Develop Bugs

unlock CE 6.0 of Windows Phone 7? Is this will help?

Hi
I thought this may be useful to our gurus in development. I am sorry if it is wrong place to post.
Is this a way to unlock CE 6.0 of Windows Phone 7? This I have seen in endgadget. This brings the native CE explorer in Zune. can we use this to bring file explorer in WP7?
Links:
http://www.zuneboards.com/forums/download-openzdk-applications/54495-liberate-explorer-zune-hd.html
http://www.engadget.com/2010/11/01/liberate-for-the-zune-hd-unlocks-hidden-windows-ce-potential/
Thanks,
Ravi

I can't find the source for that exact project (if you have a link, please post it), but I've spent a lot of time looking at the OpenZDK exploit source code, trying to adapt it to WP7.
There are a couple problems. The first is that you need to be able to install an app on the phone in order to get the exploit to work. Zune already allows you to install third-party apps, so the only problem they had was how to break out of the XNA/managed/C# jail. Then they can distribute the breakout as an executable, and anyone can run it. That won't work on WP7 because the only way to install a third-party app is if you have a developer license and the sourcecode. Or you can download it from the app store, but obviously Microsoft isn't going to allow exploits onto the store (they even have automated checking for the kind of exploit they have over at Zuneboards).
The second problem is even if you were able to run random apps on WP7, the exploit still wouldn't work. Microsoft has gotten a lot more serious about security on WP7, and they've closed off all the easy hacks like that (as far as I can tell, of course I'll keep looking). They didn't take security so seriously on WP7, and accidentally gave developers access to an unsafe memcpy(). In WP7 they have a much more robust security model, and closed that off. Which is sad.
I haven't been able to get pInvoke to work on WP7, or even use pointers. You can get the compiler to generate unsafe code, but the runtime on the phone crashes when it comes to any pointer. pInvoke might theoretically work, it's possible I've just been using it wrong, but I've tried a lot of different things and haven't gotten it to work.

Oh yeah, I found the announcement here:
http://www.zuneboards.com/forums/zu...-your-zune-new-version-includes-keyboard.html
Says it's built on openZDK, which means it is using the memcpy() exploit, and my last post wasn't completely off

athompson said:
Oh yeah, I found the announcement here:
http://www.zuneboards.com/forums/zu...-your-zune-new-version-includes-keyboard.html
Says it's built on openZDK, which means it is using the memcpy() exploit, and my last post wasn't completely off
Click to expand...
Click to collapse
I am really sorry, because most of the things you said, i'm not understanding, because I am not a professional developer or for that not even near to that area of coding (am a Pharmacist... my highest knoweldge is little HTML coding).
I am wondering is this will help in any way to access file system in WP7 and build an file explorer kind of app or can we install Totalchrom or resco file explorer kind of app??? using this can we enable bluetooth ftp or internet file download kind of options?
Thanks

lol ya, I guess I should have started with the executive summary. In short, my assessment is no, it doesn't help, because Windows Phone 7 is too different. I really wish it did help.

athompson said:
lol ya, I guess I should have started with the executive summary. In short, my assessment is no, it doesn't help, because Windows Phone 7 is too different. I really wish it did help.
Click to expand...
Click to collapse
+1, unfortunately this won't help us at all.

[singularity]

[SINGULARITY] -
Singularity
Singularity (and the language of such Sing#) is a Microsoft operating system currently on codeplex as RDK 2.0 which is now core to this project - getting Sing# and Singularity to run on ARM (hd2) then can easily boot NT or anything and everything - essentially, NT will happen, but is irrelevant, as need to here first give MAGLDR an d HD2 ability to run Common Language Runtime AND Singularity (.ARM ver of .X86) -
GOAL= make ARM Singularity Kernel run on HD2 then run apps using this core as native apps or strap out onto whatever...
See update on last page of this thread.
ntonhd2 said:
Cotulla: repsonse to your question along with basic test build, just for compile practice run (check for errors), was succesfull; this is for ARM low level bootloader (ARMLDR ) which runs on ARM (hd2, ultimately here) and then grabs LDR (ntldr) then all other files (see my reply) then NTOSKRNL.EXE -> its attached for you to download on next page - thanks again for your input .
NT on ARM:
http://www.microsoft.com/presspass/press/2011/jan11/01-05SOCsupport.mspx
http://www.microsoft.com/Presspass/Features/2011/jan11/01-05SinofskySOC.mspx
http://www.bloomberg.com/news/2010-...ion-of-windows-for-arm-chips-at-ces-show.html
http://thecoffeedesk.com/news/index.php/2009/04/23/net-could-be-key-in-windows-on-arm-netbooks/
http://www.osnews.com/story/24165/Windows_NT_on_ARM_It_s_a_Server_Thing
Please also read my last post regarding Xbox running NT.
And understand I AM TALKING ABOUT NTOSKRNL with Native CLI and not running full WindowsXP or 7 or watever! .
hi xda, put this in hd2 general as could be relevant to linux or wp7 or hd2. Thinking of starting project here of pretty grand scale if people are interested. Now that a lot of work has already been done i think it will not be as hard as it may appear or sound at first.
I am thinking about using new wp7 bldr +- oal +- nk.exe to set up emulation of bios expected on pc then trying to jump to 2003 server equiv ntoskrnl.exe. (and then probably just a native command line interface like alex ionescu tinykrnl project back in the day, a ncli for nt with usb keyboard and not much more to start with: Further dev much later).
Nk will handle underlying lack of pci, bios, ints, and addresses, (+is firmware) but actual switching to nt kernel is for real after that: To build a strapping kernel with ce7/wp7 architecture and initial drivers that goes on to then launch full nt kernel.
Yeah - i have \nt\private\ntos\ source code and no it is not the normal nt4 or other w2k leak- it is a complete and buildable kernel; pm me and i will give proof, or the code if you can build and want to work on this. This is not x86/x64 work obviously so is not for those without ability: Need to do some heavy lifting to get recompile build happening for arm, qualcomm ' snapdragon nt :d. Otherwise is only emulation and not a good idea. This is 2be real. As non-x86/x64 support for nt (nt4 did ppc, mips, and now ia64) this kinda porting is not a foreign concept: There is sufficient info out there with reference to everything from softpc.new (inside ms code) to wow64cpu.dll and other x86/x64 specific init routines, spinlock and interrupt handling, asm code samps, bochs methods, qemu methods, et.al. Which can be used in one way or another or taken over if required: If all taken into account to paint big picture: Use of emulation technology methods for non-emulation project just opens up underlying logic. That is it. This is also why i suggest using wp7/ce7 base 4 init. Do not want emulation. Real deal here only. I refer to all these items above as observations which could be taken into account if need be: From tinykrnl, reactos, bochs, wine, efi, and other such things can make porting over kernel easier: At the end of the day, ce7/wp7 ' bldr, oal, nk.exe (or whatever derivatives thereof) will be 'firmware' in big picture. Another reason i am considering wp7 as base to strap is drivers are there to make a ce+bios or efi-type (?) pre-loader that takes all ce7 initialization further and passes on to nt (nk.exe runs including all setup as would be done by ntldr, a fake or psuedo-real ntdetect.com, system.hiv then passes data structs to our ntoskrnl.exe) and do all that needs be done. I can handle pc side completely but need bit of help with someone who gets nkglobal and other structures and use of platform builder with experience prefered in creation of new bsp. Maybe other ways - instead of ce, ie- grub, linux, openbios, openefi, but either way just want to prove it could be done is all.
Click to expand...
Click to collapse
anybody here capable?

