Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 136 insertions, 41 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 196f701665..657bcd887f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -168,7 +168,7 @@ static void filemap_unaccount_folio(struct address_space *mapping,
 		add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 
 		if (mapping_exiting(mapping) && !folio_test_large(folio)) {
-			int mapcount = page_mapcount(&folio->page);
+			int mapcount = folio_mapcount(folio);
 
 			if (folio_ref_count(folio) >= mapcount + 2) {
 				/*
@@ -852,23 +852,18 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 		struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp)
 {
 	XA_STATE(xas, &mapping->i_pages, index);
-	bool huge = folio_test_hugetlb(folio);
-	bool charged = false;
-	long nr = 1;
+	void *alloced_shadow = NULL;
+	int alloced_order = 0;
+	bool huge;
+	long nr;
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
 	mapping_set_update(&xas, mapping);
 
-	if (!huge) {
-		int error = mem_cgroup_charge(folio, NULL, gfp);
-		if (error)
-			return error;
-		charged = true;
-	}
-
 	VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
 	xas_set_order(&xas, index, folio_order(folio));
+	huge = folio_test_hugetlb(folio);
 	nr = folio_nr_pages(folio);
 
 	gfp &= GFP_RECLAIM_MASK;
@@ -876,13 +871,10 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 	folio->mapping = mapping;
 	folio->index = xas.xa_index;
 
-	do {
-		unsigned int order = xa_get_order(xas.xa, xas.xa_index);
+	for (;;) {
+		int order = -1, split_order = 0;
 		void *entry, *old = NULL;
 
-		if (order > folio_order(folio))
-			xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
-					order, gfp);
 		xas_lock_irq(&xas);
 		xas_for_each_conflict(&xas, entry) {
 			old = entry;
@@ -890,19 +882,33 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 				xas_set_err(&xas, -EEXIST);
 				goto unlock;
 			}
+			/*
+			 * If a larger entry exists,
+			 * it will be the first and only entry iterated.
+			 */
+			if (order == -1)
+				order = xas_get_order(&xas);
+		}
+
+		/* entry may have changed before we re-acquire the lock */
+		if (alloced_order && (old != alloced_shadow || order != alloced_order)) {
+			xas_destroy(&xas);
+			alloced_order = 0;
 		}
 
 		if (old) {
-			if (shadowp)
-				*shadowp = old;
-			/* entry may have been split before we acquired lock */
-			order = xa_get_order(xas.xa, xas.xa_index);
-			if (order > folio_order(folio)) {
+			if (order > 0 && order > folio_order(folio)) {
 				/* How to handle large swap entries? */
 				BUG_ON(shmem_mapping(mapping));
+				if (!alloced_order) {
+					split_order = order;
+					goto unlock;
+				}
 				xas_split(&xas, old, order);
 				xas_reset(&xas);
 			}
+			if (shadowp)
+				*shadowp = old;
 		}
 
 		xas_store(&xas, folio);
@@ -918,9 +924,24 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 				__lruvec_stat_mod_folio(folio,
 						NR_FILE_THPS, nr);
 		}
+
 unlock:
 		xas_unlock_irq(&xas);
-	} while (xas_nomem(&xas, gfp));
+
+		/* split needed, alloc here and retry. */
+		if (split_order) {
+			xas_split_alloc(&xas, old, split_order, gfp);
+			if (xas_error(&xas))
+				goto error;
+			alloced_shadow = old;
+			alloced_order = split_order;
+			xas_reset(&xas);
+			continue;
+		}
+
+		if (!xas_nomem(&xas, gfp))
+			break;
+	}
 
 	if (xas_error(&xas))
 		goto error;
@@ -928,8 +949,6 @@ unlock:
 	trace_mm_filemap_add_to_page_cache(folio);
 	return 0;
 error:
-	if (charged)
-		mem_cgroup_uncharge(folio);
 	folio->mapping = NULL;
 	/* Leave page->index set: truncation relies upon it */
 	folio_put_refs(folio, nr);
@@ -943,11 +962,16 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio,
 	void *shadow = NULL;
 	int ret;
 
