swap: turn get_swap_page() into folio_alloc_swap()

This removes an assumption that a large folio is HPAGE_PMD_NR pages
in size.

Link: https://lkml.kernel.org/r/20220504182857.4013401-8-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5553189..252c23a 100644 (file)
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -470,7 +470,7 @@ static inline long get_nr_swap_pages(void)
 }
 
 extern void si_swapinfo(struct sysinfo *);
-extern swp_entry_t get_swap_page(struct page *page);
+swp_entry_t folio_alloc_swap(struct folio *folio);
 extern void put_swap_page(struct page *page, swp_entry_t entry);
 extern swp_entry_t get_swap_page_of_type(int);
 extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
@@ -583,7 +583,7 @@ static inline int try_to_free_swap(struct page *page)
        return 0;
 }
 
-static inline swp_entry_t get_swap_page(struct page *page)
+static inline swp_entry_t folio_alloc_swap(struct folio *folio)
 {
        swp_entry_t entry;
        entry.val = 0;
@@ -643,12 +643,13 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
 
 #ifdef CONFIG_MEMCG_SWAP
 void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry);
-extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
-static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry);
+static inline int mem_cgroup_try_charge_swap(struct folio *folio,
+               swp_entry_t entry)
 {
        if (mem_cgroup_disabled())
                return 0;
-       return __mem_cgroup_try_charge_swap(page, entry);
+       return __mem_cgroup_try_charge_swap(folio, entry);
 }
 
 extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
@@ -666,7 +667,7 @@ static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 {
 }
 
-static inline int mem_cgroup_try_charge_swap(struct page *page,
+static inline int mem_cgroup_try_charge_swap(struct folio *folio,
                                             swp_entry_t entry)
 {
        return 0;

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6e74ca9..e1b5823 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7162,17 +7162,17 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 }
 
 /**
- * __mem_cgroup_try_charge_swap - try charging swap space for a page
- * @page: page being added to swap
+ * __mem_cgroup_try_charge_swap - try charging swap space for a folio
+ * @folio: folio being added to swap
  * @entry: swap entry to charge
  *
- * Try to charge @page's memcg for the swap space at @entry.
+ * Try to charge @folio's memcg for the swap space at @entry.
  *
  * Returns 0 on success, -ENOMEM on failure.
  */
-int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 {
-       unsigned int nr_pages = thp_nr_pages(page);
+       unsigned int nr_pages = folio_nr_pages(folio);
        struct page_counter *counter;
        struct mem_cgroup *memcg;
        unsigned short oldid;
@@ -7180,9 +7180,9 @@ int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
        if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
                return 0;
 
-       memcg = page_memcg(page);
+       memcg = folio_memcg(folio);
 
-       VM_WARN_ON_ONCE_PAGE(!memcg, page);
+       VM_WARN_ON_ONCE_FOLIO(!memcg, folio);
        if (!memcg)
                return 0;
 
@@ -7205,7 +7205,7 @@ int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
        if (nr_pages > 1)
                mem_cgroup_id_get_many(memcg, nr_pages - 1);
        oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages);
-       VM_BUG_ON_PAGE(oldid, page);
+       VM_BUG_ON_FOLIO(oldid, folio);
        mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
        return 0;

diff --git a/mm/shmem.c b/mm/shmem.c
index 7994421..7cfe763 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1313,6 +1313,7 @@ int shmem_unuse(unsigned int type)
  */
 static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 {
+       struct folio *folio = page_folio(page);
        struct shmem_inode_info *info;
        struct address_space *mapping;
        struct inode *inode;
@@ -1386,7 +1387,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
                SetPageUptodate(page);
        }
 
-       swap = get_swap_page(page);
+       swap = folio_alloc_swap(folio);
        if (!swap.val)
                goto redirty;
 

diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 2b55318..0218ec1 100644 (file)
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -117,7 +117,7 @@ static int alloc_swap_slot_cache(unsigned int cpu)
 
