[PATCH v14c 00/39] Memory folios: Pagecache edition

[PATCH v14c 00/39] Memory folios: Pagecache edition

[Matthew Wilcox (Oracle)]

This patch series is for human review.  The bots are going to complain
because it depends on the previous 50 folio patches which are now quite
well reviewed (thanks!)  It's almost identical to patches 51-89 of
folio v14 (added a few R-b tags and a couple of minor build fixes)

This set of patches are everything that needs to be done before I can
convert iomap to use folios.  It's probably also all or most of what
needs to be done before other filesystems can be converted to use folios.
So getting this into v5.15 will enable a lot of other work to start.

Matthew Wilcox (Oracle) (39):
  mm: Add folio_pfn()
  mm: Add folio_raw_mapping()
  mm: Add flush_dcache_folio()
  mm: Add kmap_local_folio()
  mm: Add arch_make_folio_accessible()
  mm: Add folio_young and folio_idle
  mm/swap: Add folio_activate()
  mm/swap: Add folio_mark_accessed()
  mm/rmap: Add folio_mkclean()
  mm/migrate: Add folio_migrate_mapping()
  mm/migrate: Add folio_migrate_flags()
  mm/migrate: Add folio_migrate_copy()
  mm/writeback: Rename __add_wb_stat() to wb_stat_mod()
  flex_proportions: Allow N events instead of 1
  mm/writeback: Change __wb_writeout_inc() to __wb_writeout_add()
  mm/writeback: Add __folio_end_writeback()
  mm/writeback: Add folio_start_writeback()
  mm/writeback: Add folio_mark_dirty()
  mm/writeback: Add __folio_mark_dirty()
  mm/writeback: Convert tracing writeback_page_template to folios
  mm/writeback: Add filemap_dirty_folio()
  mm/writeback: Add folio_account_cleaned()
  mm/writeback: Add folio_cancel_dirty()
  mm/writeback: Add folio_clear_dirty_for_io()
  mm/writeback: Add folio_account_redirty()
  mm/writeback: Add folio_redirty_for_writepage()
  mm/filemap: Add i_blocks_per_folio()
  mm/filemap: Add folio_mkwrite_check_truncate()
  mm/filemap: Add readahead_folio()
  mm/workingset: Convert workingset_refault() to take a folio
  mm: Add folio_evictable()
  mm/lru: Convert __pagevec_lru_add_fn to take a folio
  mm/lru: Add folio_add_lru()
  mm/page_alloc: Add folio allocation functions
  mm/filemap: Add filemap_alloc_folio
  mm/filemap: Add filemap_add_folio()
  mm/filemap: Convert mapping_get_entry to return a folio
  mm/filemap: Add filemap_get_folio
  mm/filemap: Add FGP_STABLE

 Documentation/core-api/cachetlb.rst |   6 +
 arch/arm/include/asm/cacheflush.h   |   1 +
 arch/nds32/include/asm/cacheflush.h |   1 +
 fs/jfs/jfs_metapage.c               |   1 +
 include/asm-generic/cacheflush.h    |   6 +
 include/linux/backing-dev.h         |   6 +-
 include/linux/flex_proportions.h    |   9 +-
 include/linux/gfp.h                 |  22 +-
 include/linux/highmem-internal.h    |  11 +
 include/linux/highmem.h             |  38 +++
 include/linux/ksm.h                 |   4 +-
 include/linux/memcontrol.h          |   5 +-
 include/linux/migrate.h             |   4 +
 include/linux/mm.h                  |  62 +++--
 include/linux/page-flags.h          |  20 +-
 include/linux/page_idle.h           |  99 ++++---
 include/linux/page_owner.h          |   8 +-
 include/linux/pagemap.h             | 189 ++++++++++----
 include/linux/rmap.h                |  10 +-
 include/linux/swap.h                |   8 +-
 include/linux/writeback.h           |   9 +-
 include/trace/events/pagemap.h      |  46 ++--
 include/trace/events/writeback.h    |  20 +-
 kernel/bpf/verifier.c               |   2 +-
 lib/flex_proportions.c              |  28 +-
 mm/filemap.c                        | 238 ++++++++---------
 mm/folio-compat.c                   |  99 +++++++
 mm/hugetlb.c                        |   2 +-
 mm/internal.h                       |  35 ++-
 mm/ksm.c                            |  31 ++-
 mm/memory.c                         |   3 +-
 mm/mempolicy.c                      |  10 +
 mm/migrate.c                        | 187 +++++++-------
 mm/page-writeback.c                 | 383 +++++++++++++++-------------
 mm/page_alloc.c                     |  12 +
 mm/page_owner.c                     |  10 +-
 mm/rmap.c                           |  12 +-
 mm/swap.c                           | 136 +++++-----
 mm/swap_state.c                     |   2 +-
 mm/util.c                           |  39 +--
 mm/workingset.c                     |  34 +--
 41 files changed, 1095 insertions(+), 753 deletions(-)

-- 
2.30.2

[PATCH v14 01/39] mm: Add folio_pfn()

[Matthew Wilcox (Oracle)]

This is the folio equivalent of page_to_pfn().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/mm.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c6e2a1682a6d..89daae93aa9b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1623,6 +1623,20 @@ static inline unsigned long page_to_section(const struct page *page)
 }
 #endif
 
+/**
+ * folio_pfn - Return the Page Frame Number of a folio.
+ * @folio: The folio.
+ *
+ * A folio may contain multiple pages.  The pages have consecutive
+ * Page Frame Numbers.
+ *
+ * Return: The Page Frame Number of the first page in the folio.
+ */
+static inline unsigned long folio_pfn(struct folio *folio)
+{
+	return page_to_pfn(&folio->page);
+}
+
 /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
 #ifdef CONFIG_MIGRATION
 static inline bool is_pinnable_page(struct page *page)
-- 
2.30.2

[PATCH v14 02/39] mm: Add folio_raw_mapping()

[Matthew Wilcox (Oracle)]

Convert __page_rmapping to folio_raw_mapping and move it to mm/internal.h.
It's only a couple of instructions (load and mask), so it's definitely
going to be cheaper to inline it than call it.  Leave page_rmapping
out of line.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 mm/internal.h |  7 +++++++
 mm/util.c     | 20 ++++----------------
 2 files changed, 11 insertions(+), 16 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 1a8851b73031..fa31a7f0ed79 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -34,6 +34,13 @@
 
 void page_writeback_init(void);
 
+static inline void *folio_raw_mapping(struct folio *folio)
+{
+	unsigned long mapping = (unsigned long)folio->mapping;
+
+	return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
+}
+
 vm_fault_t do_swap_page(struct vm_fault *vmf);
 void folio_rotate_reclaimable(struct folio *folio);
 
diff --git a/mm/util.c b/mm/util.c
index e8c12350b3eb..d0aa1d9c811e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -635,21 +635,10 @@ void kvfree_sensitive(const void *addr, size_t len)
 }
 EXPORT_SYMBOL(kvfree_sensitive);
 
-static inline void *__page_rmapping(struct page *page)
-{
-	unsigned long mapping;
-
-	mapping = (unsigned long)page->mapping;
-	mapping &= ~PAGE_MAPPING_FLAGS;
-
-	return (void *)mapping;
-}
-
 /* Neutral page->mapping pointer to address_space or anon_vma or other */
 void *page_rmapping(struct page *page)
 {
-	page = compound_head(page);
-	return __page_rmapping(page);
+	return folio_raw_mapping(page_folio(page));
 }
 
 /**
@@ -680,13 +669,12 @@ EXPORT_SYMBOL(folio_mapped);
 
 struct anon_vma *page_anon_vma(struct page *page)
 {
-	unsigned long mapping;
+	struct folio *folio = page_folio(page);
+	unsigned long mapping = (unsigned long)folio->mapping;
 
-	page = compound_head(page);
-	mapping = (unsigned long)page->mapping;
 	if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
 		return NULL;
-	return __page_rmapping(page);
+	return (void *)(mapping - PAGE_MAPPING_ANON);
 }
 
 /**
-- 
2.30.2

[PATCH v14 03/39] mm: Add flush_dcache_folio()

[Matthew Wilcox (Oracle)]

This is a default implementation which calls flush_dcache_page() on
each page in the folio.  If architectures can do better, they should
implement their own version of it.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 Documentation/core-api/cachetlb.rst |  6 ++++++
 arch/arm/include/asm/cacheflush.h   |  1 +
 arch/nds32/include/asm/cacheflush.h |  1 +
 include/asm-generic/cacheflush.h    |  6 ++++++
 mm/util.c                           | 13 +++++++++++++
 5 files changed, 27 insertions(+)

diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst
index fe4290e26729..29682f69a915 100644
--- a/Documentation/core-api/cachetlb.rst
+++ b/Documentation/core-api/cachetlb.rst
@@ -325,6 +325,12 @@ maps this page at its virtual address.
 			dirty.  Again, see sparc64 for examples of how
 			to deal with this.
 
+  ``void flush_dcache_folio(struct folio *folio)``
+	This function is called under the same circumstances as
+	flush_dcache_page().  It allows the architecture to
+	optimise for flushing the entire folio of pages instead
+	of flushing one page at a time.
+
   ``void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
   unsigned long user_vaddr, void *dst, void *src, int len)``
   ``void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 2e24e765e6d3..23bf823376e1 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -290,6 +290,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
  */
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *folio);
 
 static inline void flush_kernel_vmap_range(void *addr, int size)
 {
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 7d6824f7c0e8..f10d13af4ae5 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -38,6 +38,7 @@ void flush_anon_page(struct vm_area_struct *vma,
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 void flush_kernel_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
 void flush_kernel_vmap_range(void *addr, int size);
 void invalidate_kernel_vmap_range(void *addr, int size);
 #define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 4a674db4e1fa..fedc0dfa4877 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -49,9 +49,15 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 static inline void flush_dcache_page(struct page *page)
 {
 }
+
+static inline void flush_dcache_folio(struct folio *folio) { }
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
 #endif
 
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio);
+#endif
 
 #ifndef flush_dcache_mmap_lock
 static inline void flush_dcache_mmap_lock(struct address_space *mapping)
diff --git a/mm/util.c b/mm/util.c
index d0aa1d9c811e..149537120a91 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1057,3 +1057,16 @@ void page_offline_end(void)
 	up_write(&page_offline_rwsem);
 }
 EXPORT_SYMBOL(page_offline_end);
+
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio)
+{
+	unsigned int n = folio_nr_pages(folio);
+
+	do {
+		n--;
+		flush_dcache_page(folio_page(folio, n));
+	} while (n);
+}
+EXPORT_SYMBOL(flush_dcache_folio);
+#endif
-- 
2.30.2

[PATCH v14 04/39] mm: Add kmap_local_folio()

[Matthew Wilcox (Oracle)]

This allows us to map a portion of a folio.  Callers can only expect
to access up to the next page boundary.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/highmem-internal.h | 11 +++++++++
 include/linux/highmem.h          | 38 ++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 7902c7d8b55f..d5d6f930ae1d 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -73,6 +73,12 @@ static inline void *kmap_local_page(struct page *page)
 	return __kmap_local_page_prot(page, kmap_prot);
 }
 
+static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+{
+	struct page *page = folio_page(folio, offset / PAGE_SIZE);
+	return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE;
+}
+
 static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
 {
 	return __kmap_local_page_prot(page, prot);
@@ -160,6 +166,11 @@ static inline void *kmap_local_page(struct page *page)
 	return page_address(page);
 }
 
+static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+{
+	return page_address(&folio->page) + offset;
+}
+
 static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
 {
 	return kmap_local_page(page);
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 8c6e8e996c87..85de3bd0b47d 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -96,6 +96,44 @@ static inline void kmap_flush_unused(void);
  */
 static inline void *kmap_local_page(struct page *page);
 
+/**
+ * kmap_local_folio - Map a page in this folio for temporary usage
+ * @folio:	The folio to be mapped.
+ * @offset:	The byte offset within the folio.
+ *
+ * Returns: The virtual address of the mapping
+ *
+ * Can be invoked from any context.
+ *
+ * Requires careful handling when nesting multiple mappings because the map
+ * management is stack based. The unmap has to be in the reverse order of
+ * the map operation:
+ *
+ * addr1 = kmap_local_folio(page1, offset1);
+ * addr2 = kmap_local_folio(page2, offset2);
+ * ...
+ * kunmap_local(addr2);
+ * kunmap_local(addr1);
+ *
+ * Unmapping addr1 before addr2 is invalid and causes malfunction.
+ *
+ * Contrary to kmap() mappings the mapping is only valid in the context of
+ * the caller and cannot be handed to other contexts.
+ *
+ * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the
+ * virtual address of the direct mapping. Only real highmem pages are
+ * temporarily mapped.
+ *
+ * While it is significantly faster than kmap() for the higmem case it
+ * comes with restrictions about the pointer validity. Only use when really
+ * necessary.
+ *
+ * On HIGHMEM enabled systems mapping a highmem page has the side effect of
+ * disabling migration in order to keep the virtual address stable across
+ * preemption. No caller of kmap_local_folio() can rely on this side effect.
+ */
+static inline void *kmap_local_folio(struct folio *folio, size_t offset);
+
 /**
  * kmap_atomic - Atomically map a page for temporary usage - Deprecated!
  * @page:	Pointer to the page to be mapped
-- 
2.30.2

[PATCH v14 05/39] mm: Add arch_make_folio_accessible()

[Matthew Wilcox (Oracle)]

As a default implementation, call arch_make_page_accessible n times.
If an architecture can do better, it can override this.

Also move the default implementation of arch_make_page_accessible()
from gfp.h to mm.h.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/gfp.h |  6 ------
 include/linux/mm.h  | 21 +++++++++++++++++++++
 2 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 55b2ec1f965a..dc5ff40608ce 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -520,12 +520,6 @@ static inline void arch_free_page(struct page *page, int order) { }
 #ifndef HAVE_ARCH_ALLOC_PAGE
 static inline void arch_alloc_page(struct page *page, int order) { }
 #endif
-#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
-static inline int arch_make_page_accessible(struct page *page)
-{
-	return 0;
-}
-#endif
 
 struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 		nodemask_t *nodemask);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 89daae93aa9b..deb0f5efaa65 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1732,6 +1732,27 @@ static inline size_t folio_size(struct folio *folio)
 	return PAGE_SIZE << folio_order(folio);
 }
 
+#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
+static inline int arch_make_page_accessible(struct page *page)
+{
+	return 0;
+}
+#endif
+
+#ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE
+static inline int arch_make_folio_accessible(struct folio *folio)
+{
+	int ret, i;
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		ret = arch_make_page_accessible(folio_page(folio, i));
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+#endif
+
 /*
  * Some inline functions in vmstat.h depend on page_zone()
  */
-- 
2.30.2

[PATCH v14 06/39] mm: Add folio_young and folio_idle

[Matthew Wilcox (Oracle)]

Idle page tracking is handled through page_ext on 32-bit architectures.
Add folio equivalents for 32-bit and move all the page compatibility
parts to common code.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/page_idle.h | 99 +++++++++++++++++++--------------------
 1 file changed, 49 insertions(+), 50 deletions(-)

diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index 1e894d34bdce..1bcb1365b1d0 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -8,46 +8,16 @@
 
 #ifdef CONFIG_IDLE_PAGE_TRACKING
 
-#ifdef CONFIG_64BIT
-static inline bool page_is_young(struct page *page)
-{
-	return PageYoung(page);
-}
-
-static inline void set_page_young(struct page *page)
-{
-	SetPageYoung(page);
-}
-
-static inline bool test_and_clear_page_young(struct page *page)
-{
-	return TestClearPageYoung(page);
-}
-
-static inline bool page_is_idle(struct page *page)
-{
-	return PageIdle(page);
-}
-
-static inline void set_page_idle(struct page *page)
-{
-	SetPageIdle(page);
-}
-
-static inline void clear_page_idle(struct page *page)
-{
-	ClearPageIdle(page);
-}
-#else /* !CONFIG_64BIT */
+#ifndef CONFIG_64BIT
 /*
  * If there is not enough space to store Idle and Young bits in page flags, use
  * page ext flags instead.
  */
 extern struct page_ext_operations page_idle_ops;
 
-static inline bool page_is_young(struct page *page)
+static inline bool folio_test_young(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = lookup_page_ext(&folio->page);
 
 	if (unlikely(!page_ext))
 		return false;
@@ -55,9 +25,9 @@ static inline bool page_is_young(struct page *page)
 	return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
-static inline void set_page_young(struct page *page)
+static inline void folio_set_young(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = lookup_page_ext(&folio->page);
 
 	if (unlikely(!page_ext))
 		return;
@@ -65,9 +35,9 @@ static inline void set_page_young(struct page *page)
 	set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
-static inline bool test_and_clear_page_young(struct page *page)
+static inline bool folio_test_clear_young(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = lookup_page_ext(&folio->page);
 
 	if (unlikely(!page_ext))
 		return false;
@@ -75,9 +45,9 @@ static inline bool test_and_clear_page_young(struct page *page)
 	return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
-static inline bool page_is_idle(struct page *page)
+static inline bool folio_test_idle(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = lookup_page_ext(&folio->page);
 
 	if (unlikely(!page_ext))
 		return false;
@@ -85,9 +55,9 @@ static inline bool page_is_idle(struct page *page)
 	return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
-static inline void set_page_idle(struct page *page)
+static inline void folio_set_idle(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = lookup_page_ext(&folio->page);
 
 	if (unlikely(!page_ext))
 		return;
@@ -95,46 +65,75 @@ static inline void set_page_idle(struct page *page)
 	set_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
-static inline void clear_page_idle(struct page *page)
+static inline void folio_clear_idle(struct folio *folio)
 {
-	struct page_ext *page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = lookup_page_ext(&folio->page);
 
 	if (unlikely(!page_ext))
 		return;
 
 	clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
-#endif /* CONFIG_64BIT */
+#endif /* !CONFIG_64BIT */
 
 #else /* !CONFIG_IDLE_PAGE_TRACKING */
 
-static inline bool page_is_young(struct page *page)
+static inline bool folio_test_young(struct folio *folio)
 {
 	return false;
 }
 
-static inline void set_page_young(struct page *page)
+static inline void folio_set_young(struct folio *folio)
 {
 }
 
-static inline bool test_and_clear_page_young(struct page *page)
+static inline bool folio_test_clear_young(struct folio *folio)
 {
 	return false;
 }
 
-static inline bool page_is_idle(struct page *page)
+static inline bool folio_test_idle(struct folio *folio)
 {
 	return false;
 }
 
-static inline void set_page_idle(struct page *page)
+static inline void folio_set_idle(struct folio *folio)
 {
 }
 
-static inline void clear_page_idle(struct page *page)
+static inline void folio_clear_idle(struct folio *folio)
 {
 }
 
 #endif /* CONFIG_IDLE_PAGE_TRACKING */
 
+static inline bool page_is_young(struct page *page)
+{
+	return folio_test_young(page_folio(page));
+}
+
+static inline void set_page_young(struct page *page)
+{
+	folio_set_young(page_folio(page));
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+	return folio_test_clear_young(page_folio(page));
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+	return folio_test_idle(page_folio(page));
+}
+
+static inline void set_page_idle(struct page *page)
+{
+	folio_set_idle(page_folio(page));
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+	folio_clear_idle(page_folio(page));
+}
 #endif /* _LINUX_MM_PAGE_IDLE_H */
-- 
2.30.2

[PATCH v14 07/39] mm/swap: Add folio_activate()

[Matthew Wilcox (Oracle)]

This replaces activate_page() and eliminates lots of calls to
compound_head().  Saves net 118 bytes of kernel text.  There are still
some redundant calls to page_folio() here which will be removed when
pagevec_lru_move_fn() is converted to use folios.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/trace/events/pagemap.h | 14 +++++-------
 mm/swap.c                      | 41 ++++++++++++++++++----------------
 2 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
index 92ad176210ff..1fd0185d66e8 100644
--- a/include/trace/events/pagemap.h
+++ b/include/trace/events/pagemap.h
@@ -60,23 +60,21 @@ TRACE_EVENT(mm_lru_insertion,
 
 TRACE_EVENT(mm_lru_activate,
 
-	TP_PROTO(struct page *page),
+	TP_PROTO(struct folio *folio),
 
-	TP_ARGS(page),
+	TP_ARGS(folio),
 
 	TP_STRUCT__entry(
-		__field(struct page *,	page	)
+		__field(struct folio *,	folio	)
 		__field(unsigned long,	pfn	)
 	),
 
 	TP_fast_assign(
-		__entry->page	= page;
-		__entry->pfn	= page_to_pfn(page);
+		__entry->folio	= folio;
+		__entry->pfn	= folio_pfn(folio);
 	),
 
-	/* Flag format is based on page-types.c formatting for pagemap */
-	TP_printk("page=%p pfn=0x%lx", __entry->page, __entry->pfn)
-
+	TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn)
 );
 
