@@ -336,6 +336,8 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
unsigned long *nr_scanned);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
+extern int atomic_remove_mapping(struct address_space *mapping,
+ struct page *page);
extern int remove_mapping(struct address_space *mapping, struct page *page);
extern unsigned long vm_total_pages;
@@ -441,6 +443,7 @@ static inline long get_nr_swap_pages(void)
}
extern void si_swapinfo(struct sysinfo *);
+extern struct swap_info_struct *swap_info_get(swp_entry_t entry);
extern swp_entry_t get_swap_page(void);
extern swp_entry_t get_swap_page_of_type(int);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
@@ -449,6 +452,7 @@ extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t);
extern void swapcache_free(swp_entry_t);
+extern void __swapcache_free(swp_entry_t);
extern int free_swap_and_cache(swp_entry_t);
extern int swap_type_of(dev_t, sector_t, struct block_device **);
extern unsigned int count_swap_pages(int, int);
@@ -722,7 +722,7 @@ swp_entry_t get_swap_page_of_type(int type)
return (swp_entry_t) {0};
}
-static struct swap_info_struct *swap_info_get(swp_entry_t entry)
+struct swap_info_struct *swap_info_get(swp_entry_t entry)
{
struct swap_info_struct *p;
unsigned long offset, type;
@@ -855,6 +855,15 @@ void swapcache_free(swp_entry_t entry)
}
}
+void __swapcache_free(swp_entry_t entry)
+{
+ struct swap_info_struct *p;
+
+ p = swap_info_get(entry);
+ if (p)
+ swap_entry_free(p, entry, SWAP_HAS_CACHE);
+}
+
/*
* How many references to page are currently swapped out?
* This does not give an exact answer when swap count is continued,
@@ -526,6 +526,69 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
}
/*
+ * Attempt to detach a locked page from its ->mapping in atomic context.
+ * If it is dirty or if someone else has a ref on the page or couldn't
+ * get necessary locks, abort and return 0.
+ * If it was successfully detached, return 1.
+ * Assumes the caller has a single ref on this page.
+ */
+int atomic_remove_mapping(struct address_space *mapping,
+ struct page *page)
+{
+ BUG_ON(!PageLocked(page));
+ BUG_ON(mapping != page_mapping(page));
+ BUG_ON(!irqs_disabled());
+
+ spin_lock(&mapping->tree_lock);
+
+ /* Look at comment in __remove_mapping */
+ if (!page_freeze_refs(page, 2))
+ goto cannot_free;
+ /* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
+ if (unlikely(PageDirty(page))) {
+ page_unfreeze_refs(page, 2);
+ goto cannot_free;
+ }
+
+ if (PageSwapCache(page)) {
+ swp_entry_t swap = { .val = page_private(page) };
+ struct swap_info_struct *p = swap_info_get(swap);
+
+ if (!p || !spin_trylock(&p->lock)) {
+ page_unfreeze_refs(page, 2);
+ goto cannot_free;
+ }
+
+ mem_cgroup_swapout(page, swap);
+ __delete_from_swap_cache(page);
+ spin_unlock(&mapping->tree_lock);
+ __swapcache_free(swap);
+ spin_unlock(&p->lock);
+ } else {
+ void (*freepage)(struct page *);
+
+ freepage = mapping->a_ops->freepage;
+ __delete_from_page_cache(page, NULL);
+ spin_unlock(&mapping->tree_lock);
+
+ if (freepage != NULL)
+ freepage(page);
+ }
+
+ /*
+ * Unfreezing the refcount with 1 rather than 2 effectively
+ * drops the pagecache ref for us without requiring another
+ * atomic operation.
+ */
+ page_unfreeze_refs(page, 1);
+ return 1;
+
+cannot_free:
+ spin_unlock(&mapping->tree_lock);
+ return 0;
+}
+
+/*
* Same as remove_mapping, but if the page is removed from the mapping, it
* gets returned with a refcount of 0.
*/
For release page from atomic context(ie, softirq), locks related to the work should be aware of that. There are two locks. One is mapping->tree_lock and the other is swap_info_struct->lock. The mapping->tree_lock is alreay aware of irq so it's no problem but swap_info_struct->lock isn't so atomic_remove_mapping uses just try_spinlock and if it fails to hold a lock, it just depends on a fallback plan which moves the page into LRU's tail and expect page freeing in next. A change I know is mapping->a_ops->free is called on atomic context by this patch. Only user is nfs_readdir_clear_array which is no problem when I look at. Cc: Trond Myklebust <trond.myklebust@primarydata.com> Cc: linux-nfs@vger.kernel.org Signed-off-by: Minchan Kim <minchan@kernel.org> --- include/linux/swap.h | 4 ++++ mm/swapfile.c | 11 ++++++++- mm/vmscan.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 77 insertions(+), 1 deletion(-)