summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig6
-rw-r--r--fs/aio.c4
-rw-r--r--fs/block_dev.c7
-rw-r--r--fs/btrfs/btrfs_inode.h13
-rw-r--r--fs/btrfs/disk-io.c8
-rw-r--r--fs/btrfs/extent-tree.c2
-rw-r--r--fs/btrfs/tree-log.c17
-rw-r--r--fs/btrfs/volumes.c13
-rw-r--r--fs/buffer.c34
-rw-r--r--fs/cachefiles/bind.c8
-rw-r--r--fs/cachefiles/daemon.c30
-rw-r--r--fs/cachefiles/internal.h2
-rw-r--r--fs/cachefiles/main.c2
-rw-r--r--fs/cachefiles/namei.c17
-rw-r--r--fs/cachefiles/rdwr.c6
-rw-r--r--fs/cachefiles/xattr.c10
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/connect.c19
-rw-r--r--fs/cifs/file.c8
-rw-r--r--fs/cifs/link.c12
-rw-r--r--fs/cifs/netmisc.c20
-rw-r--r--fs/cifs/sess.c17
-rw-r--r--fs/cifs/smb1ops.c2
-rw-r--r--fs/cifs/smb2maperror.c2
-rw-r--r--fs/dcache.c112
-rw-r--r--fs/direct-io.c2
-rw-r--r--fs/ext2/super.c6
-rw-r--r--fs/ext3/super.c6
-rw-r--r--fs/ext4/super.c14
-rw-r--r--fs/f2fs/checkpoint.c97
-rw-r--r--fs/f2fs/data.c69
-rw-r--r--fs/f2fs/debug.c20
-rw-r--r--fs/f2fs/dir.c19
-rw-r--r--fs/f2fs/f2fs.h163
-rw-r--r--fs/f2fs/file.c257
-rw-r--r--fs/f2fs/gc.c26
-rw-r--r--fs/f2fs/inline.c20
-rw-r--r--fs/f2fs/inode.c37
-rw-r--r--fs/f2fs/namei.c53
-rw-r--r--fs/f2fs/node.c460
-rw-r--r--fs/f2fs/node.h60
-rw-r--r--fs/f2fs/recovery.c191
-rw-r--r--fs/f2fs/segment.c520
-rw-r--r--fs/f2fs/segment.h160
-rw-r--r--fs/f2fs/super.c47
-rw-r--r--fs/f2fs/xattr.c8
-rw-r--r--fs/file_table.c2
-rw-r--r--fs/fscache/object.c1
-rw-r--r--fs/fscache/page.c25
-rw-r--r--fs/fuse/file.c1
-rw-r--r--fs/internal.h5
-rw-r--r--fs/lockd/Makefile3
-rw-r--r--fs/lockd/mon.c6
-rw-r--r--fs/lockd/netns.h1
-rw-r--r--fs/lockd/procfs.c92
-rw-r--r--fs/lockd/procfs.h28
-rw-r--r--fs/lockd/svc.c16
-rw-r--r--fs/mpage.c2
-rw-r--r--fs/nfs/blocklayout/Makefile3
-rw-r--r--fs/nfs/blocklayout/blocklayout.c1386
-rw-r--r--fs/nfs/blocklayout/blocklayout.h213
-rw-r--r--fs/nfs/blocklayout/blocklayoutdev.c384
-rw-r--r--fs/nfs/blocklayout/blocklayoutdm.c108
-rw-r--r--fs/nfs/blocklayout/dev.c363
-rw-r--r--fs/nfs/blocklayout/extent_tree.c602
-rw-r--r--fs/nfs/blocklayout/extents.c908
-rw-r--r--fs/nfs/blocklayout/rpc_pipefs.c285
-rw-r--r--fs/nfs/callback.c4
-rw-r--r--fs/nfs/callback_proc.c23
-rw-r--r--fs/nfs/client.c6
-rw-r--r--fs/nfs/direct.c14
-rw-r--r--fs/nfs/file.c52
-rw-r--r--fs/nfs/filelayout/filelayout.c34
-rw-r--r--fs/nfs/filelayout/filelayout.h7
-rw-r--r--fs/nfs/filelayout/filelayoutdev.c108
-rw-r--r--fs/nfs/fscache-index.c3
-rw-r--r--fs/nfs/inode.c4
-rw-r--r--fs/nfs/internal.h7
-rw-r--r--fs/nfs/nfs3_fs.h34
-rw-r--r--fs/nfs/nfs3acl.c1
-rw-r--r--fs/nfs/nfs3client.c1
-rw-r--r--fs/nfs/nfs3proc.c1
-rw-r--r--fs/nfs/nfs3super.c1
-rw-r--r--fs/nfs/nfs4client.c38
-rw-r--r--fs/nfs/nfs4proc.c178
-rw-r--r--fs/nfs/nfs4renewd.c12
-rw-r--r--fs/nfs/nfs4state.c18
-rw-r--r--fs/nfs/nfs4xdr.c179
-rw-r--r--fs/nfs/objlayout/objio_osd.c113
-rw-r--r--fs/nfs/objlayout/objlayout.c70
-rw-r--r--fs/nfs/objlayout/objlayout.h5
-rw-r--r--fs/nfs/pagelist.c8
-rw-r--r--fs/nfs/pnfs.c105
-rw-r--r--fs/nfs/pnfs.h50
-rw-r--r--fs/nfs/pnfs_dev.c150
-rw-r--r--fs/nfs/super.c11
-rw-r--r--fs/nfs/write.c150
-rw-r--r--fs/nfs_common/Makefile3
-rw-r--r--fs/nfs_common/grace.c (renamed from fs/lockd/grace.c)68
-rw-r--r--fs/nfsd/Kconfig4
-rw-r--r--fs/nfsd/cache.h1
-rw-r--r--fs/nfsd/export.c1
-rw-r--r--fs/nfsd/nfs3proc.c13
-rw-r--r--fs/nfsd/nfs4callback.c144
-rw-r--r--fs/nfsd/nfs4idmap.c20
-rw-r--r--fs/nfsd/nfs4proc.c49
-rw-r--r--fs/nfsd/nfs4recover.c205
-rw-r--r--fs/nfsd/nfs4state.c115
-rw-r--r--fs/nfsd/nfs4xdr.c78
-rw-r--r--fs/nfsd/nfscache.c214
-rw-r--r--fs/nfsd/nfsctl.c45
-rw-r--r--fs/nfsd/nfsd.h2
-rw-r--r--fs/nfsd/nfsfh.c6
-rw-r--r--fs/nfsd/state.h31
-rw-r--r--fs/nfsd/vfs.c37
-rw-r--r--fs/nfsd/xdr4.h14
-rw-r--r--fs/nilfs2/inode.c7
-rw-r--r--fs/notify/fanotify/fanotify_user.c2
-rw-r--r--fs/notify/fsnotify.h3
-rw-r--r--fs/notify/group.c2
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c6
-rw-r--r--fs/ntfs/debug.c2
-rw-r--r--fs/ntfs/file.c5
-rw-r--r--fs/ntfs/super.c2
-rw-r--r--fs/ocfs2/aops.c15
-rw-r--r--fs/ocfs2/cluster/heartbeat.c19
-rw-r--r--fs/ocfs2/cluster/heartbeat.h1
-rw-r--r--fs/ocfs2/cluster/netdebug.c78
-rw-r--r--fs/ocfs2/cluster/tcp.c43
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c39
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c44
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c25
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c7
-rw-r--r--fs/ocfs2/dlmglue.c23
-rw-r--r--fs/ocfs2/file.c47
-rw-r--r--fs/ocfs2/inode.h2
-rw-r--r--fs/ocfs2/move_extents.c2
-rw-r--r--fs/ocfs2/stack_user.c2
-rw-r--r--fs/ocfs2/super.c1
-rw-r--r--fs/proc/base.c75
-rw-r--r--fs/proc/internal.h5
-rw-r--r--fs/proc/kcore.c4
-rw-r--r--fs/proc/page.c3
-rw-r--r--fs/proc/task_mmu.c361
-rw-r--r--fs/proc/task_nommu.c88
-rw-r--r--fs/quota/dquot.c2
-rw-r--r--fs/stack.c2
-rw-r--r--fs/super.c3
-rw-r--r--fs/timerfd.c3
-rw-r--r--fs/ufs/ialloc.c6
-rw-r--r--fs/ufs/namei.c4
151 files changed, 5407 insertions, 5005 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 312393f32948..db5dc1598716 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -233,9 +233,13 @@ if NETWORK_FILESYSTEMS
source "fs/nfs/Kconfig"
source "fs/nfsd/Kconfig"
+config GRACE_PERIOD
+ tristate
+
config LOCKD
tristate
depends on FILE_LOCKING
+ select GRACE_PERIOD
config LOCKD_V4
bool
@@ -249,7 +253,7 @@ config NFS_ACL_SUPPORT
config NFS_COMMON
bool
- depends on NFSD || NFS_FS
+ depends on NFSD || NFS_FS || LOCKD
default y
source "net/sunrpc/Kconfig"
diff --git a/fs/aio.c b/fs/aio.c
index 733750096b71..84a751005f5b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -661,10 +661,10 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
INIT_LIST_HEAD(&ctx->active_reqs);
- if (percpu_ref_init(&ctx->users, free_ioctx_users))
+ if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL))
goto err;
- if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
+ if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, 0, GFP_KERNEL))
goto err;
ctx->cpu = alloc_percpu(struct kioctx_cpu);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6d7274619bf9..e2f3ad0879ce 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -304,6 +304,12 @@ static int blkdev_readpage(struct file * file, struct page * page)
return block_read_full_page(page, blkdev_get_block);
}
+static int blkdev_readpages(struct file *file, struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages)
+{
+ return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block);
+}
+
static int blkdev_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -1622,6 +1628,7 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
static const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
+ .readpages = blkdev_readpages,
.writepage = blkdev_writepage,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 43527fd78825..56b8522d5767 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -234,8 +234,17 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
BTRFS_I(inode)->last_sub_trans <=
BTRFS_I(inode)->last_log_commit &&
BTRFS_I(inode)->last_sub_trans <=
- BTRFS_I(inode)->root->last_log_commit)
- return 1;
+ BTRFS_I(inode)->root->last_log_commit) {
+ /*
+ * After a ranged fsync we might have left some extent maps
+ * (that fall outside the fsync's range). So return false
+ * here if the list isn't empty, to make sure btrfs_log_inode()
+ * will be called and process those extent maps.
+ */
+ smp_mb();
+ if (list_empty(&BTRFS_I(inode)->extent_tree.modified_extents))
+ return 1;
+ }
return 0;
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a1d36e62179c..d0d78dc07792 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1183,7 +1183,7 @@ static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
if (!writers)
return ERR_PTR(-ENOMEM);
- ret = percpu_counter_init(&writers->counter, 0);
+ ret = percpu_counter_init(&writers->counter, 0, GFP_KERNEL);
if (ret < 0) {
kfree(writers);
return ERR_PTR(ret);
@@ -2188,7 +2188,7 @@ int open_ctree(struct super_block *sb,
goto fail_srcu;
}
- ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0);
+ ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_bdi;
@@ -2196,13 +2196,13 @@ int open_ctree(struct super_block *sb,
fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE *
(1 + ilog2(nr_cpu_ids));
- ret = percpu_counter_init(&fs_info->delalloc_bytes, 0);
+ ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_dirty_metadata_bytes;
}
- ret = percpu_counter_init(&fs_info->bio_counter, 0);
+ ret = percpu_counter_init(&fs_info->bio_counter, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_delalloc_bytes;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3efe1c3877bf..caaf015d6e4b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3494,7 +3494,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
if (!found)
return -ENOMEM;
- ret = percpu_counter_init(&found->total_bytes_pinned, 0);
+ ret = percpu_counter_init(&found->total_bytes_pinned, 0, GFP_KERNEL);
if (ret) {
kfree(found);
return ret;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d296efe2d3e7..d0262ceb85e1 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3994,7 +3994,8 @@ again:
if (ret < 0) {
err = ret;
goto out_unlock;
- } if (ret) {
+ }
+ if (ret) {
ins_nr = 0;
btrfs_release_path(path);
continue;
@@ -4093,18 +4094,8 @@ log_extents:
}
}
- write_lock(&em_tree->lock);
- /*
- * If we're doing a ranged fsync and there are still modified extents
- * in the list, we must run on the next fsync call as it might cover
- * those extents (a full fsync or an fsync for other range).
- */
- if (list_empty(&em_tree->modified_extents)) {
- BTRFS_I(inode)->logged_trans = trans->transid;
- BTRFS_I(inode)->last_log_commit =
- BTRFS_I(inode)->last_sub_trans;
- }
- write_unlock(&em_tree->lock);
+ BTRFS_I(inode)->logged_trans = trans->transid;
+ BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans;
out_unlock:
if (unlikely(err))
btrfs_put_logged_extents(&logged_list);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 340a92d08e84..2c2d6d1d8eee 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -529,12 +529,12 @@ static noinline int device_list_add(const char *path,
*/
/*
- * As of now don't allow update to btrfs_fs_device through
- * the btrfs dev scan cli, after FS has been mounted.
+ * For now, we do allow update to btrfs_fs_device through the
+ * btrfs dev scan cli after FS has been mounted. We're still
+ * tracking a problem where systems fail mount by subvolume id
+ * when we reject replacement on a mounted FS.
*/
- if (fs_devices->opened) {
- return -EBUSY;
- } else {
+ if (!fs_devices->opened && found_transid < device->generation) {
/*
* That is if the FS is _not_ mounted and if you
* are here, that means there is more than one
@@ -542,8 +542,7 @@ static noinline int device_list_add(const char *path,
* with larger generation number or the last-in if
* generation are equal.
*/
- if (found_transid < device->generation)
- return -EEXIST;
+ return -EEXIST;
}
name = rcu_string_strdup(path, GFP_NOFS);
diff --git a/fs/buffer.c b/fs/buffer.c
index 8f05111bbb8b..44c14a87750e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1022,7 +1022,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
bh = page_buffers(page);
if (bh->b_size == size) {
end_block = init_page_buffers(page, bdev,
- index << sizebits, size);
+ (sector_t)index << sizebits,
+ size);
goto done;
}
if (!try_to_free_buffers(page))
@@ -1043,7 +1044,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
*/
spin_lock(&inode->i_mapping->private_lock);
link_dev_buffers(page, bh);
- end_block = init_page_buffers(page, bdev, index << sizebits, size);
+ end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
+ size);
spin_unlock(&inode->i_mapping->private_lock);
done:
ret = (block < end_block) ? 1 : -ENXIO;
@@ -1251,7 +1253,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh)
* a local interrupt disable for that.
*/
-#define BH_LRU_SIZE 8
+#define BH_LRU_SIZE 16
struct bh_lru {
struct buffer_head *bhs[BH_LRU_SIZE];
@@ -2954,7 +2956,7 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
/*
* This allows us to do IO even on the odd last sectors
- * of a device, even if the bh block size is some multiple
+ * of a device, even if the block size is some multiple
* of the physical sector size.
*
* We'll just truncate the bio to the size of the device,
@@ -2964,10 +2966,11 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
* errors, this only handles the "we need to be able to
* do IO at the final sector" case.
*/
-static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
+void guard_bio_eod(int rw, struct bio *bio)
{
sector_t maxsector;
- unsigned bytes;
+ struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
+ unsigned truncated_bytes;
maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
if (!maxsector)
@@ -2982,23 +2985,20 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
return;
maxsector -= bio->bi_iter.bi_sector;
- bytes = bio->bi_iter.bi_size;
- if (likely((bytes >> 9) <= maxsector))
+ if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
return;
- /* Uhhuh. We've got a bh that straddles the device size! */
- bytes = maxsector << 9;
+ /* Uhhuh. We've got a bio that straddles the device size! */
+ truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
/* Truncate the bio.. */
- bio->bi_iter.bi_size = bytes;
- bio->bi_io_vec[0].bv_len = bytes;
+ bio->bi_iter.bi_size -= truncated_bytes;
+ bvec->bv_len -= truncated_bytes;
/* ..and clear the end of the buffer for reads */
if ((rw & RW_MASK) == READ) {
- void *kaddr = kmap_atomic(bh->b_page);
- memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes);
- kunmap_atomic(kaddr);
- flush_dcache_page(bh->b_page);
+ zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+ truncated_bytes);
}
}
@@ -3039,7 +3039,7 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
bio->bi_flags |= bio_flags;
/* Take care of bh's that straddle the end of the device */
- guard_bh_eod(rw, bio, bh);
+ guard_bio_eod(rw, bio);
if (buffer_meta(bh))
rw |= REQ_META;
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index d749731dc0ee..fbb08e97438d 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -50,18 +50,18 @@ int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
cache->brun_percent < 100);
if (*args) {
- pr_err("'bind' command doesn't take an argument");
+ pr_err("'bind' command doesn't take an argument\n");
return -EINVAL;
}
if (!cache->rootdirname) {
- pr_err("No cache directory specified");
+ pr_err("No cache directory specified\n");
return -EINVAL;
}
/* don't permit already bound caches to be re-bound */
if (test_bit(CACHEFILES_READY, &cache->flags)) {
- pr_err("Cache already bound");
+ pr_err("Cache already bound\n");
return -EBUSY;
}
@@ -248,7 +248,7 @@ error_open_root:
kmem_cache_free(cachefiles_object_jar, fsdef);
error_root_object:
cachefiles_end_secure(cache, saved_cred);
- pr_err("Failed to register: %d", ret);
+ pr_err("Failed to register: %d\n", ret);
return ret;
}
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index b078d3081d6c..ce1b115dcc28 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -315,7 +315,7 @@ static unsigned int cachefiles_daemon_poll(struct file *file,
static int cachefiles_daemon_range_error(struct cachefiles_cache *cache,
char *args)
{
- pr_err("Free space limits must be in range 0%%<=stop<cull<run<100%%");
+ pr_err("Free space limits must be in range 0%%<=stop<cull<run<100%%\n");
return -EINVAL;
}
@@ -475,12 +475,12 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args)
_enter(",%s", args);
if (!*args) {
- pr_err("Empty directory specified");
+ pr_err("Empty directory specified\n");
return -EINVAL;
}
if (cache->rootdirname) {
- pr_err("Second cache directory specified");
+ pr_err("Second cache directory specified\n");
return -EEXIST;
}
@@ -503,12 +503,12 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args)
_enter(",%s", args);
if (!*args) {
- pr_err("Empty security context specified");
+ pr_err("Empty security context specified\n");
return -EINVAL;
}
if (cache->secctx) {
- pr_err("Second security context specified");
+ pr_err("Second security context specified\n");
return -EINVAL;
}
@@ -531,7 +531,7 @@ static int cachefiles_daemon_tag(struct cachefiles_cache *cache, char *args)
_enter(",%s", args);
if (!*args) {
- pr_err("Empty tag specified");
+ pr_err("Empty tag specified\n");
return -EINVAL;
}
@@ -562,12 +562,12 @@ static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args)
goto inval;
if (!test_bit(CACHEFILES_READY, &cache->flags)) {
- pr_err("cull applied to unready cache");
+ pr_err("cull applied to unready cache\n");
return -EIO;
}
if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
- pr_err("cull applied to dead cache");
+ pr_err("cull applied to dead cache\n");
return -EIO;
}
@@ -587,11 +587,11 @@ static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args)
notdir:
path_put(&path);
- pr_err("cull command requires dirfd to be a directory");
+ pr_err("cull command requires dirfd to be a directory\n");
return -ENOTDIR;
inval:
- pr_err("cull command requires dirfd and filename");
+ pr_err("cull command requires dirfd and filename\n");
return -EINVAL;
}
@@ -614,7 +614,7 @@ static int cachefiles_daemon_debug(struct cachefiles_cache *cache, char *args)
return 0;
inval:
- pr_err("debug command requires mask");
+ pr_err("debug command requires mask\n");
return -EINVAL;
}
@@ -634,12 +634,12 @@ static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args)
goto inval;
if (!test_bit(CACHEFILES_READY, &cache->flags)) {
- pr_err("inuse applied to unready cache");
+ pr_err("inuse applied to unready cache\n");
return -EIO;
}
if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
- pr_err("inuse applied to dead cache");
+ pr_err("inuse applied to dead cache\n");
return -EIO;
}
@@ -659,11 +659,11 @@ static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args)
notdir:
path_put(&path);
- pr_err("inuse command requires dirfd to be a directory");
+ pr_err("inuse command requires dirfd to be a directory\n");
return -ENOTDIR;
inval:
- pr_err("inuse command requires dirfd and filename");
+ pr_err("inuse command requires dirfd and filename\n");
return -EINVAL;
}
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 3d50998abf57..8c52472d2efa 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -255,7 +255,7 @@ extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
#define cachefiles_io_error(___cache, FMT, ...) \
do { \
- pr_err("I/O Error: " FMT, ##__VA_ARGS__); \
+ pr_err("I/O Error: " FMT"\n", ##__VA_ARGS__); \
fscache_io_error(&(___cache)->cache); \
set_bit(CACHEFILES_DEAD, &(___cache)->flags); \
} while (0)
diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c
index 180edfb45f66..711f13d8c2de 100644
--- a/fs/cachefiles/main.c
+++ b/fs/cachefiles/main.c
@@ -84,7 +84,7 @@ error_proc:
error_object_jar:
misc_deregister(&cachefiles_dev);
error_dev:
- pr_err("failed to register: %d", ret);
+ pr_err("failed to register: %d\n", ret);
return ret;
}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 5bf2b41e66d3..dad7d9542a24 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -543,7 +543,7 @@ lookup_again:
next, next->d_inode, next->d_inode->i_ino);
} else if (!S_ISDIR(next->d_inode->i_mode)) {
- pr_err("inode %lu is not a directory",
+ pr_err("inode %lu is not a directory\n",
next->d_inode->i_ino);
ret = -ENOBUFS;
goto error;
@@ -574,7 +574,7 @@ lookup_again:
} else if (!S_ISDIR(next->d_inode->i_mode) &&
!S_ISREG(next->d_inode->i_mode)
) {
- pr_err("inode %lu is not a file or directory",
+ pr_err("inode %lu is not a file or directory\n",
next->d_inode->i_ino);
ret = -ENOBUFS;
goto error;
@@ -768,7 +768,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
ASSERT(subdir->d_inode);
if (!S_ISDIR(subdir->d_inode->i_mode)) {
- pr_err("%s is not a directory", dirname);
+ pr_err("%s is not a directory\n", dirname);
ret = -EIO;
goto check_error;
}
@@ -779,7 +779,8 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
!subdir->d_inode->i_op->lookup ||
!subdir->d_inode->i_op->mkdir ||
!subdir->d_inode->i_op->create ||
- !subdir->d_inode->i_op->rename ||
+ (!subdir->d_inode->i_op->rename &&
+ !subdir->d_inode->i_op->rename2) ||
!subdir->d_inode->i_op->rmdir ||
!subdir->d_inode->i_op->unlink)
goto check_error;
@@ -795,13 +796,13 @@ check_error:
mkdir_error:
mutex_unlock(&dir->d_inode->i_mutex);
dput(subdir);
- pr_err("mkdir %s failed with error %d", dirname, ret);
+ pr_err("mkdir %s failed with error %d\n", dirname, ret);
return ERR_PTR(ret);
lookup_error:
mutex_unlock(&dir->d_inode->i_mutex);
ret = PTR_ERR(subdir);
- pr_err("Lookup %s failed with error %d", dirname, ret);
+ pr_err("Lookup %s failed with error %d\n", dirname, ret);
return ERR_PTR(ret);
nomem_d_alloc:
@@ -891,7 +892,7 @@ lookup_error:
if (ret == -EIO) {
cachefiles_io_error(cache, "Lookup failed");
} else if (ret != -ENOMEM) {
- pr_err("Internal error: %d", ret);
+ pr_err("Internal error: %d\n", ret);
ret = -EIO;
}
@@ -950,7 +951,7 @@ error:
}
if (ret != -ENOMEM) {
- pr_err("Internal error: %d", ret);
+ pr_err("Internal error: %d\n", ret);
ret = -EIO;
}
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 4b1fb5ca65b8..25e745b8eb1b 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -151,7 +151,6 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
struct cachefiles_one_read *monitor;
struct cachefiles_object *object;
struct fscache_retrieval *op;
- struct pagevec pagevec;
int error, max;
op = container_of(_op, struct fscache_retrieval, op);
@@ -160,8 +159,6 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
_enter("{ino=%lu}", object->backer->d_inode->i_ino);
- pagevec_init(&pagevec, 0);
-
max = 8;
spin_lock_irq(&object->work_lock);
@@ -396,7 +393,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
{
struct cachefiles_object *object;
struct cachefiles_cache *cache;
- struct pagevec pagevec;
struct inode *inode;
sector_t block0, block;
unsigned shift;
@@ -427,8 +423,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
op->op.flags |= FSCACHE_OP_ASYNC;
op->op.processor = cachefiles_read_copier;
- pagevec_init(&pagevec, 0);
-
/* we assume the absence or presence of the first block is a good
* enough indication for the page as a whole
* - TODO: don't use bmap() for this as it is _not_ actually good
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index 1ad51ffbb275..acbc1f094fb1 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -51,7 +51,7 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
}
if (ret != -EEXIST) {
- pr_err("Can't set xattr on %*.*s [%lu] (err %d)",
+ pr_err("Can't set xattr on %*.*s [%lu] (err %d)\n",
dentry->d_name.len, dentry->d_name.len,
dentry->d_name.name, dentry->d_inode->i_ino,
-ret);
@@ -64,7 +64,7 @@ int cachefiles_check_object_type(struct cachefiles_object *object)
if (ret == -ERANGE)
goto bad_type_length;
- pr_err("Can't read xattr on %*.*s [%lu] (err %d)",
+ pr_err("Can't read xattr on %*.*s [%lu] (err %d)\n",
dentry->d_name.len, dentry->d_name.len,
dentry->d_name.name, dentry->d_inode->i_ino,
-ret);
@@ -85,14 +85,14 @@ error:
return ret;
bad_type_length:
- pr_err("Cache object %lu type xattr length incorrect",
+ pr_err("Cache object %lu type xattr length incorrect\n",
dentry->d_inode->i_ino);
ret = -EIO;
goto error;
bad_type:
xtype[2] = 0;
- pr_err("Cache object %*.*s [%lu] type %s not %s",
+ pr_err("Cache object %*.*s [%lu] type %s not %s\n",
dentry->d_name.len, dentry->d_name.len,
dentry->d_name.name, dentry->d_inode->i_ino,
xtype, type);
@@ -293,7 +293,7 @@ error:
return ret;
bad_type_length:
- pr_err("Cache object %lu xattr length incorrect",
+ pr_err("Cache object %lu xattr length incorrect\n",
dentry->d_inode->i_ino);
ret = -EIO;
goto error;
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index b0fafa499505..002e0c173939 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -136,5 +136,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.04"
+#define CIFS_VERSION "2.05"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 8a9fded7c135..36ca2045009b 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -837,6 +837,7 @@ cifs_demultiplex_thread(void *p)
struct TCP_Server_Info *server = p;
unsigned int pdu_length;
char *buf = NULL;
+ struct task_struct *task_to_wake = NULL;
struct mid_q_entry *mid_entry;
current->flags |= PF_MEMALLOC;
@@ -927,7 +928,19 @@ cifs_demultiplex_thread(void *p)
if (server->smallbuf) /* no sense logging a debug message if NULL */
cifs_small_buf_release(server->smallbuf);
+ task_to_wake = xchg(&server->tsk, NULL);
clean_demultiplex_info(server);
+
+ /* if server->tsk was NULL then wait for a signal before exiting */
+ if (!task_to_wake) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!signal_pending(current)) {
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ set_current_state(TASK_RUNNING);
+ }
+
module_put_and_exit(0);
}
@@ -2050,6 +2063,8 @@ cifs_find_tcp_session(struct smb_vol *vol)
static void
cifs_put_tcp_session(struct TCP_Server_Info *server)
{
+ struct task_struct *task;
+
spin_lock(&cifs_tcp_ses_lock);
if (--server->srv_count > 0) {
spin_unlock(&cifs_tcp_ses_lock);
@@ -2073,6 +2088,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server)
kfree(server->session_key.response);
server->session_key.response = NULL;
server->session_key.len = 0;
+
+ task = xchg(&server->tsk, NULL);
+ if (task)
+ force_sig(SIGKILL, task);
}
static struct TCP_Server_Info *
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 7c018a1c52f7..5f29354b072a 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3568,15 +3568,9 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
lru_cache_add_file(page);
unlock_page(page);
page_cache_release(page);
- if (rc == -EAGAIN)
- list_add_tail(&page->lru, &tmplist);
}
+ /* Fallback to the readpage in error/reconnect cases */
kref_put(&rdata->refcount, cifs_readdata_release);
- if (rc == -EAGAIN) {
- /* Re-add pages to the page_list and retry */
- list_splice(&tmplist, page_list);
- continue;
- }
break;
}
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 68559fd557fb..5657416d3483 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -213,8 +213,12 @@ create_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
goto out;
- rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, cifs_sb,
- fromName, buf, &bytes_written);
+ if (tcon->ses->server->ops->create_mf_symlink)
+ rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon,
+ cifs_sb, fromName, buf, &bytes_written);
+ else
+ rc = -EOPNOTSUPP;
+
if (rc)
goto out;
@@ -339,9 +343,11 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE))
+ if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) {
+ rc = -ENOENT;
/* it's not a symlink */
goto out;
+ }
io_parms.netfid = fid.netfid;
io_parms.pid = current->tgid;
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 6834b9c3bec1..b333ff60781d 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -925,11 +925,23 @@ cifs_NTtimeToUnix(__le64 ntutc)
/* BB what about the timezone? BB */
/* Subtract the NTFS time offset, then convert to 1s intervals. */
- u64 t;
+ s64 t = le64_to_cpu(ntutc) - NTFS_TIME_OFFSET;
+
+ /*
+ * Unfortunately can not use normal 64 bit division on 32 bit arch, but
+ * the alternative, do_div, does not work with negative numbers so have
+ * to special case them
+ */
+ if (t < 0) {
+ t = -t;
+ ts.tv_nsec = (long)(do_div(t, 10000000) * 100);
+ ts.tv_nsec = -ts.tv_nsec;
+ ts.tv_sec = -t;
+ } else {
+ ts.tv_nsec = (long)do_div(t, 10000000) * 100;
+ ts.tv_sec = t;
+ }
- t = le64_to_cpu(ntutc) - NTFS_TIME_OFFSET;
- ts.tv_nsec = do_div(t, 10000000) * 100;
- ts.tv_sec = t;
return ts;
}
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 3a5e83317683..57db63ff88da 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -745,14 +745,6 @@ out:
sess_free_buffer(sess_data);
}
-#else
-
-static void
-sess_auth_lanman(struct sess_data *sess_data)
-{
- sess_data->result = -EOPNOTSUPP;
- sess_data->func = NULL;
-}
#endif
static void
@@ -1103,15 +1095,6 @@ out:
ses->auth_key.response = NULL;
}
-#else
-
-static void
-sess_auth_kerberos(struct sess_data *sess_data)
-{
- cifs_dbg(VFS, "Kerberos negotiated but upcall support disabled!\n");
- sess_data->result = -ENOSYS;
- sess_data->func = NULL;
-}
#endif /* ! CONFIG_CIFS_UPCALL */
/*
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 1a6df4b03f67..52131d8cb4d5 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -586,7 +586,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
tmprc = CIFS_open(xid, &oparms, &oplock, NULL);
if (tmprc == -EOPNOTSUPP)
*symlink = true;
- else
+ else if (tmprc == 0)
CIFSSMBClose(xid, tcon, fid.netfid);
}
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index af59d03db492..8257a5a97cc0 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -256,6 +256,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
{STATUS_DLL_MIGHT_BE_INCOMPATIBLE, -EIO,
"STATUS_DLL_MIGHT_BE_INCOMPATIBLE"},
{STATUS_STOPPED_ON_SYMLINK, -EOPNOTSUPP, "STATUS_STOPPED_ON_SYMLINK"},
+ {STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EOPNOTSUPP,
+ "STATUS_REPARSE_NOT_HANDLED"},
{STATUS_DEVICE_REQUIRES_CLEANING, -EIO,
"STATUS_DEVICE_REQUIRES_CLEANING"},
{STATUS_DEVICE_DOOR_OPEN, -EIO, "STATUS_DEVICE_DOOR_OPEN"},
diff --git a/fs/dcache.c b/fs/dcache.c
index 7a5b51440afa..cb25a1a5e307 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2372,7 +2372,8 @@ void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
}
EXPORT_SYMBOL(dentry_update_name_case);
-static void switch_names(struct dentry *dentry, struct dentry *target)
+static void switch_names(struct dentry *dentry, struct dentry *target,
+ bool exchange)
{
if (dname_external(target)) {
if (dname_external(dentry)) {
@@ -2406,13 +2407,19 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
*/
unsigned int i;
BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+ if (!exchange) {
+ memcpy(dentry->d_iname, target->d_name.name,
+ target->d_name.len + 1);
+ dentry->d_name.hash_len = target->d_name.hash_len;
+ return;
+ }
for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
swap(((long *) &dentry->d_iname)[i],
((long *) &target->d_iname)[i]);
}
}
}
- swap(dentry->d_name.len, target->d_name.len);
+ swap(dentry->d_name.hash_len, target->d_name.hash_len);
}
static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
@@ -2442,25 +2449,29 @@ static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
}
}
-static void dentry_unlock_parents_for_move(struct dentry *dentry,
- struct dentry *target)
+static void dentry_unlock_for_move(struct dentry *dentry, struct dentry *target)
{
if (target->d_parent != dentry->d_parent)
spin_unlock(&dentry->d_parent->d_lock);
if (target->d_parent != target)
spin_unlock(&target->d_parent->d_lock);
+ spin_unlock(&target->d_lock);
+ spin_unlock(&dentry->d_lock);
}
/*
* When switching names, the actual string doesn't strictly have to
* be preserved in the target - because we're dropping the target
* anyway. As such, we can just do a simple memcpy() to copy over
- * the new name before we switch.
- *
- * Note that we have to be a lot more careful about getting the hash
- * switched - we have to switch the hash value properly even if it
- * then no longer matches the actual (corrupted) string of the target.
- * The hash value has to match the hash queue that the dentry is on..
+ * the new name before we switch, unless we are going to rehash
+ * it. Note that if we *do* unhash the target, we are not allowed
+ * to rehash it without giving it a new name/hash key - whether
+ * we swap or overwrite the names here, resulting name won't match
+ * the reality in filesystem; it's only there for d_path() purposes.
+ * Note that all of this is happening under rename_lock, so the
+ * any hash lookup seeing it in the middle of manipulations will
+ * be discarded anyway. So we do not care what happens to the hash
+ * key in that case.
*/
/*
* __d_move - move a dentry
@@ -2506,36 +2517,30 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
d_hash(dentry->d_parent, dentry->d_name.hash));
}
- list_del(&dentry->d_u.d_child);
- list_del(&target->d_u.d_child);
-
/* Switch the names.. */
- switch_names(dentry, target);
- swap(dentry->d_name.hash, target->d_name.hash);
+ switch_names(dentry, target, exchange);
- /* ... and switch the parents */
+ /* ... and switch them in the tree */
if (IS_ROOT(dentry)) {
+ /* splicing a tree */
dentry->d_parent = target->d_parent;
target->d_parent = target;
- INIT_LIST_HEAD(&target->d_u.d_child);
+ list_del_init(&target->d_u.d_child);
+ list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
} else {
+ /* swapping two dentries */
swap(dentry->d_parent, target->d_parent);
-
- /* And add them back to the (new) parent lists */
- list_add(&target->d_u.d_child, &target->d_parent->d_subdirs);
+ list_move(&target->d_u.d_child, &target->d_parent->d_subdirs);
+ list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+ if (exchange)
+ fsnotify_d_move(target);
+ fsnotify_d_move(dentry);
}
- list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
-
write_seqcount_end(&target->d_seq);
write_seqcount_end(&dentry->d_seq);
- dentry_unlock_parents_for_move(dentry, target);
- if (exchange)
- fsnotify_d_move(target);
- spin_unlock(&target->d_lock);
- fsnotify_d_move(dentry);
- spin_unlock(&dentry->d_lock);
+ dentry_unlock_for_move(dentry, target);
}
/*
@@ -2633,45 +2638,6 @@ out_err:
return ret;
}
-/*
- * Prepare an anonymous dentry for life in the superblock's dentry tree as a
- * named dentry in place of the dentry to be replaced.
- * returns with anon->d_lock held!
- */
-static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
-{
- struct dentry *dparent;
-
- dentry_lock_for_move(anon, dentry);
-
- write_seqcount_begin(&dentry->d_seq);
- write_seqcount_begin_nested(&anon->d_seq, DENTRY_D_LOCK_NESTED);
-
- dparent = dentry->d_parent;
-
- switch_names(dentry, anon);
- swap(dentry->d_name.hash, anon->d_name.hash);
-
- dentry->d_parent = dentry;
- list_del_init(&dentry->d_u.d_child);
- anon->d_parent = dparent;
- if (likely(!d_unhashed(anon))) {
- hlist_bl_lock(&anon->d_sb->s_anon);
- __hlist_bl_del(&anon->d_hash);
- anon->d_hash.pprev = NULL;
- hlist_bl_unlock(&anon->d_sb->s_anon);
- }
- list_move(&anon->d_u.d_child, &dparent->d_subdirs);
-
- write_seqcount_end(&dentry->d_seq);
- write_seqcount_end(&anon->d_seq);
-
- dentry_unlock_parents_for_move(anon, dentry);
- spin_unlock(&dentry->d_lock);
-
- /* anon->d_lock still locked, returns locked */
-}
-
/**
* d_splice_alias - splice a disconnected dentry into the tree if one exists
* @inode: the inode which may have a disconnected dentry
@@ -2717,10 +2683,8 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
return ERR_PTR(-EIO);
}
write_seqlock(&rename_lock);
- __d_materialise_dentry(dentry, new);
+ __d_move(new, dentry, false);
write_sequnlock(&rename_lock);
- _d_rehash(new);
- spin_unlock(&new->d_lock);
spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
iput(inode);
@@ -2780,7 +2744,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
} else if (IS_ROOT(alias)) {
/* Is this an anonymous mountpoint that we
* could splice into our tree? */
- __d_materialise_dentry(dentry, alias);
+ __d_move(alias, dentry, false);
write_sequnlock(&rename_lock);
goto found;
} else {
@@ -2807,13 +2771,9 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
actual = __d_instantiate_unique(dentry, inode);
if (!actual)
actual = dentry;
- else
- BUG_ON(!d_unhashed(actual));
- spin_lock(&actual->d_lock);
+ d_rehash(actual);
found:
- _d_rehash(actual);
- spin_unlock(&actual->d_lock);
spin_unlock(&inode->i_lock);
out_nolock:
if (actual == dentry) {
diff --git a/fs/direct-io.c b/fs/direct-io.c
index c3116404ab49..e181b6b2e297 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -158,7 +158,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
{
ssize_t ret;
- ret = iov_iter_get_pages(sdio->iter, dio->pages, DIO_PAGES,
+ ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
&sdio->from);
if (ret < 0 && sdio->blocks_available && (dio->rw & WRITE)) {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index b88edc05c230..170dc41e8bf4 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1067,14 +1067,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);
err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext2_count_free_blocks(sb));
+ ext2_count_free_blocks(sb), GFP_KERNEL);
if (!err) {
err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext2_count_free_inodes(sb));
+ ext2_count_free_inodes(sb), GFP_KERNEL);
}
if (!err) {
err = percpu_counter_init(&sbi->s_dirs_counter,
- ext2_count_dirs(sb));
+ ext2_count_dirs(sb), GFP_KERNEL);
}
if (err) {
ext2_msg(sb, KERN_ERR, "error: insufficient memory");
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 622e88249024..bb0fdacad058 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2039,14 +2039,14 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext3_count_free_blocks(sb));
+ ext3_count_free_blocks(sb), GFP_KERNEL);
if (!err) {
err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext3_count_free_inodes(sb));
+ ext3_count_free_inodes(sb), GFP_KERNEL);
}
if (!err) {
err = percpu_counter_init(&sbi->s_dirs_counter,
- ext3_count_dirs(sb));
+ ext3_count_dirs(sb), GFP_KERNEL);
}
if (err) {
ext3_msg(sb, KERN_ERR, "error: insufficient memory");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0b28b36e7915..05c159218bc2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3892,7 +3892,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
/* Register extent status tree shrinker */
ext4_es_register_shrinker(sbi);
- if ((err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0)) != 0) {
+ err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0, GFP_KERNEL);
+ if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount3;
}
@@ -4106,17 +4107,20 @@ no_journal:
block = ext4_count_free_clusters(sb);
ext4_free_blocks_count_set(sbi->s_es,
EXT4_C2B(sbi, block));
- err = percpu_counter_init(&sbi->s_freeclusters_counter, block);
+ err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
+ GFP_KERNEL);
if (!err) {
unsigned long freei = ext4_count_free_inodes(sb);
sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
- err = percpu_counter_init(&sbi->s_freeinodes_counter, freei);
+ err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
+ GFP_KERNEL);
}
if (!err)
err = percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
+ ext4_count_dirs(sb), GFP_KERNEL);
if (!err)
- err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
+ err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
+ GFP_KERNEL);
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount6;
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ec3b7a5381fa..dd10a031c052 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -72,7 +72,22 @@ out:
return page;
}
-static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+struct page *get_meta_page_ra(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ bool readahead = false;
+ struct page *page;
+
+ page = find_get_page(META_MAPPING(sbi), index);
+ if (!page || (page && !PageUptodate(page)))
+ readahead = true;
+ f2fs_put_page(page, 0);
+
+ if (readahead)
+ ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR);
+ return get_meta_page(sbi, index);
+}
+
+static inline block_t get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
{
switch (type) {
case META_NAT:
@@ -82,6 +97,8 @@ static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
case META_SSA:
case META_CP:
return 0;
+ case META_POR:
+ return MAX_BLKADDR(sbi);
default:
BUG();
}
@@ -90,12 +107,12 @@ static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
/*
* Readahead CP/NAT/SIT/SSA pages
*/
-int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type)
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type)
{
block_t prev_blk_addr = 0;
struct page *page;
- int blkno = start;
- int max_blks = get_max_meta_blks(sbi, type);
+ block_t blkno = start;
+ block_t max_blks = get_max_meta_blks(sbi, type);
struct f2fs_io_info fio = {
.type = META,
@@ -125,7 +142,11 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type)
break;
case META_SSA:
case META_CP:
- /* get ssa/cp block addr */
+ case META_POR:
+ if (unlikely(blkno >= max_blks))
+ goto out;
+ if (unlikely(blkno < SEG0_BLKADDR(sbi)))
+ goto out;
blk_addr = blkno;
break;
default:
@@ -151,8 +172,7 @@ out:
static int f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc)
{
- struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
trace_f2fs_writepage(page, META);
@@ -177,7 +197,7 @@ redirty_out:
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
trace_f2fs_writepages(mapping->host, wbc, META);
@@ -259,15 +279,12 @@ continue_unlock:
static int f2fs_set_meta_page_dirty(struct page *page)
{
- struct address_space *mapping = page->mapping;
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
-
trace_f2fs_set_page_dirty(page, META);
SetPageUptodate(page);
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- inc_page_count(sbi, F2FS_DIRTY_META);
+ inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
return 1;
}
return 0;
@@ -378,7 +395,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
void release_orphan_inode(struct f2fs_sb_info *sbi)
{
spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- f2fs_bug_on(sbi->n_orphans == 0);
+ f2fs_bug_on(sbi, sbi->n_orphans == 0);
sbi->n_orphans--;
spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
}
@@ -398,7 +415,7 @@ void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode = f2fs_iget(sbi->sb, ino);
- f2fs_bug_on(IS_ERR(inode));
+ f2fs_bug_on(sbi, IS_ERR(inode));
clear_nlink(inode);
/* truncate all the data during iput */
@@ -459,7 +476,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
list_for_each_entry(orphan, head, list) {
if (!page) {
page = find_get_page(META_MAPPING(sbi), start_blk++);
- f2fs_bug_on(!page);
+ f2fs_bug_on(sbi, !page);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
@@ -619,7 +636,7 @@ fail_no_cp:
static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
return -EEXIST;
@@ -631,32 +648,38 @@ static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
return 0;
}
-void set_dirty_dir_page(struct inode *inode, struct page *page)
+void update_dirty_page(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dir_inode_entry *new;
int ret = 0;
- if (!S_ISDIR(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
return;
+ if (!S_ISDIR(inode->i_mode)) {
+ inode_inc_dirty_pages(inode);
+ goto out;
+ }
+
new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
new->inode = inode;
INIT_LIST_HEAD(&new->list);
spin_lock(&sbi->dir_inode_lock);
ret = __add_dirty_inode(inode, new);
- inode_inc_dirty_dents(inode);
- SetPagePrivate(page);
+ inode_inc_dirty_pages(inode);
spin_unlock(&sbi->dir_inode_lock);
if (ret)
kmem_cache_free(inode_entry_slab, new);
+out:
+ SetPagePrivate(page);
}
void add_dirty_dir_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dir_inode_entry *new =
f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
int ret = 0;
@@ -674,14 +697,14 @@ void add_dirty_dir_inode(struct inode *inode)
void remove_dirty_dir_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dir_inode_entry *entry;
if (!S_ISDIR(inode->i_mode))
return;
spin_lock(&sbi->dir_inode_lock);
- if (get_dirty_dents(inode) ||
+ if (get_dirty_pages(inode) ||
!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
spin_unlock(&sbi->dir_inode_lock);
return;
@@ -802,11 +825,12 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
finish_wait(&sbi->cp_wait, &wait);
}
-static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
- nid_t last_nid = 0;
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ nid_t last_nid = nm_i->next_scan_nid;
block_t start_blk;
struct page *cp_page;
unsigned int data_sum_blocks, orphan_blocks;
@@ -869,7 +893,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
- if (is_umount) {
+ if (cpc->reason == CP_UMOUNT) {
set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
cp_payload_blks + data_sum_blocks +
@@ -886,6 +910,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
else
clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+ if (sbi->need_fsck)
+ set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
@@ -920,7 +947,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
- if (is_umount) {
+ if (cpc->reason == CP_UMOUNT) {
write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
@@ -960,23 +987,23 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
/*
* We guarantee that this checkpoint procedure will not fail.
*/
-void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
mutex_lock(&sbi->cp_mutex);
- if (!sbi->s_dirty)
+ if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
goto out;
if (unlikely(f2fs_cp_error(sbi)))
goto out;
if (block_operations(sbi))
goto out;
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
f2fs_submit_merged_bio(sbi, DATA, WRITE);
f2fs_submit_merged_bio(sbi, NODE, WRITE);
@@ -992,16 +1019,16 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
/* write cached NAT/SIT entries to NAT/SIT area */
flush_nat_entries(sbi);
- flush_sit_entries(sbi);
+ flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
- do_checkpoint(sbi, is_umount);
+ do_checkpoint(sbi, cpc);
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
out:
mutex_unlock(&sbi->cp_mutex);
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
}
void init_ino_entry_info(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 76de83e25a89..8e58c4cc2cb9 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -85,7 +85,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
bio = bio_alloc(GFP_NOIO, npages);
bio->bi_bdev = sbi->sb->s_bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
bio->bi_private = sbi;
@@ -193,7 +193,7 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
- int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ int bio_blocks = MAX_BIO_BLOCKS(sbi);
io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
io->fio = *fio;
@@ -236,7 +236,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
int reserve_new_block(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return -EPERM;
@@ -258,7 +258,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
int err;
/* if inode_page exists, index should be zero */
- f2fs_bug_on(!need_put && index);
+ f2fs_bug_on(F2FS_I_SB(dn->inode), !need_put && index);
err = get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
@@ -321,7 +321,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
block_t start_blkaddr, end_blkaddr;
int need_update = true;
- f2fs_bug_on(blk_addr == NEW_ADDR);
+ f2fs_bug_on(F2FS_I_SB(dn->inode), blk_addr == NEW_ADDR);
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
dn->ofs_in_node;
@@ -396,7 +396,6 @@ end_update:
struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
@@ -429,7 +428,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
return page;
}
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, dn.data_blkaddr,
sync ? READ_SYNC : READA);
if (err)
return ERR_PTR(err);
@@ -451,7 +450,6 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
*/
struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
@@ -490,7 +488,8 @@ repeat:
return page;
}
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, READ_SYNC);
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
+ dn.data_blkaddr, READ_SYNC);
if (err)
return ERR_PTR(err);
@@ -517,7 +516,6 @@ repeat:
struct page *get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct dnode_of_data dn;
@@ -541,8 +539,8 @@ repeat:
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
} else {
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
- READ_SYNC);
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
+ dn.data_blkaddr, READ_SYNC);
if (err)
goto put_err;
@@ -573,10 +571,12 @@ put_err:
static int __allocate_data_block(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ struct f2fs_inode_info *fi = F2FS_I(dn->inode);
struct f2fs_summary sum;
block_t new_blkaddr;
struct node_info ni;
+ pgoff_t fofs;
int type;
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
@@ -599,6 +599,12 @@ static int __allocate_data_block(struct dnode_of_data *dn)
update_extent_cache(new_blkaddr, dn);
clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
+ /* update i_size */
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ dn->ofs_in_node;
+ if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
+ i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
+
dn->data_blkaddr = new_blkaddr;
return 0;
}
@@ -614,7 +620,6 @@ static int __allocate_data_block(struct dnode_of_data *dn)
static int __get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create, bool fiemap)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
unsigned int blkbits = inode->i_sb->s_blocksize_bits;
unsigned maxblocks = bh_result->b_size >> blkbits;
struct dnode_of_data dn;
@@ -630,8 +635,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
goto out;
if (create) {
- f2fs_balance_fs(sbi);
- f2fs_lock_op(sbi);
+ f2fs_balance_fs(F2FS_I_SB(inode));
+ f2fs_lock_op(F2FS_I_SB(inode));
}
/* When reading holes, we need its node page */
@@ -707,7 +712,7 @@ put_out:
f2fs_put_dnode(&dn);
unlock_out:
if (create)
- f2fs_unlock_op(sbi);
+ f2fs_unlock_op(F2FS_I_SB(inode));
out:
trace_f2fs_get_data_block(inode, iblock, bh_result, err);
return err;
@@ -804,7 +809,7 @@ static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_CACHE_SHIFT;
@@ -846,7 +851,7 @@ write:
if (unlikely(f2fs_cp_error(sbi))) {
SetPageError(page);
unlock_page(page);
- return 0;
+ goto out;
}
if (!wbc->for_reclaim)
@@ -866,7 +871,7 @@ done:
clear_cold_data(page);
out:
- inode_dec_dirty_dents(inode);
+ inode_dec_dirty_pages(inode);
unlock_page(page);
if (need_balance_fs)
f2fs_balance_fs(sbi);
@@ -892,7 +897,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
bool locked = false;
int ret;
long diff;
@@ -904,7 +909,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
return 0;
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
- get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
+ get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
@@ -926,7 +931,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
return ret;
skip_write:
- wbc->pages_skipped += get_dirty_dents(inode);
+ wbc->pages_skipped += get_dirty_pages(inode);
return 0;
}
@@ -945,7 +950,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
struct dnode_of_data dn;
@@ -1047,7 +1052,10 @@ static int f2fs_write_end(struct file *file,
trace_f2fs_write_end(inode, pos, len, copied);
- set_page_dirty(page);
+ if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
+ register_inmem_page(inode, page);
+ else
+ set_page_dirty(page);
if (pos + copied > i_size_read(inode)) {
i_size_write(inode, pos + copied);
@@ -1092,9 +1100,6 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
if (check_direct_IO(inode, rw, iter, offset))
return 0;
- /* clear fsync mark to recover these blocks */
- fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino);
-
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block);
@@ -1110,8 +1115,12 @@ static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
unsigned int length)
{
struct inode *inode = page->mapping->host;
+
+ if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)
+ return;
+
if (PageDirty(page))
- inode_dec_dirty_dents(inode);
+ inode_dec_dirty_pages(inode);
ClearPagePrivate(page);
}
@@ -1133,7 +1142,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- set_dirty_dir_page(inode, page);
+ update_dirty_page(inode, page);
return 1;
}
return 0;
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index fecebdbfd781..0a91ab813a9e 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -93,7 +93,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
total_vblocks = 0;
blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
hblks_per_sec = blks_per_sec / 2;
- for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
dist = abs(vblocks - hblks_per_sec);
bimodal += dist * dist;
@@ -103,7 +103,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
ndirty++;
}
}
- dist = TOTAL_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
+ dist = MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
si->bimodal = bimodal / dist;
if (si->dirty_count)
si->avg_vblocks = total_vblocks / ndirty;
@@ -131,17 +131,17 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* build sit */
si->base_mem += sizeof(struct sit_info);
- si->base_mem += TOTAL_SEGS(sbi) * sizeof(struct seg_entry);
- si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi);
+ si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
+ si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
if (sbi->segs_per_sec > 1)
- si->base_mem += TOTAL_SECS(sbi) * sizeof(struct sec_entry);
+ si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
/* build free segmap */
si->base_mem += sizeof(struct free_segmap_info);
- si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
/* build curseg */
si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
@@ -149,8 +149,8 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* build dirty segmap */
si->base_mem += sizeof(struct dirty_seglist_info);
- si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+ si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
/* build nm */
si->base_mem += sizeof(struct f2fs_nm_info);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 155fb056b7f1..b54f87149c09 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -126,7 +126,7 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
* For the most part, it should be a bug when name_len is zero.
* We stop here for figuring out where the bugs has occurred.
*/
- f2fs_bug_on(!de->name_len);
+ f2fs_bug_on(F2FS_P_SB(dentry_page), !de->name_len);
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
}
@@ -151,7 +151,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
bool room = false;
int max_slots = 0;
- f2fs_bug_on(level > MAX_DIR_HASH_DEPTH);
+ f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
@@ -284,10 +284,9 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
int update_dent_inode(struct inode *inode, const struct qstr *name)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *page;
- page = get_node_page(sbi, inode->i_ino);
+ page = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(page))
return PTR_ERR(page);
@@ -337,7 +336,6 @@ static int make_empty_dir(struct inode *inode,
static struct page *init_inode_metadata(struct inode *inode,
struct inode *dir, const struct qstr *name)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct page *page;
int err;
@@ -360,7 +358,7 @@ static struct page *init_inode_metadata(struct inode *inode,
if (err)
goto put_error;
} else {
- page = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
+ page = get_node_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
return page;
@@ -381,7 +379,7 @@ static struct page *init_inode_metadata(struct inode *inode,
* we should remove this inode from orphan list.
