[RFC PATCH 1/3] mm/mincore, swap: consolidate swap cache checking for mincore

Kairui Song posted 3 patches 1 month, 4 weeks ago
[RFC PATCH 1/3] mm/mincore, swap: consolidate swap cache checking for mincore
Posted by Kairui Song 1 month, 4 weeks ago
From: Kairui Song <kasong@tencent.com>

The filemap_get_incore_folio (previously find_get_incore_page) helper
was introduced by commit 61ef18655704 ("mm: factor find_get_incore_page
out of mincore_page") to be used by later commit f5df8635c5a3 ("mm: use
find_get_incore_page in memcontrol"), so memory cgroup charge move code
can be simplified.

But commit 6b611388b626 ("memcg-v1: remove charge move code") removed
that user completely, it's only used by mincore now.

So this commit basically reverts commit 61ef18655704 ("mm: factor
find_get_incore_page out of mincore_page"). Move it back to mincore side
to simplify the code.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/mincore.c    | 29 +++++++++++++++++++++++++++--
 mm/swap.h       | 10 ----------
 mm/swap_state.c | 38 --------------------------------------
 3 files changed, 27 insertions(+), 50 deletions(-)

diff --git a/mm/mincore.c b/mm/mincore.c
index 10dabefc3acc..f0d3c9419e58 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -64,8 +64,33 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-	folio = filemap_get_incore_folio(mapping, index);
-	if (!IS_ERR(folio)) {
+	if (IS_ENABLED(CONFIG_SWAP) && shmem_mapping(mapping)) {
+		folio = filemap_get_entry(mapping, index);
+		/*
+		 * shmem/tmpfs may return swap: account for swapcache
+		 * page too.
+		 */
+		if (xa_is_value(folio)) {
+			struct swap_info_struct *si;
+			swp_entry_t swp = radix_to_swp_entry(folio);
+			/* There might be swapin error entries in shmem mapping. */
+			if (non_swap_entry(swp))
+				return 0;
+			/* Prevent swap device to being swapoff under us */
+			si = get_swap_device(swp);
+			if (si) {
+				folio = filemap_get_folio(swap_address_space(swp),
+							  swap_cache_index(swp));
+				put_swap_device(si);
+			} else {
+				return 0;
+			}
+		}
+	} else {
+		folio = filemap_get_folio(mapping, index);
+	}
+
+	if (folio) {
 		present = folio_test_uptodate(folio);
 		folio_put(folio);
 	}
diff --git a/mm/swap.h b/mm/swap.h
index 911ad5ff0f89..1ae44d4193b1 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -64,9 +64,6 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin,
 void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr);
 struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr);
-struct folio *filemap_get_incore_folio(struct address_space *mapping,
-		pgoff_t index);
-
 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);
@@ -178,13 +175,6 @@ static inline struct folio *swap_cache_get_folio(swp_entry_t entry,
 	return NULL;
 }
 
-static inline
-struct folio *filemap_get_incore_folio(struct address_space *mapping,
-		pgoff_t index)
-{
-	return filemap_get_folio(mapping, index);
-}
-
 static inline void *get_shadow_from_swap_cache(swp_entry_t entry)
 {
 	return NULL;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index c354435a0923..99513b74b5d8 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -323,44 +323,6 @@ struct folio *swap_cache_get_folio(swp_entry_t entry,
 	return folio;
 }
 
