Skip to contentSkip to conversation

better block swap batching and a different take on swap_ops v2

PATCH In review Christoph Hellwig 6 participants 37 messages Jun 1 – Jun 11

Subsystems (16)
lore
Share & tools
lore
#0 lore raw

Hi all,

this series makes use of the swap_iocb for block as well so that it doesn't do inefficient single-bio I/O, and then rebases the swap_ops from Baoquan on top of the now very different method structure.

When running doing kernels builds, which is a workload that doesn't really do much THP anonymous memory it still gets 2x clustering for writeout and 1.2x for reading back swap in. The overall times do not actually change, though.

Note that the buildbot is slow at the moment, so while I fixed all issues from the previous round, that run did take multiple days and the new one is still pending, so I'd rather get a v1 out now as we're most likely to have additional roundtrips anyway.

Changes since v1:
- drop the memcg accounting for fs backed swap as it can't really work as-is
- change the related refactoring to not create a bisection hazard or compile issue with the wrong set of cgroup config options enabled
- remove a now dead function

Diffstat:

 Documentation/filesystems/locking.rst     |    5 
 Documentation/filesystems/vfs.rst         |    4 
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c |    2 
 drivers/gpu/drm/ttm/ttm_backup.c          |    2 
 fs/nfs/file.c                             |    4 
 fs/smb/client/file.c                      |    4 
 include/linux/shmem_fs.h                  |    5 
 include/linux/swap.h                      |    7 
 include/linux/vm_event_item.h             |    4 
 mm/madvise.c                              |   16 
 mm/page_io.c                              |  586 ++++++++++++++----------------
 mm/shmem.c                                |   18 
 mm/swap.h                                 |   61 +--
 mm/swap_state.c                           |   53 +-
 mm/swapfile.c                             |   11 
 mm/vmscan.c                               |   88 ++--
 mm/vmstat.c                               |    6 
 mm/zswap.c                                |    4 
 18 files changed, 450 insertions(+), 430 deletions(-)
#1 lore raw

PATCH 1/8 shmem: provide a shmem_write_folio wrapper

Provide a wrapper for the shmem abuses in drm to preparare for swap I/O refactoring by keepin swap_iocb handling entirely contained in mm/.

---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 2 +-
 drivers/gpu/drm/ttm/ttm_backup.c          | 2 +-
 include/linux/shmem_fs.h                  | 5 +----
 mm/shmem.c                                | 7 ++++++-
 mm/swap.h                                 | 4 ++++
 5 files changed, 13 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/gem/i915_gem_shmem.c +1 -1
index 06543ae60706..ef9440166295 100644
@@ -325,7 +325,7 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
 		if (folio_mapped(folio))
 			folio_redirty_for_writepage(&wbc, folio);
 		else
-			error = shmem_writeout(folio, NULL, NULL);
+			error = shmem_write_folio(folio);
 	}
 }
 
drivers/gpu/drm/ttm/ttm_backup.c +1 -1
index 81df4cb5606b..c5b813a563e7 100644
@@ -117,7 +117,7 @@ ttm_backup_backup_page(struct file *backup, struct page *page,
 	if (writeback && !folio_mapped(to_folio) &&
 	    folio_clear_dirty_for_io(to_folio)) {
 		folio_set_reclaim(to_folio);
-		ret = shmem_writeout(to_folio, NULL, NULL);
+		ret = shmem_write_folio(to_folio);
 		if (!folio_test_writeback(to_folio))
 			folio_clear_reclaim(to_folio);
 		/*
include/linux/shmem_fs.h +1 -4
index acb8dd961b45..f35c752f27af 100644
@@ -12,8 +12,6 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/bits.h>
 
-struct swap_iocb;
-
 /* inode in-kernel data */
 
 #ifdef CONFIG_TMPFS_QUOTA
@@ -122,8 +120,7 @@ static inline bool shmem_mapping(const struct address_space *mapping)
 void shmem_unlock_mapping(struct address_space *mapping);
 struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
-		struct list_head *folio_list);
+int shmem_write_folio(struct folio *folio);
 void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end);
 int shmem_unuse(unsigned int type);
 
mm/shmem.c +6 -1
index 56c23a7b15c7..d10735e49b25 100644
@@ -1738,7 +1738,12 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 	folio_mark_dirty(folio);
 	return AOP_WRITEPAGE_ACTIVATE;	/* Return with folio locked */
 }
-EXPORT_SYMBOL_GPL(shmem_writeout);
+
+int shmem_write_folio(struct folio *folio)
+{
+	return shmem_writeout(folio, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(shmem_write_folio);
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS)
 static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
mm/swap.h +4 -0
index 77d2d14eda42..4f86ef338a60 100644
@@ -473,4 +473,8 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 }
 
 #endif /* CONFIG_SWAP */
+
+int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+		struct list_head *folio_list);
+
 #endif /* _MM_SWAP_H */
Signature · 1 line
2.53.0
reviewer Reviewed-by on v1 1/8
#2 lore raw

Re: [PATCH 1/8] shmem: provide a shmem_write_folio wrapper

Quoted 1 line · Christoph Hellwig

Provide a wrapper for the shmem abuses in drm to preparare for swap I/O

                                                   ~~~~~ prepare, typo
Quoted 1 line

refactoring by keepin swap_iocb handling entirely contained in mm/.

                 ~~~~~ keeping, typo
Quoted 9 lines
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 2 +-
 drivers/gpu/drm/ttm/ttm_backup.c          | 2 +-
 include/linux/shmem_fs.h                  | 5 +----
 mm/shmem.c                                | 7 ++++++-
 mm/swap.h                                 | 4 ++++
 5 files changed, 13 insertions(+), 7 deletions(-)

Other then typos, LGTM,

Quoted 84 lines
drivers/gpu/drm/i915/gem/i915_gem_shmem.c +1 -1
index 06543ae60706..ef9440166295 100644
@@ -325,7 +325,7 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
 		if (folio_mapped(folio))
 			folio_redirty_for_writepage(&wbc, folio);
 		else
-			error = shmem_writeout(folio, NULL, NULL);
+			error = shmem_write_folio(folio);
 	}
 }
 
drivers/gpu/drm/ttm/ttm_backup.c +1 -1
index 81df4cb5606b..c5b813a563e7 100644
@@ -117,7 +117,7 @@ ttm_backup_backup_page(struct file *backup, struct page *page,
 	if (writeback && !folio_mapped(to_folio) &&
 	    folio_clear_dirty_for_io(to_folio)) {
 		folio_set_reclaim(to_folio);
-		ret = shmem_writeout(to_folio, NULL, NULL);
+		ret = shmem_write_folio(to_folio);
 		if (!folio_test_writeback(to_folio))
 			folio_clear_reclaim(to_folio);
 		/*
include/linux/shmem_fs.h +1 -4
index acb8dd961b45..f35c752f27af 100644
@@ -12,8 +12,6 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/bits.h>
 
-struct swap_iocb;
-
 /* inode in-kernel data */
 
 #ifdef CONFIG_TMPFS_QUOTA
@@ -122,8 +120,7 @@ static inline bool shmem_mapping(const struct address_space *mapping)
 void shmem_unlock_mapping(struct address_space *mapping);
 struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
-		struct list_head *folio_list);
+int shmem_write_folio(struct folio *folio);
 void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end);
 int shmem_unuse(unsigned int type);
 
mm/shmem.c +6 -1
index 56c23a7b15c7..d10735e49b25 100644
@@ -1738,7 +1738,12 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 	folio_mark_dirty(folio);
 	return AOP_WRITEPAGE_ACTIVATE;	/* Return with folio locked */
 }
-EXPORT_SYMBOL_GPL(shmem_writeout);
+
+int shmem_write_folio(struct folio *folio)
+{
+	return shmem_writeout(folio, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(shmem_write_folio);
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS)
 static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
mm/swap.h +4 -0
index 77d2d14eda42..4f86ef338a60 100644
@@ -473,4 +473,8 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 }
 
 #endif /* CONFIG_SWAP */
+
+int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+		struct list_head *folio_list);
+
 #endif /* _MM_SWAP_H */
Signature · 1 line
2.53.0
#4 lore raw

better shmem writeback interface for drm, was: Re: [PATCH 1/8] shmem: provide a shmem_write_folio wrapper

In reply to Christoph Hellwig

Sashiko complains about a lot of pre-existing issues in i915/ttm here:

https://sashiko.dev/#/patchset/20260601113449.3464734-1-hch%40lst.de

This might be a good time to fix these, and as part of it provide saner interfaces for drm. The i915 case look like a plain writeback range, which looks somewhat easy. I don't really get what the ttm code is trying to do.

Any takers to get drm out of messing with these lowlevel shmemfs internals?

Quoted 95 lines · Christoph Hellwig

Provide a wrapper for the shmem abuses in drm to preparare for swap I/O refactoring by keepin swap_iocb handling entirely contained in mm/.

---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 2 +-
 drivers/gpu/drm/ttm/ttm_backup.c          | 2 +-
 include/linux/shmem_fs.h                  | 5 +----
 mm/shmem.c                                | 7 ++++++-
 mm/swap.h                                 | 4 ++++
 5 files changed, 13 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/gem/i915_gem_shmem.c +1 -1
index 06543ae60706..ef9440166295 100644
@@ -325,7 +325,7 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
 		if (folio_mapped(folio))
 			folio_redirty_for_writepage(&wbc, folio);
 		else
-			error = shmem_writeout(folio, NULL, NULL);
+			error = shmem_write_folio(folio);
 	}
 }
 
drivers/gpu/drm/ttm/ttm_backup.c +1 -1
index 81df4cb5606b..c5b813a563e7 100644
@@ -117,7 +117,7 @@ ttm_backup_backup_page(struct file *backup, struct page *page,
 	if (writeback && !folio_mapped(to_folio) &&
 	    folio_clear_dirty_for_io(to_folio)) {
 		folio_set_reclaim(to_folio);
-		ret = shmem_writeout(to_folio, NULL, NULL);
+		ret = shmem_write_folio(to_folio);
 		if (!folio_test_writeback(to_folio))
 			folio_clear_reclaim(to_folio);
 		/*
include/linux/shmem_fs.h +1 -4
index acb8dd961b45..f35c752f27af 100644
@@ -12,8 +12,6 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/bits.h>
 
-struct swap_iocb;
-
 /* inode in-kernel data */
 
 #ifdef CONFIG_TMPFS_QUOTA
@@ -122,8 +120,7 @@ static inline bool shmem_mapping(const struct address_space *mapping)
 void shmem_unlock_mapping(struct address_space *mapping);
 struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
-		struct list_head *folio_list);
+int shmem_write_folio(struct folio *folio);
 void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end);
 int shmem_unuse(unsigned int type);
 
mm/shmem.c +6 -1
index 56c23a7b15c7..d10735e49b25 100644
@@ -1738,7 +1738,12 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 	folio_mark_dirty(folio);
 	return AOP_WRITEPAGE_ACTIVATE;	/* Return with folio locked */
 }
-EXPORT_SYMBOL_GPL(shmem_writeout);
+
+int shmem_write_folio(struct folio *folio)
+{
+	return shmem_writeout(folio, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(shmem_write_folio);
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS)
 static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
mm/swap.h +4 -0
index 77d2d14eda42..4f86ef338a60 100644
@@ -473,4 +473,8 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 }
 
 #endif /* CONFIG_SWAP */
+
+int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+		struct list_head *folio_list);
+
 #endif /* _MM_SWAP_H */
Signature · 1 line
2.53.0

---end quoted text---

maintainer Acked-by on v1 1/8
#5 lore raw

Re: [PATCH 1/8] shmem: provide a shmem_write_folio wrapper

In reply to Christoph Hellwig
Quoted 5 lines · Christoph Hellwig

Provide a wrapper for the shmem abuses in drm to preparare for swap I/O refactoring by keepin swap_iocb handling entirely contained in mm/.

Chris

Quoted 91 lines
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 2 +-
 drivers/gpu/drm/ttm/ttm_backup.c          | 2 +-
 include/linux/shmem_fs.h                  | 5 +----
 mm/shmem.c                                | 7 ++++++-
 mm/swap.h                                 | 4 ++++
 5 files changed, 13 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/gem/i915_gem_shmem.c +1 -1
index 06543ae60706..ef9440166295 100644
@@ -325,7 +325,7 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
                if (folio_mapped(folio))
                        folio_redirty_for_writepage(&wbc, folio);
                else
-                       error = shmem_writeout(folio, NULL, NULL);
+                       error = shmem_write_folio(folio);
        }
 }
 
drivers/gpu/drm/ttm/ttm_backup.c +1 -1
index 81df4cb5606b..c5b813a563e7 100644
@@ -117,7 +117,7 @@ ttm_backup_backup_page(struct file *backup, struct page *page,
        if (writeback && !folio_mapped(to_folio) &&
            folio_clear_dirty_for_io(to_folio)) {
                folio_set_reclaim(to_folio);
-               ret = shmem_writeout(to_folio, NULL, NULL);
+               ret = shmem_write_folio(to_folio);
                if (!folio_test_writeback(to_folio))
                        folio_clear_reclaim(to_folio);
                /*
include/linux/shmem_fs.h +1 -4
index acb8dd961b45..f35c752f27af 100644
@@ -12,8 +12,6 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/bits.h>
 
-struct swap_iocb;
-
 /* inode in-kernel data */
 
 #ifdef CONFIG_TMPFS_QUOTA
@@ -122,8 +120,7 @@ static inline bool shmem_mapping(const struct address_space *mapping)
 void shmem_unlock_mapping(struct address_space *mapping);
 struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
                                        pgoff_t index, gfp_t gfp_mask);
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
-               struct list_head *folio_list);
+int shmem_write_folio(struct folio *folio);
 void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end);
 int shmem_unuse(unsigned int type);
 
mm/shmem.c +6 -1
index 56c23a7b15c7..d10735e49b25 100644
@@ -1738,7 +1738,12 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
        folio_mark_dirty(folio);
        return AOP_WRITEPAGE_ACTIVATE;  /* Return with folio locked */
 }
-EXPORT_SYMBOL_GPL(shmem_writeout);
+
+int shmem_write_folio(struct folio *folio)
+{
+       return shmem_writeout(folio, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(shmem_write_folio);
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS)
 static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
mm/swap.h +4 -1
index 77d2d14eda42..4f86ef338a60 100644
@@ -473,4 +473,8 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 }
 
 #endif /* CONFIG_SWAP */
+
+int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+               struct list_head *folio_list);
+
 #endif /* _MM_SWAP_H */
--

2.53.0

#6 lore raw

PATCH 2/8 mm: merge writeout into pageout

In reply to Christoph Hellwig

writeout is only called from pageout, and a straight flow at the end, so merge the two functions.

---
 mm/vmscan.c | 63 ++++++++++++++++++++++++-----------------------------
 1 file changed, 29 insertions(+), 34 deletions(-)
mm/vmscan.c +29 -34
index e8a90911bf88..d7303eea1265 100644
@@ -612,45 +612,14 @@ typedef enum {
 	PAGE_CLEAN,
 } pageout_t;
 
-static pageout_t writeout(struct folio *folio, struct address_space *mapping,
-		struct swap_iocb **plug, struct list_head *folio_list)
-{
-	int res;
-
-	folio_set_reclaim(folio);
-
-	/*
-	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
-	 * or we failed to allocate contiguous swap entries, in which case
-	 * the split out folios get added back to folio_list.
-	 */
-	if (shmem_mapping(mapping))
-		res = shmem_writeout(folio, plug, folio_list);
-	else
-		res = swap_writeout(folio, plug);
-
-	if (res < 0)
-		handle_write_error(mapping, folio, res);
-	if (res == AOP_WRITEPAGE_ACTIVATE) {
-		folio_clear_reclaim(folio);
-		return PAGE_ACTIVATE;
-	}
-
-	/* synchronous write? */
-	if (!folio_test_writeback(folio))
-		folio_clear_reclaim(folio);
-
-	trace_mm_vmscan_write_folio(folio);
-	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
-	return PAGE_SUCCESS;
-}
-
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
 static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 			 struct swap_iocb **plug, struct list_head *folio_list)
 {
+	int res;
+
 	/*
 	 * We no longer attempt to writeback filesystem folios here, other
 	 * than tmpfs/shmem.  That's taken care of in page-writeback.
@@ -674,7 +643,33 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 		return PAGE_ACTIVATE;
 	if (!folio_clear_dirty_for_io(folio))
 		return PAGE_CLEAN;
-	return writeout(folio, mapping, plug, folio_list);
+
+	folio_set_reclaim(folio);
+
+	/*
+	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
+	 * or we failed to allocate contiguous swap entries, in which case
+	 * the split out folios get added back to folio_list.
+	 */
+	if (shmem_mapping(mapping))
+		res = shmem_writeout(folio, plug, folio_list);
+	else
+		res = swap_writeout(folio, plug);
+
+	if (res < 0)
+		handle_write_error(mapping, folio, res);
+	if (res == AOP_WRITEPAGE_ACTIVATE) {
+		folio_clear_reclaim(folio);
+		return PAGE_ACTIVATE;
+	}
+
+	/* synchronous write? */
+	if (!folio_test_writeback(folio))
+		folio_clear_reclaim(folio);
+
+	trace_mm_vmscan_write_folio(folio);
+	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
+	return PAGE_SUCCESS;
 }
 
 /*
Signature · 1 line
2.53.0
reviewer Reviewed-by on v1 2/8
#7 lore raw

Re: [PATCH 2/8] mm: merge writeout into pageout

Quoted 7 lines · Christoph Hellwig

writeout is only called from pageout, and a straight flow at the end, so merge the two functions.

---
 mm/vmscan.c | 63 ++++++++++++++++++++++++-----------------------------
 1 file changed, 29 insertions(+), 34 deletions(-)
Quoted 91 lines
mm/vmscan.c +29 -34
index e8a90911bf88..d7303eea1265 100644
@@ -612,45 +612,14 @@ typedef enum {
 	PAGE_CLEAN,
 } pageout_t;
 
-static pageout_t writeout(struct folio *folio, struct address_space *mapping,
-		struct swap_iocb **plug, struct list_head *folio_list)
-{
-	int res;
-
-	folio_set_reclaim(folio);
-
-	/*
-	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
-	 * or we failed to allocate contiguous swap entries, in which case
-	 * the split out folios get added back to folio_list.
-	 */
-	if (shmem_mapping(mapping))
-		res = shmem_writeout(folio, plug, folio_list);
-	else
-		res = swap_writeout(folio, plug);
-
-	if (res < 0)
-		handle_write_error(mapping, folio, res);
-	if (res == AOP_WRITEPAGE_ACTIVATE) {
-		folio_clear_reclaim(folio);
-		return PAGE_ACTIVATE;
-	}
-
-	/* synchronous write? */
-	if (!folio_test_writeback(folio))
-		folio_clear_reclaim(folio);
-
-	trace_mm_vmscan_write_folio(folio);
-	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
-	return PAGE_SUCCESS;
-}
-
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
 static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 			 struct swap_iocb **plug, struct list_head *folio_list)
 {
+	int res;
+
 	/*
 	 * We no longer attempt to writeback filesystem folios here, other
 	 * than tmpfs/shmem.  That's taken care of in page-writeback.
@@ -674,7 +643,33 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 		return PAGE_ACTIVATE;
 	if (!folio_clear_dirty_for_io(folio))
 		return PAGE_CLEAN;
-	return writeout(folio, mapping, plug, folio_list);
+
+	folio_set_reclaim(folio);
+
+	/*
+	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
+	 * or we failed to allocate contiguous swap entries, in which case
+	 * the split out folios get added back to folio_list.
+	 */
+	if (shmem_mapping(mapping))
+		res = shmem_writeout(folio, plug, folio_list);
+	else
+		res = swap_writeout(folio, plug);
+
+	if (res < 0)
+		handle_write_error(mapping, folio, res);
+	if (res == AOP_WRITEPAGE_ACTIVATE) {
+		folio_clear_reclaim(folio);
+		return PAGE_ACTIVATE;
+	}
+
+	/* synchronous write? */
+	if (!folio_test_writeback(folio))
+		folio_clear_reclaim(folio);
+
+	trace_mm_vmscan_write_folio(folio);
+	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
+	return PAGE_SUCCESS;
 }
 
 /*
Signature · 1 line
2.53.0
#9 lore raw

7.2 candidate? was: Re: [PATCH 2/8] mm: merge writeout into pageout

In reply to Christoph Hellwig

Can we maybe pick this up for 7.2? It is a trivial cleanup that would be nice to get out of the way.