*/
if (inode->i_nlink == 0)
- remove_orphan_inode(sbi, inode->i_ino);
+ remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
inc_nlink(inode);
}
return page;
@@ -571,8 +569,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
{
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
- struct address_space *mapping = page->mapping;
- struct inode *dir = mapping->host;
+ struct inode *dir = page->mapping->host;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
int i;
@@ -594,7 +591,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
if (inode) {
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
down_write(&F2FS_I(inode)->i_sem);
@@ -621,7 +618,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
truncate_hole(dir, page->index, page->index + 1);
clear_page_dirty_for_io(page);
ClearPageUptodate(page);
- inode_dec_dirty_dents(dir);
+ inode_dec_dirty_pages(dir);
}
f2fs_put_page(page, 1);
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e921242186f6..8171e80b2ee9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -21,10 +21,16 @@
#include <linux/sched.h>
#ifdef CONFIG_F2FS_CHECK_FS
-#define f2fs_bug_on(condition) BUG_ON(condition)
+#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
#define f2fs_down_write(x, y) down_write_nest_lock(x, y)
#else
-#define f2fs_bug_on(condition) WARN_ON(condition)
+#define f2fs_bug_on(sbi, condition) \
+ do { \
+ if (unlikely(condition)) { \
+ WARN_ON(1); \
+ sbi->need_fsck = true; \
+ } \
+ } while (0)
#define f2fs_down_write(x, y) down_write(x)
#endif
@@ -90,6 +96,20 @@ enum {
SIT_BITMAP
};
+enum {
+ CP_UMOUNT,
+ CP_SYNC,
+ CP_DISCARD,
+};
+
+struct cp_control {
+ int reason;
+ __u64 trim_start;
+ __u64 trim_end;
+ __u64 trim_minlen;
+ __u64 trimmed;
+};
+
/*
* For CP/NAT/SIT/SSA readahead
*/
@@ -97,7 +117,8 @@ enum {
META_CP,
META_NAT,
META_SIT,
- META_SSA
+ META_SSA,
+ META_POR,
};
/* for the list of ino */
@@ -130,7 +151,9 @@ struct discard_entry {
struct fsync_inode_entry {
struct list_head list; /* list head */
struct inode *inode; /* vfs inode pointer */
- block_t blkaddr; /* block address locating the last inode */
+ block_t blkaddr; /* block address locating the last fsync */
+ block_t last_dentry; /* block address locating the last dentry */
+ block_t last_inode; /* block address locating the last inode */
};
#define nats_in_cursum(sum) (le16_to_cpu(sum->n_nats))
@@ -141,6 +164,9 @@ struct fsync_inode_entry {
#define sit_in_journal(sum, i) (sum->sit_j.entries[i].se)
#define segno_in_journal(sum, i) (sum->sit_j.entries[i].segno)
+#define MAX_NAT_JENTRIES(sum) (NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
+#define MAX_SIT_JENTRIES(sum) (SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
+
static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
{
int before = nats_in_cursum(rs);
@@ -155,11 +181,24 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
return before;
}
+static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
+ int type)
+{
+ if (type == NAT_JOURNAL)
+ return size <= MAX_NAT_JENTRIES(sum);
+ return size <= MAX_SIT_JENTRIES(sum);
+}
+
/*
* ioctl commands
*/
-#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
+#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+
+#define F2FS_IOCTL_MAGIC 0xf5
+#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
+#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
+#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -222,13 +261,16 @@ struct f2fs_inode_info {
/* Use below internally in f2fs*/
unsigned long flags; /* use to pass per-file flags */
struct rw_semaphore i_sem; /* protect fi info */
- atomic_t dirty_dents; /* # of dirty dentry pages */
+ atomic_t dirty_pages; /* # of dirty pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
nid_t i_xattr_nid; /* node id that contains xattrs */
unsigned long long xattr_ver; /* cp version of xattr modification */
struct extent_info ext; /* in-memory extent cache entry */
struct dir_inode_entry *dirty_dir; /* the pointer of dirty dir */
+
+ struct list_head inmem_pages; /* inmemory pages managed by f2fs */
+ struct mutex inmem_lock; /* lock for inmemory pages */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -260,11 +302,10 @@ struct f2fs_nm_info {
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
+ struct radix_tree_root nat_set_root;/* root of the nat set cache */
rwlock_t nat_tree_lock; /* protect nat_tree_lock */
- unsigned int nat_cnt; /* the # of cached nat entries */
struct list_head nat_entries; /* cached nat entry list (clean) */
- struct list_head dirty_nat_entries; /* cached nat entry list (dirty) */
- struct list_head nat_entry_set; /* nat entry set list */
+ unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
/* free node ids management */
@@ -332,18 +373,16 @@ enum {
};
struct flush_cmd {
- struct flush_cmd *next;
struct completion wait;
+ struct llist_node llnode;
int ret;
};
struct flush_cmd_control {
struct task_struct *f2fs_issue_flush; /* flush thread */
wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
- struct flush_cmd *issue_list; /* list for command issue */
- struct flush_cmd *dispatch_list; /* list for command dispatch */
- spinlock_t issue_lock; /* for issue list lock */
- struct flush_cmd *issue_tail; /* list tail of issue list */
+ struct llist_head issue_list; /* list for command issue */
+ struct llist_node *dispatch_list; /* list for command dispatch */
};
struct f2fs_sm_info {
@@ -369,8 +408,11 @@ struct f2fs_sm_info {
int nr_discards; /* # of discards in the list */
int max_discards; /* max. discards to be issued */
+ struct list_head sit_entry_set; /* sit entry set list */
+
unsigned int ipu_policy; /* in-place-update policy */
unsigned int min_ipu_util; /* in-place-update threshold */
+ unsigned int min_fsync_blocks; /* threshold for fsync */
/* for flush command control */
struct flush_cmd_control *cmd_control_info;
@@ -434,6 +476,7 @@ struct f2fs_sb_info {
struct buffer_head *raw_super_buf; /* buffer head of raw sb */
struct f2fs_super_block *raw_super; /* raw super block pointer */
int s_dirty; /* dirty flag for checkpoint */
+ bool need_fsck; /* need fsck.f2fs to fix */
/* for node-related operations */
struct f2fs_nm_info *nm_info; /* node manager */
@@ -539,6 +582,21 @@ static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb)
return sb->s_fs_info;
}
+static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode)
+{
+ return F2FS_SB(inode->i_sb);
+}
+
+static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping)
+{
+ return F2FS_I_SB(mapping->host);
+}
+
+static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page)
+{
+ return F2FS_M_SB(page->mapping);
+}
+
static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
{
return (struct f2fs_super_block *)(sbi->raw_super);
@@ -703,8 +761,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
blkcnt_t count)
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi->total_valid_block_count < (block_t) count);
- f2fs_bug_on(inode->i_blocks < count);
+ f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
+ f2fs_bug_on(sbi, inode->i_blocks < count);
inode->i_blocks -= count;
sbi->total_valid_block_count -= (block_t)count;
spin_unlock(&sbi->stat_lock);
@@ -716,10 +774,11 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
F2FS_SET_SB_DIRT(sbi);
}
-static inline void inode_inc_dirty_dents(struct inode *inode)
+static inline void inode_inc_dirty_pages(struct inode *inode)
{
- inc_page_count(F2FS_SB(inode->i_sb), F2FS_DIRTY_DENTS);
- atomic_inc(&F2FS_I(inode)->dirty_dents);
+ atomic_inc(&F2FS_I(inode)->dirty_pages);
+ if (S_ISDIR(inode->i_mode))
+ inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
}
static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -727,13 +786,15 @@ static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
atomic_dec(&sbi->nr_pages[count_type]);
}
-static inline void inode_dec_dirty_dents(struct inode *inode)
+static inline void inode_dec_dirty_pages(struct inode *inode)
{
- if (!S_ISDIR(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
return;
- dec_page_count(F2FS_SB(inode->i_sb), F2FS_DIRTY_DENTS);
- atomic_dec(&F2FS_I(inode)->dirty_dents);
+ atomic_dec(&F2FS_I(inode)->dirty_pages);
+
+ if (S_ISDIR(inode->i_mode))
+ dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
}
static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
@@ -741,9 +802,9 @@ static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
return atomic_read(&sbi->nr_pages[count_type]);
}
-static inline int get_dirty_dents(struct inode *inode)
+static inline int get_dirty_pages(struct inode *inode)
{
- return atomic_read(&F2FS_I(inode)->dirty_dents);
+ return atomic_read(&F2FS_I(inode)->dirty_pages);
}
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
@@ -848,9 +909,9 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(!sbi->total_valid_block_count);
- f2fs_bug_on(!sbi->total_valid_node_count);
- f2fs_bug_on(!inode->i_blocks);
+ f2fs_bug_on(sbi, !sbi->total_valid_block_count);
+ f2fs_bug_on(sbi, !sbi->total_valid_node_count);
+ f2fs_bug_on(sbi, !inode->i_blocks);
inode->i_blocks--;
sbi->total_valid_node_count--;
@@ -867,7 +928,7 @@ static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi->total_valid_inode_count == sbi->total_node_count);
+ f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count);
sbi->total_valid_inode_count++;
spin_unlock(&sbi->stat_lock);
}
@@ -875,7 +936,7 @@ static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(!sbi->total_valid_inode_count);
+ f2fs_bug_on(sbi, !sbi->total_valid_inode_count);
sbi->total_valid_inode_count--;
spin_unlock(&sbi->stat_lock);
}
@@ -891,7 +952,7 @@ static inline void f2fs_put_page(struct page *page, int unlock)
return;
if (unlock) {
- f2fs_bug_on(!PageLocked(page));
+ f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
unlock_page(page);
}
page_cache_release(page);
@@ -998,7 +1059,9 @@ enum {
FI_INLINE_DATA, /* used for inline data*/
FI_APPEND_WRITE, /* inode has appended data */
FI_UPDATE_WRITE, /* inode has in-place-update data */
- FI_NEED_IPU, /* used fo ipu for fdatasync */
+ FI_NEED_IPU, /* used for ipu per file */
+ FI_ATOMIC_FILE, /* indicate atomic file */
+ FI_VOLATILE_FILE, /* indicate volatile file */
};
static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -1085,6 +1148,16 @@ static inline int f2fs_has_inline_data(struct inode *inode)
return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA);
}
+static inline bool f2fs_is_atomic_file(struct inode *inode)
+{
+ return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE);
+}
+
+static inline bool f2fs_is_volatile_file(struct inode *inode)
+{
+ return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
+}
+
static inline void *inline_data_addr(struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
@@ -1141,6 +1214,7 @@ void update_inode(struct inode *, struct page *);
void update_inode_page(struct inode *);
int f2fs_write_inode(struct inode *, struct writeback_control *);
void f2fs_evict_inode(struct inode *);
+void handle_failed_inode(struct inode *);
/*
* namei.c
@@ -1188,9 +1262,9 @@ struct dnode_of_data;
struct node_info;
bool available_free_memory(struct f2fs_sb_info *, int);
-int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
-bool fsync_mark_done(struct f2fs_sb_info *, nid_t);
-void fsync_mark_clear(struct f2fs_sb_info *, nid_t);
+bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
+bool has_fsynced_inode(struct f2fs_sb_info *, nid_t);
+bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
@@ -1221,6 +1295,8 @@ void destroy_node_manager_caches(void);
/*
* segment.c
*/
+void register_inmem_page(struct inode *, struct page *);
+void commit_inmem_pages(struct inode *, bool);
void f2fs_balance_fs(struct f2fs_sb_info *);
void f2fs_balance_fs_bg(struct f2fs_sb_info *);
int f2fs_issue_flush(struct f2fs_sb_info *);
@@ -1229,9 +1305,11 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *);
void invalidate_blocks(struct f2fs_sb_info *, block_t);
void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
void clear_prefree_segments(struct f2fs_sb_info *);
+void release_discard_addrs(struct f2fs_sb_info *);
void discard_next_dnode(struct f2fs_sb_info *, block_t);
int npages_for_summary_flush(struct f2fs_sb_info *);
void allocate_new_segments(struct f2fs_sb_info *);
+int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
void write_meta_page(struct f2fs_sb_info *, struct page *);
void write_node_page(struct f2fs_sb_info *, struct page *,
@@ -1248,7 +1326,7 @@ void write_data_summaries(struct f2fs_sb_info *, block_t);
void write_node_summaries(struct f2fs_sb_info *, block_t);
int lookup_journal_in_cursum(struct f2fs_summary_block *,
int, unsigned int, int);
-void flush_sit_entries(struct f2fs_sb_info *);
+void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
int build_segment_manager(struct f2fs_sb_info *);
void destroy_segment_manager(struct f2fs_sb_info *);
int __init create_segment_manager_caches(void);
@@ -1259,7 +1337,8 @@ void destroy_segment_manager_caches(void);
*/
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
-int ra_meta_pages(struct f2fs_sb_info *, int, int, int);
+struct page *get_meta_page_ra(struct f2fs_sb_info *, pgoff_t);
+int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
@@ -1271,11 +1350,11 @@ void add_orphan_inode(struct f2fs_sb_info *, nid_t);
void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
void recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
-void set_dirty_dir_page(struct inode *, struct page *);
+void update_dirty_page(struct inode *, struct page *);
void add_dirty_dir_inode(struct inode *);
void remove_dirty_dir_inode(struct inode *);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, bool);
+void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
void init_ino_entry_info(struct f2fs_sb_info *);
int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
@@ -1359,12 +1438,12 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
#define stat_inc_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
- ((F2FS_SB(inode->i_sb))->inline_inode++); \
+ ((F2FS_I_SB(inode))->inline_inode++); \
} while (0)
#define stat_dec_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
- ((F2FS_SB(inode->i_sb))->inline_inode--); \
+ ((F2FS_I_SB(inode))->inline_inode--); \
} while (0)
#define stat_inc_seg_type(sbi, curseg) \
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 060aee65aee8..8e68bb64f835 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -33,7 +33,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int err;
@@ -117,7 +117,7 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
static inline bool need_do_checkpoint(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
bool need_cp = false;
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
@@ -138,7 +138,8 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_inode_info *fi = F2FS_I(inode);
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ nid_t ino = inode->i_ino;
int ret = 0;
bool need_cp = false;
struct writeback_control wbc = {
@@ -153,12 +154,11 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
trace_f2fs_sync_file_enter(inode);
/* if fdatasync is triggered, let's do in-place-update */
- if (datasync)
+ if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(fi, FI_NEED_IPU);
-
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (datasync)
- clear_inode_flag(fi, FI_NEED_IPU);
+ clear_inode_flag(fi, FI_NEED_IPU);
+
if (ret) {
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
return ret;
@@ -168,13 +168,22 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
- !exist_written_data(sbi, inode->i_ino, APPEND_INO)) {
+ !exist_written_data(sbi, ino, APPEND_INO)) {
+ struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
+
+ /* But we need to avoid that there are some inode updates */
+ if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) {
+ f2fs_put_page(i, 0);
+ goto go_write;
+ }
+ f2fs_put_page(i, 0);
+
if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
- exist_written_data(sbi, inode->i_ino, UPDATE_INO))
+ exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
-
+go_write:
/* guarantee free sections for fsync */
f2fs_balance_fs(sbi);
@@ -207,26 +216,28 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
up_write(&fi->i_sem);
}
} else {
- /* if there is no written node page, write its inode page */
- while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
- if (fsync_mark_done(sbi, inode->i_ino))
- goto out;
+sync_nodes:
+ sync_node_pages(sbi, ino, &wbc);
+
+ if (need_inode_block_update(sbi, ino)) {
mark_inode_dirty_sync(inode);
ret = f2fs_write_inode(inode, NULL);
if (ret)
goto out;
+ goto sync_nodes;
}
- ret = wait_on_node_pages_writeback(sbi, inode->i_ino);
+
+ ret = wait_on_node_pages_writeback(sbi, ino);
if (ret)
goto out;
/* once recovery info is written, don't need to tack this */
- remove_dirty_inode(sbi, inode->i_ino, APPEND_INO);
+ remove_dirty_inode(sbi, ino, APPEND_INO);
clear_inode_flag(fi, FI_APPEND_WRITE);
flush_out:
- remove_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
+ remove_dirty_inode(sbi, ino, UPDATE_INO);
clear_inode_flag(fi, FI_UPDATE_WRITE);
- ret = f2fs_issue_flush(F2FS_SB(inode->i_sb));
+ ret = f2fs_issue_flush(F2FS_I_SB(inode));
}
out:
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
@@ -353,6 +364,8 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
maxbytes, i_size_read(inode));
case SEEK_DATA:
case SEEK_HOLE:
+ if (offset < 0)
+ return -ENXIO;
return f2fs_seek_block(file, offset, whence);
}
@@ -369,7 +382,7 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
int nr_free = 0, ofs = dn->ofs_in_node;
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
__le32 *addr;
@@ -432,7 +445,7 @@ out:
int truncate_blocks(struct inode *inode, u64 from, bool lock)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int blocksize = inode->i_sb->s_blocksize;
struct dnode_of_data dn;
pgoff_t free_from;
@@ -463,7 +476,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
count -= dn.ofs_in_node;
- f2fs_bug_on(count < 0);
+ f2fs_bug_on(sbi, count < 0);
if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
truncate_data_blocks_range(&dn, count);
@@ -547,15 +560,22 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
if (err)
return err;
- if ((attr->ia_valid & ATTR_SIZE) &&
- attr->ia_size != i_size_read(inode)) {
+ if (attr->ia_valid & ATTR_SIZE) {
err = f2fs_convert_inline_data(inode, attr->ia_size, NULL);
if (err)
return err;
- truncate_setsize(inode, attr->ia_size);
- f2fs_truncate(inode);
- f2fs_balance_fs(F2FS_SB(inode->i_sb));
+ if (attr->ia_size != i_size_read(inode)) {
+ truncate_setsize(inode, attr->ia_size);
+ f2fs_truncate(inode);
+ f2fs_balance_fs(F2FS_I_SB(inode));
+ } else {
+ /*
+ * giving a chance to truncate blocks past EOF which
+ * are fallocated with FALLOC_FL_KEEP_SIZE.
+ */
+ f2fs_truncate(inode);
+ }
}
__setattr_copy(inode, attr);
@@ -589,7 +609,7 @@ const struct inode_operations f2fs_file_inode_operations = {
static void fill_zero(struct inode *inode, pgoff_t index,
loff_t start, loff_t len)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
if (!len)
@@ -638,6 +658,13 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
loff_t off_start, off_end;
int ret = 0;
+ if (!S_ISREG(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ /* skip punching hole beyond i_size */
+ if (offset >= inode->i_size)
+ return ret;
+
ret = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL);
if (ret)
return ret;
@@ -661,7 +688,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (pg_start < pg_end) {
struct address_space *mapping = inode->i_mapping;
loff_t blk_start, blk_end;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
f2fs_balance_fs(sbi);
@@ -682,7 +709,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
static int expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
@@ -778,61 +805,157 @@ static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
return flags & F2FS_OTHER_FLMASK;
}
-long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ return put_user(flags, (int __user *)arg);
+}
+
+static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int flags;
+ unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ unsigned int oldflags;
int ret;
- switch (cmd) {
- case F2FS_IOC_GETFLAGS:
- flags = fi->i_flags & FS_FL_USER_VISIBLE;
- return put_user(flags, (int __user *) arg);
- case F2FS_IOC_SETFLAGS:
- {
- unsigned int oldflags;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
+ if (!inode_owner_or_capable(inode)) {
+ ret = -EACCES;
+ goto out;
+ }
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out;
- }
+ if (get_user(flags, (int __user *)arg)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ flags = f2fs_mask_flags(inode->i_mode, flags);
+
+ mutex_lock(&inode->i_mutex);
- if (get_user(flags, (int __user *) arg)) {
- ret = -EFAULT;
+ oldflags = fi->i_flags;
+
+ if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
+ if (!capable(CAP_LINUX_IMMUTABLE)) {
+ mutex_unlock(&inode->i_mutex);
+ ret = -EPERM;
goto out;
}
+ }
- flags = f2fs_mask_flags(inode->i_mode, flags);
+ flags = flags & FS_FL_USER_MODIFIABLE;
+ flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
+ fi->i_flags = flags;
+ mutex_unlock(&inode->i_mutex);
- mutex_lock(&inode->i_mutex);
+ f2fs_set_inode_flags(inode);
+ inode->i_ctime = CURRENT_TIME;
+ mark_inode_dirty(inode);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
- oldflags = fi->i_flags;
+static int f2fs_ioc_start_atomic_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
- if (!capable(CAP_LINUX_IMMUTABLE)) {
- mutex_unlock(&inode->i_mutex);
- ret = -EPERM;
- goto out;
- }
- }
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
- flags = flags & FS_FL_USER_MODIFIABLE;
- flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
- fi->i_flags = flags;
- mutex_unlock(&inode->i_mutex);
+ f2fs_balance_fs(sbi);
- f2fs_set_inode_flags(inode);
- inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
-out:
- mnt_drop_write_file(filp);
+ set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+
+ return f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL);
+}
+
+static int f2fs_ioc_commit_atomic_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (f2fs_is_volatile_file(inode))
+ return 0;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
return ret;
- }
+
+ if (f2fs_is_atomic_file(inode))
+ commit_inmem_pages(inode, false);
+
+ ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_start_volatile_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ return 0;
+}
+
+static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct super_block *sb = inode->i_sb;
+ struct request_queue *q = bdev_get_queue(sb->s_bdev);
+ struct fstrim_range range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&range, (struct fstrim_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ range.minlen = max((unsigned int)range.minlen,
+ q->limits.discard_granularity);
+ ret = f2fs_trim_fs(F2FS_SB(sb), &range);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user((struct fstrim_range __user *)arg, &range,
+ sizeof(range)))
+ return -EFAULT;
+ return 0;
+}
+
+long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case F2FS_IOC_GETFLAGS:
+ return f2fs_ioc_getflags(filp, arg);
+ case F2FS_IOC_SETFLAGS:
+ return f2fs_ioc_setflags(filp, arg);
+ case F2FS_IOC_START_ATOMIC_WRITE:
+ return f2fs_ioc_start_atomic_write(filp);
+ case F2FS_IOC_COMMIT_ATOMIC_WRITE:
+ return f2fs_ioc_commit_atomic_write(filp);
+ case F2FS_IOC_START_VOLATILE_WRITE:
+ return f2fs_ioc_start_volatile_write(filp);
+ case FITRIM:
+ return f2fs_ioc_fitrim(filp, arg);
default:
return -ENOTTY;
}
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 943a31db7cc3..2a8f4acdb86b 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -193,7 +193,7 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
* selected by background GC before.
* Those segments guarantee they have small valid blocks.
*/
- for_each_set_bit(secno, dirty_i->victim_secmap, TOTAL_SECS(sbi)) {
+ for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
if (sec_usage_check(sbi, secno))
continue;
clear_bit(secno, dirty_i->victim_secmap);
@@ -263,14 +263,14 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
unsigned int secno, max_cost;
int nsearched = 0;
+ mutex_lock(&dirty_i->seglist_lock);
+
p.alloc_mode = alloc_mode;
select_policy(sbi, gc_type, type, &p);
p.min_segno = NULL_SEGNO;
p.min_cost = max_cost = get_max_cost(sbi, &p);
- mutex_lock(&dirty_i->seglist_lock);
-
if (p.alloc_mode == LFS && gc_type == FG_GC) {
p.min_segno = check_bg_victims(sbi);
if (p.min_segno != NULL_SEGNO)
@@ -281,9 +281,8 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
unsigned long cost;
unsigned int segno;
- segno = find_next_bit(p.dirty_segmap,
- TOTAL_SEGS(sbi), p.offset);
- if (segno >= TOTAL_SEGS(sbi)) {
+ segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset);
+ if (segno >= MAIN_SEGS(sbi)) {
if (sbi->last_victim[p.gc_mode]) {
sbi->last_victim[p.gc_mode] = 0;
p.offset = 0;
@@ -423,6 +422,12 @@ next_step:
if (IS_ERR(node_page))
continue;
+ /* block may become invalid during get_node_page */
+ if (check_valid_map(sbi, segno, off) == 0) {
+ f2fs_put_page(node_page, 1);
+ continue;
+ }
+
/* set page dirty and write it */
if (gc_type == FG_GC) {
f2fs_wait_on_page_writeback(node_page, NODE);
@@ -531,7 +536,7 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
f2fs_wait_on_page_writeback(page, DATA);
if (clear_page_dirty_for_io(page))
- inode_dec_dirty_dents(inode);
+ inode_dec_dirty_pages(inode);
set_cold_data(page);
do_write_data_page(page, &fio);
clear_cold_data(page);
@@ -688,6 +693,9 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
int gc_type = BG_GC;
int nfree = 0;
int ret = -1;
+ struct cp_control cpc = {
+ .reason = CP_SYNC,
+ };
INIT_LIST_HEAD(&ilist);
gc_more:
@@ -698,7 +706,7 @@ gc_more:
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
gc_type = FG_GC;
- write_checkpoint(sbi, false);
+ write_checkpoint(sbi, &cpc);
}
if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
@@ -723,7 +731,7 @@ gc_more:
goto gc_more;
if (gc_type == FG_GC)
- write_checkpoint(sbi, false);
+ write_checkpoint(sbi, &cpc);
stop:
mutex_unlock(&sbi->gc_mutex);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 3e8ecdf3742b..88036fd75797 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -15,11 +15,13 @@
bool f2fs_may_inline(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
block_t nr_blocks;
loff_t i_size;
- if (!test_opt(sbi, INLINE_DATA))
+ if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
+ return false;
+
+ if (f2fs_is_atomic_file(inode))
return false;
nr_blocks = F2FS_I(inode)->i_xattr_nid ? 3 : 2;
@@ -35,7 +37,6 @@ bool f2fs_may_inline(struct inode *inode)
int f2fs_read_inline_data(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *ipage;
void *src_addr, *dst_addr;
@@ -44,7 +45,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
goto out;
}
- ipage = get_node_page(sbi, inode->i_ino);
+ ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
unlock_page(page);
return PTR_ERR(ipage);
@@ -73,7 +74,7 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
struct dnode_of_data dn;
void *src_addr, *dst_addr;
block_t new_blk_addr;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_io_info fio = {
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
@@ -189,13 +190,12 @@ int f2fs_write_inline_data(struct inode *inode,
void truncate_inline_data(struct inode *inode, u64 from)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *ipage;
if (from >= MAX_INLINE_DATA)
return;
- ipage = get_node_page(sbi, inode->i_ino);
+ ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return;
@@ -209,7 +209,7 @@ void truncate_inline_data(struct inode *inode, u64 from)
bool recover_inline_data(struct inode *inode, struct page *npage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
void *src_addr, *dst_addr;
struct page *ipage;
@@ -229,7 +229,7 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
ipage = get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(IS_ERR(ipage));
+ f2fs_bug_on(sbi, IS_ERR(ipage));
f2fs_wait_on_page_writeback(ipage, NODE);
@@ -243,7 +243,7 @@ process_inline:
if (f2fs_has_inline_data(inode)) {
ipage = get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(IS_ERR(ipage));
+ f2fs_bug_on(sbi, IS_ERR(ipage));
f2fs_wait_on_page_writeback(ipage, NODE);
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 2c39999f3868..0deead4505e7 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -69,7 +69,7 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
static int do_read_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
@@ -218,7 +218,7 @@ void update_inode(struct inode *inode, struct page *node_page)
void update_inode_page(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *node_page;
retry:
node_page = get_node_page(sbi, inode->i_ino);
@@ -238,7 +238,7 @@ retry:
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
@@ -266,9 +266,13 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
*/
void f2fs_evict_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ /* some remained atomic pages should discarded */
+ if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
+ commit_inmem_pages(inode, true);
+
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
@@ -276,7 +280,7 @@ void f2fs_evict_inode(struct inode *inode)
inode->i_ino == F2FS_META_INO(sbi))
goto out_clear;
- f2fs_bug_on(get_dirty_dents(inode));
+ f2fs_bug_on(sbi, get_dirty_pages(inode));
remove_dirty_dir_inode(inode);
if (inode->i_nlink || is_bad_inode(inode))
@@ -306,3 +310,26 @@ no_delete:
out_clear:
clear_inode(inode);
}
+
+/* caller should call f2fs_lock_op() */
+void handle_failed_inode(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ clear_nlink(inode);
+ make_bad_inode(inode);
+ unlock_new_inode(inode);
+
+ i_size_write(inode, 0);
+ if (F2FS_HAS_BLOCKS(inode))
+ f2fs_truncate(inode);
+
+ remove_inode_page(inode);
+ stat_dec_inline_inode(inode);
+
+ alloc_nid_failed(sbi, inode->i_ino);
+ f2fs_unlock_op(sbi);
+
+ /* iput will drop the inode object */
+ iput(inode);
+}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index ee103fd7283c..0d2526e5aa11 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -23,7 +23,7 @@
static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
nid_t ino;
struct inode *inode;
bool nid_free = false;
@@ -102,7 +102,7 @@ static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode,
static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool excl)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
nid_t ino = 0;
int err;
@@ -123,9 +123,9 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ f2fs_unlock_op(sbi);
alloc_nid_done(sbi, ino);
@@ -133,9 +133,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
unlock_new_inode(inode);
return 0;
out:
- clear_nlink(inode);
- iget_failed(inode);
- alloc_nid_failed(sbi, ino);
+ handle_failed_inode(inode);
return err;
}
@@ -143,7 +141,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
int err;
f2fs_balance_fs(sbi);
@@ -154,15 +152,16 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ f2fs_unlock_op(sbi);
d_instantiate(dentry, inode);
return 0;
out:
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
iput(inode);
+ f2fs_unlock_op(sbi);
return err;
}
@@ -203,7 +202,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode = dentry->d_inode;
struct f2fs_dir_entry *de;
struct page *page;
@@ -237,7 +236,7 @@ fail:
static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
size_t symlen = strlen(symname) + 1;
int err;
@@ -253,9 +252,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ f2fs_unlock_op(sbi);
err = page_symlink(inode, symname, symlen);
alloc_nid_done(sbi, inode->i_ino);
@@ -264,15 +263,13 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
unlock_new_inode(inode);
return err;
out:
- clear_nlink(inode);
- iget_failed(inode);
- alloc_nid_failed(sbi, inode->i_ino);
+ handle_failed_inode(inode);
return err;
}
static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err;
@@ -290,9 +287,9 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out_fail;
+ f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
@@ -303,9 +300,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
out_fail:
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
- clear_nlink(inode);
- iget_failed(inode);
- alloc_nid_failed(sbi, inode->i_ino);
+ handle_failed_inode(inode);
return err;
}
@@ -320,7 +315,7 @@ static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t rdev)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err = 0;
@@ -338,25 +333,23 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
return 0;
out:
- clear_nlink(inode);
- iget_failed(inode);
- alloc_nid_failed(sbi, inode->i_ino);
+ handle_failed_inode(inode);
return err;
}
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
- struct f2fs_sb_info *sbi = F2FS_SB(old_dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct page *old_dir_page;
@@ -480,8 +473,7 @@ out:
static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
- struct super_block *sb = old_dir->i_sb;
- struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct page *old_dir_page, *new_dir_page;
@@ -642,7 +634,7 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err;
@@ -678,10 +670,7 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
release_out:
release_orphan_inode(sbi);
out:
- f2fs_unlock_op(sbi);
- clear_nlink(inode);
- iget_failed(inode);
- alloc_nid_failed(sbi, inode->i_ino);
+ handle_failed_inode(inode);
return err;
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 45378196e19a..44b8afef43d9 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -54,7 +54,6 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
static void clear_node_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
unsigned int long flags;
if (PageDirty(page)) {
@@ -65,7 +64,7 @@ static void clear_node_page_dirty(struct page *page)
spin_unlock_irqrestore(&mapping->tree_lock, flags);
clear_page_dirty_for_io(page);
- dec_page_count(sbi, F2FS_DIRTY_NODES);
+ dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES);
}
ClearPageUptodate(page);
}
@@ -92,7 +91,7 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
/* get current nat block page with lock */
src_page = get_meta_page(sbi, src_off);
dst_page = grab_meta_page(sbi, dst_off);
- f2fs_bug_on(PageDirty(src_page));
+ f2fs_bug_on(sbi, PageDirty(src_page));
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
@@ -124,44 +123,99 @@ static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
kmem_cache_free(nat_entry_slab, e);
}
-int is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
+static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
+ struct nat_entry *ne)
+{
+ nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
+ struct nat_entry_set *head;
+
+ if (get_nat_flag(ne, IS_DIRTY))
+ return;
+retry:
+ head = radix_tree_lookup(&nm_i->nat_set_root, set);
+ if (!head) {
+ head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC);
+
+ INIT_LIST_HEAD(&head->entry_list);
+ INIT_LIST_HEAD(&head->set_list);
+ head->set = set;
+ head->entry_cnt = 0;
+
+ if (radix_tree_insert(&nm_i->nat_set_root, set, head)) {
+ cond_resched();
+ goto retry;
+ }
+ }
+ list_move_tail(&ne->list, &head->entry_list);
+ nm_i->dirty_nat_cnt++;
+ head->entry_cnt++;
+ set_nat_flag(ne, IS_DIRTY, true);
+}
+
+static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
+ struct nat_entry *ne)
+{
+ nid_t set = ne->ni.nid / NAT_ENTRY_PER_BLOCK;
+ struct nat_entry_set *head;
+
+ head = radix_tree_lookup(&nm_i->nat_set_root, set);
+ if (head) {
+ list_move_tail(&ne->list, &nm_i->nat_entries);
+ set_nat_flag(ne, IS_DIRTY, false);
+ head->entry_cnt--;
+ nm_i->dirty_nat_cnt--;
+ }
+}
+
+static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
+ nid_t start, unsigned int nr, struct nat_entry_set **ep)
+{
+ return radix_tree_gang_lookup(&nm_i->nat_set_root, (void **)ep,
+ start, nr);
+}
+
+bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- int is_cp = 1;
+ bool is_cp = true;
read_lock(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
- if (e && !e->checkpointed)
- is_cp = 0;
+ if (e && !get_nat_flag(e, IS_CHECKPOINTED))
+ is_cp = false;
read_unlock(&nm_i->nat_tree_lock);
return is_cp;
}
-bool fsync_mark_done(struct f2fs_sb_info *sbi, nid_t nid)
+bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- bool fsync_done = false;
+ bool fsynced = false;
read_lock(&nm_i->nat_tree_lock);
- e = __lookup_nat_cache(nm_i, nid);
- if (e)
- fsync_done = e->fsync_done;
+ e = __lookup_nat_cache(nm_i, ino);
+ if (e && get_nat_flag(e, HAS_FSYNCED_INODE))
+ fsynced = true;
read_unlock(&nm_i->nat_tree_lock);
- return fsync_done;
+ return fsynced;
}
-void fsync_mark_clear(struct f2fs_sb_info *sbi, nid_t nid)
+bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
+ bool need_update = true;
- write_lock(&nm_i->nat_tree_lock);
- e = __lookup_nat_cache(nm_i, nid);
- if (e)
- e->fsync_done = false;
- write_unlock(&nm_i->nat_tree_lock);
+ read_lock(&nm_i->nat_tree_lock);
+ e = __lookup_nat_cache(nm_i, ino);
+ if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
+ (get_nat_flag(e, IS_CHECKPOINTED) ||
+ get_nat_flag(e, HAS_FSYNCED_INODE)))
+ need_update = false;
+ read_unlock(&nm_i->nat_tree_lock);
+ return need_update;
}
static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
@@ -177,7 +231,7 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
}
memset(new, 0, sizeof(struct nat_entry));
nat_set_nid(new, nid);
- new->checkpointed = true;
+ nat_reset_flag(new);
list_add_tail(&new->list, &nm_i->nat_entries);
nm_i->nat_cnt++;
return new;
@@ -216,7 +270,7 @@ retry:
goto retry;
}
e->ni = *ni;
- f2fs_bug_on(ni->blk_addr == NEW_ADDR);
+ f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
} else if (new_blkaddr == NEW_ADDR) {
/*
* when nid is reallocated,
@@ -224,16 +278,16 @@ retry:
* So, reinitialize it with new information.
*/
e->ni = *ni;
- f2fs_bug_on(ni->blk_addr != NULL_ADDR);
+ f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
}
/* sanity check */
- f2fs_bug_on(nat_get_blkaddr(e) != ni->blk_addr);
- f2fs_bug_on(nat_get_blkaddr(e) == NULL_ADDR &&
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr);
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) == NULL_ADDR &&
new_blkaddr == NULL_ADDR);
- f2fs_bug_on(nat_get_blkaddr(e) == NEW_ADDR &&
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
new_blkaddr == NEW_ADDR);
- f2fs_bug_on(nat_get_blkaddr(e) != NEW_ADDR &&
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR &&
nat_get_blkaddr(e) != NULL_ADDR &&
new_blkaddr == NEW_ADDR);
@@ -245,12 +299,17 @@ retry:
/* change address */
nat_set_blkaddr(e, new_blkaddr);
+ if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR)
+ set_nat_flag(e, IS_CHECKPOINTED, false);
__set_nat_cache_dirty(nm_i, e);
/* update fsync_mark if its inode nat entry is still alive */
e = __lookup_nat_cache(nm_i, ni->ino);
- if (e)
- e->fsync_done = fsync_done;
+ if (e) {
+ if (fsync_done && ni->nid == ni->ino)
+ set_nat_flag(e, HAS_FSYNCED_INODE, true);
+ set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
+ }
write_unlock(&nm_i->nat_tree_lock);
}
@@ -411,7 +470,7 @@ got:
*/
int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct page *npage[4];
struct page *parent;
int offset[4];
@@ -504,15 +563,15 @@ release_out:
static void truncate_node(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info ni;
get_node_info(sbi, dn->nid, &ni);
if (dn->inode->i_blocks == 0) {
- f2fs_bug_on(ni.blk_addr != NULL_ADDR);
+ f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR);
goto invalidate;
}
- f2fs_bug_on(ni.blk_addr == NULL_ADDR);
+ f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
/* Deallocate node address */
invalidate_blocks(sbi, ni.blk_addr);
@@ -540,14 +599,13 @@ invalidate:
static int truncate_dnode(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
struct page *page;
if (dn->nid == 0)
return 1;
/* get direct node */
- page = get_node_page(sbi, dn->nid);
+ page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page) && PTR_ERR(page) == -ENOENT)
return 1;
else if (IS_ERR(page))
@@ -564,7 +622,6 @@ static int truncate_dnode(struct dnode_of_data *dn)
static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
int ofs, int depth)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
struct dnode_of_data rdn = *dn;
struct page *page;
struct f2fs_node *rn;
@@ -578,7 +635,7 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr);
- page = get_node_page(sbi, dn->nid);
+ page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page)) {
trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page));
return PTR_ERR(page);
@@ -636,7 +693,6 @@ out_err:
static int truncate_partial_nodes(struct dnode_of_data *dn,
struct f2fs_inode *ri, int *offset, int depth)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
struct page *pages[2];
nid_t nid[3];
nid_t child_nid;
@@ -651,7 +707,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
/* get indirect nodes in the path */
for (i = 0; i < idx + 1; i++) {
/* reference count'll be increased */
- pages[i] = get_node_page(sbi, nid[i]);
+ pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]);
if (IS_ERR(pages[i])) {
err = PTR_ERR(pages[i]);
idx = i - 1;
@@ -696,7 +752,7 @@ fail:
*/
int truncate_inode_blocks(struct inode *inode, pgoff_t from)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err = 0, cont = 1;
int level, offset[4], noffset[4];
unsigned int nofs = 0;
@@ -792,7 +848,7 @@ fail:
int truncate_xattr_node(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t nid = F2FS_I(inode)->i_xattr_nid;
struct dnode_of_data dn;
struct page *npage;
@@ -840,7 +896,8 @@ void remove_inode_page(struct inode *inode)
truncate_data_blocks_range(&dn, 1);
/* 0 is possible, after f2fs_new_inode() has failed */
- f2fs_bug_on(inode->i_blocks != 0 && inode->i_blocks != 1);
+ f2fs_bug_on(F2FS_I_SB(inode),
+ inode->i_blocks != 0 && inode->i_blocks != 1);
/* will put inode & node pages */
truncate_node(&dn);
@@ -860,7 +917,7 @@ struct page *new_inode_page(struct inode *inode)
struct page *new_node_page(struct dnode_of_data *dn,
unsigned int ofs, struct page *ipage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info old_ni, new_ni;
struct page *page;
int err;
@@ -880,7 +937,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
get_node_info(sbi, dn->nid, &old_ni);
/* Reinitialize old_ni with new node page */
- f2fs_bug_on(old_ni.blk_addr != NULL_ADDR);
+ f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR);
new_ni = old_ni;
new_ni.ino = dn->inode->i_ino;
set_node_addr(sbi, &new_ni, NEW_ADDR, false);
@@ -918,7 +975,7 @@ fail:
*/
static int read_node_page(struct page *page, int rw)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct node_info ni;
get_node_info(sbi, page->index, &ni);
@@ -994,7 +1051,7 @@ got_it:
*/
struct page *get_node_page_ra(struct page *parent, int start)
{
- struct f2fs_sb_info *sbi = F2FS_SB(parent->mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
struct blk_plug plug;
struct page *page;
int err, i, end;
@@ -1124,10 +1181,14 @@ continue_unlock:
/* called by fsync() */
if (ino && IS_DNODE(page)) {
- int mark = !is_checkpointed_node(sbi, ino);
set_fsync_mark(page, 1);
- if (IS_INODE(page))
- set_dentry_mark(page, mark);
+ if (IS_INODE(page)) {
+ if (!is_checkpointed_node(sbi, ino) &&
+ !has_fsynced_inode(sbi, ino))
+ set_dentry_mark(page, 1);
+ else
+ set_dentry_mark(page, 0);
+ }
nwritten++;
} else {
set_fsync_mark(page, 0);
@@ -1206,7 +1267,7 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
static int f2fs_write_node_page(struct page *page,
struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
nid_t nid;
block_t new_addr;
struct node_info ni;
@@ -1226,7 +1287,7 @@ static int f2fs_write_node_page(struct page *page,
/* get old block addr of this node page */
nid = nid_of_node(page);
- f2fs_bug_on(page->index != nid);
+ f2fs_bug_on(sbi, page->index != nid);
get_node_info(sbi, nid, &ni);
@@ -1257,7 +1318,7 @@ redirty_out:
static int f2fs_write_node_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff;
trace_f2fs_writepages(mapping->host, wbc, NODE);
@@ -1282,15 +1343,12 @@ skip_write:
static int f2fs_set_node_page_dirty(struct page *page)
{
- struct address_space *mapping = page->mapping;
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
-
trace_f2fs_set_page_dirty(page, NODE);
SetPageUptodate(page);
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- inc_page_count(sbi, F2FS_DIRTY_NODES);
+ inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
SetPagePrivate(page);
return 1;
}
@@ -1301,9 +1359,8 @@ static void f2fs_invalidate_node_page(struct page *page, unsigned int offset,
unsigned int length)
{
struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
if (PageDirty(page))
- dec_page_count(sbi, F2FS_DIRTY_NODES);
+ dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_NODES);
ClearPagePrivate(page);
}
@@ -1356,7 +1413,8 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
read_lock(&nm_i->nat_tree_lock);
ne = __lookup_nat_cache(nm_i, nid);
if (ne &&
- (!ne->checkpointed || nat_get_blkaddr(ne) != NULL_ADDR))
+ (!get_nat_flag(ne, IS_CHECKPOINTED) ||
+ nat_get_blkaddr(ne) != NULL_ADDR))
allocated = true;
read_unlock(&nm_i->nat_tree_lock);
if (allocated)
@@ -1413,7 +1471,7 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
break;
blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
- f2fs_bug_on(blk_addr == NEW_ADDR);
+ f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
if (blk_addr == NULL_ADDR) {
if (add_free_nid(sbi, start_nid, true) < 0)
break;
@@ -1483,12 +1541,12 @@ retry:
/* We should not use stale free nids created by build_free_nids */
if (nm_i->fcnt && !on_build_free_nids(nm_i)) {
- f2fs_bug_on(list_empty(&nm_i->free_nid_list));
+ f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
list_for_each_entry(i, &nm_i->free_nid_list, list)
if (i->state == NID_NEW)
break;
- f2fs_bug_on(i->state != NID_NEW);
+ f2fs_bug_on(sbi, i->state != NID_NEW);
*nid = i->nid;
i->state = NID_ALLOC;
nm_i->fcnt--;
@@ -1514,7 +1572,7 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
spin_lock(&nm_i->free_nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(!i || i->state != NID_ALLOC);
+ f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
__del_from_free_nid_list(nm_i, i);
spin_unlock(&nm_i->free_nid_list_lock);
@@ -1535,7 +1593,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
spin_lock(&nm_i->free_nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(!i || i->state != NID_ALLOC);
+ f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
if (!available_free_memory(sbi, FREE_NIDS)) {
__del_from_free_nid_list(nm_i, i);
need_free = true;
@@ -1551,14 +1609,13 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
void recover_inline_xattr(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
void *src_addr, *dst_addr;
size_t inline_size;
struct page *ipage;
struct f2fs_inode *ri;
- ipage = get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(IS_ERR(ipage));
+ ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage));
ri = F2FS_INODE(page);
if (!(ri->i_inline & F2FS_INLINE_XATTR)) {
@@ -1579,7 +1636,7 @@ update_inode:
void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
nid_t new_xnid = nid_of_node(page);
struct node_info ni;
@@ -1590,7 +1647,7 @@ void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
/* Deallocate node address */
get_node_info(sbi, prev_xnid, &ni);
- f2fs_bug_on(ni.blk_addr == NULL_ADDR);
+ f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
invalidate_blocks(sbi, ni.blk_addr);
dec_valid_node_count(sbi, inode);
set_node_addr(sbi, &ni, NULL_ADDR, false);
@@ -1598,7 +1655,7 @@ void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
recover_xnid:
/* 2: allocate new xattr nid */
if (unlikely(!inc_valid_node_count(sbi, inode)))
- f2fs_bug_on(1);
+ f2fs_bug_on(sbi, 1);
remove_free_nid(NM_I(sbi), new_xnid);
get_node_info(sbi, new_xnid, &ni);
@@ -1691,7 +1748,7 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
struct f2fs_summary *sum_entry;
struct inode *inode = sbi->sb->s_bdev->bd_inode;
block_t addr;
- int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ int bio_blocks = MAX_BIO_BLOCKS(sbi);
struct page *pages[bio_blocks];
int i, idx, last_offset, nrpages, err = 0;
@@ -1733,89 +1790,6 @@ skip:
return err;
}
-static struct nat_entry_set *grab_nat_entry_set(void)
-{
- struct nat_entry_set *nes =
- f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC);
-
- nes->entry_cnt = 0;
- INIT_LIST_HEAD(&nes->set_list);
- INIT_LIST_HEAD(&nes->entry_list);
- return nes;
-}
-
-static void release_nat_entry_set(struct nat_entry_set *nes,
- struct f2fs_nm_info *nm_i)
-{
- f2fs_bug_on(!list_empty(&nes->entry_list));
-
- nm_i->dirty_nat_cnt -= nes->entry_cnt;
- list_del(&nes->set_list);
- kmem_cache_free(nat_entry_set_slab, nes);
-}
-
-static void adjust_nat_entry_set(struct nat_entry_set *nes,
- struct list_head *head)
-{
- struct nat_entry_set *next = nes;
-
- if (list_is_last(&nes->set_list, head))
- return;
-
- list_for_each_entry_continue(next, head, set_list)
- if (nes->entry_cnt <= next->entry_cnt)
- break;
-
- list_move_tail(&nes->set_list, &next->set_list);
-}
-
-static void add_nat_entry(struct nat_entry *ne, struct list_head *head)
-{
- struct nat_entry_set *nes;
- nid_t start_nid = START_NID(ne->ni.nid);
-
- list_for_each_entry(nes, head, set_list) {
- if (nes->start_nid == start_nid) {
- list_move_tail(&ne->list, &nes->entry_list);
- nes->entry_cnt++;
- adjust_nat_entry_set(nes, head);
- return;
- }
- }
-
- nes = grab_nat_entry_set();
-
- nes->start_nid = start_nid;
- list_move_tail(&ne->list, &nes->entry_list);
- nes->entry_cnt++;
- list_add(&nes->set_list, head);
-}
-
-static void merge_nats_in_set(struct f2fs_sb_info *sbi)
-{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct list_head *dirty_list = &nm_i->dirty_nat_entries;
- struct list_head *set_list = &nm_i->nat_entry_set;
- struct nat_entry *ne, *tmp;
-
- write_lock(&nm_i->nat_tree_lock);
- list_for_each_entry_safe(ne, tmp, dirty_list, list) {
- if (nat_get_blkaddr(ne) == NEW_ADDR)
- continue;
- add_nat_entry(ne, set_list);
- nm_i->dirty_nat_cnt++;
- }
- write_unlock(&nm_i->nat_tree_lock);
-}
-
-static bool __has_cursum_space(struct f2fs_summary_block *sum, int size)
-{
- if (nats_in_cursum(sum) + size <= NAT_JOURNAL_ENTRIES)
- return true;
- else
- return false;
-}
-
static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -1850,99 +1824,130 @@ found:
mutex_unlock(&curseg->curseg_mutex);
}
-/*
- * This function is called during the checkpointing process.
- */
-void flush_nat_entries(struct f2fs_sb_info *sbi)
+static void __adjust_nat_entry_set(struct nat_entry_set *nes,
+ struct list_head *head, int max)
{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
- struct nat_entry_set *nes, *tmp;
- struct list_head *head = &nm_i->nat_entry_set;
- bool to_journal = true;
+ struct nat_entry_set *cur;
- /* merge nat entries of dirty list to nat entry set temporarily */
- merge_nats_in_set(sbi);
+ if (nes->entry_cnt >= max)
+ goto add_out;
- /*
- * if there are no enough space in journal to store dirty nat
- * entries, remove all entries from journal and merge them
- * into nat entry set.
- */
- if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt)) {
- remove_nats_in_journal(sbi);
-
- /*
- * merge nat entries of dirty list to nat entry set temporarily
- */
- merge_nats_in_set(sbi);
+ list_for_each_entry(cur, head, set_list) {
+ if (cur->entry_cnt >= nes->entry_cnt) {
+ list_add(&nes->set_list, cur->set_list.prev);
+ return;
+ }
}
+add_out:
+ list_add_tail(&nes->set_list, head);
+}
- if (!nm_i->dirty_nat_cnt)
- return;
+static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
+ struct nat_entry_set *set)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
+ struct f2fs_summary_block *sum = curseg->sum_blk;
+ nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK;
+ bool to_journal = true;
+ struct f2fs_nat_block *nat_blk;
+ struct nat_entry *ne, *cur;
+ struct page *page = NULL;
/*
* there are two steps to flush nat entries:
* #1, flush nat entries to journal in current hot data summary block.
* #2, flush nat entries to nat page.
*/
- list_for_each_entry_safe(nes, tmp, head, set_list) {
- struct f2fs_nat_block *nat_blk;
- struct nat_entry *ne, *cur;
- struct page *page;
- nid_t start_nid = nes->start_nid;
+ if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL))
+ to_journal = false;
- if (to_journal && !__has_cursum_space(sum, nes->entry_cnt))
- to_journal = false;
+ if (to_journal) {
+ mutex_lock(&curseg->curseg_mutex);
+ } else {
+ page = get_next_nat_page(sbi, start_nid);
+ nat_blk = page_address(page);
+ f2fs_bug_on(sbi, !nat_blk);
+ }
+
+ /* flush dirty nats in nat entry set */
+ list_for_each_entry_safe(ne, cur, &set->entry_list, list) {
+ struct f2fs_nat_entry *raw_ne;
+ nid_t nid = nat_get_nid(ne);
+ int offset;
+
+ if (nat_get_blkaddr(ne) == NEW_ADDR)
+ continue;
if (to_journal) {
- mutex_lock(&curseg->curseg_mutex);
+ offset = lookup_journal_in_cursum(sum,
+ NAT_JOURNAL, nid, 1);
+ f2fs_bug_on(sbi, offset < 0);
+ raw_ne = &nat_in_journal(sum, offset);
+ nid_in_journal(sum, offset) = cpu_to_le32(nid);
} else {
- page = get_next_nat_page(sbi, start_nid);
- nat_blk = page_address(page);
- f2fs_bug_on(!nat_blk);
+ raw_ne = &nat_blk->entries[nid - start_nid];
}
+ raw_nat_from_node_info(raw_ne, &ne->ni);
- /* flush dirty nats in nat entry set */
- list_for_each_entry_safe(ne, cur, &nes->entry_list, list) {
- struct f2fs_nat_entry *raw_ne;
- nid_t nid = nat_get_nid(ne);
- int offset;
+ write_lock(&NM_I(sbi)->nat_tree_lock);
+ nat_reset_flag(ne);
+ __clear_nat_cache_dirty(NM_I(sbi), ne);
+ write_unlock(&NM_I(sbi)->nat_tree_lock);
- if (to_journal) {
- offset = lookup_journal_in_cursum(sum,
- NAT_JOURNAL, nid, 1);
- f2fs_bug_on(offset < 0);
- raw_ne = &nat_in_journal(sum, offset);
- nid_in_journal(sum, offset) = cpu_to_le32(nid);
- } else {
- raw_ne = &nat_blk->entries[nid - start_nid];
- }
- raw_nat_from_node_info(raw_ne, &ne->ni);
+ if (nat_get_blkaddr(ne) == NULL_ADDR)
+ add_free_nid(sbi, nid, false);
+ }
- if (nat_get_blkaddr(ne) == NULL_ADDR &&
- add_free_nid(sbi, nid, false) <= 0) {
- write_lock(&nm_i->nat_tree_lock);
- __del_from_nat_cache(nm_i, ne);
- write_unlock(&nm_i->nat_tree_lock);
- } else {
- write_lock(&nm_i->nat_tree_lock);
- __clear_nat_cache_dirty(nm_i, ne);
- write_unlock(&nm_i->nat_tree_lock);
- }
- }
+ if (to_journal)
+ mutex_unlock(&curseg->curseg_mutex);
+ else
+ f2fs_put_page(page, 1);
- if (to_journal)
- mutex_unlock(&curseg->curseg_mutex);
- else
- f2fs_put_page(page, 1);
+ if (!set->entry_cnt) {
+ radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
+ kmem_cache_free(nat_entry_set_slab, set);
+ }
+}
+
+/*
+ * This function is called during the checkpointing process.
+ */
+void flush_nat_entries(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
+ struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct nat_entry_set *setvec[NATVEC_SIZE];
+ struct nat_entry_set *set, *tmp;
+ unsigned int found;
+ nid_t set_idx = 0;
+ LIST_HEAD(sets);
+
+ /*
+ * if there are no enough space in journal to store dirty nat
+ * entries, remove all entries from journal and merge them
+ * into nat entry set.
