2012-06-02 22:31 or diff -r if you're bold and they should be the same :) 2012-06-02 22:31 already thought abizt du -sh, but thanks for the moving suggestion 2012-06-02 22:32 about* 2012-06-02 22:36 jr@HaleBopp:~/halley/jr> du -sh /home/jr/halley2/home/jr/; du -sh /home/jr/halley 2012-06-02 22:36 28G /home/jr/halley2/home/jr/ 2012-06-02 22:36 13G /home/jr/halley 2012-06-02 22:36 wpwrak: thanks 2012-06-02 22:37 it seems like the destination argument on that rsync cmd took no effect at all 2012-06-02 22:38 anyway 28G is what I expected 2012-06-02 22:39 you could du a find with md5sum on source and origin to be 100% sure 2012-06-02 22:39 s/du /do 2012-06-02 22:39 wpwrak meant: "you could do a find with md5sum on source and origin to be 100% sure" 2012-06-02 22:41 qwebirc27345 has joined #qi-hardware 2012-06-02 22:41 cd /home/jr/halley; find . -type f -exec md5sum '{}' \; >~/output 2012-06-02 22:41 qwebirc27345 is now known as rjeffries 2012-06-02 22:41 then do a sort out1 out2 | uniq -u 2012-06-02 22:41 what for? 2012-06-02 22:42 wolfspraul expresed interest in making hos own PCBs. this article is not bad. http://hackaday.com/2012/06/02/pcb-manufacturing-tutorial/ 2012-06-02 22:42 that will allow you to see if a) all the files made it and b) if they were copied correctly 2012-06-02 22:42 s /hos/his/ 2012-06-02 22:43 this will take longer than doing another rsync 2012-06-02 22:46 no. worst case, it takes just as long :) 2012-06-02 22:47 friggin idiot I am, giving -R parameter without thinking 2012-06-02 22:50 better than --remove-source-files :) 2012-06-02 22:52 rjeffries: seems reasonably up to date. the etchant tank is a bit overkill, though, unless you plan to do monster boards 2012-06-02 22:53 wprak did you see [not talking about this artcle] where one person made a spray chamber so he could etch boards quickly with no muss or fuss? amusing. 2012-06-02 22:53 he seems a bit confused about what 3D printers do, too 2012-06-02 22:55 HAH, now the benefits of rsync hit 2012-06-02 22:55 +mwDGO1eWKyOiCJnpYZVFtUcItXrsync: readlink_stat("/home/jr/.gvfs") failed: Permission denied (13) 2012-06-02 22:55 rsync error: some files/attrs were not transferred (see previous errors) (code 23) at main.c(1530) [generator=3.0.9] 2012-06-02 22:56 second run was "lightning fast" 2012-06-02 22:57 nfc what's this >>key_read: uudecode AAAAB3NzaC1kc3MAAAEBAP8Bo+QhQ...<< foo at beginning though 2012-06-02 22:57 friggin 7 lines of uuencoded key, WHY oh WHY? 2012-06-02 22:58 rjeffries: the chemistry link is interesting, though: http://www.stephenhobley.com/blog/2011/03/02/still-messing-with-forces-i-dont-understand-the-formula/ 2012-06-02 22:58 replacing the muriatic acid (HCl) with household chemicals 2012-06-02 22:58 OUCH 2012-06-02 22:59 i just hope those people never get their hands on higher grade peroxide. the graveyard of overly adventurous pioneers is already quite full :) 2012-06-02 22:59 he could rub some marshmallows on it and let ants eat away the copper 2012-06-02 23:03 ~curse gnome and all g* 2012-06-02 23:03 May you be reincarnated as a Windows XP administrator, gnome and all g* ! 2012-06-02 23:03 that could work. probably a bit slow, though 2012-06-02 23:04 faster than just waiting for proton decay, though :) 2012-06-02 23:09 wpwrak: would you be interested in getting involved into a bit of kernel development discussion? 2012-06-02 23:11 the kernel is vast. what area of it ? 