mm: introduce do_set_pmd()

With postponed page table allocation we have chance to setup huge pages.
do_set_pte() calls do_set_pmd() if following criteria met:

 - page is compound;
 - pmd entry in pmd_none();
 - vma has suitable size and alignment;

Link: http://lkml.kernel.org/r/1466021202-61880-12-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/huge_mm.h

@@ -143,6 +143,8 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 struct page *get_huge_zero_page(void);
 void put_huge_zero_page(void);
 
+#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })

mm/huge_memory.c

@@ -796,11 +796,6 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 	return pmd;
 }
 
-static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
-{
-	return pmd_mkhuge(mk_pmd(page, prot));
-}
-
 static inline struct list_head *page_deferred_list(struct page *page)
 {
 	/*

mm/memory.c

@@ -2920,6 +2920,66 @@ map_pte:
 	return 0;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1)
+static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
+		unsigned long haddr)
+{
+	if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) !=
+			(vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK))
+		return false;
+	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+		return false;
+	return true;
+}
+
+static int do_set_pmd(struct fault_env *fe, struct page *page)
+{
+	struct vm_area_struct *vma = fe->vma;
+	bool write = fe->flags & FAULT_FLAG_WRITE;
+	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	pmd_t entry;
+	int i, ret;
+
+	if (!transhuge_vma_suitable(vma, haddr))
+		return VM_FAULT_FALLBACK;
+
+	ret = VM_FAULT_FALLBACK;
+	page = compound_head(page);
+
+	fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
+	if (unlikely(!pmd_none(*fe->pmd)))
+		goto out;
+
+	for (i = 0; i < HPAGE_PMD_NR; i++)
+		flush_icache_page(vma, page + i);
+
+	entry = mk_huge_pmd(page, vma->vm_page_prot);
+	if (write)
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+
+	add_mm_counter(vma->vm_mm, MM_FILEPAGES, HPAGE_PMD_NR);
+	page_add_file_rmap(page, true);
+
+	set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry);
+
+	update_mmu_cache_pmd(vma, haddr, fe->pmd);
+
+	/* fault is handled */
+	ret = 0;
+out:
+	spin_unlock(fe->ptl);
+	return ret;
+}
+#else
+static int do_set_pmd(struct fault_env *fe, struct page *page)
+{
+	BUILD_BUG();
+	return 0;
+}
+#endif
+
 /**
  * alloc_set_pte - setup new PTE entry for given page and add reverse page
  * mapping. If needed, the fucntion allocates page table or use pre-allocated.
@@ -2939,9 +2999,19 @@ int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
 	struct vm_area_struct *vma = fe->vma;
 	bool write = fe->flags & FAULT_FLAG_WRITE;
 	pte_t entry;
+	int ret;
+
+	if (pmd_none(*fe->pmd) && PageTransCompound(page)) {
+		/* THP on COW? */
+		VM_BUG_ON_PAGE(memcg, page);
+
+		ret = do_set_pmd(fe, page);
+		if (ret != VM_FAULT_FALLBACK)
+			return ret;
+	}
 
 	if (!fe->pte) {
-		int ret = pte_alloc_one_map(fe);
+		ret = pte_alloc_one_map(fe);
 		if (ret)
 			return ret;
 	}

mm/migrate.c

@@ -1986,8 +1986,7 @@ fail_putback:
 	}
 
 	orig_entry = *pmd;
-	entry = mk_pmd(new_page, vma->vm_page_prot);
+	entry = mk_huge_pmd(new_page, vma->vm_page_prot);
-	entry = pmd_mkhuge(entry);
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
 	/*