[PATCH v2 01/14] f2fs: extend folio state for large folio write path

[Nanzhe Zhao <zhaonanzhe@xiaomi.com>]

Large folio write path needs a subpage status bitmap and write
pages pending counter, while keeping compatible with f2fs private
flags.

Move struct f2fs_folio_state to f2fs.h, add private_flags and
subpage state bitmap, and change PAGE_PRIVATE functions to be
compatible with f2fs_folio_state. Allocate f2fs_folio_state via kzalloc
instead of kmem_cache, since the state size depends on the folio order.

Note: Now if a path wants to use f2fs_folio_state, it must call
`folio_has_ffs` instead of `folio_test_large`` to make check.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 72 ++++++++++++++++++++++++++++++++------------------
 fs/f2fs/f2fs.h | 70 +++++++++++++++++++++++++++++++++++-------------
 2 files changed, 98 insertions(+), 44 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a3b02c067e89..b3303109a696 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -32,15 +32,9 @@
 
 static struct kmem_cache *bio_post_read_ctx_cache;
 static struct kmem_cache *bio_entry_slab;
-static struct kmem_cache *ffs_entry_slab;
 static mempool_t *bio_post_read_ctx_pool;
 static struct bio_set f2fs_bioset;
 
-struct f2fs_folio_state {
-	spinlock_t		state_lock;
-	unsigned int		read_pages_pending;
-};
-
 struct f2fs_bio {
 	struct work_struct work;
 	struct bio bio;
@@ -125,6 +119,9 @@ struct bio_post_read_ctx {
 	block_t fs_blkaddr;
 };
 
+static bool __ffs_mark_subrange_uptodate(struct folio *folio,
+		struct f2fs_folio_state *ffs, size_t offset, size_t len);
+
 /*
  * Update and unlock a bio's pages, and free the bio.
  *
@@ -139,6 +136,23 @@ struct bio_post_read_ctx {
  * called (i.e., I/O error or decryption error, but *not* verity error), and
  * release the bio's reference to the decompress_io_ctx of the page's cluster.
  */
+/*
+ * Update read_pages_pending.
+ */
+static inline void f2fs_update_read_folio_pending(struct folio *folio, int nr)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned long flags;
+
+	if (!f2fs_folio_has_ffs(folio))
+		return;
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	spin_lock_irqsave(&ffs->state_lock, flags);
+	ffs->read_pages_pending += nr;
+	spin_unlock_irqrestore(&ffs->state_lock, flags);
+}
+
 static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 {
 	struct folio_iter fi;
@@ -147,7 +161,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 
 	bio_for_each_folio_all(fi, bio) {
 		struct folio *folio = fi.folio;
-		unsigned nr_pages = fi.length >> PAGE_SHIFT;
+		unsigned int nr_pages = fi.length >> PAGE_SHIFT;
 		bool finished = true;
 
 		if (!folio_test_large(folio) &&
@@ -2487,17 +2501,31 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 }
 #endif
 
-static struct f2fs_folio_state *ffs_find_or_alloc(struct folio *folio)
+struct f2fs_folio_state *f2fs_ffs_find_or_alloc(struct folio *folio)
 {
-	struct f2fs_folio_state *ffs = folio->private;
+	struct f2fs_folio_state *ffs;
+	unsigned int nr_subpages = folio_nr_pages(folio);
+	unsigned long private = (unsigned long)folio->private;
+
+	f2fs_bug_on(F2FS_F_SB(folio), !folio_test_large(folio));
+	f2fs_bug_on(F2FS_F_SB(folio),
+		    test_bit(PAGE_PRIVATE_NOT_POINTER, &private));
 
-	if (ffs)
-		return ffs;
+	if (f2fs_folio_has_ffs(folio))
+		return (struct f2fs_folio_state *)folio->private;
 