2012-06-02 23:12 Maroni has quit [Quit: 'quit_message'] 2012-06-02 23:12 there's this guy FreemanGordon over there at #maemo-ssu, and he investigated for almost a felt year now how to make thumb interworking working on N900 which has an OMAP with a silicon erratum that fscks up the branch prediction when you (mem)swap a thumb branch for a ARM branch, or sth like that 2012-06-02 23:13 actually there are (at least) two silicon errata, and common urban legend is the fixes for those two are mutually exclusive 2012-06-02 23:13 nice ;-) 2012-06-02 23:13 sounds like a topic for the linux-arm list ? 2012-06-02 23:14 freemanG now claims he made it work, but none of the "experts" is willing to listen 2012-06-02 23:15 kristoffer has quit [Quit: Leaving] 2012-06-02 23:15 which is kinda expected, since that OMAP3430 is rather old silicon anyway 2012-06-02 23:15 did he try that list ? i'm no longer on it, so it can't check quickly 2012-06-02 23:16 and not much to earn on fixing kernel stuff to make thumb interworking fixed for that particular chip - at least unless you're a fan of N900 2012-06-02 23:16 list not yet afaik 2012-06-02 23:16 thumb is for running closed binaries ? 2012-06-02 23:18 well, thumb is a smaller (16bit) alternative opcode set 2012-06-02 23:18 or what's been the question? 2012-06-02 23:19 his interest is in reducing RAM footprint of certain libraries like Qt etc 2012-06-02 23:19 since N900 is in a permanent swap hell 2012-06-02 23:20 ah, i see 2012-06-02 23:20 thumb instruction set is supposed to be ~30% smaller than ARM, but possibly slower in execution 2012-06-02 23:21 i think (conceptually) what thumb is. just never saw anyone actually use it 2012-06-02 23:21 you usually don't even realize I guess 2012-06-02 23:21 you mean s/instruction set/code size/ ? 2012-06-02 23:21 err yep 2012-06-02 23:22 e.g. STE modem is all thumb afaik 2012-06-02 23:22 evil blobs :) 2012-06-02 23:22 sure 2012-06-02 23:24 do you think you could give some guidance what to post to linux-arm ML 2012-06-02 23:26 *my* problem with FreemanG is that our ideas of patch validation differ vastly 2012-06-02 23:26 i'm only an occasional visitor there myself. haven't posted there since openmoko. so i wouldn't have any specific recommendations. just do the usual - describe problem, solution, and see what happens 2012-06-02 23:26 patch validation ? 2012-06-02 23:27 somehow I think such a patch for a silicon erratum has to be validated somehow 2012-06-02 23:27 to be effective 2012-06-02 23:27 and actually target the problem comprehensively 2012-06-02 23:27 well it needs testing, like anything else. if the erratum is version-dependent, it may need a switch, too 2012-06-02 23:28 esp since here we got 2 bugs in chip, with common notion (seemingly based on rumour) being that the already esisting patches are mutually exclusive 2012-06-02 23:30 and my approach is based on building a testbed that 100% reproducably and traceably invokes the problem 2012-06-02 23:30 while FMG's approach is "it's not possible to write such testbed. but ubuntu is all thumb and it runs on my N900 since 3 weeks now. That's proof enough" 2012-06-02 23:32 maybe slightly different rationale and wording, but the general idea AIUI is like that 2012-06-02 23:34 I'm affraid with this approach of his, he won't see benevolent reviews on linux-arm ML 2012-06-02 23:35 he does seem to have a certain, erm, assertive style, yes 2012-06-02 23:35 that's where your comments are welcome 2012-06-02 23:35 kuribas has quit [Quit: ERC Version 5.3 (IRC client for Emacs)] 2012-06-02 23:37 just tell him the key guys on linux-arm have had daily exercise as top of the foodchain bullies for the last 20 years. he's not going to out-stubborn them ;-) 2012-06-02 23:37 well, some of them have. others are gentle :) 2012-06-02 23:37 (version dependent) one of the