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

[Chao Yu <chao@kernel.org>]

On 8/26/26 16:26, Nanzhe Zhao wrote:
> 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/compress.c |  2 +
>  fs/f2fs/data.c     | 60 ++++++++++++++++--------------
>  fs/f2fs/f2fs.h     | 92 ++++++++++++++++++++++++++++++++++++----------
>  fs/f2fs/segment.c  |  2 +-
>  4 files changed, 108 insertions(+), 48 deletions(-)
> 
> diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
> index 91855d91bbdd..84da3e39efb4 100644
> --- a/fs/f2fs/compress.c
> +++ b/fs/f2fs/compress.c
> @@ -78,6 +78,8 @@ bool f2fs_is_compressed_page(struct folio *folio)
>  		return false;
>  	if (folio_test_f2fs_nonpointer(folio))
>  		return false;
> +	if (f2fs_folio_has_ffs(folio))
> +		return false;

Shouldn't this be changed in "f2fs: make compressed files compatible with
large folio" or other patch? I guess in this patch we only introduce new
ffs facilities.

>  
>  	f2fs_bug_on(F2FS_F_SB(folio),
>  		*((u32 *)folio->private) != F2FS_COMPRESSED_PAGE_MAGIC);
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index 6ae0eb37d20f..578a90d427e2 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -32,20 +32,13 @@
>  
>  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;
>  };
> -

Unnecessary change.

>  #define	F2FS_BIO_POOL_SIZE	NR_CURSEG_TYPE
>  
>  int __init f2fs_init_bioset(void)
> @@ -133,6 +126,9 @@ 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.
>   *
> @@ -155,7 +151,7 @@ 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;

No need to change in this patch?

>  		bool finished = true;
>  
>  		if (!folio_test_large(folio) &&
> @@ -360,6 +356,7 @@ static void f2fs_write_end_bio(struct bio *bio)
>  
>  	bio_for_each_folio_all(fi, bio) {
>  		struct folio *folio = fi.folio;
> +		unsigned int nr_pages = fi.length >> PAGE_SHIFT;

No need to change in this patch?

>  		enum count_type type;
>  
>  		if (fscrypt_is_bounce_folio(folio)) {
> @@ -2516,17 +2513,32 @@ 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_flags = 0;
> +
> +	f2fs_bug_on(F2FS_F_SB(folio), !folio_test_large(folio));
>  
> -	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);
> +	if (folio_test_private(folio) && folio_test_f2fs_nonpointer(folio))
> +		private_flags = (unsigned long)folio->private;
> +
> +	ffs = kzalloc(struct_size(ffs, state, BITS_TO_LONGS(2 * nr_subpages)),
> +			GFP_NOIO | __GFP_NOFAIL);
>  
>  	spin_lock_init(&ffs->state_lock);
> +	ffs->private_flags = private_flags;
> +	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);
> +
> +	if (folio_test_private(folio))
> +		folio_detach_private(folio);
>  	folio_attach_private(folio, ffs);
>  	return ffs;
>  }
> @@ -2535,7 +2547,7 @@ 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;
>  	}
> @@ -2545,7 +2557,8 @@ 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,
> @@ -2558,7 +2571,7 @@ 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, len_blks;
>  	struct f2fs_folio_state *ffs;
>  	int ret = 0;
>  	bool folio_in_bio = false;
> @@ -2634,7 +2647,7 @@ 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);
> @@ -2987,7 +3000,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
>  		return true;
>  
>  	if (fio) {
> -		if (page_private_gcing(fio->page))
> +		if (folio_test_f2fs_gcing(fio->folio))

Shouldn't this be changed in "f2fs: make GC migration large-folio aware"?

>  			return true;
>  		if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
>  			f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
> @@ -4586,21 +4599,12 @@ 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 16720f1f0a9c..2e8f85cea6d0 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -1628,6 +1628,18 @@ 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 */
> @@ -1637,6 +1649,14 @@ 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 &&
> +		!(private & BIT(PAGE_PRIVATE_NOT_POINTER));

Is this a bug? in which case we will set PAGE_PRIVATE_NOT_POINTER in
a large folio? maybe I missed some cases...

folio_test_large(folio) && private is true and
(private & BIT(PAGE_PRIVATE_NOT_POINTER) is true?