Quoted 98 lines · Christoph Hellwig

writeout is only called from pageout, and a straight flow at the end, so merge the two functions.

---
 mm/vmscan.c | 63 ++++++++++++++++++++++++-----------------------------
 1 file changed, 29 insertions(+), 34 deletions(-)
mm/vmscan.c +29 -34
index e8a90911bf88..d7303eea1265 100644
@@ -612,45 +612,14 @@ typedef enum {
 	PAGE_CLEAN,
 } pageout_t;
 
-static pageout_t writeout(struct folio *folio, struct address_space *mapping,
-		struct swap_iocb **plug, struct list_head *folio_list)
-{
-	int res;
-
-	folio_set_reclaim(folio);
-
-	/*
-	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
-	 * or we failed to allocate contiguous swap entries, in which case
-	 * the split out folios get added back to folio_list.
-	 */
-	if (shmem_mapping(mapping))
-		res = shmem_writeout(folio, plug, folio_list);
-	else
-		res = swap_writeout(folio, plug);
-
-	if (res < 0)
-		handle_write_error(mapping, folio, res);
-	if (res == AOP_WRITEPAGE_ACTIVATE) {
-		folio_clear_reclaim(folio);
-		return PAGE_ACTIVATE;
-	}
-
-	/* synchronous write? */
-	if (!folio_test_writeback(folio))
-		folio_clear_reclaim(folio);
-
-	trace_mm_vmscan_write_folio(folio);
-	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
-	return PAGE_SUCCESS;
-}
-
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
 static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 			 struct swap_iocb **plug, struct list_head *folio_list)
 {
+	int res;
+
 	/*
 	 * We no longer attempt to writeback filesystem folios here, other
 	 * than tmpfs/shmem.  That's taken care of in page-writeback.
@@ -674,7 +643,33 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 		return PAGE_ACTIVATE;
 	if (!folio_clear_dirty_for_io(folio))
 		return PAGE_CLEAN;
-	return writeout(folio, mapping, plug, folio_list);
+
+	folio_set_reclaim(folio);
+
+	/*
+	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
+	 * or we failed to allocate contiguous swap entries, in which case
+	 * the split out folios get added back to folio_list.
+	 */
+	if (shmem_mapping(mapping))
+		res = shmem_writeout(folio, plug, folio_list);
+	else
+		res = swap_writeout(folio, plug);
+
+	if (res < 0)
+		handle_write_error(mapping, folio, res);
+	if (res == AOP_WRITEPAGE_ACTIVATE) {
+		folio_clear_reclaim(folio);
+		return PAGE_ACTIVATE;
+	}
+
+	/* synchronous write? */
+	if (!folio_test_writeback(folio))
+		folio_clear_reclaim(folio);
+
+	trace_mm_vmscan_write_folio(folio);
+	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
+	return PAGE_SUCCESS;
 }
 
 /*
Signature · 1 line
2.53.0

---end quoted text---

maintainer Acked-by
#10 lore raw

Re: 7.2 candidate? was: Re: [PATCH 2/8] mm: merge writeout into pageout

Quoted 89 lines · Christoph Hellwig

Can we maybe pick this up for 7.2? It is a trivial cleanup that would be nice to get out of the way.

Quoted 85 lines · Christoph Hellwig

writeout is only called from pageout, and a straight flow at the end, so merge the two functions.

---
 mm/vmscan.c | 63 ++++++++++++++++++++++++-----------------------------
 1 file changed, 29 insertions(+), 34 deletions(-)
mm/vmscan.c +22 -34
index e8a90911bf88..d7303eea1265 100644
@@ -612,45 +612,14 @@ typedef enum {
 	PAGE_CLEAN,
 } pageout_t;
 
-static pageout_t writeout(struct folio *folio, struct address_space *mapping,
-		struct swap_iocb **plug, struct list_head *folio_list)
-{
-	int res;
-
-	folio_set_reclaim(folio);
-
-	/*
-	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
-	 * or we failed to allocate contiguous swap entries, in which case
-	 * the split out folios get added back to folio_list.
-	 */
-	if (shmem_mapping(mapping))
-		res = shmem_writeout(folio, plug, folio_list);
-	else
-		res = swap_writeout(folio, plug);
-
-	if (res < 0)
-		handle_write_error(mapping, folio, res);
-	if (res == AOP_WRITEPAGE_ACTIVATE) {
-		folio_clear_reclaim(folio);
-		return PAGE_ACTIVATE;
-	}
-
-	/* synchronous write? */
-	if (!folio_test_writeback(folio))
-		folio_clear_reclaim(folio);
-
-	trace_mm_vmscan_write_folio(folio);
-	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
-	return PAGE_SUCCESS;
-}
-
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
 static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 			 struct swap_iocb **plug, struct list_head *folio_list)
 {
+	int res;
+
 	/*
 	 * We no longer attempt to writeback filesystem folios here, other
 	 * than tmpfs/shmem.  That's taken care of in page-writeback.
@@ -674,7 +643,33 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 		return PAGE_ACTIVATE;
 	if (!folio_clear_dirty_for_io(folio))
 		return PAGE_CLEAN;
-	return writeout(folio, mapping, plug, folio_list);
+
+	folio_set_reclaim(folio);
+
+	/*
+	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
+	 * or we failed to allocate contiguous swap entries, in which case
+	 * the split out folios get added back to folio_list.
+	 */
+	if (shmem_mapping(mapping))
+		res = shmem_writeout(folio, plug, folio_list);
+	else
+		res = swap_writeout(folio, plug);
+
+	if (res < 0)
+		handle_write_error(mapping, folio, res);
+	if (res == AOP_WRITEPAGE_ACTIVATE) {
+		folio_clear_reclaim(folio);
+		return PAGE_ACTIVATE;
+	}
+
Quoted 8 lines

mm/vmscan.c static pageout_t pageout(struct folio *folio, struct address_space *mapping, · line 673

Quoted 8 lines
mm/vmscan.c +7 -0
+	/* synchronous write? */
+	if (!folio_test_writeback(folio))
+		folio_clear_reclaim(folio);
+
+	trace_mm_vmscan_write_folio(folio);
+	node_stat_add_folio(folio, NR_VMSCAN_WRITE);
+	return PAGE_SUCCESS;
 }

LGTM

It's rather trivial, so throwing it into mm-unstable for a bit to merge it in the second MM PULL would make sense to me.

Signature · 3 lines
Cheers,

David
maintainer Acked-by on v1 2/8
#12 lore raw

Re: [PATCH 2/8] mm: merge writeout into pageout

In reply to Christoph Hellwig
Quoted 5 lines · Christoph Hellwig

writeout is only called from pageout, and a straight flow at the end, so merge the two functions.

Chris

Quoted 94 lines
---
 mm/vmscan.c | 63 ++++++++++++++++++++++++-----------------------------
 1 file changed, 29 insertions(+), 34 deletions(-)
mm/vmscan.c +29 -35
index e8a90911bf88..d7303eea1265 100644
@@ -612,45 +612,14 @@ typedef enum {
        PAGE_CLEAN,
 } pageout_t;
 
-static pageout_t writeout(struct folio *folio, struct address_space *mapping,
-               struct swap_iocb **plug, struct list_head *folio_list)
-{
-       int res;
-
-       folio_set_reclaim(folio);
-
-       /*
-        * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
-        * or we failed to allocate contiguous swap entries, in which case
-        * the split out folios get added back to folio_list.
-        */
-       if (shmem_mapping(mapping))
-               res = shmem_writeout(folio, plug, folio_list);
-       else
-               res = swap_writeout(folio, plug);
-
-       if (res < 0)
-               handle_write_error(mapping, folio, res);
-       if (res == AOP_WRITEPAGE_ACTIVATE) {
-               folio_clear_reclaim(folio);
-               return PAGE_ACTIVATE;
-       }
-
-       /* synchronous write? */
-       if (!folio_test_writeback(folio))
-               folio_clear_reclaim(folio);
-
-       trace_mm_vmscan_write_folio(folio);
-       node_stat_add_folio(folio, NR_VMSCAN_WRITE);
-       return PAGE_SUCCESS;
-}
-
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
 static pageout_t pageout(struct folio *folio, struct address_space *mapping,
                         struct swap_iocb **plug, struct list_head *folio_list)
 {
+       int res;
+
        /*
         * We no longer attempt to writeback filesystem folios here, other
         * than tmpfs/shmem.  That's taken care of in page-writeback.
@@ -674,7 +643,33 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
                return PAGE_ACTIVATE;
        if (!folio_clear_dirty_for_io(folio))
                return PAGE_CLEAN;
-       return writeout(folio, mapping, plug, folio_list);
+
+       folio_set_reclaim(folio);
+
+       /*
+        * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
+        * or we failed to allocate contiguous swap entries, in which case
+        * the split out folios get added back to folio_list.
+        */
+       if (shmem_mapping(mapping))
+               res = shmem_writeout(folio, plug, folio_list);
+       else
+               res = swap_writeout(folio, plug);
+
+       if (res < 0)
+               handle_write_error(mapping, folio, res);
+       if (res == AOP_WRITEPAGE_ACTIVATE) {
+               folio_clear_reclaim(folio);
+               return PAGE_ACTIVATE;
+       }
+
+       /* synchronous write? */
+       if (!folio_test_writeback(folio))
+               folio_clear_reclaim(folio);
+
+       trace_mm_vmscan_write_folio(folio);
+       node_stat_add_folio(folio, NR_VMSCAN_WRITE);
+       return PAGE_SUCCESS;
 }
 
 /*
--

2.53.0

#13 lore raw

PATCH 3/8 mm/swap: introduce struct swap_io_ctx

In reply to Christoph Hellwig

Generalize the context currently provided by double pointers to struct swap_iocb to an on-stack context. This cleans up the code and prepares for adding more fields and supporting batching multiple folios into a single bio for block-based swap as well.

This new swap_io_ctx is required for all functions using it, the old way of allowing a NULL iocb for some callers is removed to keep the interface consistent.

---
 mm/madvise.c    | 16 ++++++-------
 mm/page_io.c    | 60 ++++++++++++++++++++++++++-----------------------
 mm/shmem.c      | 13 +++++++----
 mm/swap.h       | 36 +++++++++++++----------------
 mm/swap_state.c | 53 +++++++++++++++++++++++++------------------
 mm/vmscan.c     | 15 ++++++-------
 mm/zswap.c      |  4 +++-
 7 files changed, 106 insertions(+), 91 deletions(-)
mm/madvise.c +8 -8
index cd9bb077072c..cd84e993190a 100644
@@ -188,7 +188,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 		unsigned long end, struct mm_walk *walk)
 {
 	struct vm_area_struct *vma = walk->private;
-	struct swap_iocb *splug = NULL;
+	struct swap_io_ctx ctx = {};
 	pte_t *ptep = NULL;
 	spinlock_t *ptl;
 	unsigned long addr;
@@ -212,15 +212,15 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 		pte_unmap_unlock(ptep, ptl);
 		ptep = NULL;
 
-		folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
-					     vma, addr, &splug);
+		folio = read_swap_cache_async(&ctx, entry, GFP_HIGHUSER_MOVABLE,
+					vma, addr);
 		if (folio)
 			folio_put(folio);
 	}
 
 	if (ptep)
 		pte_unmap_unlock(ptep, ptl);
-	swap_read_unplug(splug);
+	swap_read_submit(&ctx);
 	cond_resched();
 
 	return 0;
@@ -238,7 +238,7 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
 	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
 	pgoff_t end_index = linear_page_index(vma, end) - 1;
 	struct folio *folio;
-	struct swap_iocb *splug = NULL;
+	struct swap_io_ctx ctx = {};
 
 	rcu_read_lock();
 	xas_for_each(&xas, folio, end_index) {
@@ -257,15 +257,15 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
 		xas_pause(&xas);
 		rcu_read_unlock();
 
-		folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
-					     vma, addr, &splug);
+		folio = read_swap_cache_async(&ctx, entry,
+				mapping_gfp_mask(mapping), vma, addr);
 		if (folio)
 			folio_put(folio);
 
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
-	swap_read_unplug(splug);
+	swap_read_submit(&ctx);
 }
 #endif		/* CONFIG_SWAP */
 
mm/page_io.c +32 -28

162 lines not on this page · raw message

mm/shmem.c +9 -4
index d10735e49b25..17eb16dbfaa9 100644
@@ -1584,13 +1584,13 @@ int shmem_unuse(unsigned int type)
 
 /**
  * shmem_writeout - Write the folio to swap
+ * @ctx: swap I/O context
  * @folio: The folio to write
- * @plug: swap plug
  * @folio_list: list to put back folios on split
  *
  * Move the folio from the page cache to the swap cache.
  */
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		struct list_head *folio_list)
 {
 	struct address_space *mapping = folio->mapping;
@@ -1702,7 +1702,7 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 		shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap));
 
 		BUG_ON(folio_mapped(folio));
-		error = swap_writeout(folio, plug);
+		error = swap_writeout(ctx, folio);
 		if (error != AOP_WRITEPAGE_ACTIVATE) {
 			/* folio has been unlocked */
 			return error;
@@ -1741,7 +1741,12 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 
 int shmem_write_folio(struct folio *folio)
 {
-	return shmem_writeout(folio, NULL, NULL);
+	struct swap_io_ctx ctx = {};
+	int err;
+
+	err = shmem_writeout(&ctx, folio, NULL);
+	swap_write_submit(&ctx);
+	return err;
 }
 EXPORT_SYMBOL_GPL(shmem_write_folio);
 
mm/swap.h +16 -20
index 4f86ef338a60..79d66272dfd4 100644
@@ -4,6 +4,7 @@
 
 #include <linux/atomic.h> /* for atomic_long_t */
 #include <linux/mm.h> /* for PAGE_SHIFT */
+
 struct mempolicy;
 struct swap_iocb;
 struct swap_memcg_table;
@@ -78,6 +79,10 @@ enum swap_cluster_flags {
 	CLUSTER_FLAG_MAX,
 };
 
+struct swap_io_ctx {
+	struct swap_iocb	*sio;
+};
+
 #ifdef CONFIG_SWAP
 #include <linux/swapops.h> /* for swp_offset */
 #include <linux/blk_types.h> /* for bio_end_io_t */
@@ -240,17 +245,11 @@ extern void __swap_cluster_free_entries(struct swap_info_struct *si,
 
 /* linux/mm/page_io.c */
 int sio_pool_init(void);
-struct swap_iocb;
-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)
-{
-	if (unlikely(plug))
-		__swap_read_unplug(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);
+void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio);
+void swap_read_submit(struct swap_io_ctx *ctx);
+void swap_write_submit(struct swap_io_ctx *ctx);
+int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio);
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio);
 
 /* linux/mm/swap_state.c */
 extern struct address_space swap_space __read_mostly;
@@ -317,9 +316,8 @@ void __swap_cache_replace_folio(struct swap_cluster_info *ci,
 
 void show_swap_cache_info(void);
 void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr);
-struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-		struct vm_area_struct *vma, unsigned long addr,
-		struct swap_iocb **plug);
+struct folio *read_swap_cache_async(struct swap_io_ctx *ctx, swp_entry_t entry,
+		gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr);
 struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
 		struct mempolicy *mpol, pgoff_t ilx);
 struct folio *swapin_readahead(swp_entry_t entry, gfp_t flag,
@@ -335,7 +333,6 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 }
 
 #else /* CONFIG_SWAP */
-struct swap_iocb;
 static inline struct swap_cluster_info *swap_cluster_lock(
 	struct swap_info_struct *si, pgoff_t offset, bool irq)
 {
@@ -381,11 +378,11 @@ static inline void folio_put_swap(struct folio *folio, struct page *page)
 {
 }
 
-static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
+static inline void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 {
 }
 
-static inline void swap_write_unplug(struct swap_iocb *sio)
+static inline void swap_write_submit(struct swap_io_ctx *ctx)
 {
 }
 
@@ -427,8 +424,7 @@ static inline void swap_update_readahead(struct folio *folio,
 {
 }
 
-static inline int swap_writeout(struct folio *folio,
-		struct swap_iocb **swap_plug)
+static inline int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	return 0;
 }
@@ -474,7 +470,7 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 
 #endif /* CONFIG_SWAP */
 
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		struct list_head *folio_list);
 
 #endif /* _MM_SWAP_H */
mm/swap_state.c +31 -22

137 lines not on this page · raw message

mm/vmscan.c +7 -8
index d7303eea1265..c43177a8e4dd 100644
@@ -615,8 +615,8 @@ typedef enum {
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
-static pageout_t pageout(struct folio *folio, struct address_space *mapping,
-			 struct swap_iocb **plug, struct list_head *folio_list)
+static pageout_t pageout(struct swap_io_ctx *ctx, struct address_space *mapping,
+		struct folio *folio, struct list_head *folio_list)
 {
 	int res;
 
@@ -652,9 +652,9 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 	 * the split out folios get added back to folio_list.
 	 */
 	if (shmem_mapping(mapping))
-		res = shmem_writeout(folio, plug, folio_list);
+		res = shmem_writeout(ctx, folio, folio_list);
 	else
-		res = swap_writeout(folio, plug);
+		res = swap_writeout(ctx, folio);
 
 	if (res < 0)
 		handle_write_error(mapping, folio, res);
@@ -1063,7 +1063,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 	unsigned int nr_reclaimed = 0, nr_demoted = 0;
 	unsigned int pgactivate = 0;
 	bool do_demote_pass;
-	struct swap_iocb *plug = NULL;
+	struct swap_io_ctx ctx = {};
 
 	folio_batch_init(&free_folios);
 	memset(stat, 0, sizeof(*stat));
@@ -1394,7 +1394,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 			 * starts and then write it out here.
 			 */
 			try_to_unmap_flush_dirty();
-			switch (pageout(folio, mapping, &plug, folio_list)) {
+			switch (pageout(&ctx, mapping, folio, folio_list)) {
 			case PAGE_KEEP:
 				goto keep_locked;
 			case PAGE_ACTIVATE:
@@ -1584,8 +1584,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 	list_splice(&ret_folios, folio_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 
-	if (plug)
-		swap_write_unplug(plug);
+	swap_write_submit(&ctx);
 	return nr_reclaimed;
 }
 
mm/zswap.c +3 -1
index 761cd699e0a3..feed2557f6ed 100644
@@ -992,6 +992,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	struct folio *folio;
 	struct mempolicy *mpol;
 	struct swap_info_struct *si;
+	struct swap_io_ctx ctx = {};
 	int ret = 0;
 
 	/* try to allocate swap cache folio */
@@ -1049,7 +1050,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	folio_set_reclaim(folio);
 
 	/* start writeback */
-	__swap_writepage(folio, NULL);
+	__swap_writepage(&ctx, folio);
+	swap_write_submit(&ctx);
 
 out:
 	if (ret) {
Signature · 1 line
2.53.0
reviewer
#14 lore raw

Re: [PATCH 3/8] mm/swap: introduce struct swap_io_ctx

Quoted 8 lines · Christoph Hellwig

Generalize the context currently provided by double pointers to struct swap_iocb to an on-stack context. This cleans up the code and prepares for adding more fields and supporting batching multiple folios into a single bio for block-based swap as well.

