From: Peter Zijlstra Subject: [PATCH 23/31] mm: add support for non block device backed swap files Patch-mainline: not yet New addres_space_operations methods are added: int swapon(struct file *); int swapoff(struct file *); int swap_out(struct file *, struct page *, struct writeback_control *); int swap_in(struct file *, struct page *); When during sys_swapon() the ->swapon() method is found and returns no error the swapper_space.a_ops will proxy to sis->swap_file->f_mapping->a_ops, and make use of ->swap_{out,in}() to write/read swapcache pages. The ->swapon() method will be used to communicate to the file that the VM relies on it, and the address_space should take adequate measures (like reserving memory for mempools or the like). The ->swapoff() method will be called on sys_swapoff() when ->swapon() was found and returned no error. This new interface can be used to obviate the need for ->bmap in the swapfile code. A filesystem would need to load (and maybe even allocate) the full block map for a file into memory and pin it there on ->swapon() so that ->swap_{out,in}() have instant access to it. It can be released on ->swapoff(). The reason to provide ->swap_{out,in}() over using {write,read}page() is to 1) make a distinction between swapcache and pagecache pages, and 2) to provide a struct file * for credential context (normally not needed in the context of writepage, as the page content is normally dirtied using either of the following interfaces: write_{begin,end}() {prepare,commit}_write() page_mkwrite() which do have the file context. [miklos@szeredi.hu: cleanups] Signed-off-by: Peter Zijlstra Signed-off-by: Suresh Jayaraman --- Documentation/filesystems/Locking | 22 ++++++++++++++++ Documentation/filesystems/vfs.txt | 18 +++++++++++++ include/linux/buffer_head.h | 1 include/linux/fs.h | 9 ++++++ include/linux/swap.h | 4 ++ mm/page_io.c | 52 ++++++++++++++++++++++++++++++++++++++ mm/swap_state.c | 4 +- mm/swapfile.c | 30 ++++++++++++++++++++- 8 files changed, 136 insertions(+), 4 deletions(-) --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -198,6 +198,10 @@ prototypes: int (*launder_page)(struct page *); int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long); int (*error_remove_page)(struct address_space *, struct page *); + int (*swapon) (struct file *); + int (*swapoff) (struct file *); + int (*swap_out) (struct file *, struct page *, struct writeback_control *); + int (*swap_in) (struct file *, struct page *); locking rules: All except set_page_dirty and freepage may block @@ -221,6 +225,10 @@ migratepage: yes (both) launder_page: yes is_partially_uptodate: yes error_remove_page: yes +swapon no +swapoff no +swap_out no yes, unlocks +swap_in no yes, unlocks ->write_begin(), ->write_end(), ->sync_page() and ->readpage() may be called from the request handler (/dev/loop). @@ -322,6 +330,20 @@ cleaned, or an error value if not. Note getting mapped back in and redirtied, it needs to be kept locked across the entire operation. + ->swapon() will be called with a non-zero argument on files backing +(non block device backed) swapfiles. A return value of zero indicates success, +in which case this file can be used for backing swapspace. The swapspace +operations will be proxied to the address space operations. + + ->swapoff() will be called in the sys_swapoff() path when ->swapon() +returned success. + + ->swap_out() when swapon() returned success, this method is used to +write the swap page. + + ->swap_in() when swapon() returned success, this method is used to +read the swap page. + ----------------------- file_lock_operations ------------------------------ prototypes: void (*fl_copy_lock)(struct file_lock *, struct file_lock *); --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -543,6 +543,11 @@ struct address_space_operations { int (*migratepage) (struct page *, struct page *); int (*launder_page) (struct page *); int (*error_remove_page) (struct mapping *mapping, struct page *page); + int (*swapon)(struct file *); + int (*swapoff)(struct file *); + int (*swap_out)(struct file *file, struct page *page, + struct writeback_control *wbc); + int (*swap_in)(struct file *file, struct page *page); }; writepage: called by the VM to write a dirty page to backing store. @@ -712,6 +717,19 @@ struct address_space_operations { unless you have them locked or reference counts increased. + swapon: Called when swapon is used on a file. A + return value of zero indicates success, in which case this + file can be used to back swapspace. The swapspace operations + will be proxied to this address space's ->swap_{out,in} methods. + + swapoff: Called during swapoff on files where swapon was successfull. + + swap_out: Called to write a swapcache page to a backing store, similar to + writepage. + + swap_in: Called to read a swapcache page from a backing store, similar to + readpage. + The File Object =============== --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -330,6 +330,7 @@ static inline int inode_has_buffers(stru static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +static inline void block_sync_page(struct page *) { } #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -622,6 +622,15 @@ struct address_space_operations { int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); int (*error_remove_page)(struct address_space *, struct page *); + + /* + * swapfile support + */ + int (*swapon)(struct file *file); + int (*swapoff)(struct file *file); + int (*swap_out)(struct file *file, struct page *page, + struct writeback_control *wbc); + int (*swap_in)(struct file *file, struct page *page); }; /* --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -148,6 +148,7 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ + SWP_FILE = (1 << 7), /* file swap area */ /* add others here before... */ SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */ }; @@ -303,6 +304,8 @@ extern void swap_unplug_io_fn(struct bac /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); +extern void swap_sync_page(struct page *page); +extern int swap_set_page_dirty(struct page *page); extern void end_swap_bio_read(struct bio *bio, int err); /* linux/mm/swap_state.c */ @@ -339,6 +342,7 @@ extern int swap_type_of(dev_t, sector_t, extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); +extern struct swap_info_struct *page_swap_info(struct page *); extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; --- a/mm/page_io.c +++ b/mm/page_io.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -93,11 +94,23 @@ int swap_writepage(struct page *page, st { struct bio *bio; int ret = 0, rw = WRITE; + struct swap_info_struct *sis = page_swap_info(page); if (try_to_free_swap(page)) { unlock_page(page); goto out; } + + if (sis->flags & SWP_FILE) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + ret = mapping->a_ops->swap_out(swap_file, page, wbc); + if (!ret) + count_vm_event(PSWPOUT); + return ret; + } + bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write); if (bio == NULL) { set_page_dirty(page); @@ -115,13 +128,52 @@ out: return ret; } +void swap_sync_page(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + + if (sis->flags & SWP_FILE) { + struct address_space *mapping = sis->swap_file->f_mapping; + + if (mapping->a_ops->sync_page) + mapping->a_ops->sync_page(page); + } else { + block_sync_page(page); + } +} + +int swap_set_page_dirty(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + + if (sis->flags & SWP_FILE) { + struct address_space *mapping = sis->swap_file->f_mapping; + + return mapping->a_ops->set_page_dirty(page); + } else { + return __set_page_dirty_nobuffers(page); + } +} + int swap_readpage(struct page *page) { struct bio *bio; int ret = 0; + struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageUptodate(page)); + + if (sis->flags & SWP_FILE) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + ret = mapping->a_ops->swap_in(swap_file, page); + if (!ret) + count_vm_event(PSWPIN); + return ret; + } + bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read); if (bio == NULL) { unlock_page(page); --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -29,8 +29,8 @@ */ static const struct address_space_operations swap_aops = { .writepage = swap_writepage, - .sync_page = block_sync_page, - .set_page_dirty = __set_page_dirty_nobuffers, + .sync_page = swap_sync_page, + .set_page_dirty = swap_set_page_dirty, .migratepage = migrate_page, }; --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1373,6 +1373,14 @@ static void destroy_swap_extents(struct list_del(&se->list); kfree(se); } + + if (sis->flags & SWP_FILE) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + sis->flags &= ~SWP_FILE; + mapping->a_ops->swapoff(swap_file); + } } /* @@ -1454,7 +1462,9 @@ add_swap_extent(struct swap_info_struct */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { - struct inode *inode; + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; unsigned blocks_per_page; unsigned long page_no; unsigned blkbits; @@ -1465,13 +1475,22 @@ static int setup_swap_extents(struct swa int nr_extents = 0; int ret; - inode = sis->swap_file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; goto out; } + if (mapping->a_ops->swapon) { + ret = mapping->a_ops->swapon(swap_file); + if (!ret) { + sis->flags |= SWP_FILE; + ret = add_swap_extent(sis, 0, sis->max, 0); + *span = sis->pages; + } + goto out; + } + blkbits = inode->i_blkbits; blocks_per_page = PAGE_SIZE >> blkbits; @@ -2290,6 +2309,13 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +struct swap_info_struct *page_swap_info(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + BUG_ON(!PageSwapCache(page)); + return swap_info[swp_type(swap)]; +} + /* * swap_lock prevents swap_map being freed. Don't grab an extra * reference on the swaphandle, it doesn't matter if it becomes unused.