to quote Da_G:
Yup, RustyGrom pretty much has it covered. First, it's called "CE" for Compact Edition, and this is not a misnomer in any way. The system is designed to be as compact as possible (There are build-time switches for everything, so you can toggle off nearly all the components to acheive a very "light" image) obviously, including drivers for components not present would be a waste of space, as they would never get used. So there are none included. On the PC side of things the BIOS provides a basic level of functionality using a standard interface so generic drivers are created to bring the platform up to that level, and from there vendor-specific drivers can be loaded.
If you want to put an embedded device in terms of a desktop computer and loading Windows 7 on it, you start out with a fully assembled computer (video card, motherboard, cpu, ram, etc.) - power it on. It loads up the BIOS which initializes the basic hardware and begins to load the rest from the hard drive. The embedded device loads up the NAND XLDR, which provides only flash read/write support. The XLDR then loads the "EBOOT" or "IPL" into ram on typical devices. HTC doesn't use the EBOOT/IPL model as such (here already we're breaking away from the "standard" even further) and instead has that split out into mARM AMSS (a custom designed RtOS that loads and runs the Modem ARM CPU) and SPL. Once the AMSS loads the SPL into ram and executes it, the SPL initializes the aARM (apps ARM CPU), does various checks (are we in update mode? do we need to expose a flash interface to update the rest of the OS? do we just boot up the os and move aside?)
Then finally you get past the highly device-specific code and on to the (slightly) more generic CE Kernel/drivers which get copied into ram by the SPL and executed (Native Kernel/XIP partition)
So, how different is CE7/WP7 from that model? (Which is the model we have now in CE5.x/WM6.x) - The mARM AMSS provides a different interface and initialization proceedure. That means any of the WP7 drivers from a donor device we might port from would not work at all with our current AMSS. Which in turn means no boot without re-writing the drivers/kernel or AMSS.
So to compare it to a desktop PC once again, we need to write a BIOS, a Hardware Abstraction Layer, and a set of drivers for each component on the system (likely a good deal of the drivers would be usable once the rest is done)
Do I sound jaded yet? Yes, yes I am It's probably a factor of 10 more complicated than I thought it would be initially.
Here's the JTAG pinouts that need to be connected, btw. There are pins on both sides of the motherboard which also is truely a pain in my ****, as i originally intended to mount an external port on the HD2 so I could easily keep a JTAG connection with it, but you basically have to remove the entire motherboard to maintain a reliable connection, which really precludes running it on a live device.
Click to expand...
Click to collapse
JTAG working now .

Ummm expect to hear from Microsoft lawyers in 5....4....3....

RustyGrom said:
Ummm expect to hear from Microsoft lawyers in 5....4....3....
Click to expand...
Click to collapse
Yeah i would be in breach of the non-disclosure-agreement i signed so removed.
But i am in inner city cbd wifi hotspot area and jump around unsecured cafe signals and other businesses and also use proxy servers and..... on top of that..... my own added tweaks for safe measure!
so, cafe+wifi+proxy, +other_anon, means there is absolutely no chance.

RustyGrom said:
Ummm expect to hear from Microsoft lawyers in 5....4....3....
Click to expand...
Click to collapse
reading your stuff on ce7. is this a bad idea you think? or not possible? no interest? i think it can be done.

ntonhd2 said:
reading your stuff on ce7. is this a bad idea you think? or not possible? no interest? i think it can be done.
Click to expand...
Click to collapse
I just don't think it's possible or worth it to bother trying to port NT to ARM while Microsoft is doing the same already. You're not going to be able to put together the team required meanwhile hiding from MS. It's just a stupid idea imo and really has no benefit. I mean what's your end goal here? To run Win7 on our devices?

Judging from this and other posts you have made, I suspect the most "source" you have is the "Windows Research Kernel", which is the source for a portion of ntoskrnl.exe from Server 2003 SP1, approximately. That would be no-where near enough, and it's not even enough to compile "just a kernel". It actually has a number of pre-compiled parts that it just pulls in.
Not to mention such a project is just asking to get shot down in a legal firefight. The WRK is given to academic institutions for studying the world's most popular desktop kernel, and is done so under a strict NDA.
ntoskrnl.exe by itself isn't enough to produce a workable OS anyway, especially one from the Server 2003 era.

hounsell said:
Judging from this and other posts you have made, I suspect the most "source" you have is the "Windows Research Kernel", which is the source for a portion of ntoskrnl.exe from Server 2003 SP1, approximately. That would be no-where near enough, and it's not even enough to compile "just a kernel". It actually has a number of pre-compiled parts that it just pulls in.
Not to mention such a project is just asking to get shot down in a legal firefight. The WRK is given to academic institutions for studying the world's most popular desktop kernel, and is done so under a strict NDA.
ntoskrnl.exe by itself isn't enough to produce a workable OS anyway, especially one from the Server 2003 era.
Click to expand...
Click to collapse
Sigh.. why don't people read before they make these ridiculous and thoughtless posts? Realize that there are people from Microsoft ON these threads. Also, RESEARCH IN DEPTH BEFORE POSTING SUCH A THREAD.

snickler said:
Sigh.. why don't people read before they make these ridiculous and thoughtless posts? Realize that there are people from Microsoft ON these threads. Also, RESEARCH IN DEPTH BEFORE POSTING SUCH A THREAD.
Click to expand...
Click to collapse
There are more microsoft people on xda than most realize .

RustyGrom said:
I just don't think it's possible or worth it to bother trying to port NT to ARM while Microsoft is doing the same already. You're not going to be able to put together the team required meanwhile hiding from MS. It's just a stupid idea imo and really has no benefit. I mean what's your end goal here? To run Win7 on our devices?
Click to expand...
Click to collapse
sure, sourcecode factor (nda) and secrecy/MS are complexities: but not as hard as people think here: it is TWO COMPLETELY DIFFERENT THINGS TO TRY AND GET WINDOWS7-ON-ARM to what I suggested (NT-CONCEPT-ON-ARM-WITH-Native-CLI) and no I would not use WRK sourcecode (lol) as part of my daywork i have access to (not ce) full sourcecode.
see my last post here,
can be done .

hounsell said:
Judging from this and other posts you have made, I suspect the most "source" you have is the "Windows Research Kernel", which is the source for a portion of ntoskrnl.exe from Server 2003 SP1, approximately. That would be no-where near enough, and it's not even enough to compile "just a kernel". It actually has a number of pre-compiled parts that it just pulls in.
Not to mention such a project is just asking to get shot down in a legal firefight. The WRK is given to academic institutions for studying the world's most popular desktop kernel, and is done so under a strict NDA.
ntoskrnl.exe by itself isn't enough to produce a workable OS anyway, especially one from the Server 2003 era.
Click to expand...
Click to collapse
What does this statement really mean?
might be a bad idea on hd2, fine, accepted, but your comment at the end doesn't make sense to me. so, ntoskrnl.exe for wp7 or nt4 (another era than 2003 .net) would make a difference? that is silly. besides, i made it clear that a psuedo-firmware setup would be required to setup the datastructures that NTLDR would prepare (along with NTDETECT.COM, and bios+pci_bus+ACPI interaction, (plus system or setupreg.hiv)), etc: so what are you saying exactly? my point was to not run any win32 or win64 gui or subsystem. never even mention win32k, gdi, etc. I was very clearly talking about native cli (ntdll.dll) and a prompt- maybe usb keyboard- as ARM NT Conceptual. Please, enlighten me . PS> yeah, I know the wrk and am fully aware of \prebuilt\ libraries and obj code: but, no, I was not intending on using this as base. I admit, hd2 nt prob bad idea: btw was ARM NT concept more than anything! and yeah, with the secrecy and legal issues it would be too complex and overwhelming to do so, accepted, but if I were truly to do this NO i would not use WRK lol .
And regarding Microsoft, yes, I accept that there are a LOT of employees on xda and it is crawled and watched for obvious reasons: covered that.
PPS> re WRK, no, would (if i were to try doing this that is) use what I already have access to as part of my work> under full NDA I have full source to a few different bases including all of 2003 and even HyperVServer and AzureOS trees. .
unfortunately I do not have windows phone 7 code access though! Thanks.

