aboutsummaryrefslogtreecommitdiffstats
path: root/mm/memory.c
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2012-10-05 21:36:27 +0200
committerMel Gorman <mgorman@suse.de>2012-12-11 14:42:37 +0000
commit0b9d705297b273657923518dbea2377cd03532ed (patch)
tree9049d172d6fcd71790a4689c7fed62a912516265 /mm/memory.c
parentbe3a728427a605990a7a0b6dbf9e29b68e266146 (diff)
downloadkernel_goldelico_gta04-0b9d705297b273657923518dbea2377cd03532ed.zip
kernel_goldelico_gta04-0b9d705297b273657923518dbea2377cd03532ed.tar.gz
kernel_goldelico_gta04-0b9d705297b273657923518dbea2377cd03532ed.tar.bz2
mm: numa: Support NUMA hinting page faults from gup/gup_fast
Introduce FOLL_NUMA to tell follow_page to check pte/pmd_numa. get_user_pages must use FOLL_NUMA, and it's safe to do so because it always invokes handle_mm_fault and retries the follow_page later. KVM secondary MMU page faults will trigger the NUMA hinting page faults through gup_fast -> get_user_pages -> follow_page -> handle_mm_fault. Other follow_page callers like KSM should not use FOLL_NUMA, or they would fail to get the pages if they use follow_page instead of get_user_pages. [ This patch was picked up from the AutoNUMA tree. ] Originally-by: Andrea Arcangeli <aarcange@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ ported to this tree. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Rik van Riel <riel@redhat.com>
Diffstat (limited to 'mm/memory.c')
-rw-r--r--mm/memory.c17
1 files changed, 17 insertions, 0 deletions
diff --git a/mm/memory.c b/mm/memory.c
index 7cf7628..cd8e0da 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1517,6 +1517,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
goto out;
}
+ if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+ goto no_page_table;
if (pmd_trans_huge(*pmd)) {
if (flags & FOLL_SPLIT) {
split_huge_page_pmd(mm, pmd);
@@ -1546,6 +1548,8 @@ split_fallthrough:
pte = *ptep;
if (!pte_present(pte))
goto no_page;
+ if ((flags & FOLL_NUMA) && pte_numa(pte))
+ goto no_page;
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
@@ -1697,6 +1701,19 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
vm_flags &= (gup_flags & FOLL_FORCE) ?
(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+
+ /*
+ * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault
+ * would be called on PROT_NONE ranges. We must never invoke
+ * handle_mm_fault on PROT_NONE ranges or the NUMA hinting
+ * page faults would unprotect the PROT_NONE ranges if
+ * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd
+ * bitflag. So to avoid that, don't set FOLL_NUMA if
+ * FOLL_FORCE is set.
+ */
+ if (!(gup_flags & FOLL_FORCE))
+ gup_flags |= FOLL_NUMA;
+
i = 0;
do {