On 04/28, Jiri Olsa wrote: > > On Sun, Apr 27, 2025 at 04:24:01PM +0200, Oleg Nesterov wrote: > > > > And perhaps the comment above mmap_write_lock() in register_for_each_vma() > > should be updated too... or even removed. > > hum, not sure now how it's related to this change, but will stare at it bit > more
That comment tries to explain why register_for_each_vma() has to take mm->mmap_lock for writing. Without the described race it could use mmap_read_lock(). See 84455e6923c79 for the details. Now that we have another (obvious) reason for mmap_write_lock(mm), this comment looks confusing. Oleg.