RustyGrom said:
I just don't think it's possible or worth it to bother trying to port NT to ARM while Microsoft is doing the same already. You're not going to be able to put together the team required meanwhile hiding from MS. It's just a stupid idea imo and really has no benefit. I mean what's your end goal here? To run Win7 on our devices?
Click to expand...
Click to collapse
Yep...... but there is a LOT of portability in the original nt4 and even w2k trees with alpha, mips, ppc, os2+posix, original softpc.new+ntvdm, and even newer, that would let this be done a lot easier than most realize: remember here that:
I AM NOT SAYING LETS RUN WIN32 ON OUR HD2: I AM SAYING LETS TRY RUN NTOSKRNL ON ARM.
big difference guys.
RustyGrom, I assume your talking about ARM-Cortex etc (msnt-2-arm)..... THIS is what i wanted to do but a much more lightweight and ms-testing-protocol-free-process; homebrew version in experimental state would ensure much speedier development: it is not that hard a concept to attempt to port over an earlier (nt4 or w2k) kernel FIRST then look at better (2003 & 7) memory management etc: the point here is PROOF OF CONCEPT NT ON ARM: that is it, like what you refer to. Read my first post: any remember tinykrnl.org? Alex Ionescu ? Reactos? it could be done a LOT easier than you all think!
only NT on ARM official stuff i am aware of is this (rumour/talk/concept/theory/design atm):
http://www.microsoft.com/Presspass/Features/2011/jan11/01-05SinofskySOC.mspx
http://thecoffeedesk.com/news/index.php/2009/04/23/net-could-be-key-in-windows-on-arm-netbooks/
http://www.osnews.com/story/24165/Windows_NT_on_ARM_It_s_a_Server_Thing
If you know NT like i do- then you would see it could readily be done but yes, I admit I do not know enoug about 'phones'/ce-platform. That's why I started THIS THREAD HERE: to get some thought on the subject is all .
what then would be major problems to overcome then and this is assuming concept of say:
0). hd2 power on
1). ipl/equiv
2). hspl.
3). magldr
4). dft leo70 rom
5). bsp/oal, bldr/uldr, OS.NB ->(NK.EXE).
6). remap, reinit, load and place (prep) data structures expected by ntoskrnl.exe (osloader, detect, pci, bios, etc).
7). jump to ntoskrnl.exe
?

For the record, a few years ago i did this exact thing: ported nt kernel over to another platform. myself and others re-wrote ntoskrnl.exe (+hal+drivers) and integrated osloader.exe(ntldr), and all data structures as would be passed to kernel from ntldr, registry system hiv, ntdetect, missing bios, missing interrupt+dma+pci-bus+acpi+power, etc into one (debug/xdk) single DEFAULT.XBE.
it only worked on XDK debug kit xbox consoles with serial+scsi+128mbRAM (and a custom lpc debug mod) but it worked. using code from intel and tianocore EFI/UEFI toolkits (and bits and pieces from here and there) and concepts such as PALcode as used by non-x86 osloader (.exe not ntldr) for simulacrum bios/firmware you can pass a predefined set of structures to ntoskrnl and ensure processor regs etc ARE ALL GOOD AND SYSTEM IS READY then call into KiSystemStartup, ExpInitializeExecutive, and begin modified phase0 of NTOSKRNL.EXE.
similar thing was done with CE.NET for Xbox - a default.xbe with linux code b4 NK.NB0
worked and works .

anyway, how u wanna solve the next problems?
1)missing CL compiler for ARM with same set of features like CL for X86.
(CL version for ARM for WCE doesn't have all features supported and usually outdated)
2)this ARM compiler store exception info in other format (not SEH frames, but universal table for functions ".pdata")
3)which files u exactly wanna build for ARM? is it "ntoskrnl.exe bootvid.dll hal.dll"?
4)which final results u gotta got?
5)why u need touch WP7? u can just look to example code in Android kernel and implement something. so replace PC standard timer realization inside HAL.dll with QSD8250 specific timer code. it's much better to start.
how many ppl u have in ur team?

