mm: numa: Do not batch handle PMD pages

With the THP migration races closed it is still possible to occasionally
see corruption. The problem is related to handling PMD pages in batch.
When a page fault is handled it can be assumed that the page being
faulted will also be flushed from the TLB. The same flushing does not
happen when handling PMD pages in batch. Fixing is straight forward but
there are a number of reasons not to

1. Multiple TLB flushes may have to be sent depending on what pages get
   migrated
2. The handling of PMDs in batch means that faults get accounted to
   the task that is handling the fault. While care is taken to only
   mark PMDs where the last CPU and PID match it can still have problems
   due to PID truncation when matching PIDs.
3. Batching on the PMD level may reduce faults but setting pmd_numa
   requires taking a heavy lock that can contend with THP migration
   and handling the fault requires the release/acquisition of the PTL
   for every page migrated. It's still pretty heavy.

PMD batch handling is not something that people ever have been happy
with. This patch removes it and later patches will deal with the
additional fault overhead using more installigent migrate rate adaption.

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/1381141781-10992-48-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 2 insertions, 99 deletions

diff --git a/mm/memory.c b/mm/memory.c
index eba846bcf124..9898eeb9a21c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3606,103 +3606,6 @@ out:
         return 0;
 }
 
-/* NUMA hinting page fault entry point for regular pmds */
-#ifdef CONFIG_NUMA_BALANCING
-static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-                     unsigned long addr, pmd_t *pmdp)
-{
-        pmd_t pmd;
-        pte_t *pte, *orig_pte;
-        unsigned long _addr = addr & PMD_MASK;
-        unsigned long offset;
-        spinlock_t *ptl;
-        bool numa = false;
-        int last_cpupid;
-
-        spin_lock(&mm->page_table_lock);
-        pmd = *pmdp;
-        if (pmd_numa(pmd)) {
-                set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd));
-                numa = true;
-        }
-        spin_unlock(&mm->page_table_lock);
-
-        if (!numa)
-                return 0;
-
-        /* we're in a page fault so some vma must be in the range */
-        BUG_ON(!vma);
-        BUG_ON(vma->vm_start >= _addr + PMD_SIZE);
-        offset = max(_addr, vma->vm_start) & ~PMD_MASK;
-        VM_BUG_ON(offset >= PMD_SIZE);
-        orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl);
-        pte += offset >> PAGE_SHIFT;
-        for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
-                pte_t pteval = *pte;
-                struct page *page;
-                int page_nid = -1;
-                int target_nid;
-                bool migrated = false;
-                int flags = 0;
-
-                if (!pte_present(pteval))
-                        continue;
-                if (!pte_numa(pteval))
-                        continue;
-                if (addr >= vma->vm_end) {
-                        vma = find_vma(mm, addr);
-                        /* there's a pte present so there must be a vma */
-                        BUG_ON(!vma);
-                        BUG_ON(addr < vma->vm_start);
-                }
-                if (pte_numa(pteval)) {
-                        pteval = pte_mknonnuma(pteval);
-                        set_pte_at(mm, addr, pte, pteval);
-                }
-                page = vm_normal_page(vma, addr, pteval);
-                if (unlikely(!page))
-                        continue;
-
-                /*
-                 * Avoid grouping on DSO/COW pages in specific and RO pages
-                 * in general, RO pages shouldn't hurt as much anyway since
-                 * they can be in shared cache state.
-                 */
-                if (!pte_write(pteval))
-                        flags |= TNF_NO_GROUP;
-
-                last_cpupid = page_cpupid_last(page);
-                page_nid = page_to_nid(page);
-                target_nid = numa_migrate_prep(page, vma, addr, page_nid);
-                pte_unmap_unlock(pte, ptl);
-                if (target_nid != -1) {
-                        migrated = migrate_misplaced_page(page, vma, target_nid);
-                        if (migrated) {
-                                page_nid = target_nid;
-                                flags |= TNF_MIGRATED;
-                        }
-                } else {
-                        put_page(page);
-                }
-
-                if (page_nid != -1)
-                        task_numa_fault(last_cpupid, page_nid, 1, flags);
-
-                pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
-        }
-        pte_unmap_unlock(orig_pte, ptl);
-
-        return 0;
-}
-#else
-static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-                     unsigned long addr, pmd_t *pmdp)
-{
-        BUG();
-        return 0;
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 /*
  * These routines also need to handle stuff like marking pages dirty
  * and/or accessed for architectures that don't do it in hardware (most
@@ -3841,8 +3744,8 @@ retry:
                 }
         }
 
-        if (pmd_numa(*pmd))
-                return do_pmd_numa_page(mm, vma, address, pmd);
+        /* THP should already have been handled */
+        BUG_ON(pmd_numa(*pmd));
 
         /*
          * Use __pte_alloc instead of pte_alloc_map, because we can't