summaryrefslogtreecommitdiff
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2013-10-07 14:28:45 +0400
committerIngo Molnar <mingo@kernel.org>2013-10-09 14:39:44 +0400
commit8191acbd30c73e45c24ad16c372e0b42cc7ac8f8 (patch)
tree1c558203ad1f7e141ef3e587d5d3d846ac82e0ec /mm/huge_memory.c
parentb8916634b77bffb233d8f2f45703c80343457cc1 (diff)
downloadlinux-8191acbd30c73e45c24ad16c372e0b42cc7ac8f8.tar.xz
mm: numa: Sanitize task_numa_fault() callsites
There are three callers of task_numa_fault(): - do_huge_pmd_numa_page(): Accounts against the current node, not the node where the page resides, unless we migrated, in which case it accounts against the node we migrated to. - do_numa_page(): Accounts against the current node, not the node where the page resides, unless we migrated, in which case it accounts against the node we migrated to. - do_pmd_numa_page(): Accounts not at all when the page isn't migrated, otherwise accounts against the node we migrated towards. This seems wrong to me; all three sites should have the same sementaics, furthermore we should accounts against where the page really is, we already know where the task is. So modify all three sites to always account; we did after all receive the fault; and always account to where the page is after migration, regardless of success. They all still differ on when they clear the PTE/PMD; ideally that would get sorted too. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-8-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c25
1 files changed, 13 insertions, 12 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1d6334fc8b6d..c3bb65f284d5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1281,18 +1281,19 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct anon_vma *anon_vma = NULL;
struct page *page;
unsigned long haddr = addr & HPAGE_PMD_MASK;
+ int page_nid = -1, this_nid = numa_node_id();
int target_nid;
- int current_nid = -1;
- bool migrated, page_locked;
+ bool page_locked;
+ bool migrated = false;
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(pmd, *pmdp)))
goto out_unlock;
page = pmd_page(pmd);
- current_nid = page_to_nid(page);
+ page_nid = page_to_nid(page);
count_vm_numa_event(NUMA_HINT_FAULTS);
- if (current_nid == numa_node_id())
+ if (page_nid == this_nid)
count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
/*
@@ -1335,19 +1336,18 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
spin_unlock(&mm->page_table_lock);
migrated = migrate_misplaced_transhuge_page(mm, vma,
pmdp, pmd, addr, page, target_nid);
- if (!migrated)
+ if (migrated)
+ page_nid = target_nid;
+ else
goto check_same;
- task_numa_fault(target_nid, HPAGE_PMD_NR, true);
- if (anon_vma)
- page_unlock_anon_vma_read(anon_vma);
- return 0;
+ goto out;
check_same:
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(pmd, *pmdp))) {
/* Someone else took our fault */
- current_nid = -1;
+ page_nid = -1;
goto out_unlock;
}
clear_pmdnuma:
@@ -1362,8 +1362,9 @@ out:
if (anon_vma)
page_unlock_anon_vma_read(anon_vma);
- if (current_nid != -1)
- task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+ if (page_nid != -1)
+ task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+
return 0;
}