+	ret = mem_cgroup_charge(folio, NULL, gfp);
+	if (ret)
+		return ret;
+
 	__folio_set_locked(folio);
 	ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
+		mem_cgroup_uncharge(folio);
 		__folio_clear_locked(folio);
-	else {
+	} else {
 		/*
 		 * The folio might have been evicted from cache only
 		 * recently, in which case it should be activated like
@@ -966,7 +990,7 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio,
 EXPORT_SYMBOL_GPL(filemap_add_folio);
 
 #ifdef CONFIG_NUMA
-struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
+struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
 {
 	int n;
 	struct folio *folio;
@@ -976,14 +1000,14 @@ struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
 		do {
 			cpuset_mems_cookie = read_mems_allowed_begin();
 			n = cpuset_mem_spread_node();
-			folio = __folio_alloc_node(gfp, order, n);
+			folio = __folio_alloc_node_noprof(gfp, order, n);
 		} while (!folio && read_mems_allowed_retry(cpuset_mems_cookie));
 
 		return folio;
 	}
-	return folio_alloc(gfp, order);
+	return folio_alloc_noprof(gfp, order);
 }
-EXPORT_SYMBOL(filemap_alloc_folio);
+EXPORT_SYMBOL(filemap_alloc_folio_noprof);
 #endif
 
 /*
@@ -1540,7 +1564,7 @@ EXPORT_SYMBOL(folio_end_private_2);
  * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio.
  * @folio: The folio to wait on.
  *
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio.
+ * Wait for PG_private_2 to be cleared on a folio.
  */
 void folio_wait_private_2(struct folio *folio)
 {
@@ -1553,8 +1577,8 @@ EXPORT_SYMBOL(folio_wait_private_2);
  * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio.
  * @folio: The folio to wait on.
  *
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a
- * fatal signal is received by the calling task.
+ * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is
+ * received by the calling task.
  *
  * Return:
  * - 0 if successful.
@@ -1786,7 +1810,7 @@ EXPORT_SYMBOL(page_cache_prev_miss);
  * C. Return the page to the page allocator
  *
  * This means that any page may have its reference count temporarily
- * increased by a speculative page cache (or fast GUP) lookup as it can
+ * increased by a speculative page cache (or GUP-fast) lookup as it can
  * be allocated by another user before the RCU grace period expires.
  * Because the refcount temporarily acquired here may end up being the
  * last refcount on the page, any page allocation must be freeable by
@@ -3482,7 +3506,7 @@ skip:
 static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 			struct folio *folio, unsigned long start,
 			unsigned long addr, unsigned int nr_pages,
-			unsigned int *mmap_miss)
+			unsigned long *rss, unsigned int *mmap_miss)
 {
 	vm_fault_t ret = 0;
 	struct page *page = folio_page(folio, start);
@@ -3493,7 +3517,15 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 		if (PageHWPoison(page + count))
 			goto skip;
 
-		(*mmap_miss)++;
+		/*
+		 * If there are too many folios that are recently evicted
+		 * in a file, they will probably continue to be evicted.
+		 * In such situation, read-ahead is only a waste of IO.
+		 * Don't decrease mmap_miss in this scenario to make sure
+		 * we can stop read-ahead.
+		 */
+		if (!folio_test_workingset(folio))
+			(*mmap_miss)++;
 
 		/*
 		 * NOTE: If there're PTE markers, we'll leave them to be
@@ -3508,6 +3540,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 skip:
 		if (count) {
 			set_pte_range(vmf, folio, page, count, addr);
+			*rss += count;
 			folio_ref_add(folio, count);
 			if (in_range(vmf->address, addr, count * PAGE_SIZE))
 				ret = VM_FAULT_NOPAGE;
@@ -3522,6 +3555,7 @@ skip:
 
 	if (count) {
 		set_pte_range(vmf, folio, page, count, addr);
+		*rss += count;
 		folio_ref_add(folio, count);
 		if (in_range(vmf->address, addr, count * PAGE_SIZE))
 			ret = VM_FAULT_NOPAGE;
@@ -3534,7 +3568,7 @@ skip:
 
 static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf,
 		struct folio *folio, unsigned long addr,
-		unsigned int *mmap_miss)
+		unsigned long *rss, unsigned int *mmap_miss)
 {
 	vm_fault_t ret = 0;
 	struct page *page = &folio->page;
@@ -3542,7 +3576,9 @@ static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf,
 	if (PageHWPoison(page))
 		return ret;
 