Cotulla said:
anyway, how u wanna solve the next problems?
1)missing CL compiler for ARM with same set of features like CL for X86.
(CL version for ARM for WCE doesn't have all features supported and usually outdated)
2)this ARM compiler store exception info in other format (not SEH frames, but universal table for functions ".pdata")
3)which files u exactly wanna build for ARM? is it "ntoskrnl.exe bootvid.dll hal.dll"?
4)which final results u gotta got?
5)why u need touch WP7? u can just look to example code in Android kernel and implement something. so replace PC standard timer realization inside HAL.dll with QSD8250 specific timer code. it's much better to start.
how many ppl u have in ur team?
Click to expand...
Click to collapse
************************************************************
update: Attached is ARM low level bootloader just built; this could be used to load LDR and then ntoskrnl.exe .
************************************************************
Please let me know your thoughts and please try to get this to run with debug if you can and pass results & thoughts back to me - Cheers. Hopefully it built ok. What do you think of using this method then? but with FULL & PROPER NTOSKRNL.EXE!
************************************************************
Hi Cotulla, thanks for your reply: appreciate it here.
[also much thanks for hspl, magldr, dft android, leo70ROM. .]
ok, sorry if this is a bit all over the place, i have cut and pasted my answers around to try clean it up but it is late and i think my brain is a bit dead sorry, but answers are here anyway . hope makes sense. firstly please have a look at this video and let me know what you think .
http://www.youtube.com/watch?v=RFNuY2OFRjU
that is ARM..... i am going through build environment and sourcecode now..... thoughts?
http://www.youtube.com/watch?v=n3v4YC9RT-g&feature=related
can learn a lot from wine. i agree with you on linux. same for virtualization, emulation, etc, like bochs qemu everything . sandboxing and hypervisor unveils a LOT . another thing i wanted to ask you was what do you think of FPGA technology for reverse engineering unknown systems? for example, if i were to start almost any project, like say leo70DFTrelease, or NT on Xbox, or whatever, doesnt matter, i think it is worth spending the time or money (for private company to do it for you) and have an FPGA version of the target device being hacked (hd2 in leo70rom case) and then undo the software problems from a hardware logic perspective. just the way i have worked on things many times and it works for me anyway. but I digress.......... . if i were to have done wp7hd2 (leo70rom) and magldr, then i would have had to have had (for me, not as good a dev as you) a FPGA based HD2 made up that ran in every way same but with which i could get right in there and do whatever i needed to do to see response& debug. let me know what you reckon... ok... digress now :
1)missing CL compiler for ARM with same set of features like CL for X86.
(CL version for ARM for WCE doesn't have all features supported and usually outdated)
what features specifically we need here?
what about tweaking this:
http://reactos.colinfinck.de/files/RosBE-Windows/RosBE-ARM-1.0.exe
2)this ARM compiler store exception info in other format (not SEH frames, but universal table for functions ".pdata")
http://www.reactos.org/wiki/PSEH
http://www.reactos.org/forum/viewtopic.php?f=9&t=5716
reading up on _IMAGE_CE_RUNTIME_FUNCTION_ENTRY. just going over stacks and frames and overall exception handling on ARM. are there any issues with reverse execute, virtual unwind? for this type of execution- how would you handle?
more to the point- how would you do this project lol.
problems with prolog/epi? what about moving over x86 asm code? i am right now typing this to you whilst getting updated on specifics on registerslooking at emulators to see this in action. i am reading these here. let me know if on right path and please put up links to whatev will make this project concept a reality . Cheers .
see here
http://www.cl.cam.ac.uk/~mwd24/phd/swarm.html
http://gcc.gnu.org/onlinedocs/gcc/ARM-Options.html
http://www.codeproject.com/KB/threads/StackWalker.aspx?msg=2818356
can you recommend any compiler, emulator, os, setup, even equipment (JTAG etc etc) i should use, buy, try?
3)which files u exactly wanna build for ARM? is it "ntoskrnl.exe bootvid.dll hal.dll"?
depends on method: i agree (see below) that probably android or (htc-)linux is probably more likely to work but leo70_rom made me think maybe jump from (touch wp7) nk.exe? and are you saying use linux as in LinuxBios type setup?
would need emulated bios, pci bus fixed up (?), QSD timer HAL, ACPI (?), etc ,,, so probably would end up with the following:
a) BIOS (ce7 exe or linux ?): options here could be to make NT think it is running on PALcode, uEFI, or standard ACPI BIOS (your thoughts?). I think uEFI (tianocore/Intel) is best bet here perhaps. this would include MBR code (efi equiv or pal equiv depending) and any psuedo-real or "real" initialization i think.
b) mbr execution merged to and included in above, bootsect. in sim' 'firmware'.
c) $LDR$ @ OSLOADER.EXE (osloader.exe is non-x86 ntldr as im sure you know WITHOUT the code to run ntdetect.com and acts in PALcode architecture to pass on predefined data structues from firmware: tells NTOSKRNL.EXE where and what 2 execute).
d) HAL.DLL (timer, power/acpi, spinlocks, interrupts). another reason i leant towards WP7 as pre-NT launcher is because i assumed that something like BSP, OAL, etc, could be maybe used as base: if not for code, then logical base. what base(s) did you use to create WP7 if i may ask? ie: CE7? I have just installed Platform-Builder. but yeah, i here you regarding android/linux kernel example: ultimately are you saying better, easier, more logical, to go with android/linux you think Cotulla?
e) BOOTVID.DLL
f) KDCOM.DLL (if wp7 would make use of KITL?)
g) drivers as required including the following: ntbootdd.sys (?) might allow easier diversion from bios lack of INT13 and other support: remap to whatever can handle this properly. equivalents for ACPI.sys, filesystem drivers, other power, basics. how should i be looking at things from NT side of things, as in \ObjectTypes like \??, \Global?? etc .... and items like ROOT device in ARM (either CE or linux preloaded) context? any thoughts on how object manager would need to be brought up? for me, now, that is where it gets crucial and is core.
h)SMSS.EXE (NATIVE.EXE) but to begin with could just get drivers and all that working first and strap up into cmdcons (SPCMDCON.SYS). just blue-screen SMSS (windows setup) enough to prove kernel to run on ARM cpu. your thoughts?
i) SYSTEM reg key hive (setupreg.hiv etc?)
...
4)which final results u gotta got?
Tinykrnl type native CLI.
http://www.betaarchive.co.uk/imageupload/1193217573.or.99024.jpg
with USB keyboard support like htc-linux then go from there..... would love a prompt from which could just call any given call - be it CreateProcess or NtCreateProcess or ANYTHING: and it just does it (with debug/KITL) without question . but native NT command line is good for now. not going near win32.
5)why u need touch WP7? u can just look to example code in Android kernel and implement something. so replace PC standard timer realization inside HAL.dll with QSD8250 specific timer code. it's much better to start.
yeah....
I thought linux probably would end up being better: just liked symmetry of windowsCEx-strapping-windowsNTx: making a windowsCE-EFI/BIOS: but yeah, something like LinuxBios (android kernel etc) would be a lot easier in the end yeah? All this is overly simplified and very conceptual but there are basic answers. . once a solid idea has been formed then this could actually be done i think. and before Microsoft . Do you believe Reactos-ARM-build environment could be used? Am i missing anything? 9 people team+myself (+any help you can offer) would make 10 (+1). I think this is a good idea to at least try and i believe with your assistance, guidance, well, it would get done and then complete the HD2 line up fully. . In conclusion, right now, I need ARM emulator software, platform builder, and fully working Compact Edition 7 on HD2 to get some more thoughts and try few things out in platform builder debug then can get final decision, design, plan and start to get everything working. Even though will probably go with Linux/Android obviously as above, I still need 2see init on CE7 on HD2 and be able 2use this along with whatever else we can! have a look at all above links... thanks.
Cotulla, thanks again 4reply>please PM [email protected] something but not posting..... await your PM.
what about this ( http://research.microsoft.com/en-us/projects/singularity/ ) could be of use to NT port with respect to CLR ? haha, or just outright hd2 port Microsoft RDK OS ' singularity ' ? .
************************************************************
update: Attached is ARM low level bootloader just built; this could be used to load LDR and then ntoskrnl.exe .
************************************************************
Please let me know your thoughts and please try to get this to run with debug if you can and pass results & thoughts back to me - Cheers. Hopefully it built ok. What do you think of using this method then? but with FULL & PROPER NTOSKRNL.EXE!
************************************************************

I don't have big knowledge of Windows NT system, but I think it's must be enough to provide basic stuffs for kernel start up.
I guess NT using only int13 services for reading data from disk, int15 services used to detect memory configuration and int10 for initial boot mode.
Because it's embedded hardware, the devices in the system are fixed and limited. So it's enough to provide fixed values for kernel, like available ram memory range.
No need of using any complex systems with CE / Linux.
About CE, you can get almost full kernel sources in PB6.0, trial can be downloaded from MS site.
afaik it's enough to load kernel and dependent modules (drivers) to ram and then run them. after this action kernel drivers should able to run properly on hardware.
About Reactos, I appreciate work of involved people, but I doubt that it's stable
About this project, I don't know yet if I will contribute. I am looking how much it's interesting for me
I always have interesting different things in my hobby as well, so I have choose that to do As well, me is part of DFT team, I need discuss it with them
Now I am asking you to understand more details about your idea(s)

