mm,thp: add read-only THP support for (non-shmem) FS

This patch is (hopefully) the first step to enable THP for non-shmem
filesystems.

This patch enables an application to put part of its text sections to THP
via madvise, for example:

    madvise((void *)0x600000, 0x200000, MADV_HUGEPAGE);

We tried to reuse the logic for THP on tmpfs.

Currently, write is not supported for non-shmem THP.  khugepaged will only
process vma with VM_DENYWRITE.  sys_mmap() ignores VM_DENYWRITE requests
(see ksys_mmap_pgoff).  The only way to create vma with VM_DENYWRITE is
execve().  This requirement limits non-shmem THP to text sections.

The next patch will handle writes, which would only happen when the all
the vmas with VM_DENYWRITE are unmapped.

An EXPERIMENTAL config, READ_ONLY_THP_FOR_FS, is added to gate this
feature.

[songliubraving@fb.com: fix build without CONFIG_SHMEM]
  Link: http://lkml.kernel.org/r/F53407FB-96CC-42E8-9862-105C92CC2B98@fb.com
[songliubraving@fb.com: fix double unlock in collapse_file()]
  Link: http://lkml.kernel.org/r/B960CBFA-8EFC-4DA4-ABC5-1977FFF2CA57@fb.com
Link: http://lkml.kernel.org/r/20190801184244.3169074-7-songliubraving@fb.com
Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Rik van Riel <riel@surriel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/Kconfig

@@ -712,6 +712,17 @@ config GUP_BENCHMARK
 config GUP_GET_PTE_LOW_HIGH
 	bool
 
+config READ_ONLY_THP_FOR_FS
+	bool "Read-only THP for filesystems (EXPERIMENTAL)"
+	depends on TRANSPARENT_HUGE_PAGECACHE && SHMEM
+
+	help
+	  Allow khugepaged to put read-only file-backed pages in THP.
+
+	  This is marked experimental because it is a new feature. Write
+	  support of file THPs will be developed in the next few release
+	  cycles.
+
 config ARCH_HAS_PTE_SPECIAL
 	bool
 

mm/filemap.c

@@ -203,8 +203,8 @@ static void unaccount_page_cache_page(struct address_space *mapping,
 		__mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
 		if (PageTransHuge(page))
 			__dec_node_page_state(page, NR_SHMEM_THPS);
-	} else {
+	} else if (PageTransHuge(page)) {
-		VM_BUG_ON_PAGE(PageTransHuge(page), page);
+		__dec_node_page_state(page, NR_FILE_THPS);
 	}
 
 	/*

mm/khugepaged.c

@@ -48,6 +48,7 @@ enum scan_result {
 	SCAN_CGROUP_CHARGE_FAIL,
 	SCAN_EXCEED_SWAP_PTE,
 	SCAN_TRUNCATED,
+	SCAN_PAGE_HAS_PRIVATE,
 };
 
 #define CREATE_TRACE_POINTS
@@ -404,7 +405,11 @@ static bool hugepage_vma_check(struct vm_area_struct *vma,
 	    (vm_flags & VM_NOHUGEPAGE) ||
 	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
 		return false;
-	if (shmem_file(vma->vm_file)) {
+
+	if (shmem_file(vma->vm_file) ||
+	    (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
+	     vma->vm_file &&
+	     (vm_flags & VM_DENYWRITE))) {
 		if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
 			return false;
 		return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
@@ -456,8 +461,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 	unsigned long hstart, hend;
 
 	/*
-	 * khugepaged does not yet work on non-shmem files or special
+	 * khugepaged only supports read-only files for non-shmem files.
-	 * mappings. And file-private shmem THP is not supported.
+	 * khugepaged does not yet work on special mappings. And
+	 * file-private shmem THP is not supported.
 	 */
 	if (!hugepage_vma_check(vma, vm_flags))
 		return 0;
@@ -1287,12 +1293,12 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 }
 
 /**
- * collapse_file - collapse small tmpfs/shmem pages into huge one.
+ * collapse_file - collapse filemap/tmpfs/shmem pages into huge one.
  *
  * Basic scheme is simple, details are more complex:
  *  - allocate and lock a new huge page;
  *  - scan page cache replacing old pages with the new one
- *    + swap in pages if necessary;
+ *    + swap/gup in pages if necessary;
  *    + fill in gaps;
  *    + keep old pages around in case rollback is required;
  *  - if replacing succeeds:
@@ -1316,7 +1322,9 @@ static void collapse_file(struct mm_struct *mm,
 	LIST_HEAD(pagelist);
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
 	int nr_none = 0, result = SCAN_SUCCEED;
+	bool is_shmem = shmem_file(file);
 