+ */
+ if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+ remove_nats_in_journal(sbi);
- release_nat_entry_set(nes, nm_i);
+ if (!nm_i->dirty_nat_cnt)
+ return;
+
+ while ((found = __gang_lookup_nat_set(nm_i,
+ set_idx, NATVEC_SIZE, setvec))) {
+ unsigned idx;
+ set_idx = setvec[found - 1]->set + 1;
+ for (idx = 0; idx < found; idx++)
+ __adjust_nat_entry_set(setvec[idx], &sets,
+ MAX_NAT_JENTRIES(sum));
}
- f2fs_bug_on(!list_empty(head));
- f2fs_bug_on(nm_i->dirty_nat_cnt);
+ /* flush dirty nats in nat entry set */
+ list_for_each_entry_safe(set, tmp, &sets, set_list)
+ __flush_nat_entry_set(sbi, set);
+
+ f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
static int init_node_manager(struct f2fs_sb_info *sbi)
@@ -1969,9 +1974,8 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
INIT_LIST_HEAD(&nm_i->free_nid_list);
INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC);
+ INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_ATOMIC);
INIT_LIST_HEAD(&nm_i->nat_entries);
- INIT_LIST_HEAD(&nm_i->dirty_nat_entries);
- INIT_LIST_HEAD(&nm_i->nat_entry_set);
mutex_init(&nm_i->build_lock);
spin_lock_init(&nm_i->free_nid_list_lock);
@@ -2020,14 +2024,14 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
/* destroy free nid list */
spin_lock(&nm_i->free_nid_list_lock);
list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) {
- f2fs_bug_on(i->state == NID_ALLOC);
+ f2fs_bug_on(sbi, i->state == NID_ALLOC);
__del_from_free_nid_list(nm_i, i);
nm_i->fcnt--;
spin_unlock(&nm_i->free_nid_list_lock);
kmem_cache_free(free_nid_slab, i);
spin_lock(&nm_i->free_nid_list_lock);
}
- f2fs_bug_on(nm_i->fcnt);
+ f2fs_bug_on(sbi, nm_i->fcnt);
spin_unlock(&nm_i->free_nid_list_lock);
/* destroy nat cache */
@@ -2039,7 +2043,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
for (idx = 0; idx < found; idx++)
__del_from_nat_cache(nm_i, natvec[idx]);
}
- f2fs_bug_on(nm_i->nat_cnt);
+ f2fs_bug_on(sbi, nm_i->nat_cnt);
write_unlock(&nm_i->nat_tree_lock);
kfree(nm_i->nat_bitmap);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 8a116a407599..8d5e6e0dd840 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -39,10 +39,16 @@ struct node_info {
unsigned char version; /* version of the node */
};
+enum {
+ IS_CHECKPOINTED, /* is it checkpointed before? */
+ HAS_FSYNCED_INODE, /* is the inode fsynced before? */
+ HAS_LAST_FSYNC, /* has the latest node fsync mark? */
+ IS_DIRTY, /* this nat entry is dirty? */
+};
+
struct nat_entry {
struct list_head list; /* for clean or dirty nat list */
- bool checkpointed; /* whether it is checkpointed or not */
- bool fsync_done; /* whether the latest node has fsync mark */
+ unsigned char flag; /* for node information bits */
struct node_info ni; /* in-memory node information */
};
@@ -55,18 +61,32 @@ struct nat_entry {
#define nat_get_version(nat) (nat->ni.version)
#define nat_set_version(nat, v) (nat->ni.version = v)
-#define __set_nat_cache_dirty(nm_i, ne) \
- do { \
- ne->checkpointed = false; \
- list_move_tail(&ne->list, &nm_i->dirty_nat_entries); \
- } while (0)
-#define __clear_nat_cache_dirty(nm_i, ne) \
- do { \
- ne->checkpointed = true; \
- list_move_tail(&ne->list, &nm_i->nat_entries); \
- } while (0)
#define inc_node_version(version) (++version)
+static inline void set_nat_flag(struct nat_entry *ne,
+ unsigned int type, bool set)
+{
+ unsigned char mask = 0x01 << type;
+ if (set)
+ ne->flag |= mask;
+ else
+ ne->flag &= ~mask;
+}
+
+static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
+{
+ unsigned char mask = 0x01 << type;
+ return ne->flag & mask;
+}
+
+static inline void nat_reset_flag(struct nat_entry *ne)
+{
+ /* these states can be set only after checkpoint was done */
+ set_nat_flag(ne, IS_CHECKPOINTED, true);
+ set_nat_flag(ne, HAS_FSYNCED_INODE, false);
+ set_nat_flag(ne, HAS_LAST_FSYNC, true);
+}
+
static inline void node_info_from_raw_nat(struct node_info *ni,
struct f2fs_nat_entry *raw_ne)
{
@@ -90,9 +110,9 @@ enum mem_type {
};
struct nat_entry_set {
- struct list_head set_list; /* link with all nat sets */
+ struct list_head set_list; /* link with other nat sets */
struct list_head entry_list; /* link with dirty nat entries */
- nid_t start_nid; /* start nid of nats in set */
+ nid_t set; /* set number*/
unsigned int entry_cnt; /* the # of nat entries in set */
};
@@ -110,18 +130,19 @@ struct free_nid {
int state; /* in use or not: NID_NEW or NID_ALLOC */
};
-static inline int next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
+static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *fnid;
- if (nm_i->fcnt <= 0)
- return -1;
spin_lock(&nm_i->free_nid_list_lock);
+ if (nm_i->fcnt <= 0) {
+ spin_unlock(&nm_i->free_nid_list_lock);
+ return;
+ }
fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
*nid = fnid->nid;
spin_unlock(&nm_i->free_nid_list_lock);
- return 0;
}
/*
@@ -197,8 +218,7 @@ static inline void copy_node_footer(struct page *dst, struct page *src)
static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
struct f2fs_node *rn = F2FS_NODE(page);
rn->footer.cp_ver = ckpt->checkpoint_ver;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 756c41cd2582..ebd013225788 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -14,6 +14,37 @@
#include "node.h"
#include "segment.h"
+/*
+ * Roll forward recovery scenarios.
+ *
+ * [Term] F: fsync_mark, D: dentry_mark
+ *
+ * 1. inode(x) | CP | inode(x) | dnode(F)
+ * -> Update the latest inode(x).
+ *
+ * 2. inode(x) | CP | inode(F) | dnode(F)
+ * -> No problem.
+ *
+ * 3. inode(x) | CP | dnode(F) | inode(x)
+ * -> Recover to the latest dnode(F), and drop the last inode(x)
+ *
+ * 4. inode(x) | CP | dnode(F) | inode(F)
+ * -> No problem.
+ *
+ * 5. CP | inode(x) | dnode(F)
+ * -> The inode(DF) was missing. Should drop this dnode(F).
+ *
+ * 6. CP | inode(DF) | dnode(F)
+ * -> No problem.
+ *
+ * 7. CP | dnode(F) | inode(DF)
+ * -> If f2fs_iget fails, then goto next to find inode(DF).
+ *
+ * 8. CP | dnode(F) | inode(x)
+ * -> If f2fs_iget fails, then goto next to find inode(DF).
+ * But it will fail due to no inode(DF).
+ */
+
static struct kmem_cache *fsync_entry_slab;
bool space_for_roll_forward(struct f2fs_sb_info *sbi)
@@ -36,7 +67,7 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
return NULL;
}
-static int recover_dentry(struct page *ipage, struct inode *inode)
+static int recover_dentry(struct inode *inode, struct page *ipage)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,7 +106,7 @@ retry:
err = -EEXIST;
goto out_unmap_put;
}
- err = acquire_orphan_inode(F2FS_SB(inode->i_sb));
+ err = acquire_orphan_inode(F2FS_I_SB(inode));
if (err) {
iput(einode);
goto out_unmap_put;
@@ -110,35 +141,28 @@ out:
return err;
}
-static int recover_inode(struct inode *inode, struct page *node_page)
+static void recover_inode(struct inode *inode, struct page *page)
{
- struct f2fs_inode *raw_inode = F2FS_INODE(node_page);
-
- if (!IS_INODE(node_page))
- return 0;
+ struct f2fs_inode *raw = F2FS_INODE(page);
- inode->i_mode = le16_to_cpu(raw_inode->i_mode);
- i_size_write(inode, le64_to_cpu(raw_inode->i_size));
- inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
- inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
- inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
- inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
- inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
-
- if (is_dent_dnode(node_page))
- return recover_dentry(node_page, inode);
+ inode->i_mode = le16_to_cpu(raw->i_mode);
+ i_size_write(inode, le64_to_cpu(raw->i_size));
+ inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
+ inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
+ inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
+ inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+ inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
+ inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
- ino_of_node(node_page), raw_inode->i_name);
- return 0;
+ ino_of_node(page), F2FS_INODE(page)->i_name);
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
- struct page *page;
+ struct page *page = NULL;
block_t blkaddr;
int err = 0;
@@ -146,20 +170,13 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- /* read node page */
- page = alloc_page(GFP_F2FS_ZERO);
- if (!page)
- return -ENOMEM;
- lock_page(page);
-
while (1) {
struct fsync_inode_entry *entry;
- err = f2fs_submit_page_bio(sbi, page, blkaddr, READ_SYNC);
- if (err)
- return err;
+ if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
+ return 0;
- lock_page(page);
+ page = get_meta_page_ra(sbi, blkaddr);
if (cp_ver != cpver_of_node(page))
break;
@@ -180,33 +197,38 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
}
/* add this fsync inode to the list */
- entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS);
+ entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
if (!entry) {
err = -ENOMEM;
break;
}
-
+ /*
+ * CP | dnode(F) | inode(DF)
+ * For this case, we should not give up now.
+ */
entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
if (IS_ERR(entry->inode)) {
err = PTR_ERR(entry->inode);
kmem_cache_free(fsync_entry_slab, entry);
+ if (err == -ENOENT)
+ goto next;
break;
}
list_add_tail(&entry->list, head);
}
entry->blkaddr = blkaddr;
- err = recover_inode(entry->inode, page);
- if (err && err != -ENOENT)
- break;
+ if (IS_INODE(page)) {
+ entry->last_inode = blkaddr;
+ if (is_dent_dnode(page))
+ entry->last_dentry = blkaddr;
+ }
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
+ f2fs_put_page(page, 1);
}
-
- unlock_page(page);
- __free_pages(page, 0);
-
+ f2fs_put_page(page, 1);
return err;
}
@@ -279,16 +301,30 @@ got_it:
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
- /* Deallocate previous index in the node page */
- inode = f2fs_iget(sbi->sb, ino);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
+ if (ino != dn->inode->i_ino) {
+ /* Deallocate previous index in the node page */
+ inode = f2fs_iget(sbi->sb, ino);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+ } else {
+ inode = dn->inode;
+ }
bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
- le16_to_cpu(sum.ofs_in_node);
+ le16_to_cpu(sum.ofs_in_node);
- truncate_hole(inode, bidx, bidx + 1);
- iput(inode);
+ if (ino != dn->inode->i_ino) {
+ truncate_hole(inode, bidx, bidx + 1);
+ iput(inode);
+ } else {
+ struct dnode_of_data tdn;
+ set_new_dnode(&tdn, inode, dn->inode_page, NULL, 0);
+ if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
+ return 0;
+ if (tdn.data_blkaddr != NULL_ADDR)
+ truncate_data_blocks_range(&tdn, 1);
+ f2fs_put_page(tdn.node_page, 1);
+ }
return 0;
}
@@ -331,8 +367,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
f2fs_wait_on_page_writeback(dn.node_page, NODE);
get_node_info(sbi, dn.nid, &ni);
- f2fs_bug_on(ni.ino != ino_of_node(page));
- f2fs_bug_on(ofs_of_node(dn.node_page) != ofs_of_node(page));
+ f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
+ f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page));
for (; start < end; start++) {
block_t src, dest;
@@ -344,7 +380,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
/* We should not get -ENOSPC */
- f2fs_bug_on(err);
+ f2fs_bug_on(sbi, err);
}
/* Check the previous node page having this index */
@@ -386,7 +422,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
- struct page *page;
+ struct page *page = NULL;
int err = 0;
block_t blkaddr;
@@ -394,32 +430,41 @@ static int recover_data(struct f2fs_sb_info *sbi,
curseg = CURSEG_I(sbi, type);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- /* read node page */
- page = alloc_page(GFP_F2FS_ZERO);
- if (!page)
- return -ENOMEM;
-
- lock_page(page);
-
while (1) {
struct fsync_inode_entry *entry;
- err = f2fs_submit_page_bio(sbi, page, blkaddr, READ_SYNC);
- if (err)
- return err;
+ if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
+ break;
- lock_page(page);
+ page = get_meta_page_ra(sbi, blkaddr);
- if (cp_ver != cpver_of_node(page))
+ if (cp_ver != cpver_of_node(page)) {
+ f2fs_put_page(page, 1);
break;
+ }
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry)
goto next;
-
+ /*
+ * inode(x) | CP | inode(x) | dnode(F)
+ * In this case, we can lose the latest inode(x).
+ * So, call recover_inode for the inode update.
+ */
+ if (entry->last_inode == blkaddr)
+ recover_inode(entry->inode, page);
+ if (entry->last_dentry == blkaddr) {
+ err = recover_dentry(entry->inode, page);
+ if (err) {
+ f2fs_put_page(page, 1);
+ break;
+ }
+ }
err = do_recover_data(sbi, entry->inode, page, blkaddr);
- if (err)
+ if (err) {
+ f2fs_put_page(page, 1);
break;
+ }
if (entry->blkaddr == blkaddr) {
iput(entry->inode);
@@ -429,11 +474,8 @@ static int recover_data(struct f2fs_sb_info *sbi,
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
+ f2fs_put_page(page, 1);
}
-
- unlock_page(page);
- __free_pages(page, 0);
-
if (!err)
allocate_new_segments(sbi);
return err;
@@ -474,11 +516,15 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
/* step #2: recover data */
err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
if (!err)
- f2fs_bug_on(!list_empty(&inode_list));
+ f2fs_bug_on(sbi, !list_empty(&inode_list));
out:
destroy_fsync_dnodes(&inode_list);
kmem_cache_destroy(fsync_entry_slab);
+ /* truncate meta pages to be used by the recovery */
+ truncate_inode_pages_range(META_MAPPING(sbi),
+ MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
@@ -494,8 +540,11 @@ out:
set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
mutex_unlock(&sbi->cp_mutex);
} else if (need_writecp) {
+ struct cp_control cpc = {
+ .reason = CP_SYNC,
+ };
mutex_unlock(&sbi->cp_mutex);
- write_checkpoint(sbi, false);
+ write_checkpoint(sbi, &cpc);
} else {
mutex_unlock(&sbi->cp_mutex);
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 0aa337cd5bba..923cb76fdc46 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -25,6 +25,8 @@
#define __reverse_ffz(x) __reverse_ffs(~(x))
static struct kmem_cache *discard_entry_slab;
+static struct kmem_cache *sit_entry_set_slab;
+static struct kmem_cache *inmem_entry_slab;
/*
* __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
@@ -172,6 +174,60 @@ found_middle:
return result + __reverse_ffz(tmp);
}
+void register_inmem_page(struct inode *inode, struct page *page)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct inmem_pages *new;
+
+ new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
+
+ /* add atomic page indices to the list */
+ new->page = page;
+ INIT_LIST_HEAD(&new->list);
+
+ /* increase reference count with clean state */
+ mutex_lock(&fi->inmem_lock);
+ get_page(page);
+ list_add_tail(&new->list, &fi->inmem_pages);
+ mutex_unlock(&fi->inmem_lock);
+}
+
+void commit_inmem_pages(struct inode *inode, bool abort)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct inmem_pages *cur, *tmp;
+ bool submit_bio = false;
+ struct f2fs_io_info fio = {
+ .type = DATA,
+ .rw = WRITE_SYNC,
+ };
+
+ f2fs_balance_fs(sbi);
+ f2fs_lock_op(sbi);
+
+ mutex_lock(&fi->inmem_lock);
+ list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
+ lock_page(cur->page);
+ if (!abort && cur->page->mapping == inode->i_mapping) {
+ f2fs_wait_on_page_writeback(cur->page, DATA);
+ if (clear_page_dirty_for_io(cur->page))
+ inode_dec_dirty_pages(inode);
+ do_write_data_page(cur->page, &fio);
+ submit_bio = true;
+ }
+ f2fs_put_page(cur->page, 1);
+ list_del(&cur->list);
+ kmem_cache_free(inmem_entry_slab, cur);
+ }
+ if (submit_bio)
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ mutex_unlock(&fi->inmem_lock);
+
+ filemap_fdatawait_range(inode->i_mapping, 0, LLONG_MAX);
+ f2fs_unlock_op(sbi);
+}
+
/*
* This function balances dirty node and dentry pages.
* In addition, it controls garbage collection.
@@ -205,24 +261,20 @@ repeat:
if (kthread_should_stop())
return 0;
- spin_lock(&fcc->issue_lock);
- if (fcc->issue_list) {
- fcc->dispatch_list = fcc->issue_list;
- fcc->issue_list = fcc->issue_tail = NULL;
- }
- spin_unlock(&fcc->issue_lock);
-
- if (fcc->dispatch_list) {
+ if (!llist_empty(&fcc->issue_list)) {
struct bio *bio = bio_alloc(GFP_NOIO, 0);
struct flush_cmd *cmd, *next;
int ret;
+ fcc->dispatch_list = llist_del_all(&fcc->issue_list);
+ fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
+
bio->bi_bdev = sbi->sb->s_bdev;
ret = submit_bio_wait(WRITE_FLUSH, bio);
- for (cmd = fcc->dispatch_list; cmd; cmd = next) {
+ llist_for_each_entry_safe(cmd, next,
+ fcc->dispatch_list, llnode) {
cmd->ret = ret;
- next = cmd->next;
complete(&cmd->wait);
}
bio_put(bio);
@@ -230,7 +282,7 @@ repeat:
}
wait_event_interruptible(*q,
- kthread_should_stop() || fcc->issue_list);
+ kthread_should_stop() || !llist_empty(&fcc->issue_list));
goto repeat;
}
@@ -249,15 +301,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL);
init_completion(&cmd.wait);
- cmd.next = NULL;
- spin_lock(&fcc->issue_lock);
- if (fcc->issue_list)
- fcc->issue_tail->next = &cmd;
- else
- fcc->issue_list = &cmd;
- fcc->issue_tail = &cmd;
- spin_unlock(&fcc->issue_lock);
+ llist_add(&cmd.llnode, &fcc->issue_list);
if (!fcc->dispatch_list)
wake_up(&fcc->flush_wait_queue);
@@ -276,8 +321,8 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
if (!fcc)
return -ENOMEM;
- spin_lock_init(&fcc->issue_lock);
init_waitqueue_head(&fcc->flush_wait_queue);
+ init_llist_head(&fcc->issue_list);
SM_I(sbi)->cmd_control_info = fcc;
fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
@@ -317,6 +362,10 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
struct seg_entry *sentry = get_seg_entry(sbi, segno);
enum dirty_type t = sentry->type;
+ if (unlikely(t >= DIRTY)) {
+ f2fs_bug_on(sbi, 1);
+ return;
+ }
if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]++;
}
@@ -376,8 +425,8 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
block_t blkstart, block_t blklen)
{
- sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart);
- sector_t len = SECTOR_FROM_BLOCK(sbi, blklen);
+ sector_t start = SECTOR_FROM_BLOCK(blkstart);
+ sector_t len = SECTOR_FROM_BLOCK(blklen);
trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
}
@@ -392,22 +441,48 @@ void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
}
}
-static void add_discard_addrs(struct f2fs_sb_info *sbi,
- unsigned int segno, struct seg_entry *se)
+static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct list_head *head = &SM_I(sbi)->discard_list;
struct discard_entry *new;
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
int max_blocks = sbi->blocks_per_seg;
+ struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
unsigned long dmap[entries];
unsigned int start = 0, end = -1;
+ bool force = (cpc->reason == CP_DISCARD);
int i;
- if (!test_opt(sbi, DISCARD))
+ if (!force && !test_opt(sbi, DISCARD))
return;
+ if (force && !se->valid_blocks) {
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ /*
+ * if this segment is registered in the prefree list, then
+ * we should skip adding a discard candidate, and let the
+ * checkpoint do that later.
+ */
+ mutex_lock(&dirty_i->seglist_lock);
+ if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) {
+ mutex_unlock(&dirty_i->seglist_lock);
+ cpc->trimmed += sbi->blocks_per_seg;
+ return;
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
+
+ new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
+ INIT_LIST_HEAD(&new->list);
+ new->blkaddr = START_BLOCK(sbi, cpc->trim_start);
+ new->len = sbi->blocks_per_seg;
+ list_add_tail(&new->list, head);
+ SM_I(sbi)->nr_discards += sbi->blocks_per_seg;
+ cpc->trimmed += sbi->blocks_per_seg;
+ return;
+ }
+
/* zero block will be discarded through the prefree list */
if (!se->valid_blocks || se->valid_blocks == max_blocks)
return;
@@ -416,23 +491,39 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi,
for (i = 0; i < entries; i++)
dmap[i] = (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
- while (SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
+ while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
start = __find_rev_next_bit(dmap, max_blocks, end + 1);
if (start >= max_blocks)
break;
end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
+ if (end - start < cpc->trim_minlen)
+ continue;
+
new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
INIT_LIST_HEAD(&new->list);
- new->blkaddr = START_BLOCK(sbi, segno) + start;
+ new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start;
new->len = end - start;
+ cpc->trimmed += end - start;
list_add_tail(&new->list, head);
SM_I(sbi)->nr_discards += end - start;
}
}
+void release_discard_addrs(struct f2fs_sb_info *sbi)
+{
+ struct list_head *head = &(SM_I(sbi)->discard_list);
+ struct discard_entry *entry, *this;
+
+ /* drop caches */
+ list_for_each_entry_safe(entry, this, head, list) {
+ list_del(&entry->list);
+ kmem_cache_free(discard_entry_slab, entry);
+ }
+}
+
/*
* Should call clear_prefree_segments after checkpoint is done.
*/
@@ -440,10 +531,9 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int segno;
- unsigned int total_segs = TOTAL_SEGS(sbi);
mutex_lock(&dirty_i->seglist_lock);
- for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], total_segs)
+ for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], MAIN_SEGS(sbi))
__set_test_and_free(sbi, segno);
mutex_unlock(&dirty_i->seglist_lock);
}
@@ -454,17 +544,17 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi)
struct discard_entry *entry, *this;
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
- unsigned int total_segs = TOTAL_SEGS(sbi);
unsigned int start = 0, end = -1;
mutex_lock(&dirty_i->seglist_lock);
while (1) {
int i;
- start = find_next_bit(prefree_map, total_segs, end + 1);
- if (start >= total_segs)
+ start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1);
+ if (start >= MAIN_SEGS(sbi))
break;
- end = find_next_zero_bit(prefree_map, total_segs, start + 1);
+ end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi),
+ start + 1);
for (i = start; i < end; i++)
clear_bit(i, prefree_map);
@@ -488,11 +578,16 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi)
}
}
-static void __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
+static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap))
+
+ if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap)) {
sit_i->dirty_sentries++;
+ return false;
+ }
+
+ return true;
}
static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
@@ -516,7 +611,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
new_vblocks = se->valid_blocks + del;
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
- f2fs_bug_on((new_vblocks >> (sizeof(unsigned short) << 3) ||
+ f2fs_bug_on(sbi, (new_vblocks >> (sizeof(unsigned short) << 3) ||
(new_vblocks > sbi->blocks_per_seg)));
se->valid_blocks = new_vblocks;
@@ -526,10 +621,10 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
/* Update valid block bitmap */
if (del > 0) {
if (f2fs_set_bit(offset, se->cur_valid_map))
- BUG();
+ f2fs_bug_on(sbi, 1);
} else {
if (!f2fs_clear_bit(offset, se->cur_valid_map))
- BUG();
+ f2fs_bug_on(sbi, 1);
}
if (!f2fs_test_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks += del;
@@ -558,7 +653,7 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
unsigned int segno = GET_SEGNO(sbi, addr);
struct sit_info *sit_i = SIT_I(sbi);
- f2fs_bug_on(addr == NULL_ADDR);
+ f2fs_bug_on(sbi, addr == NULL_ADDR);
if (addr == NEW_ADDR)
return;
@@ -634,7 +729,7 @@ static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
unsigned int segno = curseg->segno + 1;
struct free_segmap_info *free_i = FREE_I(sbi);
- if (segno < TOTAL_SEGS(sbi) && segno % sbi->segs_per_sec)
+ if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec)
return !test_bit(segno, free_i->free_segmap);
return 0;
}
@@ -648,7 +743,7 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int segno, secno, zoneno;
- unsigned int total_zones = TOTAL_SECS(sbi) / sbi->secs_per_zone;
+ unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
unsigned int hint = *newseg / sbi->segs_per_sec;
unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
unsigned int left_start = hint;
@@ -660,18 +755,18 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
segno = find_next_zero_bit(free_i->free_segmap,
- TOTAL_SEGS(sbi), *newseg + 1);
+ MAIN_SEGS(sbi), *newseg + 1);
if (segno - *newseg < sbi->segs_per_sec -
(*newseg % sbi->segs_per_sec))
goto got_it;
}
find_other_zone:
- secno = find_next_zero_bit(free_i->free_secmap, TOTAL_SECS(sbi), hint);
- if (secno >= TOTAL_SECS(sbi)) {
+ secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
+ if (secno >= MAIN_SECS(sbi)) {
if (dir == ALLOC_RIGHT) {
secno = find_next_zero_bit(free_i->free_secmap,
- TOTAL_SECS(sbi), 0);
- f2fs_bug_on(secno >= TOTAL_SECS(sbi));
+ MAIN_SECS(sbi), 0);
+ f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi));
} else {
go_left = 1;
left_start = hint - 1;
@@ -686,8 +781,8 @@ find_other_zone:
continue;
}
left_start = find_next_zero_bit(free_i->free_secmap,
- TOTAL_SECS(sbi), 0);
- f2fs_bug_on(left_start >= TOTAL_SECS(sbi));
+ MAIN_SECS(sbi), 0);
+ f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi));
break;
}
secno = left_start;
@@ -726,7 +821,7 @@ skip_left:
}
got_it:
/* set it as dirty segment in free segmap */
- f2fs_bug_on(test_bit(segno, free_i->free_segmap));
+ f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
__set_inuse(sbi, segno);
*newseg = segno;
write_unlock(&free_i->segmap_lock);
@@ -898,6 +993,37 @@ static const struct segment_allocation default_salloc_ops = {
.allocate_segment = allocate_segment_by_default,
};
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
+{
+ __u64 start = range->start >> sbi->log_blocksize;
+ __u64 end = start + (range->len >> sbi->log_blocksize) - 1;
+ unsigned int start_segno, end_segno;
+ struct cp_control cpc;
+
+ if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) ||
+ range->len < sbi->blocksize)
+ return -EINVAL;
+
+ if (end <= MAIN_BLKADDR(sbi))
+ goto out;
+
+ /* start/end segment number in main_area */
+ start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
+ end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
+ GET_SEGNO(sbi, end);
+ cpc.reason = CP_DISCARD;
+ cpc.trim_start = start_segno;
+ cpc.trim_end = end_segno;
+ cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
+ cpc.trimmed = 0;
+
+ /* do checkpoint to issue discard commands safely */
+ write_checkpoint(sbi, &cpc);
+out:
+ range->len = cpc.trimmed << sbi->log_blocksize;
+ return 0;
+}
+
static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -953,15 +1079,15 @@ static int __get_segment_type_6(struct page *page, enum page_type p_type)
static int __get_segment_type(struct page *page, enum page_type p_type)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
- switch (sbi->active_logs) {
+ switch (F2FS_P_SB(page)->active_logs) {
case 2:
return __get_segment_type_2(page, p_type);
case 4:
return __get_segment_type_4(page, p_type);
}
/* NR_CURSEG_TYPE(6) logs by default */
- f2fs_bug_on(sbi->active_logs != NR_CURSEG_TYPE);
+ f2fs_bug_on(F2FS_P_SB(page),
+ F2FS_P_SB(page)->active_logs != NR_CURSEG_TYPE);
return __get_segment_type_6(page, p_type);
}
@@ -1041,11 +1167,11 @@ void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
void write_data_page(struct page *page, struct dnode_of_data *dn,
block_t *new_blkaddr, struct f2fs_io_info *fio)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
- f2fs_bug_on(dn->data_blkaddr == NULL_ADDR);
+ f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
@@ -1055,9 +1181,7 @@ void write_data_page(struct page *page, struct dnode_of_data *dn,
void rewrite_data_page(struct page *page, block_t old_blkaddr,
struct f2fs_io_info *fio)
{
- struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- f2fs_submit_page_mbio(sbi, page, old_blkaddr, fio);
+ f2fs_submit_page_mbio(F2FS_P_SB(page), page, old_blkaddr, fio);
}
void recover_data_page(struct f2fs_sb_info *sbi,
@@ -1130,8 +1254,9 @@ out:
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
if (PageWriteback(page)) {
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+
if (is_merged_page(sbi, page, type))
f2fs_submit_merged_bio(sbi, type, WRITE);
wait_on_page_writeback(page);
@@ -1400,7 +1525,7 @@ static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- unsigned int offset = SIT_BLOCK_OFFSET(sit_i, segno);
+ unsigned int offset = SIT_BLOCK_OFFSET(segno);
block_t blk_addr = sit_i->sit_base_addr + offset;
check_seg_range(sbi, segno);
@@ -1426,7 +1551,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
/* get current sit block page without lock */
src_page = get_meta_page(sbi, src_off);
dst_page = grab_meta_page(sbi, dst_off);
- f2fs_bug_on(PageDirty(src_page));
+ f2fs_bug_on(sbi, PageDirty(src_page));
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
@@ -1440,101 +1565,192 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
return dst_page;
}
-static bool flush_sits_in_journal(struct f2fs_sb_info *sbi)
+static struct sit_entry_set *grab_sit_entry_set(void)
+{
+ struct sit_entry_set *ses =
+ f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_ATOMIC);
+
+ ses->entry_cnt = 0;
+ INIT_LIST_HEAD(&ses->set_list);
+ return ses;
+}
+
+static void release_sit_entry_set(struct sit_entry_set *ses)
+{
+ list_del(&ses->set_list);
+ kmem_cache_free(sit_entry_set_slab, ses);
+}
+
+static void adjust_sit_entry_set(struct sit_entry_set *ses,
+ struct list_head *head)
+{
+ struct sit_entry_set *next = ses;
+
+ if (list_is_last(&ses->set_list, head))
+ return;
+
+ list_for_each_entry_continue(next, head, set_list)
+ if (ses->entry_cnt <= next->entry_cnt)
+ break;
+
+ list_move_tail(&ses->set_list, &next->set_list);
+}
+
+static void add_sit_entry(unsigned int segno, struct list_head *head)
+{
+ struct sit_entry_set *ses;
+ unsigned int start_segno = START_SEGNO(segno);
+
+ list_for_each_entry(ses, head, set_list) {
+ if (ses->start_segno == start_segno) {
+ ses->entry_cnt++;
+ adjust_sit_entry_set(ses, head);
+ return;
+ }
+ }
+
+ ses = grab_sit_entry_set();
+
+ ses->start_segno = start_segno;
+ ses->entry_cnt++;
+ list_add(&ses->set_list, head);
+}
+
+static void add_sits_in_set(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_sm_info *sm_info = SM_I(sbi);
+ struct list_head *set_list = &sm_info->sit_entry_set;
+ unsigned long *bitmap = SIT_I(sbi)->dirty_sentries_bitmap;
+ unsigned int segno;
+
+ for_each_set_bit(segno, bitmap, MAIN_SEGS(sbi))
+ add_sit_entry(segno, set_list);
+}
+
+static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
struct f2fs_summary_block *sum = curseg->sum_blk;
int i;
- /*
- * If the journal area in the current summary is full of sit entries,
- * all the sit entries will be flushed. Otherwise the sit entries
- * are not able to replace with newly hot sit entries.
- */
- if (sits_in_cursum(sum) >= SIT_JOURNAL_ENTRIES) {
- for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
- unsigned int segno;
- segno = le32_to_cpu(segno_in_journal(sum, i));
- __mark_sit_entry_dirty(sbi, segno);
- }
- update_sits_in_cursum(sum, -sits_in_cursum(sum));
- return true;
+ for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+ unsigned int segno;
+ bool dirtied;
+
+ segno = le32_to_cpu(segno_in_journal(sum, i));
+ dirtied = __mark_sit_entry_dirty(sbi, segno);
+
+ if (!dirtied)
+ add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
}
- return false;
+ update_sits_in_cursum(sum, -sits_in_cursum(sum));
}
/*
* CP calls this function, which flushes SIT entries including sit_journal,
* and moves prefree segs to free segs.
*/
-void flush_sit_entries(struct f2fs_sb_info *sbi)
+void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
struct f2fs_summary_block *sum = curseg->sum_blk;
- unsigned long nsegs = TOTAL_SEGS(sbi);
- struct page *page = NULL;
- struct f2fs_sit_block *raw_sit = NULL;
- unsigned int start = 0, end = 0;
- unsigned int segno;
- bool flushed;
+ struct sit_entry_set *ses, *tmp;
+ struct list_head *head = &SM_I(sbi)->sit_entry_set;
+ bool to_journal = true;
+ struct seg_entry *se;
mutex_lock(&curseg->curseg_mutex);
mutex_lock(&sit_i->sentry_lock);
/*
- * "flushed" indicates whether sit entries in journal are flushed
- * to the SIT area or not.
+ * add and account sit entries of dirty bitmap in sit entry
+ * set temporarily
*/
- flushed = flush_sits_in_journal(sbi);
+ add_sits_in_set(sbi);
- for_each_set_bit(segno, bitmap, nsegs) {
- struct seg_entry *se = get_seg_entry(sbi, segno);
- int sit_offset, offset;
+ /*
+ * if there are no enough space in journal to store dirty sit
+ * entries, remove all entries from journal and add and account
+ * them in sit entry set.
+ */
+ if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL))
+ remove_sits_in_journal(sbi);
- sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
+ if (!sit_i->dirty_sentries)
+ goto out;
- /* add discard candidates */
- if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards)
- add_discard_addrs(sbi, segno, se);
+ /*
+ * there are two steps to flush sit entries:
+ * #1, flush sit entries to journal in current cold data summary block.
+ * #2, flush sit entries to sit page.
+ */
+ list_for_each_entry_safe(ses, tmp, head, set_list) {
+ struct page *page;
+ struct f2fs_sit_block *raw_sit = NULL;
+ unsigned int start_segno = ses->start_segno;
+ unsigned int end = min(start_segno + SIT_ENTRY_PER_BLOCK,
+ (unsigned long)MAIN_SEGS(sbi));
+ unsigned int segno = start_segno;
+
+ if (to_journal &&
+ !__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL))
+ to_journal = false;
+
+ if (!to_journal) {
+ page = get_next_sit_page(sbi, start_segno);
+ raw_sit = page_address(page);
+ }
- if (flushed)
- goto to_sit_page;
+ /* flush dirty sit entries in region of current sit set */
+ for_each_set_bit_from(segno, bitmap, end) {
+ int offset, sit_offset;
- offset = lookup_journal_in_cursum(sum, SIT_JOURNAL, segno, 1);
- if (offset >= 0) {
- segno_in_journal(sum, offset) = cpu_to_le32(segno);
- seg_info_to_raw_sit(se, &sit_in_journal(sum, offset));
- goto flush_done;
- }
-to_sit_page:
- if (!page || (start > segno) || (segno > end)) {
- if (page) {
- f2fs_put_page(page, 1);
- page = NULL;
+ se = get_seg_entry(sbi, segno);
+
+ /* add discard candidates */
+ if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards) {
+ cpc->trim_start = segno;
+ add_discard_addrs(sbi, cpc);
}
- start = START_SEGNO(sit_i, segno);
- end = start + SIT_ENTRY_PER_BLOCK - 1;
+ if (to_journal) {
+ offset = lookup_journal_in_cursum(sum,
+ SIT_JOURNAL, segno, 1);
+ f2fs_bug_on(sbi, offset < 0);
+ segno_in_journal(sum, offset) =
+ cpu_to_le32(segno);
+ seg_info_to_raw_sit(se,
+ &sit_in_journal(sum, offset));
+ } else {
+ sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
+ seg_info_to_raw_sit(se,
+ &raw_sit->entries[sit_offset]);
+ }
- /* read sit block that will be updated */
- page = get_next_sit_page(sbi, start);
- raw_sit = page_address(page);
+ __clear_bit(segno, bitmap);
+ sit_i->dirty_sentries--;
+ ses->entry_cnt--;
}
- /* udpate entry in SIT block */
- seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]);
-flush_done:
- __clear_bit(segno, bitmap);
- sit_i->dirty_sentries--;
+ if (!to_journal)
+ f2fs_put_page(page, 1);
+
+ f2fs_bug_on(sbi, ses->entry_cnt);
+ release_sit_entry_set(ses);
+ }
+
+ f2fs_bug_on(sbi, !list_empty(head));
+ f2fs_bug_on(sbi, sit_i->dirty_sentries);
+out:
+ if (cpc->reason == CP_DISCARD) {
+ for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
+ add_discard_addrs(sbi, cpc);
}
mutex_unlock(&sit_i->sentry_lock);
mutex_unlock(&curseg->curseg_mutex);
- /* writeout last modified SIT block */
- f2fs_put_page(page, 1);
-
set_prefree_as_free_segments(sbi);
}
@@ -1554,16 +1770,16 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = vzalloc(TOTAL_SEGS(sbi) * sizeof(struct seg_entry));
+ sit_i->sentries = vzalloc(MAIN_SEGS(sbi) * sizeof(struct seg_entry));
if (!sit_i->sentries)
return -ENOMEM;
- bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+ bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL);
if (!sit_i->dirty_sentries_bitmap)
return -ENOMEM;
- for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+ for (start = 0; start < MAIN_SEGS(sbi); start++) {
sit_i->sentries[start].cur_valid_map
= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
sit_i->sentries[start].ckpt_valid_map
@@ -1574,7 +1790,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
}
if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = vzalloc(TOTAL_SECS(sbi) *
+ sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) *
sizeof(struct sec_entry));
if (!sit_i->sec_entries)
return -ENOMEM;
@@ -1609,7 +1825,6 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
static int build_free_segmap(struct f2fs_sb_info *sbi)
{
- struct f2fs_sm_info *sm_info = SM_I(sbi);
struct free_segmap_info *free_i;
unsigned int bitmap_size, sec_bitmap_size;
@@ -1620,12 +1835,12 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
SM_I(sbi)->free_info = free_i;
- bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+ bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL);
if (!free_i->free_segmap)
return -ENOMEM;
- sec_bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
+ sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL);
if (!free_i->free_secmap)
return -ENOMEM;
@@ -1635,8 +1850,7 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
memset(free_i->free_secmap, 0xff, sec_bitmap_size);
/* init free segmap information */
- free_i->start_segno =
- (unsigned int) GET_SEGNO_FROM_SEG0(sbi, sm_info->main_blkaddr);
+ free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi));
free_i->free_segments = 0;
free_i->free_sections = 0;
rwlock_init(&free_i->segmap_lock);
@@ -1673,7 +1887,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
int sit_blk_cnt = SIT_BLK_CNT(sbi);
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
- int nrpages = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ int nrpages = MAX_BIO_BLOCKS(sbi);
do {
readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT);
@@ -1681,7 +1895,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
start = start_blk * sit_i->sents_per_block;
end = (start_blk + readed) * sit_i->sents_per_block;
- for (; start < end && start < TOTAL_SEGS(sbi); start++) {
+ for (; start < end && start < MAIN_SEGS(sbi); start++) {
struct seg_entry *se = &sit_i->sentries[start];
struct f2fs_sit_block *sit_blk;
struct f2fs_sit_entry sit;
@@ -1719,7 +1933,7 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
unsigned int start;
int type;
- for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+ for (start = 0; start < MAIN_SEGS(sbi); start++) {
struct seg_entry *sentry = get_seg_entry(sbi, start);
if (!sentry->valid_blocks)
__set_free(sbi, start);
@@ -1736,18 +1950,22 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int segno = 0, offset = 0, total_segs = TOTAL_SEGS(sbi);
+ unsigned int segno = 0, offset = 0;
unsigned short valid_blocks;
while (1) {
/* find dirty segment based on free segmap */
- segno = find_next_inuse(free_i, total_segs, offset);
- if (segno >= total_segs)
+ segno = find_next_inuse(free_i, MAIN_SEGS(sbi), offset);
+ if (segno >= MAIN_SEGS(sbi))
break;
offset = segno + 1;
valid_blocks = get_valid_blocks(sbi, segno, 0);
- if (valid_blocks >= sbi->blocks_per_seg || !valid_blocks)
+ if (valid_blocks == sbi->blocks_per_seg || !valid_blocks)
+ continue;
+ if (valid_blocks > sbi->blocks_per_seg) {
+ f2fs_bug_on(sbi, 1);
continue;
+ }
mutex_lock(&dirty_i->seglist_lock);
__locate_dirty_segment(sbi, segno, DIRTY);
mutex_unlock(&dirty_i->seglist_lock);
@@ -1757,7 +1975,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
static int init_victim_secmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
+ unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
@@ -1778,7 +1996,7 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
SM_I(sbi)->dirty_info = dirty_i;
mutex_init(&dirty_i->seglist_lock);
- bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+ bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
for (i = 0; i < NR_DIRTY_TYPE; i++) {
dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL);
@@ -1802,7 +2020,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
sit_i->min_mtime = LLONG_MAX;
- for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
unsigned int i;
unsigned long long mtime = 0;
@@ -1840,13 +2058,16 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
sm_info->rec_prefree_segments = sm_info->main_segments *
DEF_RECLAIM_PREFREE_SEGMENTS / 100;
- sm_info->ipu_policy = F2FS_IPU_DISABLE;
+ sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
+ sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
INIT_LIST_HEAD(&sm_info->discard_list);
sm_info->nr_discards = 0;
sm_info->max_discards = 0;
+ INIT_LIST_HEAD(&sm_info->sit_entry_set);
+
if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
err = create_flush_cmd_control(sbi);
if (err)
@@ -1942,7 +2163,7 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
return;
if (sit_i->sentries) {
- for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+ for (start = 0; start < MAIN_SEGS(sbi); start++) {
kfree(sit_i->sentries[start].cur_valid_map);
kfree(sit_i->sentries[start].ckpt_valid_map);
}
@@ -1976,11 +2197,30 @@ int __init create_segment_manager_caches(void)
discard_entry_slab = f2fs_kmem_cache_create("discard_entry",
sizeof(struct discard_entry));
if (!discard_entry_slab)
- return -ENOMEM;
+ goto fail;
+
+ sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
+ sizeof(struct nat_entry_set));
+ if (!sit_entry_set_slab)
+ goto destory_discard_entry;
+
+ inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
+ sizeof(struct inmem_pages));
+ if (!inmem_entry_slab)
+ goto destroy_sit_entry_set;
return 0;
+
+destroy_sit_entry_set:
+ kmem_cache_destroy(sit_entry_set_slab);
+destory_discard_entry:
+ kmem_cache_destroy(discard_entry_slab);
+fail:
+ return -ENOMEM;
}
void destroy_segment_manager_caches(void)
{
+ kmem_cache_destroy(sit_entry_set_slab);
kmem_cache_destroy(discard_entry_slab);
+ kmem_cache_destroy(inmem_entry_slab);
}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index ff483257283b..2495bec1c621 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -45,16 +45,26 @@
(secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
sbi->segs_per_sec)) \
-#define START_BLOCK(sbi, segno) \
- (SM_I(sbi)->seg0_blkaddr + \
+#define MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr)
+#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr)
+
+#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
+#define MAIN_SECS(sbi) (sbi->total_sections)
+
+#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count)
+#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
+
+#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
+#define SEGMENT_SIZE(sbi) (1ULL << (sbi->log_blocksize + \
+ sbi->log_blocks_per_seg))
+
+#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \
(GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
+
#define NEXT_FREE_BLKADDR(sbi, curseg) \
(START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)
-#define MAIN_BASE_BLOCK(sbi) (SM_I(sbi)->main_blkaddr)
-
-#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) \
- ((blk_addr) - SM_I(sbi)->seg0_blkaddr)
+#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi))
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \
@@ -77,23 +87,21 @@
#define SIT_ENTRY_OFFSET(sit_i, segno) \
(segno % sit_i->sents_per_block)
-#define SIT_BLOCK_OFFSET(sit_i, segno) \
+#define SIT_BLOCK_OFFSET(segno) \
(segno / SIT_ENTRY_PER_BLOCK)
-#define START_SEGNO(sit_i, segno) \
- (SIT_BLOCK_OFFSET(sit_i, segno) * SIT_ENTRY_PER_BLOCK)
+#define START_SEGNO(segno) \
+ (SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
#define SIT_BLK_CNT(sbi) \
- ((TOTAL_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
+ ((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
#define f2fs_bitmap_size(nr) \
(BITS_TO_LONGS(nr) * sizeof(unsigned long))
-#define TOTAL_SEGS(sbi) (SM_I(sbi)->main_segments)
-#define TOTAL_SECS(sbi) (sbi->total_sections)
-#define SECTOR_FROM_BLOCK(sbi, blk_addr) \
- (((sector_t)blk_addr) << (sbi)->log_sectors_per_block)
-#define SECTOR_TO_BLOCK(sbi, sectors) \
- (sectors >> (sbi)->log_sectors_per_block)
-#define MAX_BIO_BLOCKS(max_hw_blocks) \
- (min((int)max_hw_blocks, BIO_MAX_PAGES))
+#define SECTOR_FROM_BLOCK(blk_addr) \
+ (((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
+#define SECTOR_TO_BLOCK(sectors) \
+ (sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
+#define MAX_BIO_BLOCKS(sbi) \
+ ((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES))
/*
* indicate a block allocation direction: RIGHT and LEFT.
@@ -167,6 +175,11 @@ struct segment_allocation {
void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
};
+struct inmem_pages {
+ struct list_head list;
+ struct page *page;
+};
+
struct sit_info {
const struct segment_allocation *s_ops;
@@ -237,6 +250,12 @@ struct curseg_info {
unsigned int next_segno; /* preallocated segment */
};
+struct sit_entry_set {
+ struct list_head set_list; /* link with all sit sets */
+ unsigned int start_segno; /* start segno of sits in set */
+ unsigned int entry_cnt; /* the # of sit entries in set */
+};
+
/*
* inline functions
*/
@@ -316,7 +335,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
clear_bit(segno, free_i->free_segmap);
free_i->free_segments++;
- next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi), start_segno);
+ next = find_next_bit(free_i->free_segmap, MAIN_SEGS(sbi), start_segno);
if (next >= start_segno + sbi->segs_per_sec) {
clear_bit(secno, free_i->free_secmap);
free_i->free_sections++;
@@ -430,8 +449,10 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi)
static inline bool need_SSR(struct f2fs_sb_info *sbi)
{
- return (prefree_segments(sbi) / sbi->segs_per_sec)
- + free_sections(sbi) < overprovision_sections(sbi);
+ int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+ int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+ return free_sections(sbi) <= (node_secs + 2 * dent_secs +
+ reserved_sections(sbi) + 1);
}
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
@@ -466,48 +487,47 @@ static inline int utilization(struct f2fs_sb_info *sbi)
* F2FS_IPU_UTIL - if FS utilization is over threashold,
* F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over
* threashold,
+ * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
+ * storages. IPU will be triggered only if the # of dirty
+ * pages over min_fsync_blocks.
* F2FS_IPUT_DISABLE - disable IPU. (=default option)
*/
#define DEF_MIN_IPU_UTIL 70
+#define DEF_MIN_FSYNC_BLOCKS 8
enum {
F2FS_IPU_FORCE,
F2FS_IPU_SSR,
F2FS_IPU_UTIL,
F2FS_IPU_SSR_UTIL,
- F2FS_IPU_DISABLE,
+ F2FS_IPU_FSYNC,
};
static inline bool need_inplace_update(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ unsigned int policy = SM_I(sbi)->ipu_policy;
/* IPU can be done only for the user data */
- if (S_ISDIR(inode->i_mode))
+ if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
return false;
- /* this is only set during fdatasync */
- if (is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
+ if (policy & (0x1 << F2FS_IPU_FORCE))
+ return true;
+ if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
+ return true;
+ if (policy & (0x1 << F2FS_IPU_UTIL) &&
+ utilization(sbi) > SM_I(sbi)->min_ipu_util)
+ return true;
+ if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
+ utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
- switch (SM_I(sbi)->ipu_policy) {
- case F2FS_IPU_FORCE:
+ /* this is only set during fdatasync */
+ if (policy & (0x1 << F2FS_IPU_FSYNC) &&
+ is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
return true;
- case F2FS_IPU_SSR:
- if (need_SSR(sbi))
- return true;
- break;
- case F2FS_IPU_UTIL:
- if (utilization(sbi) > SM_I(sbi)->min_ipu_util)
- return true;
- break;
- case F2FS_IPU_SSR_UTIL:
- if (need_SSR(sbi) && utilization(sbi) > SM_I(sbi)->min_ipu_util)
- return true;
- break;
- case F2FS_IPU_DISABLE:
- break;
- }
+
return false;
}
@@ -534,18 +554,13 @@ static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
#ifdef CONFIG_F2FS_CHECK_FS
static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
{
- unsigned int end_segno = SM_I(sbi)->segment_count - 1;
- BUG_ON(segno > end_segno);
+ BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
}
static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
{
- struct f2fs_sm_info *sm_info = SM_I(sbi);
- block_t total_blks = sm_info->segment_count << sbi->log_blocks_per_seg;
- block_t start_addr = sm_info->seg0_blkaddr;
- block_t end_addr = start_addr + total_blks - 1;
- BUG_ON(blk_addr < start_addr);
- BUG_ON(blk_addr > end_addr);
+ BUG_ON(blk_addr < SEG0_BLKADDR(sbi));
+ BUG_ON(blk_addr >= MAX_BLKADDR(sbi));
}
/*
@@ -554,8 +569,6 @@ static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
static inline void check_block_count(struct f2fs_sb_info *sbi,
int segno, struct f2fs_sit_entry *raw_sit)
{
- struct f2fs_sm_info *sm_info = SM_I(sbi);
- unsigned int end_segno = sm_info->segment_count - 1;
bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false;
int valid_blocks = 0;
int cur_pos = 0, next_pos;
@@ -564,7 +577,7 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg);
/* check boundary of a given segment number */
- BUG_ON(segno > end_segno);
+ BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
/* check bitmap with valid block count */
do {
@@ -583,16 +596,39 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
}
#else
-#define check_seg_range(sbi, segno)
-#define verify_block_addr(sbi, blk_addr)
-#define check_block_count(sbi, segno, raw_sit)
+static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+ if (segno > TOTAL_SEGS(sbi) - 1)
+ sbi->need_fsck = true;
+}
+
+static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
+{
+ if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi))
+ sbi->need_fsck = true;
+}
+
+/*
+ * Summary block is always treated as an invalid block
+ */
+static inline void check_block_count(struct f2fs_sb_info *sbi,
+ int segno, struct f2fs_sit_entry *raw_sit)
+{
+ /* check segment usage */
+ if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg)
+ sbi->need_fsck = true;
+
+ /* check boundary of a given segment number */
+ if (segno > TOTAL_SEGS(sbi) - 1)
+ sbi->need_fsck = true;
+}
#endif
static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
unsigned int start)
{
struct sit_info *sit_i = SIT_I(sbi);
- unsigned int offset = SIT_BLOCK_OFFSET(sit_i, start);
+ unsigned int offset = SIT_BLOCK_OFFSET(start);
block_t blk_addr = sit_i->sit_base_addr + offset;
check_seg_range(sbi, start);
@@ -619,7 +655,7 @@ static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi,
static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
{
- unsigned int block_off = SIT_BLOCK_OFFSET(sit_i, start);
+ unsigned int block_off = SIT_BLOCK_OFFSET(start);
if (f2fs_test_bit(block_off, sit_i->sit_bitmap))
f2fs_clear_bit(block_off, sit_i->sit_bitmap);
@@ -666,7 +702,7 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
{
struct block_device *bdev = sbi->sb->s_bdev;
struct request_queue *q = bdev_get_queue(bdev);
- return SECTOR_TO_BLOCK(sbi, queue_max_sectors(q));
+ return SECTOR_TO_BLOCK(queue_max_sectors(q));
}
/*
@@ -683,7 +719,7 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
else if (type == NODE)
return 3 * sbi->blocks_per_seg;
else if (type == META)
- return MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ return MAX_BIO_BLOCKS(sbi);
else
return 0;
}
@@ -706,7 +742,7 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
else if (type == NODE)
desired = 3 * max_hw_blocks(sbi);
else
- desired = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ desired = MAX_BIO_BLOCKS(sbi);
wbc->nr_to_write = desired;
return desired - nr_to_write;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 41bdf511003d..41d6f700f4ee 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -190,6 +190,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
@@ -204,6 +205,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(max_small_discards),
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
+ ATTR_LIST(min_fsync_blocks),
ATTR_LIST(max_victim_search),
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
@@ -366,11 +368,13 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
/* Initialize f2fs-specific inode info */
fi->vfs_inode.i_version = 1;
- atomic_set(&fi->dirty_dents, 0);
+ atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
fi->i_advise = 0;
rwlock_init(&fi->ext.ext_lock);
init_rwsem(&fi->i_sem);
+ INIT_LIST_HEAD(&fi->inmem_pages);
+ mutex_init(&fi->inmem_lock);
set_inode_flag(fi, FI_NEW_INODE);
@@ -432,14 +436,19 @@ static void f2fs_put_super(struct super_block *sb)
stop_gc_thread(sbi);
/* We don't need to do checkpoint when it's clean */
- if (sbi->s_dirty)
- write_checkpoint(sbi, true);
+ if (sbi->s_dirty) {
+ struct cp_control cpc = {
+ .reason = CP_UMOUNT,
+ };
+ write_checkpoint(sbi, &cpc);
+ }
/*
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
release_dirty_inode(sbi);
+ release_discard_addrs(sbi);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -464,8 +473,11 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
trace_f2fs_sync_fs(sb, sync);
if (sync) {
+ struct cp_control cpc = {
+ .reason = CP_SYNC,
+ };
mutex_lock(&sbi->gc_mutex);
- write_checkpoint(sbi, false);
+ write_checkpoint(sbi, &cpc);
mutex_unlock(&sbi->gc_mutex);
} else {
f2fs_balance_fs(sbi);
@@ -616,6 +628,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
+ sbi->mount_opt.opt = 0;
+ sbi->active_logs = NR_CURSEG_TYPE;
+
/* parse mount options */
err = parse_options(sb, data);
if (err)
@@ -786,14 +801,22 @@ static int sanity_check_raw_super(struct super_block *sb,
return 1;
}
- if (le32_to_cpu(raw_super->log_sectorsize) !=
- F2FS_LOG_SECTOR_SIZE) {
- f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
+ /* Currently, support 512/1024/2048/4096 bytes sector size */
+ if (le32_to_cpu(raw_super->log_sectorsize) >
+ F2FS_MAX_LOG_SECTOR_SIZE ||
+ le32_to_cpu(raw_super->log_sectorsize) <
+ F2FS_MIN_LOG_SECTOR_SIZE) {
+ f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize (%u)",
+ le32_to_cpu(raw_super->log_sectorsize));
return 1;
}
- if (le32_to_cpu(raw_super->log_sectors_per_block) !=
- F2FS_LOG_SECTORS_PER_BLOCK) {
- f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
+ if (le32_to_cpu(raw_super->log_sectors_per_block) +
+ le32_to_cpu(raw_super->log_sectorsize) !=
+ F2FS_MAX_LOG_SECTOR_SIZE) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid log sectors per block(%u) log sectorsize(%u)",
+ le32_to_cpu(raw_super->log_sectors_per_block),
+ le32_to_cpu(raw_super->log_sectorsize));
return 1;
}
return 0;
@@ -849,6 +872,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
atomic_set(&sbi->nr_pages[i], 0);
sbi->dir_level = DEF_DIR_LEVEL;
+ sbi->need_fsck = false;
}
/*
@@ -1082,6 +1106,9 @@ try_onemore:
if (err)
goto free_proc;
+ if (!retry)
+ sbi->need_fsck = true;
+
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
err = recover_fsync_data(sbi);
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 728a5dc3dc16..deca8728117b 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -266,7 +266,7 @@ static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
static void *read_all_xattrs(struct inode *inode, struct page *ipage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_xattr_header *header;
size_t size = PAGE_SIZE, inline_size = 0;
void *txattr_addr;
@@ -325,7 +325,7 @@ fail:
static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
void *txattr_addr, struct page *ipage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
size_t inline_size = 0;
void *xattr_addr;
struct page *xpage;
@@ -373,7 +373,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
alloc_nid_failed(sbi, new_nid);
return PTR_ERR(xpage);
}
- f2fs_bug_on(new_nid);
+ f2fs_bug_on(sbi, new_nid);
f2fs_wait_on_page_writeback(xpage, NODE);
} else {
struct dnode_of_data dn;
@@ -596,7 +596,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
const void *value, size_t size,
struct page *ipage, int flags)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err;
/* this case is only from init_inode_metadata */
diff --git a/fs/file_table.c b/fs/file_table.c
index 385bfd31512a..0bab12b20460 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -331,5 +331,5 @@ void __init files_init(unsigned long mempages)
n = (mempages * (PAGE_SIZE / 1024)) / 10;
files_stat.max_files = max_t(unsigned long, n, NR_FILE);
- percpu_counter_init(&nr_files, 0);
+ percpu_counter_init(&nr_files, 0, GFP_KERNEL);
}
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index d3b4539f1651..da032daf0e0d 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -982,6 +982,7 @@ nomem:
submit_op_failed:
clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
spin_unlock(&cookie->lock);
+ fscache_unuse_cookie(object);
kfree(op);
_leave(" [EIO]");
return transit_to(KILL_OBJECT);
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 85332b9d19d1..de33b3fccca6 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -44,6 +44,19 @@ void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *pa
EXPORT_SYMBOL(__fscache_wait_on_page_write);
/*
+ * wait for a page to finish being written to the cache. Put a timeout here
+ * since we might be called recursively via parent fs.