Cotulla said:
I don't have big knowledge of Windows NT system, but I think it's must be enough to provide basic stuffs for kernel start up.
I guess NT using only int13 services for reading data from disk, int15 services used to detect memory configuration and int10 for initial boot mode.
Because it's embedded hardware, the devices in the system are fixed and limited. So it's enough to provide fixed values for kernel, like available ram memory range.
No need of using any complex systems with CE / Linux.
About CE, you can get almost full kernel sources in PB6.0, trial can be downloaded from MS site.
afaik it's enough to load kernel and dependent modules (drivers) to ram and then run them. after this action kernel drivers should able to run properly on hardware.
About Reactos, I appreciate work of involved people, but I doubt that it's stable
About this project, I don't know yet if I will contribute. I am looking how much it's interesting for me
I always have interesting different things in my hobby as well, so I have choose that to do As well, me is part of DFT team, I need discuss it with them
Now I am asking you to understand more details about your idea(s)
Click to expand...
Click to collapse
sure....... . anything ReactOS -freeldr, any arm code, whatever, is just to get basic idea up- to see the actual jump whilst watching (be it by jtag, kitl, usb, or telepathy interface to QD) and go from there; although im sure you could use ReactOS arm code lowlevel bootloader to jump into EITHER "freeldr" or proper "ntldr" or "osloader.exe" (modified of course to have no pci bus scan and the rest.....) that is the dilemma: either jump COMPLETELY like winmo6-android with all structures setup DIRECTLY INTO KERNEL and avoid the whole LDR side of things in that sense anyway; or, well, totally from scratch rebuild loader and subsequently deal with 'firmware' issues... i really do not care in the end if its a jump from one kernel to another (one os to another) because project here is to RUN NT ON ARM/HD2 and not to necessarily have it homogenous down to LDR.
as long as thread, memory, native api, other calls, all that, is truly ntoskrnl = you are running nt on your arm hd2! .
LDR does not matter.... total new rebuild or jump.... whatever comes first .
Thanks Cotulla, yes, we understand where your coming from re do not need linux, ce, and complexities there and i agree: just want to use these for initial testing and deployment of early code with some kitl, debug.... on other notes, trying to put all into organized groups, slowly but surely yes, with bit of faith we will get there in the end .
if totally up to me i would probably take intel/tianocore EFI specification as the base if this could somehow be easily made to run on ARM in this particular context. ie EFI on a HD2!
look at this raw control power!>>> http://www.ami.com/support/doc/AMI_Debug_UEFI_Dsheet_PUB_2008-06-10.pdf
also along these lines, just briefly (is helpful in concept design):
http://x86asm.net/articles/uefi-hypervisors-winning-the-race-to-bare-metal/index.html
http://sourceforge.net/projects/gnu...orig.tar.gz/gnu-efi_3.0h.orig.tar.gz/download
http://x86asm.net/articles/introduction-to-uefi/
http://sourceforge.net/projects/efidevkit/
http://www.logic.nl/Products/Technology/BIOS-and-EFI.aspx
ok, summing up thoughts here>>>
0) object manager and objects; going over arm & ce7, as well as winmo6 and other ce, and comparing with nt and win32/64; just looking at how on final arm release, the \ObjectTypes will be different in the end. very interesting stuff.
1) LACK-OF. no pci bus which is highly expected by ldr/detect so make kernel prob see system in 'PALcode' or EFI mode. pass ldr data structs to kernel in that type of form. otherwise gets very messy and we are not going to hack around because you will end up with an emulator !. this will work but key is determing what 'firmware' passes this data to nt kernel - not from our perspective- but as NT.
2) BIOS. INT services are not used by kernel in that way after it becomes supervisor so will redo drivers unless preload remap somehow. INT only there during ntldr (or can load in ntbootdd.sys to supply these) and this is all pre-phase0 and is very early on.
3) HAL and clk
4) INT services are not used by kernel in that way after it becomes supervisor so will redo drivers unless preload remap somehow. INT only there during ntldr (or can load in ntbootdd.sys to supply these) and this is all pre-phase0 and is very early on.
5) kitl and kdcom
6) registry to pass on (setupreg).
8) filesystem, screen, other drivers
9) final native cli (ntdll.dll) or maybe initially just spcmdcon.sys.
above not in order ..... sorting it all out though .....
ok, looks daunting but like i said before you could get up an nt kernel in setup mode with setup ldr and drivers and old blue screen "dos" mode native subsystem which uses the SMSS.EXE and NTDLL.DLL that are seperately contained in \i386\system32\ or \cmdcons\system32\ - very limited subsystem but is full nt os at kernel . so........ if not ce and not linux preloading, WOW . it is quite an amazing project but doable; so basically just need to see how this armldr (low level strap - be it Reactos or my own clean job- will do both) code runs on the device itself and step by step add the rest in as required! but i still believe actual dev be better jumping from preexisting environment having kitl or some sort of serial or usb debug already there and then working way down to lowest possible level; so, basically, working backwards down to processor.
Doing it all from scratch and CLEAN . (in the end!). .

my brain just straight up exploded.
thanks a lot.

http://www.youtube.com/watch?v=xKc_XGuvNIk .

for the record:
so far without any errors have successfully been able to build the ntdll.dll, hal.dll, smss.exe, bootvid.dll, fastfat.sys, for ARM with no modifications at all, but not yet done a build on the LDR or NTOSKRNL.
just testing compiler here is all and not writing new: this is very early on and i have changed absolutely nothing.
once fill in gaps will give it a go on hd2.
attached.

[WORK IN PROGRESS] XML Provisioning for all devices...

At the moment I'm working on an app called "WP7 Root Tools". I got the registry editor almost finished, but I am also going to add a File Explorer, Certificate Stores and maybe more. When the registry editor is working I will release the first alplha-version. As the title of the app implies, the tool uses root privileges to perform queries and transactions. I let the tools parasitize other processes to get the code executed in the TCB chamber of the device. I have this working stable now on my Samsung Omnia 7. Unfortunately I have to use a little bit of device-specific API's to do this. And I have to make quite a detour to make it work, which has a negative impact on the performance.
So the ultimate goal is that, in the end, this will work with other, more direct API's, which work on all devices. During my research I found some possiblities that need more investagation. I already decided that I will first concentrate on getting this working with my Samsung device, so that I have at least the tools to do further research. But I thought I'd drop some of my findings here that may lead to better device-support and better performance for future-versions of the tools.
There are many ways that may lead to executing code with elevated or root privileges. But in this post I want to concentrate on XML provisioning. A lot of info can be queried and configured through these API's. I have tried to call the native OS functions for XML provisioning. The function you need to call is: DMProcessConfigXML(). And it is declared in: Cfgmgrapi.h. If you call this function it returns errorcode: 0x4ec (or 0x800704ec), which means "Access disabled by policy". If you use a native COM dll and you forget to add ID_CAP_INTEROPSERVICES to the WMAppManifest.xml, you will get the same errorcode when calling a native function through the COM-interop. So when I get the same errorcode when calling DMProcessConfigXML() this may suggest, that I might be missing a capability in the WMAppManifest.xml.
In another thread on this forum some undocumented capabilities were discussed. One of them was ID_CAP_WAP. Since OMA Client Provisioning is also call WAP-Provisioning, I thought that might be the missing capability. I was not able to add the capability from within Visual Studio, because the capability is missing from the corresponding xsd's so it will give an validation error on building the project. But I could add it manually after the project was build. When I deploy it to the device, using the Application Deployment tool, it would return "Access is denied". I thought it might be an invalid capability, but when I changed the capability to ID_CAP_XXXXXX that would return "Install failed. Fix the capabilities." which is the real error message for an invalid. That implies that ID_CAP_WAP is in fact an existing capability, but I'm just not allowed to use it. When I would be able to use it, I would probably have access to the function DMProcessConfigXML(). That part of the app would be impesonated into higher chambers.
So the big question is what is keeping me from using the ID_CAP_WAP? Why am I not allowed to use it? I tried to attach a debugger to XapDeploy.exe, but it does not throw any exceptions at all. The errorcode is generated in the phone. Getting this fixed will give a big boost to getting closer to root access on all devices. Any help or insight on this will be appreciated.
Heathcliff74

I sent some tweets to da_g, chris, chevron, julien schapman, and a few other devs to let them know this is going on...I'll try tom hounsell too he may know a bit more about this
I'm notifying notebookgrail too because he has been doing some work with dell venue pro devices
Good luck

At a wild guess, it's probably looking for a signature. Using signed code for trusted functions is the kind of thing MS likes to do. :-/
All that said, if you have ProvXML working on Samsung, I would *love* to take a look at it. I'm maintaining a cross-platform Homebrew library. Currently I have at least partial ProvisionXML on HTC and LG, but none on Samsung. I don't have a Samsung device to test with, which is making it hard to try things out...