 #endif /* _TRACE_PAGEMAP_H */
diff --git a/mm/swap.c b/mm/swap.c
index 85969b36b636..c3137e4e1cd8 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -322,15 +322,15 @@ void lru_note_cost_page(struct page *page)
 		      page_is_file_lru(page), thp_nr_pages(page));
 }
 
-static void __activate_page(struct page *page, struct lruvec *lruvec)
+static void __folio_activate(struct folio *folio, struct lruvec *lruvec)
 {
-	if (!PageActive(page) && !PageUnevictable(page)) {
-		int nr_pages = thp_nr_pages(page);
+	if (!folio_test_active(folio) && !folio_test_unevictable(folio)) {
+		int nr_pages = folio_nr_pages(folio);
 
-		del_page_from_lru_list(page, lruvec);
-		SetPageActive(page);
-		add_page_to_lru_list(page, lruvec);
-		trace_mm_lru_activate(page);
+		lruvec_del_folio(lruvec, folio);
+		folio_set_active(folio);
+		lruvec_add_folio(lruvec, folio);
+		trace_mm_lru_activate(folio);
 
 		__count_vm_events(PGACTIVATE, nr_pages);
 		__count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE,
@@ -339,6 +339,11 @@ static void __activate_page(struct page *page, struct lruvec *lruvec)
 }
 
 #ifdef CONFIG_SMP
+static void __activate_page(struct page *page, struct lruvec *lruvec)
+{
+	return __folio_activate(page_folio(page), lruvec);
+}
+
 static void activate_page_drain(int cpu)
 {
 	struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
@@ -352,16 +357,16 @@ static bool need_activate_page_drain(int cpu)
 	return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
 }
 
-static void activate_page(struct page *page)
+static void folio_activate(struct folio *folio)
 {
-	page = compound_head(page);
-	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+	if (folio_test_lru(folio) && !folio_test_active(folio) &&
+	    !folio_test_unevictable(folio)) {
 		struct pagevec *pvec;
 
+		folio_get(folio);
 		local_lock(&lru_pvecs.lock);
 		pvec = this_cpu_ptr(&lru_pvecs.activate_page);
-		get_page(page);
-		if (pagevec_add_and_need_flush(pvec, page))
+		if (pagevec_add_and_need_flush(pvec, &folio->page))
 			pagevec_lru_move_fn(pvec, __activate_page);
 		local_unlock(&lru_pvecs.lock);
 	}
@@ -372,17 +377,15 @@ static inline void activate_page_drain(int cpu)
 {
 }
 
-static void activate_page(struct page *page)
+static void folio_activate(struct folio *folio)
 {
-	struct folio *folio = page_folio(page);
 	struct lruvec *lruvec;
 
-	page = &folio->page;
-	if (TestClearPageLRU(page)) {
+	if (folio_test_clear_lru(folio)) {
 		lruvec = folio_lruvec_lock_irq(folio);
-		__activate_page(page, lruvec);
+		__folio_activate(folio, lruvec);
 		unlock_page_lruvec_irq(lruvec);
-		SetPageLRU(page);
+		folio_set_lru(folio);
 	}
 }
 #endif
@@ -447,7 +450,7 @@ void mark_page_accessed(struct page *page)
 		 * LRU on the next drain.
 		 */
 		if (PageLRU(page))
-			activate_page(page);
+			folio_activate(page_folio(page));
 		else
 			__lru_cache_activate_page(page);
 		ClearPageReferenced(page);
-- 
2.30.2

[PATCH v14 08/39] mm/swap: Add folio_mark_accessed()

[Matthew Wilcox (Oracle)]

Convert mark_page_accessed() to folio_mark_accessed().  It already
operated on the entire compound page, but now we can avoid calling
compound_head quite so many times.  Shrinks the function from 424 bytes
to 295 bytes (shrinking by 129 bytes).  The compatibility wrapper is 30
bytes, plus the 8 bytes for the exported symbol means the kernel shrinks
by 91 bytes.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/swap.h |  3 ++-
 mm/folio-compat.c    |  7 +++++++
 mm/swap.c            | 34 ++++++++++++++++------------------
 3 files changed, 25 insertions(+), 19 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 989d8f78c256..c7a4c0a5863d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -352,7 +352,8 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file,
 			  unsigned int nr_pages);
 extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
-extern void mark_page_accessed(struct page *);
+void mark_page_accessed(struct page *);
+void folio_mark_accessed(struct folio *);
 
 extern atomic_t lru_disable_count;
 
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 7044fcc8a8aa..a374747ae1c6 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/pagemap.h>
+#include <linux/swap.h>
 
 struct address_space *page_mapping(struct page *page)
 {
@@ -41,3 +42,9 @@ bool page_mapped(struct page *page)
 	return folio_mapped(page_folio(page));
 }
 EXPORT_SYMBOL(page_mapped);
+
+void mark_page_accessed(struct page *page)
+{
+	folio_mark_accessed(page_folio(page));
+}
+EXPORT_SYMBOL(mark_page_accessed);
diff --git a/mm/swap.c b/mm/swap.c
index c3137e4e1cd8..d32007fe23b3 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -390,7 +390,7 @@ static void folio_activate(struct folio *folio)
 }
 #endif
 
-static void __lru_cache_activate_page(struct page *page)
+static void __lru_cache_activate_folio(struct folio *folio)
 {
 	struct pagevec *pvec;
 	int i;
@@ -411,8 +411,8 @@ static void __lru_cache_activate_page(struct page *page)
 	for (i = pagevec_count(pvec) - 1; i >= 0; i--) {
 		struct page *pagevec_page = pvec->pages[i];
 
-		if (pagevec_page == page) {
-			SetPageActive(page);
+		if (pagevec_page == &folio->page) {
+			folio_set_active(folio);
 			break;
 		}
 	}
@@ -430,36 +430,34 @@ static void __lru_cache_activate_page(struct page *page)
  * When a newly allocated page is not yet visible, so safe for non-atomic ops,
  * __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
  */
-void mark_page_accessed(struct page *page)
+void folio_mark_accessed(struct folio *folio)
 {
-	page = compound_head(page);
-
-	if (!PageReferenced(page)) {
-		SetPageReferenced(page);
-	} else if (PageUnevictable(page)) {
+	if (!folio_test_referenced(folio)) {
+		folio_set_referenced(folio);
+	} else if (folio_test_unevictable(folio)) {
 		/*
 		 * Unevictable pages are on the "LRU_UNEVICTABLE" list. But,
 		 * this list is never rotated or maintained, so marking an
 		 * evictable page accessed has no effect.
 		 */
-	} else if (!PageActive(page)) {
+	} else if (!folio_test_active(folio)) {
 		/*
 		 * If the page is on the LRU, queue it for activation via
 		 * lru_pvecs.activate_page. Otherwise, assume the page is on a
 		 * pagevec, mark it active and it'll be moved to the active
 		 * LRU on the next drain.
 		 */
-		if (PageLRU(page))
-			folio_activate(page_folio(page));
+		if (folio_test_lru(folio))
+			folio_activate(folio);
 		else
-			__lru_cache_activate_page(page);
-		ClearPageReferenced(page);
-		workingset_activation(page_folio(page));
+			__lru_cache_activate_folio(folio);
+		folio_clear_referenced(folio);
+		workingset_activation(folio);
 	}
-	if (page_is_idle(page))
-		clear_page_idle(page);
+	if (folio_test_idle(folio))
+		folio_clear_idle(folio);
 }
-EXPORT_SYMBOL(mark_page_accessed);
+EXPORT_SYMBOL(folio_mark_accessed);
 
 /**
  * lru_cache_add - add a page to a page list
-- 
2.30.2

Re: [PATCH v14 08/39] mm/swap: Add folio_mark_accessed()

[Gregory Price]

On Thu, 15 Jul 2021 20:59:59 +0100, Matthew Wilcox wrote
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 989d8f78c256..c7a4c0a5863d 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -352,7 +352,8 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file,
>  			  unsigned int nr_pages);
>  extern void lru_note_cost_page(struct page *);
>  extern void lru_cache_add(struct page *);
> -extern void mark_page_accessed(struct page *);
> +void mark_page_accessed(struct page *);
> +void folio_mark_accessed(struct folio *);
> 
>  extern atomic_t lru_disable_count;
> 
> diff --git a/mm/folio-compat.c b/mm/folio-compat.c
> index 7044fcc8a8aa..a374747ae1c6 100644
> --- a/mm/folio-compat.c
> +++ b/mm/folio-compat.c
> @@ -5,6 +5,7 @@
>   */
> 
>  #include <linux/pagemap.h>
> +#include <linux/swap.h>
> 
>  struct address_space *page_mapping(struct page *page)
>  {
> @@ -41,3 +42,9 @@ bool page_mapped(struct page *page)
>  	return folio_mapped(page_folio(page));
>  }
>  EXPORT_SYMBOL(page_mapped);
> +
> +void mark_page_accessed(struct page *page)
> +{
> +	folio_mark_accessed(page_folio(page));
> +}
> +EXPORT_SYMBOL(mark_page_accessed);
... snip ...
>
> @@ -430,36 +430,34 @@ static void __lru_cache_activate_page(struct page *page)
>   * When a newly allocated page is not yet visible, so safe for non-atomic ops,
>   * __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
>   */
> -void mark_page_accessed(struct page *page)
> +void folio_mark_accessed(struct folio *folio)
>  {
> -	page = compound_head(page);
> -
> -	if (!PageReferenced(page)) {
> -		SetPageReferenced(page);
> -	} else if (PageUnevictable(page)) {
> +	if (!folio_test_referenced(folio)) {
> +		folio_set_referenced(folio);
> +	} else if (folio_test_unevictable(folio)) {

Hi Matthew,

My colleagues and I have been testing some page-tracking algorithms and
we tried using the reference bit by using /proc/pid/clear_clears,
/proc/pid/pagemap, and /proc/kpageflags.

I'm not 100% of the issue, but we're finding some inconsistencies when
tracking page reference bits, and this seems to be at least one of the
patches we saw that might be in the mix.

From reading up on folios, it seems like this change prevents each
individual page in a folio from being marked referenced, and instead
prefers to simply mark the entire folio containing the page as accessed.

When looking at the proc/ interface, it seems like it is still
referencing the page and not using the folio for a page (see below).

Our current suspicion is that since only the folio head gets marked
referenced, any pages inside the folio that aren't the head will
basically never be marked referenced, leading to an inconsistent view.

I'm curious your thoughts on whether (or neither):

a) Should we update kpageflags_read to use page_folio() and get the
   folio flags for the head page

or

b) the above change to mark_page_accessed() should mark both the
   individual page flags to accessed as well as the folio head accessed.

Thanks for your time.
Gregory Price


(relevant fs/proc/page.c code:)


static ssize_t kpageflags_read(struct file *file, char __user *buf,
                             size_t count, loff_t *ppos)
{
... snip ...
                ppage = pfn_to_online_page(pfn);

                if (put_user(stable_page_flags(ppage), out)) {
                        ret = -EFAULT;
                        break;
                }
... snip ...
}


u64 stable_page_flags(struct page *page)
{
... snip ...
        k = page->flags;
... snip ...
}

Re: [PATCH v14 08/39] mm/swap: Add folio_mark_accessed()

[Matthew Wilcox]

On Sun, Oct 08, 2023 at 11:34:45AM -0400, Gregory Price wrote:
> On Thu, 15 Jul 2021 20:59:59 +0100, Matthew Wilcox wrote
> > +void mark_page_accessed(struct page *page)
> > +{
> > +	folio_mark_accessed(page_folio(page));
> > +}
> > +EXPORT_SYMBOL(mark_page_accessed);
> ... snip ...
> >
> > @@ -430,36 +430,34 @@ static void __lru_cache_activate_page(struct page *page)
> >   * When a newly allocated page is not yet visible, so safe for non-atomic ops,
> >   * __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
> >   */
> > -void mark_page_accessed(struct page *page)
> > +void folio_mark_accessed(struct folio *folio)
> >  {
> > -	page = compound_head(page);
> > -
> > -	if (!PageReferenced(page)) {
> > -		SetPageReferenced(page);
> > -	} else if (PageUnevictable(page)) {
> > +	if (!folio_test_referenced(folio)) {
> > +		folio_set_referenced(folio);
> > +	} else if (folio_test_unevictable(folio)) {
> 
> Hi Matthew,
> 
> My colleagues and I have been testing some page-tracking algorithms and
> we tried using the reference bit by using /proc/pid/clear_clears,
> /proc/pid/pagemap, and /proc/kpageflags.
> 
> I'm not 100% of the issue, but we're finding some inconsistencies when
> tracking page reference bits, and this seems to be at least one of the
> patches we saw that might be in the mix.
> 
> >From reading up on folios, it seems like this change prevents each
> individual page in a folio from being marked referenced, and instead
> prefers to simply mark the entire folio containing the page as accessed.
> 
> When looking at the proc/ interface, it seems like it is still
> referencing the page and not using the folio for a page (see below).
> 
> Our current suspicion is that since only the folio head gets marked
> referenced, any pages inside the folio that aren't the head will
> basically never be marked referenced, leading to an inconsistent view.
> 
> I'm curious your thoughts on whether (or neither):
> 
> a) Should we update kpageflags_read to use page_folio() and get the
>    folio flags for the head page
> 
> or
> 
> b) the above change to mark_page_accessed() should mark both the
>    individual page flags to accessed as well as the folio head accessed.

Hi Greg, thanks for reaching out.

The referenced bit has been tracked on what is now known as a per-folio
basis since commit 8cb38fabb6bc in 2016.  That is, if you tried to
SetPageReferenced / ClearPageReferenced / test PageReferenced on a tail
page, it would redirect to the head page in order to set/clear/test
the bit in the head page's flags field.

That's not to say that all the code which sets/checks/tests this
really understands that!  We've definitely found bugs during the folio
work where code has mistakenly assumed that operations on a tail
page actually affect that page rather than the whole allocation.

There's also code which is now being exposed to compound pages for the
first time, and is not holding up well.

I hope that's helpful in finding the bug you're chasing.

> Thanks for your time.
> Gregory Price
> 
> 
> (relevant fs/proc/page.c code:)
> 
> 
> static ssize_t kpageflags_read(struct file *file, char __user *buf,
>                              size_t count, loff_t *ppos)
> {
> ... snip ...
>                 ppage = pfn_to_online_page(pfn);
> 
>                 if (put_user(stable_page_flags(ppage), out)) {
>                         ret = -EFAULT;
>                         break;
>                 }
> ... snip ...
> }
> 
> 
> u64 stable_page_flags(struct page *page)
> {
> ... snip ...
>         k = page->flags;
> ... snip ...
> }

Re: [PATCH v14 08/39] mm/swap: Add folio_mark_accessed()

[Gregory Price]

On Tue, Oct 10, 2023 at 07:08:15PM +0100, Matthew Wilcox wrote:
> On Sun, Oct 08, 2023 at 11:34:45AM -0400, Gregory Price wrote:
> > a) Should we update kpageflags_read to use page_folio() and get the
> >    folio flags for the head page
> > 
> > or
> > 
> > b) the above change to mark_page_accessed() should mark both the
> >    individual page flags to accessed as well as the folio head accessed.
> 
> Hi Greg, thanks for reaching out.
> 
> The referenced bit has been tracked on what is now known as a per-folio
> basis since commit 8cb38fabb6bc in 2016.  That is, if you tried to
> SetPageReferenced / ClearPageReferenced / test PageReferenced on a tail
> page, it would redirect to the head page in order to set/clear/test
> the bit in the head page's flags field.
> 
> That's not to say that all the code which sets/checks/tests this
> really understands that!  We've definitely found bugs during the folio
> work where code has mistakenly assumed that operations on a tail
> page actually affect that page rather than the whole allocation.
> 
> There's also code which is now being exposed to compound pages for the
> first time, and is not holding up well.
> 
> I hope that's helpful in finding the bug you're chasing.
> 

ah, very interesting.  So the kpageflags code doesn't appear to respect
flag locations defined in 8cb38fabb6bc

We tested this hack of a patch which swaps the page flags for the folio
head flags according to the flag locations defined in page-flags.h.

The result was that the referenced bit was almost *never* set on an
anonymous pages, no matter where we look, even when we have a program
constantly touching every page in a large chunk of memory.

Head scratcher.

Thank you for the response.  We're still very much confused, but it
looks like there are potentially many problems (unless we're
misunderstanding the reference bit).

(cc Naoya since I saw you were actively working on kpageflags for folio
 support not sure what else you're seeing).

~Gregory


diff --git a/fs/proc/page.c b/fs/proc/page.c
index 195b077c0fac..8022a41d7899 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -110,6 +110,7 @@ static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
 u64 stable_page_flags(struct page *page)
 {
        u64 k;
+       u64 fh;
        u64 u;

        /*
@@ -119,7 +120,7 @@ u64 stable_page_flags(struct page *page)
        if (!page)
                return 1 << KPF_NOPAGE;

-       k = page->flags;
+       fh = *folio_flags(page_folio(folio), 0);
        u = 0;

        /*
@@ -188,20 +189,20 @@ u64 stable_page_flags(struct page *page)
                u |= 1 << KPF_SLAB;

        u |= kpf_copy_bit(k, KPF_ERROR,         PG_error);
-       u |= kpf_copy_bit(k, KPF_DIRTY,         PG_dirty);
+       u |= kpf_copy_bit(fh, KPF_DIRTY,        PG_dirty);
        u |= kpf_copy_bit(k, KPF_UPTODATE,      PG_uptodate);
        u |= kpf_copy_bit(k, KPF_WRITEBACK,     PG_writeback);

-       u |= kpf_copy_bit(k, KPF_LRU,           PG_lru);
-       u |= kpf_copy_bit(k, KPF_REFERENCED,    PG_referenced);
-       u |= kpf_copy_bit(k, KPF_ACTIVE,        PG_active);
+       u |= kpf_copy_bit(fh, KPF_LRU,          PG_lru);
+       u |= kpf_copy_bit(fh, KPF_REFERENCED,   PG_referenced);
+       u |= kpf_copy_bit(fh, KPF_ACTIVE,       PG_active);
        u |= kpf_copy_bit(k, KPF_RECLAIM,       PG_reclaim);

        if (PageSwapCache(page))
                u |= 1 << KPF_SWAPCACHE;
        u |= kpf_copy_bit(k, KPF_SWAPBACKED,    PG_swapbacked);

-       u |= kpf_copy_bit(k, KPF_UNEVICTABLE,   PG_unevictable);
+       u |= kpf_copy_bit(fh, KPF_UNEVICTABLE,  PG_unevictable);
        u |= kpf_copy_bit(k, KPF_MLOCKED,       PG_mlocked);

 #ifdef CONFIG_MEMORY_FAILURE

[PATCH v14 09/39] mm/rmap: Add folio_mkclean()

[Matthew Wilcox (Oracle)]

Transform page_mkclean() into folio_mkclean() and add a page_mkclean()
wrapper around folio_mkclean().

folio_mkclean is 15 bytes smaller than page_mkclean, but the kernel
is enlarged by 33 bytes due to inlining page_folio() into each caller.
This will go away once the callers are converted to use folio_mkclean().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/rmap.h | 10 ++++++----
 mm/rmap.c            | 12 ++++++------
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 83fb86133fe1..d45584310cde 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -235,7 +235,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
  *
  * returns the number of cleaned PTEs.
  */
-int page_mkclean(struct page *);
+int folio_mkclean(struct folio *);
 
 /*
  * called in munlock()/munmap() path to check for other vmas holding
@@ -293,12 +293,14 @@ static inline int page_referenced(struct page *page, int is_locked,
 
 #define try_to_unmap(page, refs) false
 
-static inline int page_mkclean(struct page *page)
+static inline int folio_mkclean(struct folio *folio)
 {
 	return 0;
 }
-
-
 #endif	/* CONFIG_MMU */
 
+static inline int page_mkclean(struct page *page)
+{
+	return folio_mkclean(page_folio(page));
+}
 #endif	/* _LINUX_RMAP_H */
diff --git a/mm/rmap.c b/mm/rmap.c
index 1df8683c4c4c..b3aae8eeaeaf 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -980,7 +980,7 @@ static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg)
 	return true;
 }
 
-int page_mkclean(struct page *page)
+int folio_mkclean(struct folio *folio)
 {
 	int cleaned = 0;
 	struct address_space *mapping;
@@ -990,20 +990,20 @@ int page_mkclean(struct page *page)
 		.invalid_vma = invalid_mkclean_vma,
 	};
 
-	BUG_ON(!PageLocked(page));
+	BUG_ON(!folio_test_locked(folio));
 
-	if (!page_mapped(page))
+	if (!folio_mapped(folio))
 		return 0;
 
-	mapping = page_mapping(page);
+	mapping = folio_mapping(folio);
 	if (!mapping)
 		return 0;
 
-	rmap_walk(page, &rwc);
+	rmap_walk(&folio->page, &rwc);
 
 	return cleaned;
 }
-EXPORT_SYMBOL_GPL(page_mkclean);
+EXPORT_SYMBOL_GPL(folio_mkclean);
 
