Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   "Matthew Wilcox (Oracle)" <willy@infradead.org>
To:     linux-kernel@vger.kernel.org
Cc:     "Matthew Wilcox (Oracle)" <willy@infradead.org>,
        linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
        Jeff Layton <jlayton@kernel.org>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        William Kucharski <william.kucharski@oracle.com>,
        Christoph Hellwig <hch@lst.de>,
        David Howells <dhowells@redhat.com>
Subject: [PATCH v13 002/137] mm: Introduce struct folio
Date:   Mon, 12 Jul 2021 04:04:46 +0100
Message-Id: <20210712030701.4000097-3-willy@infradead.org>
In-Reply-To: <20210712030701.4000097-1-willy@infradead.org>
References: <20210712030701.4000097-1-willy@infradead.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

A struct folio is a new abstraction to replace the venerable struct page.
A function which takes a struct folio argument declares that it will
operate on the entire (possibly compound) page, not just PAGE_SIZE bytes.
In return, the caller guarantees that the pointer it is passing does
not point to a tail page.  No change to generated code.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Howells <dhowells@redhat.com>
---
 Documentation/core-api/mm-api.rst |  1 +
 include/linux/mm.h                | 74 +++++++++++++++++++++++++++++++
 include/linux/mm_types.h          | 60 +++++++++++++++++++++++++
 include/linux/page-flags.h        | 28 ++++++++++++
 4 files changed, 163 insertions(+)

diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index a42f9baddfbf..2a94e6164f80 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -95,6 +95,7 @@ More Memory Management Functions
 .. kernel-doc:: mm/mempolicy.c
 .. kernel-doc:: include/linux/mm_types.h
    :internal:
+.. kernel-doc:: include/linux/page-flags.h
 .. kernel-doc:: include/linux/mm.h
    :internal:
 .. kernel-doc:: include/linux/mmzone.h
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 02851931e958..054812351960 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -948,6 +948,20 @@ static inline unsigned int compound_order(struct page *page)
 	return page[1].compound_order;
 }
 
+/**
+ * folio_order - The allocation order of a folio.
+ * @folio: The folio.
+ *
+ * A folio is composed of 2^order pages.  See get_order() for the definition
+ * of order.
+ *
+ * Return: The order of the folio.
+ */
+static inline unsigned int folio_order(struct folio *folio)
+{
+	return compound_order(&folio->page);
+}
+
 static inline bool hpage_pincount_available(struct page *page)
 {
 	/*
@@ -1593,6 +1607,65 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 #endif
 }
 
+/**
+ * folio_nr_pages - The number of pages in the folio.
+ * @folio: The folio.
+ *
+ * Return: A number which is a power of two.
+ */
+static inline unsigned long folio_nr_pages(struct folio *folio)
+{
+	return compound_nr(&folio->page);
+}
+
+/**
+ * folio_next - Move to the next physical folio.
+ * @folio: The folio we're currently operating on.
+ *
+ * If you have physically contiguous memory which may span more than
+ * one folio (eg a &struct bio_vec), use this function to move from one
+ * folio to the next.  Do not use it if the memory is only virtually
+ * contiguous as the folios are almost certainly not adjacent to each
+ * other.  This is the folio equivalent to writing ``page++``.
+ *
+ * Context: We assume that the folios are refcounted and/or locked at a
+ * higher level and do not adjust the reference counts.
+ * Return: The next struct folio.
+ */
+static inline struct folio *folio_next(struct folio *folio)
+{
+	return (struct folio *)folio_page(folio, folio_nr_pages(folio));
+}
+
+/**
+ * folio_shift - The number of bits covered by this folio.
+ * @folio: The folio.
+ *
+ * A folio contains a number of bytes which is a power-of-two in size.
+ * This function tells you which power-of-two the folio is.
+ *
+ * Context: The caller should have a reference on the folio to prevent
+ * it from being split.  It is not necessary for the folio to be locked.
+ * Return: The base-2 logarithm of the size of this folio.
+ */
+static inline unsigned int folio_shift(struct folio *folio)
+{
+	return PAGE_SHIFT + folio_order(folio);
+}
+
+/**
+ * folio_size - The number of bytes in a folio.
+ * @folio: The folio.
+ *
+ * Context: The caller should have a reference on the folio to prevent
+ * it from being split.  It is not necessary for the folio to be locked.
+ * Return: The number of bytes in this folio.
+ */
+static inline size_t folio_size(struct folio *folio)
+{
+	return PAGE_SIZE << folio_order(folio);
+}
+
 /*
  * Some inline functions in vmstat.h depend on page_zone()
  */
@@ -1698,6 +1771,7 @@ extern void pagefault_out_of_memory(void);
 