-	ffs = f2fs_kmem_cache_alloc(ffs_entry_slab,
-			GFP_NOIO | __GFP_ZERO, true, NULL);
+	ffs = f2fs_kmalloc(F2FS_F_SB(folio),
+			struct_size(ffs, state, BITS_TO_LONGS(2 * nr_subpages)),
+			GFP_NOFS | __GFP_ZERO);
+	if (!ffs)
+		return NULL;
 
 	spin_lock_init(&ffs->state_lock);
+	if (folio_test_uptodate(folio))
+		bitmap_set(ffs->state, 0, nr_subpages);
+	if (folio_test_dirty(folio))
+		bitmap_set(ffs->state, nr_subpages, nr_subpages);
+
 	folio_attach_private(folio, ffs);
 	return ffs;
 }
@@ -2506,7 +2534,7 @@ static void ffs_detach_free(struct folio *folio)
 {
 	struct f2fs_folio_state *ffs;
 
-	if (!folio_test_large(folio)) {
+	if (!f2fs_folio_has_ffs(folio)) {
 		folio_detach_private(folio);
 		return;
 	}
@@ -2516,7 +2544,8 @@ static void ffs_detach_free(struct folio *folio)
 		return;
 
 	WARN_ON_ONCE(ffs->read_pages_pending != 0);
-	kmem_cache_free(ffs_entry_slab, ffs);
+	WARN_ON_ONCE(atomic_read(&ffs->write_pages_pending));
+	kfree(ffs);
 }
 
 static int f2fs_read_data_large_folio(struct inode *inode,
@@ -2529,7 +2558,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	pgoff_t index, offset, next_pgofs = 0;
 	unsigned max_nr_pages = rac ? readahead_count(rac) :
 				folio_nr_pages(folio);
-	unsigned nrpages;
+	unsigned int nrpages;
 	struct f2fs_folio_state *ffs;
 	int ret = 0;
 	bool folio_in_bio = false;
@@ -2605,7 +2634,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 		 * to prevent from premature folio_end_read() call on folio
 		 */
 		if (folio_test_large(folio)) {
-			ffs = ffs_find_or_alloc(folio);
+			ffs = f2fs_ffs_find_or_alloc(folio);
 
 			/* set the bitmap to wait */
 			spin_lock_irq(&ffs->state_lock);
@@ -4522,21 +4551,12 @@ int __init f2fs_init_bio_entry_cache(void)
 	if (!bio_entry_slab)
 		return -ENOMEM;
 
-	ffs_entry_slab = f2fs_kmem_cache_create("f2fs_ffs_slab",
-			sizeof(struct f2fs_folio_state));
-
-	if (!ffs_entry_slab) {
-		kmem_cache_destroy(bio_entry_slab);
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
 void f2fs_destroy_bio_entry_cache(void)
 {
 	kmem_cache_destroy(bio_entry_slab);
-	kmem_cache_destroy(ffs_entry_slab);
 }
 
 static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ebc621f302e1..9a2366a6c113 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1618,6 +1618,18 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr);
  * Layout B: lowest bit should be 0
  * page.private is a wrapped pointer.
  */
+
+struct f2fs_folio_state {
+	spinlock_t		state_lock;
+	unsigned int		read_pages_pending;
+	atomic_t		write_pages_pending;
+	unsigned long		private_flags;
+	/* state[0..nr_subpages - 1] tracks uptodate subpages.
+	 * state[nr_subpages..2 * nr_subpages - 1] tracks dirty subpages.
+	 */
+	unsigned long		state[];
+};
+
 enum {
 	PAGE_PRIVATE_NOT_POINTER,		/* private contains non-pointer data */
 	PAGE_PRIVATE_ONGOING_MIGRATION,		/* data page which is on-going migrating */
@@ -1627,6 +1639,13 @@ enum {
 	PAGE_PRIVATE_MAX
 };
 
