Thank you! This resolved the issue. On Mon, May 22, 2023 at 4:55 PM Poremba, Matthew <matthew.pore...@amd.com> wrote:
> [AMD Official Use Only - General] > > Hi, > > > > > > By compiled as a module, the Linux `.config` file should have > CONFIG_PMEM_xxx=y (i.e., not …=m). > > > > I did a quick test with the ubuntu20 disk image and kernel downloaded from > the gem5 website. I just added the `memmap=4G!12G` kernel parameter to > FSConfig.py on the most recent develop branch of gem5 and was seeing a > /dev/pmem0 device. I didn’t touch the e820 table though. Maybe you could > try with the latest gem5 resources and see if it works. > > > > > > -Matt > > > > *From:* Vincent Abraham <vincent....@gmail.com> > *Sent:* Monday, May 22, 2023 1:14 PM > *To:* Poremba, Matthew <matthew.pore...@amd.com> > *Cc:* The gem5 Users mailing list <gem5-users@gem5.org> > *Subject:* Re: [gem5-users] Persistent memory with gem5 > > > > *Caution:* This message originated from an External Source. Use proper > caution when opening attachments, clicking links, or responding. > > > > It would be great if I could get some help with this issue. It seems as if > the simulated system is not able to find the PMEM driver for some reason. > I'm using the linux 4.19.283 kernel version and the ubuntu 16.04 distro. > > > > On Sat, May 20, 2023 at 8:30 PM Vincent Abraham <vincent....@gmail.com> > wrote: > > Greetings, > > I tried passing the memmap command as a part of the cmdline variable as > well. I just wrote memmap=4G!12G at the end of the string. Even by doing > this, I'm still not able to find the pmem partition in /dev. As mentioned > earlier, the e820 table is displayed correctly and I can see the persistent > (type 12) region reserved but the pmem space is nowhere to be found. Is > there anything else I'm missing? > > > > On Sat, May 20, 2023 at 4:19 PM Vincent Abraham <vincent....@gmail.com> > wrote: > > Greetings, > > Thanks for responding. Could you tell me what exactly do you mean by > 'building it into the kernel directly'? I've changed the kernel > configuration to reflect PMEM as a module and all of the other changes that > are done in the website. I didn't pass the memmap argument yet, I just > reserved memory with the X86E820() function in the gem5 configuration file > and that did the job of the table displaying correctly. I'll try passing > the command to the argument directly > > > > On Sat, 20 May 2023, 13:29 Poremba, Matthew, <matthew.pore...@amd.com> > wrote: > > [AMD Official Use Only - General] > > > > Hi, > > > > > > Are you building pmem as a module as described in the blog? (“<M> PMEM: > Persistent memory block device support”) If so, I would try building it > into the kernel directly. It is possibly looking for the module for your > compiled kernel and does not find it on the disk image. > > > > You’ll also have to add “memmap=4G!12G” to cmdline variable in the > makeLinuxX86System function in configs/common/FSConfig.py if you are using > fs.py. > > > > > > -Matt > > > > *From:* Vincent Abraham via gem5-users <gem5-users@gem5.org> > *Sent:* Saturday, May 20, 2023 9:14 AM > *To:* gem5-users@gem5.org > *Cc:* Vincent Abraham <vincent....@gmail.com> > *Subject:* [gem5-users] Persistent memory with gem5 > > > > *Caution:* This message originated from an External Source. Use proper > caution when opening attachments, clicking links, or responding. > > > > I want to configure persistent memory in the RAM (similar to > https://pmem.io/blog/2016/02/how-to-emulate-persistent-memory/) and just > run a basic FS setup (I'm running fs.py for now). I'm able to reserve the > persistent memory space (with the X86E820Entry() function in the config > file) and the e820 table is displayed correctly. But on booting up, I can't > find any disk named pmem in /dev. Is there anything that I'm missing out > here? Any help with this would be much appreciated. > >
_______________________________________________ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org
