Signed-off-by: Andrew Morton --- 25-akpm/include/linux/swap.h | 6 +- 25-akpm/kernel/power/swsusp.c | 2 25-akpm/mm/shmem.c | 4 - 25-akpm/mm/swap_state.c | 8 ++- 25-akpm/mm/swapfile.c | 99 ++++++++++++++++-------------------------- 25-akpm/mm/vmscan.c | 5 +- 6 files changed, 56 insertions(+), 68 deletions(-) diff -puN include/linux/swap.h~swapspace-layout-improvements include/linux/swap.h --- 25/include/linux/swap.h~swapspace-layout-improvements 2005-01-23 14:46:19.839302520 -0800 +++ 25-akpm/include/linux/swap.h 2005-01-23 14:46:19.850300848 -0800 @@ -193,7 +193,7 @@ extern int rw_swap_page_sync(int, swp_en extern struct address_space swapper_space; #define total_swapcache_pages swapper_space.nrpages extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *); +extern int add_to_swap(struct page *page, void *cookie, pgoff_t index); extern void __delete_from_swap_cache(struct page *); extern void delete_from_swap_cache(struct page *); extern int move_to_swap_cache(struct page *, swp_entry_t); @@ -209,7 +209,7 @@ extern long total_swap_pages; extern unsigned int nr_swapfiles; extern struct swap_info_struct swap_info[]; extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(void); +extern swp_entry_t get_swap_page(void *cookie, pgoff_t index); extern int swap_duplicate(swp_entry_t); extern int valid_swaphandles(swp_entry_t, unsigned long *); extern void swap_free(swp_entry_t); @@ -276,7 +276,7 @@ static inline int remove_exclusive_swap_ return 0; } -static inline swp_entry_t get_swap_page(void) +static inline swp_entry_t get_swap_page(void *cookie, pgoff_t index) { swp_entry_t entry; entry.val = 0; diff -puN kernel/power/swsusp.c~swapspace-layout-improvements kernel/power/swsusp.c --- 25/kernel/power/swsusp.c~swapspace-layout-improvements 2005-01-23 14:46:19.840302368 -0800 +++ 25-akpm/kernel/power/swsusp.c 2005-01-23 14:46:19.851300696 -0800 @@ -245,7 +245,7 @@ static int write_page(unsigned long addr swp_entry_t entry; int error = 0; - entry = get_swap_page(); + entry = get_swap_page(NULL, swp_offset(*loc)); if (swp_offset(entry) && swapfile_used[swp_type(entry)] == SWAPFILE_SUSPEND) { error = rw_swap_page_sync(WRITE, entry, diff -puN mm/shmem.c~swapspace-layout-improvements mm/shmem.c --- 25/mm/shmem.c~swapspace-layout-improvements 2005-01-23 14:46:19.842302064 -0800 +++ 25-akpm/mm/shmem.c 2005-01-23 14:46:19.852300544 -0800 @@ -812,7 +812,7 @@ static int shmem_writepage(struct page * struct shmem_inode_info *info; swp_entry_t *entry, swap; struct address_space *mapping; - unsigned long index; + pgoff_t index; struct inode *inode; BUG_ON(!PageLocked(page)); @@ -824,7 +824,7 @@ static int shmem_writepage(struct page * info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; - swap = get_swap_page(); + swap = get_swap_page(mapping, index); if (!swap.val) goto redirty; diff -puN mm/swapfile.c~swapspace-layout-improvements mm/swapfile.c --- 25/mm/swapfile.c~swapspace-layout-improvements 2005-01-23 14:46:19.844301760 -0800 +++ 25-akpm/mm/swapfile.c 2005-01-23 14:46:19.854300240 -0800 @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -85,71 +86,51 @@ void swap_unplug_io_fn(struct backing_de up_read(&swap_unplug_sem); } -static inline int scan_swap_map(struct swap_info_struct *si) -{ - unsigned long offset; - /* - * We try to cluster swap pages by allocating them - * sequentially in swap. Once we've allocated - * SWAPFILE_CLUSTER pages this way, however, we resort to - * first-free allocation, starting a new cluster. This - * prevents us from scattering swap pages all over the entire - * swap partition, so that we reduce overall disk seek times - * between swap pages. -- sct */ - if (si->cluster_nr) { - while (si->cluster_next <= si->highest_bit) { - offset = si->cluster_next++; - if (si->swap_map[offset]) - continue; - si->cluster_nr--; - goto got_page; - } - } - si->cluster_nr = SWAPFILE_CLUSTER; +int