ID_CAP_WAP isn't a capability you can assign yourself. A higher up has to assign it to you.
<!-- Account loaded from: W:\WINCEROOT\temp\oakcopy28570\Release\x86\XDE\Policy\cb659c75-eac9-4db7-afd8-055632acf233.policy.xml(292,2) -->
<Account Id="S-1-5-112-0-0X71-0X49445F4341505F574150" Description="Autogenerated group for capability ID_CAP_WAP" FriendlyName="ID_CAP_WAProvides access to WAP API" Type="Group">
<!-- MemberOfGroup loaded from: W:\WINCEROOT\temp\oakcopy28570\Release\x86\XDE\Policy\cb659c75-eac9-4db7-afd8-055632acf233.policy.xml(293,2) -->
<MemberOfGroup GroupAccountId="S-1-5-112-0-0X71" />
Click to expand...
Click to collapse
(BasePolicy.xml)

domineus said:
I sent some tweets
Click to expand...
Click to collapse
Thanks.
GoodDayToDie said:
All that said, if you have ProvXML working on Samsung, I would *love* to take a look at it.
Click to expand...
Click to collapse
Well, the whole ProvXml stuff will become irrelevant, when I finish the tools. Because ProvXml is not really user-friendly and my tools will provide that functionality in a user-friendly fashion. So at this moment I want to concentrate on finishing the first alpha-version. Later on, I will probably clean-up the code and release it. But it's quite complex, because I added async multithreading to keep it all smooth.
WithinRafael said:
ID_CAP_WAP isn't a capability you can assign yourself. A higher up has to assign it to you.
Click to expand...
Click to collapse
Thanks for this info. But what I read from this is that you just need to be able to impersonate. Has anyone tried CeImpersonateToken() with this SID?

Abstraction of the ProvXml capabilities is awesome, assuming that we can fully use them and/or extend them if needed. It's useful for a ton of stuff. I've written a small amount of abstraction for registry writes and such, but having the full functionality exposed through a clean API would be fantastic.

the key to hacking the KIN

the key to hacking this phone, as ive noticed, isnt getting a new os. ive paid attention and i think i know what to do. we need a new internet browser. if you think about it, the browser is the problem because of its zero functionality. what we need to do is make an html parser in java that is invoked in javascript (dezgrz thx for finding out about the javascript apps). i think we should focus on getting this done.

Its a good idea but we have no way of uploading a new browser to the device.

X-15D9W8491 said:
the key to hacking this phone, as ive noticed, isnt getting a new os. ive paid attention and i think i know what to do. we need a new internet browser. if you think about it, the browser is the problem because of its zero functionality. what we need to do is make an html parser in java that is invoked in javascript (dezgrz thx for finding out about the javascript apps). i think we should focus on getting this done.
Click to expand...
Click to collapse
Your post makes no sense.
First because that's not the key for hacking
Second cause java applications can't be invoked from javascript.

it does make sense @johnkussack
is does make sense. you can invoke a java app through js. quit criticizing me just because you dont know what youre talking about. and besides, what i meant to say (if this makes it easier to understand) is that we code a java app onto the phone that automatically connects to the browser and a download is set off in javascript that bypasses anything written into the browser by editing the permissions, etc by editing the browser and just making a new one and not being lazy. you of all people should know this makes sense because you programmed and app onto the kin! besides, the whole thing about hacking is to be optimistic or you never get it done and youre impeding development with stupid posts like your last. get a grip and post something important instead of that trash next time!

thats the point
WEM97 said:
Its a good idea but we have no way of uploading a new browser to the device.
Click to expand...
Click to collapse
exactly my point. we could just create a new app like john did only we make it work like john obviously failed to do.

X-15D9W8491 said:
exactly my point. we could just create a new app like john did only we make it work like john obviously failed to do.
Click to expand...
Click to collapse
~~~~~~~~~~~~~~Forgotten~~~~~~~~~~~~

X-15D9W8491 said:
nonsense stuff
Click to expand...
Click to collapse
First of all, you'r messing it all
Second, to run a java application you would need to have a java virtual machine (which kin has not), or interpretation for java applets (which kin has not).
Third, i do know what i talk about, cause i code in Java & Javascript.
X-15D9W8491 said:
is that we code a java app onto the phone that automatically connects to the browser and a download is set off in javascript that bypasses anything written into the browser by editing the permissions, etc by editing the browser and just making a new one and not being lazy.
Click to expand...
Click to collapse
Here one could stop reading. Also you can call Kitt to try to hack it, but it may not answer.
So, do your work before saying that other have failed where you have no success either.
And if we could do that magic stuff, last thing we should do is care about a new browser, when you could just install opera for win ce. So all the topic is going nowhere.

johnkussack said:
First of all, you'r messing it all
Second, to run a java application you would need to have a java virtual machine (which kin has not), or interpretation for java applets (which kin has not).
Third, i do know what i talk about, cause i code in Java & Javascript.
Here one could stop reading. Also you can call Kitt to try to hack it, but it may not answer.
So, do your work before saying that other have failed where you have no success either.
And if we could do that magic stuff, last thing we should do is care about a new browser, when you could just install opera for win ce. So all the topic is going nowhere.
Click to expand...
Click to collapse
first, i havent had any success yet because those were plans. i havent tried this yet.
second, if putting on opera could help, why didnt you do it, "genius"?
if this thread is going nowhere then do me a favor and stop posting on it!

piss off
soninja8 said:
You sound like a smart-ass. You think its so simple that you decide to make fun of John. Without John we wouldnt have done anything by now so you should just shut it.
Click to expand...
Click to collapse
that post was an a and b conversation between me and john so c your way out, dumbass. and you should shut it because you havent really helped at all, john has gotten me nowhere because i started from the beginning before i was part of this, and i need absolutely no input from you.

X-15D9W8491 said:
second, if putting on opera could help, why didnt you do it, "genius"?
Click to expand...
Click to collapse
because we don't know how to do that yet.

I don't own this device, but a friend does. What happens if you download an exe or cab from the browser?

xboxfanj said:
I don't own this device, but a friend does. What happens if you download an exe or cab from the browser?
Click to expand...
Click to collapse
It tells you the file type is not supported. Basically, you can't download something to the Kin that it isn't designed to handle.

X-15D9W8491 said:
that post was an a and b conversation between me and john so c your way out, dumbass. and you should shut it because you havent really helped at all, john has gotten me nowhere because i started from the beginning before i was part of this, and i need absolutely no input from you.
Click to expand...
Click to collapse
~~~~~Forgotten~~~~~

I am not taking sides here but you guys both have points. X has a really good idea though so at least try. show proof it dosent work then i will agree with you. Its a good idea but we dont have the means of getting into the KIN.