 /**
  * page_move_anon_rmap - move a page to our anon_vma
-- 
2.30.2

[PATCH v14 10/39] mm/migrate: Add folio_migrate_mapping()

[Matthew Wilcox (Oracle)]

Reimplement migrate_page_move_mapping() as a wrapper around
folio_migrate_mapping().  Saves 193 bytes of kernel text.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/migrate.h |  2 +
 mm/folio-compat.c       | 11 ++++++
 mm/migrate.c            | 85 +++++++++++++++++++++--------------------
 3 files changed, 57 insertions(+), 41 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 23dadf7aeba8..eb14495a1f46 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -51,6 +51,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
 extern int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page, int extra_count);
+int folio_migrate_mapping(struct address_space *mapping,
+		struct folio *newfolio, struct folio *folio, int extra_count);
 #else
 
 static inline void putback_movable_pages(struct list_head *l) {}
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index a374747ae1c6..d883d964fd52 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -4,6 +4,7 @@
  * eventually.
  */
 
+#include <linux/migrate.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 
@@ -48,3 +49,13 @@ void mark_page_accessed(struct page *page)
 	folio_mark_accessed(page_folio(page));
 }
 EXPORT_SYMBOL(mark_page_accessed);
+
+#ifdef CONFIG_MIGRATION
+int migrate_page_move_mapping(struct address_space *mapping,
+		struct page *newpage, struct page *page, int extra_count)
+{
+	return folio_migrate_mapping(mapping, page_folio(newpage),
+					page_folio(page), extra_count);
+}
+EXPORT_SYMBOL(migrate_page_move_mapping);
+#endif
diff --git a/mm/migrate.c b/mm/migrate.c
index 910552318df3..aa4f2310c5bb 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -363,7 +363,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
 	 */
 	expected_count += is_device_private_page(page);
 	if (mapping)
-		expected_count += thp_nr_pages(page) + page_has_private(page);
+		expected_count += compound_nr(page) + page_has_private(page);
 
 	return expected_count;
 }
@@ -376,74 +376,75 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
  * 2 for pages with a mapping
  * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
-int migrate_page_move_mapping(struct address_space *mapping,
-		struct page *newpage, struct page *page, int extra_count)
+int folio_migrate_mapping(struct address_space *mapping,
+		struct folio *newfolio, struct folio *folio, int extra_count)
 {
-	XA_STATE(xas, &mapping->i_pages, page_index(page));
+	XA_STATE(xas, &mapping->i_pages, folio_index(folio));
 	struct zone *oldzone, *newzone;
 	int dirty;
-	int expected_count = expected_page_refs(mapping, page) + extra_count;
-	int nr = thp_nr_pages(page);
+	int expected_count = expected_page_refs(mapping, &folio->page) + extra_count;
+	int nr = folio_nr_pages(folio);
 
 	if (!mapping) {
 		/* Anonymous page without mapping */
-		if (page_count(page) != expected_count)
+		if (folio_ref_count(folio) != expected_count)
 			return -EAGAIN;
 
 		/* No turning back from here */
-		newpage->index = page->index;
-		newpage->mapping = page->mapping;
-		if (PageSwapBacked(page))
-			__SetPageSwapBacked(newpage);
+		newfolio->index = folio->index;
+		newfolio->mapping = folio->mapping;
+		if (folio_test_swapbacked(folio))
+			__folio_set_swapbacked(newfolio);
 
 		return MIGRATEPAGE_SUCCESS;
 	}
 
-	oldzone = page_zone(page);
-	newzone = page_zone(newpage);
+	oldzone = folio_zone(folio);
+	newzone = folio_zone(newfolio);
 
 	xas_lock_irq(&xas);
-	if (page_count(page) != expected_count || xas_load(&xas) != page) {
+	if (folio_ref_count(folio) != expected_count ||
+	    xas_load(&xas) != folio) {
 		xas_unlock_irq(&xas);
 		return -EAGAIN;
 	}
 
-	if (!page_ref_freeze(page, expected_count)) {
+	if (!folio_ref_freeze(folio, expected_count)) {
 		xas_unlock_irq(&xas);
 		return -EAGAIN;
 	}
 
 	/*
-	 * Now we know that no one else is looking at the page:
+	 * Now we know that no one else is looking at the folio:
 	 * no turning back from here.
 	 */
-	newpage->index = page->index;
-	newpage->mapping = page->mapping;
-	page_ref_add(newpage, nr); /* add cache reference */
-	if (PageSwapBacked(page)) {
-		__SetPageSwapBacked(newpage);
-		if (PageSwapCache(page)) {
-			SetPageSwapCache(newpage);
-			set_page_private(newpage, page_private(page));
+	newfolio->index = folio->index;
+	newfolio->mapping = folio->mapping;
+	folio_ref_add(newfolio, nr); /* add cache reference */
+	if (folio_test_swapbacked(folio)) {
+		__folio_set_swapbacked(newfolio);
+		if (folio_test_swapcache(folio)) {
+			folio_set_swapcache(newfolio);
+			newfolio->private = folio_get_private(folio);
 		}
 	} else {
-		VM_BUG_ON_PAGE(PageSwapCache(page), page);
+		VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
 	}
 
 	/* Move dirty while page refs frozen and newpage not yet exposed */
-	dirty = PageDirty(page);
+	dirty = folio_test_dirty(folio);
 	if (dirty) {
-		ClearPageDirty(page);
-		SetPageDirty(newpage);
+		folio_clear_dirty(folio);
+		folio_set_dirty(newfolio);
 	}
 
-	xas_store(&xas, newpage);
-	if (PageTransHuge(page)) {
+	xas_store(&xas, newfolio);
+	if (nr > 1) {
 		int i;
 
 		for (i = 1; i < nr; i++) {
 			xas_next(&xas);
-			xas_store(&xas, newpage);
+			xas_store(&xas, newfolio);
 		}
 	}
 
@@ -452,7 +453,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 * to one less reference.
 	 * We know this isn't the last reference.
 	 */
-	page_ref_unfreeze(page, expected_count - nr);
+	folio_ref_unfreeze(folio, expected_count - nr);
 
 	xas_unlock(&xas);
 	/* Leave irq disabled to prevent preemption while updating stats */
@@ -471,18 +472,18 @@ int migrate_page_move_mapping(struct address_space *mapping,
 		struct lruvec *old_lruvec, *new_lruvec;
 		struct mem_cgroup *memcg;
 
-		memcg = page_memcg(page);
+		memcg = folio_memcg(folio);
 		old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat);
 		new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat);
 
 		__mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr);
 		__mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr);
-		if (PageSwapBacked(page) && !PageSwapCache(page)) {
+		if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) {
 			__mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
 			__mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
 		}
 #ifdef CONFIG_SWAP
-		if (PageSwapCache(page)) {
+		if (folio_test_swapcache(folio)) {
 			__mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr);
 			__mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr);
 		}
@@ -498,11 +499,11 @@ int migrate_page_move_mapping(struct address_space *mapping,
 
 	return MIGRATEPAGE_SUCCESS;
 }
-EXPORT_SYMBOL(migrate_page_move_mapping);
+EXPORT_SYMBOL(folio_migrate_mapping);
 
 /*
  * The expected number of remaining references is the same as that
- * of migrate_page_move_mapping().
+ * of folio_migrate_mapping().
  */
 int migrate_huge_page_move_mapping(struct address_space *mapping,
 				   struct page *newpage, struct page *page)
@@ -563,7 +564,7 @@ void migrate_page_states(struct page *newpage, struct page *page)
 	if (PageMappedToDisk(page))
 		SetPageMappedToDisk(newpage);
 
-	/* Move dirty on pages not done by migrate_page_move_mapping() */
+	/* Move dirty on pages not done by folio_migrate_mapping() */
 	if (PageDirty(page))
 		SetPageDirty(newpage);
 
@@ -639,11 +640,13 @@ int migrate_page(struct address_space *mapping,
 		struct page *newpage, struct page *page,
 		enum migrate_mode mode)
 {
+	struct folio *newfolio = page_folio(newpage);
+	struct folio *folio = page_folio(page);
 	int rc;
 
-	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
+	BUG_ON(folio_test_writeback(folio));	/* Writeback must be complete */
 
-	rc = migrate_page_move_mapping(mapping, newpage, page, 0);
+	rc = folio_migrate_mapping(mapping, newfolio, folio, 0);
 
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
@@ -2387,7 +2390,7 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
  * @page: struct page to check
  *
  * Pinned pages cannot be migrated. This is the same test as in
- * migrate_page_move_mapping(), except that here we allow migration of a
+ * folio_migrate_mapping(), except that here we allow migration of a
  * ZONE_DEVICE page.
  */
 static bool migrate_vma_check_page(struct page *page)
-- 
2.30.2

[PATCH v14 11/39] mm/migrate: Add folio_migrate_flags()

[Matthew Wilcox (Oracle)]

Turn migrate_page_states() into a wrapper around folio_migrate_flags().
Also convert two functions only called from folio_migrate_flags() to
be folio-based.  ksm_migrate_page() becomes folio_migrate_ksm() and
copy_page_owner() becomes folio_copy_owner().  folio_migrate_flags()
alone shrinks by two thirds -- 1967 bytes down to 642 bytes.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/ksm.h        |  4 +-
 include/linux/migrate.h    |  1 +
 include/linux/page_owner.h |  8 ++--
 mm/folio-compat.c          |  6 +++
 mm/ksm.c                   | 31 ++++++++------
 mm/migrate.c               | 84 +++++++++++++++++++-------------------
 mm/page_owner.c            | 10 ++---
 7 files changed, 77 insertions(+), 67 deletions(-)

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 161e8164abcf..a38a5bca1ba5 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -52,7 +52,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
 			struct vm_area_struct *vma, unsigned long address);
 
 void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
-void ksm_migrate_page(struct page *newpage, struct page *oldpage);
+void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
 
 #else  /* !CONFIG_KSM */
 
@@ -83,7 +83,7 @@ static inline void rmap_walk_ksm(struct page *page,
 {
 }
 
-static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
+static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old)
 {
 }
 #endif /* CONFIG_MMU */
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index eb14495a1f46..ba0a554b3eae 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -51,6 +51,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
 extern int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page, int extra_count);
+void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
 #else
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index 719bfe5108c5..43c638c51c1f 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -12,7 +12,7 @@ extern void __reset_page_owner(struct page *page, unsigned int order);
 extern void __set_page_owner(struct page *page,
 			unsigned int order, gfp_t gfp_mask);
 extern void __split_page_owner(struct page *page, unsigned int nr);
-extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
+extern void __folio_copy_owner(struct folio *newfolio, struct folio *old);
 extern void __set_page_owner_migrate_reason(struct page *page, int reason);
 extern void __dump_page_owner(const struct page *page);
 extern void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -36,10 +36,10 @@ static inline void split_page_owner(struct page *page, unsigned int nr)
 	if (static_branch_unlikely(&page_owner_inited))
 		__split_page_owner(page, nr);
 }
-static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+static inline void folio_copy_owner(struct folio *newfolio, struct folio *old)
 {
 	if (static_branch_unlikely(&page_owner_inited))
-		__copy_page_owner(oldpage, newpage);
+		__folio_copy_owner(newfolio, old);
 }
 static inline void set_page_owner_migrate_reason(struct page *page, int reason)
 {
@@ -63,7 +63,7 @@ static inline void split_page_owner(struct page *page,
 			unsigned int order)
 {
 }
-static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio)
 {
 }
 static inline void set_page_owner_migrate_reason(struct page *page, int reason)
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index d883d964fd52..3f00ad92d1ff 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -58,4 +58,10 @@ int migrate_page_move_mapping(struct address_space *mapping,
 					page_folio(page), extra_count);
 }
 EXPORT_SYMBOL(migrate_page_move_mapping);
+
+void migrate_page_states(struct page *newpage, struct page *page)
+{
+	folio_migrate_flags(page_folio(newpage), page_folio(page));
+}
+EXPORT_SYMBOL(migrate_page_states);
 #endif
diff --git a/mm/ksm.c b/mm/ksm.c
index 23d36b59f997..3a70786906eb 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -753,7 +753,7 @@ static struct page *get_ksm_page(struct stable_node *stable_node,
 	/*
 	 * We come here from above when page->mapping or !PageSwapCache
 	 * suggests that the node is stale; but it might be under migration.
-	 * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(),
+	 * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(),
 	 * before checking whether node->kpfn has been changed.
 	 */
 	smp_rmb();
@@ -854,9 +854,14 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma,
 	return err;
 }
 
+static inline struct stable_node *folio_stable_node(struct folio *folio)
+{
+	return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL;
+}
+
 static inline struct stable_node *page_stable_node(struct page *page)
 {
-	return PageKsm(page) ? page_rmapping(page) : NULL;
+	return folio_stable_node(page_folio(page));
 }
 
 static inline void set_page_stable_node(struct page *page,
@@ -2661,26 +2666,26 @@ void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc)
 }
 
 #ifdef CONFIG_MIGRATION
-void ksm_migrate_page(struct page *newpage, struct page *oldpage)
+void folio_migrate_ksm(struct folio *newfolio, struct folio *folio)
 {
 	struct stable_node *stable_node;
 
-	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
-	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
-	VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+	VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio);
+	VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio);
 
-	stable_node = page_stable_node(newpage);
+	stable_node = folio_stable_node(folio);
 	if (stable_node) {
-		VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage);
-		stable_node->kpfn = page_to_pfn(newpage);
+		VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio);
+		stable_node->kpfn = folio_pfn(newfolio);
 		/*
-		 * newpage->mapping was set in advance; now we need smp_wmb()
+		 * newfolio->mapping was set in advance; now we need smp_wmb()
 		 * to make sure that the new stable_node->kpfn is visible
-		 * to get_ksm_page() before it can see that oldpage->mapping
-		 * has gone stale (or that PageSwapCache has been cleared).
+		 * to get_ksm_page() before it can see that folio->mapping
+		 * has gone stale (or that folio_test_swapcache has been cleared).
 		 */
 		smp_wmb();
-		set_page_stable_node(oldpage, NULL);
+		set_page_stable_node(&folio->page, NULL);
 	}
 }
 #endif /* CONFIG_MIGRATION */
diff --git a/mm/migrate.c b/mm/migrate.c
index aa4f2310c5bb..a86be2bfc9a1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -538,82 +538,80 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 }
 
 /*
- * Copy the page to its new location
+ * Copy the flags and some other ancillary information
  */
-void migrate_page_states(struct page *newpage, struct page *page)
+void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
 {
-	struct folio *folio = page_folio(page);
-	struct folio *newfolio = page_folio(newpage);
 	int cpupid;
 
-	if (PageError(page))
-		SetPageError(newpage);
-	if (PageReferenced(page))
-		SetPageReferenced(newpage);
-	if (PageUptodate(page))
-		SetPageUptodate(newpage);
-	if (TestClearPageActive(page)) {
-		VM_BUG_ON_PAGE(PageUnevictable(page), page);
-		SetPageActive(newpage);
-	} else if (TestClearPageUnevictable(page))
-		SetPageUnevictable(newpage);
-	if (PageWorkingset(page))
-		SetPageWorkingset(newpage);
-	if (PageChecked(page))
-		SetPageChecked(newpage);
-	if (PageMappedToDisk(page))
-		SetPageMappedToDisk(newpage);
+	if (folio_test_error(folio))
+		folio_set_error(newfolio);
+	if (folio_test_referenced(folio))
+		folio_set_referenced(newfolio);
+	if (folio_test_uptodate(folio))
+		folio_mark_uptodate(newfolio);
+	if (folio_test_clear_active(folio)) {
+		VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio);
+		folio_set_active(newfolio);
+	} else if (folio_test_clear_unevictable(folio))
+		folio_set_unevictable(newfolio);
+	if (folio_test_workingset(folio))
+		folio_set_workingset(newfolio);
+	if (folio_test_checked(folio))
+		folio_set_checked(newfolio);
+	if (folio_test_mappedtodisk(folio))
+		folio_set_mappedtodisk(newfolio);
 
 	/* Move dirty on pages not done by folio_migrate_mapping() */
-	if (PageDirty(page))
-		SetPageDirty(newpage);
+	if (folio_test_dirty(folio))
+		folio_set_dirty(newfolio);
 
-	if (page_is_young(page))
-		set_page_young(newpage);
-	if (page_is_idle(page))
-		set_page_idle(newpage);
+	if (folio_test_young(folio))
+		folio_set_young(newfolio);
+	if (folio_test_idle(folio))
+		folio_set_idle(newfolio);
 
 	/*
 	 * Copy NUMA information to the new page, to prevent over-eager
 	 * future migrations of this same page.
 	 */
-	cpupid = page_cpupid_xchg_last(page, -1);
-	page_cpupid_xchg_last(newpage, cpupid);
+	cpupid = page_cpupid_xchg_last(&folio->page, -1);
+	page_cpupid_xchg_last(&newfolio->page, cpupid);
 
-	ksm_migrate_page(newpage, page);
+	folio_migrate_ksm(newfolio, folio);
 	/*
 	 * Please do not reorder this without considering how mm/ksm.c's
 	 * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
 	 */
-	if (PageSwapCache(page))
-		ClearPageSwapCache(page);
-	ClearPagePrivate(page);
+	if (folio_test_swapcache(folio))
+		folio_clear_swapcache(folio);
+	folio_clear_private(folio);
 
 	/* page->private contains hugetlb specific flags */
-	if (!PageHuge(page))
-		set_page_private(page, 0);
+	if (!folio_test_hugetlb(folio))
+		folio->private = NULL;
 
 	/*
 	 * If any waiters have accumulated on the new page then
 	 * wake them up.
 	 */
-	if (PageWriteback(newpage))
-		end_page_writeback(newpage);
+	if (folio_test_writeback(newfolio))
+		folio_end_writeback(newfolio);
 
 	/*
 	 * PG_readahead shares the same bit with PG_reclaim.  The above
 	 * end_page_writeback() may clear PG_readahead mistakenly, so set the
 	 * bit after that.
 	 */
-	if (PageReadahead(page))
-		SetPageReadahead(newpage);
+	if (folio_test_readahead(folio))
+		folio_set_readahead(newfolio);
 
-	copy_page_owner(page, newpage);
+	folio_copy_owner(folio, newfolio);
 
-	if (!PageHuge(page))
+	if (!folio_test_hugetlb(folio))
 		mem_cgroup_migrate(folio, newfolio);
 }
-EXPORT_SYMBOL(migrate_page_states);
+EXPORT_SYMBOL(folio_migrate_flags);
 
 void migrate_page_copy(struct page *newpage, struct page *page)
 {
@@ -654,7 +652,7 @@ int migrate_page(struct address_space *mapping,
 	if (mode != MIGRATE_SYNC_NO_COPY)
 		migrate_page_copy(newpage, page);
 	else
-		migrate_page_states(newpage, page);
+		folio_migrate_flags(newfolio, folio);
 	return MIGRATEPAGE_SUCCESS;
 }
 EXPORT_SYMBOL(migrate_page);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index f51a57e92aa3..23bfb074ca3f 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -210,10 +210,10 @@ void __split_page_owner(struct page *page, unsigned int nr)
 	}
 }
 
-void __copy_page_owner(struct page *oldpage, struct page *newpage)
+void __folio_copy_owner(struct folio *newfolio, struct folio *old)
 {
-	struct page_ext *old_ext = lookup_page_ext(oldpage);
-	struct page_ext *new_ext = lookup_page_ext(newpage);
+	struct page_ext *old_ext = lookup_page_ext(&old->page);
+	struct page_ext *new_ext = lookup_page_ext(&newfolio->page);
 	struct page_owner *old_page_owner, *new_page_owner;
 
 	if (unlikely(!old_ext || !new_ext))
@@ -231,11 +231,11 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
 	new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
 
 	/*
-	 * We don't clear the bit on the oldpage as it's going to be freed
+	 * We don't clear the bit on the old folio as it's going to be freed
 	 * after migration. Until then, the info can be useful in case of
 	 * a bug, and the overall stats will be off a bit only temporarily.
 	 * Also, migrate_misplaced_transhuge_page() can still fail the
-	 * migration and then we want the oldpage to retain the info. But
+	 * migration and then we want the old folio to retain the info. But
 	 * in that case we also don't need to explicitly clear the info from
 	 * the new page, which will be freed.
 	 */
-- 
2.30.2

[PATCH v14 12/39] mm/migrate: Add folio_migrate_copy()

[Matthew Wilcox (Oracle)]

This is the folio equivalent of migrate_page_copy(), which is retained
as a wrapper for filesystems which are not yet converted to folios.
Also convert copy_huge_page() to folio_copy().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/migrate.h |  1 +
 include/linux/mm.h      |  2 +-
 mm/folio-compat.c       |  6 ++++++
 mm/hugetlb.c            |  2 +-
 mm/migrate.c            | 14 +++++---------
 mm/util.c               |  6 +++---
 6 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index ba0a554b3eae..6a01de9faff5 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -52,6 +52,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 extern int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page, int extra_count);
 void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
+void folio_migrate_copy(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
 #else
diff --git a/include/linux/mm.h b/include/linux/mm.h
index deb0f5efaa65..23276330ef4f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -911,7 +911,7 @@ void __put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);
-void copy_huge_page(struct page *dst, struct page *src);
+void folio_copy(struct folio *dst, struct folio *src);
 
