[HMM 13/15] mm/migrate: migrate_vma() unmap page from vma while collecting pages

[JÃrÃme Glisse]

Common case for migration of virtual address range is page are map
only once inside the vma in which migration is taking place. Because
we already walk the CPU page table for that range we can directly do
the unmap there and setup special migration swap entry.

Signed-off-by: JÃrÃme Glisse <jglisse@xxxxxxxxxx>
Signed-off-by: Evgeny Baskakov <ebaskakov@xxxxxxxxxx>
Signed-off-by: John Hubbard <jhubbard@xxxxxxxxxx>
Signed-off-by: Mark Hairgrove <mhairgrove@xxxxxxxxxx>
Signed-off-by: Sherry Cheung <SCheung@xxxxxxxxxx>
Signed-off-by: Subhash Gutti <sgutti@xxxxxxxxxx>
---
 mm/migrate.c | 114 ++++++++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 98 insertions(+), 16 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 12063f3..1f2bc61 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2119,7 +2119,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 {
 	struct migrate_vma *migrate = walk->private;
 	struct mm_struct *mm = walk->vma->vm_mm;
-	unsigned long addr = start;
+	unsigned long addr = start, unmapped = 0;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
@@ -2129,9 +2129,12 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 	}
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
+
 	for (; addr < end; addr += PAGE_SIZE, ptep++) {
 		unsigned long mpfn, pfn;
 		struct page *page;
+		swp_entry_t entry;
 		pte_t pte;
 
 		pte = *ptep;
@@ -2163,11 +2166,44 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 		mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
 		mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
 
+		/*
+		 * Optimize for the common case where page is only mapped once
+		 * in one process. If we can lock the page, then we can safely
+		 * set up a special migration page table entry now.
+		 */
+		if (trylock_page(page)) {
+			pte_t swp_pte;
+
+			mpfn |= MIGRATE_PFN_LOCKED;
+			ptep_get_and_clear(mm, addr, ptep);
+
+			/* Setup special migration page table entry */
+			entry = make_migration_entry(page, pte_write(pte));
+			swp_pte = swp_entry_to_pte(entry);
+			if (pte_soft_dirty(pte))
+				swp_pte = pte_swp_mksoft_dirty(swp_pte);
+			set_pte_at(mm, addr, ptep, swp_pte);
+
+			/*
+			 * This is like regular unmap: we remove the rmap and
+			 * drop page refcount. Page won't be freed, as we took
+			 * a reference just above.
+			 */
+			page_remove_rmap(page, false);
+			put_page(page);
+			unmapped++;
+		}
+
 next:
 		migrate->src[migrate->npages++] = mpfn;
 	}
+	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(ptep - 1, ptl);
 
+	/* Only flush the TLB if we actually modified any entries */
+	if (unmapped)
+		flush_tlb_range(walk->vma, start, end);
+
 	return 0;
 }
 
@@ -2192,7 +2228,13 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
 	mm_walk.mm = migrate->vma->vm_mm;
 	mm_walk.private = migrate;
 
+	mmu_notifier_invalidate_range_start(mm_walk.mm,
+					    migrate->start,
+					    migrate->end);
 	walk_page_range(migrate->start, migrate->end, &mm_walk);
+	mmu_notifier_invalidate_range_end(mm_walk.mm,
+					  migrate->start,
+					  migrate->end);
 
 	migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT);
 }
@@ -2248,12 +2290,16 @@ static void migrate_vma_prepare(struct migrate_vma *migrate)
 
 	for (i = 0; i < npages; i++) {
 		struct page *page = migrate_pfn_to_page(migrate->src[i]);
+		bool remap = true;
 
 		if (!page)
 			continue;
 
-		lock_page(page);
-		migrate->src[i] |= MIGRATE_PFN_LOCKED;
+		if (!(migrate->src[i] & MIGRATE_PFN_LOCKED)) {
+			remap = false;
+			lock_page(page);
+			migrate->src[i] |= MIGRATE_PFN_LOCKED;
+		}
 
 		if (!PageLRU(page) && allow_drain) {
 			/* Drain CPU's pagevec */
@@ -2262,21 +2308,50 @@ static void migrate_vma_prepare(struct migrate_vma *migrate)
 		}
 
 		if (isolate_lru_page(page)) {
-			migrate->src[i] = 0;
-			unlock_page(page);
-			migrate->cpages--;
-			put_page(page);
+			if (remap) {
+				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+				migrate->cpages--;
+				restore++;
+			} else {
+				migrate->src[i] = 0;
+				unlock_page(page);
+				migrate->cpages--;
+				put_page(page);
+			}
 			continue;
 		}
 
 		if (!migrate_vma_check_page(page)) {
-			migrate->src[i] = 0;
-			unlock_page(page);
-			migrate->cpages--;
+			if (remap) {
+				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+				migrate->cpages--;
+				restore++;
 
-			putback_lru_page(page);
+				get_page(page);
+				putback_lru_page(page);
+			} else {
+				migrate->src[i] = 0;
+				unlock_page(page);
+				migrate->cpages--;
+
+				putback_lru_page(page);
+			}
 		}
 	}
+
+	for (i = 0, addr = start; i < npages && restore; i++, addr += PAGE_SIZE) {
+		struct page *page = migrate_pfn_to_page(migrate->src[i]);
+
+		if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE))
+			continue;
+
+		remove_migration_pte(page, migrate->vma, addr, page);
+
+		migrate->src[i] = 0;
+		unlock_page(page);
+		put_page(page);
+		restore--;
+	}
 }
 
 /*
@@ -2303,12 +2378,19 @@ static void migrate_vma_unmap(struct migrate_vma *migrate)
 		if (!page || !(migrate->src[i] & MIGRATE_PFN_MIGRATE))
 			continue;
 
-		try_to_unmap(page, flags);
-		if (page_mapped(page) || !migrate_vma_check_page(page)) {
-			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
-			migrate->cpages--;
-			restore++;
+		if (page_mapped(page)) {
+			try_to_unmap(page, flags);
+			if (page_mapped(page))
+				goto restore;
 		}
+
+		if (migrate_vma_check_page(page))
+			continue;
+
+restore:
+		migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
+		migrate->cpages--;
+		restore++;
 	}
 
 	for (addr = start, i = 0; i < npages && restore; addr += PAGE_SIZE, i++) {
-- 
2.9.3