mm: introduce ->swap_rw and use it for reads from SWP_FS_OPS swap-space

swap currently uses ->readpage to read swap pages.  This can only request
one page at a time from the filesystem, which is not most efficient.

swap uses ->direct_IO for writes which while this is adequate is an
inappropriate over-loading.  ->direct_IO may need to had handle allocate
space for holes or other details that are not relevant for swap.

So this patch introduces a new address_space operation: ->swap_rw.  In
this patch it is used for reads, and a subsequent patch will switch writes
to use it.

No filesystem yet supports ->swap_rw, but that is not a problem because
no filesystem actually works with filesystem-based swap.
Only two filesystems set SWP_FS_OPS:
- cifs sets the flag, but ->direct_IO always fails so swap cannot work.
- nfs sets the flag, but ->direct_IO calls generic_write_checks()
  which has failed on swap files for several releases.

To ensure that a NULL ->swap_rw isn't called, ->activate_swap() for both
NFS and cifs are changed to fail if ->swap_rw is not set.  This can be
removed if/when the function is added.

Future patches will restore swap-over-NFS functionality.

To submit an async read with ->swap_rw() we need to allocate a structure
to hold the kiocb and other details.  swap_readpage() cannot handle
transient failure, so we create a mempool to provide the structures.

Link: https://lkml.kernel.org/r/164859778125.29473.13430559328221330589.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 14d2940..794e2cc 100644 (file)
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4905,6 +4905,10 @@ static int cifs_swap_activate(struct swap_info_struct *sis,
 
        cifs_dbg(FYI, "swap activate\n");
 
+       if (!swap_file->f_mapping->a_ops->swap_rw)
+               /* Cannot support swap */
+               return -EINVAL;
+
        spin_lock(&inode->i_lock);
        blocks = inode->i_blocks;
        isize = inode->i_size;

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index a3a0736..55bc8c8 100644 (file)
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -488,6 +488,10 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
        struct rpc_clnt *clnt = NFS_CLIENT(inode);
        struct nfs_client *cl = NFS_SERVER(inode)->nfs_client;
 
+       if (!file->f_mapping->a_ops->swap_rw)
+               /* Cannot support swap */
+               return -EINVAL;
+
        spin_lock(&inode->i_lock);
        blocks = inode->i_blocks;
        isize = inode->i_size;

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde953..dbc5d10 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -380,6 +380,7 @@ struct address_space_operations {
        int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
                                sector_t *span);
        void (*swap_deactivate)(struct file *file);
+       int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
 };
 
 extern const struct address_space_operations empty_aops;

diff --git a/mm/page_io.c b/mm/page_io.c
index 77fa0fb..2724d63 100644 (file)
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -235,6 +235,25 @@ static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
 #define bio_associate_blkg_from_page(bio, page)                do { } while (0)
 #endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
 
+struct swap_iocb {
+       struct kiocb            iocb;
+       struct bio_vec          bvec;
+};
+static mempool_t *sio_pool;
+
+int sio_pool_init(void)
+{
+       if (!sio_pool) {
+               mempool_t *pool = mempool_create_kmalloc_pool(
+                       SWAP_CLUSTER_MAX, sizeof(struct swap_iocb));
+               if (cmpxchg(&sio_pool, NULL, pool))
+                       mempool_destroy(pool);
+       }
+       if (!sio_pool)
+               return -ENOMEM;
+       return 0;
+}
+
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
                bio_end_io_t end_write_func)
 {
@@ -306,6 +325,48 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
        return 0;
 }
 
+static void sio_read_complete(struct kiocb *iocb, long ret)
+{
+       struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+       struct page *page = sio->bvec.bv_page;
+
+       if (ret != 0 && ret != PAGE_SIZE) {
+               SetPageError(page);
+               ClearPageUptodate(page);
+               pr_alert_ratelimited("Read-error on swap-device\n");
+       } else {
+               SetPageUptodate(page);
+               count_vm_event(PSWPIN);
+       }
+       unlock_page(page);
+       mempool_free(sio, sio_pool);
+}
+
+static int swap_readpage_fs(struct page *page)
+{
+       struct swap_info_struct *sis = page_swap_info(page);
+       struct file *swap_file = sis->swap_file;
+       struct address_space *mapping = swap_file->f_mapping;
+       struct iov_iter from;
+       struct swap_iocb *sio;
+       loff_t pos = page_file_offset(page);
+       int ret;
+
+       sio = mempool_alloc(sio_pool, GFP_KERNEL);
+       init_sync_kiocb(&sio->iocb, swap_file);
+       sio->iocb.ki_pos = pos;
+       sio->iocb.ki_complete = sio_read_complete;
+       sio->bvec.bv_page = page;
+       sio->bvec.bv_len = PAGE_SIZE;
+       sio->bvec.bv_offset = 0;
+
+       iov_iter_bvec(&from, READ, &sio->bvec, 1, PAGE_SIZE);
+       ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+       if (ret != -EIOCBQUEUED)
+               sio_read_complete(&sio->iocb, ret);
+       return ret;
+}
+
 int swap_readpage(struct page *page, bool synchronous)
 {
        struct bio *bio;
@@ -334,12 +395,7 @@ int swap_readpage(struct page *page, bool synchronous)
        }
 
        if (data_race(sis->flags & SWP_FS_OPS)) {
-               struct file *swap_file = sis->swap_file;
-               struct address_space *mapping = swap_file->f_mapping;
-
-               ret = mapping->a_ops->readpage(swap_file, page);
-               if (!ret)
-                       count_vm_event(PSWPIN);
+               ret = swap_readpage_fs(page);
                goto out;
        }
 

diff --git a/mm/swap.h b/mm/swap.h
index e19f185..eafac80 100644 (file)
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -6,6 +6,7 @@
 #include <linux/blk_types.h> /* for bio_end_io_t */
 
 /* linux/mm/page_io.c */
+int sio_pool_init(void);
 int swap_readpage(struct page *page, bool do_poll);
 int swap_writepage(struct page *page, struct writeback_control *wbc);
 void end_swap_bio_write(struct bio *bio);

diff --git a/mm/swapfile.c b/mm/swapfile.c
index d811458..9398e91 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2262,6 +2262,11 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
                if (ret < 0)
                        return ret;
                sis->flags |= SWP_ACTIVATED;
+               if ((sis->flags & SWP_FS_OPS) &&
+                   sio_pool_init() != 0) {
+                       destroy_swap_extents(sis);
+                       return -ENOMEM;
+               }
                return ret;
        }