[RFC PATCH v2 7/7] mm, swap: widen swap_info_struct max/pages to unsigned long

[Nhat Pham <nphamcs@gmail.com>]

Widen swap_info_struct->max and ->pages from unsigned int to
unsigned long so the vswap device can exceed the current 16 TB
cap (ALIGN_DOWN(UINT_MAX, SWAPFILE_CLUSTER) pages).

Physical swap is unaffected; backing files/bdevs continue to bound
it independently of the field width.

The new vswap cap is the cluster_info_pool xarray's allocator
limit. XA_FLAGS_ALLOC stores allocated IDs in u32, so
max_pages = UINT_MAX * SWAPFILE_CLUSTER (~8 PB at the typical
SWAPFILE_CLUSTER=512 layout).

Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
 include/linux/swap.h |  4 +--
 mm/swapfile.c        | 62 +++++++++++++++++++++++---------------------
 2 files changed, 34 insertions(+), 32 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2d6bc4cb442f..b8fc2aa4539f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -253,7 +253,7 @@ 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; /* cluster info. Only for SSD */
 	struct list_head free_clusters; /* free clusters list */
 	struct list_head full_clusters; /* full clusters list */
@@ -261,7 +261,7 @@ 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 0d48240de345..b03a81993a04 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -451,10 +451,10 @@ 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)
@@ -876,7 +876,7 @@ 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;
 	}
 	/*
@@ -1152,12 +1152,12 @@ 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 = folio ? folio_order(folio) : 0;
 	unsigned long end = start + SWAPFILE_CLUSTER;
@@ -1235,12 +1235,12 @@ 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);
@@ -1257,8 +1257,8 @@ static unsigned int alloc_swap_scan_list(struct swap_info_struct *si,
 	return found;
 }
 
-static unsigned int alloc_swap_scan_dynamic(struct swap_info_struct *si,
-					    struct folio *folio)
+static unsigned long alloc_swap_scan_dynamic(struct swap_info_struct *si,
+					     struct folio *folio)
 {
 	struct swap_cluster_info_dynamic *ci_dyn;
 	struct swap_cluster_info *ci;
@@ -1373,7 +1373,7 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si,
 {
 	unsigned int order = folio ? folio_order(folio) : 0;
 	struct swap_cluster_info *ci;
-	unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
+	unsigned long offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
 
 	/*
 	 * File-based swap can't do large contiguous IO. vswap has no IO
@@ -3492,10 +3492,10 @@ 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)
 {
-	unsigned int i;
+	unsigned long i;
 	unsigned long swp_tb;
 
 	/*
@@ -3533,7 +3533,8 @@ static int try_to_unuse(unsigned int type)
 	struct folio *folio;
 	swp_entry_t entry, vswap_entry;
 	unsigned long swp_tb;
-	unsigned int i, j, ci_off;
+	unsigned long i;
+	unsigned int j, ci_off;
 
 	if (!swap_usage_in_pages(si))
 		goto success;
@@ -3970,7 +3971,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct file *swap_file, *victim;
 	struct address_space *mapping;
 	struct inode *inode;
-	unsigned int maxpages;
+	unsigned long maxpages;
 	int err, found = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -4404,12 +4405,8 @@ 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;
@@ -4640,7 +4637,7 @@ 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;
 	}
@@ -4728,7 +4725,7 @@ 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" : "",
@@ -4900,8 +4897,13 @@ static int __init vswap_init(void)
 		return 0;
 	}
 
+	/*
+	 * Cap at the cluster_info_pool xarray's allocator limit
+	 * (XA_FLAGS_ALLOC stores IDs in u32, tops out at UINT_MAX).
+	 */
 	maxpages = min(swapfile_maximum_size,
-		       ALIGN_DOWN((unsigned long)UINT_MAX, SWAPFILE_CLUSTER));
+		       ALIGN_DOWN((unsigned long)UINT_MAX * SWAPFILE_CLUSTER,
+				  SWAPFILE_CLUSTER));
 	si->flags |= SWP_VSWAP | SWP_SOLIDSTATE | SWP_WRITEOK;
 	si->bdev = NULL;
 	si->max = maxpages;
-- 
2.53.0-Meta