This new swap_io_ctx is required for all functions using it, the old way of allowing a NULL iocb for some callers is removed to keep the interface consistent.

In this patch, except of introducng struct swap_io_ctx, it also does:
- swap_cache_read_folio_sync() helper introduced for the two readahead "skip" paths where the target page was already read
- swap_write_unplug → swap_write_submit,
__swap_read_unplug → swap_read_submit;
the NULL-checking inline swap_read_unplug() wrapper is removed

It would be better if these are mentioned in log too, or should be split into a separate patch. Otherwise it doesn't match the subject.

Quoted 26 lines
---
 mm/madvise.c    | 16 ++++++-------
 mm/page_io.c    | 60 ++++++++++++++++++++++++++-----------------------
 mm/shmem.c      | 13 +++++++----
 mm/swap.h       | 36 +++++++++++++----------------
 mm/swap_state.c | 53 +++++++++++++++++++++++++------------------
 mm/vmscan.c     | 15 ++++++-------
 mm/zswap.c      |  4 +++-
 7 files changed, 106 insertions(+), 91 deletions(-)
mm/madvise.c +1 -1
index cd9bb077072c..cd84e993190a 100644
@@ -188,7 +188,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 		unsigned long end, struct mm_walk *walk)
 {
 	struct vm_area_struct *vma = walk->private;
-	struct swap_iocb *splug = NULL;
+	struct swap_io_ctx ctx = {};
 	pte_t *ptep = NULL;
 	spinlock_t *ptl;
 	unsigned long addr;

mm/madvise.c static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, · line 216

Quoted 7 lines
mm/madvise.c +2 -2
@@ -212,15 +212,15 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 		pte_unmap_unlock(ptep, ptl);
 		ptep = NULL;
 
-		folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
-					     vma, addr, &splug);
+		folio = read_swap_cache_async(&ctx, entry, GFP_HIGHUSER_MOVABLE,
+					vma, addr);

And I am wondering why &ctx has to be put as the 1st para, is there a rule of C language or linux kernel? It obviously adds a lot of unnecessary code churn. I will read swap cache, of course swap entry is the main subject I will operate on, why bother moving &ctx which is associated date at first.

Quoted 592 lines
mm/madvise.c +5 -5
 		if (folio)
 			folio_put(folio);
 	}
 
 	if (ptep)
 		pte_unmap_unlock(ptep, ptl);
-	swap_read_unplug(splug);
+	swap_read_submit(&ctx);
 	cond_resched();
 
 	return 0;
@@ -238,7 +238,7 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
 	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
 	pgoff_t end_index = linear_page_index(vma, end) - 1;
 	struct folio *folio;
-	struct swap_iocb *splug = NULL;
+	struct swap_io_ctx ctx = {};
 
 	rcu_read_lock();
 	xas_for_each(&xas, folio, end_index) {
@@ -257,15 +257,15 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
 		xas_pause(&xas);
 		rcu_read_unlock();
 
-		folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
-					     vma, addr, &splug);
+		folio = read_swap_cache_async(&ctx, entry,
+				mapping_gfp_mask(mapping), vma, addr);
 		if (folio)
 			folio_put(folio);
 
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
-	swap_read_unplug(splug);
+	swap_read_submit(&ctx);
 }
 #endif		/* CONFIG_SWAP */
 
mm/page_io.c +32 -28
index f2d8fe7fd057..0bf035dc1170 100644
@@ -248,7 +248,7 @@ static void swap_zeromap_folio_clear(struct folio *folio)
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
  */
-int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
+int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	int ret = 0;
 
@@ -295,7 +295,7 @@ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
 	}
 	rcu_read_unlock();
 
-	__swap_writepage(folio, swap_plug);
+	__swap_writepage(ctx, folio);
 	return 0;
 out_unlock:
 	folio_unlock(folio);
@@ -385,9 +385,9 @@ 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_io_ctx *ctx, struct folio *folio)
 {
-	struct swap_iocb *sio = swap_plug ? *swap_plug : NULL;
+	struct swap_iocb *sio = ctx->sio;
 	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);
@@ -398,7 +398,7 @@ static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
 	if (sio) {
 		if (sio->iocb.ki_filp != swap_file ||
 		    sio->iocb.ki_pos + sio->len != pos) {
-			swap_write_unplug(sio);
+			swap_write_submit(ctx);
 			sio = NULL;
 		}
 	}
@@ -413,12 +413,11 @@ static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
 	bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
 	sio->len += folio_size(folio);
 	sio->nr_bvecs += 1;
-	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs) || !swap_plug) {
-		swap_write_unplug(sio);
+	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
+		swap_write_submit(ctx);
 		sio = NULL;
 	}
-	if (swap_plug)
-		*swap_plug = sio;
+	ctx->sio = sio;
 }
 
 static void swap_writepage_bdev_sync(struct folio *folio,
@@ -458,7 +457,7 @@ static void swap_writepage_bdev_async(struct folio *folio,
 	submit_bio(bio);
 }
 
-void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 
@@ -469,7 +468,7 @@ void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
 	 * is safe.
 	 */
 	if (data_race(sis->flags & SWP_FS_OPS))
-		swap_writepage_fs(folio, swap_plug);
+		swap_writepage_fs(ctx, folio);
 	/*
 	 * ->flags can be updated non-atomically,
 	 * but that will never affect SWP_SYNCHRONOUS_IO, so the data_race
@@ -481,16 +480,20 @@ void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
 		swap_writepage_bdev_async(folio, sis);
 }
 
-void swap_write_unplug(struct swap_iocb *sio)
+void swap_write_submit(struct swap_io_ctx *ctx)
 {
+	struct swap_iocb *sio = ctx->sio;
 	struct iov_iter from;
-	struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
 	int ret;
 
+	if (!sio)
+		return;
+
 	iov_iter_bvec(&from, ITER_SOURCE, sio->bvecs, sio->nr_bvecs, sio->len);
-	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
 	if (ret != -EIOCBQUEUED)
 		sio_write_complete(&sio->iocb, ret);
+	ctx->sio = NULL;
 }
 
 static void sio_read_complete(struct kiocb *iocb, long ret)
@@ -582,18 +585,16 @@ 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_io_ctx *ctx, struct folio *folio)
 {
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
-	struct swap_iocb *sio = NULL;
+	struct swap_iocb *sio = ctx->sio;
 	loff_t pos = swap_dev_pos(folio->swap);
 
-	if (plug)
-		sio = *plug;
 	if (sio) {
 		if (sio->iocb.ki_filp != sis->swap_file ||
 		    sio->iocb.ki_pos + sio->len != pos) {
-			swap_read_unplug(sio);
+			swap_read_submit(ctx);
 			sio = NULL;
 		}
 	}
@@ -608,12 +609,11 @@ static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
 	bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
 	sio->len += folio_size(folio);
 	sio->nr_bvecs += 1;
-	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs) || !plug) {
-		swap_read_unplug(sio);
+	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
+		swap_read_submit(ctx);
 		sio = NULL;
 	}
-	if (plug)
-		*plug = sio;
+	ctx->sio = sio;
 }
 
 static void swap_read_folio_bdev_sync(struct folio *folio,
@@ -653,7 +653,7 @@ static void swap_read_folio_bdev_async(struct folio *folio,
 	submit_bio(bio);
 }
 
-void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
+void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 	bool synchronous = sis->flags & SWP_SYNCHRONOUS_IO;
@@ -688,7 +688,7 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 	zswap_folio_swapin(folio);
 
 	if (data_race(sis->flags & SWP_FS_OPS)) {
-		swap_read_folio_fs(folio, plug);
+		swap_read_folio_fs(ctx, folio);
 	} else if (synchronous) {
 		swap_read_folio_bdev_sync(folio, sis);
 	} else {
@@ -703,14 +703,18 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 	delayacct_swapin_end();
 }
 
-void __swap_read_unplug(struct swap_iocb *sio)
+void swap_read_submit(struct swap_io_ctx *ctx)
 {
+	struct swap_iocb *sio = ctx->sio;
 	struct iov_iter from;
-	struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
 	int ret;
 
+	if (!sio)
+		return;
+
 	iov_iter_bvec(&from, ITER_DEST, sio->bvecs, sio->nr_bvecs, sio->len);
-	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
 	if (ret != -EIOCBQUEUED)
 		sio_read_complete(&sio->iocb, ret);
+	ctx->sio = NULL;
 }
mm/shmem.c +9 -4
index d10735e49b25..17eb16dbfaa9 100644
@@ -1584,13 +1584,13 @@ int shmem_unuse(unsigned int type)
 
 /**
  * shmem_writeout - Write the folio to swap
+ * @ctx: swap I/O context
  * @folio: The folio to write
- * @plug: swap plug
  * @folio_list: list to put back folios on split
  *
  * Move the folio from the page cache to the swap cache.
  */
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		struct list_head *folio_list)
 {
 	struct address_space *mapping = folio->mapping;
@@ -1702,7 +1702,7 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 		shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap));
 
 		BUG_ON(folio_mapped(folio));
-		error = swap_writeout(folio, plug);
+		error = swap_writeout(ctx, folio);
 		if (error != AOP_WRITEPAGE_ACTIVATE) {
 			/* folio has been unlocked */
 			return error;
@@ -1741,7 +1741,12 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 
 int shmem_write_folio(struct folio *folio)
 {
-	return shmem_writeout(folio, NULL, NULL);
+	struct swap_io_ctx ctx = {};
+	int err;
+
+	err = shmem_writeout(&ctx, folio, NULL);
+	swap_write_submit(&ctx);
+	return err;
 }
 EXPORT_SYMBOL_GPL(shmem_write_folio);
 
mm/swap.h +16 -20
index 4f86ef338a60..79d66272dfd4 100644
@@ -4,6 +4,7 @@
 
 #include <linux/atomic.h> /* for atomic_long_t */
 #include <linux/mm.h> /* for PAGE_SHIFT */
+
 struct mempolicy;
 struct swap_iocb;
 struct swap_memcg_table;
@@ -78,6 +79,10 @@ enum swap_cluster_flags {
 	CLUSTER_FLAG_MAX,
 };
 
+struct swap_io_ctx {
+	struct swap_iocb	*sio;
+};
+
 #ifdef CONFIG_SWAP
 #include <linux/swapops.h> /* for swp_offset */
 #include <linux/blk_types.h> /* for bio_end_io_t */
@@ -240,17 +245,11 @@ extern void __swap_cluster_free_entries(struct swap_info_struct *si,
 
 /* linux/mm/page_io.c */
 int sio_pool_init(void);
-struct swap_iocb;
-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)
-{
-	if (unlikely(plug))
-		__swap_read_unplug(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);
+void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio);
+void swap_read_submit(struct swap_io_ctx *ctx);
+void swap_write_submit(struct swap_io_ctx *ctx);
+int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio);
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio);
 
 /* linux/mm/swap_state.c */
 extern struct address_space swap_space __read_mostly;
@@ -317,9 +316,8 @@ void __swap_cache_replace_folio(struct swap_cluster_info *ci,
 
 void show_swap_cache_info(void);
 void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr);
-struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-		struct vm_area_struct *vma, unsigned long addr,
-		struct swap_iocb **plug);
+struct folio *read_swap_cache_async(struct swap_io_ctx *ctx, swp_entry_t entry,
+		gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr);
 struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
 		struct mempolicy *mpol, pgoff_t ilx);
 struct folio *swapin_readahead(swp_entry_t entry, gfp_t flag,
@@ -335,7 +333,6 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 }
 
 #else /* CONFIG_SWAP */
-struct swap_iocb;
 static inline struct swap_cluster_info *swap_cluster_lock(
 	struct swap_info_struct *si, pgoff_t offset, bool irq)
 {
@@ -381,11 +378,11 @@ static inline void folio_put_swap(struct folio *folio, struct page *page)
 {
 }
 
-static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
+static inline void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 {
 }
 
-static inline void swap_write_unplug(struct swap_iocb *sio)
+static inline void swap_write_submit(struct swap_io_ctx *ctx)
 {
 }
 
@@ -427,8 +424,7 @@ static inline void swap_update_readahead(struct folio *folio,
 {
 }
 
-static inline int swap_writeout(struct folio *folio,
-		struct swap_iocb **swap_plug)
+static inline int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	return 0;
 }
@@ -474,7 +470,7 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 
 #endif /* CONFIG_SWAP */
 
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		struct list_head *folio_list);
 
 #endif /* _MM_SWAP_H */
mm/swap_state.c +31 -22
index 04f5ce992401..b9613026950e 100644
@@ -623,9 +623,9 @@ void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma,
 	}
 }
 
-static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
-					   struct mempolicy *mpol, pgoff_t ilx,
-					   struct swap_iocb **plug, bool readahead)
+static struct folio *swap_cache_read_folio(struct swap_io_ctx *ctx,
+		swp_entry_t entry, gfp_t gfp, struct mempolicy *mpol,
+		pgoff_t ilx, bool readahead)
 {
 	struct folio *folio;
 
@@ -639,7 +639,7 @@ static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
 	if (IS_ERR_OR_NULL(folio))
 		return NULL;
 
-	swap_read_folio(folio, plug);
+	swap_read_folio(ctx, folio);
 	if (readahead) {
 		folio_set_readahead(folio);
 		count_vm_event(SWAP_RA);
@@ -667,6 +667,7 @@ static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
 struct folio *swapin_sync(swp_entry_t entry, gfp_t gfp, unsigned long orders,
 			   struct vm_fault *vmf, struct mempolicy *mpol, pgoff_t ilx)
 {
+	struct swap_io_ctx ctx = {};
 	struct folio *folio;
 
 	do {
@@ -679,7 +680,8 @@ struct folio *swapin_sync(swp_entry_t entry, gfp_t gfp, unsigned long orders,
 	if (IS_ERR(folio))
 		return folio;
 
-	swap_read_folio(folio, NULL);
+	swap_read_folio(&ctx, folio);
+	swap_read_submit(&ctx);
 	return folio;
 }
 
@@ -689,9 +691,8 @@ struct folio *swapin_sync(swp_entry_t entry, gfp_t gfp, unsigned long orders,
  * A failure return means that either the page allocation failed or that
  * the swap entry is no longer in use.
  */
-struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-		struct vm_area_struct *vma, unsigned long addr,
-		struct swap_iocb **plug)
+struct folio *read_swap_cache_async(struct swap_io_ctx *ctx, swp_entry_t entry,
+		gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr)
 {
 	struct swap_info_struct *si;
 	struct mempolicy *mpol;
@@ -703,13 +704,24 @@ struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		return NULL;
 
 	mpol = get_vma_policy(vma, addr, 0, &ilx);
-	folio = swap_cache_read_folio(entry, gfp_mask, mpol, ilx, plug, false);
+	folio = swap_cache_read_folio(ctx, entry, gfp_mask, mpol, ilx, false);
 	mpol_cond_put(mpol);
 
 	put_swap_device(si);
 	return folio;
 }
 
+static struct folio *swap_cache_read_folio_sync(swp_entry_t entry, gfp_t gfp,
+		struct mempolicy *mpol, pgoff_t ilx)
+{
+	struct swap_io_ctx ctx = {};
+	struct folio *folio;
+
+	folio = swap_cache_read_folio(&ctx, entry, gfp, mpol, ilx, false);
+	swap_read_submit(&ctx);
+	return folio;
+}
+
 static unsigned int __swapin_nr_pages(unsigned long prev_offset,
 				      unsigned long offset,
 				      int hits,
@@ -798,8 +810,8 @@ struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	unsigned long start_offset, end_offset;
 	unsigned long mask;
 	struct swap_info_struct *si = __swap_entry_to_info(entry);
+	struct swap_io_ctx ctx = {};
 	struct blk_plug plug;
-	struct swap_iocb *splug = NULL;
 	swp_entry_t ra_entry;
 
 	mask = swapin_nr_pages(offset) - 1;
@@ -818,18 +830,17 @@ struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
 		ra_entry = swp_entry(swp_type(entry), offset);
-		folio = swap_cache_read_folio(ra_entry, gfp_mask, mpol, ilx,
-					      &splug, offset != entry_offset);
+		folio = swap_cache_read_folio(&ctx, ra_entry, gfp_mask, mpol,
+				ilx, offset != entry_offset);
 		if (!folio)
 			continue;
 		folio_put(folio);
 	}
 	blk_finish_plug(&plug);
-	swap_read_unplug(splug);
+	swap_read_submit(&ctx);
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 skip:
-	/* The page was likely read above, so no need for plugging here */
-	return swap_cache_read_folio(entry, gfp_mask, mpol, ilx, NULL, false);
+	return swap_cache_read_folio_sync(entry, gfp_mask, mpol, ilx);
 }
 
 static int swap_vma_ra_win(struct vm_fault *vmf, unsigned long *start,
@@ -889,8 +900,8 @@ static int swap_vma_ra_win(struct vm_fault *vmf, unsigned long *start,
 static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 		struct mempolicy *mpol, pgoff_t targ_ilx, struct vm_fault *vmf)
 {
+	struct swap_io_ctx ctx = {};
 	struct blk_plug plug;
-	struct swap_iocb *splug = NULL;
 	struct folio *folio;
 	pte_t *pte = NULL, pentry;
 	int win;
@@ -929,8 +940,8 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 			if (!si)
 				continue;
 		}
-		folio = swap_cache_read_folio(entry, gfp_mask, mpol, ilx,
-					      &splug, addr != vmf->address);
+		folio = swap_cache_read_folio(&ctx, entry, gfp_mask, mpol, ilx,
+					      addr != vmf->address);
 		if (si)
 			put_swap_device(si);
 		if (!folio)
@@ -940,13 +951,11 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 	if (pte)
 		pte_unmap(pte);
 	blk_finish_plug(&plug);
-	swap_read_unplug(splug);
+	swap_read_submit(&ctx);
 	lru_add_drain();
 skip:
 	/* The folio was likely read above, so no need for plugging here */
-	folio = swap_cache_read_folio(targ_entry, gfp_mask, mpol, targ_ilx,
-				      NULL, false);
-	return folio;
+	return swap_cache_read_folio_sync(targ_entry, gfp_mask, mpol, targ_ilx);
 }
 
 /**
mm/vmscan.c +7 -8
index d7303eea1265..c43177a8e4dd 100644
@@ -615,8 +615,8 @@ typedef enum {
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
-static pageout_t pageout(struct folio *folio, struct address_space *mapping,
-			 struct swap_iocb **plug, struct list_head *folio_list)
+static pageout_t pageout(struct swap_io_ctx *ctx, struct address_space *mapping,
+		struct folio *folio, struct list_head *folio_list)
 {
 	int res;
 
@@ -652,9 +652,9 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
 	 * the split out folios get added back to folio_list.
 	 */
 	if (shmem_mapping(mapping))
-		res = shmem_writeout(folio, plug, folio_list);
+		res = shmem_writeout(ctx, folio, folio_list);
 	else
-		res = swap_writeout(folio, plug);
+		res = swap_writeout(ctx, folio);
 
 	if (res < 0)
 		handle_write_error(mapping, folio, res);
@@ -1063,7 +1063,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 	unsigned int nr_reclaimed = 0, nr_demoted = 0;
 	unsigned int pgactivate = 0;
 	bool do_demote_pass;
-	struct swap_iocb *plug = NULL;
+	struct swap_io_ctx ctx = {};
 
 	folio_batch_init(&free_folios);
 	memset(stat, 0, sizeof(*stat));
@@ -1394,7 +1394,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 			 * starts and then write it out here.
 			 */
 			try_to_unmap_flush_dirty();
-			switch (pageout(folio, mapping, &plug, folio_list)) {
+			switch (pageout(&ctx, mapping, folio, folio_list)) {
 			case PAGE_KEEP:
 				goto keep_locked;
 			case PAGE_ACTIVATE:
@@ -1584,8 +1584,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 	list_splice(&ret_folios, folio_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 
-	if (plug)
-		swap_write_unplug(plug);
+	swap_write_submit(&ctx);
 	return nr_reclaimed;
 }
 
mm/zswap.c +3 -1
index 761cd699e0a3..feed2557f6ed 100644
@@ -992,6 +992,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	struct folio *folio;
 	struct mempolicy *mpol;
 	struct swap_info_struct *si;
+	struct swap_io_ctx ctx = {};
 	int ret = 0;
 
 	/* try to allocate swap cache folio */
@@ -1049,7 +1050,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	folio_set_reclaim(folio);
 
 	/* start writeback */
-	__swap_writepage(folio, NULL);
+	__swap_writepage(&ctx, folio);
+	swap_write_submit(&ctx);
 
 out:
 	if (ret) {
Signature · 1 line
2.53.0
maintainer Reviewed-by on v1 3/8
#15 lore raw

Re: [PATCH 3/8] mm/swap: introduce struct swap_io_ctx

In reply to Christoph Hellwig
Quoted 622 lines · Christoph Hellwig

Generalize the context currently provided by double pointers to struct swap_iocb to an on-stack context. This cleans up the code and prepares for adding more fields and supporting batching multiple folios into a single bio for block-based swap as well.