+	VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
 	VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
 
 	/* Only allocate from the target node */
@@ -1348,7 +1356,8 @@ static void collapse_file(struct mm_struct *mm,
 	} while (1);
 
 	__SetPageLocked(new_page);
-	__SetPageSwapBacked(new_page);
+	if (is_shmem)
+		__SetPageSwapBacked(new_page);
 	new_page->index = start;
 	new_page->mapping = mapping;
 
@@ -1363,41 +1372,75 @@ static void collapse_file(struct mm_struct *mm,
 		struct page *page = xas_next(&xas);
 
 		VM_BUG_ON(index != xas.xa_index);
-		if (!page) {
+		if (is_shmem) {
-			/*
+			if (!page) {
-			 * Stop if extent has been truncated or hole-punched,
+				/*
-			 * and is now completely empty.
+				 * Stop if extent has been truncated or
-			 */
+				 * hole-punched, and is now completely
-			if (index == start) {
+				 * empty.
-				if (!xas_next_entry(&xas, end - 1)) {
+				 */
-					result = SCAN_TRUNCATED;
+				if (index == start) {
+					if (!xas_next_entry(&xas, end - 1)) {
+						result = SCAN_TRUNCATED;
+						goto xa_locked;
+					}
+					xas_set(&xas, index);
+				}
+				if (!shmem_charge(mapping->host, 1)) {
+					result = SCAN_FAIL;
 					goto xa_locked;
 				}
-				xas_set(&xas, index);
+				xas_store(&xas, new_page);
+				nr_none++;
+				continue;
 			}
-			if (!shmem_charge(mapping->host, 1)) {
+
-				result = SCAN_FAIL;
+			if (xa_is_value(page) || !PageUptodate(page)) {
+				xas_unlock_irq(&xas);
+				/* swap in or instantiate fallocated page */
+				if (shmem_getpage(mapping->host, index, &page,
+						  SGP_NOHUGE)) {
+					result = SCAN_FAIL;
+					goto xa_unlocked;
+				}
+			} else if (trylock_page(page)) {
+				get_page(page);
+				xas_unlock_irq(&xas);
+			} else {
+				result = SCAN_PAGE_LOCK;
 				goto xa_locked;
 			}
-			xas_store(&xas, new_page);
+		} else {	/* !is_shmem */
-			nr_none++;
+			if (!page || xa_is_value(page)) {
-			continue;
+				xas_unlock_irq(&xas);
-		}
+				page_cache_sync_readahead(mapping, &file->f_ra,
-
+							  file, index,
-		if (xa_is_value(page) || !PageUptodate(page)) {
+							  PAGE_SIZE);
-			xas_unlock_irq(&xas);
+				/* drain pagevecs to help isolate_lru_page() */
-			/* swap in or instantiate fallocated page */
+				lru_add_drain();
-			if (shmem_getpage(mapping->host, index, &page,
+				page = find_lock_page(mapping, index);
-						SGP_NOHUGE)) {
+				if (unlikely(page == NULL)) {
+					result = SCAN_FAIL;
+					goto xa_unlocked;
+				}
+			} else if (!PageUptodate(page)) {
+				xas_unlock_irq(&xas);
+				wait_on_page_locked(page);
+				if (!trylock_page(page)) {
+					result = SCAN_PAGE_LOCK;
+					goto xa_unlocked;
+				}
+				get_page(page);
+			} else if (PageDirty(page)) {
 				result = SCAN_FAIL;
-				goto xa_unlocked;
+				goto xa_locked;
+			} else if (trylock_page(page)) {
+				get_page(page);
+				xas_unlock_irq(&xas);
+			} else {
+				result = SCAN_PAGE_LOCK;
+				goto xa_locked;
 			}
-		} else if (trylock_page(page)) {
-			get_page(page);
-			xas_unlock_irq(&xas);
-		} else {
-			result = SCAN_PAGE_LOCK;
-			goto xa_locked;
 		}
 