there comes a time
Code:
the key to hacking this phone,[COLOR="Silver"][SIZE="1"] as ive noticed,[/SIZE][/COLOR] isnt getting a new os.
This is a solid point. We should not examine the possibilities of a new operating system until we are able to work with the current one.
Code:
[COLOR="Silver"][SIZE="1"] ive paid attention and i think i know what to do.[/SIZE][/COLOR] we need a new internet [B]browser.[/B] if you think about it, the browser is the problem because of its zero functionality.
Maybe so. Though the current OS has many shortcommings of, you could definitely argue that none are as confining as the browser
Code:
what we need to do is make an html parser in java
I am not sure what you mean by this. My initial impression is that coding an HTML parser from the ground up in Java is far out of the scope of this project. Perhaps you will explain it's purpose in a later part of your post.
Code:
that is invoked in javascript (dezgrz thx for finding out about the javascript apps).
I guess what you mean by this is to use the current browser's javascript interpreter to invoke the HTML parser. There are a few severe hurdles you'd have to overcome to do this.
First of all and from what I understand, the Kin's built-in browser is IE 6 for Mobile. Web developers and users alike agree that IE6, regrardless of it's environment is a very broken web browser. Despite this, it is still a full-featured web browser, at least by Microsoft's standards. So for the purpose of security, Microsoft has probably constructed the browser in such a way that code run in it will be heavily isolated from the rest of the OS. I know that exploits for IE6 are a dime a dozen but even most of those require more access to the device than we have. Our situation is compounded by the fact that, even as far as other mobile versions of IE6 go, the Kin's browser is badly crippled.
Second of all, assuming you could somehow invoke the Java code through JS, the Java code would still have to be interpreted and run using a Java interpreter which the phone lacks. Java is an interpreted language. What that means is that in the most basic sense, a Java application is comprised of a bunch of text files containing programmer code. When you 'run' a java application, what you are really doing is running a special program (called a Java INTERPRETER, what we've been talking about) that takes that programmer code and turns it into computer code that is capable of being executed. The interpreter is the part that the Kin lacks. Without it, the text files of programmer code that are the java application just look like ordinary text files to the Kin.
Code:
[COLOR="Silver"][SIZE="1"]i think we should focus on getting this done.[/SIZE][/COLOR]
...and unfortunately we've come to the end of the post. I have only talked about some of the preliminary issues with your project roadmap but IMHO they'd be pretty fatal to it's success.
Let me know if you'd like me to explain anything else to you. In the meanwhile, let's wait and see what more directed people like JK come up with.

Oh thank goodness, another post. Perhaps this one will explain some of the discontinuities that arose in the first post.
Code:
[COLOR="Silver"][SIZE="1"]is does make sense.[/SIZE][/COLOR] you can invoke a java app through js.
I am not aware of any way to do so, especially on as crippled a browser as the kin one. I've already kind of addressed this in the previous post albeit indirectly.
Code:
[COLOR="Silver"][SIZE="1"]quit criticizing me just because you dont know what youre talking about. and besides, what i meant to say (if this makes it easier to understand) is that[/SIZE][/COLOR]
I've decided to minify all the psychosocial turmoil content in his posts in order to make what I am referring to more clear.
Code:
we code a java app onto the phone that automatically connects to the browser
This portion confused me for a bit as in the first post you talked about a Java HTML parser howerver now it seems to have changed to something that simply interfaces the current browser. Maybe this would be more within the scope of the project but you'd still have to get through all the aforementioned hurdles. Even so I'm not really sure what purpose it would serve.
Code:
and a download is set off in javascript that
Oh ok, here you are explaining how the Java code gets to the browser. You use javascript injection to make the browser download the Java application.
Code:
bypasses anything written into the browser
Now, this would be a real trick. Accomplishing this would be equivalent to acquiring a U-Boat by fishing in the toilet.
Code:
by editing the permissions, etc by editing the browser
Another primary problem about your train of thought is that you seemingly assume that javascript is capable of doing debug-level computing tasks such as significantly modifying a compiled binary and perform priveleged filesystem operations. Stuff like this would be a pain in the neck to do even on a desktop computer with suited programming languages.
Code:
and just making a new one [COLOR="Silver"][SIZE="1"]and not being lazy. [/SIZE][/COLOR]
Javascript is a language designed for the web, not general purpose and certainly not for creating another web browser from scratch. JS, like Java is an interpreted language except the interpreter is included in the web browser. I am not sure coding a web browser within a web browser would produce very desireable results, esp. with such limited processing power as is available on Kin hardware.
Code:
[COLOR="Silver"][SIZE="1"]you of all people should know this makes sense because [/SIZE][/COLOR]you programmed and app onto the kin![COLOR="Silver"][SIZE="1"] besides, the whole thing about hacking is to be optimistic or you never get it done and youre impeding development with stupid posts like your last. get a grip and post something important instead of that trash next time![/SIZE][/COLOR]
hm. hm.
In conclusion, have a nice day.

In fact,iirc the Kin doesnt even have Javascript but JScript. Microsoft implementation, compatible with javascript itself.
http://en.wikipedia.org/wiki/JScript
The funny commands which could expose part of the system doesnt work, of course.

That's just weird
johnkussack said:
In fact,iirc the Kin doesnt even have Javascript but JScript. Microsoft implementation, compatible with javascript itself.
http://en.wikipedia.org/wiki/JScript
The funny commands which could expose part of the system doesnt work, of course.
Click to expand...
Click to collapse
ok. first, let's forget our arguments and move on, those have nothing to do with what we are trying to accomplish. Second, how related is jscript to javascript because microsoft always has to make weird implementations of porgramming languages. This could possibly be a minor setback. Third, i'll admit that some things I posted didn't make sense, so i'll make them more understandable in the future.

[Q] WP7 and native for beginner

Hello everybody,
I got a WP7 Samsung Focus and I want to port my old application to this device and join native forces for WP7
My plan is simple: I'll convert my app into a dll, rewrite new gui in C# (or whatever the way to do it on WP7). I saw multiple posts about calling native code (original from Cris Walsh: http://goo.gl/2Tjks). Then I saw a few posts mentioning that it's impossible etc etc.
So, a few questions:
0) can I do it for my app (I don't need marketplace exams etc, I don't care for that)? I know that some WinAPI could be unavailable/broken, all I ask at this point if it's possible to load and run native dll without changing or re-flashing ROM.
1) ms wants 100$ out of my pocket to be able to deploy to my own device (WTF?!). What can I do to deploy to my phone without paying the crooks? (VS2010 tell me to register there and registration askes for 100$).
2) Is there a sample project I could D/L and run, I have zero experience in C# and I have no idea how to load and call native DLL from managed code in WP7? All these half broken samples are totally useless to me, I simply wanted to working HelloWorld app that loads and runs simple dll.
thanks

0) Yes, what you describe is possible. There are lots of limits, though - WP7 applications have very low permissions, and calling native code doesn't fix that. Unless you need to edit something outside the app's own iolated storage, though, you're probably OK.
1) Aside from the official marketplace account ($100), there are a few options:
a) if you've got an LG phone, they come with a built-in registry editor that can be used to dev-unlock your phone. I forget the exact key you need, though.
b) if you've got a student email address (ends in .edu) you can try registering through DreamSpark. This is free.
c) if you don't mind rolling back to pre-NoDo (7004 or 7008) you can use ChevronWP7 Unlock (instructions available on this forum). If you don't have a restore point that far back you can flash an official ROM for that version.
d) if you don't mind waiting, ChevronWP7 Labs will be available at some point (no ETA that I've seen, but it's been talked about for months) and will provide dev-unlock (but not marketplace account) for a nominal fee.
2) There are lots of apps distributed with source, and most of them will use some native code. You could do a search on this forum for subject lines including the tag "[SOURCE]" and find several (I release source for all my apps). However, I suspect what you'd find most useful is Heathcliff74's guide to WP7 apps that use native code, which is on this forum at http://forum.xda-developers.com/showthread.php?t=1299134. It includes step-by-step instructions.
Hope that helps! I look forward to seeing your app. Also, don't hesitate to ask for help with the actual development; I suck at GUIs and Silverlight but am fairly proficient at C# if you need somebody who knows that language, for example.