 #define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)
 #define offset_in_thp(page, p)	((unsigned long)(p) & (thp_size(page) - 1))
+#define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1))
 
 /*
  * Flags passed to show_mem() and show_free_areas() to suppress output in
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 52bbd2b7cb46..7a11b25cf50f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -231,6 +231,66 @@ struct page {
 #endif
 } _struct_page_alignment;
 
+/**
+ * struct folio - Represents a contiguous set of bytes.
+ * @flags: Identical to the page flags.
+ * @lru: Least Recently Used list; tracks how recently this folio was used.
+ * @mapping: The file this page belongs to, or refers to the anon_vma for
+ *    anonymous pages.
+ * @index: Offset within the file, in units of pages.  For anonymous pages,
+ *    this is the index from the beginning of the mmap.
+ * @private: Filesystem per-folio data (see folio_attach_private()).
+ *    Used for swp_entry_t if folio_swapcache().
+ * @_mapcount: Do not access this member directly.  Use folio_mapcount() to
+ *    find out how many times this folio is mapped by userspace.
+ * @_refcount: Do not access this member directly.  Use folio_ref_count()
+ *    to find how many references there are to this folio.
+ * @memcg_data: Memory Control Group data.
+ *
+ * A folio is a physically, virtually and logically contiguous set
+ * of bytes.  It is a power-of-two in size, and it is aligned to that
+ * same power-of-two.  It is at least as large as %PAGE_SIZE.  If it is
+ * in the page cache, it is at a file offset which is a multiple of that
+ * power-of-two.  It may be mapped into userspace at an address which is
+ * at an arbitrary page offset, but its kernel virtual address is aligned
+ * to its size.
+ */
+struct folio {
+	/* private: don't document the anon union */
+	union {
+		struct {
+	/* public: */
+			unsigned long flags;
+			struct list_head lru;
+			struct address_space *mapping;
+			pgoff_t index;
+			void *private;
+			atomic_t _mapcount;
+			atomic_t _refcount;
+#ifdef CONFIG_MEMCG
+			unsigned long memcg_data;
+#endif
+	/* private: the union with struct page is transitional */
+		};
+		struct page page;
+	};
+};
+
+static_assert(sizeof(struct page) == sizeof(struct folio));
+#define FOLIO_MATCH(pg, fl)						\
+	static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl))
+FOLIO_MATCH(flags, flags);
+FOLIO_MATCH(lru, lru);
+FOLIO_MATCH(compound_head, lru);
+FOLIO_MATCH(index, index);
+FOLIO_MATCH(private, private);
+FOLIO_MATCH(_mapcount, _mapcount);
+FOLIO_MATCH(_refcount, _refcount);
+#ifdef CONFIG_MEMCG
+FOLIO_MATCH(memcg_data, memcg_data);
+#endif
+#undef FOLIO_MATCH
+
 static inline atomic_t *compound_mapcount_ptr(struct page *page)
 {
 	return &page[1].compound_mapcount;
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5922031ffab6..70ede8345538 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -191,6 +191,34 @@ static inline unsigned long _compound_head(const struct page *page)
 
 #define compound_head(page)	((typeof(page))_compound_head(page))
 
+/**
+ * page_folio - Converts from page to folio.
+ * @p: The page.
+ *
+ * Every page is part of a folio.  This function cannot be called on a
+ * NULL pointer.
+ *
+ * Context: No reference, nor lock is required on @page.  If the caller
+ * does not hold a reference, this call may race with a folio split, so
+ * it should re-check the folio still contains this page after gaining
+ * a reference on the folio.
+ * Return: The folio which contains this page.
+ */
+#define page_folio(p)		(_Generic((p),				\
+	const struct page *:	(const struct folio *)_compound_head(p), \
+	struct page *:		(struct folio *)_compound_head(p)))
+
+/**
+ * folio_page - Return a page from a folio.
+ * @folio: The folio.
+ * @n: The page number to return.
+ *
+ * @n is relative to the start of the folio.  This function does not
+ * check that the page number lies within @folio; the caller is presumed
+ * to have a reference to the page.
+ */
+#define folio_page(folio, n)	nth_page(&(folio)->page, n)
+
 static __always_inline int PageTail(struct page *page)
 {
 	return READ_ONCE(page->compound_head) & 1;
-- 
2.30.2