1 files changed, 228 insertions, 28 deletions

diff --git a/mm/readahead.c b/mm/readahead.c
index 6ae5693de28c..d3a47546d17d 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,6 +8,111 @@
  *		Initial version.
  */
 
+/**
+ * DOC: Readahead Overview
+ *
+ * Readahead is used to read content into the page cache before it is
+ * explicitly requested by the application.  Readahead only ever
+ * attempts to read pages that are not yet in the page cache.  If a
+ * page is present but not up-to-date, readahead will not try to read
+ * it. In that case a simple ->readpage() will be requested.
+ *
+ * Readahead is triggered when an application read request (whether a
+ * systemcall or a page fault) finds that the requested page is not in
+ * the page cache, or that it is in the page cache and has the
+ * %PG_readahead flag set.  This flag indicates that the page was loaded
+ * as part of a previous read-ahead request and now that it has been
+ * accessed, it is time for the next read-ahead.
+ *
+ * Each readahead request is partly synchronous read, and partly async
+ * read-ahead.  This is reflected in the struct file_ra_state which
+ * contains ->size being to total number of pages, and ->async_size
+ * which is the number of pages in the async section.  The first page in
+ * this async section will have %PG_readahead set as a trigger for a
+ * subsequent read ahead.  Once a series of sequential reads has been
+ * established, there should be no need for a synchronous component and
+ * all read ahead request will be fully asynchronous.
+ *
+ * When either of the triggers causes a readahead, three numbers need to
+ * be determined: the start of the region, the size of the region, and
+ * the size of the async tail.
+ *
+ * The start of the region is simply the first page address at or after
+ * the accessed address, which is not currently populated in the page
+ * cache.  This is found with a simple search in the page cache.
+ *
+ * The size of the async tail is determined by subtracting the size that
+ * was explicitly requested from the determined request size, unless
+ * this would be less than zero - then zero is used.  NOTE THIS
+ * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED
+ * PAGE.
+ *
+ * The size of the region is normally determined from the size of the
+ * previous readahead which loaded the preceding pages.  This may be
+ * discovered from the struct file_ra_state for simple sequential reads,
+ * or from examining the state of the page cache when multiple
+ * sequential reads are interleaved.  Specifically: where the readahead
+ * was triggered by the %PG_readahead flag, the size of the previous
+ * readahead is assumed to be the number of pages from the triggering
+ * page to the start of the new readahead.  In these cases, the size of
+ * the previous readahead is scaled, often doubled, for the new
+ * readahead, though see get_next_ra_size() for details.
+ *
+ * If the size of the previous read cannot be determined, the number of
+ * preceding pages in the page cache is used to estimate the size of
+ * a previous read.  This estimate could easily be misled by random
+ * reads being coincidentally adjacent, so it is ignored unless it is
+ * larger than the current request, and it is not scaled up, unless it
+ * is at the start of file.
+ *
+ * In general read ahead is accelerated at the start of the file, as
+ * reads from there are often sequential.  There are other minor
+ * adjustments to the read ahead size in various special cases and these
+ * are best discovered by reading the code.
+ *
+ * The above calculation determines the readahead, to which any requested
+ * read size may be added.
+ *
+ * Readahead requests are sent to the filesystem using the ->readahead()
+ * address space operation, for which mpage_readahead() is a canonical
+ * implementation.  ->readahead() should normally initiate reads on all
+ * pages, but may fail to read any or all pages without causing an IO
+ * error.  The page cache reading code will issue a ->readpage() request
+ * for any page which ->readahead() does not provided, and only an error
+ * from this will be final.
+ *
+ * ->readahead() will generally call readahead_page() repeatedly to get
+ * each page from those prepared for read ahead.  It may fail to read a
+ * page by:
+ *
+ * * not calling readahead_page() sufficiently many times, effectively
+ *   ignoring some pages, as might be appropriate if the path to
+ *   storage is congested.
+ *
+ * * failing to actually submit a read request for a given page,
+ *   possibly due to insufficient resources, or
+ *
+ * * getting an error during subsequent processing of a request.
+ *
+ * In the last two cases, the page should be unlocked to indicate that
+ * the read attempt has failed.  In the first case the page will be
+ * unlocked by the caller.
+ *
+ * Those pages not in the final ``async_size`` of the request should be
+ * considered to be important and ->readahead() should not fail them due
+ * to congestion or temporary resource unavailability, but should wait
+ * for necessary resources (e.g.  memory or indexing information) to
+ * become available.  Pages in the final ``async_size`` may be
+ * considered less urgent and failure to read them is more acceptable.
+ * In this case it is best to use delete_from_page_cache() to remove the
+ * pages from the page cache as is automatically done for pages that
+ * were not fetched with readahead_page().  This will allow a
+ * subsequent synchronous read ahead request to try them again.  If they
+ * are left in the page cache, then they will be read individually using
+ * ->readpage().
+ *
+ */
+
 #include <linux/kernel.h>
 #include <linux/dax.h>
 #include <linux/gfp.h>
@@ -51,7 +156,7 @@ static void read_cache_pages_invalidate_page(struct address_space *mapping,
 		if (!trylock_page(page))
 			BUG();
 		page->mapping = mapping;
-		do_invalidatepage(page, 0, PAGE_SIZE);
+		folio_invalidate(page_folio(page), 0, PAGE_SIZE);
 		page->mapping = NULL;
 		unlock_page(page);
 	}
@@ -127,8 +232,17 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages,
 
