[PATCH v5 05/19] mm, swap: widen swap_info_struct max/pages to unsigned long

[Baoquan He]

From: Baoquan He <hebaoquan@xxxxxxxxxx>

si->max and si->pages are unsigned int. With 4 KiB pages, this limits
an xswap device to 16 TB. xswap may need a larger address space, so
change both fields to unsigned long.

Several places still use unsigned int for offsets and indexes. Widen
them as well:

- the return value of cluster_offset() and the cluster scan helpers;
- the allocation offsets in cluster_alloc_swap_entry() and
  swap_alloc_fast();
- the indexes in find_next_to_unuse() and try_to_unuse().

Also change the related print formats from %u to %lu.

A real swap device is still limited by swap_header.info.last_page,
which is __u32. So this only widens the xswap address space. The old
overflow clamp in read_swap_header() is no longer needed; the header
check still limits real devices.

count_swap_pages() returns unsigned int and is only used by
hibernation. Hibernation never selects an xswap device. If that ever
changes, WARN and return 0 instead of silently truncating the value.

Signed-off-by: Baoquan He <hebaoquan@xxxxxxxxxx>
---
 include/linux/swap.h |  4 +--
 mm/swapfile.c        | 59 +++++++++++++++++++++++---------------------
 2 files changed, 33 insertions(+), 30 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 382a578140b5..569989856c25 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -240,7 +240,7 @@ struct swap_info_struct {
 	signed short	prio;		/* swap priority of this type */
 	struct plist_node list;		/* entry in swap_active_head */
 	signed char	type;		/* strange name for an index */
-	unsigned int	max;		/* size of this swap device */
+	unsigned long	max;		/* size of this swap device */
 	struct swap_cluster_info *cluster_info; /* array, one entry per cluster */
 #ifdef CONFIG_XSWAP
 	struct vm_struct	*cluster_vm;	/* VM_SPARSE area for cluster_info */
@@ -254,7 +254,7 @@ struct swap_info_struct {
 					/* list of cluster that contains at least one free slot */
 	struct list_head frag_clusters[SWAP_NR_ORDERS];
 					/* list of cluster that are fragmented or contented */
-	unsigned int pages;		/* total of usable pages of swap */
+	unsigned long pages;		/* total of usable pages of swap */
 	atomic_long_t inuse_pages;	/* number of those currently in use */
 	struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */
 	spinlock_t global_cluster_lock;	/* Serialize usage of global cluster */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 00c7b398bafe..83aaf00b75d3 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -429,10 +429,10 @@ static inline unsigned int cluster_index(struct swap_info_struct *si,
 	return ci - si->cluster_info;
 }
 
-static inline unsigned int cluster_offset(struct swap_info_struct *si,
-					  struct swap_cluster_info *ci)
+static inline unsigned long cluster_offset(struct swap_info_struct *si,
+					   struct swap_cluster_info *ci)
 {
-	return cluster_index(si, ci) * SWAPFILE_CLUSTER;
+	return (unsigned long)cluster_index(si, ci) * SWAPFILE_CLUSTER;
 }
 
 static void swap_cluster_free_table_folio_rcu_cb(struct rcu_head *head)
@@ -836,7 +836,7 @@ static int swap_cluster_setup_bad_slot(struct swap_info_struct *si,
 
 	/* si->max may got shrunk by swap swap_activate() */
 	if (offset >= si->max && !mask) {
-		pr_debug("Ignoring bad slot %u (max: %u)\n", offset, si->max);
+		pr_debug("Ignoring bad slot %u (max: %lu)\n", offset, si->max);
 		return 0;
 	}
 	/*
@@ -1002,11 +1002,12 @@ static bool __swap_cluster_alloc_entries(struct swap_info_struct *si,
 }
 
 /* Try use a new cluster for current CPU and allocate from it. */
-static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
-					    struct swap_cluster_info *ci,
-					    struct folio *folio, unsigned long offset)
+static unsigned long alloc_swap_scan_cluster(struct swap_info_struct *si,
+					     struct swap_cluster_info *ci,
+					     struct folio *folio,
+					     unsigned long offset)
 {
-	unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
+	unsigned long next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
 	unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER);
 	unsigned int order = likely(folio) ? folio_order(folio) : 0;
 	unsigned long end = start + SWAPFILE_CLUSTER;
@@ -1053,12 +1054,12 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
 	return found;
 }
 