-/**
- * filemap_get_incore_folio - Find and get a folio from the page or swap caches.
- * @mapping: The address_space to search.
- * @index: The page cache index.
- *
- * This differs from filemap_get_folio() in that it will also look for the
- * folio in the swap cache.
- *
- * Return: The found folio or %NULL.
- */
-struct folio *filemap_get_incore_folio(struct address_space *mapping,
-		pgoff_t index)
-{
-	swp_entry_t swp;
-	struct swap_info_struct *si;
-	struct folio *folio = filemap_get_entry(mapping, index);
-
-	if (!folio)
-		return ERR_PTR(-ENOENT);
-	if (!xa_is_value(folio))
-		return folio;
-	if (!shmem_mapping(mapping))
-		return ERR_PTR(-ENOENT);
-
-	swp = radix_to_swp_entry(folio);
-	/* There might be swapin error entries in shmem mapping. */
-	if (non_swap_entry(swp))
-		return ERR_PTR(-ENOENT);
-	/* Prevent swapoff from happening to us */
-	si = get_swap_device(swp);
-	if (!si)
-		return ERR_PTR(-ENOENT);
-	index = swap_cache_index(swp);
-	folio = filemap_get_folio(swap_address_space(swp), index);
-	put_swap_device(si);
-	return folio;
-}
-
 struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
 		bool skip_if_exists)
-- 
2.50.1
Re: [RFC PATCH 1/3] mm/mincore, swap: consolidate swap cache checking for mincore
Posted by Nhat Pham 1 month, 4 weeks ago
On Thu, Aug 7, 2025 at 8:27 AM Kairui Song <ryncsn@gmail.com> wrote:
>
> From: Kairui Song <kasong@tencent.com>
>
> The filemap_get_incore_folio (previously find_get_incore_page) helper
> was introduced by commit 61ef18655704 ("mm: factor find_get_incore_page
> out of mincore_page") to be used by later commit f5df8635c5a3 ("mm: use
> find_get_incore_page in memcontrol"), so memory cgroup charge move code
> can be simplified.
>
> But commit 6b611388b626 ("memcg-v1: remove charge move code") removed
> that user completely, it's only used by mincore now.
>
> So this commit basically reverts commit 61ef18655704 ("mm: factor
> find_get_incore_page out of mincore_page"). Move it back to mincore side
> to simplify the code.
>
> Signed-off-by: Kairui Song <kasong@tencent.com>

Seems reasonable to me for the most part - just a couple of questions below.

> ---
>  mm/mincore.c    | 29 +++++++++++++++++++++++++++--
>  mm/swap.h       | 10 ----------
>  mm/swap_state.c | 38 --------------------------------------
>  3 files changed, 27 insertions(+), 50 deletions(-)
>
> diff --git a/mm/mincore.c b/mm/mincore.c
> index 10dabefc3acc..f0d3c9419e58 100644
> --- a/mm/mincore.c
> +++ b/mm/mincore.c
> @@ -64,8 +64,33 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
>          * any other file mapping (ie. marked !present and faulted in with
>          * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
>          */
> -       folio = filemap_get_incore_folio(mapping, index);
> -       if (!IS_ERR(folio)) {
> +       if (IS_ENABLED(CONFIG_SWAP) && shmem_mapping(mapping)) {

Do we need CONFIG_SWAP check here? I suppose if !CONFIG_SWAP we'll
never end up with an ordinary swap entry stored here right?

Saves a couple of cycles, I suppose. No strong opinions.

> +               folio = filemap_get_entry(mapping, index);
> +               /*
> +                * shmem/tmpfs may return swap: account for swapcache
> +                * page too.
> +                */
> +               if (xa_is_value(folio)) {
> +                       struct swap_info_struct *si;
> +                       swp_entry_t swp = radix_to_swp_entry(folio);
> +                       /* There might be swapin error entries in shmem mapping. */
> +                       if (non_swap_entry(swp))
> +                               return 0;
> +                       /* Prevent swap device to being swapoff under us */
> +                       si = get_swap_device(swp);
> +                       if (si) {
> +                               folio = filemap_get_folio(swap_address_space(swp),
> +                                                         swap_cache_index(swp));
> +                               put_swap_device(si);
> +                       } else {
> +                               return 0;
> +                       }
> +               }
> +       } else {
> +               folio = filemap_get_folio(mapping, index);
> +       }
> +
> +       if (folio) {

Should this check be "if (!IS_ERR(folio))"? Seems like that's how we
inspect the output of filemap_get_folio() in other locations (for e.g,
in filemap_fault()).

