mm/migrate: allow migrate_vma() to alloc new page on empty entry

This allows callers of migrate_vma() to allocate new page for empty CPU
page table entry (pte_none or back by zero page).  This is only for
anonymous memory and it won't allow new page to be instanced if the
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.

Link: http://lkml.kernel.org/r/20170817000548.32038-18-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Evgeny Baskakov <ebaskakov@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Sherry Cheung <SCheung@nvidia.com>
Cc: Subhash Gutti <sgutti@nvidia.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 196 insertions, 9 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 77cb2fef..e581253 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -37,6 +37,7 @@
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
 #include <linux/memremap.h>
+#include <linux/userfaultfd_k.h>
 #include <linux/balloon_compaction.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
@@ -2141,6 +2142,22 @@ static int migrate_vma_collect_hole(unsigned long start,
 	unsigned long addr;
 
 	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+		migrate->src[migrate->npages++] = MIGRATE_PFN_MIGRATE;
+		migrate->dst[migrate->npages] = 0;
+		migrate->cpages++;
+	}
+
+	return 0;
+}
+
+static int migrate_vma_collect_skip(unsigned long start,
+				    unsigned long end,
+				    struct mm_walk *walk)
+{
+	struct migrate_vma *migrate = walk->private;
+	unsigned long addr;
+
+	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
 		migrate->dst[migrate->npages] = 0;
 		migrate->src[migrate->npages++] = 0;
 	}
@@ -2178,7 +2195,7 @@ again:
 			spin_unlock(ptl);
 			split_huge_pmd(vma, pmdp, addr);
 			if (pmd_trans_unstable(pmdp))
-				return migrate_vma_collect_hole(start, end,
+				return migrate_vma_collect_skip(start, end,
 								walk);
 		} else {
 			int ret;
@@ -2186,19 +2203,22 @@ again:
 			get_page(page);
 			spin_unlock(ptl);
 			if (unlikely(!trylock_page(page)))
-				return migrate_vma_collect_hole(start, end,
+				return migrate_vma_collect_skip(start, end,
 								walk);
 			ret = split_huge_page(page);
 			unlock_page(page);
 			put_page(page);
-			if (ret || pmd_none(*pmdp))
+			if (ret)
+				return migrate_vma_collect_skip(start, end,
+								walk);
+			if (pmd_none(*pmdp))
 				return migrate_vma_collect_hole(start, end,
 								walk);
 		}
 	}
 
 	if (unlikely(pmd_bad(*pmdp)))
-		return migrate_vma_collect_hole(start, end, walk);
+		return migrate_vma_collect_skip(start, end, walk);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
@@ -2213,7 +2233,9 @@ again:
 		pfn = pte_pfn(pte);
 
 		if (pte_none(pte)) {
-			mpfn = pfn = 0;
+			mpfn = MIGRATE_PFN_MIGRATE;
+			migrate->cpages++;
+			pfn = 0;
 			goto next;
 		}
 
@@ -2235,6 +2257,12 @@ again:
 			if (is_write_device_private_entry(entry))
 				mpfn |= MIGRATE_PFN_WRITE;
 		} else {
+			if (is_zero_pfn(pfn)) {
+				mpfn = MIGRATE_PFN_MIGRATE;
+				migrate->cpages++;
+				pfn = 0;
+				goto next;
+			}
 			page = vm_normal_page(migrate->vma, addr, pte);
 			mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
 			mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
@@ -2554,6 +2582,135 @@ restore:
 	}
 }
 
+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;
+	bool flush = false;
+	spinlock_t *ptl;
+	pte_t entry;
+	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	/* Only allow populating anonymous memory */
+	if (!vma_is_anonymous(vma))
+		goto abort;
+
+	pgdp = pgd_offset(mm, addr);
+	p4dp = p4d_alloc(mm, pgdp, addr);
+	if (!p4dp)
+		goto abort;
+	pudp = pud_alloc(mm, p4dp, addr);
+	if (!pudp)
+		goto abort;
+	pmdp = pmd_alloc(mm, pudp, addr);
+	if (!pmdp)
+		goto abort;
+
+	if (pmd_trans_huge(*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_private_page(page)) {
+		swp_entry_t swp_entry;
+
+		swp_entry = make_device_private_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_present(*ptep)) {
+		unsigned long pfn = pte_pfn(*ptep);
+
+		if (!is_zero_pfn(pfn)) {
+			pte_unmap_unlock(ptep, ptl);
+			mem_cgroup_cancel_charge(page, memcg, false);
+			goto abort;
+		}
+		flush = true;
+	} else 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);
+	get_page(page);
+
+	if (flush) {
+		flush_cache_page(vma, addr, pte_pfn(*ptep));
+		ptep_clear_flush_notify(vma, addr, ptep);
+		set_pte_at_notify(mm, addr, ptep, entry);
+		update_mmu_cache(vma, addr, ptep);
+	} else {
+		/* No need to invalidate - it was non-present before */
+		set_pte_at(mm, addr, ptep, entry);
+		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
@@ -2566,7 +2723,10 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
 {
 	const unsigned long npages = migrate->npages;
 	const unsigned long start = migrate->start;
-	unsigned long addr, i;
+	struct vm_area_struct *vma = migrate->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long addr, i, mmu_start;
+	bool notified = false;
 
 	for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) {
 		struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
@@ -2574,10 +2734,27 @@ 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))
+		}
+
+		if (!page) {
+			if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) {
+				continue;
+			}
+			if (!notified) {
+				mmu_start = addr;
+				notified = true;
+				mmu_notifier_invalidate_range_start(mm,
+								mmu_start,
+								migrate->end);
+			}
+			migrate_vma_insert_page(migrate, addr, newpage,
+						&migrate->src[i],
+						&migrate->dst[i]);
 			continue;
+		}
 
 		mapping = page_mapping(page);
 
@@ -2605,6 +2782,10 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
 		if (r != MIGRATEPAGE_SUCCESS)
 			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
 	}
+
+	if (notified)
+		mmu_notifier_invalidate_range_end(mm, mmu_start,
+						  migrate->end);
 }
 
 /*
@@ -2627,8 +2808,14 @@ 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);