http://www.devx.com/Intel/Article/21023
http:
Might be a good site to register for …
-pro</http:>
Looking at the code in the sample I’m just wondering if I’ve missed
something:
…
// Flush the instruction cache to make sure
// the modified code is executed.
FlushInstructionCache(GetCurrentProcess(), NULL, NULL);
…
I thought ALL x86 processors had data/instruction cache snooping. Or have
I missed something here?
–
Mats
-----Original Message-----
From: Sinha, Prokash [mailto:xxxxx@maxtor.com]
Sent: Thursday, May 20, 2004 5:20 PM
To: Windows System Software Devs Interest List
Subject: [ntdev] To whom it may concern !
http://www.devx.com/Intel/Article/21023
Might be a good site to register for …
-pro
Questions? First check the Kernel Driver FAQ at
http://www.osronline.com/article.cfm?id=256
You are currently subscribed to ntdev as: xxxxx@3dlabs.com
To unsubscribe send a blank email to xxxxx@lists.osr.com
If I’m not wrong, if it is in the instruction pipeline, it won’t update.
(Think P4E).
wrote in message news:xxxxx@ntdev…
> Looking at the code in the sample I’m just wondering if I’ve missed
> something:
>
> …
> // Flush the instruction cache to make sure
> // the modified code is executed.
> FlushInstructionCache(GetCurrentProcess(), NULL, NULL);
> …
>
> I thought ALL x86 processors had data/instruction cache snooping. Or
have
> I missed something here?
>
> –
> Mats
> -----Original Message-----
> From: Sinha, Prokash [mailto:xxxxx@maxtor.com]
> Sent: Thursday, May 20, 2004 5:20 PM
> To: Windows System Software Devs Interest List
> Subject: [ntdev] To whom it may concern !
>
>
> http://www.devx.com/Intel/Article/21023
>
> Might be a good site to register for …
>
> -pro
Right, the Pentium 4 as a whole distinguishes L1 data cache from
instructions (instructions are stored in the trace buffer). The P4
manuals explicitly talk about the special requirements of “self
modifying code”. Well, if you patch code (as they do in the article)
you’d have to make sure to flush the trace cache.
That shouldn’t be any more than a serializing instruction (like
“cpuid”).
Regards,
Tony
Tony Mason
Consulting Partner
OSR Open Systems Resources, Inc.
http://www.osr.com
-----Original Message-----
From: xxxxx@lists.osr.com
[mailto:xxxxx@lists.osr.com] On Behalf Of Marc-Antoine Ruel
Sent: Thursday, May 20, 2004 1:36 PM
To: ntdev redirect
Subject: Re:[ntdev] To whom it may concern !
If I’m not wrong, if it is in the instruction pipeline, it won’t update.
(Think P4E).
wrote in message news:xxxxx@ntdev…
> Looking at the code in the sample I’m just wondering if I’ve missed
> something:
>
> …
> // Flush the instruction cache to make sure
> // the modified code is executed.
> FlushInstructionCache(GetCurrentProcess(), NULL, NULL);
> …
>
> I thought ALL x86 processors had data/instruction cache snooping. Or
have
> I missed something here?
>
> –
> Mats
> -----Original Message-----
> From: Sinha, Prokash [mailto:xxxxx@maxtor.com]
> Sent: Thursday, May 20, 2004 5:20 PM
> To: Windows System Software Devs Interest List
> Subject: [ntdev] To whom it may concern !
>
>
> http://www.devx.com/Intel/Article/21023
>
> Might be a good site to register for …
>
> -pro
—
Questions? First check the Kernel Driver FAQ at
http://www.osronline.com/article.cfm?id=256
You are currently subscribed to ntdev as: xxxxx@osr.com
To unsubscribe send a blank email to xxxxx@lists.osr.com
On Thu, 20 May 2004 09:19:36 -0700, Sinha, Prokash
wrote:
> http://www.devx.com/Intel/Article/21023
> http:
> Might be a good site to register for …
> -pro
I looked at this code, while the reminder to call FlushInstructionCache /
KeFlushIoBuffers is important, the more specific code suggestions are not
exactly state of the art in code robustness etc., I have seen (and
written) better implementations myself, but then call interception is one
of my specialties.
–
#include <disclaimer.h></disclaimer.h></http:>
It was the first article of a list dispatched by the site to the
subscriber(s). Another one interests me was the use of SIMD instructions for
motion estimation. In any case, if anyone thinks that the Intel optimization
manual is bit of manual than a book, then “Code Optimization …” book by
Kris kaspersky is a good book. A reminder though, sometime he has bugs in
his code examples that I found in his other book(s). He is the founder of
Kaspersky lab.
If any one is interested about the Anti-virus technology (since it is
capturing lot of attention(s) ), a good place is the open source Clam-AV
package, it runs perfectly(though perfectly is a relative term) on SUSE
linux, though it is a very basic implementation.
This is only informational, and in case some of the watchers are info/event
hungry
-pro
-----Original Message-----
From: xxxxx@lists.osr.com
[mailto:xxxxx@lists.osr.com]On Behalf Of Jakob Bohm
Sent: Friday, May 21, 2004 12:07 AM
To: Windows System Software Devs Interest List
Subject: Re:[ntdev] To whom it may concern !
On Thu, 20 May 2004 09:19:36 -0700, Sinha, Prokash
wrote:
> http://www.devx.com/Intel/Article/21023
> http:
> Might be a good site to register for …
> -pro
I looked at this code, while the reminder to call FlushInstructionCache /
KeFlushIoBuffers is important, the more specific code suggestions are not
exactly state of the art in code robustness etc., I have seen (and
written) better implementations myself, but then call interception is one
of my specialties.
–
#include <disclaimer.h>
—
Questions? First check the Kernel Driver FAQ at
http://www.osronline.com/article.cfm?id=256
You are currently subscribed to ntdev as: xxxxx@garlic.com
To unsubscribe send a blank email to xxxxx@lists.osr.com</disclaimer.h></http:>
> Kris kaspersky is a good book. A reminder though, sometime he has bugs in
his code examples that I found in his other book(s). He is the founder of
Kaspersky lab.
The founder of Kaspersky Lab is Eugene Kaspersky, and not Kris. Ethnically
Russian and living in Moscow. Ex-KGB (according to some gossips).
Maxim Shatskih, Windows DDK MVP
StorageCraft Corporation
xxxxx@storagecraft.com
http://www.storagecraft.com