This new swap_io_ctx is required for all functions using it, the old way of allowing a NULL iocb for some callers is removed to keep the interface consistent.

---
 mm/madvise.c    | 16 ++++++-------
 mm/page_io.c    | 60 ++++++++++++++++++++++++++-----------------------
 mm/shmem.c      | 13 +++++++----
 mm/swap.h       | 36 +++++++++++++----------------
 mm/swap_state.c | 53 +++++++++++++++++++++++++------------------
 mm/vmscan.c     | 15 ++++++-------
 mm/zswap.c      |  4 +++-
 7 files changed, 106 insertions(+), 91 deletions(-)
mm/madvise.c +8 -8
index cd9bb077072c..cd84e993190a 100644
@@ -188,7 +188,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
                unsigned long end, struct mm_walk *walk)
 {
        struct vm_area_struct *vma = walk->private;
-       struct swap_iocb *splug = NULL;
+       struct swap_io_ctx ctx = {};
        pte_t *ptep = NULL;
        spinlock_t *ptl;
        unsigned long addr;
@@ -212,15 +212,15 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
                pte_unmap_unlock(ptep, ptl);
                ptep = NULL;
 
-               folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
-                                            vma, addr, &splug);
+               folio = read_swap_cache_async(&ctx, entry, GFP_HIGHUSER_MOVABLE,
+                                       vma, addr);
                if (folio)
                        folio_put(folio);
        }
 
        if (ptep)
                pte_unmap_unlock(ptep, ptl);
-       swap_read_unplug(splug);
+       swap_read_submit(&ctx);
        cond_resched();
 
        return 0;
@@ -238,7 +238,7 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
        XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
        pgoff_t end_index = linear_page_index(vma, end) - 1;
        struct folio *folio;
-       struct swap_iocb *splug = NULL;
+       struct swap_io_ctx ctx = {};
 
        rcu_read_lock();
        xas_for_each(&xas, folio, end_index) {
@@ -257,15 +257,15 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
                xas_pause(&xas);
                rcu_read_unlock();
 
-               folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
-                                            vma, addr, &splug);
+               folio = read_swap_cache_async(&ctx, entry,
+                               mapping_gfp_mask(mapping), vma, addr);
                if (folio)
                        folio_put(folio);
 
                rcu_read_lock();
        }
        rcu_read_unlock();
-       swap_read_unplug(splug);
+       swap_read_submit(&ctx);
 }
 #endif         /* CONFIG_SWAP */
 
mm/page_io.c +32 -28
index f2d8fe7fd057..0bf035dc1170 100644
@@ -248,7 +248,7 @@ static void swap_zeromap_folio_clear(struct folio *folio)
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
  */
-int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
+int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 {
        int ret = 0;
 
@@ -295,7 +295,7 @@ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
        }
        rcu_read_unlock();
 
-       __swap_writepage(folio, swap_plug);
+       __swap_writepage(ctx, folio);
        return 0;
 out_unlock:
        folio_unlock(folio);
@@ -385,9 +385,9 @@ 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_io_ctx *ctx, struct folio *folio)
 {
-       struct swap_iocb *sio = swap_plug ? *swap_plug : NULL;
+       struct swap_iocb *sio = ctx->sio;
        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);
@@ -398,7 +398,7 @@ static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
        if (sio) {
                if (sio->iocb.ki_filp != swap_file ||
                    sio->iocb.ki_pos + sio->len != pos) {
-                       swap_write_unplug(sio);
+                       swap_write_submit(ctx);
                        sio = NULL;
                }
        }
@@ -413,12 +413,11 @@ static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
        bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
        sio->len += folio_size(folio);
        sio->nr_bvecs += 1;
-       if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs) || !swap_plug) {
-               swap_write_unplug(sio);
+       if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
+               swap_write_submit(ctx);
                sio = NULL;
        }
-       if (swap_plug)
-               *swap_plug = sio;
+       ctx->sio = sio;
 }
 
 static void swap_writepage_bdev_sync(struct folio *folio,
@@ -458,7 +457,7 @@ static void swap_writepage_bdev_async(struct folio *folio,
        submit_bio(bio);
 }
 
-void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
 {
        struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 
@@ -469,7 +468,7 @@ void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
         * is safe.
         */
        if (data_race(sis->flags & SWP_FS_OPS))
-               swap_writepage_fs(folio, swap_plug);
+               swap_writepage_fs(ctx, folio);
        /*
         * ->flags can be updated non-atomically,
         * but that will never affect SWP_SYNCHRONOUS_IO, so the data_race
@@ -481,16 +480,20 @@ void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
                swap_writepage_bdev_async(folio, sis);
 }
 
-void swap_write_unplug(struct swap_iocb *sio)
+void swap_write_submit(struct swap_io_ctx *ctx)
 {
+       struct swap_iocb *sio = ctx->sio;
        struct iov_iter from;
-       struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
        int ret;
 
+       if (!sio)
+               return;
+
        iov_iter_bvec(&from, ITER_SOURCE, sio->bvecs, sio->nr_bvecs, sio->len);
-       ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+       ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
        if (ret != -EIOCBQUEUED)
                sio_write_complete(&sio->iocb, ret);
+       ctx->sio = NULL;
 }
 
 static void sio_read_complete(struct kiocb *iocb, long ret)
@@ -582,18 +585,16 @@ 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_io_ctx *ctx, struct folio *folio)
 {
        struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
-       struct swap_iocb *sio = NULL;
+       struct swap_iocb *sio = ctx->sio;
        loff_t pos = swap_dev_pos(folio->swap);
 
-       if (plug)
-               sio = *plug;
        if (sio) {
                if (sio->iocb.ki_filp != sis->swap_file ||
                    sio->iocb.ki_pos + sio->len != pos) {
-                       swap_read_unplug(sio);
+                       swap_read_submit(ctx);
                        sio = NULL;
                }
        }
@@ -608,12 +609,11 @@ static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
        bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
        sio->len += folio_size(folio);
        sio->nr_bvecs += 1;
-       if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs) || !plug) {
-               swap_read_unplug(sio);
+       if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
+               swap_read_submit(ctx);
                sio = NULL;
        }
-       if (plug)
-               *plug = sio;
+       ctx->sio = sio;
 }
 
 static void swap_read_folio_bdev_sync(struct folio *folio,
@@ -653,7 +653,7 @@ static void swap_read_folio_bdev_async(struct folio *folio,
        submit_bio(bio);
 }
 
-void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
+void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 {
        struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
        bool synchronous = sis->flags & SWP_SYNCHRONOUS_IO;
@@ -688,7 +688,7 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
        zswap_folio_swapin(folio);
 
        if (data_race(sis->flags & SWP_FS_OPS)) {
-               swap_read_folio_fs(folio, plug);
+               swap_read_folio_fs(ctx, folio);
        } else if (synchronous) {
                swap_read_folio_bdev_sync(folio, sis);
        } else {
@@ -703,14 +703,18 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
        delayacct_swapin_end();
 }
 
-void __swap_read_unplug(struct swap_iocb *sio)
+void swap_read_submit(struct swap_io_ctx *ctx)
 {
+       struct swap_iocb *sio = ctx->sio;
        struct iov_iter from;
-       struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
        int ret;
 
+       if (!sio)
+               return;
+
        iov_iter_bvec(&from, ITER_DEST, sio->bvecs, sio->nr_bvecs, sio->len);
-       ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+       ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
        if (ret != -EIOCBQUEUED)
                sio_read_complete(&sio->iocb, ret);
+       ctx->sio = NULL;
 }
mm/shmem.c +9 -4
index d10735e49b25..17eb16dbfaa9 100644
@@ -1584,13 +1584,13 @@ int shmem_unuse(unsigned int type)
 
 /**
  * shmem_writeout - Write the folio to swap
+ * @ctx: swap I/O context
  * @folio: The folio to write
- * @plug: swap plug
  * @folio_list: list to put back folios on split
  *
  * Move the folio from the page cache to the swap cache.
  */
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
                struct list_head *folio_list)
 {
        struct address_space *mapping = folio->mapping;
@@ -1702,7 +1702,7 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
                shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap));
 
                BUG_ON(folio_mapped(folio));
-               error = swap_writeout(folio, plug);
+               error = swap_writeout(ctx, folio);
                if (error != AOP_WRITEPAGE_ACTIVATE) {
                        /* folio has been unlocked */
                        return error;
@@ -1741,7 +1741,12 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 
 int shmem_write_folio(struct folio *folio)
 {
-       return shmem_writeout(folio, NULL, NULL);
+       struct swap_io_ctx ctx = {};
+       int err;
+
+       err = shmem_writeout(&ctx, folio, NULL);
+       swap_write_submit(&ctx);
+       return err;
 }
 EXPORT_SYMBOL_GPL(shmem_write_folio);
 
mm/swap.h +16 -20
index 4f86ef338a60..79d66272dfd4 100644
@@ -4,6 +4,7 @@
 
 #include <linux/atomic.h> /* for atomic_long_t */
 #include <linux/mm.h> /* for PAGE_SHIFT */
+
 struct mempolicy;
 struct swap_iocb;
 struct swap_memcg_table;
@@ -78,6 +79,10 @@ enum swap_cluster_flags {
        CLUSTER_FLAG_MAX,
 };
 
+struct swap_io_ctx {
+       struct swap_iocb        *sio;
+};
+
 #ifdef CONFIG_SWAP
 #include <linux/swapops.h> /* for swp_offset */
 #include <linux/blk_types.h> /* for bio_end_io_t */
@@ -240,17 +245,11 @@ extern void __swap_cluster_free_entries(struct swap_info_struct *si,
 
 /* linux/mm/page_io.c */
 int sio_pool_init(void);
-struct swap_iocb;
-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)
-{
-       if (unlikely(plug))
-               __swap_read_unplug(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);
+void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio);
+void swap_read_submit(struct swap_io_ctx *ctx);
+void swap_write_submit(struct swap_io_ctx *ctx);
+int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio);
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio);
 
 /* linux/mm/swap_state.c */
 extern struct address_space swap_space __read_mostly;
@@ -317,9 +316,8 @@ void __swap_cache_replace_folio(struct swap_cluster_info *ci,
 
 void show_swap_cache_info(void);
 void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr);
-struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-               struct vm_area_struct *vma, unsigned long addr,
-               struct swap_iocb **plug);
+struct folio *read_swap_cache_async(struct swap_io_ctx *ctx, swp_entry_t entry,
+               gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr);
 struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
                struct mempolicy *mpol, pgoff_t ilx);
 struct folio *swapin_readahead(swp_entry_t entry, gfp_t flag,
@@ -335,7 +333,6 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 }
 
 #else /* CONFIG_SWAP */
-struct swap_iocb;
 static inline struct swap_cluster_info *swap_cluster_lock(
        struct swap_info_struct *si, pgoff_t offset, bool irq)
 {
@@ -381,11 +378,11 @@ static inline void folio_put_swap(struct folio *folio, struct page *page)
 {
 }
 
-static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
+static inline void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 {
 }
 
-static inline void swap_write_unplug(struct swap_iocb *sio)
+static inline void swap_write_submit(struct swap_io_ctx *ctx)
 {
 }
 
@@ -427,8 +424,7 @@ static inline void swap_update_readahead(struct folio *folio,
 {
 }
 
-static inline int swap_writeout(struct folio *folio,
-               struct swap_iocb **swap_plug)
+static inline int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 {
        return 0;
 }
@@ -474,7 +470,7 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 
 #endif /* CONFIG_SWAP */
 
-int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
                struct list_head *folio_list);
 
 #endif /* _MM_SWAP_H */
mm/swap_state.c +31 -22
index 04f5ce992401..b9613026950e 100644
@@ -623,9 +623,9 @@ void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma,
        }
 }
 
-static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
-                                          struct mempolicy *mpol, pgoff_t ilx,
-                                          struct swap_iocb **plug, bool readahead)
+static struct folio *swap_cache_read_folio(struct swap_io_ctx *ctx,
+               swp_entry_t entry, gfp_t gfp, struct mempolicy *mpol,
+               pgoff_t ilx, bool readahead)
 {
        struct folio *folio;
 
@@ -639,7 +639,7 @@ static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
        if (IS_ERR_OR_NULL(folio))
                return NULL;
 
-       swap_read_folio(folio, plug);
+       swap_read_folio(ctx, folio);
        if (readahead) {
                folio_set_readahead(folio);
                count_vm_event(SWAP_RA);
@@ -667,6 +667,7 @@ static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
 struct folio *swapin_sync(swp_entry_t entry, gfp_t gfp, unsigned long orders,
                           struct vm_fault *vmf, struct mempolicy *mpol, pgoff_t ilx)
 {
+       struct swap_io_ctx ctx = {};
        struct folio *folio;
 
        do {
@@ -679,7 +680,8 @@ struct folio *swapin_sync(swp_entry_t entry, gfp_t gfp, unsigned long orders,
        if (IS_ERR(folio))
                return folio;
 
-       swap_read_folio(folio, NULL);
+       swap_read_folio(&ctx, folio);
+       swap_read_submit(&ctx);
        return folio;
 }
 
@@ -689,9 +691,8 @@ struct folio *swapin_sync(swp_entry_t entry, gfp_t gfp, unsigned long orders,
  * A failure return means that either the page allocation failed or that
  * the swap entry is no longer in use.
  */
-struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-               struct vm_area_struct *vma, unsigned long addr,
-               struct swap_iocb **plug)
+struct folio *read_swap_cache_async(struct swap_io_ctx *ctx, swp_entry_t entry,
+               gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr)
 {
        struct swap_info_struct *si;
        struct mempolicy *mpol;
@@ -703,13 +704,24 @@ struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
                return NULL;
 
        mpol = get_vma_policy(vma, addr, 0, &ilx);
-       folio = swap_cache_read_folio(entry, gfp_mask, mpol, ilx, plug, false);
+       folio = swap_cache_read_folio(ctx, entry, gfp_mask, mpol, ilx, false);
        mpol_cond_put(mpol);
 
        put_swap_device(si);
        return folio;
 }
 
+static struct folio *swap_cache_read_folio_sync(swp_entry_t entry, gfp_t gfp,
+               struct mempolicy *mpol, pgoff_t ilx)
+{
+       struct swap_io_ctx ctx = {};
+       struct folio *folio;
+
+       folio = swap_cache_read_folio(&ctx, entry, gfp, mpol, ilx, false);
+       swap_read_submit(&ctx);
+       return folio;
+}
+
 static unsigned int __swapin_nr_pages(unsigned long prev_offset,
                                      unsigned long offset,
                                      int hits,
@@ -798,8 +810,8 @@ struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
        unsigned long start_offset, end_offset;
        unsigned long mask;
        struct swap_info_struct *si = __swap_entry_to_info(entry);
+       struct swap_io_ctx ctx = {};
        struct blk_plug plug;
-       struct swap_iocb *splug = NULL;
        swp_entry_t ra_entry;
 
        mask = swapin_nr_pages(offset) - 1;
@@ -818,18 +830,17 @@ struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
        for (offset = start_offset; offset <= end_offset ; offset++) {
                /* Ok, do the async read-ahead now */
                ra_entry = swp_entry(swp_type(entry), offset);
-               folio = swap_cache_read_folio(ra_entry, gfp_mask, mpol, ilx,
-                                             &splug, offset != entry_offset);
+               folio = swap_cache_read_folio(&ctx, ra_entry, gfp_mask, mpol,
+                               ilx, offset != entry_offset);
                if (!folio)
                        continue;
                folio_put(folio);
        }
        blk_finish_plug(&plug);
-       swap_read_unplug(splug);
+       swap_read_submit(&ctx);
        lru_add_drain();        /* Push any new pages onto the LRU now */
 skip:
-       /* The page was likely read above, so no need for plugging here */
-       return swap_cache_read_folio(entry, gfp_mask, mpol, ilx, NULL, false);
+       return swap_cache_read_folio_sync(entry, gfp_mask, mpol, ilx);
 }
 
 static int swap_vma_ra_win(struct vm_fault *vmf, unsigned long *start,
@@ -889,8 +900,8 @@ static int swap_vma_ra_win(struct vm_fault *vmf, unsigned long *start,
 static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
                struct mempolicy *mpol, pgoff_t targ_ilx, struct vm_fault *vmf)
 {
+       struct swap_io_ctx ctx = {};
        struct blk_plug plug;
-       struct swap_iocb *splug = NULL;
        struct folio *folio;
        pte_t *pte = NULL, pentry;
        int win;
@@ -929,8 +940,8 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
                        if (!si)
                                continue;
                }
-               folio = swap_cache_read_folio(entry, gfp_mask, mpol, ilx,
-                                             &splug, addr != vmf->address);
+               folio = swap_cache_read_folio(&ctx, entry, gfp_mask, mpol, ilx,
+                                             addr != vmf->address);
                if (si)
                        put_swap_device(si);
                if (!folio)
@@ -940,13 +951,11 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
        if (pte)
                pte_unmap(pte);
        blk_finish_plug(&plug);
-       swap_read_unplug(splug);
+       swap_read_submit(&ctx);
        lru_add_drain();
 skip:
        /* The folio was likely read above, so no need for plugging here */
-       folio = swap_cache_read_folio(targ_entry, gfp_mask, mpol, targ_ilx,
-                                     NULL, false);
-       return folio;
+       return swap_cache_read_folio_sync(targ_entry, gfp_mask, mpol, targ_ilx);
 }
 
 /**
mm/vmscan.c +7 -8
index d7303eea1265..c43177a8e4dd 100644
@@ -615,8 +615,8 @@ typedef enum {
 /*
  * pageout is called by shrink_folio_list() for each dirty folio.
  */
-static pageout_t pageout(struct folio *folio, struct address_space *mapping,
-                        struct swap_iocb **plug, struct list_head *folio_list)
+static pageout_t pageout(struct swap_io_ctx *ctx, struct address_space *mapping,
+               struct folio *folio, struct list_head *folio_list)
 {
        int res;
 
@@ -652,9 +652,9 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping,
         * the split out folios get added back to folio_list.
         */
        if (shmem_mapping(mapping))
-               res = shmem_writeout(folio, plug, folio_list);
+               res = shmem_writeout(ctx, folio, folio_list);
        else
-               res = swap_writeout(folio, plug);
+               res = swap_writeout(ctx, folio);
 
        if (res < 0)
                handle_write_error(mapping, folio, res);
@@ -1063,7 +1063,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
        unsigned int nr_reclaimed = 0, nr_demoted = 0;
        unsigned int pgactivate = 0;
        bool do_demote_pass;
-       struct swap_iocb *plug = NULL;
+       struct swap_io_ctx ctx = {};
 
        folio_batch_init(&free_folios);
        memset(stat, 0, sizeof(*stat));
@@ -1394,7 +1394,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
                         * starts and then write it out here.
                         */
                        try_to_unmap_flush_dirty();
-                       switch (pageout(folio, mapping, &plug, folio_list)) {
+                       switch (pageout(&ctx, mapping, folio, folio_list)) {
                        case PAGE_KEEP:
                                goto keep_locked;
                        case PAGE_ACTIVATE:
@@ -1584,8 +1584,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
        list_splice(&ret_folios, folio_list);
        count_vm_events(PGACTIVATE, pgactivate);
 
-       if (plug)
-               swap_write_unplug(plug);
+       swap_write_submit(&ctx);
        return nr_reclaimed;
 }
 
mm/zswap.c +1 -0
index 761cd699e0a3..feed2557f6ed 100644
@@ -992,6 +992,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
        struct folio *folio;
        struct mempolicy *mpol;
        struct swap_info_struct *si;
+       struct swap_io_ctx ctx = {};
        int ret = 0;
 
        /* try to allocate swap cache folio */

mm/zswap.c static int zswap_writeback_entry(struct zswap_entry *entry, · line 1054

Quoted 6 lines
mm/zswap.c +2 -1
@@ -1049,7 +1050,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
        folio_set_reclaim(folio);
 
        /* start writeback */
-       __swap_writepage(folio, NULL);
+       __swap_writepage(&ctx, folio);
+       swap_write_submit(&ctx);

LGTM.