 /*
  * Compound pages have a destructor function.  Provide a
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 3f00ad92d1ff..2ccd8f213fc4 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -64,4 +64,10 @@ void migrate_page_states(struct page *newpage, struct page *page)
 	folio_migrate_flags(page_folio(newpage), page_folio(page));
 }
 EXPORT_SYMBOL(migrate_page_states);
+
+void migrate_page_copy(struct page *newpage, struct page *page)
+{
+	folio_migrate_copy(page_folio(newpage), page_folio(page));
+}
+EXPORT_SYMBOL(migrate_page_copy);
 #endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 924553aa8f78..b46f9d09aa94 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5200,7 +5200,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 			*pagep = NULL;
 			goto out;
 		}
-		copy_huge_page(page, *pagep);
+		folio_copy(page_folio(page), page_folio(*pagep));
 		put_page(*pagep);
 		*pagep = NULL;
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index a86be2bfc9a1..36cdae0a1235 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -613,16 +613,12 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
 }
 EXPORT_SYMBOL(folio_migrate_flags);
 
-void migrate_page_copy(struct page *newpage, struct page *page)
+void folio_migrate_copy(struct folio *newfolio, struct folio *folio)
 {
-	if (PageHuge(page) || PageTransHuge(page))
-		copy_huge_page(newpage, page);
-	else
-		copy_highpage(newpage, page);
-
-	migrate_page_states(newpage, page);
+	folio_copy(newfolio, folio);
+	folio_migrate_flags(newfolio, folio);
 }
-EXPORT_SYMBOL(migrate_page_copy);
+EXPORT_SYMBOL(folio_migrate_copy);
 
 /************************************************************
  *                    Migration functions
@@ -650,7 +646,7 @@ int migrate_page(struct address_space *mapping,
 		return rc;
 
 	if (mode != MIGRATE_SYNC_NO_COPY)
-		migrate_page_copy(newpage, page);
+		folio_migrate_copy(newfolio, folio);
 	else
 		folio_migrate_flags(newfolio, folio);
 	return MIGRATEPAGE_SUCCESS;
diff --git a/mm/util.c b/mm/util.c
index 149537120a91..904a75612307 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -728,13 +728,13 @@ int __page_mapcount(struct page *page)
 }
 EXPORT_SYMBOL_GPL(__page_mapcount);
 
-void copy_huge_page(struct page *dst, struct page *src)
+void folio_copy(struct folio *dst, struct folio *src)
 {
-	unsigned i, nr = compound_nr(src);
+	unsigned i, nr = folio_nr_pages(src);
 
 	for (i = 0; i < nr; i++) {
 		cond_resched();
-		copy_highpage(nth_page(dst, i), nth_page(src, i));
+		copy_highpage(folio_page(dst, i), folio_page(src, i));
 	}
 }
 
-- 
2.30.2

[PATCH v14 13/39] mm/writeback: Rename __add_wb_stat() to wb_stat_mod()

[Matthew Wilcox (Oracle)]

Make this look like the newly renamed vmstat functions.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/backing-dev.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 44df4fcef65c..a852876bb6e2 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -64,7 +64,7 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi)
 	return atomic_long_read(&bdi->tot_write_bandwidth);
 }
 
-static inline void __add_wb_stat(struct bdi_writeback *wb,
+static inline void wb_stat_mod(struct bdi_writeback *wb,
 				 enum wb_stat_item item, s64 amount)
 {
 	percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
@@ -72,12 +72,12 @@ static inline void __add_wb_stat(struct bdi_writeback *wb,
 
 static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	__add_wb_stat(wb, item, 1);
+	wb_stat_mod(wb, item, 1);
 }
 
 static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	__add_wb_stat(wb, item, -1);
+	wb_stat_mod(wb, item, -1);
 }
 
 static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
-- 
2.30.2

[PATCH v14 14/39] flex_proportions: Allow N events instead of 1

[Matthew Wilcox (Oracle)]

When batching events (such as writing back N pages in a single I/O), it
is better to do one flex_proportion operation instead of N.  There is
only one caller of __fprop_inc_percpu_max(), and it's the one we're
going to change in the next patch, so rename it instead of adding a
compatibility wrapper.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 include/linux/flex_proportions.h |  9 +++++----
 lib/flex_proportions.c           | 28 +++++++++++++++++++---------
 mm/page-writeback.c              |  4 ++--
 3 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h
index c12df59d3f5f..3e378b1fb0bc 100644
--- a/include/linux/flex_proportions.h
+++ b/include/linux/flex_proportions.h
@@ -83,9 +83,10 @@ struct fprop_local_percpu {
 
 int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp);
 void fprop_local_destroy_percpu(struct fprop_local_percpu *pl);
-void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl);
-void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl,
-			    int max_frac);
+void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl,
+		long nr);
+void __fprop_add_percpu_max(struct fprop_global *p,
+		struct fprop_local_percpu *pl, int max_frac, long nr);
 void fprop_fraction_percpu(struct fprop_global *p,
 	struct fprop_local_percpu *pl, unsigned long *numerator,
 	unsigned long *denominator);
@@ -96,7 +97,7 @@ void fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__fprop_inc_percpu(p, pl);
+	__fprop_add_percpu(p, pl, 1);
 	local_irq_restore(flags);
 }
 
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
index 451543937524..53e7eb1dd76c 100644
--- a/lib/flex_proportions.c
+++ b/lib/flex_proportions.c
@@ -217,11 +217,12 @@ static void fprop_reflect_period_percpu(struct fprop_global *p,
 }
 
 /* Event of type pl happened */
-void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
+void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl,
+		long nr)
 {
 	fprop_reflect_period_percpu(p, pl);
-	percpu_counter_add_batch(&pl->events, 1, PROP_BATCH);
-	percpu_counter_add(&p->events, 1);
+	percpu_counter_add_batch(&pl->events, nr, PROP_BATCH);
+	percpu_counter_add(&p->events, nr);
 }
 
 void fprop_fraction_percpu(struct fprop_global *p,
@@ -253,20 +254,29 @@ void fprop_fraction_percpu(struct fprop_global *p,
 }
 
 /*
- * Like __fprop_inc_percpu() except that event is counted only if the given
+ * Like __fprop_add_percpu() except that event is counted only if the given
  * type has fraction smaller than @max_frac/FPROP_FRAC_BASE
  */
-void __fprop_inc_percpu_max(struct fprop_global *p,
-			    struct fprop_local_percpu *pl, int max_frac)
+void __fprop_add_percpu_max(struct fprop_global *p,
+		struct fprop_local_percpu *pl, int max_frac, long nr)
 {
 	if (unlikely(max_frac < FPROP_FRAC_BASE)) {
 		unsigned long numerator, denominator;
+		s64 tmp;
 
 		fprop_fraction_percpu(p, pl, &numerator, &denominator);
-		if (numerator >
-		    (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
+		/* Adding 'nr' to fraction exceeds max_frac/FPROP_FRAC_BASE? */
+		tmp = (u64)denominator * max_frac -
+					((u64)numerator << FPROP_FRAC_SHIFT);
+		if (tmp < 0) {
+			/* Maximum fraction already exceeded? */
 			return;
+		} else if (tmp < nr * (FPROP_FRAC_BASE - max_frac)) {
+			/* Add just enough for the fraction to saturate */
+			nr = div_u64(tmp + FPROP_FRAC_BASE - max_frac - 1,
+					FPROP_FRAC_BASE - max_frac);
+		}
 	}
 
-	__fprop_inc_percpu(p, pl);
+	__fprop_add_percpu(p, pl, nr);
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b34278d05395..f55f2ebdd9a9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -566,8 +566,8 @@ static void wb_domain_writeout_inc(struct wb_domain *dom,
 				   struct fprop_local_percpu *completions,
 				   unsigned int max_prop_frac)
 {
-	__fprop_inc_percpu_max(&dom->completions, completions,
-			       max_prop_frac);
+	__fprop_add_percpu_max(&dom->completions, completions,
+			       max_prop_frac, 1);
 	/* First event after period switching was turned off? */
 	if (unlikely(!dom->period_time)) {
 		/*
-- 
2.30.2

[PATCH v14 15/39] mm/writeback: Change __wb_writeout_inc() to __wb_writeout_add()

[Matthew Wilcox (Oracle)]

Allow for accounting N pages at once instead of one page at a time.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 mm/page-writeback.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f55f2ebdd9a9..e542ea37d605 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -562,12 +562,12 @@ static unsigned long wp_next_time(unsigned long cur_time)
 	return cur_time;
 }
 
-static void wb_domain_writeout_inc(struct wb_domain *dom,
+static void wb_domain_writeout_add(struct wb_domain *dom,
 				   struct fprop_local_percpu *completions,
-				   unsigned int max_prop_frac)
+				   unsigned int max_prop_frac, long nr)
 {
 	__fprop_add_percpu_max(&dom->completions, completions,
-			       max_prop_frac, 1);
+			       max_prop_frac, nr);
 	/* First event after period switching was turned off? */
 	if (unlikely(!dom->period_time)) {
 		/*
@@ -585,18 +585,18 @@ static void wb_domain_writeout_inc(struct wb_domain *dom,
  * Increment @wb's writeout completion count and the global writeout
  * completion count. Called from test_clear_page_writeback().
  */
-static inline void __wb_writeout_inc(struct bdi_writeback *wb)
+static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr)
 {
 	struct wb_domain *cgdom;
 
-	inc_wb_stat(wb, WB_WRITTEN);
-	wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
-			       wb->bdi->max_prop_frac);
+	wb_stat_mod(wb, WB_WRITTEN, nr);
+	wb_domain_writeout_add(&global_wb_domain, &wb->completions,
+			       wb->bdi->max_prop_frac, nr);
 
 	cgdom = mem_cgroup_wb_domain(wb);
 	if (cgdom)
-		wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb),
-				       wb->bdi->max_prop_frac);
+		wb_domain_writeout_add(cgdom, wb_memcg_completions(wb),
+				       wb->bdi->max_prop_frac, nr);
 }
 
 void wb_writeout_inc(struct bdi_writeback *wb)
@@ -604,7 +604,7 @@ void wb_writeout_inc(struct bdi_writeback *wb)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__wb_writeout_inc(wb);
+	__wb_writeout_add(wb, 1);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(wb_writeout_inc);
@@ -2751,7 +2751,7 @@ int test_clear_page_writeback(struct page *page)
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
 				dec_wb_stat(wb, WB_WRITEBACK);
-				__wb_writeout_inc(wb);
+				__wb_writeout_add(wb, 1);
 			}
 		}
 
-- 
2.30.2

[PATCH v14 16/39] mm/writeback: Add __folio_end_writeback()

[Matthew Wilcox (Oracle)]

test_clear_page_writeback() is actually an mm-internal function, although
it's named as if it's a pagecache function.  Move it to mm/internal.h,
rename it to __folio_end_writeback() and change the return type to bool.

The conversion from page to folio is mostly about accounting the number
of pages being written back, although it does eliminate a couple of
calls to compound_head().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/page-flags.h |  1 -
 mm/filemap.c               |  2 +-
 mm/internal.h              |  1 +
 mm/page-writeback.c        | 29 +++++++++++++++--------------
 4 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index ddb660688086..6f9d1f26b1ef 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -655,7 +655,6 @@ static __always_inline void SetPageUptodate(struct page *page)
 
 CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
 
-int test_clear_page_writeback(struct page *page);
 int __test_set_page_writeback(struct page *page, bool keep_write);
 
 #define test_set_page_writeback(page)			\
diff --git a/mm/filemap.c b/mm/filemap.c
index 5c4e3185ecb3..a74c69a938ab 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1535,7 +1535,7 @@ void folio_end_writeback(struct folio *folio)
 	 * reused before the folio_wake().
 	 */
 	folio_get(folio);
-	if (!test_clear_page_writeback(&folio->page))
+	if (!__folio_end_writeback(folio))
 		BUG();
 
 	smp_mb__after_atomic();
diff --git a/mm/internal.h b/mm/internal.h
index fa31a7f0ed79..08e8a28994d1 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -43,6 +43,7 @@ static inline void *folio_raw_mapping(struct folio *folio)
 
 vm_fault_t do_swap_page(struct vm_fault *vmf);
 void folio_rotate_reclaimable(struct folio *folio);
+bool __folio_end_writeback(struct folio *folio);
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e542ea37d605..8d5d7921b157 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -583,7 +583,7 @@ static void wb_domain_writeout_add(struct wb_domain *dom,
 
 /*
  * Increment @wb's writeout completion count and the global writeout
- * completion count. Called from test_clear_page_writeback().
+ * completion count. Called from __folio_end_writeback().
  */
 static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr)
 {
@@ -2731,27 +2731,28 @@ int clear_page_dirty_for_io(struct page *page)
 }
 EXPORT_SYMBOL(clear_page_dirty_for_io);
 
-int test_clear_page_writeback(struct page *page)
+bool __folio_end_writeback(struct folio *folio)
 {
-	struct address_space *mapping = page_mapping(page);
-	int ret;
+	long nr = folio_nr_pages(folio);
+	struct address_space *mapping = folio_mapping(folio);
+	bool ret;
 
-	lock_page_memcg(page);
+	folio_memcg_lock(folio);
 	if (mapping && mapping_use_writeback_tags(mapping)) {
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
 		unsigned long flags;
 
 		xa_lock_irqsave(&mapping->i_pages, flags);
-		ret = TestClearPageWriteback(page);
+		ret = folio_test_clear_writeback(folio);
 		if (ret) {
-			__xa_clear_mark(&mapping->i_pages, page_index(page),
+			__xa_clear_mark(&mapping->i_pages, folio_index(folio),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
-				dec_wb_stat(wb, WB_WRITEBACK);
-				__wb_writeout_add(wb, 1);
+				wb_stat_mod(wb, WB_WRITEBACK, -nr);
+				__wb_writeout_add(wb, nr);
 			}
 		}
 
@@ -2761,14 +2762,14 @@ int test_clear_page_writeback(struct page *page)
 
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 	} else {
-		ret = TestClearPageWriteback(page);
+		ret = folio_test_clear_writeback(folio);
 	}
 	if (ret) {
-		dec_lruvec_page_state(page, NR_WRITEBACK);
-		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
-		inc_node_page_state(page, NR_WRITTEN);
+		lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr);
+		zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+		node_stat_mod_folio(folio, NR_WRITTEN, nr);
 	}
-	unlock_page_memcg(page);
+	folio_memcg_unlock(folio);
 	return ret;
 }
 
-- 
2.30.2

[PATCH v14 17/39] mm/writeback: Add folio_start_writeback()

[Matthew Wilcox (Oracle)]

Rename set_page_writeback() to folio_start_writeback() to match
folio_end_writeback().  Do not bother with wrappers that return void;
callers are perfectly capable of ignoring return values.

Add wrappers for set_page_writeback(), set_page_writeback_keepwrite() and
test_set_page_writeback() for compatibililty with existing filesystems.
The main advantage of this patch is getting the statistics right,
although it does eliminate a couple of calls to compound_head().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/page-flags.h | 19 +++++++++---------
 mm/folio-compat.c          |  6 ++++++
 mm/page-writeback.c        | 40 ++++++++++++++++++++------------------
 3 files changed, 37 insertions(+), 28 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6f9d1f26b1ef..54c4af35c628 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -655,21 +655,22 @@ static __always_inline void SetPageUptodate(struct page *page)
 
 CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
 
-int __test_set_page_writeback(struct page *page, bool keep_write);
+bool __folio_start_writeback(struct folio *folio, bool keep_write);
+bool set_page_writeback(struct page *page);
 
-#define test_set_page_writeback(page)			\
-	__test_set_page_writeback(page, false)
-#define test_set_page_writeback_keepwrite(page)	\
-	__test_set_page_writeback(page, true)
+#define folio_start_writeback(folio)			\
+	__folio_start_writeback(folio, false)
+#define folio_start_writeback_keepwrite(folio)	\
+	__folio_start_writeback(folio, true)
 
-static inline void set_page_writeback(struct page *page)
+static inline void set_page_writeback_keepwrite(struct page *page)
 {
-	test_set_page_writeback(page);
+	folio_start_writeback_keepwrite(page_folio(page));
 }
 
-static inline void set_page_writeback_keepwrite(struct page *page)
+static inline bool test_set_page_writeback(struct page *page)
 {
-	test_set_page_writeback_keepwrite(page);
+	return set_page_writeback(page);
 }
 
 __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 2ccd8f213fc4..10ce5582d869 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -71,3 +71,9 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 }
 EXPORT_SYMBOL(migrate_page_copy);
 #endif
+
+bool set_page_writeback(struct page *page)
+{
+	return folio_start_writeback(page_folio(page));
+}
+EXPORT_SYMBOL(set_page_writeback);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 8d5d7921b157..0336273154fb 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2773,21 +2773,23 @@ bool __folio_end_writeback(struct folio *folio)
 	return ret;
 }
 
-int __test_set_page_writeback(struct page *page, bool keep_write)
+bool __folio_start_writeback(struct folio *folio, bool keep_write)
 {
-	struct address_space *mapping = page_mapping(page);
-	int ret, access_ret;
+	long nr = folio_nr_pages(folio);
+	struct address_space *mapping = folio_mapping(folio);
+	bool ret;
+	int access_ret;
 
-	lock_page_memcg(page);
+	folio_memcg_lock(folio);
 	if (mapping && mapping_use_writeback_tags(mapping)) {
-		XA_STATE(xas, &mapping->i_pages, page_index(page));
+		XA_STATE(xas, &mapping->i_pages, folio_index(folio));
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
 		unsigned long flags;
 
 		xas_lock_irqsave(&xas, flags);
 		xas_load(&xas);
-		ret = TestSetPageWriteback(page);
+		ret = folio_test_set_writeback(folio);
 		if (!ret) {
 			bool on_wblist;
 
@@ -2796,40 +2798,40 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 
 			xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
 			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT)
-				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
+				wb_stat_mod(inode_to_wb(inode), WB_WRITEBACK,
+						nr);
 
 			/*
-			 * We can come through here when swapping anonymous
-			 * pages, so we don't necessarily have an inode to track
-			 * for sync.
+			 * We can come through here when swapping
+			 * anonymous folios, so we don't necessarily
+			 * have an inode to track for sync.
 			 */
 			if (mapping->host && !on_wblist)
 				sb_mark_inode_writeback(mapping->host);
 		}
-		if (!PageDirty(page))
+		if (!folio_test_dirty(folio))
 			xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
 		if (!keep_write)
 			xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
 		xas_unlock_irqrestore(&xas, flags);
 	} else {
-		ret = TestSetPageWriteback(page);
+		ret = folio_test_set_writeback(folio);
 	}
 	if (!ret) {
-		inc_lruvec_page_state(page, NR_WRITEBACK);
-		inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
+		lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
+		zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
 	}
-	unlock_page_memcg(page);
-	access_ret = arch_make_page_accessible(page);
+	folio_memcg_unlock(folio);
+	access_ret = arch_make_folio_accessible(folio);
 	/*
 	 * If writeback has been triggered on a page that cannot be made
 	 * accessible, it is too late to recover here.
 	 */
-	VM_BUG_ON_PAGE(access_ret != 0, page);
+	VM_BUG_ON_FOLIO(access_ret != 0, folio);
 
 	return ret;
-
 }
-EXPORT_SYMBOL(__test_set_page_writeback);
+EXPORT_SYMBOL(__folio_start_writeback);
 
 /**
  * folio_wait_writeback - Wait for a folio to finish writeback.
-- 
2.30.2

[PATCH v14 18/39] mm/writeback: Add folio_mark_dirty()

[Matthew Wilcox (Oracle)]

Reimplement set_page_dirty() as a wrapper around folio_mark_dirty().
There is no change to filesystems as they were already being called
with the compound_head of the page being marked dirty.  We avoid
several calls to compound_head(), both statically (through
using folio_test_dirty() instead of PageDirty() and dynamically by
calling folio_mapping() instead of page_mapping().

