On 9/4/24 17:06, Ryan Roberts wrote:
Hi Dev,
On 04/09/2024 11:09, Dev Jain wrote:
It was observed at [1] and [2] that the current kernel behaviour of
shattering a hugezeropage is inconsistent and suboptimal. For a VMA with
a THP allowable order, when we write-fault on it, the kernel installs a
PMD-mapped THP. On the other hand, if we first get a read fault, we get
a PMD pointing to the hugezeropage; subsequent write will trigger a
write-protection fault, shattering the hugezeropage into one writable
page, and all the other PTEs write-protected. The conclusion being, as
compared to the case of a single write-fault, applications have to suffer
512 extra page faults if they were to use the VMA as such, plus we get
the overhead of khugepaged trying to replace that area with a THP anyway.
Instead, replace the hugezeropage with a THP on wp-fault.
v1->v2:
- Wrap do_huge_zero_wp_pmd_locked() around lock and unlock
- Call thp_fault_alloc() before do_huge_zero_wp_pmd_locked() to avoid
- calling sleeping function from spinlock context
[1]: https://lore.kernel.org/all/3743d7e1-0b79-4eaf-82d5-d1ca29fe347d@xxxxxxx/
[2]: https://lore.kernel.org/all/1cfae0c0-96a2-4308-9c62-f7a640520242@xxxxxxx/
Dev Jain (2):
mm: Abstract THP allocation
mm: Allocate THP on hugezeropage wp-fault
include/linux/huge_mm.h | 6 ++
mm/huge_memory.c | 171 +++++++++++++++++++++++++++++-----------
mm/memory.c | 5 +-
3 files changed, 136 insertions(+), 46 deletions(-)
What is the base for this? It doesn't apply on top of mm-unstable.
Sorry, forgot to mention, it applies on v6.11-rc5.
Thanks,
Ryan
