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, 45 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 9a74855f1241..a0302ac0be98 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,15 +37,12 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                 unsigned long addr, unsigned long end, pgprot_t newprot,
-                int dirty_accountable, int prot_numa, bool *ret_all_same_cpupid)
+                int dirty_accountable, int prot_numa)
 {
         struct mm_struct *mm = vma->vm_mm;
         pte_t *pte, oldpte;
         spinlock_t *ptl;
         unsigned long pages = 0;
-        bool all_same_cpupid = true;
-        int last_cpu = -1;
-        int last_pid = -1;
 
         pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
         arch_enter_lazy_mmu_mode();
@@ -64,19 +61,6 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
                                 page = vm_normal_page(vma, addr, oldpte);
                                 if (page) {
-                                        int cpupid = page_cpupid_last(page);
-                                        int this_cpu = cpupid_to_cpu(cpupid);
-                                        int this_pid = cpupid_to_pid(cpupid);
-
-                                        if (last_cpu == -1)
-                                                last_cpu = this_cpu;
-                                        if (last_pid == -1)
-                                                last_pid = this_pid;
-                                        if (last_cpu != this_cpu ||
-                                            last_pid != this_pid) {
-                                                all_same_cpupid = false;
-                                        }
-
                                         if (!pte_numa(oldpte)) {
                                                 ptent = pte_mknuma(ptent);
                                                 updated = true;
@@ -115,26 +99,9 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
         arch_leave_lazy_mmu_mode();
         pte_unmap_unlock(pte - 1, ptl);
 
-        *ret_all_same_cpupid = all_same_cpupid;
         return pages;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-                                       pmd_t *pmd)
-{
-        spin_lock(&mm->page_table_lock);
-        set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
-        spin_unlock(&mm->page_table_lock);
-}
-#else
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-                                       pmd_t *pmd)
-{
-        BUG();
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
                 pud_t *pud, unsigned long addr, unsigned long end,
                 pgprot_t newprot, int dirty_accountable, int prot_numa)
@@ -142,7 +109,6 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
         pmd_t *pmd;
         unsigned long next;
         unsigned long pages = 0;
-        bool all_same_cpupid;
 
         pmd = pmd_offset(pud, addr);
         do {
@@ -168,17 +134,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
                 if (pmd_none_or_clear_bad(pmd))
                         continue;
                 this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-                                 dirty_accountable, prot_numa, &all_same_cpupid);
+                                 dirty_accountable, prot_numa);
                 pages += this_pages;
-
-                /*
-                 * If we are changing protections for NUMA hinting faults then
-                 * set pmd_numa if the examined pages were all on the same
-                 * node. This allows a regular PMD to be handled as one fault
-                 * and effectively batches the taking of the PTL
-                 */
-                if (prot_numa && this_pages && all_same_cpupid)
-                        change_pmd_protnuma(vma->vm_mm, addr, pmd);
         } while (pmd++, addr = next, addr != end);
 
         return pages;