From: Andi Kleen <ak@xxxxxxxxxxxxxxx> Subject: mm/mprotect.c: don't touch single threaded PTEs which are on the right node We had some problems with pages getting unmapped in single threaded affinitized processes. It was tracked down to NUMA scanning. In this case it doesn't make any sense to unmap pages if the process is single threaded and the page is already on the node the process is running on. Add a check for this case into the numa protection code, and skip unmapping if true. In theory the process could be migrated later, but we will eventually rescan and unmap and migrate then. In theory this could be made more fancy: remembering this state per process or even whole mm. However that would need extra tracking and be more complicated, and the simple check seems to work fine so far. [ak@xxxxxxxxxxxxxxx: v3: Minor updates from Mel. Change code layout] Link: http://lkml.kernel.org/r/1476382117-5440-1-git-send-email-andi@xxxxxxxxxxxxxx Link: http://lkml.kernel.org/r/1476288949-20970-1-git-send-email-andi@xxxxxxxxxxxxxx Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx> Acked-by: Mel Gorman <mgorman@xxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/mprotect.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff -puN mm/mprotect.c~dont-touch-single-threaded-ptes-which-are-on-the-right-node mm/mprotect.c --- a/mm/mprotect.c~dont-touch-single-threaded-ptes-which-are-on-the-right-node +++ a/mm/mprotect.c @@ -69,11 +69,17 @@ static unsigned long change_pte_range(st pte_t *pte, oldpte; spinlock_t *ptl; unsigned long pages = 0; + int target_node = NUMA_NO_NODE; pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl); if (!pte) return 0; + /* Get target node for single threaded private VMAs */ + if (prot_numa && !(vma->vm_flags & VM_SHARED) && + atomic_read(&vma->vm_mm->mm_users) == 1) + target_node = numa_node_id(); + arch_enter_lazy_mmu_mode(); do { oldpte = *pte; @@ -95,6 +101,13 @@ static unsigned long change_pte_range(st /* Avoid TLB flush if possible */ if (pte_protnone(oldpte)) continue; + + /* + * Don't mess with PTEs if page is already on the node + * a single-threaded process is running on. + */ + if (target_node == page_to_nid(page)) + continue; } ptent = ptep_modify_prot_start(mm, addr, pte); _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
