swp_swap_info is the most commonly used helper for retrieving swap info.
It has an internal check that may lead to a NULL return value, but almost
none of its caller checks the return value, making the internal check
pointless. In fact, most of these callers already ensured the entry is
valid and never expect a NULL value.
Tidy this up and improve the function names. If the caller can make sure
the swap entry/type is valid and the device is pinned, use the new
introduced __swap_entry_to_info/__swap_type_to_info instead. They have
more debug sanity checks and lower overhead as they are inlined.
Callers that may expect a NULL value should use
swap_entry_to_info/swap_type_to_info instead.
No feature change. The rearranged codes should have had no effect, or
they should have been hitting NULL de-ref bugs already. Only some new
sanity checks are added so potential issues may show up in debug build.
The new helpers will be frequently used with swap table later when working
with swap cache folios. A locked swap cache folio ensures the entries are
valid and stable so these helpers are very helpful.
Link: https://lkml.kernel.org/r/20250910160833.3464-8-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Acked-by: Chris Li <chrisl@kernel.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
extern int __swap_count(swp_entry_t entry);
extern bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry);
extern int swp_swapcount(swp_entry_t entry);
-struct swap_info_struct *swp_swap_info(swp_entry_t entry);
struct backing_dev_info;
extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
extern void exit_swap_address_space(unsigned int type);
}
#else /* CONFIG_SWAP */
-static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
-{
- return NULL;
-}
-
static inline struct swap_info_struct *get_swap_device(swp_entry_t entry)
{
return NULL;
static void swap_zeromap_folio_set(struct folio *folio)
{
struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio);
- struct swap_info_struct *sis = swp_swap_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
int nr_pages = folio_nr_pages(folio);
swp_entry_t entry;
unsigned int i;
static void swap_zeromap_folio_clear(struct folio *folio)
{
- struct swap_info_struct *sis = swp_swap_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
swp_entry_t entry;
unsigned int i;
static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
{
struct swap_iocb *sio = swap_plug ? *swap_plug : NULL;
- struct swap_info_struct *sis = swp_swap_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
struct file *swap_file = sis->swap_file;
loff_t pos = swap_dev_pos(folio->swap);
void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
{
- struct swap_info_struct *sis = swp_swap_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
/*
static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
{
- struct swap_info_struct *sis = swp_swap_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
struct swap_iocb *sio = NULL;
loff_t pos = swap_dev_pos(folio->swap);
void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
{
- struct swap_info_struct *sis = swp_swap_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
bool synchronous = sis->flags & SWP_SYNCHRONOUS_IO;
bool workingset = folio_test_workingset(folio);
unsigned long pflags;
#define swap_entry_order(order) 0
#endif
+extern struct swap_info_struct *swap_info[];
+
/*
* We use this to track usage of a cluster. A cluster is a block of swap disk
* space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
#include <linux/swapops.h> /* for swp_offset */
#include <linux/blk_types.h> /* for bio_end_io_t */
-static inline struct swap_cluster_info *swp_offset_cluster(
+/*
+ * Callers of all helpers below must ensure the entry, type, or offset is
+ * valid, and protect the swap device with reference count or locks.
+ */
+static inline struct swap_info_struct *__swap_type_to_info(int type)
+{
+ struct swap_info_struct *si;
+
+ si = READ_ONCE(swap_info[type]); /* rcu_dereference() */
+ VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */
+ return si;
+}
+
+static inline struct swap_info_struct *__swap_entry_to_info(swp_entry_t entry)
+{
+ return __swap_type_to_info(swp_type(entry));
+}
+
+static inline struct swap_cluster_info *__swap_offset_to_cluster(
struct swap_info_struct *si, pgoff_t offset)
{
+ VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */
+ VM_WARN_ON_ONCE(offset >= si->max);
return &si->cluster_info[offset / SWAPFILE_CLUSTER];
}
static inline struct swap_cluster_info *swap_cluster_lock(
struct swap_info_struct *si, unsigned long offset)
{
- struct swap_cluster_info *ci = swp_offset_cluster(si, offset);
+ struct swap_cluster_info *ci = __swap_offset_to_cluster(si, offset);
+ VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */
spin_lock(&ci->lock);
return ci;
}
static inline unsigned int folio_swap_flags(struct folio *folio)
{
- return swp_swap_info(folio->swap)->flags;
+ return __swap_entry_to_info(folio->swap)->flags;
}
/*
static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
bool *is_zeromap)
{
- struct swap_info_struct *sis = swp_swap_info(entry);
+ struct swap_info_struct *sis = __swap_entry_to_info(entry);
unsigned long start = swp_offset(entry);
unsigned long end = start + max_nr;
bool first_bit;
static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
{
- struct swap_info_struct *si = swp_swap_info(entry);
+ struct swap_info_struct *si = __swap_entry_to_info(entry);
pgoff_t offset = swp_offset(entry);
int i;
#else /* CONFIG_SWAP */
struct swap_iocb;
+static inline struct swap_info_struct *__swap_entry_to_info(swp_entry_t entry)
+{
+ return NULL;
+}
+
static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
{
}
struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
bool skip_if_exists)
{
- struct swap_info_struct *si = swp_swap_info(entry);
+ struct swap_info_struct *si = __swap_entry_to_info(entry);
struct folio *folio;
struct folio *new_folio = NULL;
struct folio *result = NULL;
unsigned long offset = entry_offset;
unsigned long start_offset, end_offset;
unsigned long mask;
- struct swap_info_struct *si = swp_swap_info(entry);
+ struct swap_info_struct *si = __swap_entry_to_info(entry);
struct blk_plug plug;
struct swap_iocb *splug = NULL;
bool page_allocated;
static struct plist_head *swap_avail_heads;
static DEFINE_SPINLOCK(swap_avail_lock);
-static struct swap_info_struct *swap_info[MAX_SWAPFILES];
+struct swap_info_struct *swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
.lock = INIT_LOCAL_LOCK(),
};
-static struct swap_info_struct *swap_type_to_swap_info(int type)
+/* May return NULL on invalid type, caller must check for NULL return */
+static struct swap_info_struct *swap_type_to_info(int type)
{
if (type >= MAX_SWAPFILES)
return NULL;
-
return READ_ONCE(swap_info[type]); /* rcu_dereference() */
}
+/* May return NULL on invalid entry, caller must check for NULL return */
+static struct swap_info_struct *swap_entry_to_info(swp_entry_t entry)
+{
+ return swap_type_to_info(swp_type(entry));
+}
+
static inline unsigned char swap_count(unsigned char ent)
{
return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */
sector_t swap_folio_sector(struct folio *folio)
{
- struct swap_info_struct *sis = swp_swap_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
struct swap_extent *se;
sector_t sector;
pgoff_t offset;
if (!entry.val)
goto out;
- si = swp_swap_info(entry);
+ si = swap_entry_to_info(entry);
if (!si)
goto bad_nofile;
if (data_race(!(si->flags & SWP_USED)))
if (!entry.val)
goto out;
- si = swp_swap_info(entry);
+ si = swap_entry_to_info(entry);
if (!si)
goto bad_nofile;
if (!get_swap_device_info(si))
unsigned char *map_end = map + nr_pages;
/* It should never free entries across different clusters */
- VM_BUG_ON(ci != swp_offset_cluster(si, offset + nr_pages - 1));
+ VM_BUG_ON(ci != __swap_offset_to_cluster(si, offset + nr_pages - 1));
VM_BUG_ON(cluster_is_empty(ci));
VM_BUG_ON(ci->count < nr_pages);
int __swap_count(swp_entry_t entry)
{
- struct swap_info_struct *si = swp_swap_info(entry);
+ struct swap_info_struct *si = __swap_entry_to_info(entry);
pgoff_t offset = swp_offset(entry);
return swap_count(si->swap_map[offset]);
swp_entry_t get_swap_page_of_type(int type)
{
- struct swap_info_struct *si = swap_type_to_swap_info(type);
+ struct swap_info_struct *si = swap_type_to_info(type);
unsigned long offset;
swp_entry_t entry = {0};
*/
sector_t swapdev_block(int type, pgoff_t offset)
{
- struct swap_info_struct *si = swap_type_to_swap_info(type);
+ struct swap_info_struct *si = swap_type_to_info(type);
struct swap_extent *se;
if (!si || !(si->flags & SWP_WRITEOK))
if (!l)
return SEQ_START_TOKEN;
- for (type = 0; (si = swap_type_to_swap_info(type)); type++) {
+ for (type = 0; (si = swap_type_to_info(type)); type++) {
if (!(si->flags & SWP_USED) || !si->swap_map)
continue;
if (!--l)
type = si->type + 1;
++(*pos);
- for (; (si = swap_type_to_swap_info(type)); type++) {
+ for (; (si = swap_type_to_info(type)); type++) {
if (!(si->flags & SWP_USED) || !si->swap_map)
continue;
return si;
unsigned char has_cache;
int err, i;
- si = swp_swap_info(entry);
+ si = swap_entry_to_info(entry);
if (WARN_ON_ONCE(!si)) {
pr_err("%s%08lx\n", Bad_file, entry.val);
return -EINVAL;
swap_entries_put_cache(si, entry, nr);
}
-struct swap_info_struct *swp_swap_info(swp_entry_t entry)
-{
- return swap_type_to_swap_info(swp_type(entry));
-}
-
/*
* add_swap_count_continuation - called when a swap count is duplicated
* beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's