mm: THP page cache support for ppc64

Add arch specific callback in the generic THP page cache code that will
deposit and withdarw preallocated page table.  Archs like ppc64 use this
preallocated table to store the hash pte slot information.

Testing:
kernel build of the patch series on tmpfs mounted with option huge=always

The related thp stat:
thp_fault_alloc 72939
thp_fault_fallback 60547
thp_collapse_alloc 603
thp_collapse_alloc_failed 0
thp_file_alloc 253763
thp_file_mapped 4251
thp_split_page 51518
thp_split_page_failed 1
thp_deferred_split_page 73566
thp_split_pmd 665
thp_zero_page_alloc 3
thp_zero_page_alloc_failed 0

[akpm@linux-foundation.org: remove unneeded parentheses, per Kirill]
Link: http://lkml.kernel.org/r/20161113150025.17942-2-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 17 insertions, 0 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b54044c21076..2b44ac11178f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1380,6 +1380,15 @@ out_unlocked:
         return ret;
 }
 
+static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
+{
+        pgtable_t pgtable;
+
+        pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+        pte_free(mm, pgtable);
+        atomic_long_dec(&mm->nr_ptes);
+}
+
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
                  pmd_t *pmd, unsigned long addr)
 {
@@ -1421,6 +1430,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
                         atomic_long_dec(&tlb->mm->nr_ptes);
                         add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
                 } else {
+                        if (arch_needs_pgtable_deposit())
+                                zap_deposited_table(tlb->mm, pmd);
                         add_mm_counter(tlb->mm, MM_FILEPAGES, -HPAGE_PMD_NR);
                 }
                 spin_unlock(ptl);
@@ -1607,6 +1618,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
         if (!vma_is_anonymous(vma)) {
                 _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+                /*
+                 * We are going to unmap this huge page. So
+                 * just go ahead and zap it
+                 */
+                if (arch_needs_pgtable_deposit())
+                        zap_deposited_table(mm, pmd);
                 if (vma_is_dax(vma))
                         return;
                 page = pmd_page(_pmd);