 	if (aops->readahead) {
 		aops->readahead(rac);
-		/* Clean up the remaining pages */
+		/*
+		 * Clean up the remaining pages.  The sizes in ->ra
+		 * maybe be used to size next read-ahead, so make sure
+		 * they accurately reflect what happened.
+		 */
 		while ((page = readahead_page(rac))) {
+			rac->ra->size -= 1;
+			if (rac->ra->async_size > 0) {
+				rac->ra->async_size -= 1;
+				delete_from_page_cache(page);
+			}
 			unlock_page(page);
 			put_page(page);
 		}
@@ -148,7 +262,7 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages,
 
 	blk_finish_plug(&plug);
 
-	BUG_ON(!list_empty(pages));
+	BUG_ON(pages && !list_empty(pages));
 	BUG_ON(readahead_count(rac));
 
 out:
@@ -196,9 +310,9 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	 * Preallocate as many pages as we will need.
 	 */
 	for (i = 0; i < nr_to_read; i++) {
-		struct page *page = xa_load(&mapping->i_pages, index + i);
+		struct folio *folio = xa_load(&mapping->i_pages, index + i);
 
-		if (page && !xa_is_value(page)) {
+		if (folio && !xa_is_value(folio)) {
 			/*
 			 * Page already present?  Kick off the current batch
 			 * of contiguous pages before continuing with the
@@ -212,21 +326,21 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			continue;
 		}
 
-		page = __page_cache_alloc(gfp_mask);
-		if (!page)
+		folio = filemap_alloc_folio(gfp_mask, 0);
+		if (!folio)
 			break;
 		if (mapping->a_ops->readpages) {
-			page->index = index + i;
-			list_add(&page->lru, &page_pool);
-		} else if (add_to_page_cache_lru(page, mapping, index + i,
+			folio->index = index + i;
+			list_add(&folio->lru, &page_pool);
+		} else if (filemap_add_folio(mapping, folio, index + i,
 					gfp_mask) < 0) {
-			put_page(page);
+			folio_put(folio);
 			read_pages(ractl, &page_pool, true);
 			i = ractl->_index + ractl->_nr_pages - index - 1;
 			continue;
 		}
 		if (i == nr_to_read - lookahead_size)
-			SetPageReadahead(page);
+			folio_set_readahead(folio);
 		ractl->_nr_pages++;
 	}
 
@@ -247,7 +361,7 @@ EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
  * behaviour which would occur if page allocations are causing VM writeback.
  * We really don't want to intermingle reads and writes like that.
  */
-void do_page_cache_ra(struct readahead_control *ractl,
+static void do_page_cache_ra(struct readahead_control *ractl,
 		unsigned long nr_to_read, unsigned long lookahead_size)
 {
 	struct inode *inode = ractl->mapping->host;
@@ -432,10 +546,102 @@ static int try_context_readahead(struct address_space *mapping,
 }
 