+ */
+static
+bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page)
+{
+ wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0);
+
+ return wait_event_timeout(*wq, !__fscache_check_page_write(cookie, page),
+ HZ);
+}
+
+/*
* decide whether a page can be released, possibly by cancelling a store to it
* - we're allowed to sleep if __GFP_WAIT is flagged
*/
@@ -115,7 +128,10 @@ page_busy:
}
fscache_stat(&fscache_n_store_vmscan_wait);
- __fscache_wait_on_page_write(cookie, page);
+ if (!release_page_wait_timeout(cookie, page))
+ _debug("fscache writeout timeout page: %p{%lx}",
+ page, page->index);
+
gfp &= ~__GFP_WAIT;
goto try_again;
}
@@ -182,7 +198,7 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
{
struct fscache_operation *op;
struct fscache_object *object;
- bool wake_cookie;
+ bool wake_cookie = false;
_enter("%p", cookie);
@@ -212,15 +228,16 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
__fscache_use_cookie(cookie);
if (fscache_submit_exclusive_op(object, op) < 0)
- goto nobufs;
+ goto nobufs_dec;
spin_unlock(&cookie->lock);
fscache_stat(&fscache_n_attr_changed_ok);
fscache_put_operation(op);
_leave(" = 0");
return 0;
-nobufs:
+nobufs_dec:
wake_cookie = __fscache_unuse_cookie(cookie);
+nobufs:
spin_unlock(&cookie->lock);
kfree(op);
if (wake_cookie)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 912061ac4baf..caa8d95b24e8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1305,6 +1305,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
size_t start;
ssize_t ret = iov_iter_get_pages(ii,
&req->pages[req->num_pages],
+ *nbytesp - nbytes,
req->max_pages - req->num_pages,
&start);
if (ret < 0)
diff --git a/fs/internal.h b/fs/internal.h
index e325b4f9c799..b2623200107b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -35,6 +35,11 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
#endif
/*
+ * buffer.c
+ */
+extern void guard_bio_eod(int rw, struct bio *bio);
+
+/*
* char_dev.c
*/
extern void __init chrdev_init(void);
diff --git a/fs/lockd/Makefile b/fs/lockd/Makefile
index ca58d64374ca..9b320cc2a8cf 100644
--- a/fs/lockd/Makefile
+++ b/fs/lockd/Makefile
@@ -5,6 +5,7 @@
obj-$(CONFIG_LOCKD) += lockd.o
lockd-objs-y := clntlock.o clntproc.o clntxdr.o host.o svc.o svclock.o \
- svcshare.o svcproc.o svcsubs.o mon.o xdr.o grace.o
+ svcshare.o svcproc.o svcsubs.o mon.o xdr.o
lockd-objs-$(CONFIG_LOCKD_V4) += clnt4xdr.o xdr4.o svc4proc.o
+lockd-objs-$(CONFIG_PROC_FS) += procfs.o
lockd-objs := $(lockd-objs-y)
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index daa8e7514eae..9106f42c472c 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
msg.rpc_proc = &clnt->cl_procinfo[proc];
status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+ if (status == -ECONNREFUSED) {
+ dprintk("lockd: NSM upcall RPC failed, status=%d, forcing rebind\n",
+ status);
+ rpc_force_rebind(clnt);
+ status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+ }
if (status < 0)
dprintk("lockd: NSM upcall RPC failed, status=%d\n",
status);
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index 5010b55628b4..097bfa3adb1c 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -11,7 +11,6 @@ struct lockd_net {
struct delayed_work grace_period_end;
struct lock_manager lockd_manager;
- struct list_head grace_list;
spinlock_t nsm_clnt_lock;
unsigned int nsm_users;
diff --git a/fs/lockd/procfs.c b/fs/lockd/procfs.c
new file mode 100644
index 000000000000..2a0a98480e39
--- /dev/null
+++ b/fs/lockd/procfs.c
@@ -0,0 +1,92 @@
+/*
+ * Procfs support for lockd
+ *
+ * Copyright (c) 2014 Jeff Layton <jlayton@primarydata.com>
+ */
+
+#include <linux/fs.h>
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+
+#include "netns.h"
+#include "procfs.h"
+
+/*
+ * We only allow strings that start with 'Y', 'y', or '1'.
+ */
+static ssize_t
+nlm_end_grace_write(struct file *file, const char __user *buf, size_t size,
+ loff_t *pos)
+{
+ char *data;
+ struct lockd_net *ln = net_generic(current->nsproxy->net_ns,
+ lockd_net_id);
+
+ if (size < 1)
+ return -EINVAL;
+
+ data = simple_transaction_get(file, buf, size);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ switch(data[0]) {
+ case 'Y':
+ case 'y':
+ case '1':
+ locks_end_grace(&ln->lockd_manager);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return size;
+}
+
+static ssize_t
+nlm_end_grace_read(struct file *file, char __user *buf, size_t size,
+ loff_t *pos)
+{
+ struct lockd_net *ln = net_generic(current->nsproxy->net_ns,
+ lockd_net_id);
+ char resp[3];
+
+ resp[0] = list_empty(&ln->lockd_manager.list) ? 'Y' : 'N';
+ resp[1] = '\n';
+ resp[2] = '\0';
+
+ return simple_read_from_buffer(buf, size, pos, resp, sizeof(resp));
+}
+
+static const struct file_operations lockd_end_grace_operations = {
+ .write = nlm_end_grace_write,
+ .read = nlm_end_grace_read,
+ .llseek = default_llseek,
+ .release = simple_transaction_release,
+ .owner = THIS_MODULE,
+};
+
+int __init
+lockd_create_procfs(void)
+{
+ struct proc_dir_entry *entry;
+
+ entry = proc_mkdir("fs/lockd", NULL);
+ if (!entry)
+ return -ENOMEM;
+ entry = proc_create("nlm_end_grace", S_IRUGO|S_IWUSR, entry,
+ &lockd_end_grace_operations);
+ if (!entry) {
+ remove_proc_entry("fs/lockd", NULL);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+void __exit
+lockd_remove_procfs(void)
+{
+ remove_proc_entry("fs/lockd/nlm_end_grace", NULL);
+ remove_proc_entry("fs/lockd", NULL);
+}
diff --git a/fs/lockd/procfs.h b/fs/lockd/procfs.h
new file mode 100644
index 000000000000..2257a1311027
--- /dev/null
+++ b/fs/lockd/procfs.h
@@ -0,0 +1,28 @@
+/*
+ * Procfs support for lockd
+ *
+ * Copyright (c) 2014 Jeff Layton <jlayton@primarydata.com>
+ */
+#ifndef _LOCKD_PROCFS_H
+#define _LOCKD_PROCFS_H
+
+#include <linux/kconfig.h>
+
+#if IS_ENABLED(CONFIG_PROC_FS)
+int lockd_create_procfs(void);
+void lockd_remove_procfs(void);
+#else
+static inline int
+lockd_create_procfs(void)
+{
+ return 0;
+}
+
+static inline void
+lockd_remove_procfs(void)
+{
+ return;
+}
+#endif /* IS_ENABLED(CONFIG_PROC_FS) */
+
+#endif /* _LOCKD_PROCFS_H */
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index ec9e082f9ecd..d1bb7ecfd201 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -36,6 +36,7 @@
#include <linux/nfs.h>
#include "netns.h"
+#include "procfs.h"
#define NLMDBG_FACILITY NLMDBG_SVC
#define LOCKD_BUFSIZE (1024 + NLMSVC_XDRSIZE)
@@ -304,13 +305,16 @@ static int lockd_start_svc(struct svc_serv *serv)
svc_sock_update_bufs(serv);
serv->sv_maxconn = nlm_max_connections;
- nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, "%s", serv->sv_name);
+ nlmsvc_task = kthread_create(lockd, nlmsvc_rqst, "%s", serv->sv_name);
if (IS_ERR(nlmsvc_task)) {
error = PTR_ERR(nlmsvc_task);
printk(KERN_WARNING
"lockd_up: kthread_run failed, error=%d\n", error);
goto out_task;
}
+ nlmsvc_rqst->rq_task = nlmsvc_task;
+ wake_up_process(nlmsvc_task);
+
dprintk("lockd_up: service started\n");
return 0;
@@ -581,7 +585,7 @@ static int lockd_init_net(struct net *net)
struct lockd_net *ln = net_generic(net, lockd_net_id);
INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
- INIT_LIST_HEAD(&ln->grace_list);
+ INIT_LIST_HEAD(&ln->lockd_manager.list);
spin_lock_init(&ln->nsm_clnt_lock);
return 0;
}
@@ -615,8 +619,15 @@ static int __init init_nlm(void)
err = register_pernet_subsys(&lockd_net_ops);
if (err)
goto err_pernet;
+
+ err = lockd_create_procfs();
+ if (err)
+ goto err_procfs;
+
return 0;
+err_procfs:
+ unregister_pernet_subsys(&lockd_net_ops);
err_pernet:
#ifdef CONFIG_SYSCTL
unregister_sysctl_table(nlm_sysctl_table);
@@ -629,6 +640,7 @@ static void __exit exit_nlm(void)
{
/* FIXME: delete all NLM clients */
nlm_shutdown_hosts();
+ lockd_remove_procfs();
unregister_pernet_subsys(&lockd_net_ops);
#ifdef CONFIG_SYSCTL
unregister_sysctl_table(nlm_sysctl_table);
diff --git a/fs/mpage.c b/fs/mpage.c
index 5f9ed622274f..3e79220babac 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -28,6 +28,7 @@
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/cleancache.h>
+#include "internal.h"
/*
* I/O completion handler for multipage BIOs.
@@ -57,6 +58,7 @@ static void mpage_end_io(struct bio *bio, int err)
static struct bio *mpage_bio_submit(int rw, struct bio *bio)
{
bio->bi_end_io = mpage_end_io;
+ guard_bio_eod(rw, bio);
submit_bio(rw, bio);
return NULL;
}
diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile
index d5815505c020..3ca14c36d08b 100644
--- a/fs/nfs/blocklayout/Makefile
+++ b/fs/nfs/blocklayout/Makefile
@@ -2,4 +2,5 @@
# Makefile for the pNFS block layout driver kernel module
#
obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o
-blocklayoutdriver-objs := blocklayout.o extents.o blocklayoutdev.o blocklayoutdm.o
+
+blocklayoutdriver-y += blocklayout.o dev.o extent_tree.o rpc_pipefs.o
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index cbb1797149d5..5228f201d3d5 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -35,7 +35,6 @@
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/bio.h> /* struct bio */
-#include <linux/buffer_head.h> /* various write calls */
#include <linux/prefetch.h>
#include <linux/pagevec.h>
@@ -50,40 +49,16 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
-static void print_page(struct page *page)
+static bool is_hole(struct pnfs_block_extent *be)
{
- dprintk("PRINTPAGE page %p\n", page);
- dprintk(" PagePrivate %d\n", PagePrivate(page));
- dprintk(" PageUptodate %d\n", PageUptodate(page));
- dprintk(" PageError %d\n", PageError(page));
- dprintk(" PageDirty %d\n", PageDirty(page));
- dprintk(" PageReferenced %d\n", PageReferenced(page));
- dprintk(" PageLocked %d\n", PageLocked(page));
- dprintk(" PageWriteback %d\n", PageWriteback(page));
- dprintk(" PageMappedToDisk %d\n", PageMappedToDisk(page));
- dprintk("\n");
-}
-
-/* Given the be associated with isect, determine if page data needs to be
- * initialized.
- */
-static int is_hole(struct pnfs_block_extent *be, sector_t isect)
-{
- if (be->be_state == PNFS_BLOCK_NONE_DATA)
- return 1;
- else if (be->be_state != PNFS_BLOCK_INVALID_DATA)
- return 0;
- else
- return !bl_is_sector_init(be->be_inval, isect);
-}
-
-/* Given the be associated with isect, determine if page data can be
- * written to disk.
- */
-static int is_writable(struct pnfs_block_extent *be, sector_t isect)
-{
- return (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
- be->be_state == PNFS_BLOCK_INVALID_DATA);
+ switch (be->be_state) {
+ case PNFS_BLOCK_NONE_DATA:
+ return true;
+ case PNFS_BLOCK_INVALID_DATA:
+ return be->be_tag ? false : true;
+ default:
+ return false;
+ }
}
/* The data we are handed might be spread across several bios. We need
@@ -91,9 +66,8 @@ static int is_writable(struct pnfs_block_extent *be, sector_t isect)
*/
struct parallel_io {
struct kref refcnt;
- void (*pnfs_callback) (void *data, int num_se);
+ void (*pnfs_callback) (void *data);
void *data;
- int bse_count;
};
static inline struct parallel_io *alloc_parallel(void *data)
@@ -104,7 +78,6 @@ static inline struct parallel_io *alloc_parallel(void *data)
if (rv) {
rv->data = data;
kref_init(&rv->refcnt);
- rv->bse_count = 0;
}
return rv;
}
@@ -119,7 +92,7 @@ static void destroy_parallel(struct kref *kref)
struct parallel_io *p = container_of(kref, struct parallel_io, refcnt);
dprintk("%s enter\n", __func__);
- p->pnfs_callback(p->data, p->bse_count);
+ p->pnfs_callback(p->data);
kfree(p);
}
@@ -141,10 +114,9 @@ bl_submit_bio(int rw, struct bio *bio)
return NULL;
}
-static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
- struct pnfs_block_extent *be,
- void (*end_io)(struct bio *, int err),
- struct parallel_io *par)
+static struct bio *
+bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector,
+ void (*end_io)(struct bio *, int err), struct parallel_io *par)
{
struct bio *bio;
@@ -156,58 +128,64 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
}
if (bio) {
- bio->bi_iter.bi_sector = isect - be->be_f_offset +
- be->be_v_offset;
- bio->bi_bdev = be->be_mdev;
+ bio->bi_iter.bi_sector = disk_sector;
+ bio->bi_bdev = bdev;
bio->bi_end_io = end_io;
bio->bi_private = par;
}
return bio;
}
-static struct bio *do_add_page_to_bio(struct bio *bio, int npg, int rw,
- sector_t isect, struct page *page,
- struct pnfs_block_extent *be,
- void (*end_io)(struct bio *, int err),
- struct parallel_io *par,
- unsigned int offset, int len)
+static struct bio *
+do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
+ struct page *page, struct pnfs_block_dev_map *map,
+ struct pnfs_block_extent *be,
+ void (*end_io)(struct bio *, int err),
+ struct parallel_io *par, unsigned int offset, int *len)
{
- isect = isect + (offset >> SECTOR_SHIFT);
+ struct pnfs_block_dev *dev =
+ container_of(be->be_device, struct pnfs_block_dev, node);
+ u64 disk_addr, end;
+
dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
- npg, rw, (unsigned long long)isect, offset, len);
+ npg, rw, (unsigned long long)isect, offset, *len);
+
+ /* translate to device offset */
+ isect += be->be_v_offset;
+ isect -= be->be_f_offset;
+
+ /* translate to physical disk offset */
+ disk_addr = (u64)isect << SECTOR_SHIFT;
+ if (disk_addr < map->start || disk_addr >= map->start + map->len) {
+ if (!dev->map(dev, disk_addr, map))
+ return ERR_PTR(-EIO);
+ bio = bl_submit_bio(rw, bio);
+ }
+ disk_addr += map->disk_offset;
+ disk_addr -= map->start;
+
+ /* limit length to what the device mapping allows */
+ end = disk_addr + *len;
+ if (end >= map->start + map->len)
+ *len = map->start + map->len - disk_addr;
+
retry:
if (!bio) {
- bio = bl_alloc_init_bio(npg, isect, be, end_io, par);
+ bio = bl_alloc_init_bio(npg, map->bdev,
+ disk_addr >> SECTOR_SHIFT, end_io, par);
if (!bio)
return ERR_PTR(-ENOMEM);
}
- if (bio_add_page(bio, page, len, offset) < len) {
+ if (bio_add_page(bio, page, *len, offset) < *len) {
bio = bl_submit_bio(rw, bio);
goto retry;
}
return bio;
}
-static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
- sector_t isect, struct page *page,
- struct pnfs_block_extent *be,
- void (*end_io)(struct bio *, int err),
- struct parallel_io *par)
-{
- return do_add_page_to_bio(bio, npg, rw, isect, page, be,
- end_io, par, 0, PAGE_CACHE_SIZE);
-}
-
-/* This is basically copied from mpage_end_io_read */
static void bl_end_io_read(struct bio *bio, int err)
{
struct parallel_io *par = bio->bi_private;
- struct bio_vec *bvec;
- int i;
-
- if (!err)
- bio_for_each_segment_all(bvec, bio, i)
- SetPageUptodate(bvec->bv_page);
if (err) {
struct nfs_pgio_header *header = par->data;
@@ -216,6 +194,7 @@ static void bl_end_io_read(struct bio *bio, int err)
header->pnfs_error = -EIO;
pnfs_set_lo_fail(header->lseg);
}
+
bio_put(bio);
put_parallel(par);
}
@@ -231,7 +210,7 @@ static void bl_read_cleanup(struct work_struct *work)
}
static void
-bl_end_par_io_read(void *data, int unused)
+bl_end_par_io_read(void *data)
{
struct nfs_pgio_header *hdr = data;
@@ -241,88 +220,78 @@ bl_end_par_io_read(void *data, int unused)
}
static enum pnfs_try_status
-bl_read_pagelist(struct nfs_pgio_header *hdr)
+bl_read_pagelist(struct nfs_pgio_header *header)
{
- struct nfs_pgio_header *header = hdr;
- int i, hole;
+ struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
+ struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
struct bio *bio = NULL;
- struct pnfs_block_extent *be = NULL, *cow_read = NULL;
+ struct pnfs_block_extent be;
sector_t isect, extent_length = 0;
struct parallel_io *par;
- loff_t f_offset = hdr->args.offset;
- size_t bytes_left = hdr->args.count;
+ loff_t f_offset = header->args.offset;
+ size_t bytes_left = header->args.count;
unsigned int pg_offset, pg_len;
- struct page **pages = hdr->args.pages;
- int pg_index = hdr->args.pgbase >> PAGE_CACHE_SHIFT;
+ struct page **pages = header->args.pages;
+ int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
const bool is_dio = (header->dreq != NULL);
+ struct blk_plug plug;
+ int i;
dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
- hdr->page_array.npages, f_offset,
- (unsigned int)hdr->args.count);
+ header->page_array.npages, f_offset,
+ (unsigned int)header->args.count);
- par = alloc_parallel(hdr);
+ par = alloc_parallel(header);
if (!par)
- goto use_mds;
+ return PNFS_NOT_ATTEMPTED;
par->pnfs_callback = bl_end_par_io_read;
- /* At this point, we can no longer jump to use_mds */
+
+ blk_start_plug(&plug);
isect = (sector_t) (f_offset >> SECTOR_SHIFT);
/* Code assumes extents are page-aligned */
- for (i = pg_index; i < hdr->page_array.npages; i++) {
- if (!extent_length) {
+ for (i = pg_index; i < header->page_array.npages; i++) {
+ if (extent_length <= 0) {
/* We've used up the previous extent */
- bl_put_extent(be);
- bl_put_extent(cow_read);
bio = bl_submit_bio(READ, bio);
+
/* Get the next one */
- be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
- isect, &cow_read);
- if (!be) {
+ if (!ext_tree_lookup(bl, isect, &be, false)) {
header->pnfs_error = -EIO;
goto out;
}
- extent_length = be->be_length -
- (isect - be->be_f_offset);
- if (cow_read) {
- sector_t cow_length = cow_read->be_length -
- (isect - cow_read->be_f_offset);
- extent_length = min(extent_length, cow_length);
- }
+ extent_length = be.be_length - (isect - be.be_f_offset);
}
+ pg_offset = f_offset & ~PAGE_CACHE_MASK;
if (is_dio) {
- pg_offset = f_offset & ~PAGE_CACHE_MASK;
if (pg_offset + bytes_left > PAGE_CACHE_SIZE)
pg_len = PAGE_CACHE_SIZE - pg_offset;
else
pg_len = bytes_left;
-
- f_offset += pg_len;
- bytes_left -= pg_len;
- isect += (pg_offset >> SECTOR_SHIFT);
} else {
- pg_offset = 0;
+ BUG_ON(pg_offset != 0);
pg_len = PAGE_CACHE_SIZE;
}
- hole = is_hole(be, isect);
- if (hole && !cow_read) {
+ isect += (pg_offset >> SECTOR_SHIFT);
+ extent_length -= (pg_offset >> SECTOR_SHIFT);
+
+ if (is_hole(&be)) {
bio = bl_submit_bio(READ, bio);
/* Fill hole w/ zeroes w/o accessing device */
dprintk("%s Zeroing page for hole\n", __func__);
zero_user_segment(pages[i], pg_offset, pg_len);
- print_page(pages[i]);
- SetPageUptodate(pages[i]);
- } else {
- struct pnfs_block_extent *be_read;
- be_read = (hole && cow_read) ? cow_read : be;
+ /* invalidate map */
+ map.start = NFS4_MAX_UINT64;
+ } else {
bio = do_add_page_to_bio(bio,
- hdr->page_array.npages - i,
+ header->page_array.npages - i,
READ,
- isect, pages[i], be_read,
+ isect, pages[i], &map, &be,
bl_end_io_read, par,
- pg_offset, pg_len);
+ pg_offset, &pg_len);
if (IS_ERR(bio)) {
header->pnfs_error = PTR_ERR(bio);
bio = NULL;
@@ -330,75 +299,21 @@ bl_read_pagelist(struct nfs_pgio_header *hdr)
}
}
isect += (pg_len >> SECTOR_SHIFT);
- extent_length -= PAGE_CACHE_SECTORS;
+ extent_length -= (pg_len >> SECTOR_SHIFT);
+ f_offset += pg_len;
+ bytes_left -= pg_len;
}
if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
- hdr->res.eof = 1;
- hdr->res.count = header->inode->i_size - hdr->args.offset;
+ header->res.eof = 1;
+ header->res.count = header->inode->i_size - header->args.offset;
} else {
- hdr->res.count = (isect << SECTOR_SHIFT) - hdr->args.offset;
+ header->res.count = (isect << SECTOR_SHIFT) - header->args.offset;
}
out:
- bl_put_extent(be);
- bl_put_extent(cow_read);
bl_submit_bio(READ, bio);
+ blk_finish_plug(&plug);
put_parallel(par);
return PNFS_ATTEMPTED;
-
- use_mds:
- dprintk("Giving up and using normal NFS\n");
- return PNFS_NOT_ATTEMPTED;
-}
-
-static void mark_extents_written(struct pnfs_block_layout *bl,
- __u64 offset, __u32 count)
-{
- sector_t isect, end;
- struct pnfs_block_extent *be;
- struct pnfs_block_short_extent *se;
-
- dprintk("%s(%llu, %u)\n", __func__, offset, count);
- if (count == 0)
- return;
- isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT;
- end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK);
- end >>= SECTOR_SHIFT;
- while (isect < end) {
- sector_t len;
- be = bl_find_get_extent(bl, isect, NULL);
- BUG_ON(!be); /* FIXME */
- len = min(end, be->be_f_offset + be->be_length) - isect;
- if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
- se = bl_pop_one_short_extent(be->be_inval);
- BUG_ON(!se);
- bl_mark_for_commit(be, isect, len, se);
- }
- isect += len;
- bl_put_extent(be);
- }
-}
-
-static void bl_end_io_write_zero(struct bio *bio, int err)
-{
- struct parallel_io *par = bio->bi_private;
- struct bio_vec *bvec;
- int i;
-
- bio_for_each_segment_all(bvec, bio, i) {
- /* This is the zeroing page we added */
- end_page_writeback(bvec->bv_page);
- page_cache_release(bvec->bv_page);
- }
-
- if (unlikely(err)) {
- struct nfs_pgio_header *header = par->data;
-
- if (!header->pnfs_error)
- header->pnfs_error = -EIO;
- pnfs_set_lo_fail(header->lseg);
- }
- bio_put(bio);
- put_parallel(par);
}
static void bl_end_io_write(struct bio *bio, int err)
@@ -421,533 +336,118 @@ static void bl_end_io_write(struct bio *bio, int err)
*/
static void bl_write_cleanup(struct work_struct *work)
{
- struct rpc_task *task;
- struct nfs_pgio_header *hdr;
+ struct rpc_task *task = container_of(work, struct rpc_task, u.tk_work);
+ struct nfs_pgio_header *hdr =
+ container_of(task, struct nfs_pgio_header, task);
+
dprintk("%s enter\n", __func__);
- task = container_of(work, struct rpc_task, u.tk_work);
- hdr = container_of(task, struct nfs_pgio_header, task);
+
if (likely(!hdr->pnfs_error)) {
- /* Marks for LAYOUTCOMMIT */
- mark_extents_written(BLK_LSEG2EXT(hdr->lseg),
- hdr->args.offset, hdr->args.count);
+ struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg);
+ u64 start = hdr->args.offset & (loff_t)PAGE_CACHE_MASK;
+ u64 end = (hdr->args.offset + hdr->args.count +
+ PAGE_CACHE_SIZE - 1) & (loff_t)PAGE_CACHE_MASK;
+
+ ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
+ (end - start) >> SECTOR_SHIFT);
}
+
pnfs_ld_write_done(hdr);
}
/* Called when last of bios associated with a bl_write_pagelist call finishes */
-static void bl_end_par_io_write(void *data, int num_se)
+static void bl_end_par_io_write(void *data)
{
struct nfs_pgio_header *hdr = data;
- if (unlikely(hdr->pnfs_error)) {
- bl_free_short_extents(&BLK_LSEG2EXT(hdr->lseg)->bl_inval,
- num_se);
- }
-
hdr->task.tk_status = hdr->pnfs_error;
hdr->verf.committed = NFS_FILE_SYNC;
INIT_WORK(&hdr->task.u.tk_work, bl_write_cleanup);
schedule_work(&hdr->task.u.tk_work);
}
-/* FIXME STUB - mark intersection of layout and page as bad, so is not
- * used again.
- */
-static void mark_bad_read(void)
-{
- return;
-}
-
-/*
- * map_block: map a requested I/0 block (isect) into an offset in the LVM
- * block_device
- */
-static void
-map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be)
-{
- dprintk("%s enter be=%p\n", __func__, be);
-
- set_buffer_mapped(bh);
- bh->b_bdev = be->be_mdev;
- bh->b_blocknr = (isect - be->be_f_offset + be->be_v_offset) >>
- (be->be_mdev->bd_inode->i_blkbits - SECTOR_SHIFT);
-
- dprintk("%s isect %llu, bh->b_blocknr %ld, using bsize %Zd\n",
- __func__, (unsigned long long)isect, (long)bh->b_blocknr,
- bh->b_size);
- return;
-}
-
-static void
-bl_read_single_end_io(struct bio *bio, int error)
-{
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct page *page = bvec->bv_page;
-
- /* Only one page in bvec */
- unlock_page(page);
-}
-
-static int
-bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be,
- unsigned int offset, unsigned int len)
-{
- struct bio *bio;
- struct page *shadow_page;
- sector_t isect;
- char *kaddr, *kshadow_addr;
- int ret = 0;
-
- dprintk("%s: offset %u len %u\n", __func__, offset, len);
-
- shadow_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
- if (shadow_page == NULL)
- return -ENOMEM;
-
- bio = bio_alloc(GFP_NOIO, 1);
- if (bio == NULL)
- return -ENOMEM;
-
- isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) +
- (offset / SECTOR_SIZE);
-
- bio->bi_iter.bi_sector = isect - be->be_f_offset + be->be_v_offset;
- bio->bi_bdev = be->be_mdev;
- bio->bi_end_io = bl_read_single_end_io;
-
- lock_page(shadow_page);
- if (bio_add_page(bio, shadow_page,
- SECTOR_SIZE, round_down(offset, SECTOR_SIZE)) == 0) {
- unlock_page(shadow_page);
- bio_put(bio);
- return -EIO;
- }
-
- submit_bio(READ, bio);
- wait_on_page_locked(shadow_page);
- if (unlikely(!test_bit(BIO_UPTODATE, &bio->bi_flags))) {
- ret = -EIO;
- } else {
- kaddr = kmap_atomic(page);
- kshadow_addr = kmap_atomic(shadow_page);
- memcpy(kaddr + offset, kshadow_addr + offset, len);
- kunmap_atomic(kshadow_addr);
- kunmap_atomic(kaddr);
- }
- __free_page(shadow_page);
- bio_put(bio);
-
- return ret;
-}
-
-static int
-bl_read_partial_page_sync(struct page *page, struct pnfs_block_extent *be,
- unsigned int dirty_offset, unsigned int dirty_len,
- bool full_page)
-{
- int ret = 0;
- unsigned int start, end;
-
- if (full_page) {
- start = 0;
- end = PAGE_CACHE_SIZE;
- } else {
- start = round_down(dirty_offset, SECTOR_SIZE);
- end = round_up(dirty_offset + dirty_len, SECTOR_SIZE);
- }
-
- dprintk("%s: offset %u len %d\n", __func__, dirty_offset, dirty_len);
- if (!be) {
- zero_user_segments(page, start, dirty_offset,
- dirty_offset + dirty_len, end);
- if (start == 0 && end == PAGE_CACHE_SIZE &&
- trylock_page(page)) {
- SetPageUptodate(page);
- unlock_page(page);
- }
- return ret;
- }
-
- if (start != dirty_offset)
- ret = bl_do_readpage_sync(page, be, start, dirty_offset - start);
-
- if (!ret && (dirty_offset + dirty_len < end))
- ret = bl_do_readpage_sync(page, be, dirty_offset + dirty_len,
- end - dirty_offset - dirty_len);
-
- return ret;
-}
-
-/* Given an unmapped page, zero it or read in page for COW, page is locked
- * by caller.
- */
-static int
-init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read)
-{
- struct buffer_head *bh = NULL;
- int ret = 0;
- sector_t isect;
-
- dprintk("%s enter, %p\n", __func__, page);
- BUG_ON(PageUptodate(page));
- if (!cow_read) {
- zero_user_segment(page, 0, PAGE_SIZE);
- SetPageUptodate(page);
- goto cleanup;
- }
-
- bh = alloc_page_buffers(page, PAGE_CACHE_SIZE, 0);
- if (!bh) {
- ret = -ENOMEM;
- goto cleanup;
- }
-
- isect = (sector_t) page->index << PAGE_CACHE_SECTOR_SHIFT;
- map_block(bh, isect, cow_read);
- if (!bh_uptodate_or_lock(bh))
- ret = bh_submit_read(bh);
- if (ret)
- goto cleanup;
- SetPageUptodate(page);
-
-cleanup:
- if (bh)
- free_buffer_head(bh);
- if (ret) {
- /* Need to mark layout with bad read...should now
- * just use nfs4 for reads and writes.
- */
- mark_bad_read();
- }
- return ret;
-}
-
-/* Find or create a zeroing page marked being writeback.
- * Return ERR_PTR on error, NULL to indicate skip this page and page itself
- * to indicate write out.
- */
-static struct page *
-bl_find_get_zeroing_page(struct inode *inode, pgoff_t index,
- struct pnfs_block_extent *cow_read)
-{
- struct page *page;
- int locked = 0;
- page = find_get_page(inode->i_mapping, index);
- if (page)
- goto check_page;
-
- page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
- if (unlikely(!page)) {
- dprintk("%s oom\n", __func__);
- return ERR_PTR(-ENOMEM);
- }
- locked = 1;
-
-check_page:
- /* PageDirty: Other will write this out
- * PageWriteback: Other is writing this out
- * PageUptodate: It was read before
- */
- if (PageDirty(page) || PageWriteback(page)) {
- print_page(page);
- if (locked)
- unlock_page(page);
- page_cache_release(page);
- return NULL;
- }
-
- if (!locked) {
- lock_page(page);
- locked = 1;
- goto check_page;
- }
- if (!PageUptodate(page)) {
- /* New page, readin or zero it */
- init_page_for_write(page, cow_read);
- }
- set_page_writeback(page);
- unlock_page(page);
-
- return page;
-}
-
static enum pnfs_try_status
bl_write_pagelist(struct nfs_pgio_header *header, int sync)
{
- int i, ret, npg_zero, pg_index, last = 0;
+ struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
+ struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
struct bio *bio = NULL;
- struct pnfs_block_extent *be = NULL, *cow_read = NULL;
- sector_t isect, last_isect = 0, extent_length = 0;
+ struct pnfs_block_extent be;
+ sector_t isect, extent_length = 0;
struct parallel_io *par = NULL;
loff_t offset = header->args.offset;
size_t count = header->args.count;
- unsigned int pg_offset, pg_len, saved_len;
struct page **pages = header->args.pages;
- struct page *page;
- pgoff_t index;
- u64 temp;
- int npg_per_block =
- NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
+ int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+ unsigned int pg_len;
+ struct blk_plug plug;
+ int i;
dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
- if (header->dreq != NULL &&
- (!IS_ALIGNED(offset, NFS_SERVER(header->inode)->pnfs_blksize) ||
- !IS_ALIGNED(count, NFS_SERVER(header->inode)->pnfs_blksize))) {
- dprintk("pnfsblock nonblock aligned DIO writes. Resend MDS\n");
- goto out_mds;
- }
/* At this point, header->page_aray is a (sequential) list of nfs_pages.
* We want to write each, and if there is an error set pnfs_error
* to have it redone using nfs.
*/
par = alloc_parallel(header);
if (!par)
- goto out_mds;
+ return PNFS_NOT_ATTEMPTED;
par->pnfs_callback = bl_end_par_io_write;
- /* At this point, have to be more careful with error handling */
- isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
- be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read);
- if (!be || !is_writable(be, isect)) {
- dprintk("%s no matching extents!\n", __func__);
- goto out_mds;
- }
+ blk_start_plug(&plug);
- /* First page inside INVALID extent */
- if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
- if (likely(!bl_push_one_short_extent(be->be_inval)))
- par->bse_count++;
- else
- goto out_mds;
- temp = offset >> PAGE_CACHE_SHIFT;
- npg_zero = do_div(temp, npg_per_block);
- isect = (sector_t) (((offset - npg_zero * PAGE_CACHE_SIZE) &
- (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
- extent_length = be->be_length - (isect - be->be_f_offset);
-
-fill_invalid_ext:
- dprintk("%s need to zero %d pages\n", __func__, npg_zero);
- for (;npg_zero > 0; npg_zero--) {
- if (bl_is_sector_init(be->be_inval, isect)) {
- dprintk("isect %llu already init\n",
- (unsigned long long)isect);
- goto next_page;
- }
- /* page ref released in bl_end_io_write_zero */
- index = isect >> PAGE_CACHE_SECTOR_SHIFT;
- dprintk("%s zero %dth page: index %lu isect %llu\n",
- __func__, npg_zero, index,
- (unsigned long long)isect);
- page = bl_find_get_zeroing_page(header->inode, index,
- cow_read);
- if (unlikely(IS_ERR(page))) {
- header->pnfs_error = PTR_ERR(page);
- goto out;
- } else if (page == NULL)
- goto next_page;
-
- ret = bl_mark_sectors_init(be->be_inval, isect,
- PAGE_CACHE_SECTORS);
- if (unlikely(ret)) {
- dprintk("%s bl_mark_sectors_init fail %d\n",
- __func__, ret);
- end_page_writeback(page);
- page_cache_release(page);
- header->pnfs_error = ret;
- goto out;
- }
- if (likely(!bl_push_one_short_extent(be->be_inval)))
- par->bse_count++;
- else {
- end_page_writeback(page);
- page_cache_release(page);
- header->pnfs_error = -ENOMEM;
- goto out;
- }
- /* FIXME: This should be done in bi_end_io */
- mark_extents_written(BLK_LSEG2EXT(header->lseg),
- page->index << PAGE_CACHE_SHIFT,
- PAGE_CACHE_SIZE);
-
- bio = bl_add_page_to_bio(bio, npg_zero, WRITE,
- isect, page, be,
- bl_end_io_write_zero, par);
- if (IS_ERR(bio)) {
- header->pnfs_error = PTR_ERR(bio);
- bio = NULL;
- goto out;
- }
-next_page:
- isect += PAGE_CACHE_SECTORS;
- extent_length -= PAGE_CACHE_SECTORS;
- }
- if (last)
- goto write_done;
- }
- bio = bl_submit_bio(WRITE, bio);
+ /* we always write out the whole page */
+ offset = offset & (loff_t)PAGE_CACHE_MASK;
+ isect = offset >> SECTOR_SHIFT;
- /* Middle pages */
- pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
for (i = pg_index; i < header->page_array.npages; i++) {
- if (!extent_length) {
+ if (extent_length <= 0) {
/* We've used up the previous extent */
- bl_put_extent(be);
- bl_put_extent(cow_read);
bio = bl_submit_bio(WRITE, bio);
/* Get the next one */
- be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
- isect, &cow_read);
- if (!be || !is_writable(be, isect)) {
+ if (!ext_tree_lookup(bl, isect, &be, true)) {
header->pnfs_error = -EINVAL;
goto out;
}
- if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
- if (likely(!bl_push_one_short_extent(
- be->be_inval)))
- par->bse_count++;
- else {
- header->pnfs_error = -ENOMEM;
- goto out;
- }
- }
- extent_length = be->be_length -
- (isect - be->be_f_offset);
- }
-
- dprintk("%s offset %lld count %Zu\n", __func__, offset, count);
- pg_offset = offset & ~PAGE_CACHE_MASK;
- if (pg_offset + count > PAGE_CACHE_SIZE)
- pg_len = PAGE_CACHE_SIZE - pg_offset;
- else
- pg_len = count;
-
- saved_len = pg_len;
- if (be->be_state == PNFS_BLOCK_INVALID_DATA &&
- !bl_is_sector_init(be->be_inval, isect)) {
- ret = bl_read_partial_page_sync(pages[i], cow_read,
- pg_offset, pg_len, true);
- if (ret) {
- dprintk("%s bl_read_partial_page_sync fail %d\n",
- __func__, ret);
- header->pnfs_error = ret;
- goto out;
- }
-
- ret = bl_mark_sectors_init(be->be_inval, isect,
- PAGE_CACHE_SECTORS);
- if (unlikely(ret)) {
- dprintk("%s bl_mark_sectors_init fail %d\n",
- __func__, ret);
- header->pnfs_error = ret;
- goto out;
- }
- /* Expand to full page write */
- pg_offset = 0;
- pg_len = PAGE_CACHE_SIZE;
- } else if ((pg_offset & (SECTOR_SIZE - 1)) ||
- (pg_len & (SECTOR_SIZE - 1))){
- /* ahh, nasty case. We have to do sync full sector
- * read-modify-write cycles.
- */
- unsigned int saved_offset = pg_offset;
- ret = bl_read_partial_page_sync(pages[i], be, pg_offset,
- pg_len, false);
- pg_offset = round_down(pg_offset, SECTOR_SIZE);
- pg_len = round_up(saved_offset + pg_len, SECTOR_SIZE)
- - pg_offset;
+ extent_length = be.be_length - (isect - be.be_f_offset);
}
-
+ pg_len = PAGE_CACHE_SIZE;
bio = do_add_page_to_bio(bio, header->page_array.npages - i,
- WRITE,
- isect, pages[i], be,
+ WRITE, isect, pages[i], &map, &be,
bl_end_io_write, par,
- pg_offset, pg_len);
+ 0, &pg_len);
if (IS_ERR(bio)) {
header->pnfs_error = PTR_ERR(bio);
bio = NULL;
goto out;
}
- offset += saved_len;
- count -= saved_len;
- isect += PAGE_CACHE_SECTORS;
- last_isect = isect;
- extent_length -= PAGE_CACHE_SECTORS;
- }
- /* Last page inside INVALID extent */
- if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
- bio = bl_submit_bio(WRITE, bio);
- temp = last_isect >> PAGE_CACHE_SECTOR_SHIFT;
- npg_zero = npg_per_block - do_div(temp, npg_per_block);
- if (npg_zero < npg_per_block) {
- last = 1;
- goto fill_invalid_ext;
- }
+ offset += pg_len;
+ count -= pg_len;
+ isect += (pg_len >> SECTOR_SHIFT);
+ extent_length -= (pg_len >> SECTOR_SHIFT);
}
-write_done:
header->res.count = header->args.count;
out:
- bl_put_extent(be);
- bl_put_extent(cow_read);
bl_submit_bio(WRITE, bio);
+ blk_finish_plug(&plug);
put_parallel(par);
return PNFS_ATTEMPTED;
-out_mds:
- bl_put_extent(be);
- bl_put_extent(cow_read);
- kfree(par);
- return PNFS_NOT_ATTEMPTED;
-}
-
-/* FIXME - range ignored */
-static void
-release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range)
-{
- int i;
- struct pnfs_block_extent *be;
-
- spin_lock(&bl->bl_ext_lock);
- for (i = 0; i < EXTENT_LISTS; i++) {
- while (!list_empty(&bl->bl_extents[i])) {
- be = list_first_entry(&bl->bl_extents[i],
- struct pnfs_block_extent,
- be_node);
- list_del(&be->be_node);
- bl_put_extent(be);
- }
- }
- spin_unlock(&bl->bl_ext_lock);
-}
-
-static void
-release_inval_marks(struct pnfs_inval_markings *marks)
-{
- struct pnfs_inval_tracking *pos, *temp;
- struct pnfs_block_short_extent *se, *stemp;
-
- list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) {
- list_del(&pos->it_link);
- kfree(pos);
- }
-
- list_for_each_entry_safe(se, stemp, &marks->im_extents, bse_node) {
- list_del(&se->bse_node);
- kfree(se);
- }
- return;
}
static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+ int err;
dprintk("%s enter\n", __func__);
- release_extents(bl, NULL);
- release_inval_marks(&bl->bl_inval);
+
+ err = ext_tree_remove(bl, true, 0, LLONG_MAX);
+ WARN_ON(err);
+
kfree(bl);
}
@@ -960,14 +460,11 @@ static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
bl = kzalloc(sizeof(*bl), gfp_flags);
if (!bl)
return NULL;
+
+ bl->bl_ext_rw = RB_ROOT;
+ bl->bl_ext_ro = RB_ROOT;
spin_lock_init(&bl->bl_ext_lock);
- INIT_LIST_HEAD(&bl->bl_extents[0]);
- INIT_LIST_HEAD(&bl->bl_extents[1]);
- INIT_LIST_HEAD(&bl->bl_commit);
- INIT_LIST_HEAD(&bl->bl_committing);
- bl->bl_count = 0;
- bl->bl_blocksize = NFS_SERVER(inode)->pnfs_blksize >> SECTOR_SHIFT;
- BL_INIT_INVAL_MARKS(&bl->bl_inval, bl->bl_blocksize);
+
return &bl->bl_layout;
}
@@ -977,215 +474,318 @@ static void bl_free_lseg(struct pnfs_layout_segment *lseg)
kfree(lseg);
}
-/* We pretty much ignore lseg, and store all data layout wide, so we
- * can correctly merge.
- */
-static struct pnfs_layout_segment *bl_alloc_lseg(struct pnfs_layout_hdr *lo,
- struct nfs4_layoutget_res *lgr,
- gfp_t gfp_flags)
-{
- struct pnfs_layout_segment *lseg;
- int status;
+/* Tracks info needed to ensure extents in layout obey constraints of spec */
+struct layout_verification {
+ u32 mode; /* R or RW */
+ u64 start; /* Expected start of next non-COW extent */
+ u64 inval; /* Start of INVAL coverage */
+ u64 cowread; /* End of COW read coverage */
+};
- dprintk("%s enter\n", __func__);
- lseg = kzalloc(sizeof(*lseg), gfp_flags);
- if (!lseg)
- return ERR_PTR(-ENOMEM);
- status = nfs4_blk_process_layoutget(lo, lgr, gfp_flags);
- if (status) {
- /* We don't want to call the full-blown bl_free_lseg,
- * since on error extents were not touched.
- */
- kfree(lseg);
- return ERR_PTR(status);
+/* Verify the extent meets the layout requirements of the pnfs-block draft,
+ * section 2.3.1.
+ */
+static int verify_extent(struct pnfs_block_extent *be,
+ struct layout_verification *lv)
+{
+ if (lv->mode == IOMODE_READ) {
+ if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
+ be->be_state == PNFS_BLOCK_INVALID_DATA)
+ return -EIO;
+ if (be->be_f_offset != lv->start)
+ return -EIO;
+ lv->start += be->be_length;
+ return 0;
}
- return lseg;
+ /* lv->mode == IOMODE_RW */
+ if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
+ if (be->be_f_offset != lv->start)
+ return -EIO;
+ if (lv->cowread > lv->start)
+ return -EIO;
+ lv->start += be->be_length;
+ lv->inval = lv->start;
+ return 0;
+ } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+ if (be->be_f_offset != lv->start)
+ return -EIO;
+ lv->start += be->be_length;
+ return 0;
+ } else if (be->be_state == PNFS_BLOCK_READ_DATA) {
+ if (be->be_f_offset > lv->start)
+ return -EIO;
+ if (be->be_f_offset < lv->inval)
+ return -EIO;
+ if (be->be_f_offset < lv->cowread)
+ return -EIO;
+ /* It looks like you might want to min this with lv->start,
+ * but you really don't.
+ */
+ lv->inval = lv->inval + be->be_length;
+ lv->cowread = be->be_f_offset + be->be_length;
+ return 0;
+ } else
+ return -EIO;
}
-static void
-bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
- const struct nfs4_layoutcommit_args *arg)
+static int decode_sector_number(__be32 **rp, sector_t *sp)
{
- dprintk("%s enter\n", __func__);
- encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg);
+ uint64_t s;
+
+ *rp = xdr_decode_hyper(*rp, &s);
+ if (s & 0x1ff) {
+ printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
+ return -1;
+ }
+ *sp = s >> SECTOR_SHIFT;
+ return 0;
}
-static void
-bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
+static int
+bl_alloc_extent(struct xdr_stream *xdr, struct pnfs_layout_hdr *lo,
+ struct layout_verification *lv, struct list_head *extents,
+ gfp_t gfp_mask)
{
- struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout;
+ struct pnfs_block_extent *be;
+ struct nfs4_deviceid id;
+ int error;
+ __be32 *p;
- dprintk("%s enter\n", __func__);
- clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status);
-}
+ p = xdr_inline_decode(xdr, 28 + NFS4_DEVICEID4_SIZE);
+ if (!p)
+ return -EIO;
-static void free_blk_mountid(struct block_mount_id *mid)
-{
- if (mid) {
- struct pnfs_block_dev *dev, *tmp;
+ be = kzalloc(sizeof(*be), GFP_NOFS);
+ if (!be)
+ return -ENOMEM;
- /* No need to take bm_lock as we are last user freeing bm_devlist */
- list_for_each_entry_safe(dev, tmp, &mid->bm_devlist, bm_node) {
- list_del(&dev->bm_node);
- bl_free_block_dev(dev);
- }
- kfree(mid);
+ memcpy(&id, p, NFS4_DEVICEID4_SIZE);
+ p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+
+ error = -EIO;
+ be->be_device = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id,
+ lo->plh_lc_cred, gfp_mask);
+ if (!be->be_device)
+ goto out_free_be;
+
+ /*
+ * The next three values are read in as bytes, but stored in the
+ * extent structure in 512-byte granularity.
+ */
+ if (decode_sector_number(&p, &be->be_f_offset) < 0)
+ goto out_put_deviceid;
+ if (decode_sector_number(&p, &be->be_length) < 0)
+ goto out_put_deviceid;
+ if (decode_sector_number(&p, &be->be_v_offset) < 0)
+ goto out_put_deviceid;
+ be->be_state = be32_to_cpup(p++);
+
+ error = verify_extent(be, lv);
+ if (error) {
+ dprintk("%s: extent verification failed\n", __func__);
+ goto out_put_deviceid;
}
+
+ list_add_tail(&be->be_list, extents);
+ return 0;
+
+out_put_deviceid:
+ nfs4_put_deviceid_node(be->be_device);
+out_free_be:
+ kfree(be);
+ return error;
}
-/* This is mostly copied from the filelayout_get_device_info function.
- * It seems much of this should be at the generic pnfs level.
- */
-static struct pnfs_block_dev *
-nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
- struct nfs4_deviceid *d_id)
+static struct pnfs_layout_segment *
+bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
+ gfp_t gfp_mask)
{
- struct pnfs_device *dev;
- struct pnfs_block_dev *rv;
- u32 max_resp_sz;
- int max_pages;
- struct page **pages = NULL;
- int i, rc;
+ struct layout_verification lv = {
+ .mode = lgr->range.iomode,
+ .start = lgr->range.offset >> SECTOR_SHIFT,
+ .inval = lgr->range.offset >> SECTOR_SHIFT,
+ .cowread = lgr->range.offset >> SECTOR_SHIFT,
+ };
+ struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+ struct pnfs_layout_segment *lseg;
+ struct xdr_buf buf;
+ struct xdr_stream xdr;
+ struct page *scratch;
+ int status, i;
+ uint32_t count;
+ __be32 *p;
+ LIST_HEAD(extents);
+
+ dprintk("---> %s\n", __func__);
+
+ lseg = kzalloc(sizeof(*lseg), gfp_mask);
+ if (!lseg)
+ return ERR_PTR(-ENOMEM);
+
+ status = -ENOMEM;
+ scratch = alloc_page(gfp_mask);
+ if (!scratch)
+ goto out;
+
+ xdr_init_decode_pages(&xdr, &buf,
+ lgr->layoutp->pages, lgr->layoutp->len);
+ xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
+
+ status = -EIO;
+ p = xdr_inline_decode(&xdr, 4);
+ if (unlikely(!p))
+ goto out_free_scratch;
+
+ count = be32_to_cpup(p++);
+ dprintk("%s: number of extents %d\n", __func__, count);
/*
- * Use the session max response size as the basis for setting
- * GETDEVICEINFO's maxcount
+ * Decode individual extents, putting them in temporary staging area
+ * until whole layout is decoded to make error recovery easier.
*/
- max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
- max_pages = nfs_page_array_len(0, max_resp_sz);
- dprintk("%s max_resp_sz %u max_pages %d\n",
- __func__, max_resp_sz, max_pages);
-
- dev = kmalloc(sizeof(*dev), GFP_NOFS);
- if (!dev) {
- dprintk("%s kmalloc failed\n", __func__);
- return ERR_PTR(-ENOMEM);
+ for (i = 0; i < count; i++) {
+ status = bl_alloc_extent(&xdr, lo, &lv, &extents, gfp_mask);
+ if (status)
+ goto process_extents;
}
- pages = kcalloc(max_pages, sizeof(struct page *), GFP_NOFS);
- if (pages == NULL) {
- kfree(dev);
- return ERR_PTR(-ENOMEM);
+ if (lgr->range.offset + lgr->range.length !=
+ lv.start << SECTOR_SHIFT) {
+ dprintk("%s Final length mismatch\n", __func__);
+ status = -EIO;
+ goto process_extents;
}
- for (i = 0; i < max_pages; i++) {
- pages[i] = alloc_page(GFP_NOFS);
- if (!pages[i]) {
- rv = ERR_PTR(-ENOMEM);
- goto out_free;
- }
+
+ if (lv.start < lv.cowread) {
+ dprintk("%s Final uncovered COW extent\n", __func__);
+ status = -EIO;
}
- memcpy(&dev->dev_id, d_id, sizeof(*d_id));
- dev->layout_type = LAYOUT_BLOCK_VOLUME;
- dev->pages = pages;
- dev->pgbase = 0;
- dev->pglen = PAGE_SIZE * max_pages;
- dev->mincount = 0;
- dev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;
-
- dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
- rc = nfs4_proc_getdeviceinfo(server, dev, NULL);
- dprintk("%s getdevice info returns %d\n", __func__, rc);
- if (rc) {
- rv = ERR_PTR(rc);
- goto out_free;
+process_extents:
+ while (!list_empty(&extents)) {
+ struct pnfs_block_extent *be =
+ list_first_entry(&extents, struct pnfs_block_extent,
+ be_list);
+ list_del(&be->be_list);
+
+ if (!status)
+ status = ext_tree_insert(bl, be);
+
+ if (status) {
+ nfs4_put_deviceid_node(be->be_device);
+ kfree(be);
+ }
}
- rv = nfs4_blk_decode_device(server, dev);
- out_free:
- for (i = 0; i < max_pages; i++)
- __free_page(pages[i]);
- kfree(pages);
- kfree(dev);
- return rv;
+out_free_scratch:
+ __free_page(scratch);
+out:
+ dprintk("%s returns %d\n", __func__, status);
+ if (status) {
+ kfree(lseg);
+ return ERR_PTR(status);
+ }
+ return lseg;
}
-static int
-bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
+static void
+bl_return_range(struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_range *range)
{
- struct block_mount_id *b_mt_id = NULL;
- struct pnfs_devicelist *dlist = NULL;
- struct pnfs_block_dev *bdev;
- LIST_HEAD(block_disklist);
- int status, i;
-
- dprintk("%s enter\n", __func__);
+ struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+ sector_t offset = range->offset >> SECTOR_SHIFT, end;
- if (server->pnfs_blksize == 0) {
- dprintk("%s Server did not return blksize\n", __func__);
- return -EINVAL;
- }
- b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS);
- if (!b_mt_id) {
- status = -ENOMEM;
- goto out_error;
- }
- /* Initialize nfs4 block layout mount id */
- spin_lock_init(&b_mt_id->bm_lock);
- INIT_LIST_HEAD(&b_mt_id->bm_devlist);
-
- dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS);
- if (!dlist) {
- status = -ENOMEM;
- goto out_error;
+ if (range->offset % 8) {
+ dprintk("%s: offset %lld not block size aligned\n",
+ __func__, range->offset);
+ return;
}
- dlist->eof = 0;
- while (!dlist->eof) {
- status = nfs4_proc_getdevicelist(server, fh, dlist);
- if (status)
- goto out_error;
- dprintk("%s GETDEVICELIST numdevs=%i, eof=%i\n",
- __func__, dlist->num_devs, dlist->eof);
- for (i = 0; i < dlist->num_devs; i++) {
- bdev = nfs4_blk_get_deviceinfo(server, fh,
- &dlist->dev_id[i]);
- if (IS_ERR(bdev)) {
- status = PTR_ERR(bdev);
- goto out_error;
- }
- spin_lock(&b_mt_id->bm_lock);
- list_add(&bdev->bm_node, &b_mt_id->bm_devlist);
- spin_unlock(&b_mt_id->bm_lock);
+
+ if (range->length != NFS4_MAX_UINT64) {
+ if (range->length % 8) {
+ dprintk("%s: length %lld not block size aligned\n",
+ __func__, range->length);
+ return;
}
- }
- dprintk("%s SUCCESS\n", __func__);
- server->pnfs_ld_data = b_mt_id;
- out_return:
- kfree(dlist);
- return status;
+ end = offset + (range->length >> SECTOR_SHIFT);
+ } else {
+ end = round_down(NFS4_MAX_UINT64, PAGE_SIZE);
+ }
- out_error:
- free_blk_mountid(b_mt_id);
- goto out_return;
+ ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end);
}
static int
-bl_clear_layoutdriver(struct nfs_server *server)
+bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg)
+{
+ return ext_tree_prepare_commit(arg);
+}
+
+static void
+bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
{
- struct block_mount_id *b_mt_id = server->pnfs_ld_data;
+ ext_tree_mark_committed(&lcdata->args, lcdata->res.status);
+}
+static int
+bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
+{
dprintk("%s enter\n", __func__);
- free_blk_mountid(b_mt_id);
- dprintk("%s RETURNS\n", __func__);
+
+ if (server->pnfs_blksize == 0) {
+ dprintk("%s Server did not return blksize\n", __func__);
+ return -EINVAL;
+ }
+ if (server->pnfs_blksize > PAGE_SIZE) {
+ printk(KERN_ERR "%s: pNFS blksize %d not supported.\n",
+ __func__, server->pnfs_blksize);
+ return -EINVAL;
+ }
+
return 0;
}
static bool
-is_aligned_req(struct nfs_page *req, unsigned int alignment)
+is_aligned_req(struct nfs_pageio_descriptor *pgio,
+ struct nfs_page *req, unsigned int alignment)
{
- return IS_ALIGNED(req->wb_offset, alignment) &&
- IS_ALIGNED(req->wb_bytes, alignment);
+ /*
+ * Always accept buffered writes, higher layers take care of the
+ * right alignment.
