[PATCH v6 2/3] mm/swap: use swap_ops to register swap device's methods

[Baoquan He <baoquan.he@linux.dev>]

This simplifies codes and makes logic clearer. And also makes later any
new swap device type being added easier to handle.

Currently there are three types of swap devices: bdev_fs, bdev_sync
and bdev_async, and only operations read_folio and write_folio are
included. In the future, there could be more swap device types added
and more appropriate opeations adapted into swap_ops.

Suggested-by: Chris Li <chrisl@kernel.org>
Acked-by: Chris Li <chrisl@kernel.org>
Co-developed-by: Barry Song <baohua@kernel.org>
Signed-off-by: Barry Song <baohua@kernel.org>
Signed-off-by: Baoquan He <baoquan.he@linux.dev>
---
 include/linux/swap.h |   2 +
 mm/swap.h            |  10 ++++-
 mm/swap_io.c         | 102 +++++++++++++++++++++++++------------------
 mm/swapfile.c        |   9 ++++
 mm/zswap.c           |   2 +-
 5 files changed, 80 insertions(+), 45 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index aa89e1d30a77..85f15ec326c1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -243,6 +243,7 @@ struct swap_sequential_cluster {
 	unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
 };
 
+struct swap_ops;
 /*
  * The in-memory structure used to track swap areas.
  */
@@ -283,6 +284,7 @@ struct swap_info_struct {
 	struct work_struct reclaim_work; /* reclaim worker */
 	struct list_head discard_clusters; /* discard clusters list */
 	struct plist_node avail_list;   /* entry in swap_avail_head */
+	const struct swap_ops *ops;
 };
 
 static inline swp_entry_t page_swap_entry(struct page *page)
diff --git a/mm/swap.h b/mm/swap.h
index 161185057993..29bdc679fa98 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -217,6 +217,15 @@ extern void __swap_cluster_free_entries(struct swap_info_struct *si,
 /* linux/mm/swap_io.c */
 int sio_pool_init(void);
 struct swap_iocb;
+struct swap_ops {
+	void (*read_folio)(struct swap_info_struct *sis,
+			struct folio *folio,
+			struct swap_iocb **plug);
+	void (*write_folio)(struct swap_info_struct *sis,
+			struct folio *folio,
+			struct swap_iocb **plug);
+};
+int init_swap_ops(struct swap_info_struct *sis);
 void swap_read_folio(struct folio *folio, struct swap_iocb **plug);
 void __swap_read_unplug(struct swap_iocb *plug);
 static inline void swap_read_unplug(struct swap_iocb *plug)
@@ -226,7 +235,6 @@ static inline void swap_read_unplug(struct swap_iocb *plug)
 }
 void swap_write_unplug(struct swap_iocb *sio);
 int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug);
-void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug);
 
 /* linux/mm/swap_state.c */
 extern struct address_space swap_space __read_mostly;
diff --git a/mm/swap_io.c b/mm/swap_io.c
index 7c1a3a3a53f8..3f9aee5b6a4d 100644
--- a/mm/swap_io.c
+++ b/mm/swap_io.c
@@ -238,6 +238,7 @@ static void swap_zeromap_folio_clear(struct folio *folio)
 int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
 {
 	int ret = 0;
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 
 	if (folio_free_swap(folio))
 		goto out_unlock;
@@ -283,7 +284,7 @@ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
 	}
 	rcu_read_unlock();
 
-	__swap_writepage(folio, swap_plug);
+	sis->ops->write_folio(sis, folio, swap_plug);
 	return 0;
 out_unlock:
 	folio_unlock(folio);
@@ -373,10 +374,11 @@ static void sio_write_complete(struct kiocb *iocb, long ret)
 	mempool_free(sio, sio_pool);
 }
 
-static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
+static void swap_writepage_fs(struct swap_info_struct *sis,
+			      struct folio *folio,
+			      struct swap_iocb **swap_plug)
 {
 	struct swap_iocb *sio = swap_plug ? *swap_plug : NULL;
-	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 	struct file *swap_file = sis->swap_file;
 	loff_t pos = swap_dev_pos(folio->swap);
 
@@ -409,8 +411,9 @@ static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
 		*swap_plug = sio;
 }
 
-static void swap_writepage_bdev_sync(struct folio *folio,
-		struct swap_info_struct *sis)
+static void swap_writepage_bdev_sync(struct swap_info_struct *sis,
+				     struct folio *folio,
+				     struct swap_iocb **plug)
 {
 	struct bio_vec bv;
 	struct bio bio;
@@ -429,8 +432,9 @@ static void swap_writepage_bdev_sync(struct folio *folio,
 	__end_swap_bio_write(&bio);
 }
 
-static void swap_writepage_bdev_async(struct folio *folio,
-		struct swap_info_struct *sis)
+static void swap_writepage_bdev_async(struct swap_info_struct *sis,
+				      struct folio *folio,
+				      struct swap_iocb **plug)
 {
 	struct bio *bio;
 
@@ -446,29 +450,6 @@ static void swap_writepage_bdev_async(struct folio *folio,
 	submit_bio(bio);
 }
 