 /*
+ * There are some parts of the kernel which assume that PMD entries
+ * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
+ * limit the maximum allocation order to PMD size.  I'm not aware of any
+ * assumptions about maximum order if THP are disabled, but 8 seems like
+ * a good order (that's 1MB if you're using 4kB pages)
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
+#else
+#define MAX_PAGECACHE_ORDER	8
+#endif
+
+static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
+		pgoff_t mark, unsigned int order, gfp_t gfp)
+{
+	int err;
+	struct folio *folio = filemap_alloc_folio(gfp, order);
+
+	if (!folio)
+		return -ENOMEM;
+	if (mark - index < (1UL << order))
+		folio_set_readahead(folio);
+	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
+	if (err)
+		folio_put(folio);
+	else
+		ractl->_nr_pages += 1UL << order;
+	return err;
+}
+
+void page_cache_ra_order(struct readahead_control *ractl,
+		struct file_ra_state *ra, unsigned int new_order)
+{
+	struct address_space *mapping = ractl->mapping;
+	pgoff_t index = readahead_index(ractl);
+	pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
+	pgoff_t mark = index + ra->size - ra->async_size;
+	int err = 0;
+	gfp_t gfp = readahead_gfp_mask(mapping);
+
+	if (!mapping_large_folio_support(mapping) || ra->size < 4)
+		goto fallback;
+
+	limit = min(limit, index + ra->size - 1);
+
+	if (new_order < MAX_PAGECACHE_ORDER) {
+		new_order += 2;
+		if (new_order > MAX_PAGECACHE_ORDER)
+			new_order = MAX_PAGECACHE_ORDER;
+		while ((1 << new_order) > ra->size)
+			new_order--;
+	}
+
+	while (index <= limit) {
+		unsigned int order = new_order;
+
+		/* Align with smaller pages if needed */
+		if (index & ((1UL << order) - 1)) {
+			order = __ffs(index);
+			if (order == 1)
+				order = 0;
+		}
+		/* Don't allocate pages past EOF */
+		while (index + (1UL << order) - 1 > limit) {
+			if (--order == 1)
+				order = 0;
+		}
+		err = ra_alloc_folio(ractl, index, mark, order, gfp);
+		if (err)
+			break;
+		index += 1UL << order;
+	}
+
+	if (index > limit) {
+		ra->size += index - limit - 1;
+		ra->async_size += index - limit - 1;
+	}
+
+	read_pages(ractl, NULL, false);
+
+	/*
+	 * If there were already pages in the page cache, then we may have
+	 * left some gaps.  Let the regular readahead code take care of this
+	 * situation.
+	 */
+	if (!err)
+		return;
+fallback:
+	do_page_cache_ra(ractl, ra->size, ra->async_size);
+}
+
+/*
  * A minimal readahead algorithm for trivial sequential/random reads.
  */
 static void ondemand_readahead(struct readahead_control *ractl,
-		bool hit_readahead_marker, unsigned long req_size)
+		struct folio *folio, unsigned long req_size)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host);
 	struct file_ra_state *ra = ractl->ra;
@@ -470,12 +676,12 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	}
 
 	/*
-	 * Hit a marked page without valid readahead state.
+	 * Hit a marked folio without valid readahead state.
 	 * E.g. interleaved reads.
 	 * Query the pagecache for async_size, which normally equals to
 	 * readahead size. Ramp it up and use it as the new readahead size.
 	 */
-	if (hit_readahead_marker) {
+	if (folio) {
 		pgoff_t start;
 
 		rcu_read_lock();
@@ -548,7 +754,7 @@ readit:
 	}
 
 	ractl->_index = ra->start;
-	do_page_cache_ra(ractl, ra->size, ra->async_size);
+	page_cache_ra_order(ractl, ra, folio ? folio_order(folio) : 0);
 }
 
 void page_cache_sync_ra(struct readahead_control *ractl,
@@ -576,12 +782,12 @@ void page_cache_sync_ra(struct readahead_control *ractl,
 	}
 
 	/* do read-ahead */
-	ondemand_readahead(ractl, false, req_count);
+	ondemand_readahead(ractl, NULL, req_count);
 }
 EXPORT_SYMBOL_GPL(page_cache_sync_ra);
 
 void page_cache_async_ra(struct readahead_control *ractl,
-		struct page *page, unsigned long req_count)
+		struct folio *folio, unsigned long req_count)
 {
 	/* no read-ahead */
 	if (!ractl->ra->ra_pages)
@@ -590,22 +796,16 @@ void page_cache_async_ra(struct readahead_control *ractl,
 	/*
 	 * Same bit is used for PG_readahead and PG_reclaim.
 	 */
-	if (PageWriteback(page))
+	if (folio_test_writeback(folio))
 		return;
 
-	ClearPageReadahead(page);
-
-	/*
-	 * Defer asynchronous read-ahead on IO congestion.
-	 */
-	if (inode_read_congested(ractl->mapping->host))
-		return;
+	folio_clear_readahead(folio);
 
 	if (blk_cgroup_congested())
 		return;
 
 	/* do read-ahead */
-	ondemand_readahead(ractl, true, req_count);
+	ondemand_readahead(ractl, folio, req_count);
 }
 EXPORT_SYMBOL_GPL(page_cache_async_ra);