+ */
+ if (pgio->pg_dreq == NULL)
+ return true;
+
+ if (!IS_ALIGNED(req->wb_offset, alignment))
+ return false;
+
+ if (IS_ALIGNED(req->wb_bytes, alignment))
+ return true;
+
+ if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) {
+ /*
+ * If the write goes up to the inode size, just write
+ * the full page. Data past the inode size is
+ * guaranteed to be zeroed by the higher level client
+ * code, and this behaviour is mandated by RFC 5663
+ * section 2.3.2.
+ */
+ return true;
+ }
+
+ return false;
}
static void
bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
- if (pgio->pg_dreq != NULL &&
- !is_aligned_req(req, SECTOR_SIZE))
+ if (!is_aligned_req(pgio, req, SECTOR_SIZE)) {
nfs_pageio_reset_read_mds(pgio);
- else
- pnfs_generic_pg_init_read(pgio, req);
+ return;
+ }
+
+ pnfs_generic_pg_init_read(pgio, req);
}
/*
@@ -1196,10 +796,8 @@ static size_t
bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
- if (pgio->pg_dreq != NULL &&
- !is_aligned_req(req, SECTOR_SIZE))
+ if (!is_aligned_req(pgio, req, SECTOR_SIZE))
return 0;
-
return pnfs_generic_pg_test(pgio, prev, req);
}
@@ -1229,19 +827,20 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
static void
bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
- if (pgio->pg_dreq != NULL &&
- !is_aligned_req(req, PAGE_CACHE_SIZE)) {
+ u64 wb_size;
+
+ if (!is_aligned_req(pgio, req, PAGE_SIZE)) {
nfs_pageio_reset_write_mds(pgio);
- } else {
- u64 wb_size;
- if (pgio->pg_dreq == NULL)
- wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
- req->wb_index);
- else
- wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
-
- pnfs_generic_pg_init_write(pgio, req, wb_size);
+ return;
}
+
+ if (pgio->pg_dreq == NULL)
+ wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
+ req->wb_index);
+ else
+ wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+ pnfs_generic_pg_init_write(pgio, req, wb_size);
}
/*
@@ -1252,10 +851,8 @@ static size_t
bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
struct nfs_page *req)
{
- if (pgio->pg_dreq != NULL &&
- !is_aligned_req(req, PAGE_CACHE_SIZE))
+ if (!is_aligned_req(pgio, req, PAGE_SIZE))
return 0;
-
return pnfs_generic_pg_test(pgio, prev, req);
}
@@ -1275,146 +872,24 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
.id = LAYOUT_BLOCK_VOLUME,
.name = "LAYOUT_BLOCK_VOLUME",
.owner = THIS_MODULE,
+ .flags = PNFS_LAYOUTRET_ON_SETATTR |
+ PNFS_READ_WHOLE_PAGE,
.read_pagelist = bl_read_pagelist,
.write_pagelist = bl_write_pagelist,
.alloc_layout_hdr = bl_alloc_layout_hdr,
.free_layout_hdr = bl_free_layout_hdr,
.alloc_lseg = bl_alloc_lseg,
.free_lseg = bl_free_lseg,
- .encode_layoutcommit = bl_encode_layoutcommit,
+ .return_range = bl_return_range,
+ .prepare_layoutcommit = bl_prepare_layoutcommit,
.cleanup_layoutcommit = bl_cleanup_layoutcommit,
.set_layoutdriver = bl_set_layoutdriver,
- .clear_layoutdriver = bl_clear_layoutdriver,
+ .alloc_deviceid_node = bl_alloc_deviceid_node,
+ .free_deviceid_node = bl_free_deviceid_node,
.pg_read_ops = &bl_pg_read_ops,
.pg_write_ops = &bl_pg_write_ops,
};
-static const struct rpc_pipe_ops bl_upcall_ops = {
- .upcall = rpc_pipe_generic_upcall,
- .downcall = bl_pipe_downcall,
- .destroy_msg = bl_pipe_destroy_msg,
-};
-
-static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
- struct rpc_pipe *pipe)
-{
- struct dentry *dir, *dentry;
-
- dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
- if (dir == NULL)
- return ERR_PTR(-ENOENT);
- dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
- dput(dir);
- return dentry;
-}
-
-static void nfs4blocklayout_unregister_sb(struct super_block *sb,
- struct rpc_pipe *pipe)
-{
- if (pipe->dentry)
- rpc_unlink(pipe->dentry);
-}
-
-static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
- void *ptr)
-{
- struct super_block *sb = ptr;
- struct net *net = sb->s_fs_info;
- struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct dentry *dentry;
- int ret = 0;
-
- if (!try_module_get(THIS_MODULE))
- return 0;
-
- if (nn->bl_device_pipe == NULL) {
- module_put(THIS_MODULE);
- return 0;
- }
-
- switch (event) {
- case RPC_PIPEFS_MOUNT:
- dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
- if (IS_ERR(dentry)) {
- ret = PTR_ERR(dentry);
- break;
- }
- nn->bl_device_pipe->dentry = dentry;
- break;
- case RPC_PIPEFS_UMOUNT:
- if (nn->bl_device_pipe->dentry)
- nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
- break;
- default:
- ret = -ENOTSUPP;
- break;
- }
- module_put(THIS_MODULE);
- return ret;
-}
-
-static struct notifier_block nfs4blocklayout_block = {
- .notifier_call = rpc_pipefs_event,
-};
-
-static struct dentry *nfs4blocklayout_register_net(struct net *net,
- struct rpc_pipe *pipe)
-{
- struct super_block *pipefs_sb;
- struct dentry *dentry;
-
- pipefs_sb = rpc_get_sb_net(net);
- if (!pipefs_sb)
- return NULL;
- dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
- rpc_put_sb_net(net);
- return dentry;
-}
-
-static void nfs4blocklayout_unregister_net(struct net *net,
- struct rpc_pipe *pipe)
-{
- struct super_block *pipefs_sb;
-
- pipefs_sb = rpc_get_sb_net(net);
- if (pipefs_sb) {
- nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
- rpc_put_sb_net(net);
- }
-}
-
-static int nfs4blocklayout_net_init(struct net *net)
-{
- struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct dentry *dentry;
-
- init_waitqueue_head(&nn->bl_wq);
- nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
- if (IS_ERR(nn->bl_device_pipe))
- return PTR_ERR(nn->bl_device_pipe);
- dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
- if (IS_ERR(dentry)) {
- rpc_destroy_pipe_data(nn->bl_device_pipe);
- return PTR_ERR(dentry);
- }
- nn->bl_device_pipe->dentry = dentry;
- return 0;
-}
-
-static void nfs4blocklayout_net_exit(struct net *net)
-{
- struct nfs_net *nn = net_generic(net, nfs_net_id);
-
- nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
- rpc_destroy_pipe_data(nn->bl_device_pipe);
- nn->bl_device_pipe = NULL;
-}
-
-static struct pernet_operations nfs4blocklayout_net_ops = {
- .init = nfs4blocklayout_net_init,
- .exit = nfs4blocklayout_net_exit,
-};
-
static int __init nfs4blocklayout_init(void)
{
int ret;
@@ -1424,20 +899,14 @@ static int __init nfs4blocklayout_init(void)
ret = pnfs_register_layoutdriver(&blocklayout_type);
if (ret)
goto out;
-
- ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+ ret = bl_init_pipefs();
if (ret)
- goto out_remove;
- ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
- if (ret)
- goto out_notifier;
-out:
- return ret;
+ goto out_unregister;
+ return 0;
-out_notifier:
- rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
-out_remove:
+out_unregister:
pnfs_unregister_layoutdriver(&blocklayout_type);
+out:
return ret;
}
@@ -1446,8 +915,7 @@ static void __exit nfs4blocklayout_exit(void)
dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
__func__);
- rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
- unregister_pernet_subsys(&nfs4blocklayout_net_ops);
+ bl_cleanup_pipefs();
pnfs_unregister_layoutdriver(&blocklayout_type);
}
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 9838fb020473..92dca9e90d8d 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -44,105 +44,112 @@
#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
#define SECTOR_SIZE (1 << SECTOR_SHIFT)
-struct block_mount_id {
- spinlock_t bm_lock; /* protects list */
- struct list_head bm_devlist; /* holds pnfs_block_dev */
-};
+struct pnfs_block_dev;
-struct pnfs_block_dev {
- struct list_head bm_node;
- struct nfs4_deviceid bm_mdevid; /* associated devid */
- struct block_device *bm_mdev; /* meta device itself */
- struct net *net;
+enum pnfs_block_volume_type {
+ PNFS_BLOCK_VOLUME_SIMPLE = 0,
+ PNFS_BLOCK_VOLUME_SLICE = 1,
+ PNFS_BLOCK_VOLUME_CONCAT = 2,
+ PNFS_BLOCK_VOLUME_STRIPE = 3,
};
-enum exstate4 {
- PNFS_BLOCK_READWRITE_DATA = 0,
- PNFS_BLOCK_READ_DATA = 1,
- PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */
- PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */
+#define PNFS_BLOCK_MAX_UUIDS 4
+#define PNFS_BLOCK_MAX_DEVICES 64
+
+/*
+ * Random upper cap for the uuid length to avoid unbounded allocation.
+ * Not actually limited by the protocol.
+ */
+#define PNFS_BLOCK_UUID_LEN 128
+
+
+struct pnfs_block_volume {
+ enum pnfs_block_volume_type type;
+ union {
+ struct {
+ int len;
+ int nr_sigs;
+ struct {
+ u64 offset;
+ u32 sig_len;
+ u8 sig[PNFS_BLOCK_UUID_LEN];
+ } sigs[PNFS_BLOCK_MAX_UUIDS];
+ } simple;
+ struct {
+ u64 start;
+ u64 len;
+ u32 volume;
+ } slice;
+ struct {
+ u32 volumes_count;
+ u32 volumes[PNFS_BLOCK_MAX_DEVICES];
+ } concat;
+ struct {
+ u64 chunk_size;
+ u32 volumes_count;
+ u32 volumes[PNFS_BLOCK_MAX_DEVICES];
+ } stripe;
+ };
};
-#define MY_MAX_TAGS (15) /* tag bitnums used must be less than this */
+struct pnfs_block_dev_map {
+ sector_t start;
+ sector_t len;
-struct my_tree {
- sector_t mtt_step_size; /* Internal sector alignment */
- struct list_head mtt_stub; /* Should be a radix tree */
+ sector_t disk_offset;
+ struct block_device *bdev;
};
-struct pnfs_inval_markings {
- spinlock_t im_lock;
- struct my_tree im_tree; /* Sectors that need LAYOUTCOMMIT */
- sector_t im_block_size; /* Server blocksize in sectors */
- struct list_head im_extents; /* Short extents for INVAL->RW conversion */
+struct pnfs_block_dev {
+ struct nfs4_deviceid_node node;
+
+ u64 start;
+ u64 len;
+
+ u32 nr_children;
+ struct pnfs_block_dev *children;
+ u64 chunk_size;
+
+ struct block_device *bdev;
+ u64 disk_offset;
+
+ bool (*map)(struct pnfs_block_dev *dev, u64 offset,
+ struct pnfs_block_dev_map *map);
};
-struct pnfs_inval_tracking {
- struct list_head it_link;
- int it_sector;
- int it_tags;
+enum exstate4 {
+ PNFS_BLOCK_READWRITE_DATA = 0,
+ PNFS_BLOCK_READ_DATA = 1,
+ PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */
+ PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */
};
/* sector_t fields are all in 512-byte sectors */
struct pnfs_block_extent {
- struct kref be_refcnt;
- struct list_head be_node; /* link into lseg list */
- struct nfs4_deviceid be_devid; /* FIXME: could use device cache instead */
- struct block_device *be_mdev;
+ union {
+ struct rb_node be_node;
+ struct list_head be_list;
+ };
+ struct nfs4_deviceid_node *be_device;
sector_t be_f_offset; /* the starting offset in the file */
sector_t be_length; /* the size of the extent */
sector_t be_v_offset; /* the starting offset in the volume */
enum exstate4 be_state; /* the state of this extent */
- struct pnfs_inval_markings *be_inval; /* tracks INVAL->RW transition */
+#define EXTENT_WRITTEN 1
+#define EXTENT_COMMITTING 2
+ unsigned int be_tag;
};
-/* Shortened extent used by LAYOUTCOMMIT */
-struct pnfs_block_short_extent {
- struct list_head bse_node;
- struct nfs4_deviceid bse_devid;
- struct block_device *bse_mdev;
- sector_t bse_f_offset; /* the starting offset in the file */
- sector_t bse_length; /* the size of the extent */
-};
-
-static inline void
-BL_INIT_INVAL_MARKS(struct pnfs_inval_markings *marks, sector_t blocksize)
-{
- spin_lock_init(&marks->im_lock);
- INIT_LIST_HEAD(&marks->im_tree.mtt_stub);
- INIT_LIST_HEAD(&marks->im_extents);
- marks->im_block_size = blocksize;
- marks->im_tree.mtt_step_size = min((sector_t)PAGE_CACHE_SECTORS,
- blocksize);
-}
-
-enum extentclass4 {
- RW_EXTENT = 0, /* READWRTE and INVAL */
- RO_EXTENT = 1, /* READ and NONE */
- EXTENT_LISTS = 2,
-};
-
-static inline int bl_choose_list(enum exstate4 state)
-{
- if (state == PNFS_BLOCK_READ_DATA || state == PNFS_BLOCK_NONE_DATA)
- return RO_EXTENT;
- else
- return RW_EXTENT;
-}
+/* on the wire size of the extent */
+#define BL_EXTENT_SIZE (7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE)
struct pnfs_block_layout {
- struct pnfs_layout_hdr bl_layout;
- struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */
+ struct pnfs_layout_hdr bl_layout;
+ struct rb_root bl_ext_rw;
+ struct rb_root bl_ext_ro;
spinlock_t bl_ext_lock; /* Protects list manipulation */
- struct list_head bl_extents[EXTENT_LISTS]; /* R and RW extents */
- struct list_head bl_commit; /* Needs layout commit */
- struct list_head bl_committing; /* Layout committing */
- unsigned int bl_count; /* entries in bl_commit */
- sector_t bl_blocksize; /* Server blocksize in sectors */
};
-#define BLK_ID(lo) ((struct block_mount_id *)(NFS_SERVER(lo->plh_inode)->pnfs_ld_data))
-
static inline struct pnfs_block_layout *
BLK_LO2EXT(struct pnfs_layout_hdr *lo)
{
@@ -171,41 +178,27 @@ struct bl_msg_hdr {
#define BL_DEVICE_REQUEST_PROC 0x1 /* User level process succeeds */
#define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */
-/* blocklayoutdev.c */
-ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
-void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
-void nfs4_blkdev_put(struct block_device *bdev);
-struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
- struct pnfs_device *dev);
-int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
- struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
-
-/* blocklayoutdm.c */
-void bl_free_block_dev(struct pnfs_block_dev *bdev);
-
-/* extents.c */
-struct pnfs_block_extent *
-bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
- struct pnfs_block_extent **cow_read);
-int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
- sector_t offset, sector_t length);
-void bl_put_extent(struct pnfs_block_extent *be);
-struct pnfs_block_extent *bl_alloc_extent(void);
-int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect);
-int encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
- struct xdr_stream *xdr,
- const struct nfs4_layoutcommit_args *arg);
-void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
- const struct nfs4_layoutcommit_args *arg,
- int status);
-int bl_add_merge_extent(struct pnfs_block_layout *bl,
- struct pnfs_block_extent *new);
-int bl_mark_for_commit(struct pnfs_block_extent *be,
- sector_t offset, sector_t length,
- struct pnfs_block_short_extent *new);
-int bl_push_one_short_extent(struct pnfs_inval_markings *marks);
-struct pnfs_block_short_extent *
-bl_pop_one_short_extent(struct pnfs_inval_markings *marks);
-void bl_free_short_extents(struct pnfs_inval_markings *marks, int num_to_free);
+/* dev.c */
+struct nfs4_deviceid_node *bl_alloc_deviceid_node(struct nfs_server *server,
+ struct pnfs_device *pdev, gfp_t gfp_mask);
+void bl_free_deviceid_node(struct nfs4_deviceid_node *d);
+
+/* extent_tree.c */
+int ext_tree_insert(struct pnfs_block_layout *bl,
+ struct pnfs_block_extent *new);
+int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start,
+ sector_t end);
+int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
+ sector_t len);
+bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
+ struct pnfs_block_extent *ret, bool rw);
+int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
+void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status);
+
+/* rpc_pipefs.c */
+dev_t bl_resolve_deviceid(struct nfs_server *server,
+ struct pnfs_block_volume *b, gfp_t gfp_mask);
+int __init bl_init_pipefs(void);
+void __exit bl_cleanup_pipefs(void);
#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
deleted file mode 100644
index 04303b5c9361..000000000000
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ /dev/null
@@ -1,384 +0,0 @@
-/*
- * linux/fs/nfs/blocklayout/blocklayoutdev.c
- *
- * Device operations for the pnfs nfs4 file layout driver.
- *
- * Copyright (c) 2006 The Regents of the University of Michigan.
- * All rights reserved.
- *
- * Andy Adamson <andros@citi.umich.edu>
- * Fred Isaman <iisaman@umich.edu>
- *
- * permission is granted to use, copy, create derivative works and
- * redistribute this software and such derivative works for any purpose,
- * so long as the name of the university of michigan is not used in
- * any advertising or publicity pertaining to the use or distribution
- * of this software without specific, written prior authorization. if
- * the above copyright notice or any other identification of the
- * university of michigan is included in any copy of any portion of
- * this software, then the disclaimer below must also be included.
- *
- * this software is provided as is, without representation from the
- * university of michigan as to its fitness for any purpose, and without
- * warranty by the university of michigan of any kind, either express
- * or implied, including without limitation the implied warranties of
- * merchantability and fitness for a particular purpose. the regents
- * of the university of michigan shall not be liable for any damages,
- * including special, indirect, incidental, or consequential damages,
- * with respect to any claim arising out or in connection with the use
- * of the software, even if it has been or is hereafter advised of the
- * possibility of such damages.
- */
-#include <linux/module.h>
-#include <linux/buffer_head.h> /* __bread */
-
-#include <linux/genhd.h>
-#include <linux/blkdev.h>
-#include <linux/hash.h>
-
-#include "blocklayout.h"
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-
-static int decode_sector_number(__be32 **rp, sector_t *sp)
-{
- uint64_t s;
-
- *rp = xdr_decode_hyper(*rp, &s);
- if (s & 0x1ff) {
- printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
- return -1;
- }
- *sp = s >> SECTOR_SHIFT;
- return 0;
-}
-
-/*
- * Release the block device
- */
-void nfs4_blkdev_put(struct block_device *bdev)
-{
- dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev),
- MINOR(bdev->bd_dev));
- blkdev_put(bdev, FMODE_READ);
-}
-
-ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
- size_t mlen)
-{
- struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
- nfs_net_id);
-
- if (mlen != sizeof (struct bl_dev_msg))
- return -EINVAL;
-
- if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0)
- return -EFAULT;
-
- wake_up(&nn->bl_wq);
-
- return mlen;
-}
-
-void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
-{
- struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg);
-
- if (msg->errno >= 0)
- return;
- wake_up(bl_pipe_msg->bl_wq);
-}
-
-/*
- * Decodes pnfs_block_deviceaddr4 which is XDR encoded in dev->dev_addr_buf.
- */
-struct pnfs_block_dev *
-nfs4_blk_decode_device(struct nfs_server *server,
- struct pnfs_device *dev)
-{
- struct pnfs_block_dev *rv;
- struct block_device *bd = NULL;
- struct bl_pipe_msg bl_pipe_msg;
- struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
- struct bl_msg_hdr bl_msg = {
- .type = BL_DEVICE_MOUNT,
- .totallen = dev->mincount,
- };
- uint8_t *dataptr;
- DECLARE_WAITQUEUE(wq, current);
- int offset, len, i, rc;
- struct net *net = server->nfs_client->cl_net;
- struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct bl_dev_msg *reply = &nn->bl_mount_reply;
-
- dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
- dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
- dev->mincount);
-
- bl_pipe_msg.bl_wq = &nn->bl_wq;
- memset(msg, 0, sizeof(*msg));
- msg->data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
- if (!msg->data) {
- rv = ERR_PTR(-ENOMEM);
- goto out;
- }
-
- memcpy(msg->data, &bl_msg, sizeof(bl_msg));
- dataptr = (uint8_t *) msg->data;
- len = dev->mincount;
- offset = sizeof(bl_msg);
- for (i = 0; len > 0; i++) {
- memcpy(&dataptr[offset], page_address(dev->pages[i]),
- len < PAGE_CACHE_SIZE ? len : PAGE_CACHE_SIZE);
- len -= PAGE_CACHE_SIZE;
- offset += PAGE_CACHE_SIZE;
- }
- msg->len = sizeof(bl_msg) + dev->mincount;
-
- dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
- add_wait_queue(&nn->bl_wq, &wq);
- rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
- if (rc < 0) {
- remove_wait_queue(&nn->bl_wq, &wq);
- rv = ERR_PTR(rc);
- goto out;
- }
-
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule();
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&nn->bl_wq, &wq);
-
- if (reply->status != BL_DEVICE_REQUEST_PROC) {
- dprintk("%s failed to open device: %d\n",
- __func__, reply->status);
- rv = ERR_PTR(-EINVAL);
- goto out;
- }
-
- bd = blkdev_get_by_dev(MKDEV(reply->major, reply->minor),
- FMODE_READ, NULL);
- if (IS_ERR(bd)) {
- dprintk("%s failed to open device : %ld\n", __func__,
- PTR_ERR(bd));
- rv = ERR_CAST(bd);
- goto out;
- }
-
- rv = kzalloc(sizeof(*rv), GFP_NOFS);
- if (!rv) {
- rv = ERR_PTR(-ENOMEM);
- goto out;
- }
-
- rv->bm_mdev = bd;
- memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid));
- rv->net = net;
- dprintk("%s Created device %s with bd_block_size %u\n",
- __func__,
- bd->bd_disk->disk_name,
- bd->bd_block_size);
-
-out:
- kfree(msg->data);
- return rv;
-}
-
-/* Map deviceid returned by the server to constructed block_device */
-static struct block_device *translate_devid(struct pnfs_layout_hdr *lo,
- struct nfs4_deviceid *id)
-{
- struct block_device *rv = NULL;
- struct block_mount_id *mid;
- struct pnfs_block_dev *dev;
-
- dprintk("%s enter, lo=%p, id=%p\n", __func__, lo, id);
- mid = BLK_ID(lo);
- spin_lock(&mid->bm_lock);
- list_for_each_entry(dev, &mid->bm_devlist, bm_node) {
- if (memcmp(id->data, dev->bm_mdevid.data,
- NFS4_DEVICEID4_SIZE) == 0) {
- rv = dev->bm_mdev;
- goto out;
- }
- }
- out:
- spin_unlock(&mid->bm_lock);
- dprintk("%s returning %p\n", __func__, rv);
- return rv;
-}
-
-/* Tracks info needed to ensure extents in layout obey constraints of spec */
-struct layout_verification {
- u32 mode; /* R or RW */
- u64 start; /* Expected start of next non-COW extent */
- u64 inval; /* Start of INVAL coverage */
- u64 cowread; /* End of COW read coverage */
-};
-
-/* Verify the extent meets the layout requirements of the pnfs-block draft,
- * section 2.3.1.
- */
-static int verify_extent(struct pnfs_block_extent *be,
- struct layout_verification *lv)
-{
- if (lv->mode == IOMODE_READ) {
- if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
- be->be_state == PNFS_BLOCK_INVALID_DATA)
- return -EIO;
- if (be->be_f_offset != lv->start)
- return -EIO;
- lv->start += be->be_length;
- return 0;
- }
- /* lv->mode == IOMODE_RW */
- if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
- if (be->be_f_offset != lv->start)
- return -EIO;
- if (lv->cowread > lv->start)
- return -EIO;
- lv->start += be->be_length;
- lv->inval = lv->start;
- return 0;
- } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
- if (be->be_f_offset != lv->start)
- return -EIO;
- lv->start += be->be_length;
- return 0;
- } else if (be->be_state == PNFS_BLOCK_READ_DATA) {
- if (be->be_f_offset > lv->start)
- return -EIO;
- if (be->be_f_offset < lv->inval)
- return -EIO;
- if (be->be_f_offset < lv->cowread)
- return -EIO;
- /* It looks like you might want to min this with lv->start,
- * but you really don't.
- */
- lv->inval = lv->inval + be->be_length;
- lv->cowread = be->be_f_offset + be->be_length;
- return 0;
- } else
- return -EIO;
-}
-
-/* XDR decode pnfs_block_layout4 structure */
-int
-nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
- struct nfs4_layoutget_res *lgr, gfp_t gfp_flags)
-{
- struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
- int i, status = -EIO;
- uint32_t count;
- struct pnfs_block_extent *be = NULL, *save;
- struct xdr_stream stream;
- struct xdr_buf buf;
- struct page *scratch;
- __be32 *p;
- struct layout_verification lv = {
- .mode = lgr->range.iomode,
- .start = lgr->range.offset >> SECTOR_SHIFT,
- .inval = lgr->range.offset >> SECTOR_SHIFT,
- .cowread = lgr->range.offset >> SECTOR_SHIFT,
- };
- LIST_HEAD(extents);
-
- dprintk("---> %s\n", __func__);
-
- scratch = alloc_page(gfp_flags);
- if (!scratch)
- return -ENOMEM;
-
- xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
- xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
-
- p = xdr_inline_decode(&stream, 4);
- if (unlikely(!p))
- goto out_err;
-
- count = be32_to_cpup(p++);
-
- dprintk("%s enter, number of extents %i\n", __func__, count);
- p = xdr_inline_decode(&stream, (28 + NFS4_DEVICEID4_SIZE) * count);
- if (unlikely(!p))
- goto out_err;
-
- /* Decode individual extents, putting them in temporary
- * staging area until whole layout is decoded to make error
- * recovery easier.
- */
- for (i = 0; i < count; i++) {
- be = bl_alloc_extent();
- if (!be) {
- status = -ENOMEM;
- goto out_err;
- }
- memcpy(&be->be_devid, p, NFS4_DEVICEID4_SIZE);
- p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
- be->be_mdev = translate_devid(lo, &be->be_devid);
- if (!be->be_mdev)
- goto out_err;
-
- /* The next three values are read in as bytes,
- * but stored as 512-byte sector lengths
- */
- if (decode_sector_number(&p, &be->be_f_offset) < 0)
- goto out_err;
- if (decode_sector_number(&p, &be->be_length) < 0)
- goto out_err;
- if (decode_sector_number(&p, &be->be_v_offset) < 0)
- goto out_err;
- be->be_state = be32_to_cpup(p++);
- if (be->be_state == PNFS_BLOCK_INVALID_DATA)
- be->be_inval = &bl->bl_inval;
- if (verify_extent(be, &lv)) {
- dprintk("%s verify failed\n", __func__);
- goto out_err;
- }
- list_add_tail(&be->be_node, &extents);
- }
- if (lgr->range.offset + lgr->range.length !=
- lv.start << SECTOR_SHIFT) {
- dprintk("%s Final length mismatch\n", __func__);
- be = NULL;
- goto out_err;
- }
- if (lv.start < lv.cowread) {
- dprintk("%s Final uncovered COW extent\n", __func__);
- be = NULL;
- goto out_err;
- }
- /* Extents decoded properly, now try to merge them in to
- * existing layout extents.
- */
- spin_lock(&bl->bl_ext_lock);
- list_for_each_entry_safe(be, save, &extents, be_node) {
- list_del(&be->be_node);
- status = bl_add_merge_extent(bl, be);
- if (status) {
- spin_unlock(&bl->bl_ext_lock);
- /* This is a fairly catastrophic error, as the
- * entire layout extent lists are now corrupted.
- * We should have some way to distinguish this.
- */
- be = NULL;
- goto out_err;
- }
- }
- spin_unlock(&bl->bl_ext_lock);
- status = 0;
- out:
- __free_page(scratch);
- dprintk("%s returns %i\n", __func__, status);
- return status;
-
- out_err:
- bl_put_extent(be);
- while (!list_empty(&extents)) {
- be = list_first_entry(&extents, struct pnfs_block_extent,
- be_node);
- list_del(&be->be_node);
- bl_put_extent(be);
- }
- goto out;
-}
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
deleted file mode 100644
index 8999cfddd866..000000000000
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- * linux/fs/nfs/blocklayout/blocklayoutdm.c
- *
- * Module for the NFSv4.1 pNFS block layout driver.
- *
- * Copyright (c) 2007 The Regents of the University of Michigan.
- * All rights reserved.
- *
- * Fred Isaman <iisaman@umich.edu>
- * Andy Adamson <andros@citi.umich.edu>
- *
- * permission is granted to use, copy, create derivative works and
- * redistribute this software and such derivative works for any purpose,
- * so long as the name of the university of michigan is not used in
- * any advertising or publicity pertaining to the use or distribution
- * of this software without specific, written prior authorization. if
- * the above copyright notice or any other identification of the
- * university of michigan is included in any copy of any portion of
- * this software, then the disclaimer below must also be included.
- *
- * this software is provided as is, without representation from the
- * university of michigan as to its fitness for any purpose, and without
- * warranty by the university of michigan of any kind, either express
- * or implied, including without limitation the implied warranties of
- * merchantability and fitness for a particular purpose. the regents
- * of the university of michigan shall not be liable for any damages,
- * including special, indirect, incidental, or consequential damages,
- * with respect to any claim arising out or in connection with the use
- * of the software, even if it has been or is hereafter advised of the
- * possibility of such damages.
- */
-
-#include <linux/genhd.h> /* gendisk - used in a dprintk*/
-#include <linux/sched.h>
-#include <linux/hash.h>
-
-#include "blocklayout.h"
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-
-static void dev_remove(struct net *net, dev_t dev)
-{
- struct bl_pipe_msg bl_pipe_msg;
- struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
- struct bl_dev_msg bl_umount_request;
- struct bl_msg_hdr bl_msg = {
- .type = BL_DEVICE_UMOUNT,
- .totallen = sizeof(bl_umount_request),
- };
- uint8_t *dataptr;
- DECLARE_WAITQUEUE(wq, current);
- struct nfs_net *nn = net_generic(net, nfs_net_id);
-
- dprintk("Entering %s\n", __func__);
-
- bl_pipe_msg.bl_wq = &nn->bl_wq;
- memset(msg, 0, sizeof(*msg));
- msg->len = sizeof(bl_msg) + bl_msg.totallen;
- msg->data = kzalloc(msg->len, GFP_NOFS);
- if (!msg->data)
- goto out;
-
- memset(&bl_umount_request, 0, sizeof(bl_umount_request));
- bl_umount_request.major = MAJOR(dev);
- bl_umount_request.minor = MINOR(dev);
-
- memcpy(msg->data, &bl_msg, sizeof(bl_msg));
- dataptr = (uint8_t *) msg->data;
- memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
-
- add_wait_queue(&nn->bl_wq, &wq);
- if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
- remove_wait_queue(&nn->bl_wq, &wq);
- goto out;
- }
-
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule();
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&nn->bl_wq, &wq);
-
-out:
- kfree(msg->data);
-}
-
-/*
- * Release meta device
- */
-static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
-{
- dprintk("%s Releasing\n", __func__);
- nfs4_blkdev_put(bdev->bm_mdev);
- dev_remove(bdev->net, bdev->bm_mdev->bd_dev);
-}
-
-void bl_free_block_dev(struct pnfs_block_dev *bdev)
-{
- if (bdev) {
- if (bdev->bm_mdev) {
- dprintk("%s Removing DM device: %d:%d\n",
- __func__,
- MAJOR(bdev->bm_mdev->bd_dev),
- MINOR(bdev->bm_mdev->bd_dev));
- nfs4_blk_metadev_release(bdev);
- }
- kfree(bdev);
- }
-}
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
new file mode 100644
index 000000000000..5aed4f98df41
--- /dev/null
+++ b/fs/nfs/blocklayout/dev.c
@@ -0,0 +1,363 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/blkdev.h>
+#include <linux/nfs4.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_xdr.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY NFSDBG_PNFS_LD
+
+static void
+bl_free_device(struct pnfs_block_dev *dev)
+{
+ if (dev->nr_children) {
+ int i;
+
+ for (i = 0; i < dev->nr_children; i++)
+ bl_free_device(&dev->children[i]);
+ kfree(dev->children);
+ } else {
+ if (dev->bdev)
+ blkdev_put(dev->bdev, FMODE_READ);
+ }
+}
+
+void
+bl_free_deviceid_node(struct nfs4_deviceid_node *d)
+{
+ struct pnfs_block_dev *dev =
+ container_of(d, struct pnfs_block_dev, node);
+
+ bl_free_device(dev);
+ kfree(dev);
+}
+
+static int
+nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
+{
+ __be32 *p;
+ int i;
+
+ p = xdr_inline_decode(xdr, 4);
+ if (!p)
+ return -EIO;
+ b->type = be32_to_cpup(p++);
+
+ switch (b->type) {
+ case PNFS_BLOCK_VOLUME_SIMPLE:
+ p = xdr_inline_decode(xdr, 4);
+ if (!p)
+ return -EIO;
+ b->simple.nr_sigs = be32_to_cpup(p++);
+ if (!b->simple.nr_sigs) {
+ dprintk("no signature\n");
+ return -EIO;
+ }
+
+ b->simple.len = 4 + 4;
+ for (i = 0; i < b->simple.nr_sigs; i++) {
+ p = xdr_inline_decode(xdr, 8 + 4);
+ if (!p)
+ return -EIO;
+ p = xdr_decode_hyper(p, &b->simple.sigs[i].offset);
+ b->simple.sigs[i].sig_len = be32_to_cpup(p++);
+
+ p = xdr_inline_decode(xdr, b->simple.sigs[i].sig_len);
+ if (!p)
+ return -EIO;
+ memcpy(&b->simple.sigs[i].sig, p,
+ b->simple.sigs[i].sig_len);
+
+ b->simple.len += 8 + 4 + b->simple.sigs[i].sig_len;
+ }
+ break;
+ case PNFS_BLOCK_VOLUME_SLICE:
+ p = xdr_inline_decode(xdr, 8 + 8 + 4);
+ if (!p)
+ return -EIO;
+ p = xdr_decode_hyper(p, &b->slice.start);
+ p = xdr_decode_hyper(p, &b->slice.len);
+ b->slice.volume = be32_to_cpup(p++);
+ break;
+ case PNFS_BLOCK_VOLUME_CONCAT:
+ p = xdr_inline_decode(xdr, 4);
+ if (!p)
+ return -EIO;
+ b->concat.volumes_count = be32_to_cpup(p++);
+
+ p = xdr_inline_decode(xdr, b->concat.volumes_count * 4);
+ if (!p)
+ return -EIO;
+ for (i = 0; i < b->concat.volumes_count; i++)
+ b->concat.volumes[i] = be32_to_cpup(p++);
+ break;
+ case PNFS_BLOCK_VOLUME_STRIPE:
+ p = xdr_inline_decode(xdr, 8 + 4);
+ if (!p)
+ return -EIO;
+ p = xdr_decode_hyper(p, &b->stripe.chunk_size);
+ b->stripe.volumes_count = be32_to_cpup(p++);
+
+ p = xdr_inline_decode(xdr, b->stripe.volumes_count * 4);
+ if (!p)
+ return -EIO;
+ for (i = 0; i < b->stripe.volumes_count; i++)
+ b->stripe.volumes[i] = be32_to_cpup(p++);
+ break;
+ default:
+ dprintk("unknown volume type!\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset,
+ struct pnfs_block_dev_map *map)
+{
+ map->start = dev->start;
+ map->len = dev->len;
+ map->disk_offset = dev->disk_offset;
+ map->bdev = dev->bdev;
+ return true;
+}
+
+static bool bl_map_concat(struct pnfs_block_dev *dev, u64 offset,
+ struct pnfs_block_dev_map *map)
+{
+ int i;
+
+ for (i = 0; i < dev->nr_children; i++) {
+ struct pnfs_block_dev *child = &dev->children[i];
+
+ if (child->start > offset ||
+ child->start + child->len <= offset)
+ continue;
+
+ child->map(child, offset - child->start, map);
+ return true;
+ }
+
+ dprintk("%s: ran off loop!\n", __func__);
+ return false;
+}
+
+static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
+ struct pnfs_block_dev_map *map)
+{
+ struct pnfs_block_dev *child;
+ u64 chunk;
+ u32 chunk_idx;
+ u64 disk_offset;
+
+ chunk = div_u64(offset, dev->chunk_size);
+ div_u64_rem(chunk, dev->nr_children, &chunk_idx);
+
+ if (chunk_idx > dev->nr_children) {
+ dprintk("%s: invalid chunk idx %d (%lld/%lld)\n",
+ __func__, chunk_idx, offset, dev->chunk_size);
+ /* error, should not happen */
+ return false;
+ }
+
+ /* truncate offset to the beginning of the stripe */
+ offset = chunk * dev->chunk_size;
+
+ /* disk offset of the stripe */
+ disk_offset = div_u64(offset, dev->nr_children);
+
+ child = &dev->children[chunk_idx];
+ child->map(child, disk_offset, map);
+
+ map->start += offset;
+ map->disk_offset += disk_offset;
+ map->len = dev->chunk_size;
+ return true;
+}
+
+static int
+bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
+ struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask);
+
+
+static int
+bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
+ struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
+{
+ struct pnfs_block_volume *v = &volumes[idx];
+ dev_t dev;
+
+ dev = bl_resolve_deviceid(server, v, gfp_mask);
+ if (!dev)
+ return -EIO;
+
+ d->bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+ if (IS_ERR(d->bdev)) {
+ printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
+ MAJOR(dev), MINOR(dev), PTR_ERR(d->bdev));
+ return PTR_ERR(d->bdev);
+ }
+
+
+ d->len = i_size_read(d->bdev->bd_inode);
+ d->map = bl_map_simple;
+
+ printk(KERN_INFO "pNFS: using block device %s\n",
+ d->bdev->bd_disk->disk_name);
+ return 0;
+}
+
+static int
+bl_parse_slice(struct nfs_server *server, struct pnfs_block_dev *d,
+ struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
+{
+ struct pnfs_block_volume *v = &volumes[idx];
+ int ret;
+
+ ret = bl_parse_deviceid(server, d, volumes, v->slice.volume, gfp_mask);
+ if (ret)
+ return ret;
+
+ d->disk_offset = v->slice.start;
+ d->len = v->slice.len;
+ return 0;
+}
+
+static int
+bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d,
+ struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
+{
+ struct pnfs_block_volume *v = &volumes[idx];
+ u64 len = 0;
+ int ret, i;
+
+ d->children = kcalloc(v->concat.volumes_count,
+ sizeof(struct pnfs_block_dev), GFP_KERNEL);
+ if (!d->children)
+ return -ENOMEM;
+
+ for (i = 0; i < v->concat.volumes_count; i++) {
+ ret = bl_parse_deviceid(server, &d->children[i],
+ volumes, v->concat.volumes[i], gfp_mask);
+ if (ret)
+ return ret;
+
+ d->nr_children++;
+ d->children[i].start += len;
+ len += d->children[i].len;
+ }
+
+ d->len = len;
+ d->map = bl_map_concat;
+ return 0;
+}
+
+static int
+bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d,
+ struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
+{
+ struct pnfs_block_volume *v = &volumes[idx];
+ u64 len = 0;
+ int ret, i;
+
+ d->children = kcalloc(v->stripe.volumes_count,
+ sizeof(struct pnfs_block_dev), GFP_KERNEL);
+ if (!d->children)
+ return -ENOMEM;
+
+ for (i = 0; i < v->stripe.volumes_count; i++) {
+ ret = bl_parse_deviceid(server, &d->children[i],
+ volumes, v->stripe.volumes[i], gfp_mask);
+ if (ret)
+ return ret;
+
+ d->nr_children++;
+ len += d->children[i].len;
+ }
+
+ d->len = len;
+ d->chunk_size = v->stripe.chunk_size;
+ d->map = bl_map_stripe;
+ return 0;
+}
+
+static int
+bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
+ struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
+{
+ switch (volumes[idx].type) {
+ case PNFS_BLOCK_VOLUME_SIMPLE:
+ return bl_parse_simple(server, d, volumes, idx, gfp_mask);
+ case PNFS_BLOCK_VOLUME_SLICE:
+ return bl_parse_slice(server, d, volumes, idx, gfp_mask);
+ case PNFS_BLOCK_VOLUME_CONCAT:
+ return bl_parse_concat(server, d, volumes, idx, gfp_mask);
+ case PNFS_BLOCK_VOLUME_STRIPE:
+ return bl_parse_stripe(server, d, volumes, idx, gfp_mask);
+ default:
+ dprintk("unsupported volume type: %d\n", volumes[idx].type);
+ return -EIO;
+ }
+}
+
+struct nfs4_deviceid_node *
+bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+ gfp_t gfp_mask)
+{
+ struct nfs4_deviceid_node *node = NULL;
+ struct pnfs_block_volume *volumes;
+ struct pnfs_block_dev *top;
+ struct xdr_stream xdr;
+ struct xdr_buf buf;
+ struct page *scratch;
+ int nr_volumes, ret, i;
+ __be32 *p;
+
+ scratch = alloc_page(gfp_mask);
+ if (!scratch)
+ goto out;
+
+ xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen);
+ xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
+
+ p = xdr_inline_decode(&xdr, sizeof(__be32));
+ if (!p)
+ goto out_free_scratch;
+ nr_volumes = be32_to_cpup(p++);
+
+ volumes = kcalloc(nr_volumes, sizeof(struct pnfs_block_volume),
+ gfp_mask);
+ if (!volumes)
+ goto out_free_scratch;
+
+ for (i = 0; i < nr_volumes; i++) {
+ ret = nfs4_block_decode_volume(&xdr, &volumes[i]);
+ if (ret < 0)
+ goto out_free_volumes;
+ }
+
+ top = kzalloc(sizeof(*top), gfp_mask);
+ if (!top)
+ goto out_free_volumes;
+
+ ret = bl_parse_deviceid(server, top, volumes, nr_volumes - 1, gfp_mask);
+ if (ret) {
+ bl_free_device(top);
+ kfree(top);
+ goto out_free_volumes;
+ }
+
+ node = &top->node;
+ nfs4_init_deviceid_node(node, server, &pdev->dev_id);
+
+out_free_volumes:
+ kfree(volumes);
+out_free_scratch:
+ __free_page(scratch);
+out:
+ return node;
+}
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
new file mode 100644
index 000000000000..31d0b5e53dfd
--- /dev/null
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -0,0 +1,602 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+
+#include <linux/vmalloc.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY NFSDBG_PNFS_LD
+
+static inline struct pnfs_block_extent *
+ext_node(struct rb_node *node)
+{
+ return rb_entry(node, struct pnfs_block_extent, be_node);
+}
+
+static struct pnfs_block_extent *
+ext_tree_first(struct rb_root *root)
+{
+ struct rb_node *node = rb_first(root);
+ return node ? ext_node(node) : NULL;
+}
+
+static struct pnfs_block_extent *
+ext_tree_prev(struct pnfs_block_extent *be)
+{
+ struct rb_node *node = rb_prev(&be->be_node);
+ return node ? ext_node(node) : NULL;
+}
+
+static struct pnfs_block_extent *
+ext_tree_next(struct pnfs_block_extent *be)
+{
+ struct rb_node *node = rb_next(&be->be_node);
+ return node ? ext_node(node) : NULL;
+}
+
+static inline sector_t
+ext_f_end(struct pnfs_block_extent *be)
+{
+ return be->be_f_offset + be->be_length;
+}
+
+static struct pnfs_block_extent *
+__ext_tree_search(struct rb_root *root, sector_t start)
+{
+ struct rb_node *node = root->rb_node;
+ struct pnfs_block_extent *be = NULL;
+
+ while (node) {
+ be = ext_node(node);
+ if (start < be->be_f_offset)
+ node = node->rb_left;
+ else if (start >= ext_f_end(be))
+ node = node->rb_right;
+ else
+ return be;
+ }
+
+ if (be) {
+ if (start < be->be_f_offset)
+ return be;
+
+ if (start >= ext_f_end(be))
+ return ext_tree_next(be);
+ }
+
+ return NULL;
+}
+
+static bool
+ext_can_merge(struct pnfs_block_extent *be1, struct pnfs_block_extent *be2)
+{
+ if (be1->be_state != be2->be_state)
+ return false;
+ if (be1->be_device != be2->be_device)
+ return false;
+
+ if (be1->be_f_offset + be1->be_length != be2->be_f_offset)
+ return false;
+
+ if (be1->be_state != PNFS_BLOCK_NONE_DATA &&
+ (be1->be_v_offset + be1->be_length != be2->be_v_offset))
+ return false;
+
+ if (be1->be_state == PNFS_BLOCK_INVALID_DATA &&
+ be1->be_tag != be2->be_tag)
+ return false;
+
+ return true;
+}
+
+static struct pnfs_block_extent *
+ext_try_to_merge_left(struct rb_root *root, struct pnfs_block_extent *be)
+{
+ struct pnfs_block_extent *left = ext_tree_prev(be);
+
+ if (left && ext_can_merge(left, be)) {
+ left->be_length += be->be_length;
+ rb_erase(&be->be_node, root);
+ nfs4_put_deviceid_node(be->be_device);
+ kfree(be);
+ return left;
+ }
+
+ return be;
+}
+
+static struct pnfs_block_extent *
+ext_try_to_merge_right(struct rb_root *root, struct pnfs_block_extent *be)
+{
+ struct pnfs_block_extent *right = ext_tree_next(be);
+
+ if (right && ext_can_merge(be, right)) {
+ be->be_length += right->be_length;
+ rb_erase(&right->be_node, root);
+ nfs4_put_deviceid_node(right->be_device);
+ kfree(right);
+ }
+
+ return be;
+}
+
+static void
+__ext_tree_insert(struct rb_root *root,
+ struct pnfs_block_extent *new, bool merge_ok)
+{
+ struct rb_node **p = &root->rb_node, *parent = NULL;
+ struct pnfs_block_extent *be;
+
+ while (*p) {
+ parent = *p;
+ be = ext_node(parent);
+
+ if (new->be_f_offset < be->be_f_offset) {
+ if (merge_ok && ext_can_merge(new, be)) {
+ be->be_f_offset = new->be_f_offset;
+ if (be->be_state != PNFS_BLOCK_NONE_DATA)
+ be->be_v_offset = new->be_v_offset;
+ be->be_length += new->be_length;
+ be = ext_try_to_merge_left(root, be);
+ goto free_new;
+ }
+ p = &(*p)->rb_left;
+ } else if (new->be_f_offset >= ext_f_end(be)) {
+ if (merge_ok && ext_can_merge(be, new)) {
+ be->be_length += new->be_length;
+ be = ext_try_to_merge_right(root, be);
+ goto free_new;
+ }
+ p = &(*p)->rb_right;
+ } else {
+ BUG();
+ }
+ }
+
+ rb_link_node(&new->be_node, parent, p);
+ rb_insert_color(&new->be_node, root);
+ return;
+free_new:
+ nfs4_put_deviceid_node(new->be_device);
+ kfree(new);
+}
+
+static int
+__ext_tree_remove(struct rb_root *root, sector_t start, sector_t end)
+{
+ struct pnfs_block_extent *be;
+ sector_t len1 = 0, len2 = 0;
+ sector_t orig_v_offset;
+ sector_t orig_len;
+
+ be = __ext_tree_search(root, start);
+ if (!be)
+ return 0;
+ if (be->be_f_offset >= end)
+ return 0;
+
+ orig_v_offset = be->be_v_offset;
+ orig_len = be->be_length;
+
+ if (start > be->be_f_offset)
+ len1 = start - be->be_f_offset;
+ if (ext_f_end(be) > end)
+ len2 = ext_f_end(be) - end;
+
+ if (len2 > 0) {
+ if (len1 > 0) {
+ struct pnfs_block_extent *new;
+
+ new = kzalloc(sizeof(*new), GFP_ATOMIC);
+ if (!new)
+ return -ENOMEM;
+
+ be->be_length = len1;
+
+ new->be_f_offset = end;
+ if (be->be_state != PNFS_BLOCK_NONE_DATA) {
+ new->be_v_offset =
+ orig_v_offset + orig_len - len2;
+ }
+ new->be_length = len2;
+ new->be_state = be->be_state;
+ new->be_tag = be->be_tag;
+ new->be_device = nfs4_get_deviceid(be->be_device);
+
+ __ext_tree_insert(root, new, true);
+ } else {
+ be->be_f_offset = end;
+ if (be->be_state != PNFS_BLOCK_NONE_DATA) {
+ be->be_v_offset =
+ orig_v_offset + orig_len - len2;
+ }
+ be->be_length = len2;
+ }
+ } else {
+ if (len1 > 0) {
+ be->be_length = len1;
+ be = ext_tree_next(be);
+ }
+
+ while (be && ext_f_end(be) <= end) {
+ struct pnfs_block_extent *next = ext_tree_next(be);
+
+ rb_erase(&be->be_node, root);
+ nfs4_put_deviceid_node(be->be_device);
+ kfree(be);
+ be = next;
+ }
+
+ if (be && be->be_f_offset < end) {
+ len1 = ext_f_end(be) - end;
+ be->be_f_offset = end;
+ if (be->be_state != PNFS_BLOCK_NONE_DATA)
+ be->be_v_offset += be->be_length - len1;
+ be->be_length = len1;
+ }
+ }
+
+ return 0;
+}
+
+int
+ext_tree_insert(struct pnfs_block_layout *bl, struct pnfs_block_extent *new)
+{
+ struct pnfs_block_extent *be;
+ struct rb_root *root;
+ int err = 0;
+
+ switch (new->be_state) {
+ case PNFS_BLOCK_READWRITE_DATA:
+ case PNFS_BLOCK_INVALID_DATA:
+ root = &bl->bl_ext_rw;
+ break;
+ case PNFS_BLOCK_READ_DATA:
+ case PNFS_BLOCK_NONE_DATA:
+ root = &bl->bl_ext_ro;
+ break;
+ default:
+ dprintk("invalid extent type\n");
+ return -EINVAL;
+ }
+
+ spin_lock(&bl->bl_ext_lock);
+retry:
+ be = __ext_tree_search(root, new->be_f_offset);
+ if (!be || be->be_f_offset >= ext_f_end(new)) {
+ __ext_tree_insert(root, new, true);
+ } else if (new->be_f_offset >= be->be_f_offset) {
+ if (ext_f_end(new) <= ext_f_end(be)) {
+ nfs4_put_deviceid_node(new->be_device);
+ kfree(new);
+ } else {
+ sector_t new_len = ext_f_end(new) - ext_f_end(be);
+ sector_t diff = new->be_length - new_len;
+
+ new->be_f_offset += diff;
+ new->be_v_offset += diff;
+ new->be_length = new_len;
+ goto retry;
+ }
+ } else if (ext_f_end(new) <= ext_f_end(be)) {
+ new->be_length = be->be_f_offset - new->be_f_offset;
+ __ext_tree_insert(root, new, true);
+ } else {
+ struct pnfs_block_extent *split;
+ sector_t new_len = ext_f_end(new) - ext_f_end(be);
+ sector_t diff = new->be_length - new_len;
+
+ split = kmemdup(new, sizeof(*new), GFP_ATOMIC);
+ if (!split) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ split->be_length = be->be_f_offset - split->be_f_offset;
+ split->be_device = nfs4_get_deviceid(new->be_device);
+ __ext_tree_insert(root, split, true);
+
+ new->be_f_offset += diff;
+ new->be_v_offset += diff;
+ new->be_length = new_len;
+ goto retry;
+ }
+out:
+ spin_unlock(&bl->bl_ext_lock);
+ return err;
+}
+
+static bool
+__ext_tree_lookup(struct rb_root *root, sector_t isect,
+ struct pnfs_block_extent *ret)
+{
+ struct rb_node *node;
+ struct pnfs_block_extent *be;
+
+ node = root->rb_node;
+ while (node) {
+ be = ext_node(node);
+ if (isect < be->be_f_offset)
+ node = node->rb_left;
+ else if (isect >= ext_f_end(be))
+ node = node->rb_right;
+ else {
+ *ret = *be;
+ return true;
+ }
+ }
+
+ return false;
+}
+
+bool
+ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
+ struct pnfs_block_extent *ret, bool rw)
+{
+ bool found = false;
+
+ spin_lock(&bl->bl_ext_lock);
+ if (!rw)
+ found = __ext_tree_lookup(&bl->bl_ext_ro, isect, ret);
+ if (!found)
+ found = __ext_tree_lookup(&bl->bl_ext_rw, isect, ret);
+ spin_unlock(&bl->bl_ext_lock);
+
+ return found;
+}
+
+int ext_tree_remove(struct pnfs_block_layout *bl, bool rw,
+ sector_t start, sector_t end)
+{
+ int err, err2;
+
+ spin_lock(&bl->bl_ext_lock);
+ err = __ext_tree_remove(&bl->bl_ext_ro, start, end);
+ if (rw) {
+ err2 = __ext_tree_remove(&bl->bl_ext_rw, start, end);
+ if (!err)
+ err = err2;
+ }
+ spin_unlock(&bl->bl_ext_lock);
+
+ return err;
+}
+
+static int
+ext_tree_split(struct rb_root *root, struct pnfs_block_extent *be,
+ sector_t split)
+{
+ struct pnfs_block_extent *new;
+ sector_t orig_len = be->be_length;
+
+ new = kzalloc(sizeof(*new), GFP_ATOMIC);
+ if (!new)
+ return -ENOMEM;
+
+ be->be_length = split - be->be_f_offset;
+
+ new->be_f_offset = split;
+ if (be->be_state != PNFS_BLOCK_NONE_DATA)
+ new->be_v_offset = be->be_v_offset + be->be_length;
+ new->be_length = orig_len - be->be_length;
+ new->be_state = be->be_state;
+ new->be_tag = be->be_tag;
+ new->be_device = nfs4_get_deviceid(be->be_device);
+
+ __ext_tree_insert(root, new, false);
+ return 0;
+}
+
+int
+ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
+ sector_t len)
+{
+ struct rb_root *root = &bl->bl_ext_rw;
+ sector_t end = start + len;
+ struct pnfs_block_extent *be;
+ int err = 0;
+
+ spin_lock(&bl->bl_ext_lock);
+ /*
+ * First remove all COW extents or holes from written to range.
+ */
+ err = __ext_tree_remove(&bl->bl_ext_ro, start, end);
+ if (err)
+ goto out;
+
+ /*
+ * Then mark all invalid extents in the range as written to.