> +}
> +
>  /* For compression */
>  enum compress_algorithm_type {
>  	COMPRESS_LZO,
> @@ -2682,10 +2702,57 @@ 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)
> +{
> +	if (f2fs_folio_has_ffs(folio)) {
> +		struct f2fs_folio_state *ffs = folio->private;
> +
> +		return ffs->private_flags;
> +	}
> +
> +	return (unsigned long)folio->private;
> +}
> +
> +static inline void f2fs_folio_set_private_flags(struct folio *folio,
> +						unsigned long flags)
> +{
> +	if (f2fs_folio_has_ffs(folio)) {
> +		struct f2fs_folio_state *ffs = folio->private;
> +
> +		ffs->private_flags |= flags;
> +		return;
> +	}
> +
> +	if (!folio_test_private(folio))
> +		folio_attach_private(folio, (void *)flags);
> +	else
> +		folio->private = (void *)((unsigned long)folio->private | flags);
> +}
> +
> +static inline void f2fs_folio_clear_private_flags(struct folio *folio,
> +						 unsigned long flags)
> +{
> +	unsigned long private;
> +
> +	if (f2fs_folio_has_ffs(folio)) {
> +		struct f2fs_folio_state *ffs = folio->private;
> +
> +		ffs->private_flags &= ~flags;
> +		return;
> +	}
> +
> +	private = (unsigned long)folio->private;
> +	private &= ~flags;
> +	if (private == BIT(PAGE_PRIVATE_NOT_POINTER))
> +		folio_detach_private(folio);
> +	else
> +		folio->private = (void *)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 priv = f2fs_folio_get_private_flags(folio);		\
>  	unsigned long v = (1UL << PAGE_PRIVATE_NOT_POINTER) |		\
>  			     (1UL << PAGE_PRIVATE_##flagname);		\
>  	return (priv & v) == v;						\
> @@ -2702,12 +2769,7 @@ 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;				\
> -	}								\
> +	f2fs_folio_set_private_flags(folio, v);				\
>  }									\
>  static inline void set_page_private_##name(struct page *page) \
>  { \
> @@ -2720,13 +2782,8 @@ 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))			\
> -		folio_detach_private(folio);				\
> -	else								\
> -		folio->private = (void *)v;				\
> +	f2fs_folio_clear_private_flags(folio,				\
> +			1UL << PAGE_PRIVATE_##flagname);			\
>  }									\
>  static inline void clear_page_private_##name(struct page *page) \
>  { \
> @@ -2752,7 +2809,7 @@ 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;
> @@ -2763,10 +2820,7 @@ static inline void folio_set_f2fs_data(struct folio *folio, unsigned long data)
>  {
>  	data = (1UL << PAGE_PRIVATE_NOT_POINTER) | (data << PAGE_PRIVATE_MAX);
>  
> -	if (!folio_test_private(folio))
> -		folio_attach_private(folio, (void *)data);
> -	else
> -		folio->private = (void *)((unsigned long)folio->private | data);
> +	f2fs_folio_set_private_flags(folio, data);
>  }
>  
>  static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> index ed6f2947210b..df10119d94ad 100644
> --- a/fs/f2fs/segment.c
> +++ b/fs/f2fs/segment.c
> @@ -3803,7 +3803,7 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
>  		if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
>  			return CURSEG_COLD_DATA_PINNED;
>  
> -		if (page_private_gcing(fio->page)) {
> +		if (folio_test_f2fs_gcing(fio->folio)) {

Shouldn't this be changed in "f2fs: make GC migration large-folio aware"?

Thanks,

>  			if (fio->sbi->am.atgc_enabled &&
>  				(fio->io_type == FS_DATA_IO) &&
>  				(fio->sbi->gc_mode != GC_URGENT_HIGH) &&