linux-kernel - [RFC PATCH 02/14] mm: swap: add an abstract API for locking out swapoff

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250407234223.1059191-3-nphamcs@gmail.com>
Date: Mon,  7 Apr 2025 16:42:03 -0700
From: Nhat Pham <nphamcs@...il.com>
To: linux-mm@...ck.org
Cc: akpm@...ux-foundation.org,
	hannes@...xchg.org,
	hughd@...gle.com,
	yosry.ahmed@...ux.dev,
	mhocko@...nel.org,
	roman.gushchin@...ux.dev,
	shakeel.butt@...ux.dev,
	muchun.song@...ux.dev,
	len.brown@...el.com,
	chengming.zhou@...ux.dev,
	kasong@...cent.com,
	chrisl@...nel.org,
	huang.ying.caritas@...il.com,
	ryan.roberts@....com,
	viro@...iv.linux.org.uk,
	baohua@...nel.org,
	osalvador@...e.de,
	lorenzo.stoakes@...cle.com,
	christophe.leroy@...roup.eu,
	pavel@...nel.org,
	kernel-team@...a.com,
	linux-kernel@...r.kernel.org,
	cgroups@...r.kernel.org,
	linux-pm@...r.kernel.org
Subject: [RFC PATCH 02/14] mm: swap: add an abstract API for locking out swapoff

Currently, we get a reference to the backing swap device in order to
lock out swapoff and ensure its validity. This is no longer sufficient
and/or doable when the swap entries are decoupled from their backing
stores - a swap entry might not have any backing swap device at all.

In preparation for this decoupling work, abstract away the swapoff
locking out behavior into a generic API (whose implementation will
eventually differ between the old and the new swap implementation).

Signed-off-by: Nhat Pham <nphamcs@...il.com>
---
 include/linux/swap.h | 12 ++++++++++++
 mm/memory.c          | 13 +++++++------
 mm/shmem.c           |  7 +++----
 mm/swap_state.c      | 10 ++++------
 4 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index b13b72645db3..e479fd31c6d6 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -706,5 +706,17 @@ static inline bool mem_cgroup_swap_full(struct folio *folio)
 }
 #endif
 
+static inline bool trylock_swapoff(swp_entry_t entry,
+				struct swap_info_struct **si)
+{
+	return get_swap_device(entry);
+}
+
+static inline void unlock_swapoff(swp_entry_t entry,
+				struct swap_info_struct *si)
+{
+	put_swap_device(si);
+}
+
 #endif /* __KERNEL__*/
 #endif /* _LINUX_SWAP_H */
diff --git a/mm/memory.c b/mm/memory.c
index fb7b8dc75167..e92914df5ca7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4305,6 +4305,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
 	bool need_clear_cache = false;
+	bool swapoff_locked = false;
 	bool exclusive = false;
 	swp_entry_t entry;
 	pte_t pte;
@@ -4365,8 +4366,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	}
 
 	/* Prevent swapoff from happening to us. */
-	si = get_swap_device(entry);
-	if (unlikely(!si))
+	swapoff_locked = trylock_swapoff(entry, &si);
+	if (unlikely(!swapoff_locked))
 		goto out;
 
 	folio = swap_cache_get_folio(entry, vma, vmf->address);
@@ -4713,8 +4714,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		if (waitqueue_active(&swapcache_wq))
 			wake_up(&swapcache_wq);
 	}
-	if (si)
-		put_swap_device(si);
+	if (swapoff_locked)
+		unlock_swapoff(entry, si);
 	return ret;
 out_nomap:
 	if (vmf->pte)
@@ -4732,8 +4733,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		if (waitqueue_active(&swapcache_wq))
 			wake_up(&swapcache_wq);
 	}
-	if (si)
-		put_swap_device(si);
+	if (swapoff_locked)
+		unlock_swapoff(entry, si);
 	return ret;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 1ede0800e846..8ef72dcc592e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2262,8 +2262,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	if (is_poisoned_swp_entry(swap))
 		return -EIO;
 
-	si = get_swap_device(swap);
-	if (!si) {
+	if (!trylock_swapoff(swap, &si)) {
 		if (!shmem_confirm_swap(mapping, index, swap))
 			return -EEXIST;
 		else
@@ -2411,7 +2410,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	}
 	folio_mark_dirty(folio);
 	swap_free_nr(swap, nr_pages);
-	put_swap_device(si);
+	unlock_swapoff(swap, si);
 
 	*foliop = folio;
 	return 0;
@@ -2428,7 +2427,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 		folio_unlock(folio);
 		folio_put(folio);
 	}
-	put_swap_device(si);
+	unlock_swapoff(swap, si);
 
 	return error;
 }
diff --git a/mm/swap_state.c b/mm/swap_state.c
index ca42b2be64d9..81f69b2df550 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -419,12 +419,11 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping,
 	if (non_swap_entry(swp))
 		return ERR_PTR(-ENOENT);
 	/* Prevent swapoff from happening to us */
-	si = get_swap_device(swp);
-	if (!si)
+	if (!trylock_swapoff(swp, &si))
 		return ERR_PTR(-ENOENT);
 	index = swap_cache_index(swp);
 	folio = filemap_get_folio(swap_address_space(swp), index);
-	put_swap_device(si);
+	unlock_swapoff(swp, si);
 	return folio;
 }
 
@@ -439,8 +438,7 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	void *shadow = NULL;
 
 	*new_page_allocated = false;
-	si = get_swap_device(entry);
-	if (!si)
+	if (!trylock_swapoff(entry, &si))
 		return NULL;
 
 	for (;;) {
@@ -538,7 +536,7 @@ struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	put_swap_folio(new_folio, entry);
 	folio_unlock(new_folio);
 put_and_return:
-	put_swap_device(si);
+	unlock_swapoff(entry, si);
 	if (!(*new_page_allocated) && new_folio)
 		folio_put(new_folio);
 	return result;
-- 
2.47.1