+ */
+ for (be = __ext_tree_search(root, start); be; be = ext_tree_next(be)) {
+ if (be->be_f_offset >= end)
+ break;
+
+ if (be->be_state != PNFS_BLOCK_INVALID_DATA || be->be_tag)
+ continue;
+
+ if (be->be_f_offset < start) {
+ struct pnfs_block_extent *left = ext_tree_prev(be);
+
+ if (left && ext_can_merge(left, be)) {
+ sector_t diff = start - be->be_f_offset;
+
+ left->be_length += diff;
+
+ be->be_f_offset += diff;
+ be->be_v_offset += diff;
+ be->be_length -= diff;
+ } else {
+ err = ext_tree_split(root, be, start);
+ if (err)
+ goto out;
+ }
+ }
+
+ if (ext_f_end(be) > end) {
+ struct pnfs_block_extent *right = ext_tree_next(be);
+
+ if (right && ext_can_merge(be, right)) {
+ sector_t diff = end - be->be_f_offset;
+
+ be->be_length -= diff;
+
+ right->be_f_offset -= diff;
+ right->be_v_offset -= diff;
+ right->be_length += diff;
+ } else {
+ err = ext_tree_split(root, be, end);
+ if (err)
+ goto out;
+ }
+ }
+
+ if (be->be_f_offset >= start && ext_f_end(be) <= end) {
+ be->be_tag = EXTENT_WRITTEN;
+ be = ext_try_to_merge_left(root, be);
+ be = ext_try_to_merge_right(root, be);
+ }
+ }
+out:
+ spin_unlock(&bl->bl_ext_lock);
+ return err;
+}
+
+static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
+ size_t buffer_size)
+{
+ if (arg->layoutupdate_pages != &arg->layoutupdate_page) {
+ int nr_pages = DIV_ROUND_UP(buffer_size, PAGE_SIZE), i;
+
+ for (i = 0; i < nr_pages; i++)
+ put_page(arg->layoutupdate_pages[i]);
+ kfree(arg->layoutupdate_pages);
+ } else {
+ put_page(arg->layoutupdate_page);
+ }
+}
+
+static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+ size_t buffer_size, size_t *count)
+{
+ struct pnfs_block_extent *be;
+ int ret = 0;
+
+ spin_lock(&bl->bl_ext_lock);
+ for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+ if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+ be->be_tag != EXTENT_WRITTEN)
+ continue;
+
+ (*count)++;
+ if (*count * BL_EXTENT_SIZE > buffer_size) {
+ /* keep counting.. */
+ ret = -ENOSPC;
+ continue;
+ }
+
+ p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
+ NFS4_DEVICEID4_SIZE);
+ p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
+ p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
+ p = xdr_encode_hyper(p, 0LL);
+ *p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
+
+ be->be_tag = EXTENT_COMMITTING;
+ }
+ spin_unlock(&bl->bl_ext_lock);
+
+ return ret;
+}
+
+int
+ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
+{
+ struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout);
+ size_t count = 0, buffer_size = PAGE_SIZE;
+ __be32 *start_p;
+ int ret;
+
+ dprintk("%s enter\n", __func__);
+
+ arg->layoutupdate_page = alloc_page(GFP_NOFS);
+ if (!arg->layoutupdate_page)
+ return -ENOMEM;
+ start_p = page_address(arg->layoutupdate_page);
+ arg->layoutupdate_pages = &arg->layoutupdate_page;
+
+retry:
+ ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count);
+ if (unlikely(ret)) {
+ ext_tree_free_commitdata(arg, buffer_size);
+
+ buffer_size = sizeof(__be32) + BL_EXTENT_SIZE * count;
+ count = 0;
+
+ arg->layoutupdate_pages =
+ kcalloc(DIV_ROUND_UP(buffer_size, PAGE_SIZE),
+ sizeof(struct page *), GFP_NOFS);
+ if (!arg->layoutupdate_pages)
+ return -ENOMEM;
+
+ start_p = __vmalloc(buffer_size, GFP_NOFS, PAGE_KERNEL);
+ if (!start_p) {
+ kfree(arg->layoutupdate_pages);
+ return -ENOMEM;
+ }
+
+ goto retry;
+ }
+
+ *start_p = cpu_to_be32(count);
+ arg->layoutupdate_len = sizeof(__be32) + BL_EXTENT_SIZE * count;
+
+ if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) {
+ __be32 *p = start_p;
+ int i = 0;
+
+ for (p = start_p;
+ p < start_p + arg->layoutupdate_len;
+ p += PAGE_SIZE) {
+ arg->layoutupdate_pages[i++] = vmalloc_to_page(p);
+ }
+ }
+
+ dprintk("%s found %zu ranges\n", __func__, count);
+ return 0;
+}
+
+void
+ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status)
+{
+ struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout);
+ struct rb_root *root = &bl->bl_ext_rw;
+ struct pnfs_block_extent *be;
+
+ dprintk("%s status %d\n", __func__, status);
+
+ ext_tree_free_commitdata(arg, arg->layoutupdate_len);
+
+ spin_lock(&bl->bl_ext_lock);
+ for (be = ext_tree_first(root); be; be = ext_tree_next(be)) {
+ if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+ be->be_tag != EXTENT_COMMITTING)
+ continue;
+
+ if (status) {
+ /*
+ * Mark as written and try again.
+ *
+ * XXX: some real error handling here wouldn't hurt..
+ */
+ be->be_tag = EXTENT_WRITTEN;
+ } else {
+ be->be_state = PNFS_BLOCK_READWRITE_DATA;
+ be->be_tag = 0;
+ }
+
+ be = ext_try_to_merge_left(root, be);
+ be = ext_try_to_merge_right(root, be);
+ }
+ spin_unlock(&bl->bl_ext_lock);
+}
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
deleted file mode 100644
index 4d0161442565..000000000000
--- a/fs/nfs/blocklayout/extents.c
+++ /dev/null
@@ -1,908 +0,0 @@
-/*
- * linux/fs/nfs/blocklayout/blocklayout.h
- *
- * Module for the NFSv4.1 pNFS block layout driver.
- *
- * Copyright (c) 2006 The Regents of the University of Michigan.
- * All rights reserved.
- *
- * Andy Adamson <andros@citi.umich.edu>
- * Fred Isaman <iisaman@umich.edu>
- *
- * permission is granted to use, copy, create derivative works and
- * redistribute this software and such derivative works for any purpose,
- * so long as the name of the university of michigan is not used in
- * any advertising or publicity pertaining to the use or distribution
- * of this software without specific, written prior authorization. if
- * the above copyright notice or any other identification of the
- * university of michigan is included in any copy of any portion of
- * this software, then the disclaimer below must also be included.
- *
- * this software is provided as is, without representation from the
- * university of michigan as to its fitness for any purpose, and without
- * warranty by the university of michigan of any kind, either express
- * or implied, including without limitation the implied warranties of
- * merchantability and fitness for a particular purpose. the regents
- * of the university of michigan shall not be liable for any damages,
- * including special, indirect, incidental, or consequential damages,
- * with respect to any claim arising out or in connection with the use
- * of the software, even if it has been or is hereafter advised of the
- * possibility of such damages.
- */
-
-#include "blocklayout.h"
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-
-/* Bit numbers */
-#define EXTENT_INITIALIZED 0
-#define EXTENT_WRITTEN 1
-#define EXTENT_IN_COMMIT 2
-#define INTERNAL_EXISTS MY_MAX_TAGS
-#define INTERNAL_MASK ((1 << INTERNAL_EXISTS) - 1)
-
-/* Returns largest t<=s s.t. t%base==0 */
-static inline sector_t normalize(sector_t s, int base)
-{
- sector_t tmp = s; /* Since do_div modifies its argument */
- return s - sector_div(tmp, base);
-}
-
-static inline sector_t normalize_up(sector_t s, int base)
-{
- return normalize(s + base - 1, base);
-}
-
-/* Complete stub using list while determine API wanted */
-
-/* Returns tags, or negative */
-static int32_t _find_entry(struct my_tree *tree, u64 s)
-{
- struct pnfs_inval_tracking *pos;
-
- dprintk("%s(%llu) enter\n", __func__, s);
- list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
- if (pos->it_sector > s)
- continue;
- else if (pos->it_sector == s)
- return pos->it_tags & INTERNAL_MASK;
- else
- break;
- }
- return -ENOENT;
-}
-
-static inline
-int _has_tag(struct my_tree *tree, u64 s, int32_t tag)
-{
- int32_t tags;
-
- dprintk("%s(%llu, %i) enter\n", __func__, s, tag);
- s = normalize(s, tree->mtt_step_size);
- tags = _find_entry(tree, s);
- if ((tags < 0) || !(tags & (1 << tag)))
- return 0;
- else
- return 1;
-}
-
-/* Creates entry with tag, or if entry already exists, unions tag to it.
- * If storage is not NULL, newly created entry will use it.
- * Returns number of entries added, or negative on error.
- */
-static int _add_entry(struct my_tree *tree, u64 s, int32_t tag,
- struct pnfs_inval_tracking *storage)
-{
- int found = 0;
- struct pnfs_inval_tracking *pos;
-
- dprintk("%s(%llu, %i, %p) enter\n", __func__, s, tag, storage);
- list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
- if (pos->it_sector > s)
- continue;
- else if (pos->it_sector == s) {
- found = 1;
- break;
- } else
- break;
- }
- if (found) {
- pos->it_tags |= (1 << tag);
- return 0;
- } else {
- struct pnfs_inval_tracking *new;
- new = storage;
- new->it_sector = s;
- new->it_tags = (1 << tag);
- list_add(&new->it_link, &pos->it_link);
- return 1;
- }
-}
-
-/* XXXX Really want option to not create */
-/* Over range, unions tag with existing entries, else creates entry with tag */
-static int _set_range(struct my_tree *tree, int32_t tag, u64 s, u64 length)
-{
- u64 i;
-
- dprintk("%s(%i, %llu, %llu) enter\n", __func__, tag, s, length);
- for (i = normalize(s, tree->mtt_step_size); i < s + length;
- i += tree->mtt_step_size)
- if (_add_entry(tree, i, tag, NULL))
- return -ENOMEM;
- return 0;
-}
-
-/* Ensure that future operations on given range of tree will not malloc */
-static int _preload_range(struct pnfs_inval_markings *marks,
- u64 offset, u64 length)
-{
- u64 start, end, s;
- int count, i, used = 0, status = -ENOMEM;
- struct pnfs_inval_tracking **storage;
- struct my_tree *tree = &marks->im_tree;
-
- dprintk("%s(%llu, %llu) enter\n", __func__, offset, length);
- start = normalize(offset, tree->mtt_step_size);
- end = normalize_up(offset + length, tree->mtt_step_size);
- count = (int)(end - start) / (int)tree->mtt_step_size;
-
- /* Pre-malloc what memory we might need */
- storage = kcalloc(count, sizeof(*storage), GFP_NOFS);
- if (!storage)
- return -ENOMEM;
- for (i = 0; i < count; i++) {
- storage[i] = kmalloc(sizeof(struct pnfs_inval_tracking),
- GFP_NOFS);
- if (!storage[i])
- goto out_cleanup;
- }
-
- spin_lock_bh(&marks->im_lock);
- for (s = start; s < end; s += tree->mtt_step_size)
- used += _add_entry(tree, s, INTERNAL_EXISTS, storage[used]);
- spin_unlock_bh(&marks->im_lock);
-
- status = 0;
-
- out_cleanup:
- for (i = used; i < count; i++) {
- if (!storage[i])
- break;
- kfree(storage[i]);
- }
- kfree(storage);
- return status;
-}
-
-/* We are relying on page lock to serialize this */
-int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect)
-{
- int rv;
-
- spin_lock_bh(&marks->im_lock);
- rv = _has_tag(&marks->im_tree, isect, EXTENT_INITIALIZED);
- spin_unlock_bh(&marks->im_lock);
- return rv;
-}
-
-/* Assume start, end already sector aligned */
-static int
-_range_has_tag(struct my_tree *tree, u64 start, u64 end, int32_t tag)
-{
- struct pnfs_inval_tracking *pos;
- u64 expect = 0;
-
- dprintk("%s(%llu, %llu, %i) enter\n", __func__, start, end, tag);
- list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
- if (pos->it_sector >= end)
- continue;
- if (!expect) {
- if ((pos->it_sector == end - tree->mtt_step_size) &&
- (pos->it_tags & (1 << tag))) {
- expect = pos->it_sector - tree->mtt_step_size;
- if (pos->it_sector < tree->mtt_step_size || expect < start)
- return 1;
- continue;
- } else {
- return 0;
- }
- }
- if (pos->it_sector != expect || !(pos->it_tags & (1 << tag)))
- return 0;
- expect -= tree->mtt_step_size;
- if (expect < start)
- return 1;
- }
- return 0;
-}
-
-static int is_range_written(struct pnfs_inval_markings *marks,
- sector_t start, sector_t end)
-{
- int rv;
-
- spin_lock_bh(&marks->im_lock);
- rv = _range_has_tag(&marks->im_tree, start, end, EXTENT_WRITTEN);
- spin_unlock_bh(&marks->im_lock);
- return rv;
-}
-
-/* Marks sectors in [offest, offset_length) as having been initialized.
- * All lengths are step-aligned, where step is min(pagesize, blocksize).
- * Currently assumes offset is page-aligned
- */
-int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
- sector_t offset, sector_t length)
-{
- sector_t start, end;
-
- dprintk("%s(offset=%llu,len=%llu) enter\n",
- __func__, (u64)offset, (u64)length);
-
- start = normalize(offset, marks->im_block_size);
- end = normalize_up(offset + length, marks->im_block_size);
- if (_preload_range(marks, start, end - start))
- goto outerr;
-
- spin_lock_bh(&marks->im_lock);
- if (_set_range(&marks->im_tree, EXTENT_INITIALIZED, offset, length))
- goto out_unlock;
- spin_unlock_bh(&marks->im_lock);
-
- return 0;
-
-out_unlock:
- spin_unlock_bh(&marks->im_lock);
-outerr:
- return -ENOMEM;
-}
-
-/* Marks sectors in [offest, offset+length) as having been written to disk.
- * All lengths should be block aligned.
- */
-static int mark_written_sectors(struct pnfs_inval_markings *marks,
- sector_t offset, sector_t length)
-{
- int status;
-
- dprintk("%s(offset=%llu,len=%llu) enter\n", __func__,
- (u64)offset, (u64)length);
- spin_lock_bh(&marks->im_lock);
- status = _set_range(&marks->im_tree, EXTENT_WRITTEN, offset, length);
- spin_unlock_bh(&marks->im_lock);
- return status;
-}
-
-static void print_short_extent(struct pnfs_block_short_extent *be)
-{
- dprintk("PRINT SHORT EXTENT extent %p\n", be);
- if (be) {
- dprintk(" be_f_offset %llu\n", (u64)be->bse_f_offset);
- dprintk(" be_length %llu\n", (u64)be->bse_length);
- }
-}
-
-static void print_clist(struct list_head *list, unsigned int count)
-{
- struct pnfs_block_short_extent *be;
- unsigned int i = 0;
-
- ifdebug(FACILITY) {
- printk(KERN_DEBUG "****************\n");
- printk(KERN_DEBUG "Extent list looks like:\n");
- list_for_each_entry(be, list, bse_node) {
- i++;
- print_short_extent(be);
- }
- if (i != count)
- printk(KERN_DEBUG "\n\nExpected %u entries\n\n\n", count);
- printk(KERN_DEBUG "****************\n");
- }
-}
-
-/* Note: In theory, we should do more checking that devid's match between
- * old and new, but if they don't, the lists are too corrupt to salvage anyway.
- */
-/* Note this is very similar to bl_add_merge_extent */
-static void add_to_commitlist(struct pnfs_block_layout *bl,
- struct pnfs_block_short_extent *new)
-{
- struct list_head *clist = &bl->bl_commit;
- struct pnfs_block_short_extent *old, *save;
- sector_t end = new->bse_f_offset + new->bse_length;
-
- dprintk("%s enter\n", __func__);
- print_short_extent(new);
- print_clist(clist, bl->bl_count);
- bl->bl_count++;
- /* Scan for proper place to insert, extending new to the left
- * as much as possible.
- */
- list_for_each_entry_safe(old, save, clist, bse_node) {
- if (new->bse_f_offset < old->bse_f_offset)
- break;
- if (end <= old->bse_f_offset + old->bse_length) {
- /* Range is already in list */
- bl->bl_count--;
- kfree(new);
- return;
- } else if (new->bse_f_offset <=
- old->bse_f_offset + old->bse_length) {
- /* new overlaps or abuts existing be */
- if (new->bse_mdev == old->bse_mdev) {
- /* extend new to fully replace old */
- new->bse_length += new->bse_f_offset -
- old->bse_f_offset;
- new->bse_f_offset = old->bse_f_offset;
- list_del(&old->bse_node);
- bl->bl_count--;
- kfree(old);
- }
- }
- }
- /* Note that if we never hit the above break, old will not point to a
- * valid extent. However, in that case &old->bse_node==list.
- */
- list_add_tail(&new->bse_node, &old->bse_node);
- /* Scan forward for overlaps. If we find any, extend new and
- * remove the overlapped extent.
- */
- old = list_prepare_entry(new, clist, bse_node);
- list_for_each_entry_safe_continue(old, save, clist, bse_node) {
- if (end < old->bse_f_offset)
- break;
- /* new overlaps or abuts old */
- if (new->bse_mdev == old->bse_mdev) {
- if (end < old->bse_f_offset + old->bse_length) {
- /* extend new to fully cover old */
- end = old->bse_f_offset + old->bse_length;
- new->bse_length = end - new->bse_f_offset;
- }
- list_del(&old->bse_node);
- bl->bl_count--;
- kfree(old);
- }
- }
- dprintk("%s: after merging\n", __func__);
- print_clist(clist, bl->bl_count);
-}
-
-/* Note the range described by offset, length is guaranteed to be contained
- * within be.
- * new will be freed, either by this function or add_to_commitlist if they
- * decide not to use it, or after LAYOUTCOMMIT uses it in the commitlist.
- */
-int bl_mark_for_commit(struct pnfs_block_extent *be,
- sector_t offset, sector_t length,
- struct pnfs_block_short_extent *new)
-{
- sector_t new_end, end = offset + length;
- struct pnfs_block_layout *bl = container_of(be->be_inval,
- struct pnfs_block_layout,
- bl_inval);
-
- mark_written_sectors(be->be_inval, offset, length);
- /* We want to add the range to commit list, but it must be
- * block-normalized, and verified that the normalized range has
- * been entirely written to disk.
- */
- new->bse_f_offset = offset;
- offset = normalize(offset, bl->bl_blocksize);
- if (offset < new->bse_f_offset) {
- if (is_range_written(be->be_inval, offset, new->bse_f_offset))
- new->bse_f_offset = offset;
- else
- new->bse_f_offset = offset + bl->bl_blocksize;
- }
- new_end = normalize_up(end, bl->bl_blocksize);
- if (end < new_end) {
- if (is_range_written(be->be_inval, end, new_end))
- end = new_end;
- else
- end = new_end - bl->bl_blocksize;
- }
- if (end <= new->bse_f_offset) {
- kfree(new);
- return 0;
- }
- new->bse_length = end - new->bse_f_offset;
- new->bse_devid = be->be_devid;
- new->bse_mdev = be->be_mdev;
-
- spin_lock(&bl->bl_ext_lock);
- add_to_commitlist(bl, new);
- spin_unlock(&bl->bl_ext_lock);
- return 0;
-}
-
-static void print_bl_extent(struct pnfs_block_extent *be)
-{
- dprintk("PRINT EXTENT extent %p\n", be);
- if (be) {
- dprintk(" be_f_offset %llu\n", (u64)be->be_f_offset);
- dprintk(" be_length %llu\n", (u64)be->be_length);
- dprintk(" be_v_offset %llu\n", (u64)be->be_v_offset);
- dprintk(" be_state %d\n", be->be_state);
- }
-}
-
-static void
-destroy_extent(struct kref *kref)
-{
- struct pnfs_block_extent *be;
-
- be = container_of(kref, struct pnfs_block_extent, be_refcnt);
- dprintk("%s be=%p\n", __func__, be);
- kfree(be);
-}
-
-void
-bl_put_extent(struct pnfs_block_extent *be)
-{
- if (be) {
- dprintk("%s enter %p (%i)\n", __func__, be,
- atomic_read(&be->be_refcnt.refcount));
- kref_put(&be->be_refcnt, destroy_extent);
- }
-}
-
-struct pnfs_block_extent *bl_alloc_extent(void)
-{
- struct pnfs_block_extent *be;
-
- be = kmalloc(sizeof(struct pnfs_block_extent), GFP_NOFS);
- if (!be)
- return NULL;
- INIT_LIST_HEAD(&be->be_node);
- kref_init(&be->be_refcnt);
- be->be_inval = NULL;
- return be;
-}
-
-static void print_elist(struct list_head *list)
-{
- struct pnfs_block_extent *be;
- dprintk("****************\n");
- dprintk("Extent list looks like:\n");
- list_for_each_entry(be, list, be_node) {
- print_bl_extent(be);
- }
- dprintk("****************\n");
-}
-
-static inline int
-extents_consistent(struct pnfs_block_extent *old, struct pnfs_block_extent *new)
-{
- /* Note this assumes new->be_f_offset >= old->be_f_offset */
- return (new->be_state == old->be_state) &&
- ((new->be_state == PNFS_BLOCK_NONE_DATA) ||
- ((new->be_v_offset - old->be_v_offset ==
- new->be_f_offset - old->be_f_offset) &&
- new->be_mdev == old->be_mdev));
-}
-
-/* Adds new to appropriate list in bl, modifying new and removing existing
- * extents as appropriate to deal with overlaps.
- *
- * See bl_find_get_extent for list constraints.
- *
- * Refcount on new is already set. If end up not using it, or error out,
- * need to put the reference.
- *
- * bl->bl_ext_lock is held by caller.
- */
-int
-bl_add_merge_extent(struct pnfs_block_layout *bl,
- struct pnfs_block_extent *new)
-{
- struct pnfs_block_extent *be, *tmp;
- sector_t end = new->be_f_offset + new->be_length;
- struct list_head *list;
-
- dprintk("%s enter with be=%p\n", __func__, new);
- print_bl_extent(new);
- list = &bl->bl_extents[bl_choose_list(new->be_state)];
- print_elist(list);
-
- /* Scan for proper place to insert, extending new to the left
- * as much as possible.
- */
- list_for_each_entry_safe_reverse(be, tmp, list, be_node) {
- if (new->be_f_offset >= be->be_f_offset + be->be_length)
- break;
- if (new->be_f_offset >= be->be_f_offset) {
- if (end <= be->be_f_offset + be->be_length) {
- /* new is a subset of existing be*/
- if (extents_consistent(be, new)) {
- dprintk("%s: new is subset, ignoring\n",
- __func__);
- bl_put_extent(new);
- return 0;
- } else {
- goto out_err;
- }
- } else {
- /* |<-- be -->|
- * |<-- new -->| */
- if (extents_consistent(be, new)) {
- /* extend new to fully replace be */
- new->be_length += new->be_f_offset -
- be->be_f_offset;
- new->be_f_offset = be->be_f_offset;
- new->be_v_offset = be->be_v_offset;
- dprintk("%s: removing %p\n", __func__, be);
- list_del(&be->be_node);
- bl_put_extent(be);
- } else {
- goto out_err;
- }
- }
- } else if (end >= be->be_f_offset + be->be_length) {
- /* new extent overlap existing be */
- if (extents_consistent(be, new)) {
- /* extend new to fully replace be */
- dprintk("%s: removing %p\n", __func__, be);
- list_del(&be->be_node);
- bl_put_extent(be);
- } else {
- goto out_err;
- }
- } else if (end > be->be_f_offset) {
- /* |<-- be -->|
- *|<-- new -->| */
- if (extents_consistent(new, be)) {
- /* extend new to fully replace be */
- new->be_length += be->be_f_offset + be->be_length -
- new->be_f_offset - new->be_length;
- dprintk("%s: removing %p\n", __func__, be);
- list_del(&be->be_node);
- bl_put_extent(be);
- } else {
- goto out_err;
- }
- }
- }
- /* Note that if we never hit the above break, be will not point to a
- * valid extent. However, in that case &be->be_node==list.
- */
- list_add(&new->be_node, &be->be_node);
- dprintk("%s: inserting new\n", __func__);
- print_elist(list);
- /* FIXME - The per-list consistency checks have all been done,
- * should now check cross-list consistency.
- */
- return 0;
-
- out_err:
- bl_put_extent(new);
- return -EIO;
-}
-
-/* Returns extent, or NULL. If a second READ extent exists, it is returned
- * in cow_read, if given.
- *
- * The extents are kept in two seperate ordered lists, one for READ and NONE,
- * one for READWRITE and INVALID. Within each list, we assume:
- * 1. Extents are ordered by file offset.
- * 2. For any given isect, there is at most one extents that matches.
- */
-struct pnfs_block_extent *
-bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
- struct pnfs_block_extent **cow_read)
-{
- struct pnfs_block_extent *be, *cow, *ret;
- int i;
-
- dprintk("%s enter with isect %llu\n", __func__, (u64)isect);
- cow = ret = NULL;
- spin_lock(&bl->bl_ext_lock);
- for (i = 0; i < EXTENT_LISTS; i++) {
- list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) {
- if (isect >= be->be_f_offset + be->be_length)
- break;
- if (isect >= be->be_f_offset) {
- /* We have found an extent */
- dprintk("%s Get %p (%i)\n", __func__, be,
- atomic_read(&be->be_refcnt.refcount));
- kref_get(&be->be_refcnt);
- if (!ret)
- ret = be;
- else if (be->be_state != PNFS_BLOCK_READ_DATA)
- bl_put_extent(be);
- else
- cow = be;
- break;
- }
- }
- if (ret &&
- (!cow_read || ret->be_state != PNFS_BLOCK_INVALID_DATA))
- break;
- }
- spin_unlock(&bl->bl_ext_lock);
- if (cow_read)
- *cow_read = cow;
- print_bl_extent(ret);
- return ret;
-}
-
-/* Similar to bl_find_get_extent, but called with lock held, and ignores cow */
-static struct pnfs_block_extent *
-bl_find_get_extent_locked(struct pnfs_block_layout *bl, sector_t isect)
-{
- struct pnfs_block_extent *be, *ret = NULL;
- int i;
-
- dprintk("%s enter with isect %llu\n", __func__, (u64)isect);
- for (i = 0; i < EXTENT_LISTS; i++) {
- if (ret)
- break;
- list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) {
- if (isect >= be->be_f_offset + be->be_length)
- break;
- if (isect >= be->be_f_offset) {
- /* We have found an extent */
- dprintk("%s Get %p (%i)\n", __func__, be,
- atomic_read(&be->be_refcnt.refcount));
- kref_get(&be->be_refcnt);
- ret = be;
- break;
- }
- }
- }
- print_bl_extent(ret);
- return ret;
-}
-
-int
-encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
- struct xdr_stream *xdr,
- const struct nfs4_layoutcommit_args *arg)
-{
- struct pnfs_block_short_extent *lce, *save;
- unsigned int count = 0;
- __be32 *p, *xdr_start;
-
- dprintk("%s enter\n", __func__);
- /* BUG - creation of bl_commit is buggy - need to wait for
- * entire block to be marked WRITTEN before it can be added.
- */
- spin_lock(&bl->bl_ext_lock);
- /* Want to adjust for possible truncate */
- /* We now want to adjust argument range */
-
- /* XDR encode the ranges found */
- xdr_start = xdr_reserve_space(xdr, 8);
- if (!xdr_start)
- goto out;
- list_for_each_entry_safe(lce, save, &bl->bl_commit, bse_node) {
- p = xdr_reserve_space(xdr, 7 * 4 + sizeof(lce->bse_devid.data));
- if (!p)
- break;
- p = xdr_encode_opaque_fixed(p, lce->bse_devid.data, NFS4_DEVICEID4_SIZE);
- p = xdr_encode_hyper(p, lce->bse_f_offset << SECTOR_SHIFT);
- p = xdr_encode_hyper(p, lce->bse_length << SECTOR_SHIFT);
- p = xdr_encode_hyper(p, 0LL);
- *p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
- list_move_tail(&lce->bse_node, &bl->bl_committing);
- bl->bl_count--;
- count++;
- }
- xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4);
- xdr_start[1] = cpu_to_be32(count);
-out:
- spin_unlock(&bl->bl_ext_lock);
- dprintk("%s found %i ranges\n", __func__, count);
- return 0;
-}
-
-/* Helper function to set_to_rw that initialize a new extent */
-static void
-_prep_new_extent(struct pnfs_block_extent *new,
- struct pnfs_block_extent *orig,
- sector_t offset, sector_t length, int state)
-{
- kref_init(&new->be_refcnt);
- /* don't need to INIT_LIST_HEAD(&new->be_node) */
- memcpy(&new->be_devid, &orig->be_devid, sizeof(struct nfs4_deviceid));
- new->be_mdev = orig->be_mdev;
- new->be_f_offset = offset;
- new->be_length = length;
- new->be_v_offset = orig->be_v_offset - orig->be_f_offset + offset;
- new->be_state = state;
- new->be_inval = orig->be_inval;
-}
-
-/* Tries to merge be with extent in front of it in list.
- * Frees storage if not used.
- */
-static struct pnfs_block_extent *
-_front_merge(struct pnfs_block_extent *be, struct list_head *head,
- struct pnfs_block_extent *storage)
-{
- struct pnfs_block_extent *prev;
-
- if (!storage)
- goto no_merge;
- if (&be->be_node == head || be->be_node.prev == head)
- goto no_merge;
- prev = list_entry(be->be_node.prev, struct pnfs_block_extent, be_node);
- if ((prev->be_f_offset + prev->be_length != be->be_f_offset) ||
- !extents_consistent(prev, be))
- goto no_merge;
- _prep_new_extent(storage, prev, prev->be_f_offset,
- prev->be_length + be->be_length, prev->be_state);
- list_replace(&prev->be_node, &storage->be_node);
- bl_put_extent(prev);
- list_del(&be->be_node);
- bl_put_extent(be);
- return storage;
-
- no_merge:
- kfree(storage);
- return be;
-}
-
-static u64
-set_to_rw(struct pnfs_block_layout *bl, u64 offset, u64 length)
-{
- u64 rv = offset + length;
- struct pnfs_block_extent *be, *e1, *e2, *e3, *new, *old;
- struct pnfs_block_extent *children[3];
- struct pnfs_block_extent *merge1 = NULL, *merge2 = NULL;
- int i = 0, j;
-
- dprintk("%s(%llu, %llu)\n", __func__, offset, length);
- /* Create storage for up to three new extents e1, e2, e3 */
- e1 = kmalloc(sizeof(*e1), GFP_ATOMIC);
- e2 = kmalloc(sizeof(*e2), GFP_ATOMIC);
- e3 = kmalloc(sizeof(*e3), GFP_ATOMIC);
- /* BUG - we are ignoring any failure */
- if (!e1 || !e2 || !e3)
- goto out_nosplit;
-
- spin_lock(&bl->bl_ext_lock);
- be = bl_find_get_extent_locked(bl, offset);
- rv = be->be_f_offset + be->be_length;
- if (be->be_state != PNFS_BLOCK_INVALID_DATA) {
- spin_unlock(&bl->bl_ext_lock);
- goto out_nosplit;
- }
- /* Add e* to children, bumping e*'s krefs */
- if (be->be_f_offset != offset) {
- _prep_new_extent(e1, be, be->be_f_offset,
- offset - be->be_f_offset,
- PNFS_BLOCK_INVALID_DATA);
- children[i++] = e1;
- print_bl_extent(e1);
- } else
- merge1 = e1;
- _prep_new_extent(e2, be, offset,
- min(length, be->be_f_offset + be->be_length - offset),
- PNFS_BLOCK_READWRITE_DATA);
- children[i++] = e2;
- print_bl_extent(e2);
- if (offset + length < be->be_f_offset + be->be_length) {
- _prep_new_extent(e3, be, e2->be_f_offset + e2->be_length,
- be->be_f_offset + be->be_length -
- offset - length,
- PNFS_BLOCK_INVALID_DATA);
- children[i++] = e3;
- print_bl_extent(e3);
- } else
- merge2 = e3;
-
- /* Remove be from list, and insert the e* */
- /* We don't get refs on e*, since this list is the base reference
- * set when init'ed.
- */
- if (i < 3)
- children[i] = NULL;
- new = children[0];
- list_replace(&be->be_node, &new->be_node);
- bl_put_extent(be);
- new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge1);
- for (j = 1; j < i; j++) {
- old = new;
- new = children[j];
- list_add(&new->be_node, &old->be_node);
- }
- if (merge2) {
- /* This is a HACK, should just create a _back_merge function */
- new = list_entry(new->be_node.next,
- struct pnfs_block_extent, be_node);
- new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge2);
- }
- spin_unlock(&bl->bl_ext_lock);
-
- /* Since we removed the base reference above, be is now scheduled for
- * destruction.
- */
- bl_put_extent(be);
- dprintk("%s returns %llu after split\n", __func__, rv);
- return rv;
-
- out_nosplit:
- kfree(e1);
- kfree(e2);
- kfree(e3);
- dprintk("%s returns %llu without splitting\n", __func__, rv);
- return rv;
-}
-
-void
-clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
- const struct nfs4_layoutcommit_args *arg,
- int status)
-{
- struct pnfs_block_short_extent *lce, *save;
-
- dprintk("%s status %d\n", __func__, status);
- list_for_each_entry_safe(lce, save, &bl->bl_committing, bse_node) {
- if (likely(!status)) {
- u64 offset = lce->bse_f_offset;
- u64 end = offset + lce->bse_length;
-
- do {
- offset = set_to_rw(bl, offset, end - offset);
- } while (offset < end);
- list_del(&lce->bse_node);
-
- kfree(lce);
- } else {
- list_del(&lce->bse_node);
- spin_lock(&bl->bl_ext_lock);
- add_to_commitlist(bl, lce);
- spin_unlock(&bl->bl_ext_lock);
- }
- }
-}
-
-int bl_push_one_short_extent(struct pnfs_inval_markings *marks)
-{
- struct pnfs_block_short_extent *new;
-
- new = kmalloc(sizeof(*new), GFP_NOFS);
- if (unlikely(!new))
- return -ENOMEM;
-
- spin_lock_bh(&marks->im_lock);
- list_add(&new->bse_node, &marks->im_extents);
- spin_unlock_bh(&marks->im_lock);
-
- return 0;
-}
-
-struct pnfs_block_short_extent *
-bl_pop_one_short_extent(struct pnfs_inval_markings *marks)
-{
- struct pnfs_block_short_extent *rv = NULL;
-
- spin_lock_bh(&marks->im_lock);
- if (!list_empty(&marks->im_extents)) {
- rv = list_entry((&marks->im_extents)->next,
- struct pnfs_block_short_extent, bse_node);
- list_del_init(&rv->bse_node);
- }
- spin_unlock_bh(&marks->im_lock);
-
- return rv;
-}
-
-void bl_free_short_extents(struct pnfs_inval_markings *marks, int num_to_free)
-{
- struct pnfs_block_short_extent *se = NULL, *tmp;
-
- if (num_to_free <= 0)
- return;
-
- spin_lock(&marks->im_lock);
- list_for_each_entry_safe(se, tmp, &marks->im_extents, bse_node) {
- list_del(&se->bse_node);
- kfree(se);
- if (--num_to_free == 0)
- break;
- }
- spin_unlock(&marks->im_lock);
-
- BUG_ON(num_to_free > 0);
-}
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
new file mode 100644
index 000000000000..8d04bda2bd2e
--- /dev/null
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -0,0 +1,285 @@
+/*
+ * Copyright (c) 2006,2007 The Regents of the University of Michigan.
+ * All rights reserved.
+ *
+ * Andy Adamson <andros@citi.umich.edu>
+ * Fred Isaman <iisaman@umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization. if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose. the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+
+#include <linux/module.h>
+#include <linux/genhd.h>
+#include <linux/blkdev.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY NFSDBG_PNFS_LD
+
+static void
+nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b)
+{
+ int i;
+
+ *p++ = cpu_to_be32(1);
+ *p++ = cpu_to_be32(b->type);
+ *p++ = cpu_to_be32(b->simple.nr_sigs);
+ for (i = 0; i < b->simple.nr_sigs; i++) {
+ p = xdr_encode_hyper(p, b->simple.sigs[i].offset);
+ p = xdr_encode_opaque(p, b->simple.sigs[i].sig,
+ b->simple.sigs[i].sig_len);
+ }
+}
+
+dev_t
+bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
+ gfp_t gfp_mask)
+{
+ struct net *net = server->nfs_client->cl_net;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct bl_dev_msg *reply = &nn->bl_mount_reply;
+ struct bl_pipe_msg bl_pipe_msg;
+ struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
+ struct bl_msg_hdr *bl_msg;
+ DECLARE_WAITQUEUE(wq, current);
+ dev_t dev = 0;
+ int rc;
+
+ dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
+
+ bl_pipe_msg.bl_wq = &nn->bl_wq;
+
+ b->simple.len += 4; /* single volume */
+ if (b->simple.len > PAGE_SIZE)
+ return -EIO;
+
+ memset(msg, 0, sizeof(*msg));
+ msg->len = sizeof(*bl_msg) + b->simple.len;
+ msg->data = kzalloc(msg->len, gfp_mask);
+ if (!msg->data)
+ goto out;
+
+ bl_msg = msg->data;
+ bl_msg->type = BL_DEVICE_MOUNT,
+ bl_msg->totallen = b->simple.len;
+ nfs4_encode_simple(msg->data + sizeof(*bl_msg), b);
+
+ dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
+ add_wait_queue(&nn->bl_wq, &wq);
+ rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
+ if (rc < 0) {
+ remove_wait_queue(&nn->bl_wq, &wq);
+ goto out;
+ }
+
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&nn->bl_wq, &wq);
+
+ if (reply->status != BL_DEVICE_REQUEST_PROC) {
+ printk(KERN_WARNING "%s failed to decode device: %d\n",
+ __func__, reply->status);
+ goto out;
+ }
+
+ dev = MKDEV(reply->major, reply->minor);
+out:
+ kfree(msg->data);
+ return dev;
+}
+
+static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
+ size_t mlen)
+{
+ struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+ nfs_net_id);
+
+ if (mlen != sizeof (struct bl_dev_msg))
+ return -EINVAL;
+
+ if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0)
+ return -EFAULT;
+
+ wake_up(&nn->bl_wq);
+
+ return mlen;
+}
+
+static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
+{
+ struct bl_pipe_msg *bl_pipe_msg =
+ container_of(msg, struct bl_pipe_msg, msg);
+
+ if (msg->errno >= 0)
+ return;
+ wake_up(bl_pipe_msg->bl_wq);
+}
+
+static const struct rpc_pipe_ops bl_upcall_ops = {
+ .upcall = rpc_pipe_generic_upcall,
+ .downcall = bl_pipe_downcall,
+ .destroy_msg = bl_pipe_destroy_msg,
+};
+
+static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+ struct rpc_pipe *pipe)
+{
+ struct dentry *dir, *dentry;
+
+ dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
+ if (dir == NULL)
+ return ERR_PTR(-ENOENT);
+ dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
+ dput(dir);
+ return dentry;
+}
+
+static void nfs4blocklayout_unregister_sb(struct super_block *sb,
+ struct rpc_pipe *pipe)
+{
+ if (pipe->dentry)
+ rpc_unlink(pipe->dentry);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+ void *ptr)
+{
+ struct super_block *sb = ptr;
+ struct net *net = sb->s_fs_info;
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct dentry *dentry;
+ int ret = 0;
+
+ if (!try_module_get(THIS_MODULE))
+ return 0;
+
+ if (nn->bl_device_pipe == NULL) {
+ module_put(THIS_MODULE);
+ return 0;
+ }
+
+ switch (event) {
+ case RPC_PIPEFS_MOUNT:
+ dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
+ if (IS_ERR(dentry)) {
+ ret = PTR_ERR(dentry);
+ break;
+ }
+ nn->bl_device_pipe->dentry = dentry;
+ break;
+ case RPC_PIPEFS_UMOUNT:
+ if (nn->bl_device_pipe->dentry)
+ nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+ break;
+ default:
+ ret = -ENOTSUPP;
+ break;
+ }
+ module_put(THIS_MODULE);
+ return ret;
+}
+
+static struct notifier_block nfs4blocklayout_block = {
+ .notifier_call = rpc_pipefs_event,
+};
+
+static struct dentry *nfs4blocklayout_register_net(struct net *net,
+ struct rpc_pipe *pipe)
+{
+ struct super_block *pipefs_sb;
+ struct dentry *dentry;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (!pipefs_sb)
+ return NULL;
+ dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+ rpc_put_sb_net(net);
+ return dentry;
+}
+
+static void nfs4blocklayout_unregister_net(struct net *net,
+ struct rpc_pipe *pipe)
+{
+ struct super_block *pipefs_sb;
+
+ pipefs_sb = rpc_get_sb_net(net);
+ if (pipefs_sb) {
+ nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+ rpc_put_sb_net(net);
+ }
+}
+
+static int nfs4blocklayout_net_init(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct dentry *dentry;
+
+ init_waitqueue_head(&nn->bl_wq);
+ nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
+ if (IS_ERR(nn->bl_device_pipe))
+ return PTR_ERR(nn->bl_device_pipe);
+ dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
+ if (IS_ERR(dentry)) {
+ rpc_destroy_pipe_data(nn->bl_device_pipe);
+ return PTR_ERR(dentry);
+ }
+ nn->bl_device_pipe->dentry = dentry;
+ return 0;
+}
+
+static void nfs4blocklayout_net_exit(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+ nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
+ rpc_destroy_pipe_data(nn->bl_device_pipe);
+ nn->bl_device_pipe = NULL;
+}
+
+static struct pernet_operations nfs4blocklayout_net_ops = {
+ .init = nfs4blocklayout_net_init,
+ .exit = nfs4blocklayout_net_exit,
+};
+
+int __init bl_init_pipefs(void)
+{
+ int ret;
+
+ ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+ if (ret)
+ goto out;
+ ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
+ if (ret)
+ goto out_unregister_notifier;
+ return 0;
+
+out_unregister_notifier:
+ rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+out:
+ return ret;
+}
+
+void __exit bl_cleanup_pipefs(void)
+{
+ rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+ unregister_pernet_subsys(&nfs4blocklayout_net_ops);
+}
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 54de482143cc..b8fb3a4ef649 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -235,7 +235,7 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
cb_info->serv = serv;
cb_info->rqst = rqstp;
- cb_info->task = kthread_run(callback_svc, cb_info->rqst,
+ cb_info->task = kthread_create(callback_svc, cb_info->rqst,
"nfsv4.%u-svc", minorversion);
if (IS_ERR(cb_info->task)) {
ret = PTR_ERR(cb_info->task);
@@ -244,6 +244,8 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
cb_info->task = NULL;
return ret;
}
+ rqstp->rq_task = cb_info->task;
+ wake_up_process(cb_info->task);
dprintk("nfs_callback_up: service started\n");
return 0;
}
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 41db5258e7a7..73466b934090 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -171,14 +171,26 @@ static u32 initiate_file_draining(struct nfs_client *clp,
goto out;
ino = lo->plh_inode;
+
+ spin_lock(&ino->i_lock);
+ pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
+ spin_unlock(&ino->i_lock);
+
+ pnfs_layoutcommit_inode(ino, false);
+
spin_lock(&ino->i_lock);
if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
pnfs_mark_matching_lsegs_invalid(lo, &free_me_list,
- &args->cbl_range))
+ &args->cbl_range)) {
rv = NFS4ERR_DELAY;
- else
- rv = NFS4ERR_NOMATCHING_LAYOUT;
- pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
+ goto unlock;
+ }
+
+ if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
+ NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
+ &args->cbl_range);
+ }
+unlock:
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&free_me_list);
pnfs_put_layout_hdr(lo);
@@ -277,9 +289,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
}
found:
- if (dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE)
- dprintk("%s: NOTIFY_DEVICEID4_CHANGE not supported, "
- "deleting instead\n", __func__);
nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
}
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 6a4f3666e273..f9f4845db989 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1252,6 +1252,7 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
* set up the iterator to start reading from the server list and return the first item
*/
static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
+ __acquires(&nn->nfs_client_lock)
{
struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);
@@ -1274,6 +1275,7 @@ static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
* clean up after reading from the transports list
*/
static void nfs_server_list_stop(struct seq_file *p, void *v)
+ __releases(&nn->nfs_client_lock)
{
struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);
@@ -1318,7 +1320,7 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
*/
static int nfs_volume_list_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &nfs_server_list_ops,
+ return seq_open_net(inode, file, &nfs_volume_list_ops,
sizeof(struct seq_net_private));
}
@@ -1326,6 +1328,7 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
* set up the iterator to start reading from the volume list and return the first item
*/
static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
+ __acquires(&nn->nfs_client_lock)
{
struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);
@@ -1348,6 +1351,7 @@ static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
* clean up after reading from the transports list
*/
static void nfs_volume_list_stop(struct seq_file *p, void *v)
+ __releases(&nn->nfs_client_lock)
{
struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 65ef6e00deee..dda4b8667c02 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -178,7 +178,6 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
}
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
/*
* nfs_direct_cmp_commit_data_verf - compare verifier for commit data
* @dreq - direct request possibly spanning multiple servers
@@ -197,7 +196,6 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
WARN_ON_ONCE(verfp->committed < 0);
return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
}
-#endif
/**
* nfs_direct_IO - NFS address space operation for direct I/O
@@ -576,7 +574,6 @@ out:
return result;
}
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
{
struct nfs_pageio_descriptor desc;
@@ -700,17 +697,6 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */
}
-#else
-static void nfs_direct_write_schedule_work(struct work_struct *work)
-{
-}
-
-static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
-{
- nfs_direct_complete(dreq, true);
-}
-#endif
-
static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
{
struct nfs_direct_req *dreq = hdr->dreq;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 524dd80d1898..6920127c5eb7 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -36,6 +36,7 @@
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
+#include "pnfs.h"
#include "nfstrace.h"
@@ -327,6 +328,12 @@ static int nfs_want_read_modify_write(struct file *file, struct page *page,
unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
unsigned int end = offset + len;
+ if (pnfs_ld_read_whole_page(file->f_mapping->host)) {
+ if (!PageUptodate(page))
+ return 1;
+ return 0;
+ }
+
if ((file->f_mode & FMODE_READ) && /* open for read? */
!PageUptodate(page) && /* Uptodate? */
!PagePrivate(page) && /* i/o request already? */
@@ -468,17 +475,26 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
- /* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not
- * doing this memory reclaim for a fs-related allocation.
+ /* Always try to initiate a 'commit' if relevant, but only
+ * wait for it if __GFP_WAIT is set. Even then, only wait 1
+ * second and only if the 'bdi' is not congested.
+ * Waiting indefinitely can cause deadlocks when the NFS
+ * server is on this machine, when a new TCP connection is
+ * needed and in other rare cases. There is no particular
+ * need to wait extensively here. A short wait has the
+ * benefit that someone else can worry about the freezer.
*/
- if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL &&
- !(current->flags & PF_FSTRANS)) {
- int how = FLUSH_SYNC;
-
- /* Don't let kswapd deadlock waiting for OOM RPC calls */
- if (current_is_kswapd())
- how = 0;
- nfs_commit_inode(mapping->host, how);
+ if (mapping) {
+ struct nfs_server *nfss = NFS_SERVER(mapping->host);
+ nfs_commit_inode(mapping->host, 0);
+ if ((gfp & __GFP_WAIT) &&
+ !bdi_write_congested(&nfss->backing_dev_info)) {
+ wait_on_page_bit_killable_timeout(page, PG_private,
+ HZ);
+ if (PagePrivate(page))
+ set_bdi_congested(&nfss->backing_dev_info,
+ BLK_RW_ASYNC);
+ }
}
/* If PagePrivate() is set, then the page is not freeable */
if (PagePrivate(page))
@@ -539,13 +555,25 @@ static int nfs_launder_page(struct page *page)
static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
+ int ret;
+ struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
+
*span = sis->pages;
- return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+
+ rcu_read_lock();
+ ret = xs_swapper(rcu_dereference(clnt->cl_xprt), 1);
+ rcu_read_unlock();
+
+ return ret;
}
static void nfs_swap_deactivate(struct file *file)
{
- xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0);
+ struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
+
+ rcu_read_lock();
+ xs_swapper(rcu_dereference(clnt->cl_xprt), 0);
+ rcu_read_unlock();
}
#endif
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 90978075f730..abc5056999d6 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -265,7 +265,7 @@ filelayout_set_layoutcommit(struct nfs_pgio_header *hdr)
{
if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds ||
- hdr->res.verf->committed == NFS_FILE_SYNC)
+ hdr->res.verf->committed != NFS_DATA_SYNC)
return;
pnfs_set_layoutcommit(hdr);
@@ -403,6 +403,9 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
return -EAGAIN;
}
+ if (data->verf.committed == NFS_UNSTABLE)
+ pnfs_commit_set_layoutcommit(data);
+
return 0;
}
@@ -646,18 +649,15 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
}
/* find and reference the deviceid */
- d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode)->pnfs_curr_ld,
- NFS_SERVER(lo->plh_inode)->nfs_client, id);
- if (d == NULL) {
- dsaddr = filelayout_get_device_info(lo->plh_inode, id,
- lo->plh_lc_cred, gfp_flags);
- if (dsaddr == NULL)
- goto out;
- } else
- dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+ d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), id,
+ lo->plh_lc_cred, gfp_flags);
+ if (d == NULL)
+ goto out;
+
+ dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
/* Found deviceid is unavailable */
if (filelayout_test_devid_unavailable(&dsaddr->id_node))
- goto out_put;
+ goto out_put;
fl->dsaddr = dsaddr;
@@ -1368,6 +1368,17 @@ out:
cinfo->ds->ncommitting = 0;
return PNFS_ATTEMPTED;
}
+static struct nfs4_deviceid_node *
+filelayout_alloc_deviceid_node(struct nfs_server *server,
+ struct pnfs_device *pdev, gfp_t gfp_flags)
+{
+ struct nfs4_file_layout_dsaddr *dsaddr;
+
+ dsaddr = nfs4_fl_alloc_deviceid_node(server, pdev, gfp_flags);
+ if (!dsaddr)
+ return NULL;
+ return &dsaddr->id_node;
+}
static void
filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
@@ -1420,6 +1431,7 @@ static struct pnfs_layoutdriver_type filelayout_type = {
.commit_pagelist = filelayout_commit_pagelist,
.read_pagelist = filelayout_read_pagelist,
.write_pagelist = filelayout_write_pagelist,
+ .alloc_deviceid_node = filelayout_alloc_deviceid_node,
.free_deviceid_node = filelayout_free_deveiceid_node,
};
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
index ffbddf2219ea..7c9f800c49d7 100644
--- a/fs/nfs/filelayout/filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -147,10 +147,11 @@ u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
u32 ds_idx);
+
+extern struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server,
+ struct pnfs_device *pdev, gfp_t gfp_flags);
extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
-struct nfs4_file_layout_dsaddr *
-filelayout_get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id,
- struct rpc_cred *cred, gfp_t gfp_flags);
#endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 8540516f4d71..9bb806a76d99 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -484,8 +484,9 @@ out_err:
}
/* Decode opaque device data and return the result */
-static struct nfs4_file_layout_dsaddr*
-decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
+struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+ gfp_t gfp_flags)
{
int i;
u32 cnt, num;
@@ -570,10 +571,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
dsaddr->stripe_indices = stripe_indices;
stripe_indices = NULL;
dsaddr->ds_num = num;
- nfs4_init_deviceid_node(&dsaddr->id_node,
- NFS_SERVER(ino)->pnfs_curr_ld,
- NFS_SERVER(ino)->nfs_client,
- &pdev->dev_id);
+ nfs4_init_deviceid_node(&dsaddr->id_node, server, &pdev->dev_id);
INIT_LIST_HEAD(&dsaddrs);
@@ -587,7 +585,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
mp_count = be32_to_cpup(p); /* multipath count */
for (j = 0; j < mp_count; j++) {
- da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net,
+ da = decode_ds_addr(server->nfs_client->cl_net,
&stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
@@ -637,102 +635,6 @@ out_err:
return NULL;
}
-/*
- * Decode the opaque device specified in 'dev' and add it to the cache of
- * available devices.
- */
-static struct nfs4_file_layout_dsaddr *
-decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags)
-{
- struct nfs4_deviceid_node *d;
- struct nfs4_file_layout_dsaddr *n, *new;
-
- new = decode_device(inode, dev, gfp_flags);
- if (!new) {
- printk(KERN_WARNING "NFS: %s: Could not decode or add device\n",
- __func__);
- return NULL;
- }
-
- d = nfs4_insert_deviceid_node(&new->id_node);
- n = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
- if (n != new) {
- nfs4_fl_free_deviceid(new);
- return n;
- }
-
- return new;
-}
-
-/*
- * Retrieve the information for dev_id, add it to the list
- * of available devices, and return it.
- */
-struct nfs4_file_layout_dsaddr *
-filelayout_get_device_info(struct inode *inode,
- struct nfs4_deviceid *dev_id,
- struct rpc_cred *cred,
- gfp_t gfp_flags)
-{
- struct pnfs_device *pdev = NULL;
- u32 max_resp_sz;
- int max_pages;
- struct page **pages = NULL;
- struct nfs4_file_layout_dsaddr *dsaddr = NULL;
- int rc, i;
- struct nfs_server *server = NFS_SERVER(inode);
-
- /*
- * Use the session max response size as the basis for setting
- * GETDEVICEINFO's maxcount
- */
- max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
- max_pages = nfs_page_array_len(0, max_resp_sz);
- dprintk("%s inode %p max_resp_sz %u max_pages %d\n",
- __func__, inode, max_resp_sz, max_pages);
-
- pdev = kzalloc(sizeof(struct pnfs_device), gfp_flags);
- if (pdev == NULL)
- return NULL;
-
- pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
- if (pages == NULL) {
- kfree(pdev);
- return NULL;
- }
- for (i = 0; i < max_pages; i++) {
- pages[i] = alloc_page(gfp_flags);
- if (!pages[i])
- goto out_free;
- }
-
- memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
- pdev->layout_type = LAYOUT_NFSV4_1_FILES;
- pdev->pages = pages;
- pdev->pgbase = 0;
- pdev->pglen = max_resp_sz;
- pdev->mincount = 0;
- pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;
-
- rc = nfs4_proc_getdeviceinfo(server, pdev, cred);
- dprintk("%s getdevice info returns %d\n", __func__, rc);
- if (rc)
- goto out_free;
-
- /*
- * Found new device, need to decode it and then add it to the
- * list of known devices for this mountpoint.