Also return bool instead of int to show the range of values actually
returned, and add kernel-doc.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/mm.h  |  3 ++-
 mm/folio-compat.c   |  6 ++++++
 mm/page-writeback.c | 35 +++++++++++++++++++----------------
 3 files changed, 27 insertions(+), 17 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 23276330ef4f..43c1b5731c7f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2005,7 +2005,8 @@ int redirty_page_for_writepage(struct writeback_control *wbc,
 				struct page *page);
 void account_page_cleaned(struct page *page, struct address_space *mapping,
 			  struct bdi_writeback *wb);
-int set_page_dirty(struct page *page);
+bool folio_mark_dirty(struct folio *folio);
+bool set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 void __cancel_dirty_page(struct page *page);
 static inline void cancel_dirty_page(struct page *page)
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 10ce5582d869..2c2b3917b5dc 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -77,3 +77,9 @@ bool set_page_writeback(struct page *page)
 	return folio_start_writeback(page_folio(page));
 }
 EXPORT_SYMBOL(set_page_writeback);
+
+bool set_page_dirty(struct page *page)
+{
+	return folio_mark_dirty(page_folio(page));
+}
+EXPORT_SYMBOL(set_page_dirty);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0336273154fb..d7c0cad6a57f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2564,18 +2564,21 @@ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
 }
 EXPORT_SYMBOL(redirty_page_for_writepage);
 
-/*
- * Dirty a page.
+/**
+ * folio_mark_dirty - Mark a folio as being modified.
+ * @folio: The folio.
+ *
+ * For folios with a mapping this should be done under the page lock
+ * for the benefit of asynchronous memory errors who prefer a consistent
+ * dirty state. This rule can be broken in some special cases,
+ * but should be better not to.
  *
- * For pages with a mapping this should be done under the page lock for the
- * benefit of asynchronous memory errors who prefer a consistent dirty state.
- * This rule can be broken in some special cases, but should be better not to.
+ * Return: True if the folio was newly dirtied, false if it was already dirty.
  */
-int set_page_dirty(struct page *page)
+bool folio_mark_dirty(struct folio *folio)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = folio_mapping(folio);
 
-	page = compound_head(page);
 	if (likely(mapping)) {
 		/*
 		 * readahead/lru_deactivate_page could remain
@@ -2587,17 +2590,17 @@ int set_page_dirty(struct page *page)
 		 * it will confuse readahead and make it restart the size rampup
 		 * process. But it's a trivial problem.
 		 */
-		if (PageReclaim(page))
-			ClearPageReclaim(page);
-		return mapping->a_ops->set_page_dirty(page);
+		if (folio_test_reclaim(folio))
+			folio_clear_reclaim(folio);
+		return mapping->a_ops->set_page_dirty(&folio->page);
 	}
-	if (!PageDirty(page)) {
-		if (!TestSetPageDirty(page))
-			return 1;
+	if (!folio_test_dirty(folio)) {
+		if (!folio_test_set_dirty(folio))
+			return true;
 	}
-	return 0;
+	return false;
 }
-EXPORT_SYMBOL(set_page_dirty);
+EXPORT_SYMBOL(folio_mark_dirty);
 
 /*
  * set_page_dirty() is racy if the caller has no reference against
-- 
2.30.2

[PATCH v14 19/39] mm/writeback: Add __folio_mark_dirty()

[Matthew Wilcox (Oracle)]

Turn __set_page_dirty() into a wrapper around __folio_mark_dirty().
Convert account_page_dirtied() into folio_account_dirtied() and account
the number of pages in the folio to support multi-page folios.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/memcontrol.h |  5 ++---
 include/linux/pagemap.h    |  7 ++++++-
 mm/page-writeback.c        | 41 +++++++++++++++++++-------------------
 3 files changed, 29 insertions(+), 24 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2dd660185bb3..c20adc22ea24 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1574,10 +1574,9 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
 					     struct bdi_writeback *wb);
 
-static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
 						  struct bdi_writeback *wb)
 {
-	struct folio *folio = page_folio(page);
 	if (mem_cgroup_disabled())
 		return;
 
@@ -1602,7 +1601,7 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
 {
 }
 
-static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
 						  struct bdi_writeback *wb)
 {
 }
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 08f40e004d97..3d88c17fedc9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -773,8 +773,13 @@ void end_page_writeback(struct page *page);
 void folio_end_writeback(struct folio *folio);
 void wait_for_stable_page(struct page *page);
 void folio_wait_stable(struct folio *folio);
+void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn);
+static inline void __set_page_dirty(struct page *page,
+		struct address_space *mapping, int warn)
+{
+	__folio_mark_dirty(page_folio(page), mapping, warn);
+}
 
-void __set_page_dirty(struct page *, struct address_space *, int warn);
 int __set_page_dirty_nobuffers(struct page *page);
 int __set_page_dirty_no_writeback(struct page *page);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d7c0cad6a57f..3e02c86eb445 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2421,29 +2421,30 @@ EXPORT_SYMBOL(__set_page_dirty_no_writeback);
  *
  * NOTE: This relies on being atomic wrt interrupts.
  */
-static void account_page_dirtied(struct page *page,
+static void folio_account_dirtied(struct folio *folio,
 		struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 
-	trace_writeback_dirty_page(page, mapping);
+	trace_writeback_dirty_page(&folio->page, mapping);
 
 	if (mapping_can_writeback(mapping)) {
 		struct bdi_writeback *wb;
+		long nr = folio_nr_pages(folio);
 
-		inode_attach_wb(inode, page);
+		inode_attach_wb(inode, &folio->page);
 		wb = inode_to_wb(inode);
 
-		__inc_lruvec_page_state(page, NR_FILE_DIRTY);
-		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
-		__inc_node_page_state(page, NR_DIRTIED);
-		inc_wb_stat(wb, WB_RECLAIMABLE);
-		inc_wb_stat(wb, WB_DIRTIED);
-		task_io_account_write(PAGE_SIZE);
-		current->nr_dirtied++;
-		__this_cpu_inc(bdp_ratelimits);
+		__lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr);
+		__zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
+		__node_stat_mod_folio(folio, NR_DIRTIED, nr);
+		wb_stat_mod(wb, WB_RECLAIMABLE, nr);
+		wb_stat_mod(wb, WB_DIRTIED, nr);
+		task_io_account_write(nr * PAGE_SIZE);
+		current->nr_dirtied += nr;
+		__this_cpu_add(bdp_ratelimits, nr);
 
-		mem_cgroup_track_foreign_dirty(page, wb);
+		mem_cgroup_track_foreign_dirty(folio, wb);
 	}
 }
 
@@ -2464,24 +2465,24 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
 }
 
 /*
- * Mark the page dirty, and set it dirty in the page cache, and mark the inode
- * dirty.
+ * Mark the folio dirty, and set it dirty in the page cache, and mark
+ * the inode dirty.
  *
- * If warn is true, then emit a warning if the page is not uptodate and has
+ * If warn is true, then emit a warning if the folio is not uptodate and has
  * not been truncated.
  *
  * The caller must hold lock_page_memcg().
  */
-void __set_page_dirty(struct page *page, struct address_space *mapping,
+void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
 			     int warn)
 {
 	unsigned long flags;
 
 	xa_lock_irqsave(&mapping->i_pages, flags);
-	if (page->mapping) {	/* Race with truncate? */
-		WARN_ON_ONCE(warn && !PageUptodate(page));
-		account_page_dirtied(page, mapping);
-		__xa_set_mark(&mapping->i_pages, page_index(page),
+	if (folio->mapping) {	/* Race with truncate? */
+		WARN_ON_ONCE(warn && !folio_test_uptodate(folio));
+		folio_account_dirtied(folio, mapping);
+		__xa_set_mark(&mapping->i_pages, folio_index(folio),
 				PAGECACHE_TAG_DIRTY);
 	}
 	xa_unlock_irqrestore(&mapping->i_pages, flags);
-- 
2.30.2

[PATCH v14 20/39] mm/writeback: Convert tracing writeback_page_template to folios

[Matthew Wilcox (Oracle)]

Rename writeback_dirty_page() to writeback_dirty_folio() and
wait_on_page_writeback() to folio_wait_writeback().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/trace/events/writeback.h | 20 ++++++++++----------
 mm/page-writeback.c              |  6 +++---
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 297871ca0004..7dccb66474f7 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -52,11 +52,11 @@ WB_WORK_REASON
 
 struct wb_writeback_work;
 
-DECLARE_EVENT_CLASS(writeback_page_template,
+DECLARE_EVENT_CLASS(writeback_folio_template,
 
-	TP_PROTO(struct page *page, struct address_space *mapping),
+	TP_PROTO(struct folio *folio, struct address_space *mapping),
 
-	TP_ARGS(page, mapping),
+	TP_ARGS(folio, mapping),
 
 	TP_STRUCT__entry (
 		__array(char, name, 32)
@@ -69,7 +69,7 @@ DECLARE_EVENT_CLASS(writeback_page_template,
 			    bdi_dev_name(mapping ? inode_to_bdi(mapping->host) :
 					 NULL), 32);
 		__entry->ino = mapping ? mapping->host->i_ino : 0;
-		__entry->index = page->index;
+		__entry->index = folio->index;
 	),
 
 	TP_printk("bdi %s: ino=%lu index=%lu",
@@ -79,18 +79,18 @@ DECLARE_EVENT_CLASS(writeback_page_template,
 	)
 );
 
-DEFINE_EVENT(writeback_page_template, writeback_dirty_page,
+DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio,
 
-	TP_PROTO(struct page *page, struct address_space *mapping),
+	TP_PROTO(struct folio *folio, struct address_space *mapping),
 
-	TP_ARGS(page, mapping)
+	TP_ARGS(folio, mapping)
 );
 
-DEFINE_EVENT(writeback_page_template, wait_on_page_writeback,
+DEFINE_EVENT(writeback_folio_template, folio_wait_writeback,
 
-	TP_PROTO(struct page *page, struct address_space *mapping),
+	TP_PROTO(struct folio *folio, struct address_space *mapping),
 
-	TP_ARGS(page, mapping)
+	TP_ARGS(folio, mapping)
 );
 
 DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3e02c86eb445..2dc410b110ff 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2426,7 +2426,7 @@ static void folio_account_dirtied(struct folio *folio,
 {
 	struct inode *inode = mapping->host;
 
-	trace_writeback_dirty_page(&folio->page, mapping);
+	trace_writeback_dirty_folio(folio, mapping);
 
 	if (mapping_can_writeback(mapping)) {
 		struct bdi_writeback *wb;
@@ -2852,7 +2852,7 @@ EXPORT_SYMBOL(__folio_start_writeback);
 void folio_wait_writeback(struct folio *folio)
 {
 	while (folio_test_writeback(folio)) {
-		trace_wait_on_page_writeback(&folio->page, folio_mapping(folio));
+		trace_folio_wait_writeback(folio, folio_mapping(folio));
 		folio_wait_bit(folio, PG_writeback);
 	}
 }
@@ -2874,7 +2874,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback);
 int folio_wait_writeback_killable(struct folio *folio)
 {
 	while (folio_test_writeback(folio)) {
-		trace_wait_on_page_writeback(&folio->page, folio_mapping(folio));
+		trace_folio_wait_writeback(folio, folio_mapping(folio));
 		if (folio_wait_bit_killable(folio, PG_writeback))
 			return -EINTR;
 	}
-- 
2.30.2

[PATCH v14 21/39] mm/writeback: Add filemap_dirty_folio()

[Matthew Wilcox (Oracle)]

Reimplement __set_page_dirty_nobuffers() as a wrapper around
filemap_dirty_folio().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/writeback.h |  1 +
 mm/folio-compat.c         |  6 ++++
 mm/page-writeback.c       | 60 ++++++++++++++++++++-------------------
 3 files changed, 38 insertions(+), 29 deletions(-)

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 667e86cfbdcf..eda9cc778ef6 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -398,6 +398,7 @@ void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
 
+bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio);
 void account_page_redirty(struct page *page);
 
 void sb_mark_inode_writeback(struct inode *inode);
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 2c2b3917b5dc..dad962b920e5 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -83,3 +83,9 @@ bool set_page_dirty(struct page *page)
 	return folio_mark_dirty(page_folio(page));
 }
 EXPORT_SYMBOL(set_page_dirty);
+
+int __set_page_dirty_nobuffers(struct page *page)
+{
+	return filemap_dirty_folio(page_mapping(page), page_folio(page));
+}
+EXPORT_SYMBOL(__set_page_dirty_nobuffers);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2dc410b110ff..bd97c461d499 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2488,41 +2488,43 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
 	xa_unlock_irqrestore(&mapping->i_pages, flags);
 }
 
-/*
- * For address_spaces which do not use buffers.  Just tag the page as dirty in
- * the xarray.
- *
- * This is also used when a single buffer is being dirtied: we want to set the
- * page dirty in that case, but not all the buffers.  This is a "bottom-up"
- * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
- *
- * The caller must ensure this doesn't race with truncation.  Most will simply
- * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
- * the pte lock held, which also locks out truncation.
+/**
+ * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads.
+ * @mapping: Address space this folio belongs to.
+ * @folio: Folio to be marked as dirty.
+ *
+ * Filesystems which do not use buffer heads should call this function
+ * from their set_page_dirty address space operation.  It ignores the
+ * contents of folio_get_private(), so if the filesystem marks individual
+ * blocks as dirty, the filesystem should handle that itself.
+ *
+ * This is also sometimes used by filesystems which use buffer_heads when
+ * a single buffer is being dirtied: we want to set the folio dirty in
+ * that case, but not all the buffers.  This is a "bottom-up" dirtying,
+ * whereas __set_page_dirty_buffers() is a "top-down" dirtying.
+ *
+ * The caller must ensure this doesn't race with truncation.  Most will
+ * simply hold the folio lock, but e.g. zap_pte_range() calls with the
+ * folio mapped and the pte lock held, which also locks out truncation.
  */
-int __set_page_dirty_nobuffers(struct page *page)
+bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio)
 {
-	lock_page_memcg(page);
-	if (!TestSetPageDirty(page)) {
-		struct address_space *mapping = page_mapping(page);
+	folio_memcg_lock(folio);
+	if (folio_test_set_dirty(folio)) {
+		folio_memcg_unlock(folio);
+		return false;
+	}
 
-		if (!mapping) {
-			unlock_page_memcg(page);
-			return 1;
-		}
-		__set_page_dirty(page, mapping, !PagePrivate(page));
-		unlock_page_memcg(page);
+	__folio_mark_dirty(folio, mapping, !folio_test_private(folio));
+	folio_memcg_unlock(folio);
 
-		if (mapping->host) {
-			/* !PageAnon && !swapper_space */
-			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-		}
-		return 1;
+	if (mapping->host) {
+		/* !PageAnon && !swapper_space */
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
-	unlock_page_memcg(page);
-	return 0;
+	return true;
 }
-EXPORT_SYMBOL(__set_page_dirty_nobuffers);
+EXPORT_SYMBOL(filemap_dirty_folio);
 
 /*
  * Call this whenever redirtying a page, to de-account the dirty counters
-- 
2.30.2

[PATCH v14 22/39] mm/writeback: Add folio_account_cleaned()

[Matthew Wilcox (Oracle)]

Get the statistics right; compound pages were being accounted as a
single page.  This didn't matter before now as no filesystem which
supported compound pages did writeback.  Also move the declaration
to filemap.h since this is part of the page cache.  Add a wrapper for
account_page_cleaned().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/mm.h      |  3 ---
 include/linux/pagemap.h |  7 +++++++
 mm/page-writeback.c     | 11 ++++++-----
 3 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 43c1b5731c7f..481019481d10 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -39,7 +39,6 @@ struct anon_vma_chain;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
-struct bdi_writeback;
 struct pt_regs;
 
 extern int sysctl_page_lock_unfairness;
@@ -2003,8 +2002,6 @@ extern void do_invalidatepage(struct page *page, unsigned int offset,
 
 int redirty_page_for_writepage(struct writeback_control *wbc,
 				struct page *page);
-void account_page_cleaned(struct page *page, struct address_space *mapping,
-			  struct bdi_writeback *wb);
 bool folio_mark_dirty(struct folio *folio);
 bool set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 3d88c17fedc9..665ba6a67385 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -779,6 +779,13 @@ static inline void __set_page_dirty(struct page *page,
 {
 	__folio_mark_dirty(page_folio(page), mapping, warn);
 }
+void folio_account_cleaned(struct folio *folio, struct address_space *mapping,
+			  struct bdi_writeback *wb);
+static inline void account_page_cleaned(struct page *page,
+		struct address_space *mapping, struct bdi_writeback *wb)
+{
+	return folio_account_cleaned(page_folio(page), mapping, wb);
+}
 
 int __set_page_dirty_nobuffers(struct page *page);
 int __set_page_dirty_no_writeback(struct page *page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bd97c461d499..792a83bd3917 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2453,14 +2453,15 @@ static void folio_account_dirtied(struct folio *folio,
  *
  * Caller must hold lock_page_memcg().
  */
-void account_page_cleaned(struct page *page, struct address_space *mapping,
+void folio_account_cleaned(struct folio *folio, struct address_space *mapping,
 			  struct bdi_writeback *wb)
 {
 	if (mapping_can_writeback(mapping)) {
-		dec_lruvec_page_state(page, NR_FILE_DIRTY);
-		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
-		dec_wb_stat(wb, WB_RECLAIMABLE);
-		task_io_account_cancelled_write(PAGE_SIZE);
+		long nr = folio_nr_pages(folio);
+		lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+		zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+		wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
+		task_io_account_cancelled_write(folio_size(folio));
 	}
 }
 
-- 
2.30.2

[PATCH v14 23/39] mm/writeback: Add folio_cancel_dirty()

[Matthew Wilcox (Oracle)]

Turn __cancel_dirty_page() into __folio_cancel_dirty() and add wrappers.
Move the prototypes into pagemap.h since this is page cache functionality.
Saves 44 bytes of kernel text in total; 33 bytes from __folio_cancel_dirty
and 11 from two callers of cancel_dirty_page().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/mm.h      |  7 -------
 include/linux/pagemap.h | 11 +++++++++++
 mm/page-writeback.c     | 16 ++++++++--------
 3 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 481019481d10..07ba22351d15 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2005,13 +2005,6 @@ int redirty_page_for_writepage(struct writeback_control *wbc,
 bool folio_mark_dirty(struct folio *folio);
 bool set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
-void __cancel_dirty_page(struct page *page);
-static inline void cancel_dirty_page(struct page *page)
-{
-	/* Avoid atomic ops, locking, etc. when not actually needed. */
-	if (PageDirty(page))
-		__cancel_dirty_page(page);
-}
 int clear_page_dirty_for_io(struct page *page);
 
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 665ba6a67385..a4d0aeaf884d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -786,6 +786,17 @@ static inline void account_page_cleaned(struct page *page,
 {
 	return folio_account_cleaned(page_folio(page), mapping, wb);
 }
+void __folio_cancel_dirty(struct folio *folio);
+static inline void folio_cancel_dirty(struct folio *folio)
+{
+	/* Avoid atomic ops, locking, etc. when not actually needed. */
+	if (folio_test_dirty(folio))
+		__folio_cancel_dirty(folio);
+}
+static inline void cancel_dirty_page(struct page *page)
+{
+	folio_cancel_dirty(page_folio(page));
+}
 
 int __set_page_dirty_nobuffers(struct page *page);
 int __set_page_dirty_no_writeback(struct page *page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 792a83bd3917..0854ef768d06 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2640,28 +2640,28 @@ EXPORT_SYMBOL(set_page_dirty_lock);
  * page without actually doing it through the VM. Can you say "ext3 is
  * horribly ugly"? Thought you could.
  */
-void __cancel_dirty_page(struct page *page)
+void __folio_cancel_dirty(struct folio *folio)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = folio_mapping(folio);
 
 	if (mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
 
-		lock_page_memcg(page);
+		folio_memcg_lock(folio);
 		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 
-		if (TestClearPageDirty(page))
-			account_page_cleaned(page, mapping, wb);
+		if (folio_test_clear_dirty(folio))
+			folio_account_cleaned(folio, mapping, wb);
 
 		unlocked_inode_to_wb_end(inode, &cookie);
-		unlock_page_memcg(page);
+		folio_memcg_unlock(folio);
 	} else {
-		ClearPageDirty(page);
+		folio_clear_dirty(folio);
 	}
 }
-EXPORT_SYMBOL(__cancel_dirty_page);
+EXPORT_SYMBOL(__folio_cancel_dirty);
 
 /*
  * Clear a page's dirty flag, while caring for dirty memory accounting.
-- 
2.30.2

[PATCH v14 24/39] mm/writeback: Add folio_clear_dirty_for_io()

[Matthew Wilcox (Oracle)]

Transform clear_page_dirty_for_io() into folio_clear_dirty_for_io()
and add a compatibility wrapper.  Also move the declaration to pagemap.h
as this is page cache functionality that doesn't need to be used by the
rest of the kernel.