Note to self and other zswap folks: explore batching IO for zswap writeback. Should be fairly simple to maintain swap_io_ctx for each writeback round and pass it around. Not sure how much physical swap address space contiguity these zswap entries still have at the point of zswap writeback, as zswap-ins might have already punched holes. But can't be worse than status quo, and soon we will able to defer the allocation of physical swap space until writeback time with swap virtualization, which will make batching more attractive here :)

#16 lore raw

Re: [PATCH 3/8] mm/swap: introduce struct swap_io_ctx

On Fri, Jun 05, 2026 at 10:41:56AM -0700, Nhat Pham wrote:

[fullquote]

Can you trim the parts of the mail that you are not replying to? You've quoted the entire mail without any comment on the patch, just to add a note at the end.

Quoted 3 lines

Note to self and other zswap folks: explore batching IO for zswap writeback. Should be fairly simple to maintain swap_io_ctx for each writeback round and pass it around.

Yes, compression should benefit from larger chunks to work on. I think the same would also apply to zram (to respond to Chris' comment elsewhere).

#17 lore raw

PATCH 4/8 mm/swap: also use struct swap_iocb for block I/O

In reply to Christoph Hellwig

Block I/O benefits from batching just as much as remote file systems. Extent struct swap_iocb to support building a bio on the fly as well, and rewrite the block based swap code for it. This especially benefits submit_bio based drivers that do not have the block plugging available, but also saves allocating extra bios for blk-mq drivers.

Note that the block based swap code now uses the same memcg-based check previously added for file system based swap as well.

---
 mm/page_io.c  | 526 ++++++++++++++++++++++++--------------------------
 mm/swap.h     |   1 +
 mm/swapfile.c |   9 +-
 3 files changed, 252 insertions(+), 284 deletions(-)
mm/page_io.c +247 -279
index 0bf035dc1170..22c751fe03c0 100644
@@ -28,54 +28,6 @@
 #include "swap.h"
 #include "swap_table.h"
 
-static void __end_swap_bio_write(struct bio *bio)
-{
-	struct folio *folio = bio_first_folio_all(bio);
-
-	if (bio->bi_status) {
-		/*
-		 * We failed to write the page out to swap-space.
-		 * Re-dirty the page in order to avoid it being reclaimed.
-		 * Also print a dire warning that things will go BAD (tm)
-		 * very quickly.
-		 *
-		 * Also clear PG_reclaim to avoid folio_rotate_reclaimable()
-		 */
-		folio_mark_dirty(folio);
-		pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
-				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
-				     (unsigned long long)bio->bi_iter.bi_sector);
-		folio_clear_reclaim(folio);
-	}
-	folio_end_writeback(folio);
-}
-
-static void end_swap_bio_write(struct bio *bio)
-{
-	__end_swap_bio_write(bio);
-	bio_put(bio);
-}
-
-static void __end_swap_bio_read(struct bio *bio)
-{
-	struct folio *folio = bio_first_folio_all(bio);
-
-	if (bio->bi_status) {
-		pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n",
-				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
-				     (unsigned long long)bio->bi_iter.bi_sector);
-	} else {
-		folio_mark_uptodate(folio);
-	}
-	folio_unlock(folio);
-}
-
-static void end_swap_bio_read(struct bio *bio)
-{
-	__end_swap_bio_read(bio);
-	bio_put(bio);
-}
-
 int generic_swapfile_activate(struct swap_info_struct *sis,
 				struct file *swap_file,
 				sector_t *span)
@@ -316,26 +268,47 @@ static inline void count_swpout_vm_event(struct folio *folio)
 }
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-static void bio_associate_blkg_from_page(struct bio *bio, struct folio *folio)
+static struct cgroup_subsys_state *folio_memcg_blkg_css(struct folio *folio)
+{
+	return cgroup_e_css(folio_memcg(folio)->css.cgroup, &io_cgrp_subsys);
+}
+
+static bool folio_blkg_can_merge(struct folio *folio, struct folio *prev_folio)
 {
-	struct cgroup_subsys_state *css;
-	struct mem_cgroup *memcg;
+	if (!folio_memcg_charged(folio) || !folio_memcg_charged(prev_folio))
+		return true;
+
+	rcu_read_lock();
+	if (folio_memcg_blkg_css(folio) != folio_memcg_blkg_css(prev_folio)) {
+		rcu_read_unlock();
+		return false;
+	}
+	rcu_read_unlock();
+
+	return true;
+}
 
+static void bio_associate_blkg_from_page(struct bio *bio, struct folio *folio)
+{
 	if (!folio_memcg_charged(folio))
 		return;
-
 	rcu_read_lock();
-	memcg = folio_memcg(folio);
-	css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys);
-	bio_associate_blkg_from_css(bio, css);
+	bio_associate_blkg_from_css(bio, folio_memcg_blkg_css(folio));
 	rcu_read_unlock();
 }
 #else
+static bool folio_blkg_can_merge(struct folio *folio, struct folio *prev_folio)
+{
+	return true;
+}
 #define bio_associate_blkg_from_page(bio, folio)		do { } while (0)
 #endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
 
 struct swap_iocb {
-	struct kiocb		iocb;
+	union {
+		struct kiocb	iocb;
+		struct bio	bio;
+	};
 	struct bio_vec		bvecs[SWAP_CLUSTER_MAX];
 	int			nr_bvecs;
 	int			len;
@@ -355,171 +328,70 @@ int sio_pool_init(void)
 	return 0;
 }
 
-static void sio_write_complete(struct kiocb *iocb, long ret)
+static bool swap_can_merge(struct swap_io_ctx *ctx, struct folio *folio,
+		int rw)
 {
-	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
-	struct page *page = sio->bvecs[0].bv_page;
-	int p;
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+	struct bio_vec *last_bv = &ctx->sio->bvecs[ctx->sio->nr_bvecs - 1];
+	struct folio *prev_folio = page_folio(last_bv->bv_page);
+	size_t prev_folio_size = folio_size(prev_folio);
 
-	if (ret != sio->len) {
-		/*
-		 * In the case of swap-over-nfs, this can be a
-		 * temporary failure if the system has limited
-		 * memory for allocating transmit buffers.
-		 * Mark the page dirty and avoid
-		 * folio_rotate_reclaimable but rate-limit the
-		 * messages.
-		 */
-		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
-				   ret, swap_dev_pos(page_swap_entry(page)));
-		for (p = 0; p < sio->nr_bvecs; p++) {
-			page = sio->bvecs[p].bv_page;
-			set_page_dirty(page);
-			ClearPageReclaim(page);
-		}
-	}
+	if (ctx->sis != sis)
+		return false;
 
-	for (p = 0; p < sio->nr_bvecs; p++)
-		end_page_writeback(sio->bvecs[p].bv_page);
+	if (sis->flags & SWP_FS_OPS) {
+		if (swap_dev_pos(folio->swap) !=
+		    swap_dev_pos(prev_folio->swap) + prev_folio_size)
+			return false;
+	} else {
+		if (swap_folio_sector(folio) !=
+		    swap_folio_sector(prev_folio) +
+		    (prev_folio_size >> SECTOR_SHIFT))
+			return false;
+		if (rw == WRITE && !folio_blkg_can_merge(folio, prev_folio))
+			return false;
+	}
 
-	mempool_free(sio, sio_pool);
+	return true;
 }
 
-static void swap_writepage_fs(struct swap_io_ctx *ctx, struct folio *folio)
+static void swap_add_page(struct swap_io_ctx *ctx, struct folio *folio, int rw)
 {
-	struct swap_iocb *sio = ctx->sio;
 	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);
+	struct swap_iocb *sio = ctx->sio;
 
-	count_swpout_vm_event(folio);
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-	if (sio) {
-		if (sio->iocb.ki_filp != swap_file ||
-		    sio->iocb.ki_pos + sio->len != pos) {
+	if (sio && !swap_can_merge(ctx, folio, rw)) {
+		if (rw == WRITE)
 			swap_write_submit(ctx);
-			sio = NULL;
-		}
+		else
+			swap_read_submit(ctx);
+		sio = ctx->sio;
 	}
+
 	if (!sio) {
-		sio = mempool_alloc(sio_pool, GFP_NOIO);
-		init_sync_kiocb(&sio->iocb, swap_file);
-		sio->iocb.ki_complete = sio_write_complete;
-		sio->iocb.ki_pos = pos;
+		ctx->sis = sis;
+		ctx->sio = sio = mempool_alloc(sio_pool, GFP_NOIO);
 		sio->nr_bvecs = 0;
 		sio->len = 0;
 	}
 	bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
 	sio->len += folio_size(folio);
-	sio->nr_bvecs += 1;
-	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
-		swap_write_submit(ctx);
-		sio = NULL;
+	if (++sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
+		if (rw == WRITE)
+			swap_write_submit(ctx);
+		else
+			swap_read_submit(ctx);
 	}
-	ctx->sio = sio;
-}
-
-static void swap_writepage_bdev_sync(struct folio *folio,
-		struct swap_info_struct *sis)
-{
-	struct bio_vec bv;
-	struct bio bio;
-
-	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_WRITE | REQ_SWAP);
-	bio.bi_iter.bi_sector = swap_folio_sector(folio);
-	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
-
-	bio_associate_blkg_from_page(&bio, folio);
-	count_swpout_vm_event(folio);
-
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-
-	submit_bio_wait(&bio);
-	__end_swap_bio_write(&bio);
 }
 
-static void swap_writepage_bdev_async(struct folio *folio,
-		struct swap_info_struct *sis)
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
 {
-	struct bio *bio;
-
-	bio = bio_alloc(sis->bdev, 1, REQ_OP_WRITE | REQ_SWAP, GFP_NOIO);
-	bio->bi_iter.bi_sector = swap_folio_sector(folio);
-	bio->bi_end_io = end_swap_bio_write;
-	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
+	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
 
-	bio_associate_blkg_from_page(bio, folio);
 	count_swpout_vm_event(folio);
 	folio_start_writeback(folio);
 	folio_unlock(folio);
-	submit_bio(bio);
-}
-
-void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
-{
-	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(ctx, folio);
-	/*
-	 * ->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_submit(struct swap_io_ctx *ctx)
-{
-	struct swap_iocb *sio = ctx->sio;
-	struct iov_iter from;
-	int ret;
-
-	if (!sio)
-		return;
-
-	iov_iter_bvec(&from, ITER_SOURCE, sio->bvecs, sio->nr_bvecs, sio->len);
-	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
-	if (ret != -EIOCBQUEUED)
-		sio_write_complete(&sio->iocb, ret);
-	ctx->sio = NULL;
-}
-
-static void sio_read_complete(struct kiocb *iocb, long ret)
-{
-	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
-	int p;
-
-	if (ret == sio->len) {
-		for (p = 0; p < sio->nr_bvecs; p++) {
-			struct folio *folio = page_folio(sio->bvecs[p].bv_page);
-
-			count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
-			count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
-			folio_mark_uptodate(folio);
-			folio_unlock(folio);
-		}
-		count_vm_events(PSWPIN, sio->len >> PAGE_SHIFT);
-	} else {
-		for (p = 0; p < sio->nr_bvecs; p++) {
-			struct folio *folio = page_folio(sio->bvecs[p].bv_page);
-
-			folio_unlock(folio);
-		}
-		pr_alert_ratelimited("Read-error on swap-device\n");
-	}
-	mempool_free(sio, sio_pool);
+	swap_add_page(ctx, folio, WRITE);
 }
 
 /*
@@ -585,74 +457,6 @@ static bool swap_read_folio_zeromap(struct folio *folio)
 	return true;
 }
 
-static void swap_read_folio_fs(struct swap_io_ctx *ctx, struct folio *folio)
-{
-	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
-	struct swap_iocb *sio = ctx->sio;
-	loff_t pos = swap_dev_pos(folio->swap);
-
-	if (sio) {
-		if (sio->iocb.ki_filp != sis->swap_file ||
-		    sio->iocb.ki_pos + sio->len != pos) {
-			swap_read_submit(ctx);
-			sio = NULL;
-		}
-	}
-	if (!sio) {
-		sio = mempool_alloc(sio_pool, GFP_KERNEL);
-		init_sync_kiocb(&sio->iocb, sis->swap_file);
-		sio->iocb.ki_pos = pos;
-		sio->iocb.ki_complete = sio_read_complete;
-		sio->nr_bvecs = 0;
-		sio->len = 0;
-	}
-	bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
-	sio->len += folio_size(folio);
-	sio->nr_bvecs += 1;
-	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
-		swap_read_submit(ctx);
-		sio = NULL;
-	}
-	ctx->sio = sio;
-}
-
-static void swap_read_folio_bdev_sync(struct folio *folio,
-		struct swap_info_struct *sis)
-{
-	struct bio_vec bv;
-	struct bio bio;
-
-	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ);
-	bio.bi_iter.bi_sector = swap_folio_sector(folio);
-	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
-	/*
-	 * Keep this task valid during swap readpage because the oom killer may
-	 * attempt to access it in the page fault retry time check.
-	 */
-	get_task_struct(current);
-	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
-	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
-	count_vm_events(PSWPIN, folio_nr_pages(folio));
-	submit_bio_wait(&bio);
-	__end_swap_bio_read(&bio);
-	put_task_struct(current);
-}
-
-static void swap_read_folio_bdev_async(struct folio *folio,
-		struct swap_info_struct *sis)
-{
-	struct bio *bio;
-
-	bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL);
-	bio->bi_iter.bi_sector = swap_folio_sector(folio);
-	bio->bi_end_io = end_swap_bio_read;
-	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
-	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
-	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
-	count_vm_events(PSWPIN, folio_nr_pages(folio));
-	submit_bio(bio);
-}
-
 void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
@@ -686,14 +490,7 @@ void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 
 	/* 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(ctx, folio);
-	} else if (synchronous) {
-		swap_read_folio_bdev_sync(folio, sis);
-	} else {
-		swap_read_folio_bdev_async(folio, sis);
-	}
+	swap_add_page(ctx, folio, READ);
 
 finish:
 	if (workingset) {
@@ -703,18 +500,189 @@ void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 	delayacct_swapin_end();
 }
 
-void swap_read_submit(struct swap_io_ctx *ctx)
+static void swap_write_end(struct swap_iocb *sio, bool failed)
+{
+	int p;
+
+	for (p = 0; p < sio->nr_bvecs; p++) {
+		struct page *page = sio->bvecs[p].bv_page;
+
+		if (failed) {
+			set_page_dirty(page);
+			ClearPageReclaim(page);
+		}
+		end_page_writeback(page);
+	}
+	mempool_free(sio, sio_pool);
+}
+
+static void swap_fs_write_complete(struct kiocb *iocb, long ret)
+{
+	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+	bool failed = ret != sio->len;
+
+	if (failed) {
+		struct page *page = sio->bvecs[0].bv_page;
+
+		/*
+		 * In the case of swap-over-nfs, this can be a temporary failure
+		 * if the system has limited memory for allocating transmit
+		 * buffers.  Mark the page dirty and avoid
+		 * folio_rotate_reclaimable but rate-limit the messages.
+		 */
+		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
+				   ret, swap_dev_pos(page_swap_entry(page)));
+	}
+
+	swap_write_end(sio, failed);
+}
+
+static void end_swap_bio_write(struct bio *bio)
+{
+	struct swap_iocb *sio = container_of(bio, struct swap_iocb, bio);
+	bool failed = !!bio->bi_status;
+
+	if (failed)
+		pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
+	bio_uninit(bio);
+	swap_write_end(sio, failed);
+}
+
+static void swap_read_end(struct swap_iocb *sio, bool failed)
+{
+	int p;
+
+	for (p = 0; p < sio->nr_bvecs; p++) {
+		struct folio *folio = page_folio(sio->bvecs[p].bv_page);
+
+		if (!failed) {
+			count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
+			count_memcg_folio_events(folio, PSWPIN,
+					folio_nr_pages(folio));
+			folio_mark_uptodate(folio);
+		}
+		folio_unlock(folio);
+	}
+
+	if (!failed)
+		count_vm_events(PSWPIN, sio->len >> PAGE_SHIFT);
+
+	mempool_free(sio, sio_pool);
+}
+
+static void swap_fs_read_complete(struct kiocb *iocb, long ret)
+{
+	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+	bool failed = ret != sio->len;
+
+	if (failed)
+		pr_alert_ratelimited("Read-error on swap-device\n");
+	swap_read_end(sio, failed);
+}
+
+static void swap_bio_read_end_io(struct bio *bio)
+{
+	struct swap_iocb *sio = container_of(bio, struct swap_iocb, bio);
+	bool failed = !!bio->bi_status;
+
+	if (failed)
+		pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
+	bio_uninit(bio);
+	swap_read_end(sio, failed);
+}
+
+static void swap_bdev_submit_write(struct swap_io_ctx *ctx)
 {
 	struct swap_iocb *sio = ctx->sio;
-	struct iov_iter from;
+	struct bio *bio = &sio->bio;
+
+	bio_init(bio, ctx->sis->bdev, sio->bvecs, ARRAY_SIZE(sio->bvecs),
+			REQ_OP_WRITE | REQ_SWAP);
+	bio->bi_iter.bi_size = sio->len;
+	bio->bi_iter.bi_sector = swap_folio_sector(bio_first_folio_all(bio));
+	bio_associate_blkg_from_page(bio, bio_first_folio_all(bio));
+
+	if (ctx->sis->flags & SWP_SYNCHRONOUS_IO) {
+		submit_bio_wait(bio);
+		end_swap_bio_write(bio);
+	} else {
+		bio->bi_end_io = end_swap_bio_write;
+		submit_bio(bio);
+	}
+}
+
+static void swap_bdev_submit_read(struct swap_io_ctx *ctx)
+{
+	struct swap_iocb *sio = ctx->sio;
+	struct bio *bio = &sio->bio;
+
+	bio_init(bio, ctx->sis->bdev, sio->bvecs, ARRAY_SIZE(sio->bvecs),
+			REQ_OP_READ);
+	bio->bi_iter.bi_size = sio->len;
+	bio->bi_iter.bi_sector = swap_folio_sector(bio_first_folio_all(bio));
+
+	if (ctx->sis->flags & SWP_SYNCHRONOUS_IO) {
+		/*
+		 * Keep this task valid during swap readpage because the oom
+		 * killer may attempt to access it in the page fault retry
+		 * time check.
+		 */
+		get_task_struct(current);
+		submit_bio_wait(bio);
+		swap_bio_read_end_io(bio);
+		put_task_struct(current);
+	} else {
+		bio->bi_end_io = swap_bio_read_end_io;
+		submit_bio(bio);
+	}
+}
+
+static void swap_fs_submit(struct swap_io_ctx *ctx, int rw)
+{
+	struct swap_iocb *sio = ctx->sio;
+	struct iov_iter iter;
 	int ret;
 
