4 files changed, 45 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8d1c41d28318..ac07a30a7934 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -281,6 +281,10 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
                             pmd_t *pmdp);
 
+#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+extern void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+                                    unsigned long address, pmd_t *pmdp);
+
 #define pmd_move_must_withdraw pmd_move_must_withdraw
 struct spinlock;
 static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 3124a20d0fab..cdf2123d46db 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -646,6 +646,28 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
         return pgtable;
 }
 
+void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+                             unsigned long address, pmd_t *pmdp)
+{
+        VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+        VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
+
+        /*
+         * We can't mark the pmd none here, because that will cause a race
+         * against exit_mmap. We need to continue mark pmd TRANS HUGE, while
+         * we spilt, but at the same time we wan't rest of the ppc64 code
+         * not to insert hash pte on this, because we will be modifying
+         * the deposited pgtable in the caller of this function. Hence
+         * clear the _PAGE_USER so that we move the fault handling to
+         * higher level function and that will serialize against ptl.
+         * We need to flush existing hash pte entries here even though,
+         * the translation is still valid, because we will withdraw
+         * pgtable_t after this.
+         */
+        pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_USER, 0);
+}
+
+
 /*
  * set a new huge pmd. We should not be called for updating
  * an existing pmd entry. That should go via pmd_hugepage_update.
@@ -663,10 +685,20 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
         return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
 }
 
+/*
+ * We use this to invalidate a pmdp entry before switching from a
+ * hugepte to regular pmd entry.
+ */
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
                      pmd_t *pmdp)
 {
         pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+
+        /*
+         * This ensures that generic code that rely on IRQ disabling
+         * to prevent a parallel THP split work as expected.
+         */
+        kick_all_cpus_sync();
 }
 
 /*
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 0b3c0d39ef75..c370b261c720 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -239,6 +239,14 @@ extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
                             pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+                                           unsigned long address, pmd_t *pmdp)
+{
+
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b1cf73bc3b12..de3f43cde129 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2856,6 +2856,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
         young = pmd_young(*pmd);
         dirty = pmd_dirty(*pmd);
 
+        pmdp_huge_split_prepare(vma, haddr, pmd);
         pgtable = pgtable_trans_huge_withdraw(mm, pmd);
         pmd_populate(mm, &_pmd, pgtable);