Increases the size of the kernel by 79 bytes.  While we remove a few
calls to compound_head(), we add a call to folio_nr_pages() to get the
stats correct for the eventual support of multi-page folios.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/mm.h      |  1 -
 include/linux/pagemap.h |  2 ++
 mm/folio-compat.c       |  6 ++++
 mm/page-writeback.c     | 63 +++++++++++++++++++++--------------------
 4 files changed, 40 insertions(+), 32 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 07ba22351d15..26883ea28349 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2005,7 +2005,6 @@ int redirty_page_for_writepage(struct writeback_control *wbc,
 bool folio_mark_dirty(struct folio *folio);
 bool set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
-int clear_page_dirty_for_io(struct page *page);
 
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a4d0aeaf884d..006de2d84d06 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -797,6 +797,8 @@ static inline void cancel_dirty_page(struct page *page)
 {
 	folio_cancel_dirty(page_folio(page));
 }
+bool folio_clear_dirty_for_io(struct folio *folio);
+bool clear_page_dirty_for_io(struct page *page);
 
 int __set_page_dirty_nobuffers(struct page *page);
 int __set_page_dirty_no_writeback(struct page *page);
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index dad962b920e5..39f5a8d963b1 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -89,3 +89,9 @@ int __set_page_dirty_nobuffers(struct page *page)
 	return filemap_dirty_folio(page_mapping(page), page_folio(page));
 }
 EXPORT_SYMBOL(__set_page_dirty_nobuffers);
+
+bool clear_page_dirty_for_io(struct page *page)
+{
+	return folio_clear_dirty_for_io(page_folio(page));
+}
+EXPORT_SYMBOL(clear_page_dirty_for_io);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0854ef768d06..66060bbf6aad 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2664,25 +2664,25 @@ void __folio_cancel_dirty(struct folio *folio)
 EXPORT_SYMBOL(__folio_cancel_dirty);
 
 /*
- * Clear a page's dirty flag, while caring for dirty memory accounting.
- * Returns true if the page was previously dirty.
- *
- * This is for preparing to put the page under writeout.  We leave the page
- * tagged as dirty in the xarray so that a concurrent write-for-sync
- * can discover it via a PAGECACHE_TAG_DIRTY walk.  The ->writepage
- * implementation will run either set_page_writeback() or set_page_dirty(),
- * at which stage we bring the page's dirty flag and xarray dirty tag
- * back into sync.
- *
- * This incoherency between the page's dirty flag and xarray tag is
- * unfortunate, but it only exists while the page is locked.
+ * Clear a folio's dirty flag, while caring for dirty memory accounting.
+ * Returns true if the folio was previously dirty.
+ *
+ * This is for preparing to put the folio under writeout.  We leave
+ * the folio tagged as dirty in the xarray so that a concurrent
+ * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk.
+ * The ->writepage implementation will run either folio_start_writeback()
+ * or folio_mark_dirty(), at which stage we bring the folio's dirty flag
+ * and xarray dirty tag back into sync.
+ *
+ * This incoherency between the folio's dirty flag and xarray tag is
+ * unfortunate, but it only exists while the folio is locked.
  */
-int clear_page_dirty_for_io(struct page *page)
+bool folio_clear_dirty_for_io(struct folio *folio)
 {
-	struct address_space *mapping = page_mapping(page);
-	int ret = 0;
+	struct address_space *mapping = folio_mapping(folio);
+	bool ret = false;
 
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 
 	if (mapping && mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
@@ -2695,48 +2695,49 @@ int clear_page_dirty_for_io(struct page *page)
 		 * We use this sequence to make sure that
 		 *  (a) we account for dirty stats properly
 		 *  (b) we tell the low-level filesystem to
-		 *      mark the whole page dirty if it was
+		 *      mark the whole folio dirty if it was
 		 *      dirty in a pagetable. Only to then
-		 *  (c) clean the page again and return 1 to
+		 *  (c) clean the folio again and return 1 to
 		 *      cause the writeback.
 		 *
 		 * This way we avoid all nasty races with the
 		 * dirty bit in multiple places and clearing
 		 * them concurrently from different threads.
 		 *
-		 * Note! Normally the "set_page_dirty(page)"
+		 * Note! Normally the "folio_mark_dirty(folio)"
 		 * has no effect on the actual dirty bit - since
 		 * that will already usually be set. But we
 		 * need the side effects, and it can help us
 		 * avoid races.
 		 *
-		 * We basically use the page "master dirty bit"
+		 * We basically use the folio "master dirty bit"
 		 * as a serialization point for all the different
 		 * threads doing their things.
 		 */
-		if (page_mkclean(page))
-			set_page_dirty(page);
+		if (folio_mkclean(folio))
+			folio_mark_dirty(folio);
 		/*
 		 * We carefully synchronise fault handlers against
-		 * installing a dirty pte and marking the page dirty
+		 * installing a dirty pte and marking the folio dirty
 		 * at this point.  We do this by having them hold the
-		 * page lock while dirtying the page, and pages are
+		 * page lock while dirtying the folio, and folios are
 		 * always locked coming in here, so we get the desired
 		 * exclusion.
 		 */
 		wb = unlocked_inode_to_wb_begin(inode, &cookie);
-		if (TestClearPageDirty(page)) {
-			dec_lruvec_page_state(page, NR_FILE_DIRTY);
-			dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
-			dec_wb_stat(wb, WB_RECLAIMABLE);
-			ret = 1;
+		if (folio_test_clear_dirty(folio)) {
+			long nr = folio_nr_pages(folio);
+			lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+			zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+			wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
+			ret = true;
 		}
 		unlocked_inode_to_wb_end(inode, &cookie);
 		return ret;
 	}
-	return TestClearPageDirty(page);
+	return folio_test_clear_dirty(folio);
 }
-EXPORT_SYMBOL(clear_page_dirty_for_io);
+EXPORT_SYMBOL(folio_clear_dirty_for_io);
 
 bool __folio_end_writeback(struct folio *folio)
 {
-- 
2.30.2

[PATCH v14 25/39] mm/writeback: Add folio_account_redirty()

[Matthew Wilcox (Oracle)]

Account the number of pages in the folio that we're redirtying.
Turn account_page_dirty() into a wrapper around it.  Also turn
the comment on folio_account_redirty() into kernel-doc and
edit it slightly so it makes sense to its potential callers.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/writeback.h |  6 +++++-
 mm/page-writeback.c       | 32 +++++++++++++++++++-------------
 2 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index eda9cc778ef6..50cb6e25ab9e 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -399,7 +399,11 @@ void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
 
 bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio);
-void account_page_redirty(struct page *page);
+void folio_account_redirty(struct folio *folio);
+static inline void account_page_redirty(struct page *page)
+{
+	folio_account_redirty(page_folio(page));
+}
 
 void sb_mark_inode_writeback(struct inode *inode);
 void sb_clear_inode_writeback(struct inode *inode);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 66060bbf6aad..d7bd5580c91e 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1084,7 +1084,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb,
 	 * write_bandwidth = ---------------------------------------------------
 	 *                                          period
 	 *
-	 * @written may have decreased due to account_page_redirty().
+	 * @written may have decreased due to folio_account_redirty().
 	 * Avoid underflowing @bw calculation.
 	 */
 	bw = written - min(written, wb->written_stamp);
@@ -2527,30 +2527,36 @@ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio)
 }
 EXPORT_SYMBOL(filemap_dirty_folio);
 
-/*
- * Call this whenever redirtying a page, to de-account the dirty counters
- * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written
- * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to
- * systematic errors in balanced_dirty_ratelimit and the dirty pages position
- * control.
+/**
+ * folio_account_redirty - Manually account for redirtying a page.
+ * @folio: The folio which is being redirtied.
+ *
+ * Most filesystems should call folio_redirty_for_writepage() instead
+ * of this fuction.  If your filesystem is doing writeback outside the
+ * context of a writeback_control(), it can call this when redirtying
+ * a folio, to de-account the dirty counters (NR_DIRTIED, WB_DIRTIED,
+ * tsk->nr_dirtied), so that they match the written counters (NR_WRITTEN,
+ * WB_WRITTEN) in long term. The mismatches will lead to systematic errors
+ * in balanced_dirty_ratelimit and the dirty pages position control.
  */
-void account_page_redirty(struct page *page)
+void folio_account_redirty(struct folio *folio)
 {
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping = folio->mapping;
 
 	if (mapping && mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
+		unsigned nr = folio_nr_pages(folio);
 
 		wb = unlocked_inode_to_wb_begin(inode, &cookie);
-		current->nr_dirtied--;
-		dec_node_page_state(page, NR_DIRTIED);
-		dec_wb_stat(wb, WB_DIRTIED);
+		current->nr_dirtied -= nr;
+		node_stat_mod_folio(folio, NR_DIRTIED, -nr);
+		wb_stat_mod(wb, WB_DIRTIED, -nr);
 		unlocked_inode_to_wb_end(inode, &cookie);
 	}
 }
-EXPORT_SYMBOL(account_page_redirty);
+EXPORT_SYMBOL(folio_account_redirty);
 
 /*
  * When a writepage implementation decides that it doesn't want to write this
-- 
2.30.2

[PATCH v14 26/39] mm/writeback: Add folio_redirty_for_writepage()

[Matthew Wilcox (Oracle)]

Reimplement redirty_page_for_writepage() as a wrapper around
folio_redirty_for_writepage().  Account the number of pages in the
folio, add kernel-doc and move the prototype to writeback.h.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/jfs/jfs_metapage.c     |  1 +
 include/linux/mm.h        |  4 ----
 include/linux/writeback.h |  2 ++
 mm/folio-compat.c         |  7 +++++++
 mm/page-writeback.c       | 30 ++++++++++++++++++++----------
 5 files changed, 30 insertions(+), 14 deletions(-)

diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 176580f54af9..104ae698443e 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -13,6 +13,7 @@
 #include <linux/buffer_head.h>
 #include <linux/mempool.h>
 #include <linux/seq_file.h>
+#include <linux/writeback.h>
 #include "jfs_incore.h"
 #include "jfs_superblock.h"
 #include "jfs_filsys.h"
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 26883ea28349..4803f2c01367 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -36,9 +36,7 @@
 struct mempolicy;
 struct anon_vma;
 struct anon_vma_chain;
-struct file_ra_state;
 struct user_struct;
-struct writeback_control;
 struct pt_regs;
 
 extern int sysctl_page_lock_unfairness;
@@ -2000,8 +1998,6 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
 extern void do_invalidatepage(struct page *page, unsigned int offset,
 			      unsigned int length);
 
-int redirty_page_for_writepage(struct writeback_control *wbc,
-				struct page *page);
 bool folio_mark_dirty(struct folio *folio);
 bool set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 50cb6e25ab9e..5383f7e39816 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -404,6 +404,8 @@ static inline void account_page_redirty(struct page *page)
 {
 	folio_account_redirty(page_folio(page));
 }
+bool folio_redirty_for_writepage(struct writeback_control *, struct folio *);
+bool redirty_page_for_writepage(struct writeback_control *, struct page *);
 
 void sb_mark_inode_writeback(struct inode *inode);
 void sb_clear_inode_writeback(struct inode *inode);
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 39f5a8d963b1..c1e01bc36d32 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -95,3 +95,10 @@ bool clear_page_dirty_for_io(struct page *page)
 	return folio_clear_dirty_for_io(page_folio(page));
 }
 EXPORT_SYMBOL(clear_page_dirty_for_io);
+
+bool redirty_page_for_writepage(struct writeback_control *wbc,
+		struct page *page)
+{
+	return folio_redirty_for_writepage(wbc, page_folio(page));
+}
+EXPORT_SYMBOL(redirty_page_for_writepage);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d7bd5580c91e..c2987f05c944 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2558,21 +2558,31 @@ void folio_account_redirty(struct folio *folio)
 }
 EXPORT_SYMBOL(folio_account_redirty);
 
-/*
- * When a writepage implementation decides that it doesn't want to write this
- * page for some reason, it should redirty the locked page via
- * redirty_page_for_writepage() and it should then unlock the page and return 0
+/**
+ * folio_redirty_for_writepage - Decline to write a dirty folio.
+ * @wbc: The writeback control.
+ * @folio: The folio.
+ *
+ * When a writepage implementation decides that it doesn't want to write
+ * @folio for some reason, it should call this function, unlock @folio and
+ * return 0.
+ *
+ * Return: True if we redirtied the folio.  False if someone else dirtied
+ * it first.
  */
-int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
+bool folio_redirty_for_writepage(struct writeback_control *wbc,
+		struct folio *folio)
 {
-	int ret;
+	bool ret;
+	unsigned nr = folio_nr_pages(folio);
+
+	wbc->pages_skipped += nr;
+	ret = filemap_dirty_folio(folio->mapping, folio);
+	folio_account_redirty(folio);
 
-	wbc->pages_skipped++;
-	ret = __set_page_dirty_nobuffers(page);
-	account_page_redirty(page);
 	return ret;
 }
-EXPORT_SYMBOL(redirty_page_for_writepage);
+EXPORT_SYMBOL(folio_redirty_for_writepage);
 
 /**
  * folio_mark_dirty - Mark a folio as being modified.
-- 
2.30.2

[PATCH v14 27/39] mm/filemap: Add i_blocks_per_folio()

[Matthew Wilcox (Oracle)]

Reimplement i_blocks_per_page() as a wrapper around i_blocks_per_folio().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/pagemap.h | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 006de2d84d06..412db88b8d0c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1150,19 +1150,25 @@ static inline int page_mkwrite_check_truncate(struct page *page,
 }
 
 /**
- * i_blocks_per_page - How many blocks fit in this page.
+ * i_blocks_per_folio - How many blocks fit in this folio.
  * @inode: The inode which contains the blocks.
- * @page: The page (head page if the page is a THP).
+ * @folio: The folio.
  *
- * If the block size is larger than the size of this page, return zero.
+ * If the block size is larger than the size of this folio, return zero.
  *
- * Context: The caller should hold a refcount on the page to prevent it
+ * Context: The caller should hold a refcount on the folio to prevent it
  * from being split.
- * Return: The number of filesystem blocks covered by this page.
+ * Return: The number of filesystem blocks covered by this folio.
  */
+static inline
+unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio)
+{
+	return folio_size(folio) >> inode->i_blkbits;
+}
+
 static inline
 unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
 {
-	return thp_size(page) >> inode->i_blkbits;
+	return i_blocks_per_folio(inode, page_folio(page));
 }
 #endif /* _LINUX_PAGEMAP_H */
-- 
2.30.2

[PATCH v14 28/39] mm/filemap: Add folio_mkwrite_check_truncate()

[Matthew Wilcox (Oracle)]

This is the folio equivalent of page_mkwrite_check_truncate().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/pagemap.h | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 412db88b8d0c..18c06c3e42c3 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1121,6 +1121,34 @@ static inline unsigned long dir_pages(struct inode *inode)
 			       PAGE_SHIFT;
 }
 
+/**
+ * folio_mkwrite_check_truncate - check if folio was truncated
+ * @folio: the folio to check
+ * @inode: the inode to check the folio against
+ *
+ * Return: the number of bytes in the folio up to EOF,
+ * or -EFAULT if the folio was truncated.
+ */
+static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio,
+					      struct inode *inode)
+{
+	loff_t size = i_size_read(inode);
+	pgoff_t index = size >> PAGE_SHIFT;
+	size_t offset = offset_in_folio(folio, size);
+
+	if (!folio->mapping)
+		return -EFAULT;
+
+	/* folio is wholly inside EOF */
+	if (folio_next_index(folio) - 1 < index)
+		return folio_size(folio);
+	/* folio is wholly past EOF */
+	if (folio->index > index || !offset)
+		return -EFAULT;
+	/* folio is partially inside EOF */
+	return offset;
+}
+
 /**
  * page_mkwrite_check_truncate - check if page was truncated
  * @page: the page to check
-- 
2.30.2

[PATCH v14 29/39] mm/filemap: Add readahead_folio()

[Matthew Wilcox (Oracle)]

The pointers stored in the page cache are folios, by definition.
This change comes with a behaviour change -- callers of readahead_folio()
are no longer required to put the page reference themselves.  This matches
how readpage works, rather than matching how readpages used to work.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/pagemap.h | 53 +++++++++++++++++++++++++++++------------
 1 file changed, 38 insertions(+), 15 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 18c06c3e42c3..bd4daebaf70e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -988,33 +988,56 @@ void page_cache_async_readahead(struct address_space *mapping,
 	page_cache_async_ra(&ractl, page, req_count);
 }
 
+static inline struct folio *__readahead_folio(struct readahead_control *ractl)
+{
+	struct folio *folio;
+
+	BUG_ON(ractl->_batch_count > ractl->_nr_pages);
+	ractl->_nr_pages -= ractl->_batch_count;
+	ractl->_index += ractl->_batch_count;
+
+	if (!ractl->_nr_pages) {
+		ractl->_batch_count = 0;
+		return NULL;
+	}
+
+	folio = xa_load(&ractl->mapping->i_pages, ractl->_index);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+	ractl->_batch_count = folio_nr_pages(folio);
+
+	return folio;
+}
+
 /**
  * readahead_page - Get the next page to read.
- * @rac: The current readahead request.
+ * @ractl: The current readahead request.
  *
  * Context: The page is locked and has an elevated refcount.  The caller
  * should decreases the refcount once the page has been submitted for I/O
  * and unlock the page once all I/O to that page has completed.
  * Return: A pointer to the next page, or %NULL if we are done.
  */
-static inline struct page *readahead_page(struct readahead_control *rac)
+static inline struct page *readahead_page(struct readahead_control *ractl)
 {
-	struct page *page;
+	struct folio *folio = __readahead_folio(ractl);
 
-	BUG_ON(rac->_batch_count > rac->_nr_pages);
-	rac->_nr_pages -= rac->_batch_count;
-	rac->_index += rac->_batch_count;
-
-	if (!rac->_nr_pages) {
-		rac->_batch_count = 0;
-		return NULL;
-	}
+	return &folio->page;
+}
 
-	page = xa_load(&rac->mapping->i_pages, rac->_index);
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	rac->_batch_count = thp_nr_pages(page);
+/**
+ * readahead_folio - Get the next folio to read.
+ * @ractl: The current readahead request.
+ *
+ * Context: The folio is locked.  The caller should unlock the folio once
+ * all I/O to that folio has completed.
+ * Return: A pointer to the next folio, or %NULL if we are done.
+ */
+static inline struct folio *readahead_folio(struct readahead_control *ractl)
+{
+	struct folio *folio = __readahead_folio(ractl);
 
-	return page;
+	folio_put(folio);
+	return folio;
 }
 
 static inline unsigned int __readahead_batch(struct readahead_control *rac,
-- 
2.30.2

[PATCH v14 30/39] mm/workingset: Convert workingset_refault() to take a folio

[Matthew Wilcox (Oracle)]

This nets us 178 bytes of savings from removing calls to compound_head.
The three callers all grow a little, but each of them will be converted
to use folios soon, so that's fine.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/swap.h |  4 ++--
 mm/filemap.c         |  2 +-
 mm/memory.c          |  3 ++-
 mm/swap.c            |  7 +++----
 mm/swap_state.c      |  2 +-
 mm/workingset.c      | 34 +++++++++++++++++-----------------
 6 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index c7a4c0a5863d..5e01675af7ab 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -329,7 +329,7 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio)
 /* linux/mm/workingset.c */
 void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
 void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg);
-void workingset_refault(struct page *page, void *shadow);
+void workingset_refault(struct folio *folio, void *shadow);
 void workingset_activation(struct folio *folio);
 
 /* Only track the nodes of mappings with shadow entries */
@@ -350,7 +350,7 @@ extern unsigned long nr_free_buffer_pages(void);
 /* linux/mm/swap.c */
 extern void lru_note_cost(struct lruvec *lruvec, bool file,
 			  unsigned int nr_pages);
-extern void lru_note_cost_page(struct page *);
+extern void lru_note_cost_folio(struct folio *);
 extern void lru_cache_add(struct page *);
 void mark_page_accessed(struct page *);
 void folio_mark_accessed(struct folio *);
diff --git a/mm/filemap.c b/mm/filemap.c
index a74c69a938ab..6bec995e69bd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -981,7 +981,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 		 */
 		WARN_ON_ONCE(PageActive(page));
 		if (!(gfp_mask & __GFP_WRITE) && shadow)
-			workingset_refault(page, shadow);
+			workingset_refault(page_folio(page), shadow);
 		lru_cache_add(page);
 	}
 	return ret;
diff --git a/mm/memory.c b/mm/memory.c
index 614418e26e2c..627e7836ade6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3538,7 +3538,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 				shadow = get_shadow_from_swap_cache(entry);
 				if (shadow)
-					workingset_refault(page, shadow);
+					workingset_refault(page_folio(page),
+								shadow);
 
 				lru_cache_add(page);
 
diff --git a/mm/swap.c b/mm/swap.c
index d32007fe23b3..6e80f30d2e5e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -315,11 +315,10 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
-void lru_note_cost_page(struct page *page)
+void lru_note_cost_folio(struct folio *folio)
 {
-	struct folio *folio = page_folio(page);
-	lru_note_cost(folio_lruvec(folio),
-		      page_is_file_lru(page), thp_nr_pages(page));
+	lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio),
+			folio_nr_pages(folio));
 }
 
 static void __folio_activate(struct folio *folio, struct lruvec *lruvec)
diff --git a/mm/swap_state.c b/mm/swap_state.c
index c56aa9ac050d..1a29b4f98208 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -498,7 +498,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	mem_cgroup_swapin_uncharge_swap(entry);
 
 	if (shadow)
-		workingset_refault(page, shadow);
+		workingset_refault(page_folio(page), shadow);
 
