On 11/13/23 5:26 PM, David Hildenbrand wrote:
On 13.11.23 10:05, Xu Yu wrote:In the anonymous collapse path, khugepaged collapses pte-mapped hugepages by allocating and copying to a new hugepage, which is suboptimally. In fact, we only need to update the mapping page tables for anonymous pte-mapped THPs, in the same way as file/shmem-backed pte-mapped THPs, as shown in commit 58ac9a8993a1 ("mm/khugepaged: attempt to map file/shmem-backed pte-mapped THPs by pmds").Somewhere along that patch set discussion, there was a discussion about how to deal with PageAnonExclusive properly. Quite a lot of information is documented in: commit dee2ad120571f38433211098cd6b95a59bdfc8c7 Author: David Hildenbrand <david@xxxxxxxxxx> Date: Wed Jan 4 15:49:05 2023 +0100 selftests/vm: cow: add COW tests for collapsing of PTE-mapped anon THP Currently, anonymous PTE-mapped THPs cannot be collapsed in-place: collapsing (e.g., via MADV_COLLAPSE) implies allocating a fresh THP and mapping that new THP via a PMD: as it's a fresh anon THP, it will get the exclusive flag set on the head page and everybody is happy. ... I purely speculate that you didn't consider it and got it wrong, sorry :P
As you said, I did not consider it. Actually, I didn't even know that. :(
Fortunately, I wrote a test case for that where it's documented (above)
Thanks very much! I will dig into it.
tools/testing/selftests/mm/cow.c tests: # [RUN] Basic COW after fork() when collapsing before fork() ok 169 No leak from parent into child # [RUN] Basic COW after fork() when collapsing after fork() (fully shared) ok 170 # SKIP MADV_COLLAPSE failed: Invalid argument # [RUN] Basic COW after fork() when collapsing after fork() (lower shared) ok 171 No leak from parent into child # [RUN] Basic COW after fork() when collapsing after fork() (upper shared) ok 172 No leak from parent into child If your implementation supports MADV_COLLAPSE, it might reveal any problems.
-- Thanks, Yu
