Merge tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache

Pull memory folios from Matthew Wilcox:
 "Add memory folios, a new type to represent either order-0 pages or the
  head page of a compound page. This should be enough infrastructure to
  support filesystems converting from pages to folios.

  The point of all this churn is to allow filesystems and the page cache
  to manage memory in larger chunks than PAGE_SIZE. The original plan
  was to use compound pages like THP does, but I ran into problems with
  some functions expecting only a head page while others expect the
  precise page containing a particular byte.

  The folio type allows a function to declare that it's expecting only a
  head page. Almost incidentally, this allows us to remove various calls
  to VM_BUG_ON(PageTail(page)) and compound_head().

  This converts just parts of the core MM and the page cache. For 5.17,
  we intend to convert various filesystems (XFS and AFS are ready; other
  filesystems may make it) and also convert more of the MM and page
  cache to folios. For 5.18, multi-page folios should be ready.

  The multi-page folios offer some improvement to some workloads. The
  80% win is real, but appears to be an artificial benchmark (postgres
  startup, which isn't a serious workload). Real workloads (eg building
  the kernel, running postgres in a steady state, etc) seem to benefit
  between 0-10%. I haven't heard of any performance losses as a result
  of this series. Nobody has done any serious performance tuning; I
  imagine that tweaking the readahead algorithm could provide some more
  interesting wins. There are also other places where we could choose to
  create large folios and currently do not, such as writes that are
  larger than PAGE_SIZE.

  I'd like to thank all my reviewers who've offered review/ack tags:
  Christoph Hellwig, David Howells, Jan Kara, Jeff Layton, Johannes
  Weiner, Kirill A. Shutemov, Michal Hocko, Mike Rapoport, Vlastimil
  Babka, William Kucharski, Yu Zhao and Zi Yan.

  I'd also like to thank those who gave feedback I incorporated but
  haven't offered up review tags for this part of the series: Nick
  Piggin, Mel Gorman, Ming Lei, Darrick Wong, Ted Ts'o, John Hubbard,
  Hugh Dickins, and probably a few others who I forget"

* tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache: (90 commits)
  mm/writeback: Add folio_write_one
  mm/filemap: Add FGP_STABLE
  mm/filemap: Add filemap_get_folio
  mm/filemap: Convert mapping_get_entry to return a folio
  mm/filemap: Add filemap_add_folio()
  mm/filemap: Add filemap_alloc_folio
  mm/page_alloc: Add folio allocation functions
  mm/lru: Add folio_add_lru()
  mm/lru: Convert __pagevec_lru_add_fn to take a folio
  mm: Add folio_evictable()
  mm/workingset: Convert workingset_refault() to take a folio
  mm/filemap: Add readahead_folio()
  mm/filemap: Add folio_mkwrite_check_truncate()
  mm/filemap: Add i_blocks_per_folio()
  mm/writeback: Add folio_redirty_for_writepage()
  mm/writeback: Add folio_account_redirty()
  mm/writeback: Add folio_clear_dirty_for_io()
  mm/writeback: Add folio_cancel_dirty()
  mm/writeback: Add folio_account_cleaned()
  mm/writeback: Add filemap_dirty_folio()
  ...

1 files changed, 155 insertions, 3 deletions

diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 7ad46f45df39..2e677e6ad09f 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -67,9 +67,31 @@ static inline int page_ref_count(const struct page *page)
 	return atomic_read(&page->_refcount);
 }
 
+/**
+ * folio_ref_count - The reference count on this folio.
+ * @folio: The folio.
+ *
+ * The refcount is usually incremented by calls to folio_get() and
+ * decremented by calls to folio_put().  Some typical users of the
+ * folio refcount:
+ *
+ * - Each reference from a page table
+ * - The page cache
+ * - Filesystem private data
+ * - The LRU list
+ * - Pipes
+ * - Direct IO which references this page in the process address space
+ *
+ * Return: The number of references to this folio.
+ */
+static inline int folio_ref_count(const struct folio *folio)
+{
+	return page_ref_count(&folio->page);
+}
+
 static inline int page_count(const struct page *page)
 {
-	return atomic_read(&compound_head(page)->_refcount);
+	return folio_ref_count(page_folio(page));
 }
 
 static inline void set_page_count(struct page *page, int v)
@@ -79,6 +101,11 @@ static inline void set_page_count(struct page *page, int v)
 		__page_ref_set(page, v);
 }
 