fixes - published by TI itself - is by setting some bit in auxiliary control register of CPU, to flush branch prediction on every context switch (whatever that means, now that I come to think of it) 2012-06-02 23:38 obviously there is a performance penalty in flushing branch prediction frequently 2012-06-02 23:39 if it's just per context switch, that should be negligible 2012-06-02 23:39 usually yes 2012-06-02 23:40 then there's another bug that kicks in on that (or not), related to commands that flush branch prediction which may result in some nonsensical CPU action (like branching to a destination offset by an unrelated obscure register) 2012-06-02 23:41 and patch for that is to either not use the flush-branch-prediction-queue instructions, or to initialize that random bogus unrelated register to 0, so it won't affect stuff 2012-06-02 23:41 maybe whitequark could write a thumb decompiler for you ;-) then you could recompile the whole mess with something that's actually been tested :) 2012-06-02 23:42 so zero-initialize and flush, to kill both birds ? 2012-06-02 23:42 all disclaimer: IIRC & AIUI 2012-06-02 23:44 yeah, and that's where fun starts: so far nobody was able to do that (except Nokia), as you can access that auxiliary register only in secure mode / context. The secure context gets irreversibly locked during bootloader execution 2012-06-02 23:44 [commit] Werner Almesberger: b2/test/curr: currency exchange test (master) http://qi-hw.com/p/eda-tools/0ba0abb 2012-06-02 23:44 [commit] Werner Almesberger: b2/lang.y (provider): don't allow provider to be redefined (master) http://qi-hw.com/p/eda-tools/994ed00 2012-06-02 23:44 [commit] Werner Almesberger: b2/test/prov: provider database test (master) http://qi-hw.com/p/eda-tools/4184c01 2012-06-02 23:44 [commit] Werner Almesberger: b2/test/Common (run_boom): place inventory after parts and currency (master) http://qi-hw.com/p/eda-tools/e62bb06 2012-06-02 23:44 [commit] Werner Almesberger: b2/test/inv: inventory database test (master) http://qi-hw.com/p/eda-tools/cc5d9a9 2012-06-02 23:44 [commit] Werner Almesberger: b2/: move substitutions dump from parser to boom.c (master) http://qi-hw.com/p/eda-tools/3027dac 2012-06-02 23:44 [commit] Werner Almesberger: b2/: insert a virtual empty hierarchy if test input starts with other file (master) http://qi-hw.com/p/eda-tools/d1593b6 2012-06-02 23:44 FMG now claims he found a "BIOS call" to write to that register from normal linux context 2012-06-02 23:45 OMG :) 2012-06-02 23:45 how can the BIOS write to an "irreversibly locked" register ? 2012-06-02 23:45 it's basically like a usual age old sw irq 2012-06-02 23:46 "BIOS" = ROM bootloader code here 2012-06-02 23:47 so it depends on the location of the executing code ? because it doesn't seem to be locked. else it wouldn't matter what you do once linux runs 2012-06-02 23:47 AIUI there's a way to trigger an exception that switches state of CPU to secure context and same time jumps to the "BIOS" code - just like good old INTxx 2012-06-02 23:48 it's just the RING0, RING-N concept 2012-06-02 23:48 ah, i see. well, if that register doesn't get changed by anything else, then he can put that magic code in the platform-specific initialization 2012-06-02 23:49 and still flush branch prediction on each context switch 2012-06-02 23:49 yep, probably that's what he does, or plans to do, or whatever 2012-06-02 23:49 I not *completely* wrapped my head around all that yet 2012-06-02 23:50 rjeffries has quit [Ping timeout: 245 seconds] 2012-06-02 23:52 Ayla has quit [Ping timeout: 252 seconds] 2012-06-02 23:52 Ayla has joined #qi-hardware