diff --git a/include/linux/swap.h b/include/linux/swap.h index 279c7b84bd63aad08670f6539a65617f48b8b42c..648a32b58e3eff7d26af5ae2dd3b0487ad5c0782 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -343,8 +343,13 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); /* linux/mm/swap_state.c */ -extern struct address_space swapper_spaces[]; -#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)]) +/* One swap address space for each 64M swap space */ +#define SWAP_ADDRESS_SPACE_SHIFT 14 +#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) +extern struct address_space *swapper_spaces[]; +#define swap_address_space(entry) \ + (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ + >> SWAP_ADDRESS_SPACE_SHIFT]) extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *, struct list_head *list); @@ -398,6 +403,8 @@ extern struct swap_info_struct *page_swap_info(struct page *); extern bool reuse_swap_page(struct page *, int *); extern int try_to_free_swap(struct page *); 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 */ diff --git a/mm/swap.c b/mm/swap.c index 844baedd24292f0803ddadb2a2be03a754ec150b..aabf2e90fe32d14b73554c314db20f6d6a554e12 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -971,12 +971,6 @@ EXPORT_SYMBOL(pagevec_lookup_tag); void __init swap_setup(void) { unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT); -#ifdef CONFIG_SWAP - int i; - - for (i = 0; i < MAX_SWAPFILES; i++) - spin_lock_init(&swapper_spaces[i].tree_lock); -#endif /* Use a smaller cluster for small-memory machines */ if (megs < 16) diff --git a/mm/swap_state.c b/mm/swap_state.c index 35d7e0ee1c77c9fb94915905e171f82ff859b7da..3863acd6189cba35cb0d2a811169b6b69f37981f 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -32,15 +33,8 @@ static const struct address_space_operations swap_aops = { #endif }; -struct address_space swapper_spaces[MAX_SWAPFILES] = { - [0 ... MAX_SWAPFILES - 1] = { - .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .i_mmap_writable = ATOMIC_INIT(0), - .a_ops = &swap_aops, - /* swap cache doesn't use writeback related tags */ - .flags = 1 << AS_NO_WRITEBACK_TAGS, - } -}; +struct address_space *swapper_spaces[MAX_SWAPFILES]; +static unsigned int nr_swapper_spaces[MAX_SWAPFILES]; #define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) @@ -53,11 +47,26 @@ static struct { unsigned long total_swapcache_pages(void) { - int i; + unsigned int i, j, nr; unsigned long ret = 0; + struct address_space *spaces; - for (i = 0; i < MAX_SWAPFILES; i++) - ret += swapper_spaces[i].nrpages; + rcu_read_lock(); + for (i = 0; i < MAX_SWAPFILES; i++) { + /* + * The corresponding entries in nr_swapper_spaces and + * swapper_spaces will be reused only after at least + * one grace period. So it is impossible for them + * belongs to different usage. + */ + nr = nr_swapper_spaces[i]; + spaces = rcu_dereference(swapper_spaces[i]); + if (!nr || !spaces) + continue; + for (j = 0; j < nr; j++) + ret += spaces[j].nrpages; + } + rcu_read_unlock(); return ret; } @@ -505,3 +514,38 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, skip: return read_swap_cache_async(entry, gfp_mask, vma, addr); } + +int init_swap_address_space(unsigned int type, unsigned long nr_pages) +{ + struct address_space *spaces, *space; + unsigned int i, nr; + + nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); + spaces = vzalloc(sizeof(struct address_space) * nr); + if (!spaces) + return -ENOMEM; + for (i = 0; i < nr; i++) { + space = spaces + i; + INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN); + atomic_set(&space->i_mmap_writable, 0); + space->a_ops = &swap_aops; + /* swap cache doesn't use writeback related tags */ + mapping_set_no_writeback_tags(space); + spin_lock_init(&space->tree_lock); + } + nr_swapper_spaces[type] = nr; + rcu_assign_pointer(swapper_spaces[type], spaces); + + return 0; +} + +void exit_swap_address_space(unsigned int type) +{ + struct address_space *spaces; + + spaces = swapper_spaces[type]; + nr_swapper_spaces[type] = 0; + rcu_assign_pointer(swapper_spaces[type], NULL); + synchronize_rcu(); + kvfree(spaces); +} diff --git a/mm/swapfile.c b/mm/swapfile.c index eb71b5d9430ba73cba79586ddd29acdd2cdbb759..66e95eb730407ec02604262de296278aab7b5880 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2084,6 +2084,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); + exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2407,8 +2408,12 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return maxpages; } -#define SWAP_CLUSTER_COLS \ +#define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) +#define SWAP_CLUSTER_SPACE_COLS \ + DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) +#define SWAP_CLUSTER_COLS \ + max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, @@ -2471,7 +2476,10 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, return nr_extents; - /* Reduce false cache line sharing between cluster_info */ + /* + * Reduce false cache line sharing between cluster_info and + * sharing same address space. + */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { @@ -2661,6 +2669,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } } + error = init_swap_address_space(p->type, maxpages); + if (error) + goto bad_swap; + mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER)