|
What a pain in the but it is for getting a driver signed.
Why is it so dependent on hardware? If the hardware hasn't got a serial number, fail. Device descriptor is a bit shoddy at times, fail. Device goes unresponsive. BSOD and fail.
Not only that its also dependent on the PC its tested on. One of them has a failure as big as the titanic iceberg right in the ACPI/BIOS subsystem.
So the Windows kernel is a highly structured and layered environment, and the driver you are testing sits on at least two others, and is a long way from the hardware, so why does the HCK fail on hardware errors? Why doesn't it implement a virtual piece of hardware via a filter, which it has anyway, and test JUST your driver?
It really is a pain in the but at times. Especially if the hardware is a bit flaky.
"The whole idea that carbon dioxide is the main cause of the recent global warming is based on a guess that was proved false by empirical evidence during the 1990s." climate-models-go-cold
|
|
|
|
|
I have a HP Pavilion Elite with dual monitors. I'd like to add a third monitor. Does this require a new video card or some other hardware?
If it's not broken, fix it until it is
|
|
|
|
|
Never done this myself... but you can probably find video cards that support it. When you purchase a new video card however, make sure it supports three simultaneous video outputs (just having three outputs doesn't guarantee that it's support it). I have a desktop that has three outputs (two DVI and one HDMI) but you can only use two of them at a time. Not sure if this is a hardware limitation or just the driver software. Either way, make sure it's supported by the video card.
|
|
|
|
|
Hello. AFAIK, you can stream h264 live video from IP camera on windows media player. But when I enter URL (rtsp://xxx.xxx.xxx.xxx:7070), following message is shown
Windows Media Player can not play the file because the specified protocol is not supported.
Now the same url works fine on VLC player but NOT on windows media plyer. I have read the following knowledge base article but could not fix the issue. What could be wrong? Thanks for any pointer.
modified 14-Apr-14 2:23am.
|
|
|
|
|
|
I read most of them but could not find the solution. Most of them are repetition of the KB article I provided the link of. Just not sure what should I try now.
|
|
|
|
|
Why doesn't the Bluetooth for android allow hands free talk and text like the windows does?
|
|
|
|
|
Why don't you ask Google?
|
|
|
|
|
It does... I have a Nexus phone and you can certainly do hands-free calling.
|
|
|
|
|
I have a Samsung Galaxy S4, it allows hands-free calling and text, and my previous phone, the Samsung Stratosphere v2 also did, not that I used it much since it had a keyboard. Just takes a little setup.
|
|
|
|
|
Does anyone remember Tetradyne DriverX windows driver software for WinXP and prior? I am looking for a copy of the file DxIntr3.h to build the kernel. I have all other sources. I bought a source license but Tetradyne Software is gone now. Much appreciation.
More information:
I started out just hoping someone had a copy of the file. W/o a copy I see I need to reinvent the missing file.
I have gotten it to compile with the definitions:
typedef struct
{
ULONG nOffset;
ULONG cb;
} READ_WRITE_DMA_BUFFER_INPUT, *PREAD_WRITE_DMA_BUFFER_INPUT;
typedef unsigned char *PUCHAR;
The whole function that requires these definitions is extracted from the file DxDriver.c:
NTSTATUS DxReadWriteDmaBuffer(PDXDEV_EXTENSION pExtension, PVOID pIoBuffer,
ULONG cbInput, PMDL mdl, BOOLEAN read)
{
PREAD_WRITE_DMA_BUFFER_INPUT params;
PUCHAR pOutBuffer;
// Validate parameters
if (!pIoBuffer || (cbInput < sizeof(READ_WRITE_DMA_BUFFER_INPUT)))
return STATUS_INVALID_PARAMETER;
params = (PREAD_WRITE_DMA_BUFFER_INPUT) pIoBuffer;
if ((params->nOffset + params->cb) > pExtension->nDmaBufSize)
return STATUS_INVALID_PARAMETER;
if (!mdl || (MmGetMdlByteCount(mdl) < params->cb))
return STATUS_INVALID_PARAMETER;
if (!pExtension->pDmaBuffer)
return STATUS_UNSUCCESSFUL;
pOutBuffer = MmGetSystemAddressForMdl(mdl);
if (!pOutBuffer)
return STATUS_UNSUCCESSFUL;
if (read)
{
RtlCopyMemory(
pOutBuffer,
(PUCHAR) pExtension->pDmaBuffer + params->nOffset,
params->cb);
}
else
{
RtlCopyMemory(
(PUCHAR) pExtension->pDmaBuffer + params->nOffset,
pOutBuffer,
params->cb);
}
return STATUS_SUCCESS;
}
Anyone see any problem here?
Thanks for the help and clues. Now I move to debug. Bless you all.
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Thanks Mr. Muchies for clues and hints. I have it actually working now. Turned out the DMA part was crucial. Now the trick is to port to Windows 7. Any advice or good links you have? Seems like eliminating the HAL calls will be a large part.
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
modified 9-Apr-14 14:59pm.
|
|
|
|
|
Blimey, never heard of it, and I have been writing windows drivers since the 90s.
Can you recreate it? Sounds like it might have some defines, some wrappers round WDM api funcs, that kind if thing.
"The whole idea that carbon dioxide is the main cause of the recent global warming is based on a guess that was proved false by empirical evidence during the 1990s." climate-models-go-cold
|
|
|
|
|
To build a version 4xxx kernel driver they use some stuff defined for the version 3xxx driver. Most is interrupt related and since the user mode part of the driver compiles just fine w/o it I concluded that I did not need the old interrupt parts so I faked it.
However the DMA parts wrap new methods around the methods of the prior versions and therefore need some definitions for the driver to compile. At the moment I need definition/declarations for PREAD_WRITE_DMA_BUFFER_INPUT and PUCHAR. These might be structures based on compile errors I get when I typedef'd them to integers to see what would happen.
I was hoping in the vastness of space and time and the Internet someone had a copy of the file DxIntr3.h that they would share.
Thanks for caring.
|
|
|
|
|
I guess the second one is unsigned char * (Pointer to Unsigned CHAR). The first one may be the same or more likely a pointer to the second (unsigned char ** as pointer to address of DMA input buffer).
|
|
|
|
|
Thank you. I think you are exactly right about PUCHAR. However, the other is more complicated. Still working on that one.
|
|
|
|
|
As Joachim says a puchar is just a 32 bit (or 64 bit) pointer, in this case, to an unsigned char.
PREAD_WRITE_DMA_BUFFER_INPUT is also going to be a generic pointer, and will be the size of the addressing on the OKS, so 32 or 64 bit, so a pvoid will do, or pulong, (or if you are doing it properly use SIZE_T since it cross compiles).
"The whole idea that carbon dioxide is the main cause of the recent global warming is based on a guess that was proved false by empirical evidence during the 1990s." climate-models-go-cold
|
|
|
|
|
Thanks.
I have edited the original post to include the code involved. Comments would be appreciated.
|
|
|
|
|
Looks OK. Your definitions fit with the code, time to run it up and see if it crashes! 
"The whole idea that carbon dioxide is the main cause of the recent global warming is based on a guess that was proved false by empirical evidence during the 1990s." climate-models-go-cold
|
|
|
|
|
Yes, I must now put together a WinXP system to test it. Take me a day or so. This code is in the kernel driver. The corresponding user mode driver in this configuration does not as best as I can tell contain a path that calls the function in question so I just needed it to compile (I hope). O/w I am pretty sure it will crash for lack of an actual buffer.
If it works my next chore is to port it to Win7 x64, so I may be back! Appreciate the support to date.
Thanks.
George
|
|
|
|
|
Try using SIZE_T for pointers, they automatically map to 32 and 64 bit addresses depending on which platform you compile for.
"The whole idea that carbon dioxide is the main cause of the recent global warming is based on a guess that was proved false by empirical evidence during the 1990s." climate-models-go-cold
|
|
|
|
|
Thanks Mr. Muchies for clues and hints. I have it actually working now. Turned out the DMA part was crucial. Now the trick is to port to Windows 7. Any advice or good links you have? Seems like eliminating the HAL calls will be a large part.
Thanks again.
|
|
|
|
|
Whats it running on now, XP?
THe 32 bit image will run on win7 (unless its USB, in which case it might need a tweak or two).
As for 64 bit, all your pointers are going to need looking at to make sure they are compatible, that's why I suggested using SIZE_T as it macros to the right size automatically.
Apart form thagt its just a case of building it in the 64 bit env and running it up the pole to see what happens
"The whole idea that carbon dioxide is the main cause of the recent global warming is based on a guess that was proved false by empirical evidence during the 1990s." climate-models-go-cold
|
|
|
|
|
It is running in XP, but I was suspicious when the DDK seemed to be making a Win7 x86 driver. Gave lots of "deprecated" warnings but built anyway [these warnings did not trigger the "warning same as error" switch]. It worked in XP, but Win7 x86 did not like my inf file. Anyway, on a hunch I installed Windows 7 32 bit on my test rig and gave it a try. So far it won't work but I am working on my inf file.
It is a simple driver that maps memory to my device where I have memory mapped control/status areas and some DMA memory for i/o. I am hopeful that may work since it is not USB or storage or network.
As for Win7 x64, thanks for the SIZE_T suggestion. I am sure it will help. Not so sure what to do about the Hal_xxx calls which are not defined in the amd64/x64 model.
Anyway, still plugging. To run on Win7 x86 would be a step forward since my customers don't like running XP anymore. Thanks for your input!
|
|
|
|
|
So it looks like you used the win7 32 bit build env, why not use the XP32 bit one?
Ad for the inf file, run it through chkinf, its a tool that's part of the DDK, it will tell you whats missing.
Hal_xxx? Ah, you could be screwed then. Are you calling x86 specific hal funcs? THey shouldn't be visible, are you sure they are part of the allowed api or are they a hidden func? If you are calling them MSFT wont sign your driver. If you stick to the allowed api it should be the same for all hardware platforms. NT4 used to run on Dec Alphas, Mips, x86, all sorts of stuff.
"The whole idea that carbon dioxide is the main cause of the recent global warming is based on a guess that was proved false by empirical evidence during the 1990s." climate-models-go-cold
|
|
|
|
|
"So it looks like you used the win7 32 bit build env, why not use the XP32 bit one? >>> Actually I got confused building an XP driver and when it worked in XP I was really confused. Gave me the idea to try Win7 x86.
"Ad for the inf file, run it through chkinf, its a tool that's part of the DDK, it will tell you whats missing." >>> I did do that and it was helpful. Apparently not all things are required, though, such as the CAT (certificate). Just have to confirm at install time.
"Hal_xxx? Ah, you could be screwed then. Are you calling x86 specific hal funcs?" >>> Yes. As I said, I did get deprecation warnings but it ran in XP. It may run in Win7 x86 if I can fix it. Seems to be having trouble with initialization. I do use the registry functions also and that is where my current efforts lie.
When I try to build for Win7 x64 the Hal_xxx deprecation warnings turn to undefined errors. So I am guessing that Hal_xxx functions are present in Win7 x86. Maybe Win7 x86 is really a jazzed up XP? Can't find any info about that.
My current efforts now turn to setting up a debug environment so I can trace what is going wrong. The device manager is flagging the initialization, but that covers a lot of ground. Thanks for suggestions.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