-static unsigned int alloc_swap_scan_list(struct swap_info_struct *si,
-					 struct list_head *list,
-					 struct folio *folio,
-					 bool scan_all)
+static unsigned long alloc_swap_scan_list(struct swap_info_struct *si,
+					  struct list_head *list,
+					  struct folio *folio,
+					  bool scan_all)
 {
-	unsigned int found = SWAP_ENTRY_INVALID;
+	unsigned long found = SWAP_ENTRY_INVALID;
 
 	do {
 		struct swap_cluster_info *ci = isolate_lock_cluster(si, list);
@@ -1141,7 +1142,7 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si,
 {
 	struct swap_cluster_info *ci;
 	unsigned int order = likely(folio) ? folio_order(folio) : 0;
-	unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
+	unsigned long offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
 
 	/*
 	 * Swapfile is not block device so unable
@@ -1418,7 +1419,7 @@ static bool swap_alloc_fast(struct folio *folio)
 	unsigned int order = folio_order(folio);
 	struct swap_cluster_info *ci;
 	struct swap_info_struct *si;
-	unsigned int offset;
+	unsigned long offset;
 
 	/*
 	 * Once allocated, swap_info_struct will never be completely freed,
@@ -2509,9 +2510,15 @@ unsigned int count_swap_pages(int type, int free)
 
 		spin_lock(&sis->lock);
 		if (sis->flags & SWP_WRITEOK) {
-			n = sis->pages;
-			if (free)
-				n -= swap_usage_in_pages(sis);
+			/* Hibernation only; it never selects an xswap device. */
+			if (unlikely(sis->flags & SWP_XSWAP)) {
+				WARN_ON_ONCE(1);
+				n = 0;
+			} else {
+				n = sis->pages;
+				if (free)
+					n -= swap_usage_in_pages(sis);
+			}
 		}
 		spin_unlock(&sis->lock);
 	}
@@ -2832,8 +2839,8 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type)
  * Return 0 if there are no inuse entries after prev till end of
  * the map.
  */
-static unsigned int find_next_to_unuse(struct swap_info_struct *si,
-					unsigned int prev)
+static unsigned long find_next_to_unuse(struct swap_info_struct *si,
+					unsigned long prev)
 {
 	struct swap_cluster_info *ci;
 	unsigned long i, cluster_end, end;
@@ -2903,7 +2910,7 @@ static int try_to_unuse(unsigned int type)
 	struct swap_info_struct *si = swap_info[type];
 	struct folio *folio;
 	swp_entry_t entry;
-	unsigned int i;
+	unsigned long i;
 
 	if (!swap_usage_in_pages(si))
 		goto success;
@@ -3722,12 +3729,8 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
 		pr_warn("Truncating oversized swap area, only using %luk out of %luk\n",
 			K(maxpages), K(last_page));
 	}
-	if (maxpages > last_page) {
+	if (maxpages > last_page)
 		maxpages = last_page + 1;
-		/* p->max is an unsigned int: don't overflow it */
-		if ((unsigned int)maxpages == 0)
-			maxpages = UINT_MAX;
-	}
 
 	if (!maxpages)
 		return 0;
@@ -4209,7 +4212,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 	if (si->pages != si->max - 1) {
-		pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max);
+		pr_err("swap:%lu != (max:%lu - 1)\n", si->pages, si->max);
 		error = -EINVAL;
 		goto bad_swap_unlock_inode;
 	}
@@ -4300,7 +4303,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	/* Sets SWP_WRITEOK, resurrect the percpu ref, expose the swap device */
 	enable_swap_info(si);
 
-	pr_info("Adding %uk swap on %s.  Priority:%d extents:%d across:%lluk %s%s%s%s\n",
+	pr_info("Adding %luk swap on %s.  Priority:%d extents:%d across:%lluk %s%s%s%s\n",
 		K(si->pages), name->name, si->prio, nr_extents,
 		K((unsigned long long)span),
 		(si->flags & SWP_SOLIDSTATE) ? "SS" : "",
-- 
2.54.0