-	if (!sio)
-		return;
+	init_sync_kiocb(&sio->iocb, ctx->sis->swap_file);
+	sio->iocb.ki_pos = swap_dev_pos(page_folio(sio->bvecs[0].bv_page)->swap);
+	if (rw == WRITE)
+		sio->iocb.ki_complete = swap_fs_write_complete;
+	else
+		sio->iocb.ki_complete = swap_fs_read_complete;
 
-	iov_iter_bvec(&from, ITER_DEST, sio->bvecs, sio->nr_bvecs, sio->len);
-	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
+	iov_iter_bvec(&iter, rw == WRITE ? ITER_SOURCE : ITER_DEST,
+			sio->bvecs, sio->nr_bvecs, sio->len);
+	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &iter);
 	if (ret != -EIOCBQUEUED)
-		sio_read_complete(&sio->iocb, ret);
+		sio->iocb.ki_complete(&sio->iocb, ret);
+}
+
+void swap_write_submit(struct swap_io_ctx *ctx)
+{
+	if (!ctx->sio)
+		return;
+
+	if (ctx->sis->flags & SWP_FS_OPS)
+		swap_fs_submit(ctx, WRITE);
+	else
+		swap_bdev_submit_write(ctx);
+	ctx->sio = NULL;
+	ctx->sis = NULL;
+}
+
+void swap_read_submit(struct swap_io_ctx *ctx)
+{
+	if (!ctx->sio)
+		return;
+
+	if (ctx->sis->flags & SWP_FS_OPS)
+		swap_fs_submit(ctx, READ);
+	else
+		swap_bdev_submit_read(ctx);
 	ctx->sio = NULL;
+	ctx->sis = NULL;
 }
mm/swap.h +1 -0
index 79d66272dfd4..b6ba80c2afb0 100644
@@ -81,6 +81,7 @@ enum swap_cluster_flags {
 
 struct swap_io_ctx {
 	struct swap_iocb	*sio;
+	struct swap_info_struct	*sis;
 };
 
 #ifdef CONFIG_SWAP
mm/swapfile.c +4 -5
index 615d90867111..2372f7cc4653 100644
@@ -2842,6 +2842,10 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 	struct inode *inode = mapping->host;
 	int ret;
 
+	ret = sio_pool_init();
+	if (ret)
+		return ret;
+
 	if (S_ISBLK(inode->i_mode)) {
 		ret = add_swap_extent(sis, 0, sis->max, 0);
 		*span = sis->pages;
@@ -2853,11 +2857,6 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 		if (ret < 0)
 			return ret;
 		sis->flags |= SWP_ACTIVATED;
-		if ((sis->flags & SWP_FS_OPS) &&
-		    sio_pool_init() != 0) {
-			destroy_swap_extents(sis, swap_file);
-			return -ENOMEM;
-		}
 		return ret;
 	}
 