akpm; - /* try to find an empty (even not aligned) cluster. */ - offset = si->lowest_bit; - check_next_cluster: - if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit) - { - unsigned long nr; - for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++) - if (si->swap_map[nr]) - { - offset = nr+1; - goto check_next_cluster; - } - /* We found a completly empty cluster, so start - * using it. - */ - goto got_page; - } - /* No luck, so now go finegrined as usual. -Andrea */ - for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) { - if (si->swap_map[offset]) +/* + * We divide the swapdev into 1024 kilobyte chunks. We use the cookie and the + * upper bits of the index to select a chunk and the rest of the index as the + * offset into the selected chunk. + */ +#define CHUNK_SHIFT (20 - PAGE_SHIFT) +#define CHUNK_MASK (-1UL << CHUNK_SHIFT) + +static int +scan_swap_map(struct swap_info_struct *si, void *cookie, pgoff_t index) +{ + unsigned long chunk; + unsigned long nchunks; + unsigned long block; + unsigned long scan; + + nchunks = si->max >> CHUNK_SHIFT; + chunk = 0; + if (nchunks) + chunk = hash_long((unsigned long)cookie + (index & CHUNK_MASK), + BITS_PER_LONG) % nchunks; + + block = (chunk << CHUNK_SHIFT) + (index & ~CHUNK_MASK); + + for (scan = 0; scan < si->max; scan++, block++) { + if (block == si->max) + block = 0; + if (block == 0) continue; - si->lowest_bit = offset+1; - got_page: - if (offset == si->lowest_bit) - si->lowest_bit++; - if (offset == si->highest_bit) - si->highest_bit--; - if (si->lowest_bit > si->highest_bit) { - si->lowest_bit = si->max; - si->highest_bit = 0; - } - si->swap_map[offset] = 1; - si->inuse_pages++; + if (si->swap_map[block]) + continue; + si->swap_map[block] = 1; nr_swap_pages--; - si->cluster_next = offset+1; - return offset; + if (akpm) + printk("cookie:%p, index:%lu, chunk:%lu nchunks:%lu " + "block:%lu\n", + cookie, index, chunk, nchunks, block); + return block; } - si->lowest_bit = si->max; - si->highest_bit = 0; return 0; } -swp_entry_t get_swap_page(void) +swp_entry_t get_swap_page(void *cookie, pgoff_t index) { struct swap_info_struct * p; unsigned long offset; @@ -168,7 +149,7 @@ swp_entry_t get_swap_page(void) p = &swap_info[type]; if ((p->flags & SWP_ACTIVE) == SWP_ACTIVE) { swap_device_lock(p); - offset = scan_swap_map(p); + offset = scan_swap_map(p, cookie, index); swap_device_unlock(p); if (offset) { entry = swp_entry(type,offset); diff -puN mm/swap_state.c~swapspace-layout-improvements mm/swap_state.c --- 25/mm/swap_state.c~swapspace-layout-improvements 2005-01-23 14:46:19.845301608 -0800 +++ 25-akpm/mm/swap_state.c 2005-01-23 14:46:19.855300088 -0800 @@ -139,8 +139,12 @@ void __delete_from_swap_cache(struct pag * * Allocate swap space for the page and add the page to the * swap cache. Caller needs to hold the page lock. + * + * We attempt to lay pages out on swap to that virtually-contiguous pages are + * contiguous on-disk. To do this we utilise page->index (offset into vma) and + * page->mapping (the anon_vma's address). */ -int add_to_swap(struct page * page) +int add_to_swap(struct page *page, void *cookie, pgoff_t index) { swp_entry_t entry; int pf_flags; @@ -150,7 +154,7 @@ int add_to_swap(struct page * page) BUG(); for (;;) { - entry = get_swap_page(); + entry = get_swap_page(cookie, index); if (!entry.val) return 0; diff -puN mm/vmscan.c~swapspace-layout-improvements mm/vmscan.c --- 25/mm/vmscan.c~swapspace-layout-improvements 2005-01-23 14:46:19.846301456 -0800 +++ 25-akpm/mm/vmscan.c 2005-01-23 14:46:19.856299936 -0800 @@ -397,7 +397,10 @@ static int shrink_list(struct list_head * Try to allocate it some swap space here. */ if (PageAnon(page) && !PageSwapCache(page)) { - if (!add_to_swap(page)) + void *cookie = page->mapping; + pgoff_t index = page->index; + + if (!add_to_swap(page, cookie, index)) goto activate_locked; } #endif /* CONFIG_SWAP */ _