>                 present = folio_test_uptodate(folio);
>                 folio_put(folio);
>         }
Re: [RFC PATCH 1/3] mm/mincore, swap: consolidate swap cache checking for mincore
Posted by Kairui Song 1 month, 4 weeks ago
On Fri, Aug 8, 2025 at 2:07 AM Nhat Pham <nphamcs@gmail.com> wrote:
>
> On Thu, Aug 7, 2025 at 8:27 AM Kairui Song <ryncsn@gmail.com> wrote:
> >
> > From: Kairui Song <kasong@tencent.com>
> >
> > The filemap_get_incore_folio (previously find_get_incore_page) helper
> > was introduced by commit 61ef18655704 ("mm: factor find_get_incore_page
> > out of mincore_page") to be used by later commit f5df8635c5a3 ("mm: use
> > find_get_incore_page in memcontrol"), so memory cgroup charge move code
> > can be simplified.
> >
> > But commit 6b611388b626 ("memcg-v1: remove charge move code") removed
> > that user completely, it's only used by mincore now.
> >
> > So this commit basically reverts commit 61ef18655704 ("mm: factor
> > find_get_incore_page out of mincore_page"). Move it back to mincore side
> > to simplify the code.
> >
> > Signed-off-by: Kairui Song <kasong@tencent.com>
>
> Seems reasonable to me for the most part - just a couple of questions below.
>
> > ---
> >  mm/mincore.c    | 29 +++++++++++++++++++++++++++--
> >  mm/swap.h       | 10 ----------
> >  mm/swap_state.c | 38 --------------------------------------
> >  3 files changed, 27 insertions(+), 50 deletions(-)
> >
> > diff --git a/mm/mincore.c b/mm/mincore.c
> > index 10dabefc3acc..f0d3c9419e58 100644
> > --- a/mm/mincore.c
> > +++ b/mm/mincore.c
> > @@ -64,8 +64,33 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
> >          * any other file mapping (ie. marked !present and faulted in with
> >          * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
> >          */
> > -       folio = filemap_get_incore_folio(mapping, index);
> > -       if (!IS_ERR(folio)) {
> > +       if (IS_ENABLED(CONFIG_SWAP) && shmem_mapping(mapping)) {
>
> Do we need CONFIG_SWAP check here? I suppose if !CONFIG_SWAP we'll
> never end up with an ordinary swap entry stored here right?

Yes, and in the next patch I'd like to introduce a WARN_ON if we see
swap entries with !CONFIG_SWAP. That means the memory is corrupted.

>
> Saves a couple of cycles, I suppose. No strong opinions.

Before 61ef18655704 it used a `#ifdef CONFIG_SWAP`, I used
IS_ENABLED(CONFIG_SWAP) here, same thing, the compiler will optimize
out the unused branch. Just with fewer lines of code and I personally
think this looks prettier.

>
> > +               folio = filemap_get_entry(mapping, index);
> > +               /*
> > +                * shmem/tmpfs may return swap: account for swapcache
> > +                * page too.
> > +                */
> > +               if (xa_is_value(folio)) {
> > +                       struct swap_info_struct *si;
> > +                       swp_entry_t swp = radix_to_swp_entry(folio);
> > +                       /* There might be swapin error entries in shmem mapping. */
> > +                       if (non_swap_entry(swp))
> > +                               return 0;
> > +                       /* Prevent swap device to being swapoff under us */
> > +                       si = get_swap_device(swp);
> > +                       if (si) {
> > +                               folio = filemap_get_folio(swap_address_space(swp),
> > +                                                         swap_cache_index(swp));
> > +                               put_swap_device(si);
> > +                       } else {
> > +                               return 0;
> > +                       }
> > +               }
> > +       } else {
> > +               folio = filemap_get_folio(mapping, index);
> > +       }
> > +
> > +       if (folio) {
>
> Should this check be "if (!IS_ERR(folio))"? Seems like that's how we
> inspect the output of filemap_get_folio() in other locations (for e.g,
> in filemap_fault()).

Yeah you are right, actuall should be IS_ERR_OR_NULL here as it uses
both filemap_get_entry and filemap_get_folio.
I wanted to change to always use filemap_get_entry in the next patch
for better performance, but somehow forgot it...
Will fix it.

>
> >                 present = folio_test_uptodate(folio);
> >                 folio_put(folio);
> >         }
>