+static inline void folio_set_count(struct folio *folio, int v)
+{
+	set_page_count(&folio->page, v);
+}
+
 /*
  * Setup the page count before being freed into the page allocator for
  * the first time (boot or memory hotplug)
@@ -95,6 +122,11 @@ static inline void page_ref_add(struct page *page, int nr)
 		__page_ref_mod(page, nr);
 }
 
+static inline void folio_ref_add(struct folio *folio, int nr)
+{
+	page_ref_add(&folio->page, nr);
+}
+
 static inline void page_ref_sub(struct page *page, int nr)
 {
 	atomic_sub(nr, &page->_refcount);
@@ -102,6 +134,11 @@ static inline void page_ref_sub(struct page *page, int nr)
 		__page_ref_mod(page, -nr);
 }
 
+static inline void folio_ref_sub(struct folio *folio, int nr)
+{
+	page_ref_sub(&folio->page, nr);
+}
+
 static inline int page_ref_sub_return(struct page *page, int nr)
 {
 	int ret = atomic_sub_return(nr, &page->_refcount);
@@ -111,6 +148,11 @@ static inline int page_ref_sub_return(struct page *page, int nr)
 	return ret;
 }
 
+static inline int folio_ref_sub_return(struct folio *folio, int nr)
+{
+	return page_ref_sub_return(&folio->page, nr);
+}
+
 static inline void page_ref_inc(struct page *page)
 {
 	atomic_inc(&page->_refcount);
@@ -118,6 +160,11 @@ static inline void page_ref_inc(struct page *page)
 		__page_ref_mod(page, 1);
 }
 
+static inline void folio_ref_inc(struct folio *folio)
+{
+	page_ref_inc(&folio->page);
+}
+
 static inline void page_ref_dec(struct page *page)
 {
 	atomic_dec(&page->_refcount);
@@ -125,6 +172,11 @@ static inline void page_ref_dec(struct page *page)
 		__page_ref_mod(page, -1);
 }
 
+static inline void folio_ref_dec(struct folio *folio)
+{
+	page_ref_dec(&folio->page);
+}
+
 static inline int page_ref_sub_and_test(struct page *page, int nr)
 {
 	int ret = atomic_sub_and_test(nr, &page->_refcount);
@@ -134,6 +186,11 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
 	return ret;
 }
 
+static inline int folio_ref_sub_and_test(struct folio *folio, int nr)
+{
+	return page_ref_sub_and_test(&folio->page, nr);
+}
+
 static inline int page_ref_inc_return(struct page *page)
 {
 	int ret = atomic_inc_return(&page->_refcount);
@@ -143,6 +200,11 @@ static inline int page_ref_inc_return(struct page *page)
 	return ret;
 }
 
+static inline int folio_ref_inc_return(struct folio *folio)
+{
+	return page_ref_inc_return(&folio->page);
+}
+
 static inline int page_ref_dec_and_test(struct page *page)
 {
 	int ret = atomic_dec_and_test(&page->_refcount);
@@ -152,6 +214,11 @@ static inline int page_ref_dec_and_test(struct page *page)
 	return ret;
 }
 
+static inline int folio_ref_dec_and_test(struct folio *folio)
+{
+	return page_ref_dec_and_test(&folio->page);
+}
+
 static inline int page_ref_dec_return(struct page *page)
 {
 	int ret = atomic_dec_return(&page->_refcount);
@@ -161,15 +228,91 @@ static inline int page_ref_dec_return(struct page *page)
 	return ret;
 }
 