Signature · 1 line
2.53.0
reviewer
#18 lore raw

Re: [PATCH 4/8] mm/swap: also use struct swap_iocb for block I/O

Quoted 2 lines · Christoph Hellwig

Block I/O benefits from batching just as much as remote file systems. Extent struct swap_iocb to support building a bio on the fly as well,

~~~ Extend, typo

Quoted 14 lines

and rewrite the block based swap code for it. This especially benefits submit_bio based drivers that do not have the block plugging available, but also saves allocating extra bios for blk-mq drivers.

Note that the block based swap code now uses the same memcg-based check previously added for file system based swap as well.

---
 mm/page_io.c  | 526 ++++++++++++++++++++++++--------------------------
 mm/swap.h     |   1 +
 mm/swapfile.c |   9 +-
 3 files changed, 252 insertions(+), 284 deletions(-)

...snip...

reviewer
#19 lore raw

Re: [PATCH 4/8] mm/swap: also use struct swap_iocb for block I/O

In reply to Christoph Hellwig
Quoted 8 lines · Christoph Hellwig

Block I/O benefits from batching just as much as remote file systems. Extent struct swap_iocb to support building a bio on the fly as well, and rewrite the block based swap code for it. This especially benefits submit_bio based drivers that do not have the block plugging available, but also saves allocating extra bios for blk-mq drivers.

Note that the block based swap code now uses the same memcg-based check previously added for file system based swap as well.

I would add below words in log to ease patch reviewing/studying, while it could be personal style.

What it does:
- Adds bio to a union with kiocb in struct swap_iocb, so the same sio can drive either FS or block I/O;
- Removes 6 functions (swap_writepage_bdev_sync, swap_writepage_bdev_async, swap_read_folio_bdev_sync, swap_read_folio_bdev_async, swap_writepage_fs, swap_read_folio_fs) and replaces them with a unified (swap_add_page + swap_can_merge + submit path);
- Adds sis pointer to swap_io_ctx for direct access in the submit path
- sio_pool_init() is now called unconditionally (not just for FS swap), which is necessary since bdev swap now also allocates from the sio pool;

swap_add_page() should be rename to swap_add_folio();

Quoted 664 lines
---
 mm/page_io.c  | 526 ++++++++++++++++++++++++--------------------------
 mm/swap.h     |   1 +
 mm/swapfile.c |   9 +-
 3 files changed, 252 insertions(+), 284 deletions(-)
mm/page_io.c +247 -279
index 0bf035dc1170..22c751fe03c0 100644
@@ -28,54 +28,6 @@
 #include "swap.h"
 #include "swap_table.h"
 
-static void __end_swap_bio_write(struct bio *bio)
-{
-	struct folio *folio = bio_first_folio_all(bio);
-
-	if (bio->bi_status) {
-		/*
-		 * We failed to write the page out to swap-space.
-		 * Re-dirty the page in order to avoid it being reclaimed.
-		 * Also print a dire warning that things will go BAD (tm)
-		 * very quickly.
-		 *
-		 * Also clear PG_reclaim to avoid folio_rotate_reclaimable()
-		 */
-		folio_mark_dirty(folio);
-		pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
-				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
-				     (unsigned long long)bio->bi_iter.bi_sector);
-		folio_clear_reclaim(folio);
-	}
-	folio_end_writeback(folio);
-}
-
-static void end_swap_bio_write(struct bio *bio)
-{
-	__end_swap_bio_write(bio);
-	bio_put(bio);
-}
-
-static void __end_swap_bio_read(struct bio *bio)
-{
-	struct folio *folio = bio_first_folio_all(bio);
-
-	if (bio->bi_status) {
-		pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n",
-				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
-				     (unsigned long long)bio->bi_iter.bi_sector);
-	} else {
-		folio_mark_uptodate(folio);
-	}
-	folio_unlock(folio);
-}
-
-static void end_swap_bio_read(struct bio *bio)
-{
-	__end_swap_bio_read(bio);
-	bio_put(bio);
-}
-
 int generic_swapfile_activate(struct swap_info_struct *sis,
 				struct file *swap_file,
 				sector_t *span)
@@ -316,26 +268,47 @@ static inline void count_swpout_vm_event(struct folio *folio)
 }
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-static void bio_associate_blkg_from_page(struct bio *bio, struct folio *folio)
+static struct cgroup_subsys_state *folio_memcg_blkg_css(struct folio *folio)
+{
+	return cgroup_e_css(folio_memcg(folio)->css.cgroup, &io_cgrp_subsys);
+}
+
+static bool folio_blkg_can_merge(struct folio *folio, struct folio *prev_folio)
 {
-	struct cgroup_subsys_state *css;
-	struct mem_cgroup *memcg;
+	if (!folio_memcg_charged(folio) || !folio_memcg_charged(prev_folio))
+		return true;
+
+	rcu_read_lock();
+	if (folio_memcg_blkg_css(folio) != folio_memcg_blkg_css(prev_folio)) {
+		rcu_read_unlock();
+		return false;
+	}
+	rcu_read_unlock();
+
+	return true;
+}
 
+static void bio_associate_blkg_from_page(struct bio *bio, struct folio *folio)
+{
 	if (!folio_memcg_charged(folio))
 		return;
-
 	rcu_read_lock();
-	memcg = folio_memcg(folio);
-	css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys);
-	bio_associate_blkg_from_css(bio, css);
+	bio_associate_blkg_from_css(bio, folio_memcg_blkg_css(folio));
 	rcu_read_unlock();
 }
 #else
+static bool folio_blkg_can_merge(struct folio *folio, struct folio *prev_folio)
+{
+	return true;
+}
 #define bio_associate_blkg_from_page(bio, folio)		do { } while (0)
 #endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
 
 struct swap_iocb {
-	struct kiocb		iocb;
+	union {
+		struct kiocb	iocb;
+		struct bio	bio;
+	};
 	struct bio_vec		bvecs[SWAP_CLUSTER_MAX];
 	int			nr_bvecs;
 	int			len;
@@ -355,171 +328,70 @@ int sio_pool_init(void)
 	return 0;
 }
 
-static void sio_write_complete(struct kiocb *iocb, long ret)
+static bool swap_can_merge(struct swap_io_ctx *ctx, struct folio *folio,
+		int rw)
 {
-	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
-	struct page *page = sio->bvecs[0].bv_page;
-	int p;
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+	struct bio_vec *last_bv = &ctx->sio->bvecs[ctx->sio->nr_bvecs - 1];
+	struct folio *prev_folio = page_folio(last_bv->bv_page);
+	size_t prev_folio_size = folio_size(prev_folio);
 
-	if (ret != sio->len) {
-		/*
-		 * In the case of swap-over-nfs, this can be a
-		 * temporary failure if the system has limited
-		 * memory for allocating transmit buffers.
-		 * Mark the page dirty and avoid
-		 * folio_rotate_reclaimable but rate-limit the
-		 * messages.
-		 */
-		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
-				   ret, swap_dev_pos(page_swap_entry(page)));
-		for (p = 0; p < sio->nr_bvecs; p++) {
-			page = sio->bvecs[p].bv_page;
-			set_page_dirty(page);
-			ClearPageReclaim(page);
-		}
-	}
+	if (ctx->sis != sis)
+		return false;
 
-	for (p = 0; p < sio->nr_bvecs; p++)
-		end_page_writeback(sio->bvecs[p].bv_page);
+	if (sis->flags & SWP_FS_OPS) {
+		if (swap_dev_pos(folio->swap) !=
+		    swap_dev_pos(prev_folio->swap) + prev_folio_size)
+			return false;
+	} else {
+		if (swap_folio_sector(folio) !=
+		    swap_folio_sector(prev_folio) +
+		    (prev_folio_size >> SECTOR_SHIFT))
+			return false;
+		if (rw == WRITE && !folio_blkg_can_merge(folio, prev_folio))
+			return false;
+	}
 
-	mempool_free(sio, sio_pool);
+	return true;
 }
 
-static void swap_writepage_fs(struct swap_io_ctx *ctx, struct folio *folio)
+static void swap_add_page(struct swap_io_ctx *ctx, struct folio *folio, int rw)
 {
-	struct swap_iocb *sio = ctx->sio;
 	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);
+	struct swap_iocb *sio = ctx->sio;
 
-	count_swpout_vm_event(folio);
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-	if (sio) {
-		if (sio->iocb.ki_filp != swap_file ||
-		    sio->iocb.ki_pos + sio->len != pos) {
+	if (sio && !swap_can_merge(ctx, folio, rw)) {
+		if (rw == WRITE)
 			swap_write_submit(ctx);
-			sio = NULL;
-		}
+		else
+			swap_read_submit(ctx);
+		sio = ctx->sio;
 	}
+
 	if (!sio) {
-		sio = mempool_alloc(sio_pool, GFP_NOIO);
-		init_sync_kiocb(&sio->iocb, swap_file);
-		sio->iocb.ki_complete = sio_write_complete;
-		sio->iocb.ki_pos = pos;
+		ctx->sis = sis;
+		ctx->sio = sio = mempool_alloc(sio_pool, GFP_NOIO);
 		sio->nr_bvecs = 0;
 		sio->len = 0;
 	}
 	bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
 	sio->len += folio_size(folio);
-	sio->nr_bvecs += 1;
-	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
-		swap_write_submit(ctx);
-		sio = NULL;
+	if (++sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
+		if (rw == WRITE)
+			swap_write_submit(ctx);
+		else
+			swap_read_submit(ctx);
 	}
-	ctx->sio = sio;
-}
-
-static void swap_writepage_bdev_sync(struct folio *folio,
-		struct swap_info_struct *sis)
-{
-	struct bio_vec bv;
-	struct bio bio;
-
-	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_WRITE | REQ_SWAP);
-	bio.bi_iter.bi_sector = swap_folio_sector(folio);
-	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
-
-	bio_associate_blkg_from_page(&bio, folio);
-	count_swpout_vm_event(folio);
-
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-
-	submit_bio_wait(&bio);
-	__end_swap_bio_write(&bio);
 }
 
-static void swap_writepage_bdev_async(struct folio *folio,
-		struct swap_info_struct *sis)
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
 {
-	struct bio *bio;
-
-	bio = bio_alloc(sis->bdev, 1, REQ_OP_WRITE | REQ_SWAP, GFP_NOIO);
-	bio->bi_iter.bi_sector = swap_folio_sector(folio);
-	bio->bi_end_io = end_swap_bio_write;
-	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
+	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
 
-	bio_associate_blkg_from_page(bio, folio);
 	count_swpout_vm_event(folio);
 	folio_start_writeback(folio);
 	folio_unlock(folio);
-	submit_bio(bio);
-}
-
-void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
-{
-	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(ctx, folio);
-	/*
-	 * ->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_submit(struct swap_io_ctx *ctx)
-{
-	struct swap_iocb *sio = ctx->sio;
-	struct iov_iter from;
-	int ret;
-
-	if (!sio)
-		return;
-
-	iov_iter_bvec(&from, ITER_SOURCE, sio->bvecs, sio->nr_bvecs, sio->len);
-	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
-	if (ret != -EIOCBQUEUED)
-		sio_write_complete(&sio->iocb, ret);
-	ctx->sio = NULL;
-}
-
-static void sio_read_complete(struct kiocb *iocb, long ret)
-{
-	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
-	int p;
-
-	if (ret == sio->len) {
-		for (p = 0; p < sio->nr_bvecs; p++) {
-			struct folio *folio = page_folio(sio->bvecs[p].bv_page);
-
-			count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
-			count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
-			folio_mark_uptodate(folio);
-			folio_unlock(folio);
-		}
-		count_vm_events(PSWPIN, sio->len >> PAGE_SHIFT);
-	} else {
-		for (p = 0; p < sio->nr_bvecs; p++) {
-			struct folio *folio = page_folio(sio->bvecs[p].bv_page);
-
-			folio_unlock(folio);
-		}
-		pr_alert_ratelimited("Read-error on swap-device\n");
-	}
-	mempool_free(sio, sio_pool);
+	swap_add_page(ctx, folio, WRITE);
 }
 
 /*
@@ -585,74 +457,6 @@ static bool swap_read_folio_zeromap(struct folio *folio)
 	return true;
 }
 
-static void swap_read_folio_fs(struct swap_io_ctx *ctx, struct folio *folio)
-{
-	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
-	struct swap_iocb *sio = ctx->sio;
-	loff_t pos = swap_dev_pos(folio->swap);
-
-	if (sio) {
-		if (sio->iocb.ki_filp != sis->swap_file ||
-		    sio->iocb.ki_pos + sio->len != pos) {
-			swap_read_submit(ctx);
-			sio = NULL;
-		}
-	}
-	if (!sio) {
-		sio = mempool_alloc(sio_pool, GFP_KERNEL);
-		init_sync_kiocb(&sio->iocb, sis->swap_file);
-		sio->iocb.ki_pos = pos;
-		sio->iocb.ki_complete = sio_read_complete;
-		sio->nr_bvecs = 0;
-		sio->len = 0;
-	}
-	bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
-	sio->len += folio_size(folio);
-	sio->nr_bvecs += 1;
-	if (sio->nr_bvecs == ARRAY_SIZE(sio->bvecs)) {
-		swap_read_submit(ctx);
-		sio = NULL;
-	}
-	ctx->sio = sio;
-}
-
-static void swap_read_folio_bdev_sync(struct folio *folio,
-		struct swap_info_struct *sis)
-{
-	struct bio_vec bv;
-	struct bio bio;
-
-	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ);
-	bio.bi_iter.bi_sector = swap_folio_sector(folio);
-	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
-	/*
-	 * Keep this task valid during swap readpage because the oom killer may
-	 * attempt to access it in the page fault retry time check.
-	 */
-	get_task_struct(current);
-	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
-	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
-	count_vm_events(PSWPIN, folio_nr_pages(folio));
-	submit_bio_wait(&bio);
-	__end_swap_bio_read(&bio);
-	put_task_struct(current);
-}
-
-static void swap_read_folio_bdev_async(struct folio *folio,
-		struct swap_info_struct *sis)
-{
-	struct bio *bio;
-
-	bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL);
-	bio->bi_iter.bi_sector = swap_folio_sector(folio);
-	bio->bi_end_io = end_swap_bio_read;
-	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
-	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
-	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
-	count_vm_events(PSWPIN, folio_nr_pages(folio));
-	submit_bio(bio);
-}
-
 void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
@@ -686,14 +490,7 @@ void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 
 	/* 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(ctx, folio);
-	} else if (synchronous) {
-		swap_read_folio_bdev_sync(folio, sis);
-	} else {
-		swap_read_folio_bdev_async(folio, sis);
-	}
+	swap_add_page(ctx, folio, READ);
 
 finish:
 	if (workingset) {
@@ -703,18 +500,189 @@ void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 	delayacct_swapin_end();
 }
 
-void swap_read_submit(struct swap_io_ctx *ctx)
+static void swap_write_end(struct swap_iocb *sio, bool failed)
+{
+	int p;
+
+	for (p = 0; p < sio->nr_bvecs; p++) {
+		struct page *page = sio->bvecs[p].bv_page;
+
+		if (failed) {
+			set_page_dirty(page);
+			ClearPageReclaim(page);
+		}
+		end_page_writeback(page);
+	}
+	mempool_free(sio, sio_pool);
+}
+
+static void swap_fs_write_complete(struct kiocb *iocb, long ret)
+{
+	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+	bool failed = ret != sio->len;
+
+	if (failed) {
+		struct page *page = sio->bvecs[0].bv_page;
+
+		/*
+		 * In the case of swap-over-nfs, this can be a temporary failure
+		 * if the system has limited memory for allocating transmit
+		 * buffers.  Mark the page dirty and avoid
+		 * folio_rotate_reclaimable but rate-limit the messages.
+		 */
+		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
+				   ret, swap_dev_pos(page_swap_entry(page)));
+	}
+
+	swap_write_end(sio, failed);
+}
+
+static void end_swap_bio_write(struct bio *bio)
+{
+	struct swap_iocb *sio = container_of(bio, struct swap_iocb, bio);
+	bool failed = !!bio->bi_status;
+
+	if (failed)
+		pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
+	bio_uninit(bio);
+	swap_write_end(sio, failed);
+}
+
+static void swap_read_end(struct swap_iocb *sio, bool failed)
+{
+	int p;
+
+	for (p = 0; p < sio->nr_bvecs; p++) {
+		struct folio *folio = page_folio(sio->bvecs[p].bv_page);
+
+		if (!failed) {
+			count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
+			count_memcg_folio_events(folio, PSWPIN,
+					folio_nr_pages(folio));
+			folio_mark_uptodate(folio);
+		}
+		folio_unlock(folio);
+	}
+
+	if (!failed)
+		count_vm_events(PSWPIN, sio->len >> PAGE_SHIFT);
+
+	mempool_free(sio, sio_pool);
+}
+
+static void swap_fs_read_complete(struct kiocb *iocb, long ret)
+{
+	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+	bool failed = ret != sio->len;
+
+	if (failed)
+		pr_alert_ratelimited("Read-error on swap-device\n");
+	swap_read_end(sio, failed);
+}
+
+static void swap_bio_read_end_io(struct bio *bio)
+{
+	struct swap_iocb *sio = container_of(bio, struct swap_iocb, bio);
+	bool failed = !!bio->bi_status;
+
+	if (failed)
+		pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
+	bio_uninit(bio);
+	swap_read_end(sio, failed);
+}
+
+static void swap_bdev_submit_write(struct swap_io_ctx *ctx)
 {
 	struct swap_iocb *sio = ctx->sio;
-	struct iov_iter from;
+	struct bio *bio = &sio->bio;
+
+	bio_init(bio, ctx->sis->bdev, sio->bvecs, ARRAY_SIZE(sio->bvecs),
+			REQ_OP_WRITE | REQ_SWAP);
+	bio->bi_iter.bi_size = sio->len;
+	bio->bi_iter.bi_sector = swap_folio_sector(bio_first_folio_all(bio));
+	bio_associate_blkg_from_page(bio, bio_first_folio_all(bio));
+
+	if (ctx->sis->flags & SWP_SYNCHRONOUS_IO) {
+		submit_bio_wait(bio);
+		end_swap_bio_write(bio);
+	} else {
+		bio->bi_end_io = end_swap_bio_write;
+		submit_bio(bio);
+	}
+}
+
+static void swap_bdev_submit_read(struct swap_io_ctx *ctx)
+{
+	struct swap_iocb *sio = ctx->sio;
+	struct bio *bio = &sio->bio;
+
+	bio_init(bio, ctx->sis->bdev, sio->bvecs, ARRAY_SIZE(sio->bvecs),
+			REQ_OP_READ);
+	bio->bi_iter.bi_size = sio->len;
+	bio->bi_iter.bi_sector = swap_folio_sector(bio_first_folio_all(bio));
+
+	if (ctx->sis->flags & SWP_SYNCHRONOUS_IO) {
+		/*
+		 * Keep this task valid during swap readpage because the oom
+		 * killer may attempt to access it in the page fault retry
+		 * time check.
+		 */
+		get_task_struct(current);
+		submit_bio_wait(bio);
+		swap_bio_read_end_io(bio);
+		put_task_struct(current);
+	} else {
+		bio->bi_end_io = swap_bio_read_end_io;
+		submit_bio(bio);
+	}
+}
+
+static void swap_fs_submit(struct swap_io_ctx *ctx, int rw)
+{
+	struct swap_iocb *sio = ctx->sio;
+	struct iov_iter iter;
 	int ret;
 
-	if (!sio)
-		return;
+	init_sync_kiocb(&sio->iocb, ctx->sis->swap_file);
+	sio->iocb.ki_pos = swap_dev_pos(page_folio(sio->bvecs[0].bv_page)->swap);
+	if (rw == WRITE)
+		sio->iocb.ki_complete = swap_fs_write_complete;
+	else
+		sio->iocb.ki_complete = swap_fs_read_complete;
 
-	iov_iter_bvec(&from, ITER_DEST, sio->bvecs, sio->nr_bvecs, sio->len);
-	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &from);
+	iov_iter_bvec(&iter, rw == WRITE ? ITER_SOURCE : ITER_DEST,
+			sio->bvecs, sio->nr_bvecs, sio->len);
+	ret = sio->iocb.ki_filp->f_mapping->a_ops->swap_rw(&sio->iocb, &iter);
 	if (ret != -EIOCBQUEUED)
-		sio_read_complete(&sio->iocb, ret);
+		sio->iocb.ki_complete(&sio->iocb, ret);
+}
+
+void swap_write_submit(struct swap_io_ctx *ctx)
+{
+	if (!ctx->sio)
+		return;
+
+	if (ctx->sis->flags & SWP_FS_OPS)
+		swap_fs_submit(ctx, WRITE);
+	else
+		swap_bdev_submit_write(ctx);
+	ctx->sio = NULL;
+	ctx->sis = NULL;
+}
+
+void swap_read_submit(struct swap_io_ctx *ctx)
+{
+	if (!ctx->sio)
+		return;
+
+	if (ctx->sis->flags & SWP_FS_OPS)
+		swap_fs_submit(ctx, READ);
+	else
+		swap_bdev_submit_read(ctx);
 	ctx->sio = NULL;
+	ctx->sis = NULL;
 }
mm/swap.h +1 -0
index 79d66272dfd4..b6ba80c2afb0 100644
@@ -81,6 +81,7 @@ enum swap_cluster_flags {
 
 struct swap_io_ctx {
 	struct swap_iocb	*sio;
+	struct swap_info_struct	*sis;
 };
 
 #ifdef CONFIG_SWAP
mm/swapfile.c +4 -5
index 615d90867111..2372f7cc4653 100644
@@ -2842,6 +2842,10 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 	struct inode *inode = mapping->host;
 	int ret;
 
+	ret = sio_pool_init();
+	if (ret)
+		return ret;
+
 	if (S_ISBLK(inode->i_mode)) {
 		ret = add_swap_extent(sis, 0, sis->max, 0);
 		*span = sis->pages;
@@ -2853,11 +2857,6 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 		if (ret < 0)
 			return ret;
 		sis->flags |= SWP_ACTIVATED;
-		if ((sis->flags & SWP_FS_OPS) &&
-		    sio_pool_init() != 0) {
-			destroy_swap_extents(sis, swap_file);
-			return -ENOMEM;
-		}
 		return ret;
 	}
 
Signature · 1 line
2.53.0
#20 lore raw

PATCH 5/8 mm/swap: remove count_swpout_vm_event

In reply to Christoph Hellwig

There is only one caller left, so merge it into that.

---
 mm/page_io.c | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)
mm/page_io.c +10 -14
index 22c751fe03c0..0e2aabe635c8 100644
@@ -254,19 +254,6 @@ int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 	return ret;
 }
 
-static inline void count_swpout_vm_event(struct folio *folio)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (unlikely(folio_test_pmd_mappable(folio))) {
-		count_memcg_folio_events(folio, THP_SWPOUT, 1);
-		count_vm_event(THP_SWPOUT);
-	}
-#endif
-	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT);
-	count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio));
-	count_vm_events(PSWPOUT, folio_nr_pages(folio));
-}
-
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
 static struct cgroup_subsys_state *folio_memcg_blkg_css(struct folio *folio)
 {
@@ -388,7 +375,16 @@ void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
 
-	count_swpout_vm_event(folio);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (unlikely(folio_test_pmd_mappable(folio))) {
+		count_memcg_folio_events(folio, THP_SWPOUT, 1);
+		count_vm_event(THP_SWPOUT);
+	}
+#endif
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT);
+	count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio));
+	count_vm_events(PSWPOUT, folio_nr_pages(folio));
+
 	folio_start_writeback(folio);
 	folio_unlock(folio);
 	swap_add_page(ctx, folio, WRITE);
Signature · 1 line
2.53.0
reviewer Reviewed-by on v1 5/8
#21 lore raw

Re: [PATCH 5/8] mm/swap: remove count_swpout_vm_event

Quoted 6 lines · Christoph Hellwig

There is only one caller left, so merge it into that.

---
 mm/page_io.c | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)
Quoted 46 lines
mm/page_io.c +10 -14
index 22c751fe03c0..0e2aabe635c8 100644
@@ -254,19 +254,6 @@ int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 	return ret;
 }
 
-static inline void count_swpout_vm_event(struct folio *folio)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (unlikely(folio_test_pmd_mappable(folio))) {
-		count_memcg_folio_events(folio, THP_SWPOUT, 1);
-		count_vm_event(THP_SWPOUT);
-	}
-#endif
-	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT);
-	count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio));
-	count_vm_events(PSWPOUT, folio_nr_pages(folio));
-}
-
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
 static struct cgroup_subsys_state *folio_memcg_blkg_css(struct folio *folio)
 {
@@ -388,7 +375,16 @@ void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
 {
 	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
 
-	count_swpout_vm_event(folio);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (unlikely(folio_test_pmd_mappable(folio))) {
+		count_memcg_folio_events(folio, THP_SWPOUT, 1);
+		count_vm_event(THP_SWPOUT);
+	}
+#endif
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT);
+	count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio));
+	count_vm_events(PSWPOUT, folio_nr_pages(folio));
+
 	folio_start_writeback(folio);
 	folio_unlock(folio);
 	swap_add_page(ctx, folio, WRITE);
Signature · 1 line
2.53.0
#23 lore raw

PATCH 6/8 mm/swap: use swap_ops to register swap device's methods

In reply to Christoph Hellwig

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

Currently there are two types of swap devices: fs and bdev.

[hch: updated for the new submit and can_merge abstraction]
---
 include/linux/swap.h |  1 +
 mm/page_io.c         | 68 ++++++++++++++++++++++++++++----------------
 mm/swap.h            | 10 +++++++
 mm/swapfile.c        |  4 +++
 4 files changed, 58 insertions(+), 25 deletions(-)
include/linux/swap.h +1 -0
index 8c43bc3055c9..2d6fe268c82a 100644
@@ -281,6 +281,7 @@ 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)
mm/page_io.c +43 -25

96 lines not on this page · raw message

mm/swap.h +10 -0
index b6ba80c2afb0..5119feff0e93 100644
@@ -84,6 +84,13 @@ struct swap_io_ctx {
 	struct swap_info_struct	*sis;
 };
 
+struct swap_ops {
+	bool (*can_merge)(struct folio *folio, struct folio *prev_folio,
+			size_t prev_folio_size, int rw);
+	void (*submit_write)(struct swap_io_ctx *ctx);
+	void (*submit_read)(struct swap_io_ctx *ctx);
+};
+
 #ifdef CONFIG_SWAP
 #include <linux/swapops.h> /* for swp_offset */
 #include <linux/blk_types.h> /* for bio_end_io_t */