There is an ETA for the new ChevronWP7 unlocker:only a few weeks away from launch!

Hi GoodDayToDie
GoodDayToDie said:
0) Yes, what you describe is possible. There are lots of limits, though - WP7 applications have very low permissions, and calling native code doesn't fix that. Unless you need to edit something outside the app's own iolated storage, though, you're probably OK.
Click to expand...
Click to collapse
At this point I want to make a DLL from my simple app and call a few functions that interact with filesystem and network. FS is needed only for simple stuff (loading config file etc) from installation folder and creating some temporary files for local storage. Network is tcp/udp, I guess network should be available.
GoodDayToDie said:
1) Aside from the official marketplace account ($100), there are a few options:
...
Click to expand...
Click to collapse
I did some search, it seem that I've done that part. Chevron dev unlock was pulled out from their site, but the old version remains scattered all over the board. There is a good thread a good thread on how to do it. It happens that my phone is 7004. Where can I get old ROM in case if something goes bad and I need to re-flash? Is it easy, am I risking to brick and loose my phone?
I just tried to run sample phone app and it runs on the phone. Initially it said that it was revoked by MS, I run dev-unlock one more time and now it works.
GoodDayToDie said:
2) There are lots of apps distributed with source, and most of them will use some native code. You could do a search on this forum for subject lines including the tag "[SOURCE]" and find several (I release source for all my apps). However, I suspect what you'd find most useful is Heathcliff74's guide to WP7 apps that use native code, which is on this forum at http://forum.xda-developers.com/showthread.php?t=1299134. It includes step-by-step instructions.
Click to expand...
Click to collapse
I'll try to search, hope I'll be up and running soon. Too bad WP7 is DOA. They always had much better tools than all these ghetto Symbian/Android/Xcode crapware tools... WTF is wrong with these guys, at the point when they were surpassed at speed of light by newbies iPhone and Android they made some backward steps to cut off most of the devs (but they added all these 500K Silverlight newbie devs...). I'm so disappointed with Android, seems like they hired all these retards who were fired at symbian: same **** tools

I downloaded a few samples and it seems that all of them contain prebuild dll's and all of them are COM dlls or something like that.
What I'd like to find is simple sample that contains src code to native WinMo dll and C# project that it uses.
As far as I know native dll cannot be build with latest tools (am I right?), but I can use cegcc or VS2008 to build native DLL's.
stuff like:
Code:
if (ComBridge.RegisterComDll("ComFileRw.dll", new Guid("EEA7F43B-A32D-4767-9AE7-9E53DA197455")) != 0)
is totally unknown to me. I would really like to avoid to even elarning anything about COM related stuff. I prefer not to mess up with code that isn't portable.

HI mtlgui,
unless Heathcliff finishes his WP7 Root Tools SDK, you don't have any other way to access native c++ code besides using COM. DFT (The DarkForcesTeam) released a firmware loader, that allows you to flash customized unsigned firmware. They were also able to do some native c++ coding with the WM API. However the used firmware for that is not public and it is limited to HTC devices.
Did you already consider to write your application in c#? Mango has now TCP/UDP socket support for outgoing connections. Incoming connections or services running on the phone aren't possible without using native code, at least for the moment.

Hi rudelm,
if the only way to use native is to build COM dll, then I'm OK with that. My app code is old and I'd rather throw my WP7 device to trash can than trying to rewrite my app in C#.
Eventually, down the road while hacking maybe I'll learn c# well enough to do anything with it other than GUI and calling native/COM dlls.
So, just to confirm my understanding. I need to write COM dlls that access native API (socket, filesystem, wavein/waveout etc) and then load these COM dlls and call their functions from C# (or whatever is the closest lang to c/c++ in the WP7 world).

@mtlgui:
You've pretty much got it. A few thoughts, though:
There is a webserver project available on this site. It includes source for its C++ native component (the library is called NativeIO; I can probably send you the source if you can't find it). It exposes registry, filesystem, and TCP server and client sockets to COM. Note that because this library was built for pre-Mango phones, just compiling it and shipping it may not work on Mango phones as many deprecated libraries were removed in Mango and if the DLL contains any references to them, it won't load.
Generally speaking, what you're asking for with TCP/UDP is possible, though you may have to code against the winsock API directly. It sounds like you're doing as little as possible with C#, so even if the Socket API that is available with Mango were sufficient for your app's needs, you wouldn't be using it.
Filesystem access... even if you have read access to your app's install folder (I haven't checked, though you should), you almost certainly won't have write access. Each app does have a writable "isolated storage" though, under \Applications\Data\{GUID}\Data\IsolatedStore\. I've only ever tried writing to it using C# though, so I don't know for sure if it's writable using the native APIs directly (should be, though).
It's probably perfectly OK to write your app as one big native DLL (hell, it *might* work to just change the build type from Application to Library, then rename main() or something like that). You will need to expose the library to COM, but that's easy. You can then write a very simple C#/Silverlight app (see Heathcliff's instructions, or just post the COM interface and soembody could write it for you). All the C# app needs to do is use ComBridge to access the native DLL, and call a "run()" function or something similarly simple.
For what it's worth, C# is very close to a superset of C++, at least on the desktop. The phone version is crippled a little by not allowing the use of pointers - everything has to be done with strongly-typed references instead, which can make network code a little annoying but is otherwise rarely a problem - but with a little experimentation you may find your disdain for C# to be misguided. It's a useful language to know it today's job market, if nothing else.
Why is your phone still on 7004? That's the launch retail build, something like eight months out of date. On the plus side, this means that things like ChevronWP7 Unlocker still work for you, as you found. On the minu side, it means you're putting up with bugs and missing features that you needn't be. Have you tried updating at all? If/when you do update, make sure to back up the restore points that the Zune software generates (they got in %localappdata%\Microsoft\Windows Phone Update\). That way, if you ever need to roll back to 7004, you can do it. Normally, only the most recent restore point is kept.
Flashing ROMs is safe so long as you don't try something like flashing the wrong one for your device. Unless your bootloader is unlocked (only possible on HTC), you can only flash official ROMs anyhow, which saves you from most of the risks. On the other hand, you're already on as old a ROM as you will find, and so long as you keep your restore points, you can return to it any time you want to, easily.

I'm googling now the board to find NativeIO and that webserver app. So far only references to it, but no src code.
I'm ok with isolated read/write access. All I care is persistent fs storage.
My phone is still 7004 because I just bought it so I can do some WP7 development. I don't want to mess up with updates at the moment.
As I understand from another post ComBridge is C#->COM->native c++ dll or any other dll that can be used, right? I'm just learning some COM to learn enough to start actually programming for the phone. I see that I can pass whatever data I want, but I don't seem to be able to see a way to register callbacks so that native/COM could call back to C#

mtlgui said:
I'm googling now the board to find NativeIO and that webserver app. So far only references to it, but no src code.
I'm ok with isolated read/write access. All I care is persistent fs storage.
My phone is still 7004 because I just bought it so I can do some WP7 development. I don't want to mess up with updates at the moment.
As I understand from another post ComBridge is C#->COM->native c++ dll or any other dll that can be used, right? I'm just learning some COM to learn enough to start actually programming for the phone. I see that I can pass whatever data I want, but I don't seem to be able to see a way to register callbacks so that native/COM could call back to C#
Click to expand...
Click to collapse
Basic introduction to native code and COM, including references to more background info: http://forum.xda-developers.com/showthread.php?t=1299134.
Callback from C++ -> COM -> C# can be done. Decompile the WP7 Acrobat Reader app. You'll see how it works.
Ciao,
Heathcliff74