- */
- dsaddr = decode_and_add_device(inode, pdev, gfp_flags);
-out_free:
- for (i = 0; i < max_pages; i++)
- __free_page(pages[i]);
- kfree(pages);
- kfree(pdev);
- dprintk("<-- %s dsaddr %p\n", __func__, dsaddr);
- return dsaddr;
-}
-
void
nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
{
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index 7cf2c4699b08..777b055063f6 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -74,11 +74,10 @@ static uint16_t nfs_server_get_key(const void *cookie_netfs_data,
struct nfs_server_key *key = buffer;
uint16_t len = sizeof(struct nfs_server_key);
+ memset(key, 0, len);
key->nfsversion = clp->rpc_ops->version;
key->family = clp->cl_addr.ss_family;
- memset(key, 0, len);
-
switch (clp->cl_addr.ss_family) {
case AF_INET:
key->port = sin->sin_port;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 577a36f0a510..141c9f4a40de 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -505,7 +505,9 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
attr->ia_valid &= ~ATTR_MODE;
if (attr->ia_valid & ATTR_SIZE) {
- if (!S_ISREG(inode->i_mode) || attr->ia_size == i_size_read(inode))
+ BUG_ON(!S_ISREG(inode->i_mode));
+
+ if (attr->ia_size == i_size_read(inode))
attr->ia_valid &= ~ATTR_SIZE;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9056622d2230..14ae6f20a172 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -218,13 +218,6 @@ static inline void nfs_fs_proc_exit(void)
int nfs_sockaddr_match_ipaddr(const struct sockaddr *, const struct sockaddr *);
#endif
-/* nfs3client.c */
-#if IS_ENABLED(CONFIG_NFS_V3)
-struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *);
-struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
- struct nfs_fattr *, rpc_authflavor_t);
-#endif
-
/* callback_xdr.c */
extern struct svc_version nfs4_callback_version1;
extern struct svc_version nfs4_callback_version4;
diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h
new file mode 100644
index 000000000000..333ae4068506
--- /dev/null
+++ b/fs/nfs/nfs3_fs.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2014 Anna Schumaker.
+ *
+ * NFSv3-specific filesystem definitions and declarations
+ */
+#ifndef __LINUX_FS_NFS_NFS3_FS_H
+#define __LINUX_FS_NFS_NFS3_FS_H
+
+/*
+ * nfs3acl.c
+ */
+#ifdef CONFIG_NFS_V3_ACL
+extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type);
+extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+ struct posix_acl *dfacl);
+extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
+extern const struct xattr_handler *nfs3_xattr_handlers[];
+#else
+static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+ struct posix_acl *dfacl)
+{
+ return 0;
+}
+#define nfs3_listxattr NULL
+#endif /* CONFIG_NFS_V3_ACL */
+
+/* nfs3client.c */
+struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *);
+struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
+ struct nfs_fattr *, rpc_authflavor_t);
+
+
+#endif /* __LINUX_FS_NFS_NFS3_FS_H */
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 24c6898159cc..658e586ca438 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -7,6 +7,7 @@
#include <linux/nfsacl.h>
#include "internal.h"
+#include "nfs3_fs.h"
#define NFSDBG_FACILITY NFSDBG_PROC
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index b3fc65ef39ca..8c1b437c5403 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -1,6 +1,7 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include "internal.h"
+#include "nfs3_fs.h"
#ifdef CONFIG_NFS_V3_ACL
static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program };
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 809670eba52a..524f9f837408 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -22,6 +22,7 @@
#include "iostat.h"
#include "internal.h"
+#include "nfs3_fs.h"
#define NFSDBG_FACILITY NFSDBG_PROC
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
index d6a98949af19..6af29c2da352 100644
--- a/fs/nfs/nfs3super.c
+++ b/fs/nfs/nfs3super.c
@@ -4,6 +4,7 @@
#include <linux/module.h>
#include <linux/nfs_fs.h>
#include "internal.h"
+#include "nfs3_fs.h"
#include "nfs.h"
static struct nfs_subversion nfs_v3 = {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 53e435a95260..ffdb28d86cf8 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -482,6 +482,16 @@ int nfs40_walk_client_list(struct nfs_client *new,
spin_lock(&nn->nfs_client_lock);
list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+ if (pos->rpc_ops != new->rpc_ops)
+ continue;
+
+ if (pos->cl_proto != new->cl_proto)
+ continue;
+
+ if (pos->cl_minorversion != new->cl_minorversion)
+ continue;
+
/* If "pos" isn't marked ready, we can't trust the
* remaining fields in "pos" */
if (pos->cl_cons_state > NFS_CS_READY) {
@@ -501,15 +511,6 @@ int nfs40_walk_client_list(struct nfs_client *new,
if (pos->cl_cons_state != NFS_CS_READY)
continue;
- if (pos->rpc_ops != new->rpc_ops)
- continue;
-
- if (pos->cl_proto != new->cl_proto)
- continue;
-
- if (pos->cl_minorversion != new->cl_minorversion)
- continue;
-
if (pos->cl_clientid != new->cl_clientid)
continue;
@@ -622,6 +623,16 @@ int nfs41_walk_client_list(struct nfs_client *new,
spin_lock(&nn->nfs_client_lock);
list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+ if (pos->rpc_ops != new->rpc_ops)
+ continue;
+
+ if (pos->cl_proto != new->cl_proto)
+ continue;
+
+ if (pos->cl_minorversion != new->cl_minorversion)
+ continue;
+
/* If "pos" isn't marked ready, we can't trust the
* remaining fields in "pos", especially the client
* ID and serverowner fields. Wait for CREATE_SESSION
@@ -647,15 +658,6 @@ int nfs41_walk_client_list(struct nfs_client *new,
if (pos->cl_cons_state != NFS_CS_READY)
continue;
- if (pos->rpc_ops != new->rpc_ops)
- continue;
-
- if (pos->cl_proto != new->cl_proto)
- continue;
-
- if (pos->cl_minorversion != new->cl_minorversion)
- continue;
-
if (!nfs4_match_clientids(pos, new))
continue;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7dd8aca31c29..5aa55c132aa2 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -77,7 +77,7 @@ struct nfs4_opendata;
static int _nfs4_proc_open(struct nfs4_opendata *data);
static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
-static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *);
+static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *);
static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label);
static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label);
@@ -314,20 +314,30 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
kunmap_atomic(start);
}
+static long nfs4_update_delay(long *timeout)
+{
+ long ret;
+ if (!timeout)
+ return NFS4_POLL_RETRY_MAX;
+ if (*timeout <= 0)
+ *timeout = NFS4_POLL_RETRY_MIN;
+ if (*timeout > NFS4_POLL_RETRY_MAX)
+ *timeout = NFS4_POLL_RETRY_MAX;
+ ret = *timeout;
+ *timeout <<= 1;
+ return ret;
+}
+
static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
{
int res = 0;
might_sleep();
- if (*timeout <= 0)
- *timeout = NFS4_POLL_RETRY_MIN;
- if (*timeout > NFS4_POLL_RETRY_MAX)
- *timeout = NFS4_POLL_RETRY_MAX;
- freezable_schedule_timeout_killable_unsafe(*timeout);
+ freezable_schedule_timeout_killable_unsafe(
+ nfs4_update_delay(timeout));
if (fatal_signal_pending(current))
res = -ERESTARTSYS;
- *timeout <<= 1;
return res;
}
@@ -1307,15 +1317,13 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
int ret = -EAGAIN;
for (;;) {
+ spin_lock(&state->owner->so_lock);
if (can_open_cached(state, fmode, open_mode)) {
- spin_lock(&state->owner->so_lock);
- if (can_open_cached(state, fmode, open_mode)) {
- update_open_stateflags(state, fmode);
- spin_unlock(&state->owner->so_lock);
- goto out_return_state;
- }
+ update_open_stateflags(state, fmode);
spin_unlock(&state->owner->so_lock);
+ goto out_return_state;
}
+ spin_unlock(&state->owner->so_lock);
rcu_read_lock();
delegation = rcu_dereference(nfsi->delegation);
if (!can_open_delegated(delegation, fmode)) {
@@ -2226,9 +2234,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
ret = _nfs4_proc_open(opendata);
if (ret != 0) {
if (ret == -ENOENT) {
- d_drop(opendata->dentry);
- d_add(opendata->dentry, NULL);
- nfs_set_verifier(opendata->dentry,
+ dentry = opendata->dentry;
+ if (dentry->d_inode)
+ d_delete(dentry);
+ else if (d_unhashed(dentry))
+ d_add(dentry, NULL);
+
+ nfs_set_verifier(dentry,
nfs_save_change_attribute(opendata->dir->d_inode));
}
goto out;
@@ -2585,7 +2597,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
if (calldata->arg.fmode == 0)
break;
default:
- if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
+ if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) {
rpc_restart_call_prepare(task);
goto out_release;
}
@@ -2614,23 +2626,23 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
- /* Calculate the current open share mode */
- calldata->arg.fmode = 0;
- if (is_rdonly || is_rdwr)
- calldata->arg.fmode |= FMODE_READ;
- if (is_wronly || is_rdwr)
- calldata->arg.fmode |= FMODE_WRITE;
/* Calculate the change in open mode */
+ calldata->arg.fmode = 0;
if (state->n_rdwr == 0) {
- if (state->n_rdonly == 0) {
- call_close |= is_rdonly || is_rdwr;
- calldata->arg.fmode &= ~FMODE_READ;
- }
- if (state->n_wronly == 0) {
- call_close |= is_wronly || is_rdwr;
- calldata->arg.fmode &= ~FMODE_WRITE;
- }
- }
+ if (state->n_rdonly == 0)
+ call_close |= is_rdonly;
+ else if (is_rdonly)
+ calldata->arg.fmode |= FMODE_READ;
+ if (state->n_wronly == 0)
+ call_close |= is_wronly;
+ else if (is_wronly)
+ calldata->arg.fmode |= FMODE_WRITE;
+ } else if (is_rdwr)
+ calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
+
+ if (calldata->arg.fmode == 0)
+ call_close |= is_rdwr;
+
if (!nfs4_valid_open_stateid(state))
call_close = 0;
spin_unlock(&state->owner->so_lock);
@@ -3213,7 +3225,9 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
struct nfs4_label *label = NULL;
int status;
- if (pnfs_ld_layoutret_on_setattr(inode))
+ if (pnfs_ld_layoutret_on_setattr(inode) &&
+ sattr->ia_valid & ATTR_SIZE &&
+ sattr->ia_size < i_size_read(inode))
pnfs_commit_and_return_layout(inode);
nfs_fattr_init(fattr);
@@ -3572,7 +3586,8 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
if (!nfs4_sequence_done(task, &res->seq_res))
return 0;
- if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+ if (nfs4_async_handle_error(task, res->server, NULL,
+ &data->timeout) == -EAGAIN)
return 0;
update_changeattr(dir, &res->cinfo);
return 1;
@@ -3605,7 +3620,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
if (!nfs4_sequence_done(task, &res->seq_res))
return 0;
- if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+ if (nfs4_async_handle_error(task, res->server, NULL, &data->timeout) == -EAGAIN)
return 0;
update_changeattr(old_dir, &res->old_cinfo);
@@ -4109,7 +4124,8 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr)
trace_nfs4_read(hdr, task->tk_status);
if (nfs4_async_handle_error(task, server,
- hdr->args.context->state) == -EAGAIN) {
+ hdr->args.context->state,
+ NULL) == -EAGAIN) {
rpc_restart_call_prepare(task);
return -EAGAIN;
}
@@ -4177,10 +4193,11 @@ static int nfs4_write_done_cb(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
struct inode *inode = hdr->inode;
-
+
trace_nfs4_write(hdr, task->tk_status);
if (nfs4_async_handle_error(task, NFS_SERVER(inode),
- hdr->args.context->state) == -EAGAIN) {
+ hdr->args.context->state,
+ NULL) == -EAGAIN) {
rpc_restart_call_prepare(task);
return -EAGAIN;
}
@@ -4260,7 +4277,8 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *da
struct inode *inode = data->inode;
trace_nfs4_commit(data, task->tk_status);
- if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) {
+ if (nfs4_async_handle_error(task, NFS_SERVER(inode),
+ NULL, NULL) == -EAGAIN) {
rpc_restart_call_prepare(task);
return -EAGAIN;
}
@@ -4813,7 +4831,8 @@ out:
static int
-nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs4_state *state)
+nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
+ struct nfs4_state *state, long *timeout)
{
struct nfs_client *clp = server->nfs_client;
@@ -4863,6 +4882,8 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
#endif /* CONFIG_NFS_V4_1 */
case -NFS4ERR_DELAY:
nfs_inc_server_stats(server, NFSIOS_DELAY);
+ rpc_delay(task, nfs4_update_delay(timeout));
+ goto restart_call;
case -NFS4ERR_GRACE:
rpc_delay(task, NFS4_POLL_RETRY_MAX);
case -NFS4ERR_RETRY_UNCACHED_REP:
@@ -5103,8 +5124,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
pnfs_roc_set_barrier(data->inode, data->roc_barrier);
break;
default:
- if (nfs4_async_handle_error(task, data->res.server, NULL) ==
- -EAGAIN) {
+ if (nfs4_async_handle_error(task, data->res.server,
+ NULL, NULL) == -EAGAIN) {
rpc_restart_call_prepare(task);
return;
}
@@ -5368,7 +5389,8 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
case -NFS4ERR_EXPIRED:
break;
default:
- if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
+ if (nfs4_async_handle_error(task, calldata->server,
+ NULL, NULL) == -EAGAIN)
rpc_restart_call_prepare(task);
}
nfs_release_seqid(calldata->arg.seqid);
@@ -5974,7 +5996,8 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
break;
case -NFS4ERR_LEASE_MOVED:
case -NFS4ERR_DELAY:
- if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN)
+ if (nfs4_async_handle_error(task, server,
+ NULL, NULL) == -EAGAIN)
rpc_restart_call_prepare(task);
}
}
@@ -7349,7 +7372,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
int ret = 0;
if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
- return 0;
+ return -EAGAIN;
task = _nfs41_proc_sequence(clp, cred, false);
if (IS_ERR(task))
ret = PTR_ERR(task);
@@ -7579,14 +7602,19 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
} else {
LIST_HEAD(head);
+ /*
+ * Mark the bad layout state as invalid, then retry
+ * with the current stateid.
+ */
pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
spin_unlock(&inode->i_lock);
- /* Mark the bad layout state as invalid, then
- * retry using the open stateid. */
pnfs_free_lseg_list(&head);
+
+ task->tk_status = 0;
+ rpc_restart_call_prepare(task);
}
}
- if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+ if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
rpc_restart_call_prepare(task);
out:
dprintk("<-- %s\n", __func__);
@@ -7746,7 +7774,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
case 0:
break;
case -NFS4ERR_DELAY:
- if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN)
+ if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
break;
rpc_restart_call_prepare(task);
return;
@@ -7805,54 +7833,6 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
return status;
}
-/*
- * Retrieve the list of Data Server devices from the MDS.
- */
-static int _nfs4_getdevicelist(struct nfs_server *server,
- const struct nfs_fh *fh,
- struct pnfs_devicelist *devlist)
-{
- struct nfs4_getdevicelist_args args = {
- .fh = fh,
- .layoutclass = server->pnfs_curr_ld->id,
- };
- struct nfs4_getdevicelist_res res = {
- .devlist = devlist,
- };
- struct rpc_message msg = {
- .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST],
- .rpc_argp = &args,
- .rpc_resp = &res,
- };
- int status;
-
- dprintk("--> %s\n", __func__);
- status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
- &res.seq_res, 0);
- dprintk("<-- %s status=%d\n", __func__, status);
- return status;
-}
-
-int nfs4_proc_getdevicelist(struct nfs_server *server,
- const struct nfs_fh *fh,
- struct pnfs_devicelist *devlist)
-{
- struct nfs4_exception exception = { };
- int err;
-
- do {
- err = nfs4_handle_exception(server,
- _nfs4_getdevicelist(server, fh, devlist),
- &exception);
- } while (exception.retry);
-
- dprintk("%s: err=%d, num_devs=%u\n", __func__,
- err, devlist->num_devs);
-
- return err;
-}
-EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist);
-
static int
_nfs4_proc_getdeviceinfo(struct nfs_server *server,
struct pnfs_device *pdev,
@@ -7925,7 +7905,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
case 0:
break;
default:
- if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+ if (nfs4_async_handle_error(task, server, NULL, NULL) == -EAGAIN) {
rpc_restart_call_prepare(task);
return;
}
@@ -8221,7 +8201,7 @@ static void nfs41_free_stateid_done(struct rpc_task *task, void *calldata)
switch (task->tk_status) {
case -NFS4ERR_DELAY:
- if (nfs4_async_handle_error(task, data->server, NULL) == -EAGAIN)
+ if (nfs4_async_handle_error(task, data->server, NULL, NULL) == -EAGAIN)
rpc_restart_call_prepare(task);
}
}
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 1720d32ffa54..e1ba58c3d1ad 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work)
}
nfs_expire_all_delegations(clp);
} else {
+ int ret;
+
/* Queue an asynchronous RENEW. */
- ops->sched_state_renewal(clp, cred, renew_flags);
+ ret = ops->sched_state_renewal(clp, cred, renew_flags);
put_rpccred(cred);
- goto out_exp;
+ switch (ret) {
+ default:
+ goto out_exp;
+ case -EAGAIN:
+ case -ENOMEM:
+ break;
+ }
}
} else {
dprintk("%s: failed to call renewd. Reason: lease not expired \n",
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 22fe35104c0c..5194933ed419 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1705,7 +1705,8 @@ restart:
if (status < 0) {
set_bit(ops->owner_flag_bit, &sp->so_flags);
nfs4_put_state_owner(sp);
- return nfs4_recovery_handle_error(clp, status);
+ status = nfs4_recovery_handle_error(clp, status);
+ return (status != 0) ? status : -EAGAIN;
}
nfs4_put_state_owner(sp);
@@ -1714,7 +1715,7 @@ restart:
spin_unlock(&clp->cl_lock);
}
rcu_read_unlock();
- return status;
+ return 0;
}
static int nfs4_check_lease(struct nfs_client *clp)
@@ -1761,7 +1762,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
break;
case -NFS4ERR_STALE_CLIENTID:
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
- nfs4_state_clear_reclaim_reboot(clp);
nfs4_state_start_reclaim_reboot(clp);
break;
case -NFS4ERR_CLID_INUSE:
@@ -2345,6 +2345,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
status = nfs4_check_lease(clp);
if (status < 0)
goto out_error;
+ continue;
}
if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) {
@@ -2366,14 +2367,11 @@ static void nfs4_state_manager(struct nfs_client *clp)
section = "reclaim reboot";
status = nfs4_do_reclaim(clp,
clp->cl_mvops->reboot_recovery_ops);
- if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
- test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
- continue;
- nfs4_state_end_reclaim_reboot(clp);
- if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+ if (status == -EAGAIN)
continue;
if (status < 0)
goto out_error;
+ nfs4_state_end_reclaim_reboot(clp);
}
/* Now recover expired state... */
@@ -2381,9 +2379,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
section = "reclaim nograce";
status = nfs4_do_reclaim(clp,
clp->cl_mvops->nograce_recovery_ops);
- if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
- test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
- test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+ if (status == -EAGAIN)
continue;
if (status < 0)
goto out_error;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e13b59d8d9aa..005d03c5d274 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -362,25 +362,19 @@ static int nfs4_stat_to_errno(int);
XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
#define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4)
#define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4)
-#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \
- encode_verifier_maxsz)
-#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \
- 2 /* nfs_cookie4 gdlr_cookie */ + \
- decode_verifier_maxsz \
- /* verifier4 gdlr_verifier */ + \
- 1 /* gdlr_deviceid_list count */ + \
- XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \
- NFS4_DEVICEID4_SIZE) \
- /* gdlr_deviceid_list */ + \
- 1 /* bool gdlr_eof */)
-#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \
- XDR_QUADLEN(NFS4_DEVICEID4_SIZE))
+#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + \
+ XDR_QUADLEN(NFS4_DEVICEID4_SIZE) + \
+ 1 /* layout type */ + \
+ 1 /* maxcount */ + \
+ 1 /* bitmap size */ + \
+ 1 /* notification bitmap length */ + \
+ 1 /* notification bitmap, word 0 */)
#define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \
1 /* layout type */ + \
1 /* opaque devaddr4 length */ + \
/* devaddr4 payload is read into page */ \
1 /* notification bitmap length */ + \
- 1 /* notification bitmap */)
+ 1 /* notification bitmap, word 0 */)
#define encode_layoutget_maxsz (op_encode_hdr_maxsz + 10 + \
encode_stateid_maxsz)
#define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \
@@ -395,7 +389,10 @@ static int nfs4_stat_to_errno(int);
2 /* last byte written */ + \
1 /* nt_timechanged (false) */ + \
1 /* layoutupdate4 layout type */ + \
- 1 /* NULL filelayout layoutupdate4 payload */)
+ 1 /* layoutupdate4 opaqueue len */)
+ /* the actual content of layoutupdate4 should
+ be allocated by drivers and spliced in
+ using xdr_write_pages */
#define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3)
#define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \
encode_stateid_maxsz + \
@@ -809,14 +806,6 @@ static int nfs4_stat_to_errno(int);
#define NFS4_dec_reclaim_complete_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_reclaim_complete_maxsz)
-#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \
- encode_sequence_maxsz + \
- encode_putfh_maxsz + \
- encode_getdevicelist_maxsz)
-#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \
- decode_sequence_maxsz + \
- decode_putfh_maxsz + \
- decode_getdevicelist_maxsz)
#define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz +\
encode_getdeviceinfo_maxsz)
@@ -1927,24 +1916,6 @@ static void encode_sequence(struct xdr_stream *xdr,
#ifdef CONFIG_NFS_V4_1
static void
-encode_getdevicelist(struct xdr_stream *xdr,
- const struct nfs4_getdevicelist_args *args,
- struct compound_hdr *hdr)
-{
- __be32 *p;
- nfs4_verifier dummy = {
- .data = "dummmmmy",
- };
-
- encode_op_hdr(xdr, OP_GETDEVICELIST, decode_getdevicelist_maxsz, hdr);
- p = reserve_space(xdr, 16);
- *p++ = cpu_to_be32(args->layoutclass);
- *p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM);
- xdr_encode_hyper(p, 0ULL); /* cookie */
- encode_nfs4_verifier(xdr, &dummy);
-}
-
-static void
encode_getdeviceinfo(struct xdr_stream *xdr,
const struct nfs4_getdeviceinfo_args *args,
struct compound_hdr *hdr)
@@ -1952,12 +1923,15 @@ encode_getdeviceinfo(struct xdr_stream *xdr,
__be32 *p;
encode_op_hdr(xdr, OP_GETDEVICEINFO, decode_getdeviceinfo_maxsz, hdr);
- p = reserve_space(xdr, 12 + NFS4_DEVICEID4_SIZE);
+ p = reserve_space(xdr, NFS4_DEVICEID4_SIZE + 4 + 4);
p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data,
NFS4_DEVICEID4_SIZE);
*p++ = cpu_to_be32(args->pdev->layout_type);
*p++ = cpu_to_be32(args->pdev->maxcount); /* gdia_maxcount */
- *p++ = cpu_to_be32(0); /* bitmap length 0 */
+
+ p = reserve_space(xdr, 4 + 4);
+ *p++ = cpu_to_be32(1); /* bitmap length */
+ *p++ = cpu_to_be32(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE);
}
static void
@@ -1990,7 +1964,7 @@ encode_layoutget(struct xdr_stream *xdr,
static int
encode_layoutcommit(struct xdr_stream *xdr,
struct inode *inode,
- const struct nfs4_layoutcommit_args *args,
+ struct nfs4_layoutcommit_args *args,
struct compound_hdr *hdr)
{
__be32 *p;
@@ -2011,11 +1985,16 @@ encode_layoutcommit(struct xdr_stream *xdr,
*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
- if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
+ if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) {
NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
NFS_I(inode)->layout, xdr, args);
- else
- encode_uint32(xdr, 0); /* no layout-type payload */
+ } else {
+ encode_uint32(xdr, args->layoutupdate_len);
+ if (args->layoutupdate_pages) {
+ xdr_write_pages(xdr, args->layoutupdate_pages, 0,
+ args->layoutupdate_len);
+ }
+ }
return 0;
}
@@ -2893,24 +2872,6 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
}
/*
- * Encode GETDEVICELIST request
- */
-static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req,
- struct xdr_stream *xdr,
- struct nfs4_getdevicelist_args *args)
-{
- struct compound_hdr hdr = {
- .minorversion = nfs4_xdr_minorversion(&args->seq_args),
- };
-
- encode_compound_hdr(xdr, req, &hdr);
- encode_sequence(xdr, &args->seq_args, &hdr);
- encode_putfh(xdr, args->fh, &hdr);
- encode_getdevicelist(xdr, args, &hdr);
- encode_nops(&hdr);
-}
-
-/*
* Encode GETDEVICEINFO request
*/
static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req,
@@ -5765,54 +5726,6 @@ out_overflow:
}
#if defined(CONFIG_NFS_V4_1)
-/*
- * TODO: Need to handle case when EOF != true;
- */
-static int decode_getdevicelist(struct xdr_stream *xdr,
- struct pnfs_devicelist *res)
-{
- __be32 *p;
- int status, i;
- nfs4_verifier verftemp;
-
- status = decode_op_hdr(xdr, OP_GETDEVICELIST);
- if (status)
- return status;
-
- p = xdr_inline_decode(xdr, 8 + 8 + 4);
- if (unlikely(!p))
- goto out_overflow;
-
- /* TODO: Skip cookie for now */
- p += 2;
-
- /* Read verifier */
- p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE);
-
- res->num_devs = be32_to_cpup(p);
-
- dprintk("%s: num_dev %d\n", __func__, res->num_devs);
-
- if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) {
- printk(KERN_ERR "NFS: %s too many result dev_num %u\n",
- __func__, res->num_devs);
- return -EIO;
- }
-
- p = xdr_inline_decode(xdr,
- res->num_devs * NFS4_DEVICEID4_SIZE + 4);
- if (unlikely(!p))
- goto out_overflow;
- for (i = 0; i < res->num_devs; i++)
- p = xdr_decode_opaque_fixed(p, res->dev_id[i].data,
- NFS4_DEVICEID4_SIZE);
- res->eof = be32_to_cpup(p);
- return 0;
-out_overflow:
- print_overflow_msg(__func__, xdr);
- return -EIO;
-}
-
static int decode_getdeviceinfo(struct xdr_stream *xdr,
struct pnfs_device *pdev)
{
@@ -5862,9 +5775,16 @@ static int decode_getdeviceinfo(struct xdr_stream *xdr,
p = xdr_inline_decode(xdr, 4 * len);
if (unlikely(!p))
goto out_overflow;
- for (i = 0; i < len; i++, p++) {
- if (be32_to_cpup(p)) {
- dprintk("%s: notifications not supported\n",
+
+ if (be32_to_cpup(p++) &
+ ~(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE)) {
+ dprintk("%s: unsupported notification\n",
+ __func__);
+ }
+
+ for (i = 1; i < len; i++) {
+ if (be32_to_cpup(p++)) {
+ dprintk("%s: unsupported notification\n",
__func__);
return -EIO;
}
@@ -7097,32 +7017,6 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
}
/*
- * Decode GETDEVICELIST response
- */
-static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp,
- struct xdr_stream *xdr,
- struct nfs4_getdevicelist_res *res)
-{
- struct compound_hdr hdr;
- int status;
-
- dprintk("encoding getdevicelist!\n");
-
- status = decode_compound_hdr(xdr, &hdr);
- if (status != 0)
- goto out;
- status = decode_sequence(xdr, &res->seq_res, rqstp);
- if (status != 0)
- goto out;
- status = decode_putfh(xdr);
- if (status != 0)
- goto out;
- status = decode_getdevicelist(xdr, res->devlist);
-out:
- return status;
-}
-
-/*
* Decode GETDEVINFO response
*/
static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp,
@@ -7490,7 +7384,6 @@ struct rpc_procinfo nfs4_procedures[] = {
PROC(SECINFO_NO_NAME, enc_secinfo_no_name, dec_secinfo_no_name),
PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid),
PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid),
- PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist),
PROC(BIND_CONN_TO_SESSION,
enc_bind_conn_to_session, dec_bind_conn_to_session),
PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid),
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index ae05278b3761..c6e4bda63000 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -60,52 +60,6 @@ objio_free_deviceid_node(struct nfs4_deviceid_node *d)
kfree(de);
}
-static struct objio_dev_ent *_dev_list_find(const struct nfs_server *nfss,
- const struct nfs4_deviceid *d_id)
-{
- struct nfs4_deviceid_node *d;
- struct objio_dev_ent *de;
-
- d = nfs4_find_get_deviceid(nfss->pnfs_curr_ld, nfss->nfs_client, d_id);
- if (!d)
- return NULL;
-
- de = container_of(d, struct objio_dev_ent, id_node);
- return de;
-}
-
-static struct objio_dev_ent *
-_dev_list_add(const struct nfs_server *nfss,
- const struct nfs4_deviceid *d_id, struct osd_dev *od,
- gfp_t gfp_flags)
-{
- struct nfs4_deviceid_node *d;
- struct objio_dev_ent *de = kzalloc(sizeof(*de), gfp_flags);
- struct objio_dev_ent *n;
-
- if (!de) {
- dprintk("%s: -ENOMEM od=%p\n", __func__, od);
- return NULL;
- }
-
- dprintk("%s: Adding od=%p\n", __func__, od);
- nfs4_init_deviceid_node(&de->id_node,
- nfss->pnfs_curr_ld,
- nfss->nfs_client,
- d_id);
- de->od.od = od;
-
- d = nfs4_insert_deviceid_node(&de->id_node);
- n = container_of(d, struct objio_dev_ent, id_node);
- if (n != de) {
- dprintk("%s: Race with other n->od=%p\n", __func__, n->od.od);
- objio_free_deviceid_node(&de->id_node);
- de = n;
- }
-
- return de;
-}
-
struct objio_segment {
struct pnfs_layout_segment lseg;
@@ -130,29 +84,24 @@ struct objio_state {
/* Send and wait for a get_device_info of devices in the layout,
then look them up with the osd_initiator library */
-static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
- struct objio_segment *objio_seg, unsigned c, struct nfs4_deviceid *d_id,
- gfp_t gfp_flags)
+struct nfs4_deviceid_node *
+objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+ gfp_t gfp_flags)
{
struct pnfs_osd_deviceaddr *deviceaddr;
- struct objio_dev_ent *ode;
+ struct objio_dev_ent *ode = NULL;
struct osd_dev *od;
struct osd_dev_info odi;
bool retry_flag = true;
+ __be32 *p;
int err;
- ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
- if (ode) {
- objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
- return 0;
- }
+ deviceaddr = kzalloc(sizeof(*deviceaddr), gfp_flags);
+ if (!deviceaddr)
+ return NULL;
- err = objlayout_get_deviceinfo(pnfslay, d_id, &deviceaddr, gfp_flags);
- if (unlikely(err)) {
- dprintk("%s: objlayout_get_deviceinfo dev(%llx:%llx) =>%d\n",
- __func__, _DEVID_LO(d_id), _DEVID_HI(d_id), err);
- return err;
- }
+ p = page_address(pdev->pages[0]);
+ pnfs_osd_xdr_decode_deviceaddr(deviceaddr, p);
odi.systemid_len = deviceaddr->oda_systemid.len;
if (odi.systemid_len > sizeof(odi.systemid)) {
@@ -188,14 +137,24 @@ retry_lookup:
goto out;
}
- ode = _dev_list_add(NFS_SERVER(pnfslay->plh_inode), d_id, od,
- gfp_flags);
- objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
dprintk("Adding new dev_id(%llx:%llx)\n",
- _DEVID_LO(d_id), _DEVID_HI(d_id));
+ _DEVID_LO(&pdev->dev_id), _DEVID_HI(&pdev->dev_id));
+
+ ode = kzalloc(sizeof(*ode), gfp_flags);
+ if (!ode) {
+ dprintk("%s: -ENOMEM od=%p\n", __func__, od);
+ goto out;
+ }
+
+ nfs4_init_deviceid_node(&ode->id_node, server, &pdev->dev_id);
+ kfree(deviceaddr);
+
+ ode->od.od = od;
+ return &ode->id_node;
+
out:
- objlayout_put_deviceinfo(deviceaddr);
- return err;
+ kfree(deviceaddr);
+ return NULL;
}
static void copy_single_comp(struct ore_components *oc, unsigned c,
@@ -254,6 +213,7 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
struct xdr_stream *xdr,
gfp_t gfp_flags)
{
+ struct nfs_server *server = NFS_SERVER(pnfslay->plh_inode);
struct objio_segment *objio_seg;
struct pnfs_osd_xdr_decode_layout_iter iter;
struct pnfs_osd_layout layout;
@@ -283,13 +243,21 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
objio_seg->oc.first_dev = layout.olo_comps_index;
cur_comp = 0;
while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
+ struct nfs4_deviceid_node *d;
+ struct objio_dev_ent *ode;
+
copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
- err = objio_devices_lookup(pnfslay, objio_seg, cur_comp,
- &src_comp.oc_object_id.oid_device_id,
- gfp_flags);
- if (err)
+
+ d = nfs4_find_get_deviceid(server,
+ &src_comp.oc_object_id.oid_device_id,
+ pnfslay->plh_lc_cred, gfp_flags);
+ if (!d) {
+ err = -ENXIO;
goto err;
- ++cur_comp;
+ }
+
+ ode = container_of(d, struct objio_dev_ent, id_node);
+ objio_seg->oc.ods[cur_comp++] = &ode->od;
}
/* pnfs_osd_xdr_decode_layout_comp returns false on error */
if (unlikely(err))
@@ -653,6 +621,7 @@ static struct pnfs_layoutdriver_type objlayout_type = {
.flags = PNFS_LAYOUTRET_ON_SETATTR |
PNFS_LAYOUTRET_ON_ERROR,
+ .max_deviceinfo_size = PAGE_SIZE,
.owner = THIS_MODULE,
.alloc_layout_hdr = objlayout_alloc_layout_hdr,
.free_layout_hdr = objlayout_free_layout_hdr,
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 697a16d11fac..c89357c7a914 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -574,76 +574,6 @@ loop_done:
dprintk("%s: Return\n", __func__);
}
-
-/*
- * Get Device Info API for io engines
- */
-struct objlayout_deviceinfo {
- struct page *page;
- struct pnfs_osd_deviceaddr da; /* This must be last */
-};
-
-/* Initialize and call nfs_getdeviceinfo, then decode and return a
- * "struct pnfs_osd_deviceaddr *" Eventually objlayout_put_deviceinfo()
- * should be called.
- */
-int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
- struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
- gfp_t gfp_flags)
-{
- struct objlayout_deviceinfo *odi;
- struct pnfs_device pd;
- struct page *page, **pages;
- u32 *p;
- int err;
-
- page = alloc_page(gfp_flags);
- if (!page)
- return -ENOMEM;
-
- pages = &page;
- pd.pages = pages;
-
- memcpy(&pd.dev_id, d_id, sizeof(*d_id));
- pd.layout_type = LAYOUT_OSD2_OBJECTS;
- pd.pages = &page;
- pd.pgbase = 0;
- pd.pglen = PAGE_SIZE;
- pd.mincount = 0;
- pd.maxcount = PAGE_SIZE;
-
- err = nfs4_proc_getdeviceinfo(NFS_SERVER(pnfslay->plh_inode), &pd,
- pnfslay->plh_lc_cred);
- dprintk("%s nfs_getdeviceinfo returned %d\n", __func__, err);
- if (err)
- goto err_out;
-
- p = page_address(page);
- odi = kzalloc(sizeof(*odi), gfp_flags);
- if (!odi) {
- err = -ENOMEM;
- goto err_out;
- }
- pnfs_osd_xdr_decode_deviceaddr(&odi->da, p);
- odi->page = page;
- *deviceaddr = &odi->da;
- return 0;
-
-err_out:
- __free_page(page);
- return err;
-}
-
-void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr)
-{
- struct objlayout_deviceinfo *odi = container_of(deviceaddr,
- struct objlayout_deviceinfo,
- da);
-
- __free_page(odi->page);
- kfree(odi);
-}
-
enum {
OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
index fd13f1d2f136..3a0828d57339 100644
--- a/fs/nfs/objlayout/objlayout.h
+++ b/fs/nfs/objlayout/objlayout.h
@@ -149,11 +149,6 @@ extern void objlayout_read_done(struct objlayout_io_res *oir,
extern void objlayout_write_done(struct objlayout_io_res *oir,
ssize_t status, bool sync);
-extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
- struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
- gfp_t gfp_flags);
-extern void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr);
-
/*
* exported generic objects function vectors
*/
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index be7cbce6e4c7..94e16ec88312 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -481,6 +481,14 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
return 0;
}
+ /*
+ * Limit the request size so that we can still allocate a page array
+ * for it without upsetting the slab allocator.
+ */
+ if (((desc->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
+ sizeof(struct page) > PAGE_SIZE)
+ return 0;
+
return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes);
}
EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index a3851debf8a2..76de7f568119 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -594,6 +594,9 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
dprintk("%s freeing layout for inode %lu\n", __func__,
lo->plh_inode->i_ino);
inode = lo->plh_inode;
+
+ pnfs_layoutcommit_inode(inode, false);
+
spin_lock(&inode->i_lock);
list_del_init(&lo->plh_bulk_destroy);
lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
@@ -682,17 +685,6 @@ static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
return (s32)(s1 - s2) > 0;
}
-static void
-pnfs_verify_layout_stateid(struct pnfs_layout_hdr *lo,
- const nfs4_stateid *new,
- struct list_head *free_me_list)
-{
- if (nfs4_stateid_match_other(&lo->plh_stateid, new))
- return;
- /* Layout is new! Kill existing layout segments */
- pnfs_mark_matching_lsegs_invalid(lo, free_me_list, NULL);
-}
-
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
@@ -749,7 +741,8 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
status = -EAGAIN;
} else if (!nfs4_valid_open_stateid(open_state)) {
status = -EBADF;
- } else if (list_empty(&lo->plh_segs)) {
+ } else if (list_empty(&lo->plh_segs) ||
+ test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
int seq;
do {
@@ -864,6 +857,16 @@ _pnfs_return_layout(struct inode *ino)
empty = list_empty(&lo->plh_segs);
pnfs_clear_layoutcommit(ino, &tmp_list);
pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+
+ if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
+ struct pnfs_layout_range range = {
+ .iomode = IOMODE_ANY,
+ .offset = 0,
+ .length = NFS4_MAX_UINT64,
+ };
+ NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range);
+ }
+
/* Don't send a LAYOUTRETURN if list was initially empty */
if (empty) {
spin_unlock(&ino->i_lock);
@@ -871,6 +874,8 @@ _pnfs_return_layout(struct inode *ino)
dprintk("NFS: %s no layout segments to return\n", __func__);
goto out;
}
+
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
lo->plh_block_lgets++;
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&tmp_list);
@@ -1358,25 +1363,41 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
goto out;
}
+ init_lseg(lo, lseg);
+ lseg->pls_range = res->range;
+
spin_lock(&ino->i_lock);
if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
dprintk("%s forget reply due to recall\n", __func__);
goto out_forget_reply;
}
- if (pnfs_layoutgets_blocked(lo, 1) ||
- pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+ if (pnfs_layoutgets_blocked(lo, 1)) {
dprintk("%s forget reply due to state\n", __func__);
goto out_forget_reply;
}
- /* Check that the new stateid matches the old stateid */
- pnfs_verify_layout_stateid(lo, &res->stateid, &free_me);
- /* Done processing layoutget. Set the layout stateid */
- pnfs_set_layout_stateid(lo, &res->stateid, false);
+ if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
+ /* existing state ID, make sure the sequence number matches. */
+ if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+ dprintk("%s forget reply due to sequence\n", __func__);
+ goto out_forget_reply;
+ }
+ pnfs_set_layout_stateid(lo, &res->stateid, false);
+ } else {
+ /*
+ * We got an entirely new state ID. Mark all segments for the
+ * inode invalid, and don't bother validating the stateid
+ * sequence number.
+ */
+ pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL);
+
+ nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
+ lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
+ }
+
+ clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- init_lseg(lo, lseg);
- lseg->pls_range = res->range;
pnfs_get_lseg(lseg);
pnfs_layout_insert_lseg(lo, lseg);
@@ -1797,6 +1818,35 @@ pnfs_set_layoutcommit(struct nfs_pgio_header *hdr)
}
EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
+void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data)
+{
+ struct inode *inode = data->inode;
+ struct nfs_inode *nfsi = NFS_I(inode);
+ bool mark_as_dirty = false;
+
+ spin_lock(&inode->i_lock);
+ if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
+ mark_as_dirty = true;
+ dprintk("%s: Set layoutcommit for inode %lu ",
+ __func__, inode->i_ino);
+ }
+ if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &data->lseg->pls_flags)) {
+ /* references matched in nfs4_layoutcommit_release */
+ pnfs_get_lseg(data->lseg);
+ }
+ if (data->lwb > nfsi->layout->plh_lwb)
+ nfsi->layout->plh_lwb = data->lwb;
+ spin_unlock(&inode->i_lock);
+ dprintk("%s: lseg %p end_pos %llu\n",
+ __func__, data->lseg, nfsi->layout->plh_lwb);
+
+ /* if pnfs_layoutcommit_inode() runs between inode locks, the next one
+ * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
+ if (mark_as_dirty)
+ mark_inode_dirty_sync(inode);
+}
+EXPORT_SYMBOL_GPL(pnfs_commit_set_layoutcommit);
+
void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
{
struct nfs_server *nfss = NFS_SERVER(data->args.inode);
@@ -1817,6 +1867,7 @@ void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
int
pnfs_layoutcommit_inode(struct inode *inode, bool sync)
{
+ struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
struct nfs4_layoutcommit_data *data;
struct nfs_inode *nfsi = NFS_I(inode);
loff_t end_pos;
@@ -1867,6 +1918,20 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
data->args.lastbytewritten = end_pos - 1;
data->res.server = NFS_SERVER(inode);
+ if (ld->prepare_layoutcommit) {
+ status = ld->prepare_layoutcommit(&data->args);
+ if (status) {
+ spin_lock(&inode->i_lock);
+ if (end_pos < nfsi->layout->plh_lwb)
+ nfsi->layout->plh_lwb = end_pos;
+ spin_unlock(&inode->i_lock);
+ put_rpccred(data->cred);
+ set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
+ goto clear_layoutcommitting;
+ }
+ }
+
+
status = nfs4_proc_layoutcommit(data, sync);
out:
if (status)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index aca3dff5dae6..693ce42ec683 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -65,12 +65,15 @@ enum {
NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */
NFS_LAYOUT_ROC, /* some lseg had roc bit set */
NFS_LAYOUT_RETURN, /* Return this layout ASAP */
+ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */
};
enum layoutdriver_policy_flags {
- /* Should the pNFS client commit and return the layout upon a setattr */
+ /* Should the pNFS client commit and return the layout upon truncate to
+ * a smaller size */
PNFS_LAYOUTRET_ON_SETATTR = 1 << 0,
PNFS_LAYOUTRET_ON_ERROR = 1 << 1,
+ PNFS_READ_WHOLE_PAGE = 1 << 2,
};
struct nfs4_deviceid_node;
@@ -82,6 +85,7 @@ struct pnfs_layoutdriver_type {
const char *name;
struct module *owner;
unsigned flags;
+ unsigned max_deviceinfo_size;
int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *);
int (*clear_layoutdriver) (struct nfs_server *);
@@ -92,6 +96,9 @@ struct pnfs_layoutdriver_type {
struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
void (*free_lseg) (struct pnfs_layout_segment *lseg);
+ void (*return_range) (struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_range *range);
+
/* test for nfs page cache coalescing */
const struct nfs_pageio_ops *pg_read_ops;
const struct nfs_pageio_ops *pg_write_ops;
@@ -121,14 +128,17 @@ struct pnfs_layoutdriver_type {
enum pnfs_try_status (*write_pagelist)(struct nfs_pgio_header *, int);
void (*free_deviceid_node) (struct nfs4_deviceid_node *);
+ struct nfs4_deviceid_node * (*alloc_deviceid_node)
+ (struct nfs_server *server, struct pnfs_device *pdev,
+ gfp_t gfp_flags);
void (*encode_layoutreturn) (struct pnfs_layout_hdr *layoutid,
struct xdr_stream *xdr,
const struct nfs4_layoutreturn_args *args);
void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
-
- void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
+ int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args);
+ void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo,
struct xdr_stream *xdr,
const struct nfs4_layoutcommit_args *args);
};
@@ -171,9 +181,6 @@ extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
/* nfs4proc.c */
-extern int nfs4_proc_getdevicelist(struct nfs_server *server,
- const struct nfs_fh *fh,
- struct pnfs_devicelist *devlist);
extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
struct pnfs_device *dev,
struct rpc_cred *cred);
@@ -219,6 +226,7 @@ void pnfs_roc_release(struct inode *ino);
void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
void pnfs_set_layoutcommit(struct nfs_pgio_header *);
+void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data);
void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
int _pnfs_return_layout(struct inode *);
@@ -255,11 +263,12 @@ struct nfs4_deviceid_node {
atomic_t ref;
};
-struct nfs4_deviceid_node *nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+struct nfs4_deviceid_node *
+nfs4_find_get_deviceid(struct nfs_server *server,
+ const struct nfs4_deviceid *id, struct rpc_cred *cred,
+ gfp_t gfp_mask);
void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
-void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
- const struct pnfs_layoutdriver_type *,
- const struct nfs_client *,
+void nfs4_init_deviceid_node(struct nfs4_deviceid_node *, struct nfs_server *,
const struct nfs4_deviceid *);
struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
@@ -267,6 +276,13 @@ void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
void nfs4_deviceid_purge_client(const struct nfs_client *);
+static inline struct nfs4_deviceid_node *
+nfs4_get_deviceid(struct nfs4_deviceid_node *d)
+{
+ atomic_inc(&d->ref);
+ return d;
+}
+
static inline struct pnfs_layout_segment *
pnfs_get_lseg(struct pnfs_layout_segment *lseg)
{
@@ -368,6 +384,14 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode)
}
static inline bool
+pnfs_ld_read_whole_page(struct inode *inode)
+{
+ if (!pnfs_enabled_sb(NFS_SERVER(inode)))
+ return false;
+ return NFS_SERVER(inode)->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE;
+}
+
+static inline bool
pnfs_layoutcommit_outstanding(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
@@ -443,6 +467,12 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode)
}
static inline bool
+pnfs_ld_read_whole_page(struct inode *inode)
+{
+ return false;
+}
+
+static inline bool
pnfs_roc(struct inode *ino)
{
return false;
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 6da209bd9408..aa2ec0015183 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -29,6 +29,9 @@
*/
#include <linux/export.h>
+#include <linux/nfs_fs.h>
+#include "nfs4session.h"
+#include "internal.h"
#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
@@ -89,6 +92,74 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
return NULL;
}
+static struct nfs4_deviceid_node *
+nfs4_get_device_info(struct nfs_server *server,
+ const struct nfs4_deviceid *dev_id,
+ struct rpc_cred *cred, gfp_t gfp_flags)
+{
+ struct nfs4_deviceid_node *d = NULL;
+ struct pnfs_device *pdev = NULL;
+ struct page **pages = NULL;
+ u32 max_resp_sz;
+ int max_pages;
+ int rc, i;
+
+ /*
+ * Use the session max response size as the basis for setting
+ * GETDEVICEINFO's maxcount
+ */
+ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
+ if (server->pnfs_curr_ld->max_deviceinfo_size &&
+ server->pnfs_curr_ld->max_deviceinfo_size < max_resp_sz)
+ max_resp_sz = server->pnfs_curr_ld->max_deviceinfo_size;
+ max_pages = nfs_page_array_len(0, max_resp_sz);
+ dprintk("%s: server %p max_resp_sz %u max_pages %d\n",
+ __func__, server, max_resp_sz, max_pages);
+
+ pdev = kzalloc(sizeof(*pdev), gfp_flags);
+ if (!pdev)
+ return NULL;
+
+ pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
+ if (!pages)
+ goto out_free_pdev;
+
+ for (i = 0; i < max_pages; i++) {
+ pages[i] = alloc_page(gfp_flags);
+ if (!pages[i])
+ goto out_free_pages;
+ }
+
+ memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
+ pdev->layout_type = server->pnfs_curr_ld->id;
+ pdev->pages = pages;
+ pdev->pgbase = 0;
+ pdev->pglen = max_resp_sz;
+ pdev->mincount = 0;
+ pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;
+
+ rc = nfs4_proc_getdeviceinfo(server, pdev, cred);
+ dprintk("%s getdevice info returns %d\n", __func__, rc);
+ if (rc)
+ goto out_free_pages;
+
+ /*
+ * Found new device, need to decode it and then add it to the
+ * list of known devices for this mountpoint.
+ */
+ d = server->pnfs_curr_ld->alloc_deviceid_node(server, pdev,
+ gfp_flags);
+
+out_free_pages:
+ for (i = 0; i < max_pages; i++)
+ __free_page(pages[i]);
+ kfree(pages);
+out_free_pdev:
+ kfree(pdev);
+ dprintk("<-- %s d %p\n", __func__, d);
+ return d;
+}
+
/*
* Lookup a deviceid in cache and get a reference count on it if found
*
@@ -96,14 +167,14 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
* @id deviceid to look up
*/
static struct nfs4_deviceid_node *
-_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
- const struct nfs_client *clp, const struct nfs4_deviceid *id,
- long hash)
+__nfs4_find_get_deviceid(struct nfs_server *server,
+ const struct nfs4_deviceid *id, long hash)
{
struct nfs4_deviceid_node *d;
rcu_read_lock();
- d = _lookup_deviceid(ld, clp, id, hash);
+ d = _lookup_deviceid(server->pnfs_curr_ld, server->nfs_client, id,
+ hash);
if (d != NULL)
atomic_inc(&d->ref);
rcu_read_unlock();
@@ -111,10 +182,33 @@ _find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
}
struct nfs4_deviceid_node *
-nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
- const struct nfs_client *clp, const struct nfs4_deviceid *id)
+nfs4_find_get_deviceid(struct nfs_server *server,
+ const struct nfs4_deviceid *id, struct rpc_cred *cred,
+ gfp_t gfp_mask)
{
- return _find_get_deviceid(ld, clp, id, nfs4_deviceid_hash(id));
+ long hash = nfs4_deviceid_hash(id);
+ struct nfs4_deviceid_node *d, *new;
+
+ d = __nfs4_find_get_deviceid(server, id, hash);
+ if (d)
+ return d;
+
+ new = nfs4_get_device_info(server, id, cred, gfp_mask);
+ if (!new)
+ return new;
+
+ spin_lock(&nfs4_deviceid_lock);
+ d = __nfs4_find_get_deviceid(server, id, hash);
+ if (d) {
+ spin_unlock(&nfs4_deviceid_lock);
+ server->pnfs_curr_ld->free_deviceid_node(new);
+ return d;
+ }
+ hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]);
+ atomic_inc(&new->ref);
+ spin_unlock(&nfs4_deviceid_lock);
+
+ return new;
}
EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid);
@@ -151,15 +245,13 @@ nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);
void
-nfs4_init_deviceid_node(struct nfs4_deviceid_node *d,
- const struct pnfs_layoutdriver_type *ld,
- const struct nfs_client *nfs_client,
+nfs4_init_deviceid_node(struct nfs4_deviceid_node *d, struct nfs_server *server,
const struct nfs4_deviceid *id)
{
INIT_HLIST_NODE(&d->node);
INIT_HLIST_NODE(&d->tmpnode);
- d->ld = ld;
- d->nfs_client = nfs_client;
+ d->ld = server->pnfs_curr_ld;
+ d->nfs_client = server->nfs_client;
d->flags = 0;
d->deviceid = *id;
atomic_set(&d->ref, 1);
@@ -167,39 +259,6 @@ nfs4_init_deviceid_node(struct nfs4_deviceid_node *d,
EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node);
/*
- * Uniquely initialize and insert a deviceid node into cache
- *
- * @new new deviceid node
- * Note that the caller must set up the following members:
- * new->ld
- * new->nfs_client
- * new->deviceid
- *
- * @ret the inserted node, if none found, otherwise, the found entry.
- */
-struct nfs4_deviceid_node *
-nfs4_insert_deviceid_node(struct nfs4_deviceid_node *new)
-{
- struct nfs4_deviceid_node *d;
- long hash;
-
- spin_lock(&nfs4_deviceid_lock);
- hash = nfs4_deviceid_hash(&new->deviceid);
- d = _find_get_deviceid(new->ld, new->nfs_client, &new->deviceid, hash);
- if (d) {
- spin_unlock(&nfs4_deviceid_lock);
- return d;
- }
-
- hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]);
- spin_unlock(&nfs4_deviceid_lock);
- atomic_inc(&new->ref);
-
- return new;
-}
-EXPORT_SYMBOL_GPL(nfs4_insert_deviceid_node);
-
-/*
* Dereference a deviceid node and delete it when its reference count drops
* to zero.
*
@@ -299,4 +358,3 @@ nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
}
rcu_read_unlock();
}
-
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e4499d5b51e8..31a11b0e885d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2065,11 +2065,6 @@ static int nfs23_validate_mount_data(void *options,
return NFS_TEXT_DATA;
}
-#if !IS_ENABLED(CONFIG_NFS_V3)
- if (args->version == 3)
- goto out_v3_not_compiled;
-#endif /* !CONFIG_NFS_V3 */
-
return 0;
out_no_data:
@@ -2085,12 +2080,6 @@ out_no_sec:
dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n");
return -EINVAL;
-#if !IS_ENABLED(CONFIG_NFS_V3)
-out_v3_not_compiled:
- dfprintk(MOUNT, "NFS: NFSv3 is not compiled into kernel\n");
- return -EPROTONOSUPPORT;
-#endif /* !CONFIG_NFS_V3 */
-
out_nomem:
dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n");
return -ENOMEM;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 175d5d073ccf..12493846a2d3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -49,6 +49,9 @@ static const struct nfs_rw_ops nfs_rw_write_ops;
static void nfs_clear_request_commit(struct nfs_page *req);
static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
struct inode *inode);
+static struct nfs_page *
+nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
+ struct page *page);
static struct kmem_cache *nfs_wdata_cachep;
static mempool_t *nfs_wdata_mempool;
@@ -95,38 +98,6 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
}
/*
- * nfs_page_search_commits_for_head_request_locked
- *
- * Search through commit lists on @inode for the head request for @page.
- * Must be called while holding the inode (which is cinfo) lock.
- *
- * Returns the head request if found, or NULL if not found.
- */
-static struct nfs_page *
-nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
- struct page *page)
-{
- struct nfs_page *freq, *t;
- struct nfs_commit_info cinfo;
- struct inode *inode = &nfsi->vfs_inode;
-
- nfs_init_cinfo_from_inode(&cinfo, inode);
-
- /* search through pnfs commit lists */
- freq = pnfs_search_commit_reqs(inode, &cinfo, page);
- if (freq)
- return freq->wb_head;
-
- /* Linearly search the commit list for the correct request */
- list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) {
- if (freq->wb_page == page)
- return freq->wb_head;
- }
-
- return NULL;
-}
-
-/*
* nfs_page_find_head_request_locked - find head request associated with @page
*
* must be called while holding the inode lock.
@@ -271,11 +242,14 @@ static void nfs_mark_uptodate(struct nfs_page *req)
static int wb_priority(struct writeback_control *wbc)
{
+ int ret = 0;
if (wbc->for_reclaim)
return FLUSH_HIGHPRI | FLUSH_STABLE;
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ ret = FLUSH_COND_STABLE;
if (wbc->for_kupdate || wbc->for_background)
- return FLUSH_LOWPRI | FLUSH_COND_STABLE;
- return FLUSH_COND_STABLE;
+ ret |= FLUSH_LOWPRI;
+ return ret;
}
/*
@@ -731,6 +705,8 @@ static void nfs_inode_remove_request(struct nfs_page *req)
if (likely(!PageSwapCache(head->wb_page))) {
set_page_private(head->wb_page, 0);
ClearPagePrivate(head->wb_page);
+ smp_mb__after_atomic();
+ wake_up_page(head->wb_page, PG_private);
clear_bit(PG_MAPPED, &head->wb_flags);
}
nfsi->npages--;
@@ -749,7 +725,38 @@ nfs_mark_request_dirty(struct nfs_page *req)
__set_page_dirty_nobuffers(req->wb_page);
}
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
+/*
+ * nfs_page_search_commits_for_head_request_locked
+ *
+ * Search through commit lists on @inode for the head request for @page.