+static inline bool f2fs_folio_has_ffs(const struct folio *folio)
+{
+	unsigned long private = (unsigned long)folio->private;
+
+	return folio_test_large(folio) && private;
+}
+
 /* For compression */
 enum compress_algorithm_type {
 	COMPRESS_LZO,
@@ -2738,13 +2757,35 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 	return -ENOSPC;
 }
 
+static inline unsigned long f2fs_folio_get_private_flags(const struct folio *folio)
+{
+	unsigned long private = (unsigned long)folio->private;
+
+	if (f2fs_folio_has_ffs(folio)) {
+		struct f2fs_folio_state *ffs = (struct f2fs_folio_state *)private;
+
+		return READ_ONCE(ffs->private_flags);
+	}
+
+	if (test_bit(PAGE_PRIVATE_NOT_POINTER, &private))
+		return private;
+
+	return 0;
+}
+
+static inline unsigned long *f2fs_folio_flags_addr(struct folio *folio)
+{
+	if (f2fs_folio_has_ffs(folio))
+		return &((struct f2fs_folio_state *)folio->private)->private_flags;
+
+	return (unsigned long *)&folio->private;
+}
+
 #define PAGE_PRIVATE_GET_FUNC(name, flagname) \
 static inline bool folio_test_f2fs_##name(const struct folio *folio)	\
 {									\
-	unsigned long priv = (unsigned long)folio->private;		\
-	unsigned long v = (1UL << PAGE_PRIVATE_NOT_POINTER) |		\
-			     (1UL << PAGE_PRIVATE_##flagname);		\
-	return (priv & v) == v;						\
+	return f2fs_folio_get_private_flags(folio) &			\
+				(1UL << PAGE_PRIVATE_##flagname);	\
 }									\
 static inline bool page_private_##name(struct page *page) \
 { \
@@ -2756,14 +2797,10 @@ static inline bool page_private_##name(struct page *page) \
 #define PAGE_PRIVATE_SET_FUNC(name, flagname) \
 static inline void folio_set_f2fs_##name(struct folio *folio)		\
 {									\
-	unsigned long v = (1UL << PAGE_PRIVATE_NOT_POINTER) |		\
-			     (1UL << PAGE_PRIVATE_##flagname);		\
 	if (!folio->private)						\
-		folio_attach_private(folio, (void *)v);			\
-	else {								\
-		v |= (unsigned long)folio->private;			\
-		folio->private = (void *)v;				\
-	}								\
+		folio_attach_private(folio,				\
+				(void *)BIT(PAGE_PRIVATE_NOT_POINTER));	\
+	set_bit(PAGE_PRIVATE_##flagname, f2fs_folio_flags_addr(folio));	\
 }									\
 static inline void set_page_private_##name(struct page *page) \
 { \
@@ -2776,13 +2813,10 @@ static inline void set_page_private_##name(struct page *page) \
 #define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \
 static inline void folio_clear_f2fs_##name(struct folio *folio)		\
 {									\
-	unsigned long v = (unsigned long)folio->private;		\
-									\
-	v &= ~(1UL << PAGE_PRIVATE_##flagname);				\
-	if (v == (1UL << PAGE_PRIVATE_NOT_POINTER))			\
+	clear_bit(PAGE_PRIVATE_##flagname,				\
+		  f2fs_folio_flags_addr(folio));			\
+	if (folio->private == (void *)BIT(PAGE_PRIVATE_NOT_POINTER))	\
 		folio_detach_private(folio);				\
-	else								\
-		folio->private = (void *)v;				\
 }									\
 static inline void clear_page_private_##name(struct page *page) \
 { \
@@ -2808,7 +2842,7 @@ PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
 
 static inline unsigned long folio_get_f2fs_data(struct folio *folio)
 {
-	unsigned long data = (unsigned long)folio->private;
+	unsigned long data = f2fs_folio_get_private_flags(folio);
 
 	if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data))
 		return 0;
-- 
2.43.0