[HMM 13/16] mm/migrate: allow migrate_vma() to alloc new page on empty entry

["Jérôme Glisse" <jglisse@redhat.com>]

This allow caller of migrate_vma() to allocate new page for empty CPU
page table entry. It only support anoymous memory and it won't allow
new page to be instance if userfaultfd is armed.

This is useful to device driver that want to migrate a range of virtual
address and would rather allocate new memory than having to fault later
on.

Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
---
 mm/migrate.c | 131 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 127 insertions(+), 4 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index f7a7661..cbaa4f2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -41,6 +41,7 @@
 #include <linux/page_idle.h>
 #include <linux/page_owner.h>
 #include <linux/memremap.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/tlbflush.h>
 
@@ -2111,9 +2112,10 @@ static int migrate_vma_collect_hole(unsigned long start,
 				    struct mm_walk *walk)
 {
 	struct migrate_vma *migrate = walk->private;
-	unsigned long addr, next;
+	unsigned long addr;
 
 	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+		migrate->cpages++;
 		migrate->dst[migrate->npages] = 0;
 		migrate->src[migrate->npages++] = 0;
 	}
@@ -2150,6 +2152,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 		pfn = pte_pfn(pte);
 
 		if (pte_none(pte)) {
+			migrate->cpages++;
 			mpfn = pfn = 0;
 			goto next;
 		}
@@ -2463,6 +2466,114 @@ static void migrate_vma_unmap(struct migrate_vma *migrate)
 	}
 }
 
+static void migrate_vma_insert_page(struct migrate_vma *migrate,
+				    unsigned long addr,
+				    struct page *page,
+				    unsigned long *src,
+				    unsigned long *dst)
+{
+	struct vm_area_struct *vma = migrate->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	struct mem_cgroup *memcg;
+	spinlock_t *ptl;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+	pte_t entry;
+
+	/* Only allow populating anonymous memory */
+	if (!vma_is_anonymous(vma))
+		goto abort;
+
+	pgdp = pgd_offset(mm, addr);
+	pudp = pud_alloc(mm, pgdp, addr);
+	if (!pudp)
+		goto abort;
+	pmdp = pmd_alloc(mm, pudp, addr);
+	if (!pmdp)
+		goto abort;
+
+	if (pmd_trans_unstable(pmdp) || pmd_devmap(*pmdp))
+		goto abort;
+
+	/*
+	 * Use pte_alloc() instead of pte_alloc_map().  We can't run
+	 * pte_offset_map() on pmds where a huge pmd might be created
+	 * from a different thread.
+	 *
+	 * pte_alloc_map() is safe to use under down_write(mmap_sem) or when
+	 * parallel threads are excluded by other means.
+	 *
+	 * Here we only have down_read(mmap_sem).
+	 */
+	if (pte_alloc(mm, pmdp, addr))
+		goto abort;
+
+	/* See the comment in pte_alloc_one_map() */
+	if (unlikely(pmd_trans_unstable(pmdp)))
+		goto abort;
+
+	if (unlikely(anon_vma_prepare(vma)))
+		goto abort;
+	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false))
+		goto abort;
+
+	/*
+	 * The memory barrier inside __SetPageUptodate makes sure that
+	 * preceding stores to the page contents become visible before
+	 * the set_pte_at() write.
+	 */
+	__SetPageUptodate(page);
+
+	if (is_zone_device_page(page) && is_device_unaddressable_page(page)) {
+		swp_entry_t swp_entry;
+
+		swp_entry = make_device_entry(page, vma->vm_flags & VM_WRITE);
+		entry = swp_entry_to_pte(swp_entry);
+	} else {
+		entry = mk_pte(page, vma->vm_page_prot);
+		if (vma->vm_flags & VM_WRITE)
+			entry = pte_mkwrite(pte_mkdirty(entry));
+	}
+
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!pte_none(*ptep)) {
+		pte_unmap_unlock(ptep, ptl);
+		mem_cgroup_cancel_charge(page, memcg, false);
+		goto abort;
+	}
+
+	/*
+	 * Check for usefaultfd but do not deliver the fault. Instead,
+	 * just back off.
+	 */
+	if (userfaultfd_missing(vma)) {
+		pte_unmap_unlock(ptep, ptl);
+		mem_cgroup_cancel_charge(page, memcg, false);
+		goto abort;
+	}
+
+	inc_mm_counter(mm, MM_ANONPAGES);
+	page_add_new_anon_rmap(page, vma, addr, false);
+	mem_cgroup_commit_charge(page, memcg, false, false);
+	if (!is_zone_device_page(page))
+		lru_cache_add_active_or_unevictable(page, vma);
+	set_pte_at(mm, addr, ptep, entry);
+
+	/* Take a reference on the page */
+	get_page(page);
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(vma, addr, ptep);
+	pte_unmap_unlock(ptep, ptl);
+	*src = MIGRATE_PFN_MIGRATE;
+	return;
+
+abort:
+	*src &= ~MIGRATE_PFN_MIGRATE;
+}
+
 /*
  * migrate_vma_pages() - migrate meta-data from src page to dst page
  * @migrate: migrate struct containing all migration information
@@ -2483,10 +2594,16 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
 		struct address_space *mapping;
 		int r;
 
-		if (!page || !newpage)
+		if (!newpage) {
+			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
 			continue;
-		if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
+		} else if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) {
+			if (!page)
+				migrate_vma_insert_page(migrate, addr, newpage,
+							&migrate->src[i],
+							&migrate->dst[i]);
 			continue;
+		}
 
 		mapping = page_mapping(page);
 
@@ -2536,8 +2653,14 @@ static void migrate_vma_finalize(struct migrate_vma *migrate)
 		struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
 		struct page *page = migrate_pfn_to_page(migrate->src[i]);
 
-		if (!page)
+		if (!page) {
+			if (newpage) {
+				unlock_page(newpage);
+				put_page(newpage);
+			}
 			continue;
+		}
+
 		if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) {
 			if (newpage) {
 				unlock_page(newpage);
-- 
2.9.3