filemap: Allow __filemap_get_folio to allocate large folios

Allow callers of __filemap_get_folio() to specify a preferred folio
order in the FGP flags.  This is only honoured in the FGP_CREATE path;
if there is already a folio in the page cache that covers the index,
we will return it, no matter what its order is.  No create-around is
attempted; we will only create folios which start at the specified index.
Unmodified callers will continue to allocate order 0 folios.

Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Reviewed-by: Darrick J. Wong <[email protected]>

Author: Matthew Wilcox (Oracle)

include/linux/pagemap.h

@@ -470,6 +470,19 @@ static inline void *detach_page_private(struct page *page)
 	return folio_detach_private(page_folio(page));
 }
 
+/*
+ * 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
+
 #ifdef CONFIG_NUMA
 struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
 #else
@@ -535,9 +548,30 @@ typedef unsigned int __bitwise fgf_t;
 #define FGP_NOWAIT		((__force fgf_t)0x00000020)
 #define FGP_FOR_MMAP		((__force fgf_t)0x00000040)
 #define FGP_STABLE		((__force fgf_t)0x00000080)
+#define FGF_GET_ORDER(fgf)	(((__force unsigned)fgf) >> 26)	/* top 6 bits */
 
 #define FGP_WRITEBEGIN		(FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
 
+/**
+ * fgf_set_order - Encode a length in the fgf_t flags.
+ * @size: The suggested size of the folio to create.
+ *
+ * The caller of __filemap_get_folio() can use this to suggest a preferred
+ * size for the folio that is created.  If there is already a folio at
+ * the index, it will be returned, no matter what its size.  If a folio
+ * is freshly created, it may be of a different size than requested
+ * due to alignment constraints, memory pressure, or the presence of
+ * other folios at nearby indices.
+ */
+static inline fgf_t fgf_set_order(size_t size)
+{
+	unsigned int shift = ilog2(size);
+
+	if (shift <= PAGE_SHIFT)
+		return 0;
+	return (__force fgf_t)((shift - PAGE_SHIFT) << 26);
+}
+
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
 struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);

mm/filemap.c

@@ -1905,7 +1905,9 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		folio_wait_stable(folio);
 no_page:
 	if (!folio && (fgp_flags & FGP_CREAT)) {
+		unsigned order = FGF_GET_ORDER(fgp_flags);
 		int err;
+
 		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp |= __GFP_WRITE;
 		if (fgp_flags & FGP_NOFS)
@@ -1914,26 +1916,44 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			gfp &= ~GFP_KERNEL;
 			gfp |= GFP_NOWAIT | __GFP_NOWARN;
 		}
-
-		folio = filemap_alloc_folio(gfp, 0);
-		if (!folio)
-			return ERR_PTR(-ENOMEM);
-
 		if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
 			fgp_flags |= FGP_LOCK;
 
-		/* Init accessed so avoid atomic mark_page_accessed later */
-		if (fgp_flags & FGP_ACCESSED)
-			__folio_set_referenced(folio);
+		if (!mapping_large_folio_support(mapping))
+			order = 0;
+		if (order > MAX_PAGECACHE_ORDER)
+			order = MAX_PAGECACHE_ORDER;
+		/* If we're not aligned, allocate a smaller folio */
+		if (index & ((1UL << order) - 1))
+			order = __ffs(index);
 
-		err = filemap_add_folio(mapping, folio, index, gfp);
-		if (unlikely(err)) {
+		do {
+			gfp_t alloc_gfp = gfp;
+
+			err = -ENOMEM;
+			if (order == 1)
+				order = 0;
+			if (order > 0)
+				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
+			folio = filemap_alloc_folio(alloc_gfp, order);
+			if (!folio)
+				continue;
+
+			/* Init accessed so avoid atomic mark_page_accessed later */
+			if (fgp_flags & FGP_ACCESSED)
+				__folio_set_referenced(folio);
+
+			err = filemap_add_folio(mapping, folio, index, gfp);
+			if (!err)
+				break;
 			folio_put(folio);
 			folio = NULL;
-			if (err == -EEXIST)
-				goto repeat;
-		}
+		} while (order-- > 0);
 
+		if (err == -EEXIST)
+			goto repeat;
+		if (err)
+			return ERR_PTR(err);
 		/*
 		 * filemap_add_folio locks the page, and for mmap
 		 * we expect an unlocked page.

mm/readahead.c

@@ -461,19 +461,6 @@ static int try_context_readahead(struct address_space *mapping,
 	return 1;
 }
 
-/*
- * 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)
 {