 	/* Caller will initiate read into locked page */
 	lru_cache_add(page);
diff --git a/mm/workingset.c b/mm/workingset.c
index 39bb60d50217..10830211a187 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -273,17 +273,17 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
 }
 
 /**
- * workingset_refault - evaluate the refault of a previously evicted page
- * @page: the freshly allocated replacement page
- * @shadow: shadow entry of the evicted page
+ * workingset_refault - evaluate the refault of a previously evicted folio
+ * @page: the freshly allocated replacement folio
+ * @shadow: shadow entry of the evicted folio
  *
  * Calculates and evaluates the refault distance of the previously
- * evicted page in the context of the node and the memcg whose memory
+ * evicted folio in the context of the node and the memcg whose memory
  * pressure caused the eviction.
  */
-void workingset_refault(struct page *page, void *shadow)
+void workingset_refault(struct folio *folio, void *shadow)
 {
-	bool file = page_is_file_lru(page);
+	bool file = folio_is_file_lru(folio);
 	struct mem_cgroup *eviction_memcg;
 	struct lruvec *eviction_lruvec;
 	unsigned long refault_distance;
@@ -301,10 +301,10 @@ void workingset_refault(struct page *page, void *shadow)
 	rcu_read_lock();
 	/*
 	 * Look up the memcg associated with the stored ID. It might
-	 * have been deleted since the page's eviction.
+	 * have been deleted since the folio's eviction.
 	 *
 	 * Note that in rare events the ID could have been recycled
-	 * for a new cgroup that refaults a shared page. This is
+	 * for a new cgroup that refaults a shared folio. This is
 	 * impossible to tell from the available data. However, this
 	 * should be a rare and limited disturbance, and activations
 	 * are always speculative anyway. Ultimately, it's the aging
@@ -340,14 +340,14 @@ void workingset_refault(struct page *page, void *shadow)
 	refault_distance = (refault - eviction) & EVICTION_MASK;
 
 	/*
-	 * The activation decision for this page is made at the level
+	 * The activation decision for this folio is made at the level
 	 * where the eviction occurred, as that is where the LRU order
-	 * during page reclaim is being determined.
+	 * during folio reclaim is being determined.
 	 *
-	 * However, the cgroup that will own the page is the one that
+	 * However, the cgroup that will own the folio is the one that
 	 * is actually experiencing the refault event.
 	 */
-	memcg = page_memcg(page);
+	memcg = folio_memcg(folio);
 	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
 	inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);
@@ -375,15 +375,15 @@ void workingset_refault(struct page *page, void *shadow)
 	if (refault_distance > workingset_size)
 		goto out;
 
-	SetPageActive(page);
-	workingset_age_nonresident(lruvec, thp_nr_pages(page));
+	folio_set_active(folio);
+	workingset_age_nonresident(lruvec, folio_nr_pages(folio));
 	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);
 
-	/* Page was active prior to eviction */
+	/* Folio was active prior to eviction */
 	if (workingset) {
-		SetPageWorkingset(page);
+		folio_set_workingset(folio);
 		/* XXX: Move to lru_cache_add() when it supports new vs putback */
-		lru_note_cost_page(page);
+		lru_note_cost_folio(folio);
 		inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
 	}
 out:
-- 
2.30.2

[PATCH v14 31/39] mm: Add folio_evictable()

[Matthew Wilcox (Oracle)]

This is the folio equivalent of page_evictable().  Unfortunately, it's
different from !folio_test_unevictable(), but I think it's used in places
where you have to be a VM expert and can reasonably be expected to know
the difference.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 mm/internal.h | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 08e8a28994d1..0910efec5821 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -72,17 +72,28 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
 		pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
 
 /**
- * page_evictable - test whether a page is evictable
- * @page: the page to test
+ * folio_evictable - Test whether a folio is evictable.
+ * @folio: The folio to test.
  *
- * Test whether page is evictable--i.e., should be placed on active/inactive
- * lists vs unevictable list.
- *
- * Reasons page might not be evictable:
- * (1) page's mapping marked unevictable
- * (2) page is part of an mlocked VMA
+ * Test whether @folio is evictable -- i.e., should be placed on
+ * active/inactive lists vs unevictable list.
  *
+ * Reasons folio might not be evictable:
+ * 1. folio's mapping marked unevictable
+ * 2. One of the pages in the folio is part of an mlocked VMA
  */
+static inline bool folio_evictable(struct folio *folio)
+{
+	bool ret;
+
+	/* Prevent address_space of inode and swap cache from being freed */
+	rcu_read_lock();
+	ret = !mapping_unevictable(folio_mapping(folio)) &&
+			!folio_test_mlocked(folio);
+	rcu_read_unlock();
+	return ret;
+}
+
 static inline bool page_evictable(struct page *page)
 {
 	bool ret;
-- 
2.30.2

[PATCH v14 32/39] mm/lru: Convert __pagevec_lru_add_fn to take a folio

[Matthew Wilcox (Oracle)]

This saves five calls to compound_head(), totalling 60 bytes of text.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/trace/events/pagemap.h | 32 ++++++++++++++++----------------
 mm/swap.c                      | 34 +++++++++++++++++-----------------
 2 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
index 1fd0185d66e8..171524d3526d 100644
--- a/include/trace/events/pagemap.h
+++ b/include/trace/events/pagemap.h
@@ -16,38 +16,38 @@
 #define PAGEMAP_MAPPEDDISK	0x0020u
 #define PAGEMAP_BUFFERS		0x0040u
 
-#define trace_pagemap_flags(page) ( \
-	(PageAnon(page)		? PAGEMAP_ANONYMOUS  : PAGEMAP_FILE) | \
-	(page_mapped(page)	? PAGEMAP_MAPPED     : 0) | \
-	(PageSwapCache(page)	? PAGEMAP_SWAPCACHE  : 0) | \
-	(PageSwapBacked(page)	? PAGEMAP_SWAPBACKED : 0) | \
-	(PageMappedToDisk(page)	? PAGEMAP_MAPPEDDISK : 0) | \
-	(page_has_private(page) ? PAGEMAP_BUFFERS    : 0) \
+#define trace_pagemap_flags(folio) ( \
+	(folio_test_anon(folio)		? PAGEMAP_ANONYMOUS  : PAGEMAP_FILE) | \
+	(folio_mapped(folio)		? PAGEMAP_MAPPED     : 0) | \
+	(folio_test_swapcache(folio)	? PAGEMAP_SWAPCACHE  : 0) | \
+	(folio_test_swapbacked(folio)	? PAGEMAP_SWAPBACKED : 0) | \
+	(folio_test_mappedtodisk(folio)	? PAGEMAP_MAPPEDDISK : 0) | \
+	(folio_test_private(folio)	? PAGEMAP_BUFFERS    : 0) \
 	)
 
 TRACE_EVENT(mm_lru_insertion,
 
-	TP_PROTO(struct page *page),
+	TP_PROTO(struct folio *folio),
 
-	TP_ARGS(page),
+	TP_ARGS(folio),
 
 	TP_STRUCT__entry(
-		__field(struct page *,	page	)
+		__field(struct folio *,	folio	)
 		__field(unsigned long,	pfn	)
 		__field(enum lru_list,	lru	)
 		__field(unsigned long,	flags	)
 	),
 
 	TP_fast_assign(
-		__entry->page	= page;
-		__entry->pfn	= page_to_pfn(page);
-		__entry->lru	= folio_lru_list(page_folio(page));
-		__entry->flags	= trace_pagemap_flags(page);
+		__entry->folio	= folio;
+		__entry->pfn	= folio_pfn(folio);
+		__entry->lru	= folio_lru_list(folio);
+		__entry->flags	= trace_pagemap_flags(folio);
 	),
 
 	/* Flag format is based on page-types.c formatting for pagemap */
-	TP_printk("page=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s",
-			__entry->page,
+	TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s",
+			__entry->folio,
 			__entry->pfn,
 			__entry->lru,
 			__entry->flags & PAGEMAP_MAPPED		? "M" : " ",
diff --git a/mm/swap.c b/mm/swap.c
index 6e80f30d2e5e..89d4471ceb80 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1001,17 +1001,18 @@ void __pagevec_release(struct pagevec *pvec)
 }
 EXPORT_SYMBOL(__pagevec_release);
 
-static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
+static void __pagevec_lru_add_fn(struct folio *folio, struct lruvec *lruvec)
 {
-	int was_unevictable = TestClearPageUnevictable(page);
-	int nr_pages = thp_nr_pages(page);
+	int was_unevictable = folio_test_clear_unevictable(folio);
+	int nr_pages = folio_nr_pages(folio);
 
-	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
 	/*
-	 * Page becomes evictable in two ways:
+	 * Folio becomes evictable in two ways:
 	 * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()].
-	 * 2) Before acquiring LRU lock to put the page to correct LRU and then
+	 * 2) Before acquiring LRU lock to put the folio on the correct LRU
+	 *    and then
 	 *   a) do PageLRU check with lock [check_move_unevictable_pages]
 	 *   b) do PageLRU check before lock [clear_page_mlock]
 	 *
@@ -1020,10 +1021,10 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 	 *
 	 * #0: __pagevec_lru_add_fn		#1: clear_page_mlock
 	 *
-	 * SetPageLRU()				TestClearPageMlocked()
+	 * folio_set_lru()			folio_test_clear_mlocked()
 	 * smp_mb() // explicit ordering	// above provides strict
 	 *					// ordering
-	 * PageMlocked()			PageLRU()
+	 * folio_test_mlocked()			folio_test_lru()
 	 *
 	 *
 	 * if '#1' does not observe setting of PG_lru by '#0' and fails
@@ -1034,21 +1035,21 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 	 * looking at the same page) and the evictable page will be stranded
 	 * in an unevictable LRU.
 	 */
-	SetPageLRU(page);
+	folio_set_lru(folio);
 	smp_mb__after_atomic();
 
-	if (page_evictable(page)) {
+	if (folio_evictable(folio)) {
 		if (was_unevictable)
 			__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
 	} else {
-		ClearPageActive(page);
-		SetPageUnevictable(page);
+		folio_clear_active(folio);
+		folio_set_unevictable(folio);
 		if (!was_unevictable)
 			__count_vm_events(UNEVICTABLE_PGCULLED, nr_pages);
 	}
 
-	add_page_to_lru_list(page, lruvec);
-	trace_mm_lru_insertion(page);
+	lruvec_add_folio(lruvec, folio);
+	trace_mm_lru_insertion(folio);
 }
 
 /*
@@ -1062,11 +1063,10 @@ void __pagevec_lru_add(struct pagevec *pvec)
 	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-		struct folio *folio = page_folio(page);
+		struct folio *folio = page_folio(pvec->pages[i]);
 
 		lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags);
-		__pagevec_lru_add_fn(page, lruvec);
+		__pagevec_lru_add_fn(folio, lruvec);
 	}
 	if (lruvec)
 		unlock_page_lruvec_irqrestore(lruvec, flags);
-- 
2.30.2

[PATCH v14 33/39] mm/lru: Add folio_add_lru()

[Matthew Wilcox (Oracle)]

Reimplement lru_cache_add() as a wrapper around folio_add_lru().
Saves 159 bytes of kernel text due to removing calls to compound_head().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/swap.h |  1 +
 mm/folio-compat.c    |  6 ++++++
 mm/swap.c            | 22 +++++++++++-----------
 3 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5e01675af7ab..81801ba78b1e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -351,6 +351,7 @@ extern unsigned long nr_free_buffer_pages(void);
 extern void lru_note_cost(struct lruvec *lruvec, bool file,
 			  unsigned int nr_pages);
 extern void lru_note_cost_folio(struct folio *);
+extern void folio_add_lru(struct folio *);
 extern void lru_cache_add(struct page *);
 void mark_page_accessed(struct page *);
 void folio_mark_accessed(struct folio *);
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index c1e01bc36d32..6de3cd78a4ae 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -102,3 +102,9 @@ bool redirty_page_for_writepage(struct writeback_control *wbc,
 	return folio_redirty_for_writepage(wbc, page_folio(page));
 }
 EXPORT_SYMBOL(redirty_page_for_writepage);
+
+void lru_cache_add(struct page *page)
+{
+	folio_add_lru(page_folio(page));
+}
+EXPORT_SYMBOL(lru_cache_add);
diff --git a/mm/swap.c b/mm/swap.c
index 89d4471ceb80..6f382abeccf9 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -459,29 +459,29 @@ void folio_mark_accessed(struct folio *folio)
 EXPORT_SYMBOL(folio_mark_accessed);
 
 /**
- * lru_cache_add - add a page to a page list
- * @page: the page to be added to the LRU.
+ * folio_add_lru - Add a folio to an LRU list.
+ * @folio: The folio to be added to the LRU.
  *
- * Queue the page for addition to the LRU via pagevec. The decision on whether
+ * Queue the folio for addition to the LRU. The decision on whether
  * to add the page to the [in]active [file|anon] list is deferred until the
- * pagevec is drained. This gives a chance for the caller of lru_cache_add()
- * have the page added to the active list using mark_page_accessed().
+ * pagevec is drained. This gives a chance for the caller of folio_add_lru()
+ * have the folio added to the active list using folio_mark_accessed().
  */
-void lru_cache_add(struct page *page)
+void folio_add_lru(struct folio *folio)
 {
 	struct pagevec *pvec;
 
-	VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
-	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio);
+	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
-	get_page(page);
+	folio_get(folio);
 	local_lock(&lru_pvecs.lock);
 	pvec = this_cpu_ptr(&lru_pvecs.lru_add);
-	if (pagevec_add_and_need_flush(pvec, page))
+	if (pagevec_add_and_need_flush(pvec, &folio->page))
 		__pagevec_lru_add(pvec);
 	local_unlock(&lru_pvecs.lock);
 }
-EXPORT_SYMBOL(lru_cache_add);
+EXPORT_SYMBOL(folio_add_lru);
 
 /**
  * lru_cache_add_inactive_or_unevictable
-- 
2.30.2

[PATCH v14 34/39] mm/page_alloc: Add folio allocation functions

[Matthew Wilcox (Oracle)]

The __folio_alloc(), __folio_alloc_node() and folio_alloc() functions
are mostly for type safety, but they also ensure that the page allocator
allocates a compound page and initialises the deferred list if the page
is large enough to have one.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/gfp.h | 16 ++++++++++++++++
 mm/mempolicy.c      | 10 ++++++++++
 mm/page_alloc.c     | 12 ++++++++++++
 3 files changed, 38 insertions(+)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index dc5ff40608ce..3745efd21cf6 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -523,6 +523,8 @@ static inline void arch_alloc_page(struct page *page, int order) { }
 
 struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 		nodemask_t *nodemask);
+struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+		nodemask_t *nodemask);
 
 unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 				nodemask_t *nodemask, int nr_pages,
@@ -564,6 +566,15 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 	return __alloc_pages(gfp_mask, order, nid, NULL);
 }
 
+static inline
+struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
+{
+	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
+	VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid));
+
+	return __folio_alloc(gfp, order, nid, NULL);
+}
+
 /*
  * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
  * prefer the current CPU's closest node. Otherwise node must be valid and
@@ -580,6 +591,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 
 #ifdef CONFIG_NUMA
 struct page *alloc_pages(gfp_t gfp, unsigned int order);
+struct folio *folio_alloc(gfp_t gfp, unsigned order);
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr,
 			int node, bool hugepage);
@@ -590,6 +602,10 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
 {
 	return alloc_pages_node(numa_node_id(), gfp_mask, order);
 }
+static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
+{
+	return __folio_alloc_node(gfp, order, numa_node_id());
+}
 #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
 	alloc_pages(gfp_mask, order)
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e32360e90274..95d0cf05f7ca 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2249,6 +2249,16 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
 }
 EXPORT_SYMBOL(alloc_pages);
 
+struct folio *folio_alloc(gfp_t gfp, unsigned order)
+{
+	struct page *page = alloc_pages(gfp | __GFP_COMP, order);
+
+	if (page && order > 1)
+		prep_transhuge_page(page);
+	return (struct folio *)page;
+}
+EXPORT_SYMBOL(folio_alloc);
+
 int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
 {
 	struct mempolicy *pol = mpol_dup(vma_policy(src));
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d72a0d9d4184..d03145671934 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5399,6 +5399,18 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 }
 EXPORT_SYMBOL(__alloc_pages);
 
+struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+		nodemask_t *nodemask)
+{
+	struct page *page = __alloc_pages(gfp | __GFP_COMP, order,
+			preferred_nid, nodemask);
+
+	if (page && order > 1)
+		prep_transhuge_page(page);
+	return (struct folio *)page;
+}
+EXPORT_SYMBOL(__folio_alloc);
+
 /*
  * Common helper functions. Never use with __GFP_HIGHMEM because the returned
  * address cannot represent highmem pages. Use alloc_pages and then kmap if
-- 
2.30.2

[PATCH v14 35/39] mm/filemap: Add filemap_alloc_folio

[Matthew Wilcox (Oracle)]

Reimplement __page_cache_alloc as a wrapper around filemap_alloc_folio
to allow filesystems to be converted at our leisure.  Increases
kernel text size by 133 bytes, mostly in cachefiles_read_backing_file().
pagecache_get_page() shrinks by 32 bytes, though.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/pagemap.h | 11 ++++++++---
 mm/filemap.c            | 14 +++++++-------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bd4daebaf70e..848acb44ac80 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -262,14 +262,19 @@ static inline void *detach_page_private(struct page *page)
 }
 
 #ifdef CONFIG_NUMA
-extern struct page *__page_cache_alloc(gfp_t gfp);
+struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
 #else
-static inline struct page *__page_cache_alloc(gfp_t gfp)
+static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
 {
-	return alloc_pages(gfp, 0);
+	return folio_alloc(gfp, order);
 }
 #endif
 
+static inline struct page *__page_cache_alloc(gfp_t gfp)
+{
+	return &filemap_alloc_folio(gfp, 0)->page;
+}
+
 static inline struct page *page_cache_alloc(struct address_space *x)
 {
 	return __page_cache_alloc(mapping_gfp_mask(x));
diff --git a/mm/filemap.c b/mm/filemap.c
index 6bec995e69bd..54989a32d6a8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -989,24 +989,24 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
 
 #ifdef CONFIG_NUMA
-struct page *__page_cache_alloc(gfp_t gfp)
+struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
 {
 	int n;
-	struct page *page;
+	struct folio *folio;
 
 	if (cpuset_do_page_mem_spread()) {
 		unsigned int cpuset_mems_cookie;
 		do {
 			cpuset_mems_cookie = read_mems_allowed_begin();
 			n = cpuset_mem_spread_node();
-			page = __alloc_pages_node(n, gfp, 0);
-		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
+			folio = __folio_alloc_node(gfp, order, n);
+		} while (!folio && read_mems_allowed_retry(cpuset_mems_cookie));
 
-		return page;
+		return folio;
 	}
-	return alloc_pages(gfp, 0);
+	return folio_alloc(gfp, order);
 }
-EXPORT_SYMBOL(__page_cache_alloc);
+EXPORT_SYMBOL(filemap_alloc_folio);
 #endif
 
 /*
-- 
2.30.2

[PATCH v14 36/39] mm/filemap: Add filemap_add_folio()

[Matthew Wilcox (Oracle)]

Convert __add_to_page_cache_locked() into __filemap_add_folio().
Add an assertion to it that (for !hugetlbfs), the folio is naturally
aligned within the file.  Move the prototype from mm.h to pagemap.h.
Convert add_to_page_cache_lru() into filemap_add_folio().  Add a
compatibility wrapper for unconverted callers.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/mm.h      |  7 -----
 include/linux/pagemap.h | 10 ++++--
 kernel/bpf/verifier.c   |  2 +-
 mm/filemap.c            | 70 ++++++++++++++++++++---------------------
 mm/folio-compat.c       |  7 +++++
 5 files changed, 50 insertions(+), 46 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4803f2c01367..99f5f736be64 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -213,13 +213,6 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
-/*
- * Any attempt to mark this function as static leads to build failure
- * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked()
- * is referred to by BPF code. This must be visible for error injection.
- */
-int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
-		pgoff_t index, gfp_t gfp, void **shadowp);
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 848acb44ac80..19b2e3bea14c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -877,9 +877,11 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size)
 }
 
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
-				pgoff_t index, gfp_t gfp_mask);
+		pgoff_t index, gfp_t gfp);
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
-				pgoff_t index, gfp_t gfp_mask);
+		pgoff_t index, gfp_t gfp);
+int filemap_add_folio(struct address_space *mapping, struct folio *folio,
+		pgoff_t index, gfp_t gfp);
 extern void delete_from_page_cache(struct page *page);
 extern void __delete_from_page_cache(struct page *page, void *shadow);
 void replace_page_cache_page(struct page *old, struct page *new);
@@ -904,6 +906,10 @@ static inline int add_to_page_cache(struct page *page,
 	return error;
 }
 