        /*
         * Do allocation outside swap_slots_cache_mutex
-        * as kvzalloc could trigger reclaim and get_swap_page,
+        * as kvzalloc could trigger reclaim and folio_alloc_swap,
         * which can lock swap_slots_cache_mutex.
         */
        slots = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t),
@@ -213,7 +213,7 @@ static void __drain_swap_slots_cache(unsigned int type)
         * this function can be invoked in the cpu
         * hot plug path:
         * cpu_up -> lock cpu_hotplug -> cpu hotplug state callback
-        *   -> memory allocation -> direct reclaim -> get_swap_page
+        *   -> memory allocation -> direct reclaim -> folio_alloc_swap
         *   -> drain_swap_slots_cache
         *
         * Hence the loop over current online cpu below could miss cpu that
@@ -301,16 +301,16 @@ direct_free:
        return 0;
 }
 
-swp_entry_t get_swap_page(struct page *page)
+swp_entry_t folio_alloc_swap(struct folio *folio)
 {
        swp_entry_t entry;
        struct swap_slots_cache *cache;
 
        entry.val = 0;
 
-       if (PageTransHuge(page)) {
+       if (folio_test_large(folio)) {
                if (IS_ENABLED(CONFIG_THP_SWAP))
-                       get_swap_pages(1, &entry, HPAGE_PMD_NR);
+                       get_swap_pages(1, &entry, folio_nr_pages(folio));
                goto out;
        }
 
@@ -344,8 +344,8 @@ repeat:
 
        get_swap_pages(1, &entry, 1);
 out:
-       if (mem_cgroup_try_charge_swap(page, entry)) {
-               put_swap_page(page, entry);
+       if (mem_cgroup_try_charge_swap(folio, entry)) {
+               put_swap_page(&folio->page, entry);
                entry.val = 0;
        }
        return entry;

diff --git a/mm/swap_state.c b/mm/swap_state.c
index 27c4e28..2dc0d02 100644 (file)
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -184,13 +184,14 @@ void __delete_from_swap_cache(struct page *page,
  */
 int add_to_swap(struct page *page)
 {
+       struct folio *folio = page_folio(page);
        swp_entry_t entry;
        int err;
 
        VM_BUG_ON_PAGE(!PageLocked(page), page);
        VM_BUG_ON_PAGE(!PageUptodate(page), page);
 
-       entry = get_swap_page(page);
+       entry = folio_alloc_swap(folio);
        if (!entry.val)
                return 0;
 

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 9398e91..bfa41bf 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -77,9 +77,9 @@ static PLIST_HEAD(swap_active_head);
 /*
  * all available (active, not full) swap_info_structs
  * protected with swap_avail_lock, ordered by priority.
- * This is used by get_swap_page() instead of swap_active_head
+ * This is used by folio_alloc_swap() instead of swap_active_head
  * because swap_active_head includes all swap_info_structs,
- * but get_swap_page() doesn't need to look at full ones.
+ * but folio_alloc_swap() doesn't need to look at full ones.
  * This uses its own lock instead of swap_lock because when a
  * swap_info_struct changes between not-full/full, it needs to
  * add/remove itself to/from this list, but the swap_info_struct->lock
@@ -2109,11 +2109,12 @@ retry:
         * Under global memory pressure, swap entries can be reinserted back
         * into process space after the mmlist loop above passes over them.
         *
-        * Limit the number of retries? No: when mmget_not_zero() above fails,
-        * that mm is likely to be freeing swap from exit_mmap(), which proceeds
-        * at its own independent pace; and even shmem_writepage() could have
-        * been preempted after get_swap_page(), temporarily hiding that swap.
-        * It's easy and robust (though cpu-intensive) just to keep retrying.
+        * Limit the number of retries? No: when mmget_not_zero()
+        * above fails, that mm is likely to be freeing swap from
+        * exit_mmap(), which proceeds at its own independent pace;
+        * and even shmem_writepage() could have been preempted after
+        * folio_alloc_swap(), temporarily hiding that swap.  It's easy
+        * and robust (though cpu-intensive) just to keep retrying.
         */
        if (READ_ONCE(si->inuse_pages)) {
                if (!signal_pending(current))
@@ -2327,7 +2328,7 @@ static void _enable_swap_info(struct swap_info_struct *p)
         * which on removal of any swap_info_struct with an auto-assigned
         * (i.e. negative) priority increments the auto-assigned priority
         * of any lower-priority swap_info_structs.
-        * swap_avail_head needs to be priority ordered for get_swap_page(),
+        * swap_avail_head needs to be priority ordered for folio_alloc_swap(),
         * which allocates swap pages from the highest available priority
         * swap_info_struct.
         */