search for: mmiotraces

Is this expected result for Chipset: G98 (NV98)? $ modinfo nvidia -F version 304.123 $ stat -c %s mmiotrace.log 134659197 $ file mmiotrace.log mmiotrace.log: ASCII text $ grep -i lost mmiotrace.log ; echo $? 1 $ ./envytools/rnn/demmio -f mmiotrace.log | perl -e 'open($fh409c, ">fuc409c"); open($fh409d, ">fuc409d"); open($fh41ac, ">fuc41ac");

On Mon, 14 Oct 2013 22:45:09 +0400 Eugene Shatokhin <euspectre at gmail.com> wrote: > Hi, > > There is an interesting TODO item on MmioTraceDeveloper page: > "kprobes has a generic instruction decoding facility, use that instead of > homebrewn (or KVM), and use emulation instead of page faulting" > > Actually, I have done something similar in one of my

After every iounmap mmiotrace has to free kmmio_fault_pages, but it can't do it directly, so it defers freeing by RCU. It usually works, but when mmiotraced code calls ioremap-iounmap multiple times without sleeping between (so RCU won't kick in and start freeing) it can be given the same virtual address, so at every iounmap mmiotrace will schedule the same pages for release. Obviously it

On Fri, 25 Oct 2013 17:19:56 +0400 Eugene Shatokhin <euspectre at gmail.com> wrote: > Hi, > > 2013/10/25 Pekka Paalanen <pq at iki.fi> > ... > > We could use some comments from the real reverse-engineers. I used > > to be mostly a tool writer. > > > > Yes, if some experts could share their knowledge of this matter, this would > be most

After every iounmap mmiotrace has to free kmmio_fault_pages, but it can't do it directly, so it defers freeing by RCU. It usually works, but when mmiotraced code calls ioremap-iounmap multiple times without sleeping between (so RCU won't kick in and start freeing) it can be given the same virtual address, so at every iounmap mmiotrace will schedule the same pages for release. Obviously it

On Wed, 16 Apr 2008 13:46:09 +0200 Ingo Molnar <mingo at elte.hu> wrote: > > * Pekka Paalanen <pq at iki.fi> wrote: > > > > we should fix this restriction ASAP. Forcibly dropping to UP will > > > cause mmiotrace to be much less useful for diagnostic purposes of > > > Linux > > > > Ok, how do you propose we solve this? > >

Hi, Good to know that! Yes, it should be faster than page faulting, although I haven't done the benchmarking yet. And yes, it is not needed to disable all but one CPU. In my current implementation, I use an ordered workqueue to send the data to the mmapped output buffer (where they will be read from from the user space) and that ensures the order of events is kept. May be less than ideal but

Hello in dmesg I always have these informations (I tested several kernels between 3.7 and 3.16-rc3): [ 13.742006] nouveau E[ DRM] Pointer to TMDS table invalid [ 13.742036] nouveau [ DRM] DCB version 4.0 [ 13.742038] nouveau E[ DRM] Pointer to flat panel table invalid [ 13.742079] nouveau [ DRM] ACPI backlight interface available, not registering our own [ 13.742082]

Hi all, some nouveau users and developers have an issue with mmiotracing the nvidia driver. After some digging I think it might has something todo with hugepages and/or the tracing infrastructure in general, but generally I am still clueless what is causing this. Generally it can be triggered by starting a X server on the nvidia gpu with the nvidia kernel module loaded and mmiotracer active

Od: "Ilia Mirkin" <imirkin at alum.mit.edu> Do: "Lampshade" <lampshade at poczta.fm>; Wys?ane: 19:07 Czwartek 2014-07-10 Temat: Re: [Nouveau] Warnings in dmesg and results of mmiotrace 10de:1140 Geforce620m Optimus Laptop Acer E1-531G > On Thu, Jul 10, 2014 at 11:01 AM, Lampshade wrote: > > Hello > > in dmesg I always have these informations (I

On 02.12.2014 14:40, Ilia Mirkin wrote: > On Tue, Dec 2, 2014 at 8:38 AM, poma <pomidorabelisima at gmail.com> wrote: >> Is this expected result for Chipset: G98 (NV98)? > > Yep, 100% expected. [Perhaps you might glance at the wiki page you got > that from for clues as to why.] > "You basically never need to do the mmiotrace, unless you're a nouveau

If something calls ioremap with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but the entire page was armed for mmiotracing. On calling iounmap the address passed to unregister_kmmio_probe was PAGE_SIZE aligned by the caller leading to a complete freeze of the machine. We should always page

4.14-stable review patch. If anyone has any objections, please let me know. ------------------ From: Karol Herbst <kherbst at redhat.com> [ Upstream commit 6d60ce384d1d5ca32b595244db4077a419acc687 ] If something calls ioremap() with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but

3.18-stable review patch. If anyone has any objections, please let me know. ------------------ From: Karol Herbst <kherbst at redhat.com> [ Upstream commit 6d60ce384d1d5ca32b595244db4077a419acc687 ] If something calls ioremap() with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but

4.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: Karol Herbst <kherbst at redhat.com> [ Upstream commit 6d60ce384d1d5ca32b595244db4077a419acc687 ] If something calls ioremap() with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but

4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Karol Herbst <kherbst at redhat.com> [ Upstream commit 6d60ce384d1d5ca32b595244db4077a419acc687 ] If something calls ioremap() with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but

On Fri, 18 Oct 2013 00:11:15 +0400 Eugene Shatokhin <euspectre at gmail.com> wrote: > Hi, > > Good to know that! > > Yes, it should be faster than page faulting, although I haven't done the > benchmarking yet. And yes, it is not needed to disable all but one CPU. In > my current implementation, I use an ordered workqueue to send the data to > the mmapped output

From: Karol Herbst <kherbst at redhat.com> [ Upstream commit 6d60ce384d1d5ca32b595244db4077a419acc687 ] If something calls ioremap() with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but the entire page was armed for mmiotracing. On calling iounmap() the address passed to

From: Karol Herbst <kherbst at redhat.com> [ Upstream commit 6d60ce384d1d5ca32b595244db4077a419acc687 ] If something calls ioremap() with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but the entire page was armed for mmiotracing. On calling iounmap() the address passed to

From: Karol Herbst <kherbst at redhat.com> [ Upstream commit 6d60ce384d1d5ca32b595244db4077a419acc687 ] If something calls ioremap() with an address not aligned to PAGE_SIZE, the returned address might be not aligned as well. This led to a probe registered on exactly the returned address, but the entire page was armed for mmiotracing. On calling iounmap() the address passed to