+/* Must be non-static for BPF error injection */
+int __filemap_add_folio(struct address_space *mapping, struct folio *folio,
+		pgoff_t index, gfp_t gfp, void **shadowp);
+
 /**
  * struct readahead_control - Describes a readahead request.
  *
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 42a4063de7cd..f0a4f8b818e4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13015,7 +13015,7 @@ BTF_SET_START(btf_non_sleepable_error_inject)
 /* Three functions below can be called from sleepable and non-sleepable context.
  * Assume non-sleepable from bpf safety point of view.
  */
-BTF_ID(func, __add_to_page_cache_locked)
+BTF_ID(func, __filemap_add_folio)
 BTF_ID(func, should_fail_alloc_page)
 BTF_ID(func, should_failslab)
 BTF_SET_END(btf_non_sleepable_error_inject)
diff --git a/mm/filemap.c b/mm/filemap.c
index 54989a32d6a8..4e34383fd894 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -855,26 +855,25 @@ void replace_page_cache_page(struct page *old, struct page *new)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
-noinline int __add_to_page_cache_locked(struct page *page,
-					struct address_space *mapping,
-					pgoff_t offset, gfp_t gfp,
-					void **shadowp)
+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, offset);
-	int huge = PageHuge(page);
+	XA_STATE(xas, &mapping->i_pages, index);
+	int huge = folio_test_hugetlb(folio);
 	int error;
 	bool charged = false;
 
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
 	mapping_set_update(&xas, mapping);
 
-	get_page(page);
-	page->mapping = mapping;
-	page->index = offset;
+	folio_get(folio);
+	folio->mapping = mapping;
+	folio->index = index;
 
 	if (!huge) {
-		error = mem_cgroup_charge(page_folio(page), NULL, gfp);
+		error = mem_cgroup_charge(folio, NULL, gfp);
+		VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
 		if (error)
 			goto error;
 		charged = true;
@@ -886,7 +885,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
 		unsigned int order = xa_get_order(xas.xa, xas.xa_index);
 		void *entry, *old = NULL;
 
-		if (order > thp_order(page))
+		if (order > folio_order(folio))
 			xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
 					order, gfp);
 		xas_lock_irq(&xas);
@@ -903,13 +902,13 @@ noinline int __add_to_page_cache_locked(struct page *page,
 				*shadowp = old;
 			/* entry may have been split before we acquired lock */
 			order = xa_get_order(xas.xa, xas.xa_index);
-			if (order > thp_order(page)) {
+			if (order > folio_order(folio)) {
 				xas_split(&xas, old, order);
 				xas_reset(&xas);
 			}
 		}
 
-		xas_store(&xas, page);
+		xas_store(&xas, folio);
 		if (xas_error(&xas))
 			goto unlock;
 
@@ -917,7 +916,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
 
 		/* hugetlb pages do not participate in page cache accounting */
 		if (!huge)
-			__inc_lruvec_page_state(page, NR_FILE_PAGES);
+			__lruvec_stat_add_folio(folio, NR_FILE_PAGES);
 unlock:
 		xas_unlock_irq(&xas);
 	} while (xas_nomem(&xas, gfp));
@@ -925,19 +924,19 @@ noinline int __add_to_page_cache_locked(struct page *page,
 	if (xas_error(&xas)) {
 		error = xas_error(&xas);
 		if (charged)
-			mem_cgroup_uncharge(page_folio(page));
+			mem_cgroup_uncharge(folio);
 		goto error;
 	}
 
-	trace_mm_filemap_add_to_page_cache(page);
+	trace_mm_filemap_add_to_page_cache(&folio->page);
 	return 0;
 error:
-	page->mapping = NULL;
+	folio->mapping = NULL;
 	/* Leave page->index set: truncation relies upon it */
-	put_page(page);
+	folio_put(folio);
 	return error;
 }
-ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
+ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
 
 /**
  * add_to_page_cache_locked - add a locked page to the pagecache
@@ -954,39 +953,38 @@ ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 		pgoff_t offset, gfp_t gfp_mask)
 {
-	return __add_to_page_cache_locked(page, mapping, offset,
+	return __filemap_add_folio(mapping, page_folio(page), offset,
 					  gfp_mask, NULL);
 }
 EXPORT_SYMBOL(add_to_page_cache_locked);
 
-int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
-				pgoff_t offset, gfp_t gfp_mask)
+int filemap_add_folio(struct address_space *mapping, struct folio *folio,
+				pgoff_t index, gfp_t gfp)
 {
 	void *shadow = NULL;
 	int ret;
 
-	__SetPageLocked(page);
-	ret = __add_to_page_cache_locked(page, mapping, offset,
-					 gfp_mask, &shadow);
+	__folio_set_locked(folio);
+	ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow);
 	if (unlikely(ret))
-		__ClearPageLocked(page);
+		__folio_clear_locked(folio);
 	else {
 		/*
-		 * The page might have been evicted from cache only
+		 * The folio might have been evicted from cache only
 		 * recently, in which case it should be activated like
-		 * any other repeatedly accessed page.
-		 * The exception is pages getting rewritten; evicting other
+		 * any other repeatedly accessed folio.
+		 * The exception is folios getting rewritten; evicting other
 		 * data from the working set, only to cache data that will
 		 * get overwritten with something else, is a waste of memory.
 		 */
-		WARN_ON_ONCE(PageActive(page));
-		if (!(gfp_mask & __GFP_WRITE) && shadow)
-			workingset_refault(page_folio(page), shadow);
-		lru_cache_add(page);
+		WARN_ON_ONCE(folio_test_active(folio));
+		if (!(gfp & __GFP_WRITE) && shadow)
+			workingset_refault(folio, shadow);
+		folio_add_lru(folio);
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
+EXPORT_SYMBOL_GPL(filemap_add_folio);
 
 #ifdef CONFIG_NUMA
 struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 6de3cd78a4ae..6b19bc4ed6b0 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -108,3 +108,10 @@ void lru_cache_add(struct page *page)
 	folio_add_lru(page_folio(page));
 }
 EXPORT_SYMBOL(lru_cache_add);
+
+int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
+		pgoff_t index, gfp_t gfp)
+{
+	return filemap_add_folio(mapping, page_folio(page), index, gfp);
+}
+EXPORT_SYMBOL(add_to_page_cache_lru);
-- 
2.30.2

[PATCH v14 37/39] mm/filemap: Convert mapping_get_entry to return a folio

[Matthew Wilcox (Oracle)]

The pagecache only contains folios, so indicate that this is definitely
not a tail page.  Shrinks mapping_get_entry() by 56 bytes, but grows
pagecache_get_page() by 21 bytes as gcc makes slightly different hot/cold
code decisions.  A net reduction of 35 bytes of text.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 mm/filemap.c | 35 ++++++++++++++---------------------
 1 file changed, 14 insertions(+), 21 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 4e34383fd894..85a457c7b7a7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1755,49 +1755,42 @@ EXPORT_SYMBOL(page_cache_prev_miss);
  * @mapping: the address_space to search
  * @index: The page cache index.
  *
- * Looks up the page cache slot at @mapping & @index.  If there is a
- * page cache page, the head page is returned with an increased refcount.
+ * Looks up the page cache entry at @mapping & @index.  If it is a folio,
+ * it is returned with an increased refcount.  If it is a shadow entry
+ * of a previously evicted folio, or a swap entry from shmem/tmpfs,
+ * it is returned without further action.
  *
- * If the slot holds a shadow entry of a previously evicted page, or a
- * swap entry from shmem/tmpfs, it is returned.
- *
- * Return: The head page or shadow entry, %NULL if nothing is found.
+ * Return: The folio, swap or shadow entry, %NULL if nothing is found.
  */
-static struct page *mapping_get_entry(struct address_space *mapping,
-		pgoff_t index)
+static void *mapping_get_entry(struct address_space *mapping, pgoff_t index)
 {
 	XA_STATE(xas, &mapping->i_pages, index);
-	struct page *page;
+	struct folio *folio;
 
 	rcu_read_lock();
 repeat:
 	xas_reset(&xas);
-	page = xas_load(&xas);
-	if (xas_retry(&xas, page))
+	folio = xas_load(&xas);
+	if (xas_retry(&xas, folio))
 		goto repeat;
 	/*
 	 * A shadow entry of a recently evicted page, or a swap entry from
 	 * shmem/tmpfs.  Return it without attempting to raise page count.
 	 */
-	if (!page || xa_is_value(page))
+	if (!folio || xa_is_value(folio))
 		goto out;
 
-	if (!page_cache_get_speculative(page))
+	if (!folio_try_get_rcu(folio))
 		goto repeat;
 
-	/*
-	 * Has the page moved or been split?
-	 * This is part of the lockless pagecache protocol. See
-	 * include/linux/pagemap.h for details.
-	 */
-	if (unlikely(page != xas_reload(&xas))) {
-		put_page(page);
+	if (unlikely(folio != xas_reload(&xas))) {
+		folio_put(folio);
 		goto repeat;
 	}
 out:
 	rcu_read_unlock();
 
-	return page;
+	return folio;
 }
 
 /**
-- 
2.30.2

[PATCH v14 38/39] mm/filemap: Add filemap_get_folio

[Matthew Wilcox (Oracle)]

filemap_get_folio() is a replacement for find_get_page().
Turn pagecache_get_page() into a wrapper around __filemap_get_folio().
Remove find_lock_head() as this use case is now covered by
filemap_get_folio().

Reduces overall kernel size by 209 bytes.  __filemap_get_folio() is
316 bytes shorter than pagecache_get_page() was, but the new
pagecache_get_page() is 99 bytes.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/pagemap.h | 41 +++++++++---------
 mm/filemap.c            | 92 ++++++++++++++++++++---------------------
 mm/folio-compat.c       | 12 ++++++
 3 files changed, 76 insertions(+), 69 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 19b2e3bea14c..b24933eced18 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -302,8 +302,26 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
 #define FGP_HEAD		0x00000080
 #define FGP_ENTRY		0x00000100
 
-struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
-		int fgp_flags, gfp_t cache_gfp_mask);
+struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
+		int fgp_flags, gfp_t gfp);
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
+		int fgp_flags, gfp_t gfp);
+
+/**
+ * filemap_get_folio - Find and get a folio.
+ * @mapping: The address_space to search.
+ * @index: The page index.
+ *
+ * Looks up the page cache entry at @mapping & @index.  If a folio is
+ * present, it is returned with an increased refcount.
+ *
+ * Otherwise, %NULL is returned.
+ */
+static inline struct folio *filemap_get_folio(struct address_space *mapping,
+					pgoff_t index)
+{
+	return __filemap_get_folio(mapping, index, 0, 0);
+}
 
 /**
  * find_get_page - find and get a page reference
@@ -346,25 +364,6 @@ static inline struct page *find_lock_page(struct address_space *mapping,
 	return pagecache_get_page(mapping, index, FGP_LOCK, 0);
 }
 
-/**
- * find_lock_head - Locate, pin and lock a pagecache page.
- * @mapping: The address_space to search.
- * @index: The page index.
- *
- * Looks up the page cache entry at @mapping & @index.  If there is a
- * page cache page, its head page is returned locked and with an increased
- * refcount.
- *
- * Context: May sleep.
- * Return: A struct page which is !PageTail, or %NULL if there is no page
- * in the cache for this index.
- */
-static inline struct page *find_lock_head(struct address_space *mapping,
-					pgoff_t index)
-{
-	return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0);
-}
-
 /**
  * find_or_create_page - locate or add a pagecache page
  * @mapping: the page's address_space
diff --git a/mm/filemap.c b/mm/filemap.c
index 85a457c7b7a7..061e285aae21 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1794,93 +1794,89 @@ static void *mapping_get_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /**
- * pagecache_get_page - Find and get a reference to a page.
+ * __filemap_get_folio - Find and get a reference to a folio.
  * @mapping: The address_space to search.
  * @index: The page index.
- * @fgp_flags: %FGP flags modify how the page is returned.
- * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified.
+ * @fgp_flags: %FGP flags modify how the folio is returned.
+ * @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
  *
  * Looks up the page cache entry at @mapping & @index.
  *
  * @fgp_flags can be zero or more of these flags:
  *
- * * %FGP_ACCESSED - The page will be marked accessed.
- * * %FGP_LOCK - The page is returned locked.
- * * %FGP_HEAD - If the page is present and a THP, return the head page
- *   rather than the exact page specified by the index.
+ * * %FGP_ACCESSED - The folio will be marked accessed.
+ * * %FGP_LOCK - The folio is returned locked.
  * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it
- *   instead of allocating a new page to replace it.
+ *   instead of allocating a new folio to replace it.
  * * %FGP_CREAT - If no page is present then a new page is allocated using
- *   @gfp_mask and added to the page cache and the VM's LRU list.
+ *   @gfp and added to the page cache and the VM's LRU list.
  *   The page is returned locked and with an increased refcount.
  * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
  *   page is already in cache.  If the page was allocated, unlock it before
  *   returning so the caller can do the same dance.
- * * %FGP_WRITE - The page will be written
- * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask
- * * %FGP_NOWAIT - Don't get blocked by page lock
+ * * %FGP_WRITE - The page will be written to by the caller.
+ * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
+ * * %FGP_NOWAIT - Don't get blocked by page lock.
  *
  * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
  * if the %GFP flags specified for %FGP_CREAT are atomic.
  *
  * If there is a page cache page, it is returned with an increased refcount.
  *
- * Return: The found page or %NULL otherwise.
+ * Return: The found folio or %NULL otherwise.
  */
-struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
-		int fgp_flags, gfp_t gfp_mask)
+struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
+		int fgp_flags, gfp_t gfp)
 {
-	struct page *page;
+	struct folio *folio;
 
 repeat:
-	page = mapping_get_entry(mapping, index);
-	if (xa_is_value(page)) {
+	folio = mapping_get_entry(mapping, index);
+	if (xa_is_value(folio)) {
 		if (fgp_flags & FGP_ENTRY)
-			return page;
-		page = NULL;
+			return folio;
+		folio = NULL;
 	}
-	if (!page)
+	if (!folio)
 		goto no_page;
 
 	if (fgp_flags & FGP_LOCK) {
 		if (fgp_flags & FGP_NOWAIT) {
-			if (!trylock_page(page)) {
-				put_page(page);
+			if (!folio_trylock(folio)) {
+				folio_put(folio);
 				return NULL;
 			}
 		} else {
-			lock_page(page);
+			folio_lock(folio);
 		}
 
 		/* Has the page been truncated? */
-		if (unlikely(page->mapping != mapping)) {
-			unlock_page(page);
-			put_page(page);
+		if (unlikely(folio->mapping != mapping)) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto repeat;
 		}
-		VM_BUG_ON_PAGE(!thp_contains(page, index), page);
+		VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
 	}
 
 	if (fgp_flags & FGP_ACCESSED)
-		mark_page_accessed(page);
+		folio_mark_accessed(folio);
 	else if (fgp_flags & FGP_WRITE) {
 		/* Clear idle flag for buffer write */
-		if (page_is_idle(page))
-			clear_page_idle(page);
+		if (folio_test_idle(folio))
+			folio_clear_idle(folio);
 	}
-	if (!(fgp_flags & FGP_HEAD))
-		page = find_subpage(page, index);
 
 no_page:
-	if (!page && (fgp_flags & FGP_CREAT)) {
+	if (!folio && (fgp_flags & FGP_CREAT)) {
 		int err;
 		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
-			gfp_mask |= __GFP_WRITE;
+			gfp |= __GFP_WRITE;
 		if (fgp_flags & FGP_NOFS)
-			gfp_mask &= ~__GFP_FS;
+			gfp &= ~__GFP_FS;
 
-		page = __page_cache_alloc(gfp_mask);
-		if (!page)
+		folio = filemap_alloc_folio(gfp, 0);
+		if (!folio)
 			return NULL;
 
 		if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
@@ -1888,27 +1884,27 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 
 		/* Init accessed so avoid atomic mark_page_accessed later */
 		if (fgp_flags & FGP_ACCESSED)
-			__SetPageReferenced(page);
+			__folio_set_referenced(folio);
 
-		err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
+		err = filemap_add_folio(mapping, folio, index, gfp);
 		if (unlikely(err)) {
-			put_page(page);
-			page = NULL;
+			folio_put(folio);
+			folio = NULL;
 			if (err == -EEXIST)
 				goto repeat;
 		}
 
 		/*
-		 * add_to_page_cache_lru locks the page, and for mmap we expect
-		 * an unlocked page.
+		 * filemap_add_folio locks the page, and for mmap
+		 * we expect an unlocked page.
 		 */
-		if (page && (fgp_flags & FGP_FOR_MMAP))
-			unlock_page(page);
+		if (folio && (fgp_flags & FGP_FOR_MMAP))
+			folio_unlock(folio);
 	}
 
-	return page;
+	return folio;
 }
-EXPORT_SYMBOL(pagecache_get_page);
+EXPORT_SYMBOL(__filemap_get_folio);
 
 static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max,
 		xa_mark_t mark)
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 6b19bc4ed6b0..e833e680e944 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -115,3 +115,15 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	return filemap_add_folio(mapping, page_folio(page), index, gfp);
 }
 EXPORT_SYMBOL(add_to_page_cache_lru);
+
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
+		int fgp_flags, gfp_t gfp)
+{
+	struct folio *folio;
+
+	folio = __filemap_get_folio(mapping, index, fgp_flags, gfp);
+	if ((fgp_flags & FGP_HEAD) || !folio || xa_is_value(folio))
+		return &folio->page;
+	return folio_file_page(folio, index);
+}
+EXPORT_SYMBOL(pagecache_get_page);
-- 
2.30.2

[PATCH v14 39/39] mm/filemap: Add FGP_STABLE

[Matthew Wilcox (Oracle)]

Allow filemap_get_folio() to wait for writeback to complete (if the
filesystem wants that behaviour).  This is the folio equivalent of
grab_cache_page_write_begin(), which is moved into the folio-compat
file as a reminder to migrate all the code using it.  This paves the
way for getting rid of AOP_FLAG_NOFS once grab_cache_page_write_begin()
is removed.

Kernel grows by 11 bytes.  filemap_get_folio() grows by 33 bytes but
grab_cache_page_write_begin() shrinks by 22 bytes to make up for it.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/pagemap.h |  1 +
 mm/filemap.c            | 25 +++----------------------
 mm/folio-compat.c       | 13 +++++++++++++
 3 files changed, 17 insertions(+), 22 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index b24933eced18..83c1a798265f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -301,6 +301,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
 #define FGP_FOR_MMAP		0x00000040
 #define FGP_HEAD		0x00000080
 #define FGP_ENTRY		0x00000100
+#define FGP_STABLE		0x00000200
 
 struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		int fgp_flags, gfp_t gfp);
diff --git a/mm/filemap.c b/mm/filemap.c
index 061e285aae21..0434c5a55fec 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1817,6 +1817,7 @@ static void *mapping_get_entry(struct address_space *mapping, pgoff_t index)
  * * %FGP_WRITE - The page will be written to by the caller.
  * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
  * * %FGP_NOWAIT - Don't get blocked by page lock.
+ * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
  *
  * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
  * if the %GFP flags specified for %FGP_CREAT are atomic.
@@ -1867,6 +1868,8 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			folio_clear_idle(folio);
 	}
 
+	if (fgp_flags & FGP_STABLE)
+		folio_wait_stable(folio);
 no_page:
 	if (!folio && (fgp_flags & FGP_CREAT)) {
 		int err;
@@ -3590,28 +3593,6 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 }
 EXPORT_SYMBOL(generic_file_direct_write);
 
-/*
- * Find or create a page at the given pagecache position. Return the locked
- * page. This function is specifically for buffered writes.
- */
-struct page *grab_cache_page_write_begin(struct address_space *mapping,
-					pgoff_t index, unsigned flags)
-{
-	struct page *page;
-	int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;
-
-	if (flags & AOP_FLAG_NOFS)
-		fgp_flags |= FGP_NOFS;
-
-	page = pagecache_get_page(mapping, index, fgp_flags,
-			mapping_gfp_mask(mapping));
-	if (page)
-		wait_for_stable_page(page);
-
-	return page;
-}
-EXPORT_SYMBOL(grab_cache_page_write_begin);
-
 ssize_t generic_perform_write(struct file *file,
 				struct iov_iter *i, loff_t pos)
 {
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index e833e680e944..5b6ae1da314e 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -116,6 +116,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 }
 EXPORT_SYMBOL(add_to_page_cache_lru);
 
+noinline
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		int fgp_flags, gfp_t gfp)
 {
@@ -127,3 +128,15 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 	return folio_file_page(folio, index);
 }
 EXPORT_SYMBOL(pagecache_get_page);
+
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+					pgoff_t index, unsigned flags)
+{
+	unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
+
+	if (flags & AOP_FLAG_NOFS)
+		fgp_flags |= FGP_NOFS;
+	return pagecache_get_page(mapping, index, fgp_flags,
+			mapping_gfp_mask(mapping));
+}
+EXPORT_SYMBOL(grab_cache_page_write_begin);
-- 
2.30.2