@@ -471,6 +478,9 @@ static inline unsigned int folio_swap_flags(struct folio *folio)
 
 #endif /* CONFIG_SWAP */
 
+extern const struct swap_ops swap_bdev_ops;
+extern const struct swap_ops swap_fs_ops;
+
 int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		struct list_head *folio_list);
 
mm/swapfile.c +4 -0
index 2372f7cc4653..a670635e0fbe 100644
@@ -2846,6 +2846,8 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 	if (ret)
 		return ret;
 
+	sis->ops = &swap_bdev_ops;
+
 	if (S_ISBLK(inode->i_mode)) {
 		ret = add_swap_extent(sis, 0, sis->max, 0);
 		*span = sis->pages;
@@ -2856,6 +2858,8 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 		ret = mapping->a_ops->swap_activate(sis, swap_file, span);
 		if (ret < 0)
 			return ret;
+		if (sis->flags & SWP_FS_OPS)
+			sis->ops = &swap_fs_ops;
 		sis->flags |= SWP_ACTIVATED;
 		return ret;
 	}
Signature · 1 line
2.53.0
maintainer Reviewed-by on v1 6/8
#24 lore raw

Re: [PATCH 6/8] mm/swap: use swap_ops to register swap device's methods

Quoted 10 lines · Christoph Hellwig

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

Currently there are two types of swap devices: fs and bdev.

[hch: updated for the new submit and can_merge abstraction]
reviewer
#25 lore raw
In reply to Christoph Hellwig

Hi Christoph,

Quoted 5 lines · Christoph Hellwig

Hi all,

this series makes use of the swap_iocb for block as well so that it doesn't do inefficient single-bio I/O, and then rebases the swap_ops from Baoquan on top of the now very different method structure.

What tree is this series based on? I tried the latest mainline, linux-next main branch and Andrew's mm-unstable, all failed.

And by the way, usually we add version number in each patch's subject as "[PATCH v2] xxx ".

Thanks
Baoquan

#26 lore raw
Quoted 6 lines · Baoquan He
Quoted 3 lines

this series makes use of the swap_iocb for block as well so that it doesn't do inefficient single-bio I/O, and then rebases the swap_ops from Baoquan on top of the now very different method structure.

What tree is this series based on? I tried the latest mainline, linux-next main branch and Andrew's mm-unstable, all failed.

The base is:

commit e1af79f3291a268adf4e149e1faba3052743e898 (akpm/mm-unstable)

Author: Joshua Hahn <[email protected]>
Date:   Fri May 29 13:27:54 2026 -0700

mm/nodemask: correctly describe nodemask operation return types

Quoted 2 lines

And by the way, usually we add version number in each patch's subject as "[PATCH v2] xxx ".

That does sometimes happen but is rather unusual if you take a quick look over lkml. It also isn't the default for any normal patch sending tool.

reviewer
#27 lore raw
Quoted 8 lines · Christoph Hellwig
Quoted 6 lines · Baoquan He
Quoted 3 lines

this series makes use of the swap_iocb for block as well so that it doesn't do inefficient single-bio I/O, and then rebases the swap_ops from Baoquan on top of the now very different method structure.

What tree is this series based on? I tried the latest mainline, linux-next main branch and Andrew's mm-unstable, all failed.

Quoted 7 lines

The base is:

commit e1af79f3291a268adf4e149e1faba3052743e898 (akpm/mm-unstable)

Author: Joshua Hahn <[email protected]>
Date:   Fri May 29 13:27:54 2026 -0700

mm/nodemask: correctly describe nodemask operation return types

Thanks. And seems the patchset pulled back via b4 only contains the patch 1~5/8 and patch 8/8, it misses 6~7/8. Just in case if someone else also use b4 and meets the similar issue when applying patches. This could be related to the email sending tool or its settings.

Quoted 8 lines
Quoted 4 lines

And by the way, usually we add version number in each patch's subject as "[PATCH v2] xxx ".

That does sometimes happen but is rather unusual if you take a quick look over lkml. It also isn't the default for any normal patch sending tool.

Really, what I have seen are all this kind of format, but surely I could see too few. Anyway, it doesn't matter much. Thanks.

#28 lore raw
Quoted 15 lines · Baoquan He
Quoted 14 lines · Christoph Hellwig
Quoted 6 lines · Baoquan He
Quoted 3 lines

this series makes use of the swap_iocb for block as well so that it doesn't do inefficient single-bio I/O, and then rebases the swap_ops from Baoquan on top of the now very different method structure.

What tree is this series based on? I tried the latest mainline, linux-next main branch and Andrew's mm-unstable, all failed.

The base is:

commit e1af79f3291a268adf4e149e1faba3052743e898 (akpm/mm-unstable)

Author: Joshua Hahn <[email protected]>
Date:   Fri May 29 13:27:54 2026 -0700
Quoted 6 lines
Quoted 1 line

mm/nodemask: correctly describe nodemask operation return types

Thanks. And seems the patchset pulled back via b4 only contains the patch 1~5/8 and patch 8/8, it misses 6~7/8. Just in case if someone else also use b4 and meets the similar issue when applying patches. This could be related to the email sending tool or its settings.

In case it makes your (or anyone elses) life easier, I also have a git branch here:

https://git.infradead.org/?p=users/hch/misc.git;a=shortlog;h=refs/heads/swap_ops

#29 lore raw

PATCH 7/8 mm/swap: remove SWP_FS_OPS

In reply to Christoph Hellwig

Provide a swap_fs_activate helper that directly sets up swap_fs_ops, and a flag in struct swap_ops to indicate of NOFS swapping is allowed.

---
 Documentation/filesystems/locking.rst |  5 +++--
 Documentation/filesystems/vfs.rst     |  4 ++--
 fs/nfs/file.c                         |  4 +---
 fs/smb/client/file.c                  |  4 +---
 include/linux/swap.h                  |  6 +++++-
 mm/page_io.c                          | 10 +++++++++-
 mm/swap.h                             | 16 ++++------------
 mm/swapfile.c                         |  2 --
 mm/vmscan.c                           | 14 ++++++--------
 9 files changed, 31 insertions(+), 34 deletions(-)
Documentation/filesystems/locking.rst +3 -2
index 8421ea21bd35..70481bdc031d 100644
@@ -355,13 +355,14 @@ should perform any validation and preparation necessary to ensure that
 writes can be performed with minimal memory allocation.  It should call
 add_swap_extent(), or the helper iomap_swapfile_activate(), and return
 the number of extents added.  If IO should be submitted through
-->swap_rw(), it should set SWP_FS_OPS, otherwise IO will be submitted
+->swap_rw(), it should call swap_fs_activate, otherwise IO will be submitted
 directly to the block device ``sis->bdev``.
 
 ->swap_deactivate() will be called in the sys_swapoff()
 path after ->swap_activate() returned success.
 
-->swap_rw will be called for swap IO if SWP_FS_OPS was set by ->swap_activate().
+->swap_rw will be called for swap IO if swap_fs_activate was called by
+->swap_activate().
 
 file_lock_operations
 ====================
Documentation/filesystems/vfs.rst +2 -2
index 7c753148af88..e7677423a20f 100644
@@ -977,7 +977,7 @@ cache in your filesystem.  The following members are defined:
 	can be performed with minimal memory allocation.  It should call
 	add_swap_extent(), or the helper iomap_swapfile_activate(), and
 	return the number of extents added.  If IO should be submitted
-	through ->swap_rw(), it should set SWP_FS_OPS, otherwise IO will
+	through ->swap_rw(), it should call swap_fs_activate, otherwise IO will
 	be submitted directly to the block device ``sis->bdev``.
 
 ``swap_deactivate``
@@ -985,7 +985,7 @@ cache in your filesystem.  The following members are defined:
 	successful.
 
 ``swap_rw``
-	Called to read or write swap pages when SWP_FS_OPS is set.
+	Called to read or write swap pages when swap_fs_activate was called.
 
 The File Object
 ===============
fs/nfs/file.c +1 -3
index 25048a3c2364..8172c9972b46 100644
@@ -589,7 +589,7 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	ret = rpc_clnt_swap_activate(clnt);
 	if (ret)
 		return ret;
-	ret = add_swap_extent(sis, 0, sis->max, 0);
+	ret = swap_fs_activate(sis);
 	if (ret < 0) {
 		rpc_clnt_swap_deactivate(clnt);
 		return ret;
@@ -599,8 +599,6 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 
 	if (cl->rpc_ops->enable_swap)
 		cl->rpc_ops->enable_swap(inode);
-
-	sis->flags |= SWP_FS_OPS;
 	return ret;
 }
 
fs/smb/client/file.c +1 -3
index b60344125f27..3e775c5bdcb9 100644
@@ -3332,9 +3332,7 @@ static int cifs_swap_activate(struct swap_info_struct *sis,
 	 * but we could add call to grab a byte range lock to prevent others
 	 * from reading or writing the file
 	 */
-
-	sis->flags |= SWP_FS_OPS;
-	return add_swap_extent(sis, 0, sis->max, 0);
+	return swap_fs_activate(sis);
 }
 
 static void cifs_swap_deactivate(struct file *file)
include/linux/swap.h +5 -1
index 2d6fe268c82a..636d94108166 100644
@@ -208,7 +208,6 @@ enum {
 	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
 	SWP_ACTIVATED	= (1 << 7),	/* set after swap_activate success */
-	SWP_FS_OPS	= (1 << 8),	/* swapfile operations go through fs */
 	SWP_AREA_DISCARD = (1 << 9),	/* single-time swap area discards */
 	SWP_PAGE_DISCARD = (1 << 10),	/* freed swap page-cluster discards */
 	SWP_STABLE_WRITES = (1 << 11),	/* no overwrite PG_writeback pages */
@@ -403,6 +402,7 @@ extern void __meminit kswapd_stop(int nid);
 
 #ifdef CONFIG_SWAP
 
+int swap_fs_activate(struct swap_info_struct *sis);
 int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
 		unsigned long nr_pages, sector_t start_block);
 int generic_swapfile_activate(struct swap_info_struct *, struct file *,
@@ -527,6 +527,10 @@ static inline bool folio_free_swap(struct folio *folio)
 	return false;
 }
 
+static inline int swap_fs_activate(struct swap_info_struct *sis)
+{
+	return -EINVAL;
+}
 static inline int add_swap_extent(struct swap_info_struct *sis,
 				  unsigned long start_page,
 				  unsigned long nr_pages, sector_t start_block)
mm/page_io.c +9 -1
index 218d8fd23dda..cdac55d0a2e9 100644
@@ -677,12 +677,20 @@ static bool swap_fs_can_merge(struct folio *folio, struct folio *prev_folio,
 		swap_dev_pos(prev_folio->swap) + prev_folio_size;
 }
 
-const struct swap_ops swap_fs_ops = {
+static const struct swap_ops swap_fs_ops = {
+	.flags			= SWAP_OPS_F_NOFS,
 	.submit_write		= swap_fs_submit_write,
 	.submit_read		= swap_fs_submit_read,
 	.can_merge		= swap_fs_can_merge,
 };
 
+int swap_fs_activate(struct swap_info_struct *sis)
+{
+	sis->ops = &swap_fs_ops;
+	return add_swap_extent(sis, 0, sis->max, 0);
+}
+EXPORT_SYMBOL_GPL(swap_fs_activate);
+
 void swap_write_submit(struct swap_io_ctx *ctx)
 {
 	if (!ctx->sio)
mm/swap.h +4 -12
index 5119feff0e93..edb512e619ee 100644
@@ -84,7 +84,11 @@ struct swap_io_ctx {
 	struct swap_info_struct	*sis;
 };
 
+#define SWAP_OPS_F_NOFS		(1U << 0)
+
 struct swap_ops {
+	unsigned int		flags;
+
 	bool (*can_merge)(struct folio *folio, struct folio *prev_folio,
 			size_t prev_folio_size, int rw);
 	void (*submit_write)(struct swap_io_ctx *ctx);
@@ -335,11 +339,6 @@ struct folio *swapin_sync(swp_entry_t entry, gfp_t flag, unsigned long orders,
 void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma,
 			   unsigned long addr);
 
-static inline unsigned int folio_swap_flags(struct folio *folio)
-{
-	return __swap_entry_to_info(folio->swap)->flags;
-}
-
 #else /* CONFIG_SWAP */
 static inline struct swap_cluster_info *swap_cluster_lock(
 	struct swap_info_struct *si, pgoff_t offset, bool irq)
@@ -470,16 +469,9 @@ static inline void __swap_cache_replace_folio(struct swap_cluster_info *ci,
 		struct folio *old, struct folio *new)
 {
 }
-
-static inline unsigned int folio_swap_flags(struct folio *folio)
-{
-	return 0;
-}
-
 #endif /* CONFIG_SWAP */
 
 extern const struct swap_ops swap_bdev_ops;
-extern const struct swap_ops swap_fs_ops;
 
 int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		struct list_head *folio_list);
mm/swapfile.c +0 -2
index a670635e0fbe..284eebc40a70 100644
@@ -2858,8 +2858,6 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 		ret = mapping->a_ops->swap_activate(sis, swap_file, span);
 		if (ret < 0)
 			return ret;
-		if (sis->flags & SWP_FS_OPS)
-			sis->ops = &swap_fs_ops;
 		sis->flags |= SWP_ACTIVATED;
 		return ret;
 	}
mm/vmscan.c +6 -8
index c43177a8e4dd..2d44ebfebdea 100644
@@ -1037,16 +1037,14 @@ static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask)
 {
 	if (gfp_mask & __GFP_FS)
 		return true;
-	if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO))
-		return false;
 	/*
-	 * We can "enter_fs" for swap-cache with only __GFP_IO
-	 * providing this isn't SWP_FS_OPS.
-	 * ->flags can be updated non-atomically,
-	 * but that will never affect SWP_FS_OPS, so the data_race
-	 * is safe.
+	 * We can "enter_fs" for swap-cache with only __GFP_IO unless backed by
+	 * a swapfile that requires GFP_NOFS I/O.
 	 */
-	return !data_race(folio_swap_flags(folio) & SWP_FS_OPS);
+	if (folio_test_swapcache(folio) && (gfp_mask & __GFP_IO) &&
+	    !(__swap_entry_to_info(folio->swap)->ops->flags & SWAP_OPS_F_NOFS))
+		return true;
+	return false;
 }
 
 /*
Signature · 1 line
2.53.0
reviewer
#30 lore raw

Re: [PATCH 7/8] mm/swap: remove SWP_FS_OPS

On 06/01/26 at 01:34pm, Christoph Hellwig wrote:
...snip...

mm/swap.h struct swap_io_ctx { · line 88

Quoted 10 lines
mm/swap.h +2 -0
index 5119feff0e93..edb512e619ee 100644
@@ -84,7 +84,11 @@ struct swap_io_ctx {
 	struct swap_info_struct	*sis;
 };
 
+#define SWAP_OPS_F_NOFS		(1U << 0)
+

The name of this flag and its usage are a little weird, surely the old one SWP_FS_OPS is similar. Do you think if we need add some document as below to make it clearer? Personal opinion and just for reference.

mm/swap.h +12 -0
index edb512e619ee..3d978382a7d5 100644
@@ -84,6 +84,18 @@ struct swap_io_ctx {
 	struct swap_info_struct	*sis;
 };
 
+/*
+ * SWAP_OPS_F_NOFS: swap operations that may recurse into the filesystem
+ * (e.g. NFS, CIFS).  When set, callers (specifically reclaim) must operate
+ * under GFP_NOFS / !__GFP_FS to avoid deadlock.  When clear (block-device
+ * swap), the swap I/O path does not touch the filesystem, so reclaim may
+ * safely enter the filesystem even with only __GFP_IO.
+ *
+ * In may_enter_fs() this appears as a double negative (!SWAP_OPS_F_NOFS)
+ * which reads as "not a nofs swap => may enter fs".  This is intentional:
+ * it is bdev swap (the common case) that allows filesystem re-entry, while
+ * filesystem-based swap explicitly forbids it.
+ */
 #define SWAP_OPS_F_NOFS		(1U << 0)
 
 struct swap_ops {
mm/vmscan.c +3 -1
index 2d44ebfebdea..a92956de5e10 100644
@@ -1039,7 +1039,9 @@ static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask)
 		return true;
 	/*
 	 * We can "enter_fs" for swap-cache with only __GFP_IO unless backed by
-	 * a swapfile that requires GFP_NOFS I/O.
+	 * a swapfile that requires GFP_NOFS I/O (i.e. filesystem-based swap
+	 * like NFS/CIFS, which sets SWAP_OPS_F_NOFS).  Block-device swap
+	 * never touches the filesystem, so it is safe to enter fs here.
 	 */
 	if (folio_test_swapcache(folio) && (gfp_mask & __GFP_IO) &&
 	    !(__swap_entry_to_info(folio->swap)->ops->flags & SWAP_OPS_F_NOFS))
Quoted 78 lines
mm/swap.h +2 -12
 struct swap_ops {
+	unsigned int		flags;
+
 	bool (*can_merge)(struct folio *folio, struct folio *prev_folio,
 			size_t prev_folio_size, int rw);
 	void (*submit_write)(struct swap_io_ctx *ctx);
@@ -335,11 +339,6 @@ struct folio *swapin_sync(swp_entry_t entry, gfp_t flag, unsigned long orders,
 void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma,
 			   unsigned long addr);
 
-static inline unsigned int folio_swap_flags(struct folio *folio)
-{
-	return __swap_entry_to_info(folio->swap)->flags;
-}
-
 #else /* CONFIG_SWAP */
 static inline struct swap_cluster_info *swap_cluster_lock(
 	struct swap_info_struct *si, pgoff_t offset, bool irq)
@@ -470,16 +469,9 @@ static inline void __swap_cache_replace_folio(struct swap_cluster_info *ci,
 		struct folio *old, struct folio *new)
 {
 }
-
-static inline unsigned int folio_swap_flags(struct folio *folio)
-{
-	return 0;
-}
-
 #endif /* CONFIG_SWAP */
 
 extern const struct swap_ops swap_bdev_ops;
-extern const struct swap_ops swap_fs_ops;
 
 int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		struct list_head *folio_list);
mm/swapfile.c +0 -2
index a670635e0fbe..284eebc40a70 100644
@@ -2858,8 +2858,6 @@ static int setup_swap_extents(struct swap_info_struct *sis,
 		ret = mapping->a_ops->swap_activate(sis, swap_file, span);
 		if (ret < 0)
 			return ret;
-		if (sis->flags & SWP_FS_OPS)
-			sis->ops = &swap_fs_ops;
 		sis->flags |= SWP_ACTIVATED;
 		return ret;
 	}
mm/vmscan.c +6 -8
index c43177a8e4dd..2d44ebfebdea 100644
@@ -1037,16 +1037,14 @@ static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask)
 {
 	if (gfp_mask & __GFP_FS)
 		return true;
-	if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO))
-		return false;
 	/*
-	 * We can "enter_fs" for swap-cache with only __GFP_IO
-	 * providing this isn't SWP_FS_OPS.
-	 * ->flags can be updated non-atomically,
-	 * but that will never affect SWP_FS_OPS, so the data_race
-	 * is safe.
+	 * We can "enter_fs" for swap-cache with only __GFP_IO unless backed by
+	 * a swapfile that requires GFP_NOFS I/O.
 	 */
-	return !data_race(folio_swap_flags(folio) & SWP_FS_OPS);
+	if (folio_test_swapcache(folio) && (gfp_mask & __GFP_IO) &&
+	    !(__swap_entry_to_info(folio->swap)->ops->flags & SWAP_OPS_F_NOFS))
+		return true;
+	return false;
 }
 
 /*
Signature · 1 line
2.53.0
#31 lore raw

Re: [PATCH 7/8] mm/swap: remove SWP_FS_OPS

Quoted 11 lines · Baoquan He

+ * SWAP_OPS_F_NOFS: swap operations that may recurse into the filesystem
+ * (e.g. NFS, CIFS). When set, callers (specifically reclaim) must operate
+ * under GFP_NOFS / !__GFP_FS to avoid deadlock. When clear (block-device
+ * swap), the swap I/O path does not touch the filesystem, so reclaim may
+ * safely enter the filesystem even with only __GFP_IO.
+ *
+ * In may_enter_fs() this appears as a double negative (!SWAP_OPS_F_NOFS)
+ * which reads as "not a nofs swap => may enter fs". This is intentional:
+ * it is bdev swap (the common case) that allows filesystem re-entry, while
+ * filesystem-based swap explicitly forbids it.
+ */

This is very verbose, but not incorrect. If everyone is fine with it, I can add it to the next version.

Or if people think it is clearer. we can add a gfp constraint to the ops?

#33 lore raw

PATCH 8/8 mm/vmstat: add NRSWP{IN,OUT} counters

In reply to Christoph Hellwig

Count how many swap I/Os we cause. Due to batching this can be different than the currently counter number of pages written/read, and tracking this information is useful to see how efficient the batching is.

---
 include/linux/vm_event_item.h | 4 ++++
 mm/page_io.c                  | 2 ++
 mm/vmstat.c                   | 6 +++++-
 3 files changed, 11 insertions(+), 1 deletion(-)
include/linux/vm_event_item.h +4 -0
index 03fe95f5a020..2628ccda076a 100644
@@ -175,6 +175,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		KSTACK_REST,
 #endif
 #endif /* CONFIG_DEBUG_STACK_USAGE */
+#ifdef CONFIG_SWAP
+		NRSWPIN,
+		NRSWPOUT,
+#endif /* CONFIG_SWAP */
 		NR_VM_EVENT_ITEMS
 };
 
mm/page_io.c +2 -0
index cdac55d0a2e9..c020e8ebf966 100644
@@ -695,6 +695,7 @@ void swap_write_submit(struct swap_io_ctx *ctx)
 {
 	if (!ctx->sio)
 		return;
+	count_vm_events(NRSWPOUT, 1);
 	ctx->sis->ops->submit_write(ctx);
 	ctx->sio = NULL;
 	ctx->sis = NULL;
@@ -704,6 +705,7 @@ void swap_read_submit(struct swap_io_ctx *ctx)
 {
 	if (!ctx->sio)
 		return;
+	count_vm_events(NRSWPIN, 1);
 	ctx->sis->ops->submit_read(ctx);
 	ctx->sio = NULL;
 	ctx->sis = NULL;
mm/vmstat.c +5 -1
index f534972f517d..9559f3c95735 100644
@@ -1488,7 +1488,11 @@ const char * const vmstat_text[] = {
 #if THREAD_SIZE > 65536
 	[I(KSTACK_REST)]			= "kstack_rest",
 #endif
-#endif
+#endif /* CONFIG_DEBUG_STACK_USAGE */
+#ifdef CONFIG_SWAP
+	[I(NRSWPIN)]				= "nrswpin",
+	[I(NRSWPOUT)]				= "nrswpout",
+#endif /* CONFIG_SWAP */
 #undef I
 #endif /* CONFIG_VM_EVENT_COUNTERS */
 };
Signature · 1 line
2.53.0
reviewer
#34 lore raw

Re: [PATCH 8/8] mm/vmstat: add NRSWP{IN,OUT} counters

Quoted 2 lines · Christoph Hellwig

Count how many swap I/Os we cause. Due to batching this can be different than the currently counter number of pages written/read,

                     ~~~~~~~ current, typo?
Quoted 15 lines

and tracking this information is useful to see how efficient the batching is.

---
 include/linux/vm_event_item.h | 4 ++++
 mm/page_io.c                  | 2 ++
 mm/vmstat.c                   | 6 +++++-
 3 files changed, 11 insertions(+), 1 deletion(-)
include/linux/vm_event_item.h +0 -0
index 03fe95f5a020..2628ccda076a 100644

include/linux/vm_event_item.h enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, · line 181

Quoted 7 lines
include/linux/vm_event_item.h +4 -0
@@ -175,6 +175,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		KSTACK_REST,
 #endif
 #endif /* CONFIG_DEBUG_STACK_USAGE */
+#ifdef CONFIG_SWAP
+		NRSWPIN,
+		NRSWPOUT,
+#endif /* CONFIG_SWAP */

Putting them together with 'SWAP_RA ... SWPOUT_ZERO' could impact the ongoing program/script?

Quoted 43 lines
include/linux/vm_event_item.h +0 -0
 		NR_VM_EVENT_ITEMS
 };
 
mm/page_io.c +2 -0
index cdac55d0a2e9..c020e8ebf966 100644
@@ -695,6 +695,7 @@ void swap_write_submit(struct swap_io_ctx *ctx)
 {
 	if (!ctx->sio)
 		return;
+	count_vm_events(NRSWPOUT, 1);
 	ctx->sis->ops->submit_write(ctx);
 	ctx->sio = NULL;
 	ctx->sis = NULL;
@@ -704,6 +705,7 @@ void swap_read_submit(struct swap_io_ctx *ctx)
 {
 	if (!ctx->sio)
 		return;
+	count_vm_events(NRSWPIN, 1);
 	ctx->sis->ops->submit_read(ctx);
 	ctx->sio = NULL;
 	ctx->sis = NULL;
mm/vmstat.c +5 -1
index f534972f517d..9559f3c95735 100644
@@ -1488,7 +1488,11 @@ const char * const vmstat_text[] = {
 #if THREAD_SIZE > 65536
 	[I(KSTACK_REST)]			= "kstack_rest",
 #endif
-#endif
+#endif /* CONFIG_DEBUG_STACK_USAGE */
+#ifdef CONFIG_SWAP
+	[I(NRSWPIN)]				= "nrswpin",
+	[I(NRSWPOUT)]				= "nrswpout",
+#endif /* CONFIG_SWAP */
 #undef I
 #endif /* CONFIG_VM_EVENT_COUNTERS */
 };
Signature · 1 line
2.53.0
#35 lore raw

Re: [PATCH 8/8] mm/vmstat: add NRSWP{IN,OUT} counters

Quoted 8 lines · Baoquan He

include/linux/vm_event_item.h enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, · line 181

Quoted 5 lines

#endif /* CONFIG_DEBUG_STACK_USAGE */

include/linux/vm_event_item.h +4 -0
+#ifdef CONFIG_SWAP
+		NRSWPIN,
+		NRSWPOUT,
+#endif /* CONFIG_SWAP */

Putting them together with 'SWAP_RA ... SWPOUT_ZERO' could impact the ongoing program/script?

I was under the impression that we should not reorder vmstate events?

If reordering the vmstat output is fine, I can group them.

maintainer Reviewed-by on v1 8/8
#36 lore raw

Re: [PATCH 8/8] mm/vmstat: add NRSWP{IN,OUT} counters

In reply to Christoph Hellwig
Quoted 18 lines · Christoph Hellwig

Count how many swap I/Os we cause. Due to batching this can be different than the currently counter number of pages written/read, and tracking this information is useful to see how efficient the batching is.

---
 include/linux/vm_event_item.h | 4 ++++
 mm/page_io.c                  | 2 ++
 mm/vmstat.c                   | 6 +++++-
 3 files changed, 11 insertions(+), 1 deletion(-)
include/linux/vm_event_item.h +0 -0
index 03fe95f5a020..2628ccda076a 100644

include/linux/vm_event_item.h enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, · line 181

Quoted 7 lines
include/linux/vm_event_item.h +4 -0
@@ -175,6 +175,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
                KSTACK_REST,
 #endif
 #endif /* CONFIG_DEBUG_STACK_USAGE */
+#ifdef CONFIG_SWAP
+               NRSWPIN,
+               NRSWPOUT,
+#endif /* CONFIG_SWAP */

Same question as Baoquan regarding merging this with the other CONFIG_SWAP section, but otherwise:

(Was also going to suggest documentation of these stats, but then I can't find any documentation for these vmstats at all. Oh well.)