-	(*mmap_miss)++;
+	/* See comment of filemap_map_folio_range() */
+	if (!folio_test_workingset(folio))
+		(*mmap_miss)++;
 
 	/*
 	 * NOTE: If there're PTE markers, we'll leave them to be
@@ -3556,6 +3592,7 @@ static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf,
 		ret = VM_FAULT_NOPAGE;
 
 	set_pte_range(vmf, folio, page, 1, addr);
+	(*rss)++;
 	folio_ref_inc(folio);
 
 	return ret;
@@ -3572,7 +3609,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct folio *folio;
 	vm_fault_t ret = 0;
-	unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved;
+	unsigned long rss = 0;
+	unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type;
 
 	rcu_read_lock();
 	folio = next_uptodate_folio(&xas, mapping, end_pgoff);
@@ -3591,6 +3629,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		folio_put(folio);
 		goto out;
 	}
+
+	folio_type = mm_counter_file(folio);
 	do {
 		unsigned long end;
 
@@ -3602,15 +3642,16 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 
 		if (!folio_test_large(folio))
 			ret |= filemap_map_order0_folio(vmf,
-					folio, addr, &mmap_miss);
+					folio, addr, &rss, &mmap_miss);
 		else
 			ret |= filemap_map_folio_range(vmf, folio,
 					xas.xa_index - folio->index, addr,
-					nr_pages, &mmap_miss);
+					nr_pages, &rss, &mmap_miss);
 
 		folio_unlock(folio);
 		folio_put(folio);
 	} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
+	add_mm_counter(vma->vm_mm, folio_type, rss);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
 	rcu_read_unlock();
@@ -4135,6 +4176,60 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
 }
 EXPORT_SYMBOL(filemap_release_folio);
 
+/**
+ * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache
+ * @inode: The inode to flush
+ * @flush: Set to write back rather than simply invalidate.
+ * @start: First byte to in range.
+ * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start
+ *       onwards.
+ *
+ * Invalidate all the folios on an inode that contribute to the specified
+ * range, possibly writing them back first.  Whilst the operation is
+ * undertaken, the invalidate lock is held to prevent new folios from being
+ * installed.
+ */
+int filemap_invalidate_inode(struct inode *inode, bool flush,
+			     loff_t start, loff_t end)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t first = start >> PAGE_SHIFT;
+	pgoff_t last = end >> PAGE_SHIFT;
+	pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1;
+
+	if (!mapping || !mapping->nrpages || end < start)
+		goto out;
+
+	/* Prevent new folios from being added to the inode. */
+	filemap_invalidate_lock(mapping);
+
+	if (!mapping->nrpages)
+		goto unlock;
+
+	unmap_mapping_pages(mapping, first, nr, false);
+
+	/* Write back the data if we're asked to. */
+	if (flush) {
+		struct writeback_control wbc = {
+			.sync_mode	= WB_SYNC_ALL,
+			.nr_to_write	= LONG_MAX,
+			.range_start	= start,
+			.range_end	= end,
+		};
+
+		filemap_fdatawrite_wbc(mapping, &wbc);
+	}
+
+	/* Wait for writeback to complete on all folios and discard. */
+	truncate_inode_pages_range(mapping, start, end);
+
+unlock:
+	filemap_invalidate_unlock(mapping);
+out:
+	return filemap_check_errors(mapping);
+}
+EXPORT_SYMBOL_GPL(filemap_invalidate_inode);
+
 #ifdef CONFIG_CACHESTAT_SYSCALL
 /**
  * filemap_cachestat() - compute the page cache statistics of a mapping