Re: [PATCH v2 0/3] x86/intel_rdt: task_work vs task_struct rmid/closid write race

On 25/11/20 19:06, Reinette Chatre wrote: > Hi Valentin, > > On 11/25/2020 10:39 AM, Valentin Schneider wrote: >> The (default) TWA_RESUME ensures the targeted (userspace) task gets kicked >> if it is currently running, and doesn't perturb any CPU otherwise; >> see set_notify_resume() + exit_to_u

Re: [PATCH v2 0/3] x86/intel_rdt: task_work vs task_struct rmid/closid write race

Hi Valentin, On 11/25/2020 10:39 AM, Valentin Schneider wrote: On 25/11/20 17:20, Reinette Chatre wrote: Until the queued work is run, the moved task runs with old (and even invalid in the case when its original resource group has been removed) closid and rmid. For a userspace task, that que

Re: [PATCH v2 0/3] x86/intel_rdt: task_work vs task_struct rmid/closid write race

On 25/11/20 17:20, Reinette Chatre wrote: > Hi Valentin, >>> >>> Until the queued work is run, the moved task runs with old (and even >>> invalid in the case when its original resource group has been removed) >>> closid and rmid. >>> >> >> For a userspace task, that queued work should be run as s

Re: [PATCH v2 0/3] x86/intel_rdt: task_work vs task_struct rmid/closid write race

Hi Valentin, On 11/25/2020 7:01 AM, Valentin Schneider wrote: On 24/11/20 21:37, Reinette Chatre wrote: On 11/22/2020 6:24 PM, Valentin Schneider wrote: This is a small cleanup + a fix for a race I stumbled upon while staring at resctrl stuff. Briefly tested on a Xeon Gold 5120 (m2.xlarge.x86

Re: [PATCH v2 0/3] x86/intel_rdt: task_work vs task_struct rmid/closid write race

Hi Reinette, On 24/11/20 21:37, Reinette Chatre wrote: > Hi Valentin, > > On 11/22/2020 6:24 PM, Valentin Schneider wrote: >> This is a small cleanup + a fix for a race I stumbled upon while staring at >> resctrl stuff. >> >> Briefly tested on a Xeon Gold 5120 (m2.xlarge.x86 on Equinix) by bounc

Re: [PATCH v2 0/3] x86/intel_rdt: task_work vs task_struct rmid/closid write race

Hi Valentin, On 11/22/2020 6:24 PM, Valentin Schneider wrote: This is a small cleanup + a fix for a race I stumbled upon while staring at resctrl stuff. Briefly tested on a Xeon Gold 5120 (m2.xlarge.x86 on Equinix) by bouncing a few tasks around control groups. ... Thank you very much for t

[PATCH v2 0/3] x86/intel_rdt: task_work vs task_struct rmid/closid write race

Hi folks, This is a small cleanup + a fix for a race I stumbled upon while staring at resctrl stuff. Briefly tested on a Xeon Gold 5120 (m2.xlarge.x86 on Equinix) by bouncing a few tasks around control groups. Revisions = v1 -> v2 Empty git diff between the two, but: o Collect