1 files changed, 60 insertions, 7 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cdcd25cb30fe..cee42cf05477 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -285,6 +285,15 @@ static ssize_t use_zero_page_store(struct kobject *kobj,
 }
 static struct kobj_attribute use_zero_page_attr =
 	__ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store);
+
+static ssize_t hpage_pmd_size_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lu\n", HPAGE_PMD_SIZE);
+}
+static struct kobj_attribute hpage_pmd_size_attr =
+	__ATTR_RO(hpage_pmd_size);
+
 #ifdef CONFIG_DEBUG_VM
 static ssize_t debug_cow_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *buf)
@@ -307,6 +316,7 @@ static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
 	&defrag_attr.attr,
 	&use_zero_page_attr.attr,
+	&hpage_pmd_size_attr.attr,
 #if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE)
 	&shmem_enabled_attr.attr,
 #endif
@@ -737,8 +747,9 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;
-	if (track_pfn_insert(vma, &pgprot, pfn))
-		return VM_FAULT_SIGBUS;
+
+	track_pfn_insert(vma, &pgprot, pfn);
+
 	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
 	return VM_FAULT_NOPAGE;
 }
@@ -1322,6 +1333,8 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct mm_struct *mm = tlb->mm;
 	bool ret = false;
 
+	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
 		goto out_unlocked;
@@ -1377,12 +1390,23 @@ 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)
 {
 	pmd_t orig_pmd;
 	spinlock_t *ptl;
 
+	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
 		return 0;
@@ -1398,12 +1422,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	if (vma_is_dax(vma)) {
 		spin_unlock(ptl);
 		if (is_huge_zero_pmd(orig_pmd))
-			tlb_remove_page(tlb, pmd_page(orig_pmd));
+			tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
 	} else if (is_huge_zero_pmd(orig_pmd)) {
 		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
 		atomic_long_dec(&tlb->mm->nr_ptes);
 		spin_unlock(ptl);
-		tlb_remove_page(tlb, pmd_page(orig_pmd));
+		tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
 	} else {
 		struct page *page = pmd_page(orig_pmd);
 		page_remove_rmap(page, true);
@@ -1416,6 +1440,8 @@ 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);
@@ -1424,13 +1450,29 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return 1;
 }
 
+#ifndef pmd_move_must_withdraw
+static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
+					 spinlock_t *old_pmd_ptl,
+					 struct vm_area_struct *vma)
+{
+	/*
+	 * With split pmd lock we also need to move preallocated
+	 * PTE page table if new_pmd is on different PMD page table.
+	 *
+	 * We also don't deposit and withdraw tables for file pages.
+	 */
+	return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);
+}
+#endif
+
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd)
+		  pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
 	struct mm_struct *mm = vma->vm_mm;
+	bool force_flush = false;
 
 	if ((old_addr & ~HPAGE_PMD_MASK) ||
 	    (new_addr & ~HPAGE_PMD_MASK) ||
@@ -1456,10 +1498,11 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
+		if (pmd_present(pmd) && pmd_dirty(pmd))
+			force_flush = true;
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
-		if (pmd_move_must_withdraw(new_ptl, old_ptl) &&
-				vma_is_anonymous(vma)) {
+		if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) {
 			pgtable_t pgtable;
 			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
@@ -1467,6 +1510,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
 		if (new_ptl != old_ptl)
 			spin_unlock(new_ptl);
+		if (force_flush)
+			flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
+		else
+			*need_flush = true;
 		spin_unlock(old_ptl);
 		return true;
 	}
@@ -1581,6 +1628,12 @@ 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);