 		/*
@@ -1426,6 +1469,12 @@ static void collapse_file(struct mm_struct *mm,
 			goto out_unlock;
 		}
 
+		if (page_has_private(page) &&
+		    !try_to_release_page(page, GFP_KERNEL)) {
+			result = SCAN_PAGE_HAS_PRIVATE;
+			goto out_unlock;
+		}
+
 		if (page_mapped(page))
 			unmap_mapping_pages(mapping, index, 1, false);
 
@@ -1463,12 +1512,18 @@ static void collapse_file(struct mm_struct *mm,
 		goto xa_unlocked;
 	}
 
-	__inc_node_page_state(new_page, NR_SHMEM_THPS);
+	if (is_shmem)
+		__inc_node_page_state(new_page, NR_SHMEM_THPS);
+	else
+		__inc_node_page_state(new_page, NR_FILE_THPS);
+
 	if (nr_none) {
 		struct zone *zone = page_zone(new_page);
 
 		__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
-		__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+		if (is_shmem)
+			__mod_node_page_state(zone->zone_pgdat,
+					      NR_SHMEM, nr_none);
 	}
 
 xa_locked:
@@ -1506,10 +1561,15 @@ static void collapse_file(struct mm_struct *mm,
 
 		SetPageUptodate(new_page);
 		page_ref_add(new_page, HPAGE_PMD_NR - 1);
-		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
+
+		if (is_shmem) {
+			set_page_dirty(new_page);
+			lru_cache_add_anon(new_page);
+		} else {
+			lru_cache_add_file(new_page);
+		}
 		count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1);
-		lru_cache_add_anon(new_page);
 
 		/*
 		 * Remove pte page tables, so we can re-fault the page as huge.
@@ -1524,7 +1584,9 @@ static void collapse_file(struct mm_struct *mm,
 		/* Something went wrong: roll back page cache changes */
 		xas_lock_irq(&xas);
 		mapping->nrpages -= nr_none;
-		shmem_uncharge(mapping->host, nr_none);
+
+		if (is_shmem)
+			shmem_uncharge(mapping->host, nr_none);
 
 		xas_set(&xas, start);
 		xas_for_each(&xas, page, end - 1) {
@@ -1607,7 +1669,8 @@ static void khugepaged_scan_file(struct mm_struct *mm,
 			break;
 		}
 
-		if (page_count(page) != 1 + page_mapcount(page)) {
+		if (page_count(page) !=
+		    1 + page_mapcount(page) + page_has_private(page)) {
 			result = SCAN_PAGE_COUNT;
 			break;
 		}
@@ -1713,11 +1776,13 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 			VM_BUG_ON(khugepaged_scan.address < hstart ||
 				  khugepaged_scan.address + HPAGE_PMD_SIZE >
 				  hend);
-			if (shmem_file(vma->vm_file)) {
+			if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
 				struct file *file;
 				pgoff_t pgoff = linear_page_index(vma,
 						khugepaged_scan.address);
-				if (!shmem_huge_enabled(vma))
+
+				if (shmem_file(vma->vm_file)
+				    && !shmem_huge_enabled(vma))
 					goto skip;
 				file = get_file(vma->vm_file);
 				up_read(&mm->mmap_sem);

mm/rmap.c

@@ -1189,8 +1189,10 @@ void page_add_file_rmap(struct page *page, bool compound)
 		}
 		if (!atomic_inc_and_test(compound_mapcount_ptr(page)))
 			goto out;
-		VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
+		if (PageSwapBacked(page))
-		__inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
+			__inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
+		else
+			__inc_node_page_state(page, NR_FILE_PMDMAPPED);
 	} else {
 		if (PageTransCompound(page) && page_mapping(page)) {
 			VM_WARN_ON_ONCE(!PageLocked(page));
@@ -1229,8 +1231,10 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 		}
 		if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
 			goto out;
-		VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
+		if (PageSwapBacked(page))
-		__dec_node_page_state(page, NR_SHMEM_PMDMAPPED);
+			__dec_node_page_state(page, NR_SHMEM_PMDMAPPED);
+		else
+			__dec_node_page_state(page, NR_FILE_PMDMAPPED);
 	} else {
 		if (!atomic_add_negative(-1, &page->_mapcount))
 			goto out;