As discussed in my talk at LPC, we can reuse the same mechanism for deciding whether to map a pte writable when upgrading permissions via mprotect() -- e.g., PROT_READ -> PROT_READ|PROT_WRITE -- to replace the savedwrite infrastructure used for NUMA hinting faults (e.g., PROT_NONE -> PROT_READ|PROT_WRITE). Instead of maintaining previous write permissions for a pte/pmd, we re-determine if the pte/pmd can be writable. The big benefit is that we have a common logic for deciding whether we can map a pte/pmd writable on protection changes. For private mappings, there should be no difference -- from what I understand, that is what autonuma benchmarks care about. I ran autonumabench on a system with 2 NUMA nodes, 96 GiB each via: perf stat --null --repeat 10 The numa1 benchmark is quite noisy in my environment. I suspect that there is no actual change in performance, even though the numbers indicate that this series might improve performance slightly. numa1: mm-stable: 156.75 +- 11.67 seconds time elapsed ( +- 7.44% ) mm-stable++: 147.50 +- 9.35 seconds time elapsed ( +- 6.34% ) numa2: mm-stable: 15.9834 +- 0.0589 seconds time elapsed ( +- 0.37% ) mm-stable++: 16.1467 +- 0.0946 seconds time elapsed ( +- 0.59% ) It is worth noting that for shared writable mappings that require writenotify, we will only avoid write faults if the pte/pmd is dirty (inherited from the older mprotect logic). If we ever care about optimizing that further, we'd need a different mechanism to identify whether the FS still needs to get notified on the next write access. In any case, such an optimiztion will then not be autonuma-specific, but mprotect() permission upgrades would similarly benefit from it. Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Cc: Dave Chinner <david@xxxxxxxxxxxxx> Cc: Nadav Amit <namit@xxxxxxxxxx> Cc: Peter Xu <peterx@xxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx> Cc: Nicholas Piggin <npiggin@xxxxxxxxx> Cc: Mike Rapoport <rppt@xxxxxxxxxx> Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx> David Hildenbrand (4): mm/mprotect: minor can_change_pte_writable() cleanups mm/huge_memory: try avoiding write faults when changing PMD protection mm/autonuma: use can_change_(pte|pmd)_writable() to replace savedwrite mm: remove unused savedwrite infrastructure Nadav Amit (1): mm/mprotect: allow clean exclusive anon pages to be writable arch/powerpc/include/asm/book3s/64/pgtable.h | 80 +------------------- arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +- include/linux/mm.h | 2 + include/linux/pgtable.h | 24 ------ mm/debug_vm_pgtable.c | 32 -------- mm/huge_memory.c | 66 ++++++++++++---- mm/ksm.c | 9 +-- mm/memory.c | 19 ++++- mm/mprotect.c | 23 +++--- 9 files changed, 93 insertions(+), 164 deletions(-) -- 2.37.3
