[RFC PATCH v3 06/18] mm/swap: serialize swap publication before removing swapon mutex

[Lian Wang <lianux.mm@gmail.com>]

From: Kairui Song <kasong@tencent.com>

Move publication of swap_file, resurrection of the device reference and
the writable transition into one swapon_rwsem writer section. Split out
a writer-held enable helper so initial publication can share this
section, while failed swapoff can use the locking wrapper.

With file publication and teardown serialized by the writer, remove
swapon_mutex and use a topology reader across /proc/swaps iteration.
Keep the SWP_USED filter when advancing the swap_info array.

The publication boundary excludes proc readers from partially published
state and gives the lockless live-reference users initialized device
metadata before the device becomes an allocation candidate.

Signed-off-by: Kairui Song <kasong@tencent.com>
Co-developed-by: Lian Wang <lianux.mm@gmail.com>
Signed-off-by: Lian Wang <lianux.mm@gmail.com>
---
 mm/swapfile.c | 39 +++++++++++++++++++--------------------
 1 file changed, 19 insertions(+), 20 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4ffde6827d44..4c10e4a2d9b3 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -140,9 +140,6 @@ static inline struct swap_info_struct *__swap_iter(int *i, unsigned long flag)
 
 static struct kmem_cache *swap_table_cachep;
 
-/* Protects si->swap_file for /proc/swaps usage */
-static DEFINE_MUTEX(swapon_mutex);
-
 static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait);
 /* Activity counter to indicate that a swapon or swapoff has occurred */
 static atomic_t proc_poll_event = ATOMIC_INIT(0);
@@ -3097,9 +3094,9 @@ static int setup_swap_extents(struct swap_info_struct *sis,
  * Mark a fully initialized swap device writable and expose it to the
  * allocator. The caller must have resurrected its percpu ref first.
  */
-static void swap_device_enable(struct swap_info_struct *si)
+static void __swap_device_enable(struct swap_info_struct *si)
 {
-	percpu_down_write(&swapon_rwsem);
+	lockdep_assert_held_write(&swapon_rwsem);
 	spin_lock(&swap_avail_lock);
 	si->flags |= SWP_WRITEOK;
 	spin_unlock(&swap_avail_lock);
@@ -3107,11 +3104,16 @@ static void swap_device_enable(struct swap_info_struct *si)
 	atomic_long_add(si->pages, &nr_swap_pages);
 	total_swap_pages += si->pages;
 	plist_add(&si->list, &swap_active_head);
-	percpu_up_write(&swapon_rwsem);
-
 	add_to_avail_list(si);
 }
 
+static void swap_device_enable(struct swap_info_struct *si)
+{
+	percpu_down_write(&swapon_rwsem);
+	__swap_device_enable(si);
+	percpu_up_write(&swapon_rwsem);
+}
+
 static int swap_device_disable(struct address_space *mapping,
 			       struct swap_info_struct **swap_info)
 {
@@ -3275,7 +3277,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	if (!(p->flags & SWP_SOLIDSTATE))
 		atomic_dec(&nr_rotate_swap);
 
-	mutex_lock(&swapon_mutex);
 	percpu_down_write(&swapon_rwsem);
 	spin_lock(&p->lock);
 	drain_mmlist();
@@ -3290,7 +3291,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	percpu_up_write(&swapon_rwsem);
 	arch_swap_invalidate_area(p->type);
 	zswap_swapoff(p->type);
-	mutex_unlock(&swapon_mutex);
 	kfree(p->global_cluster);
 	p->global_cluster = NULL;
 	free_swap_cluster_info(cluster_info, maxpages);
@@ -3336,20 +3336,18 @@ static __poll_t swaps_poll(struct file *file, poll_table *wait)
 	return EPOLLIN | EPOLLRDNORM;
 }
 
-/* iterator */
 static void *swap_start(struct seq_file *swap, loff_t *pos)
 {
 	struct swap_info_struct *si;
-	int type;
 	loff_t l = *pos;
 
-	mutex_lock(&swapon_mutex);
+	percpu_down_read(&swapon_rwsem);
 
 	if (!l)
 		return SEQ_START_TOKEN;
 
-	for (type = 0; (si = swap_type_to_info(type)); type++) {
-		if (!(si->swap_file))
+	for_each_swap(si) {
+		if (!si->swap_file)
 			continue;
 		if (!--l)
 			return si;
@@ -3370,7 +3368,7 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
 
 	++(*pos);
 	for (; (si = swap_type_to_info(type)); type++) {
-		if (!(si->swap_file))
+		if (!(si->flags & SWP_USED) || !(si->swap_file))
 			continue;
 		return si;
 	}
@@ -3380,7 +3378,7 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
 
 static void swap_stop(struct seq_file *swap, void *v)
 {
-	mutex_unlock(&swapon_mutex);
+	percpu_up_read(&swapon_rwsem);
 }
 
 static int swap_show(struct seq_file *swap, void *v)
@@ -3893,7 +3891,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto free_swap_zswap;
 	}
 
-	mutex_lock(&swapon_mutex);
 	prio = DEF_SWAP_PRIO;
 	if (swap_flags & SWAP_FLAG_PREFER)
 		prio = swap_flags & SWAP_FLAG_PRIO_MASK;
@@ -3905,11 +3902,14 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	si->prio = prio;
 	si->list.prio = -si->prio;
 	si->avail_list.prio = -si->prio;
+	/* Publish the file, live reference and writable state together. */
+	percpu_down_write(&swapon_rwsem);
 	si->swap_file = swap_file;
 
-	/* Sets SWP_WRITEOK, resurrect the percpu ref, expose the swap device */
+	/* Make the reference live before exposing the writable device. */
 	percpu_ref_resurrect(&si->users);
-	swap_device_enable(si);
+	__swap_device_enable(si);
+	percpu_up_write(&swapon_rwsem);
 
 	pr_info("Adding %uk swap on %s.  Priority:%d extents:%d across:%lluk %s%s%s%s\n",
 		K(si->pages), name->name, si->prio, nr_extents,
@@ -3919,7 +3919,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		(si->flags & SWP_AREA_DISCARD) ? "s" : "",
 		(si->flags & SWP_PAGE_DISCARD) ? "c" : "");
 
-	mutex_unlock(&swapon_mutex);
 	atomic_inc(&proc_poll_event);
 	wake_up_interruptible(&proc_poll_wait);