-static inline int page_ref_add_unless(struct page *page, int nr, int u)
+static inline int folio_ref_dec_return(struct folio *folio)
+{
+	return page_ref_dec_return(&folio->page);
+}
+
+static inline bool page_ref_add_unless(struct page *page, int nr, int u)
 {
-	int ret = atomic_add_unless(&page->_refcount, nr, u);
+	bool ret = atomic_add_unless(&page->_refcount, nr, u);
 
 	if (page_ref_tracepoint_active(page_ref_mod_unless))
 		__page_ref_mod_unless(page, nr, ret);
 	return ret;
 }
 
+static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u)
+{
+	return page_ref_add_unless(&folio->page, nr, u);
+}
+
+/**
+ * folio_try_get - Attempt to increase the refcount on a folio.
+ * @folio: The folio.
+ *
+ * If you do not already have a reference to a folio, you can attempt to
+ * get one using this function.  It may fail if, for example, the folio
+ * has been freed since you found a pointer to it, or it is frozen for
+ * the purposes of splitting or migration.
+ *
+ * Return: True if the reference count was successfully incremented.
+ */
+static inline bool folio_try_get(struct folio *folio)
+{
+	return folio_ref_add_unless(folio, 1, 0);
+}
+
+static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
+{
+#ifdef CONFIG_TINY_RCU
+	/*
+	 * The caller guarantees the folio will not be freed from interrupt
+	 * context, so (on !SMP) we only need preemption to be disabled
+	 * and TINY_RCU does that for us.
+	 */
+# ifdef CONFIG_PREEMPT_COUNT
+	VM_BUG_ON(!in_atomic() && !irqs_disabled());
+# endif
+	VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
+	folio_ref_add(folio, count);
+#else
+	if (unlikely(!folio_ref_add_unless(folio, count, 0))) {
+		/* Either the folio has been freed, or will be freed. */
+		return false;
+	}
+#endif
+	return true;
+}
+
+/**
+ * folio_try_get_rcu - Attempt to increase the refcount on a folio.
+ * @folio: The folio.
+ *
+ * This is a version of folio_try_get() optimised for non-SMP kernels.
+ * If you are still holding the rcu_read_lock() after looking up the
+ * page and know that the page cannot have its refcount decreased to
+ * zero in interrupt context, you can use this instead of folio_try_get().
+ *
+ * Example users include get_user_pages_fast() (as pages are not unmapped
+ * from interrupt context) and the page cache lookups (as pages are not
+ * truncated from interrupt context).  We also know that pages are not
+ * frozen in interrupt context for the purposes of splitting or migration.
+ *
+ * You can also use this function if you're holding a lock that prevents
+ * pages being frozen & removed; eg the i_pages lock for the page cache
+ * or the mmap_sem or page table lock for page tables.  In this case,
+ * it will always succeed, and you could have used a plain folio_get(),
+ * but it's sometimes more convenient to have a common function called
+ * from both locked and RCU-protected contexts.
+ *
+ * Return: True if the reference count was successfully incremented.
+ */
+static inline bool folio_try_get_rcu(struct folio *folio)
+{
+	return folio_ref_try_add_rcu(folio, 1);
+}
+
 static inline int page_ref_freeze(struct page *page, int count)
 {
 	int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
@@ -179,6 +322,11 @@ static inline int page_ref_freeze(struct page *page, int count)
 	return ret;
 }
 
+static inline int folio_ref_freeze(struct folio *folio, int count)
+{
+	return page_ref_freeze(&folio->page, count);
+}
+
 static inline void page_ref_unfreeze(struct page *page, int count)
 {
 	VM_BUG_ON_PAGE(page_count(page) != 0, page);
@@ -189,4 +337,8 @@ static inline void page_ref_unfreeze(struct page *page, int count)
 		__page_ref_unfreeze(page, count);
 }
 
+static inline void folio_ref_unfreeze(struct folio *folio, int count)
+{
+	page_ref_unfreeze(&folio->page, count);
+}
 #endif