-void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
-{
-	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
-
-	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
-	/*
-	 * ->flags can be updated non-atomically,
-	 * but that will never affect SWP_FS_OPS, so the data_race
-	 * is safe.
-	 */
-	if (data_race(sis->flags & SWP_FS_OPS))
-		swap_writepage_fs(folio, swap_plug);
-	/*
-	 * ->flags can be updated non-atomically,
-	 * but that will never affect SWP_SYNCHRONOUS_IO, so the data_race
-	 * is safe.
-	 */
-	else if (data_race(sis->flags & SWP_SYNCHRONOUS_IO))
-		swap_writepage_bdev_sync(folio, sis);
-	else
-		swap_writepage_bdev_async(folio, sis);
-}
-
 void swap_write_unplug(struct swap_iocb *sio)
 {
 	struct iov_iter from;
@@ -537,9 +518,10 @@ static bool swap_read_folio_zeromap(struct folio *folio)
 	return true;
 }
 
-static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
+static void swap_read_folio_fs(struct swap_info_struct *sis,
+			       struct folio *folio,
+			       struct swap_iocb **plug)
 {
-	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 	struct swap_iocb *sio = NULL;
 	loff_t pos = swap_dev_pos(folio->swap);
 
@@ -571,8 +553,9 @@ static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
 		*plug = sio;
 }
 
-static void swap_read_folio_bdev_sync(struct folio *folio,
-		struct swap_info_struct *sis)
+static void swap_read_folio_bdev_sync(struct swap_info_struct *sis,
+				      struct folio *folio,
+				      struct swap_iocb **plug)
 {
 	struct bio_vec bv;
 	struct bio bio;
@@ -593,8 +576,9 @@ static void swap_read_folio_bdev_sync(struct folio *folio,
 	put_task_struct(current);
 }
 
-static void swap_read_folio_bdev_async(struct folio *folio,
-		struct swap_info_struct *sis)
+static void swap_read_folio_bdev_async(struct swap_info_struct *sis,
+				       struct folio *folio,
+				       struct swap_iocb **plug)
 {
 	struct bio *bio;
 
@@ -608,6 +592,44 @@ static void swap_read_folio_bdev_async(struct folio *folio,
 	submit_bio(bio);
 }
 
+static const struct swap_ops bdev_fs_swap_ops = {
+	.read_folio = swap_read_folio_fs,
+	.write_folio = swap_writepage_fs,
+};
+
+static const struct swap_ops bdev_sync_swap_ops = {
+	.read_folio = swap_read_folio_bdev_sync,
+	.write_folio = swap_writepage_bdev_sync,
+};
+
+static const struct swap_ops bdev_async_swap_ops = {
+	.read_folio = swap_read_folio_bdev_async,
+	.write_folio = swap_writepage_bdev_async,
+};
+
+int init_swap_ops(struct swap_info_struct *sis)
+{
+	/*
+	 * ->flags can be updated non-atomically, but that will
+	 * never affect SWP_FS_OPS, so the data_race is safe.
+	 */
+	if (data_race(sis->flags & SWP_FS_OPS))
+		sis->ops = &bdev_fs_swap_ops;
+	/*
+	 * ->flags can be updated non-atomically, but that will
+	 * never affect SWP_SYNCHRONOUS_IO, so the data_race is safe.
+	 */
+	else if (data_race(sis->flags & SWP_SYNCHRONOUS_IO))
+		sis->ops = &bdev_sync_swap_ops;
+	else
+		sis->ops = &bdev_async_swap_ops;
+
+	if (!sis->ops || !sis->ops->read_folio || !sis->ops->write_folio)
+		return -EINVAL;
+
+	return 0;
+}
+
 void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 {
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
@@ -642,13 +664,7 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 	/* We have to read from slower devices. Increase zswap protection. */
 	zswap_folio_swapin(folio);
 
-	if (data_race(sis->flags & SWP_FS_OPS)) {
-		swap_read_folio_fs(folio, plug);
-	} else if (synchronous) {
-		swap_read_folio_bdev_sync(folio, sis);
-	} else {
-		swap_read_folio_bdev_async(folio, sis);
-	}
+	sis->ops->read_folio(sis, folio, plug);
 
 finish:
 	if (workingset) {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4840fd40f36f..8c42632e6765 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3780,6 +3780,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto free_swap_zswap;
 	}
 
+	/*
+	 * init_swap_ops() sets si->ops based on flags. It does not need
+	 * swapon_mutex, and must complete before enable_swap_info()
+	 * exposes the device.
+	 */
+	error = init_swap_ops(si);
+	if (error)
+		goto bad_swap_unlock_inode;
+
 	mutex_lock(&swapon_mutex);
 	prio = DEF_SWAP_PRIO;
 	if (swap_flags & SWAP_FLAG_PREFER)
diff --git a/mm/zswap.c b/mm/zswap.c
index 4b5149173b0e..192401f46de4 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1054,7 +1054,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	folio_set_reclaim(folio);
 
 	/* start writeback */
-	__swap_writepage(folio, NULL);
+	si->ops->write_folio(si, folio, NULL);
 
 out:
 	if (ret && ret != -EEXIST) {
-- 
2.52.0