+ * Must be called while holding the inode (which is cinfo) lock.
+ *
+ * Returns the head request if found, or NULL if not found.
+ */
+static struct nfs_page *
+nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
+ struct page *page)
+{
+ struct nfs_page *freq, *t;
+ struct nfs_commit_info cinfo;
+ struct inode *inode = &nfsi->vfs_inode;
+
+ nfs_init_cinfo_from_inode(&cinfo, inode);
+
+ /* search through pnfs commit lists */
+ freq = pnfs_search_commit_reqs(inode, &cinfo, page);
+ if (freq)
+ return freq->wb_head;
+
+ /* Linearly search the commit list for the correct request */
+ list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) {
+ if (freq->wb_page == page)
+ return freq->wb_head;
+ }
+
+ return NULL;
+}
+
/**
* nfs_request_add_commit_list - add request to a commit list
* @req: pointer to a struct nfs_page
@@ -867,36 +874,6 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr)
return hdr->verf.committed != NFS_FILE_SYNC;
}
-#else
-static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
- struct inode *inode)
-{
-}
-
-void nfs_init_cinfo(struct nfs_commit_info *cinfo,
- struct inode *inode,
- struct nfs_direct_req *dreq)
-{
-}
-
-void
-nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
- struct nfs_commit_info *cinfo)
-{
-}
-
-static void
-nfs_clear_request_commit(struct nfs_page *req)
-{
-}
-
-int nfs_write_need_commit(struct nfs_pgio_header *hdr)
-{
- return 0;
-}
-
-#endif
-
static void nfs_write_completion(struct nfs_pgio_header *hdr)
{
struct nfs_commit_info cinfo;
@@ -932,7 +909,6 @@ out:
hdr->release(hdr);
}
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
unsigned long
nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
{
@@ -989,19 +965,6 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
return ret;
}
-#else
-unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
-{
- return 0;
-}
-
-int nfs_scan_commit(struct inode *inode, struct list_head *dst,
- struct nfs_commit_info *cinfo)
-{
- return 0;
-}
-#endif
-
/*
* Search for an existing write request, and attempt to update
* it to reflect a new dirty region on a given page.
@@ -1394,7 +1357,6 @@ static int nfs_writeback_done(struct rpc_task *task,
return status;
nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count);
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
if (hdr->res.verf->committed < hdr->args.stable &&
task->tk_status >= 0) {
/* We tried a write call, but the server did not
@@ -1416,7 +1378,6 @@ static int nfs_writeback_done(struct rpc_task *task,
complain = jiffies + 300 * HZ;
}
}
-#endif
/* Deal with the suid/sgid bit corner case */
if (nfs_should_remove_suid(inode))
@@ -1469,7 +1430,6 @@ static void nfs_writeback_result(struct rpc_task *task,
}
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
{
int ret;
@@ -1538,6 +1498,18 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
}
EXPORT_SYMBOL_GPL(nfs_initiate_commit);
+static loff_t nfs_get_lwb(struct list_head *head)
+{
+ loff_t lwb = 0;
+ struct nfs_page *req;
+
+ list_for_each_entry(req, head, wb_list)
+ if (lwb < (req_offset(req) + req->wb_bytes))
+ lwb = req_offset(req) + req->wb_bytes;
+
+ return lwb;
+}
+
/*
* Set up the argument/result storage required for the RPC call.
*/
@@ -1557,6 +1529,9 @@ void nfs_init_commit(struct nfs_commit_data *data,
data->inode = inode;
data->cred = first->wb_context->cred;
data->lseg = lseg; /* reference transferred */
+ /* only set lwb for pnfs commit */
+ if (lseg)
+ data->lwb = nfs_get_lwb(&data->pages);
data->mds_ops = &nfs_commit_ops;
data->completion_ops = cinfo->completion_ops;
data->dreq = cinfo->dreq;
@@ -1636,6 +1611,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
struct nfs_page *req;
int status = data->task.tk_status;
struct nfs_commit_info cinfo;
+ struct nfs_server *nfss;
while (!list_empty(&data->pages)) {
req = nfs_list_entry(data->pages.next);
@@ -1669,6 +1645,10 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
next:
nfs_unlock_and_release_request(req);
}
+ nfss = NFS_SERVER(data->inode);
+ if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
+ clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+
nfs_init_cinfo(&cinfo, data->inode, data->dreq);
if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
nfs_commit_clear_lock(NFS_I(data->inode));
@@ -1778,12 +1758,6 @@ out_mark_dirty:
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
return ret;
}
-#else
-static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_control *wbc)
-{
- return 0;
-}
-#endif
int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
index f689ed82af3a..d153ca3ea577 100644
--- a/fs/nfs_common/Makefile
+++ b/fs/nfs_common/Makefile
@@ -3,5 +3,6 @@
#
obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
-
nfs_acl-objs := nfsacl.o
+
+obj-$(CONFIG_GRACE_PERIOD) += grace.o
diff --git a/fs/lockd/grace.c b/fs/nfs_common/grace.c
index 6d1ee7204c88..ae6e58ea4de5 100644
--- a/fs/lockd/grace.c
+++ b/fs/nfs_common/grace.c
@@ -1,17 +1,20 @@
/*
* Common code for control of lockd and nfsv4 grace periods.
+ *
+ * Transplanted from lockd code
*/
#include <linux/module.h>
-#include <linux/lockd/bind.h>
#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <linux/fs.h>
-#include "netns.h"
-
+static int grace_net_id;
static DEFINE_SPINLOCK(grace_lock);
/**
* locks_start_grace
+ * @net: net namespace that this lock manager belongs to
* @lm: who this grace period is for
*
* A grace period is a period during which locks should not be given
@@ -21,18 +24,20 @@ static DEFINE_SPINLOCK(grace_lock);
*
* This function is called to start a grace period.
*/
-void locks_start_grace(struct net *net, struct lock_manager *lm)
+void
+locks_start_grace(struct net *net, struct lock_manager *lm)
{
- struct lockd_net *ln = net_generic(net, lockd_net_id);
+ struct list_head *grace_list = net_generic(net, grace_net_id);
spin_lock(&grace_lock);
- list_add(&lm->list, &ln->grace_list);
+ list_add(&lm->list, grace_list);
spin_unlock(&grace_lock);
}
EXPORT_SYMBOL_GPL(locks_start_grace);
/**
* locks_end_grace
+ * @net: net namespace that this lock manager belongs to
* @lm: who this grace period is for
*
* Call this function to state that the given lock manager is ready to
@@ -41,7 +46,8 @@ EXPORT_SYMBOL_GPL(locks_start_grace);
* Note that callers count on it being safe to call this more than once,
* and the second call should be a no-op.
*/
-void locks_end_grace(struct lock_manager *lm)
+void
+locks_end_grace(struct lock_manager *lm)
{
spin_lock(&grace_lock);
list_del_init(&lm->list);
@@ -56,10 +62,52 @@ EXPORT_SYMBOL_GPL(locks_end_grace);
* to answer ordinary lock requests, and when they should accept only
* lock reclaims.
*/
-int locks_in_grace(struct net *net)
+int
+locks_in_grace(struct net *net)
{
- struct lockd_net *ln = net_generic(net, lockd_net_id);
+ struct list_head *grace_list = net_generic(net, grace_net_id);
- return !list_empty(&ln->grace_list);
+ return !list_empty(grace_list);
}
EXPORT_SYMBOL_GPL(locks_in_grace);
+
+static int __net_init
+grace_init_net(struct net *net)
+{
+ struct list_head *grace_list = net_generic(net, grace_net_id);
+
+ INIT_LIST_HEAD(grace_list);
+ return 0;
+}
+
+static void __net_exit
+grace_exit_net(struct net *net)
+{
+ struct list_head *grace_list = net_generic(net, grace_net_id);
+
+ BUG_ON(!list_empty(grace_list));
+}
+
+static struct pernet_operations grace_net_ops = {
+ .init = grace_init_net,
+ .exit = grace_exit_net,
+ .id = &grace_net_id,
+ .size = sizeof(struct list_head),
+};
+
+static int __init
+init_grace(void)
+{
+ return register_pernet_subsys(&grace_net_ops);
+}
+
+static void __exit
+exit_grace(void)
+{
+ unregister_pernet_subsys(&grace_net_ops);
+}
+
+MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>");
+MODULE_LICENSE("GPL");
+module_init(init_grace)
+module_exit(exit_grace)
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index f994e750e0d1..73395156bdb4 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -71,6 +71,7 @@ config NFSD_V4
select FS_POSIX_ACL
select SUNRPC_GSS
select CRYPTO
+ select GRACE_PERIOD
help
This option enables support in your system's NFS server for
version 4 of the NFS protocol (RFC 3530).
@@ -94,9 +95,6 @@ config NFSD_V4_SECURITY_LABEL
If you do not wish to enable fine-grained security labels SELinux or
Smack policies on NFSv4 files, say N.
- WARNING: there is still a chance of backwards-incompatible protocol changes.
- For now we recommend "Y" only for developers and testers.
-
config NFSD_FAULT_INJECTION
bool "NFS server manual fault injection"
depends on NFSD_V4 && DEBUG_KERNEL
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index b582f9ab6b2a..dd96a3830004 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -18,7 +18,6 @@
* is much larger than a sockaddr_in6.
*/
struct svc_cacherep {
- struct hlist_node c_hash;
struct list_head c_lru;
unsigned char c_state, /* unused, inprog, done */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 72ffd7cce3c3..30a739d896ff 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1145,6 +1145,7 @@ static struct flags {
{ NFSEXP_ALLSQUASH, {"all_squash", ""}},
{ NFSEXP_ASYNC, {"async", "sync"}},
{ NFSEXP_GATHERED_WRITES, {"wdelay", "no_wdelay"}},
+ { NFSEXP_NOREADDIRPLUS, {"nordirplus", ""}},
{ NFSEXP_NOHIDE, {"nohide", ""}},
{ NFSEXP_CROSSMOUNT, {"crossmnt", ""}},
{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index fa2525b2e9d7..12f2aab4f614 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -223,11 +223,6 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
newfhp = fh_init(&resp->fh, NFS3_FHSIZE);
attr = &argp->attrs;
- /* Get the directory inode */
- nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_CREATE);
- if (nfserr)
- RETURN_STATUS(nfserr);
-
/* Unfudge the mode bits */
attr->ia_mode &= ~S_IFMT;
if (!(attr->ia_valid & ATTR_MODE)) {
@@ -471,6 +466,14 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
resp->buflen = resp->count;
resp->rqstp = rqstp;
offset = argp->cookie;
+
+ nfserr = fh_verify(rqstp, &resp->fh, S_IFDIR, NFSD_MAY_NOP);
+ if (nfserr)
+ RETURN_STATUS(nfserr);
+
+ if (resp->fh.fh_export->ex_flags & NFSEXP_NOREADDIRPLUS)
+ RETURN_STATUS(nfserr_notsupp);
+
nfserr = nfsd_readdir(rqstp, &resp->fh,
&offset,
&resp->common,
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index e0be57b0f79b..ed2b1151b171 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -49,12 +49,6 @@ static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
/* Index of predefined Linux callback client operations */
-enum {
- NFSPROC4_CLNT_CB_NULL = 0,
- NFSPROC4_CLNT_CB_RECALL,
- NFSPROC4_CLNT_CB_SEQUENCE,
-};
-
struct nfs4_cb_compound_hdr {
/* args */
u32 ident; /* minorversion 0 only */
@@ -494,7 +488,7 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
const struct nfsd4_callback *cb)
{
- const struct nfs4_delegation *args = cb->cb_op;
+ const struct nfs4_delegation *dp = cb_to_delegation(cb);
struct nfs4_cb_compound_hdr hdr = {
.ident = cb->cb_clp->cl_cb_ident,
.minorversion = cb->cb_minorversion,
@@ -502,7 +496,7 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_cb_compound4args(xdr, &hdr);
encode_cb_sequence4args(xdr, cb, &hdr);
- encode_cb_recall4args(xdr, args, &hdr);
+ encode_cb_recall4args(xdr, dp, &hdr);
encode_cb_nops(&hdr);
}
@@ -746,27 +740,6 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
static struct workqueue_struct *callback_wq;
-static void run_nfsd4_cb(struct nfsd4_callback *cb)
-{
- queue_work(callback_wq, &cb->cb_work);
-}
-
-static void do_probe_callback(struct nfs4_client *clp)
-{
- struct nfsd4_callback *cb = &clp->cl_cb_null;
-
- cb->cb_op = NULL;
- cb->cb_clp = clp;
-
- cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL];
- cb->cb_msg.rpc_argp = NULL;
- cb->cb_msg.rpc_resp = NULL;
-
- cb->cb_ops = &nfsd4_cb_probe_ops;
-
- run_nfsd4_cb(cb);
-}
-
/*
* Poke the callback thread to process any updates to the callback
* parameters, and send a null probe.
@@ -775,7 +748,7 @@ void nfsd4_probe_callback(struct nfs4_client *clp)
{
clp->cl_cb_state = NFSD4_CB_UNKNOWN;
set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
- do_probe_callback(clp);
+ nfsd4_run_cb(&clp->cl_cb_null);
}
void nfsd4_probe_callback_sync(struct nfs4_client *clp)
@@ -847,23 +820,9 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
rpc_wake_up_next(&clp->cl_cb_waitq);
dprintk("%s: freed slot, new seqid=%d\n", __func__,
clp->cl_cb_session->se_cb_seq_nr);
-
- /* We're done looking into the sequence information */
- task->tk_msg.rpc_resp = NULL;
}
-}
-
-
-static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
-{
- struct nfsd4_callback *cb = calldata;
- struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
- struct nfs4_client *clp = cb->cb_clp;
- struct rpc_clnt *current_rpc_client = clp->cl_cb_client;
-
- nfsd4_cb_done(task, calldata);
- if (current_rpc_client != task->tk_client) {
+ if (clp->cl_cb_client != task->tk_client) {
/* We're shutting down or changing cl_cb_client; leave
* it to nfsd4_process_cb_update to restart the call if
* necessary. */
@@ -872,47 +831,42 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
if (cb->cb_done)
return;
- switch (task->tk_status) {
+
+ switch (cb->cb_ops->done(cb, task)) {
case 0:
- cb->cb_done = true;
+ task->tk_status = 0;
+ rpc_restart_call_prepare(task);
return;
- case -EBADHANDLE:
- case -NFS4ERR_BAD_STATEID:
- /* Race: client probably got cb_recall
- * before open reply granting delegation */
+ case 1:
break;
- default:
+ case -1:
/* Network partition? */
nfsd4_mark_cb_down(clp, task->tk_status);
+ break;
+ default:
+ BUG();
}
- if (dp->dl_retries--) {
- rpc_delay(task, 2*HZ);
- task->tk_status = 0;
- rpc_restart_call_prepare(task);
- return;
- }
- nfsd4_mark_cb_down(clp, task->tk_status);
cb->cb_done = true;
}
-static void nfsd4_cb_recall_release(void *calldata)
+static void nfsd4_cb_release(void *calldata)
{
struct nfsd4_callback *cb = calldata;
struct nfs4_client *clp = cb->cb_clp;
- struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
if (cb->cb_done) {
spin_lock(&clp->cl_lock);
list_del(&cb->cb_per_client);
spin_unlock(&clp->cl_lock);
- nfs4_put_stid(&dp->dl_stid);
+
+ cb->cb_ops->release(cb);
}
}
-static const struct rpc_call_ops nfsd4_cb_recall_ops = {
+static const struct rpc_call_ops nfsd4_cb_ops = {
.rpc_call_prepare = nfsd4_cb_prepare,
- .rpc_call_done = nfsd4_cb_recall_done,
- .rpc_release = nfsd4_cb_recall_release,
+ .rpc_call_done = nfsd4_cb_done,
+ .rpc_release = nfsd4_cb_release,
};
int nfsd4_create_callback_queue(void)
@@ -937,16 +891,10 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
* instead, nfsd4_run_cb_null() will detect the killed
* client, destroy the rpc client, and stop:
*/
- do_probe_callback(clp);
+ nfsd4_run_cb(&clp->cl_cb_null);
flush_workqueue(callback_wq);
}
-static void nfsd4_release_cb(struct nfsd4_callback *cb)
-{
- if (cb->cb_ops->rpc_release)
- cb->cb_ops->rpc_release(cb);
-}
-
/* requires cl_lock: */
static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
{
@@ -1009,63 +957,49 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
}
/* Yay, the callback channel's back! Restart any callbacks: */
list_for_each_entry(cb, &clp->cl_callbacks, cb_per_client)
- run_nfsd4_cb(cb);
+ queue_work(callback_wq, &cb->cb_work);
}
static void
-nfsd4_run_callback_rpc(struct nfsd4_callback *cb)
+nfsd4_run_cb_work(struct work_struct *work)
{
+ struct nfsd4_callback *cb =
+ container_of(work, struct nfsd4_callback, cb_work);
struct nfs4_client *clp = cb->cb_clp;
struct rpc_clnt *clnt;
+ if (cb->cb_ops && cb->cb_ops->prepare)
+ cb->cb_ops->prepare(cb);
+
if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)
nfsd4_process_cb_update(cb);
clnt = clp->cl_cb_client;
if (!clnt) {
/* Callback channel broken, or client killed; give up: */
- nfsd4_release_cb(cb);
+ if (cb->cb_ops && cb->cb_ops->release)
+ cb->cb_ops->release(cb);
return;
}
cb->cb_msg.rpc_cred = clp->cl_cb_cred;
rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
- cb->cb_ops, cb);
+ cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb);
}
-void
-nfsd4_run_cb_null(struct work_struct *w)
+void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
+ struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op)
{
- struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
- cb_work);
- nfsd4_run_callback_rpc(cb);
-}
-
-void
-nfsd4_run_cb_recall(struct work_struct *w)
-{
- struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
- cb_work);
-
- nfsd4_prepare_cb_recall(cb->cb_op);
- nfsd4_run_callback_rpc(cb);
-}
-
-void nfsd4_cb_recall(struct nfs4_delegation *dp)
-{
- struct nfsd4_callback *cb = &dp->dl_recall;
- struct nfs4_client *clp = dp->dl_stid.sc_client;
-
- dp->dl_retries = 1;
- cb->cb_op = dp;
cb->cb_clp = clp;
- cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL];
+ cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op];
cb->cb_msg.rpc_argp = cb;
cb->cb_msg.rpc_resp = cb;
-
- cb->cb_ops = &nfsd4_cb_recall_ops;
-
+ cb->cb_ops = ops;
+ INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
INIT_LIST_HEAD(&cb->cb_per_client);
cb->cb_done = true;
+}
- run_nfsd4_cb(&dp->dl_recall);
+void nfsd4_run_cb(struct nfsd4_callback *cb)
+{
+ queue_work(callback_wq, &cb->cb_work);
}
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index a0ab0a847d69..e1b3d3d472da 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -215,7 +215,8 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
memset(&ent, 0, sizeof(ent));
/* Authentication name */
- if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+ len = qword_get(&buf, buf1, PAGE_SIZE);
+ if (len <= 0 || len >= IDMAP_NAMESZ)
goto out;
memcpy(ent.authname, buf1, sizeof(ent.authname));
@@ -245,12 +246,10 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
/* Name */
error = -EINVAL;
len = qword_get(&buf, buf1, PAGE_SIZE);
- if (len < 0)
+ if (len < 0 || len >= IDMAP_NAMESZ)
goto out;
if (len == 0)
set_bit(CACHE_NEGATIVE, &ent.h.flags);
- else if (len >= IDMAP_NAMESZ)
- goto out;
else
memcpy(ent.name, buf1, sizeof(ent.name));
error = -ENOMEM;
@@ -259,15 +258,12 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
goto out;
cache_put(&res->h, cd);
-
error = 0;
out:
kfree(buf1);
-
return error;
}
-
static struct ent *
idtoname_lookup(struct cache_detail *cd, struct ent *item)
{
@@ -368,7 +364,7 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
{
struct ent ent, *res;
char *buf1;
- int error = -EINVAL;
+ int len, error = -EINVAL;
if (buf[buflen - 1] != '\n')
return (-EINVAL);
@@ -381,7 +377,8 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
memset(&ent, 0, sizeof(ent));
/* Authentication name */
- if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+ len = qword_get(&buf, buf1, PAGE_SIZE);
+ if (len <= 0 || len >= IDMAP_NAMESZ)
goto out;
memcpy(ent.authname, buf1, sizeof(ent.authname));
@@ -392,8 +389,8 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
/* Name */
- error = qword_get(&buf, buf1, PAGE_SIZE);
- if (error <= 0 || error >= IDMAP_NAMESZ)
+ len = qword_get(&buf, buf1, PAGE_SIZE);
+ if (len <= 0 || len >= IDMAP_NAMESZ)
goto out;
memcpy(ent.name, buf1, sizeof(ent.name));
@@ -421,7 +418,6 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
error = 0;
out:
kfree(buf1);
-
return (error);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 5e0dc528a0e8..cdeb3cfd6f32 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1013,6 +1013,49 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return status;
}
+static __be32
+nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+ struct nfsd4_seek *seek)
+{
+ int whence;
+ __be32 status;
+ struct file *file;
+
+ status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
+ &seek->seek_stateid,
+ RD_STATE, &file);
+ if (status) {
+ dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
+ return status;
+ }
+
+ switch (seek->seek_whence) {
+ case NFS4_CONTENT_DATA:
+ whence = SEEK_DATA;
+ break;
+ case NFS4_CONTENT_HOLE:
+ whence = SEEK_HOLE;
+ break;
+ default:
+ status = nfserr_union_notsupp;
+ goto out;
+ }
+
+ /*
+ * Note: This call does change file->f_pos, but nothing in NFSD
+ * should ever file->f_pos.
+ */
+ seek->seek_pos = vfs_llseek(file, seek->seek_offset, whence);
+ if (seek->seek_pos < 0)
+ status = nfserrno(seek->seek_pos);
+ else if (seek->seek_pos >= i_size_read(file_inode(file)))
+ seek->seek_eof = true;
+
+out:
+ fput(file);
+ return status;
+}
+
/* This routine never returns NFS_OK! If there are no other errors, it
* will return NFSERR_SAME or NFSERR_NOT_SAME depending on whether the
* attributes matched. VERIFY is implemented by mapping NFSERR_SAME
@@ -1881,6 +1924,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
+
+ /* NFSv4.2 operations */
+ [OP_SEEK] = {
+ .op_func = (nfsd4op_func)nfsd4_seek,
+ .op_name = "OP_SEEK",
+ },
};
int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 9c271f42604a..ea95a2bc21b5 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -58,7 +58,7 @@ struct nfsd4_client_tracking_ops {
void (*create)(struct nfs4_client *);
void (*remove)(struct nfs4_client *);
int (*check)(struct nfs4_client *);
- void (*grace_done)(struct nfsd_net *, time_t);
+ void (*grace_done)(struct nfsd_net *);
};
/* Globals */
@@ -188,7 +188,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
status = mnt_want_write_file(nn->rec_file);
if (status)
- return;
+ goto out_creds;
dir = nn->rec_file->f_path.dentry;
/* lock the parent */
@@ -228,6 +228,7 @@ out_unlock:
user_recovery_dirname);
}
mnt_drop_write_file(nn->rec_file);
+out_creds:
nfs4_reset_creds(original_cred);
}
@@ -392,7 +393,7 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
}
static void
-nfsd4_recdir_purge_old(struct nfsd_net *nn, time_t boot_time)
+nfsd4_recdir_purge_old(struct nfsd_net *nn)
{
int status;
@@ -479,6 +480,16 @@ nfsd4_init_recdir(struct net *net)
return status;
}
+static void
+nfsd4_shutdown_recdir(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ if (!nn->rec_file)
+ return;
+ fput(nn->rec_file);
+ nn->rec_file = NULL;
+}
static int
nfs4_legacy_state_init(struct net *net)
@@ -512,10 +523,13 @@ nfsd4_load_reboot_recovery_data(struct net *net)
int status;
status = nfsd4_init_recdir(net);
- if (!status)
- status = nfsd4_recdir_load(net);
if (status)
- printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
+ return status;
+
+ status = nfsd4_recdir_load(net);
+ if (status)
+ nfsd4_shutdown_recdir(net);
+
return status;
}
@@ -546,21 +560,12 @@ err:
}
static void
-nfsd4_shutdown_recdir(struct nfsd_net *nn)
-{
- if (!nn->rec_file)
- return;
- fput(nn->rec_file);
- nn->rec_file = NULL;
-}
-
-static void
nfsd4_legacy_tracking_exit(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
nfs4_release_reclaim(nn);
- nfsd4_shutdown_recdir(nn);
+ nfsd4_shutdown_recdir(net);
nfs4_legacy_state_shutdown(net);
}
@@ -1016,7 +1021,7 @@ nfsd4_cld_check(struct nfs4_client *clp)
}
static void
-nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time)
+nfsd4_cld_grace_done(struct nfsd_net *nn)
{
int ret;
struct cld_upcall *cup;
@@ -1029,7 +1034,7 @@ nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time)
}
cup->cu_msg.cm_cmd = Cld_GraceDone;
- cup->cu_msg.cm_u.cm_gracetime = (int64_t)boot_time;
+ cup->cu_msg.cm_u.cm_gracetime = (int64_t)nn->boot_time;
ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
if (!ret)
ret = cup->cu_msg.cm_status;
@@ -1062,6 +1067,8 @@ MODULE_PARM_DESC(cltrack_legacy_disable,
#define LEGACY_TOPDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_TOPDIR="
#define LEGACY_RECDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_RECDIR="
+#define HAS_SESSION_ENV_PREFIX "NFSDCLTRACK_CLIENT_HAS_SESSION="
+#define GRACE_START_ENV_PREFIX "NFSDCLTRACK_GRACE_START="
static char *
nfsd4_cltrack_legacy_topdir(void)
@@ -1126,10 +1133,60 @@ nfsd4_cltrack_legacy_recdir(const struct xdr_netobj *name)
return result;
}
+static char *
+nfsd4_cltrack_client_has_session(struct nfs4_client *clp)
+{
+ int copied;
+ size_t len;
+ char *result;
+
+ /* prefix + Y/N character + terminating NULL */
+ len = strlen(HAS_SESSION_ENV_PREFIX) + 1 + 1;
+
+ result = kmalloc(len, GFP_KERNEL);
+ if (!result)
+ return result;
+
+ copied = snprintf(result, len, HAS_SESSION_ENV_PREFIX "%c",
+ clp->cl_minorversion ? 'Y' : 'N');
+ if (copied >= len) {
+ /* just return nothing if output was truncated */
+ kfree(result);
+ return NULL;
+ }
+
+ return result;
+}
+
+static char *
+nfsd4_cltrack_grace_start(time_t grace_start)
+{
+ int copied;
+ size_t len;
+ char *result;
+
+ /* prefix + max width of int64_t string + terminating NULL */
+ len = strlen(GRACE_START_ENV_PREFIX) + 22 + 1;
+
+ result = kmalloc(len, GFP_KERNEL);
+ if (!result)
+ return result;
+
+ copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%ld",
+ grace_start);
+ if (copied >= len) {
+ /* just return nothing if output was truncated */
+ kfree(result);
+ return NULL;
+ }
+
+ return result;
+}
+
static int
-nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy)
+nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *env0, char *env1)
{
- char *envp[2];
+ char *envp[3];
char *argv[4];
int ret;
@@ -1140,10 +1197,12 @@ nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy)
dprintk("%s: cmd: %s\n", __func__, cmd);
dprintk("%s: arg: %s\n", __func__, arg ? arg : "(null)");
- dprintk("%s: legacy: %s\n", __func__, legacy ? legacy : "(null)");
+ dprintk("%s: env0: %s\n", __func__, env0 ? env0 : "(null)");
+ dprintk("%s: env1: %s\n", __func__, env1 ? env1 : "(null)");
- envp[0] = legacy;
- envp[1] = NULL;
+ envp[0] = env0;
+ envp[1] = env1;
+ envp[2] = NULL;
argv[0] = (char *)cltrack_prog;
argv[1] = cmd;
@@ -1187,28 +1246,78 @@ bin_to_hex_dup(const unsigned char *src, int srclen)
}
static int
-nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net)
+nfsd4_umh_cltrack_init(struct net *net)
{
+ int ret;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ char *grace_start = nfsd4_cltrack_grace_start(nn->boot_time);
+
/* XXX: The usermode helper s not working in container yet. */
if (net != &init_net) {
WARN(1, KERN_ERR "NFSD: attempt to initialize umh client "
"tracking in a container!\n");
return -EINVAL;
}
- return nfsd4_umh_cltrack_upcall("init", NULL, NULL);
+
+ ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL);
+ kfree(grace_start);
+ return ret;
+}
+
+static void
+nfsd4_cltrack_upcall_lock(struct nfs4_client *clp)
+{
+ wait_on_bit_lock(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK,
+ TASK_UNINTERRUPTIBLE);
+}
+
+static void
+nfsd4_cltrack_upcall_unlock(struct nfs4_client *clp)
+{
+ smp_mb__before_atomic();
+ clear_bit(NFSD4_CLIENT_UPCALL_LOCK, &clp->cl_flags);
+ smp_mb__after_atomic();
+ wake_up_bit(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK);
}
static void
nfsd4_umh_cltrack_create(struct nfs4_client *clp)
{
- char *hexid;
+ char *hexid, *has_session, *grace_start;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ /*
+ * With v4.0 clients, there's little difference in outcome between a
+ * create and check operation, and we can end up calling into this
+ * function multiple times per client (once for each openowner). So,
+ * for v4.0 clients skip upcalling once the client has been recorded
+ * on stable storage.
+ *
+ * For v4.1+ clients, the outcome of the two operations is different,
+ * so we must ensure that we upcall for the create operation. v4.1+
+ * clients call this on RECLAIM_COMPLETE though, so we should only end
+ * up doing a single create upcall per client.
+ */
+ if (clp->cl_minorversion == 0 &&
+ test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+ return;
hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
if (!hexid) {
dprintk("%s: can't allocate memory for upcall!\n", __func__);
return;
}
- nfsd4_umh_cltrack_upcall("create", hexid, NULL);
+
+ has_session = nfsd4_cltrack_client_has_session(clp);
+ grace_start = nfsd4_cltrack_grace_start(nn->boot_time);
+
+ nfsd4_cltrack_upcall_lock(clp);
+ if (!nfsd4_umh_cltrack_upcall("create", hexid, has_session, grace_start))
+ set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+ nfsd4_cltrack_upcall_unlock(clp);
+
+ kfree(has_session);
+ kfree(grace_start);
kfree(hexid);
}
@@ -1217,12 +1326,21 @@ nfsd4_umh_cltrack_remove(struct nfs4_client *clp)
{
char *hexid;
+ if (!test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+ return;
+
hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
if (!hexid) {
dprintk("%s: can't allocate memory for upcall!\n", __func__);
return;
}
- nfsd4_umh_cltrack_upcall("remove", hexid, NULL);
+
+ nfsd4_cltrack_upcall_lock(clp);
+ if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags) &&
+ nfsd4_umh_cltrack_upcall("remove", hexid, NULL, NULL) == 0)
+ clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+ nfsd4_cltrack_upcall_unlock(clp);
+
kfree(hexid);
}
@@ -1230,30 +1348,45 @@ static int
nfsd4_umh_cltrack_check(struct nfs4_client *clp)
{
int ret;
- char *hexid, *legacy;
+ char *hexid, *has_session, *legacy;
+
+ if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+ return 0;
hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
if (!hexid) {
dprintk("%s: can't allocate memory for upcall!\n", __func__);
return -ENOMEM;
}
+
+ has_session = nfsd4_cltrack_client_has_session(clp);
legacy = nfsd4_cltrack_legacy_recdir(&clp->cl_name);
- ret = nfsd4_umh_cltrack_upcall("check", hexid, legacy);
+
+ nfsd4_cltrack_upcall_lock(clp);
+ if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) {
+ ret = 0;
+ } else {
+ ret = nfsd4_umh_cltrack_upcall("check", hexid, has_session, legacy);
+ if (ret == 0)
+ set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+ }
+ nfsd4_cltrack_upcall_unlock(clp);
+ kfree(has_session);
kfree(legacy);
kfree(hexid);
+
return ret;
}
static void
-nfsd4_umh_cltrack_grace_done(struct nfsd_net __attribute__((unused)) *nn,
- time_t boot_time)
+nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn)
{
char *legacy;
char timestr[22]; /* FIXME: better way to determine max size? */
- sprintf(timestr, "%ld", boot_time);
+ sprintf(timestr, "%ld", nn->boot_time);
legacy = nfsd4_cltrack_legacy_topdir();
- nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy);
+ nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy, NULL);
kfree(legacy);
}
@@ -1356,10 +1489,10 @@ nfsd4_client_record_check(struct nfs4_client *clp)
}
void
-nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time)
+nfsd4_record_grace_done(struct nfsd_net *nn)
{
if (nn->client_tracking_ops)
- nn->client_tracking_ops->grace_done(nn, boot_time);
+ nn->client_tracking_ops->grace_done(nn);
}
static int
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2e80a59e7e91..5c0cac173068 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -96,6 +96,8 @@ static struct kmem_cache *deleg_slab;
static void free_session(struct nfsd4_session *);
+static struct nfsd4_callback_ops nfsd4_cb_recall_ops;
+
static bool is_session_dead(struct nfsd4_session *ses)
{
return ses->se_flags & NFS4_SESSION_DEAD;
@@ -645,7 +647,9 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh)
INIT_LIST_HEAD(&dp->dl_perclnt);
INIT_LIST_HEAD(&dp->dl_recall_lru);
dp->dl_type = NFS4_OPEN_DELEGATE_READ;
- INIT_WORK(&dp->dl_recall.cb_work, nfsd4_run_cb_recall);
+ dp->dl_retries = 1;
+ nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
+ &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
return dp;
out_dec:
atomic_long_dec(&num_delegations);
@@ -673,15 +677,20 @@ nfs4_put_stid(struct nfs4_stid *s)
static void nfs4_put_deleg_lease(struct nfs4_file *fp)
{
- lockdep_assert_held(&state_lock);
+ struct file *filp = NULL;
+ struct file_lock *fl;
- if (!fp->fi_lease)
- return;
- if (atomic_dec_and_test(&fp->fi_delegees)) {
- vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
+ spin_lock(&fp->fi_lock);
+ if (fp->fi_lease && atomic_dec_and_test(&fp->fi_delegees)) {
+ swap(filp, fp->fi_deleg_file);
+ fl = fp->fi_lease;
fp->fi_lease = NULL;
- fput(fp->fi_deleg_file);
- fp->fi_deleg_file = NULL;
+ }
+ spin_unlock(&fp->fi_lock);
+
+ if (filp) {
+ vfs_setlease(filp, F_UNLCK, &fl);
+ fput(filp);
}
}
@@ -717,8 +726,6 @@ unhash_delegation_locked(struct nfs4_delegation *dp)
list_del_init(&dp->dl_recall_lru);
list_del_init(&dp->dl_perfile);
spin_unlock(&fp->fi_lock);
- if (fp)
- nfs4_put_deleg_lease(fp);
}
static void destroy_delegation(struct nfs4_delegation *dp)
@@ -726,6 +733,7 @@ static void destroy_delegation(struct nfs4_delegation *dp)
spin_lock(&state_lock);
unhash_delegation_locked(dp);
spin_unlock(&state_lock);
+ nfs4_put_deleg_lease(dp->dl_stid.sc_file);
nfs4_put_stid(&dp->dl_stid);
}
@@ -735,6 +743,8 @@ static void revoke_delegation(struct nfs4_delegation *dp)
WARN_ON(!list_empty(&dp->dl_recall_lru));
+ nfs4_put_deleg_lease(dp->dl_stid.sc_file);
+
if (clp->cl_minorversion == 0)
nfs4_put_stid(&dp->dl_stid);
else {
@@ -1635,6 +1645,7 @@ __destroy_client(struct nfs4_client *clp)
while (!list_empty(&reaplist)) {
dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
list_del_init(&dp->dl_recall_lru);
+ nfs4_put_deleg_lease(dp->dl_stid.sc_file);
nfs4_put_stid(&dp->dl_stid);
}
while (!list_empty(&clp->cl_revoked)) {
@@ -1862,7 +1873,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
free_client(clp);
return NULL;
}
- INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_run_cb_null);
+ nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL);
clp->cl_time = get_seconds();
clear_bit(0, &clp->cl_cb_slot_busy);
copy_verf(clp, verf);
@@ -3349,8 +3360,9 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
return ret;
}
-void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
+static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
{
+ struct nfs4_delegation *dp = cb_to_delegation(cb);
struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net,
nfsd_net_id);
@@ -3371,6 +3383,43 @@ void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
spin_unlock(&state_lock);
}
+static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
+ struct rpc_task *task)
+{
+ struct nfs4_delegation *dp = cb_to_delegation(cb);
+
+ switch (task->tk_status) {
+ case 0:
+ return 1;
+ case -EBADHANDLE:
+ case -NFS4ERR_BAD_STATEID:
+ /*
+ * Race: client probably got cb_recall before open reply
+ * granting delegation.
+ */
+ if (dp->dl_retries--) {
+ rpc_delay(task, 2 * HZ);
+ return 0;
+ }
+ /*FALLTHRU*/
+ default:
+ return -1;
+ }
+}
+
+static void nfsd4_cb_recall_release(struct nfsd4_callback *cb)
+{
+ struct nfs4_delegation *dp = cb_to_delegation(cb);
+
+ nfs4_put_stid(&dp->dl_stid);
+}
+
+static struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
+ .prepare = nfsd4_cb_recall_prepare,
+ .done = nfsd4_cb_recall_done,
+ .release = nfsd4_cb_recall_release,
+};
+
static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
{
/*
@@ -3381,7 +3430,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
* it's safe to take a reference.
*/
atomic_inc(&dp->dl_stid.sc_count);
- nfsd4_cb_recall(dp);
+ nfsd4_run_cb(&dp->dl_recall);
}
/* Called from break_lease() with i_lock held. */
@@ -3759,7 +3808,6 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag)
fl = locks_alloc_lock();
if (!fl)
return NULL;
- locks_init_lock(fl);
fl->fl_lmops = &nfsd_lease_mng_ops;
fl->fl_flags = FL_DELEG;
fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
@@ -4107,7 +4155,7 @@ out:
return status;
}
-static void
+void
nfsd4_end_grace(struct nfsd_net *nn)
{
/* do nothing if grace period already ended */
@@ -4116,14 +4164,28 @@ nfsd4_end_grace(struct nfsd_net *nn)
dprintk("NFSD: end of grace period\n");
nn->grace_ended = true;
- nfsd4_record_grace_done(nn, nn->boot_time);
+ /*
+ * If the server goes down again right now, an NFSv4
+ * client will still be allowed to reclaim after it comes back up,
+ * even if it hasn't yet had a chance to reclaim state this time.
+ *
+ */
+ nfsd4_record_grace_done(nn);
+ /*
+ * At this point, NFSv4 clients can still reclaim. But if the
+ * server crashes, any that have not yet reclaimed will be out
+ * of luck on the next boot.
+ *
+ * (NFSv4.1+ clients are considered to have reclaimed once they
+ * call RECLAIM_COMPLETE. NFSv4.0 clients are considered to
+ * have reclaimed after their first OPEN.)
+ */
locks_end_grace(&nn->nfsd4_manager);
/*
- * Now that every NFSv4 client has had the chance to recover and
- * to see the (possibly new, possibly shorter) lease time, we
- * can safely set the next grace time to the current lease time:
+ * At this point, and once lockd and/or any other containers
+ * exit their grace period, further reclaims will fail and
+ * regular locking can resume.
*/
- nn->nfsd4_grace = nn->nfsd4_lease;
}
static time_t
@@ -5210,7 +5272,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
}
fp = lock_stp->st_stid.sc_file;
- locks_init_lock(file_lock);
switch (lock->lk_type) {
case NFS4_READ_LT:
case NFS4_READW_LT:
@@ -5354,7 +5415,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfserr_jukebox;
goto out;
}
- locks_init_lock(file_lock);
+
switch (lockt->lt_type) {
case NFS4_READ_LT:
case NFS4_READW_LT:
@@ -5432,7 +5493,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfserr_jukebox;
goto fput;
}
- locks_init_lock(file_lock);
+
file_lock->fl_type = F_UNLCK;
file_lock->fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
file_lock->fl_pid = current->tgid;
@@ -5645,6 +5706,9 @@ nfs4_check_open_reclaim(clientid_t *clid,
if (status)
return nfserr_reclaim_bad;
+ if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags))
+ return nfserr_no_grace;
+
if (nfsd4_client_record_check(cstate->clp))
return nfserr_reclaim_bad;
@@ -6342,10 +6406,10 @@ nfs4_state_start_net(struct net *net)
ret = nfs4_state_create_net(net);
if (ret)
return ret;
- nfsd4_client_tracking_init(net);
nn->boot_time = get_seconds();
- locks_start_grace(net, &nn->nfsd4_manager);
nn->grace_ended = false;
+ locks_start_grace(net, &nn->nfsd4_manager);
+ nfsd4_client_tracking_init(net);
printk(KERN_INFO "NFSD: starting %ld-second grace period (net %p)\n",
nn->nfsd4_grace, net);
queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ);
@@ -6402,6 +6466,7 @@ nfs4_state_shutdown_net(struct net *net)
list_for_each_safe(pos, next, &reaplist) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
list_del_init(&dp->dl_recall_lru);
+ nfs4_put_deleg_lease(dp->dl_stid.sc_file);
nfs4_put_stid(&dp->dl_stid);
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index e94457c33ad6..eeea7a90eb87 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -31,13 +31,6 @@
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * TODO: Neil Brown made the following observation: We currently
- * initially reserve NFSD_BUFSIZE space on the transmit queue and
- * never release any of that until the request is complete.
- * It would be good to calculate a new maximum response size while
- * decoding the COMPOUND, and call svc_reserve with this number
- * at the end of nfs4svc_decode_compoundargs.
*/
#include <linux/slab.h>
@@ -1521,6 +1514,22 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
}
static __be32
+nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
+{
+ DECODE_HEAD;
+
+ status = nfsd4_decode_stateid(argp, &seek->seek_stateid);
+ if (status)
+ return status;
+
+ READ_BUF(8 + 4);
+ p = xdr_decode_hyper(p, &seek->seek_offset);
+ seek->seek_whence = be32_to_cpup(p);
+
+ DECODE_TAIL;
+}
+
+static __be32
nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p)
{
return nfs_ok;
@@ -1593,6 +1602,20 @@ static nfsd4_dec nfsd4_dec_ops[] = {
[OP_WANT_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp,
[OP_DESTROY_CLIENTID] = (nfsd4_dec)nfsd4_decode_destroy_clientid,
[OP_RECLAIM_COMPLETE] = (nfsd4_dec)nfsd4_decode_reclaim_complete,
+
+ /* new operations for NFSv4.2 */
+ [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_COPY] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_LAYOUTSTATS] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_OFFLOAD_CANCEL] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_OFFLOAD_STATUS] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_READ_PLUS] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek,
+ [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp,
};
static inline bool
@@ -1670,6 +1693,14 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
readbytes += nfsd4_max_reply(argp->rqstp, op);
} else
max_reply += nfsd4_max_reply(argp->rqstp, op);
+ /*
+ * OP_LOCK may return a conflicting lock. (Special case
+ * because it will just skip encoding this if it runs
+ * out of xdr buffer space, and it is the only operation
+ * that behaves this way.)
+ */
+ if (op->opnum == OP_LOCK)
+ max_reply += NFS4_OPAQUE_LIMIT;
if (op->status) {
argp->opcnt = i+1;
@@ -3104,7 +3135,8 @@ static __be32 nfsd4_encode_splice_read(
buf->page_len = maxcount;
buf->len += maxcount;
- xdr->page_ptr += (maxcount + PAGE_SIZE - 1) / PAGE_SIZE;
+ xdr->page_ptr += (buf->page_base + maxcount + PAGE_SIZE - 1)
+ / PAGE_SIZE;
/* Use rest of head for padding and remaining ops: */
buf->tail[0].iov_base = xdr->p;
@@ -3763,6 +3795,22 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
}
static __be32
+nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
+ struct nfsd4_seek *seek)
+{
+ __be32 *p;
+
+ if (nfserr)
+ return nfserr;
+
+ p = xdr_reserve_space(&resp->xdr, 4 + 8);
+ *p++ = cpu_to_be32(seek->seek_eof);
+ p = xdr_encode_hyper(p, seek->seek_pos);
+
+ return nfserr;
+}
+
+static __be32
nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p)
{
return nfserr;
@@ -3834,6 +3882,20 @@ static nfsd4_enc nfsd4_enc_ops[] = {
[OP_WANT_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop,
[OP_DESTROY_CLIENTID] = (nfsd4_enc)nfsd4_encode_noop,
[OP_RECLAIM_COMPLETE] = (nfsd4_enc)nfsd4_encode_noop,
+
+ /* NFSv4.2 operations */
+ [OP_ALLOCATE] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_COPY] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_DEALLOCATE] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_IO_ADVISE] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_LAYOUTERROR] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_LAYOUTSTATS] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_OFFLOAD_CANCEL] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_OFFLOAD_STATUS] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_READ_PLUS] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek,
+ [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop,
};
/*
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index ff9567633245..122f69185ef5 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -27,8 +27,12 @@
*/
#define TARGET_BUCKET_SIZE 64
-static struct hlist_head * cache_hash;
-static struct list_head lru_head;
+struct nfsd_drc_bucket {
+ struct list_head lru_head;
+ spinlock_t cache_lock;
+};
+
+static struct nfsd_drc_bucket *drc_hashtbl;
static struct kmem_cache *drc_slab;
/* max number of entries allowed in the cache */
@@ -36,6 +40,7 @@ static unsigned int max_drc_entries;
/* number of significant bits in the hash value */
static unsigned int maskbits;
+static unsigned int drc_hashsize;
/*
* Stats and other tracking of on the duplicate reply cache. All of these and
@@ -43,7 +48,7 @@ static unsigned int maskbits;
*/
/* total number of entries */
-static unsigned int num_drc_entries;
+static atomic_t num_drc_entries;
/* cache misses due only to checksum comparison failures */
static unsigned int payload_misses;
@@ -75,7 +80,6 @@ static struct shrinker nfsd_reply_cache_shrinker = {
* A cache entry is "single use" if c_state == RC_INPROG
* Otherwise, it when accessing _prev or _next, the lock must be held.
*/
-static DEFINE_SPINLOCK(cache_lock);
static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
/*
@@ -116,6 +120,12 @@ nfsd_hashsize(unsigned int limit)
return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE);
}
+static u32
+nfsd_cache_hash(__be32 xid)
+{
+ return hash_32(be32_to_cpu(xid), maskbits);
+}
+
static struct svc_cacherep *
nfsd_reply_cache_alloc(void)
{
@@ -126,7 +136,6 @@ nfsd_reply_cache_alloc(void)
rp->c_state = RC_UNUSED;
rp->c_type = RC_NOCACHE;
INIT_LIST_HEAD(&rp->c_lru);
- INIT_HLIST_NODE(&rp->c_hash);
}
return rp;
}
@@ -138,29 +147,27 @@ nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
drc_mem_usage -= rp->c_replvec.iov_len;
kfree(rp->c_replvec.iov_base);
}
- if (!hlist_unhashed(&rp->c_hash))
- hlist_del(&rp->c_hash);
list_del(&rp->c_lru);
- --num_drc_entries;
+ atomic_dec(&num_drc_entries);
drc_mem_usage -= sizeof(*rp);
kmem_cache_free(drc_slab, rp);
}
static void
-nfsd_reply_cache_free(struct svc_cacherep *rp)
+nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
{
- spin_lock(&cache_lock);
+ spin_lock(&b->cache_lock);
nfsd_reply_cache_free_locked(rp);
- spin_unlock(&cache_lock);
+ spin_unlock(&b->cache_lock);
}
int nfsd_reply_cache_init(void)
{
unsigned int hashsize;
+ unsigned int i;
- INIT_LIST_HEAD(&lru_head);
max_drc_entries = nfsd_cache_size_limit();
- num_drc_entries = 0;
+ atomic_set(&num_drc_entries, 0);
hashsize = nfsd_hashsize(max_drc_entries);
maskbits = ilog2(hashsize);
@@ -170,9 +177,14 @@ int nfsd_reply_cache_init(void)
if (!drc_slab)
goto out_nomem;
- cache_hash = kcalloc(hashsize, sizeof(struct hlist_head), GFP_KERNEL);
- if (!cache_hash)
+ drc_hashtbl = kcalloc(hashsize, sizeof(*drc_hashtbl), GFP_KERNEL);
+ if (!drc_hashtbl)
goto out_nomem;
+ for (i = 0; i < hashsize; i++) {
+ INIT_LIST_HEAD(&drc_hashtbl[i].lru_head);
+ spin_lock_init(&drc_hashtbl[i].cache_lock);
+ }
+ drc_hashsize = hashsize;
return 0;
out_nomem:
@@ -184,17 +196,22 @@ out_nomem:
void nfsd_reply_cache_shutdown(void)
{
struct svc_cacherep *rp;
+ unsigned int i;
unregister_shrinker(&nfsd_reply_cache_shrinker);
cancel_delayed_work_sync(&cache_cleaner);
- while (!list_empty(&lru_head)) {
- rp = list_entry(lru_head.next, struct svc_cacherep, c_lru);
- nfsd_reply_cache_free_locked(rp);
+ for (i = 0; i < drc_hashsize; i++) {
+ struct list_head *head = &drc_hashtbl[i].lru_head;
+ while (!list_empty(head)) {
+ rp = list_first_entry(head, struct svc_cacherep, c_lru);
+ nfsd_reply_cache_free_locked(rp);
+ }
}
- kfree (cache_hash);
- cache_hash = NULL;
+ kfree (drc_hashtbl);
+ drc_hashtbl = NULL;
+ drc_hashsize = 0;
if (drc_slab) {
kmem_cache_destroy(drc_slab);
@@ -207,61 +224,63 @@ void nfsd_reply_cache_shutdown(void)
* not already scheduled.
*/
static void
-lru_put_end(struct svc_cacherep *rp)
+lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
{
rp->c_timestamp = jiffies;
- list_move_tail(&rp->c_lru, &lru_head);
+ list_move_tail(&rp->c_lru, &b->lru_head);
schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
}
-/*
- * Move a cache entry from one hash list to another
- */
-static void
-hash_refile(struct svc_cacherep *rp)
-{
- hlist_del_init(&rp->c_hash);
- /*
- * No point in byte swapping c_xid since we're just using it to pick
- * a hash bucket.
- */
- hlist_add_head(&rp->c_hash, cache_hash +
- hash_32((__force u32)rp->c_xid, maskbits));
-}
-
-/*
- * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
- * Also prune the oldest ones when the total exceeds the max number of entries.
- */
static long
-prune_cache_entries(void)
+prune_bucket(struct nfsd_drc_bucket *b)
{
struct svc_cacherep *rp, *tmp;
long freed = 0;
- list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
+ list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) {
/*
* Don't free entries attached to calls that are still
* in-progress, but do keep scanning the list.
*/
if (rp->c_state == RC_INPROG)
continue;
- if (num_drc_entries <= max_drc_entries &&
+ if (atomic_read(&num_drc_entries) <= max_drc_entries &&
time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
break;
nfsd_reply_cache_free_locked(rp);
freed++;
}
+ return freed;
+}
+
+/*
+ * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
+ * Also prune the oldest ones when the total exceeds the max number of entries.
+ */
+static long
+prune_cache_entries(void)
+{
+ unsigned int i;
+ long freed = 0;
+ bool cancel = true;
+
+ for (i = 0; i < drc_hashsize; i++) {
+ struct nfsd_drc_bucket *b = &drc_hashtbl[i];
+
+ if (list_empty(&b->lru_head))
+ continue;
+ spin_lock(&b->cache_lock);
+ freed += prune_bucket(b);
+ if (!list_empty(&b->lru_head))
+ cancel = false;
+ spin_unlock(&b->cache_lock);
+ }
/*
- * Conditionally rearm the job. If we cleaned out the list, then
- * cancel any pending run (since there won't be any work to do).
- * Otherwise, we rearm the job or modify the existing one to run in
- * RC_EXPIRE since we just ran the pruner.
+ * Conditionally rearm the job to run in RC_EXPIRE since we just
+ * ran the pruner.
*/
- if (list_empty(&lru_head))
- cancel_delayed_work(&cache_cleaner);
- else
+ if (!cancel)
mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
return freed;
}
@@ -269,32 +288,19 @@ prune_cache_entries(void)
static void
cache_cleaner_func(struct work_struct *unused)
{
- spin_lock(&cache_lock);
prune_cache_entries();
- spin_unlock(&cache_lock);
}
static unsigned long
nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
{
- unsigned long num;
-
- spin_lock(&cache_lock);
- num = num_drc_entries;
- spin_unlock(&cache_lock);
-
- return num;
+ return atomic_read(&num_drc_entries);
}
static unsigned long
nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
{
- unsigned long freed;
-
- spin_lock(&cache_lock);
- freed = prune_cache_entries();
- spin_unlock(&cache_lock);
- return freed;
+ return prune_cache_entries();
}
/*
* Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
@@ -332,20 +338,24 @@ nfsd_cache_csum(struct svc_rqst *rqstp)
static bool
nfsd_cache_match(struct svc_rqst *rqstp, __wsum csum, struct svc_cacherep *rp)
{
- /* Check RPC header info first */
- if (rqstp->rq_xid != rp->c_xid || rqstp->rq_proc != rp->c_proc ||
- rqstp->rq_prot != rp->c_prot || rqstp->rq_vers != rp->c_vers ||
- rqstp->rq_arg.len != rp->c_len ||
- !rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) ||
- rpc_get_port(svc_addr(rqstp)) != rpc_get_port((struct sockaddr *)&rp->c_addr))
+ /* Check RPC XID first */
+ if (rqstp->rq_xid != rp->c_xid)
return false;
-
/* compare checksum of NFS data */
if (csum != rp->c_csum) {
++payload_misses;
return false;
}
+ /* Other discriminators */
+ if (rqstp->rq_proc != rp->c_proc ||
+ rqstp->rq_prot != rp->c_prot ||
+ rqstp->rq_vers != rp->c_vers ||
+ rqstp->rq_arg.len != rp->c_len ||
+ !rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) ||
+ rpc_get_port(svc_addr(rqstp)) != rpc_get_port((struct sockaddr *)&rp->c_addr))
+ return false;
+
return true;
}
@@ -355,18 +365,14 @@ nfsd_cache_match(struct svc_rqst *rqstp, __wsum csum, struct svc_cacherep *rp)
* NULL on failure.
*/
static struct svc_cacherep *
-nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
+nfsd_cache_search(struct nfsd_drc_bucket *b, struct svc_rqst *rqstp,
+ __wsum csum)
{
struct svc_cacherep *rp, *ret = NULL;
- struct hlist_head *rh;
+ struct list_head *rh = &b->lru_head;
unsigned int entries = 0;
- /*
- * No point in byte swapping rq_xid since we're just using it to pick
- * a hash bucket.
- */
- rh = &cache_hash[hash_32((__force u32)rqstp->rq_xid, maskbits)];
- hlist_for_each_entry(rp, rh, c_hash) {
+ list_for_each_entry(rp, rh, c_lru) {
++entries;
if (nfsd_cache_match(rqstp, csum, rp)) {
ret = rp;
@@ -377,11 +383,12 @@ nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
/* tally hash chain length stats */
if (entries > longest_chain) {
longest_chain = entries;
- longest_chain_cachesize = num_drc_entries;
+ longest_chain_cachesize = atomic_read(&num_drc_entries);
} else if (entries == longest_chain) {
/* prefer to keep the smallest cachesize possible here */
- longest_chain_cachesize = min(longest_chain_cachesize,
- num_drc_entries);
+ longest_chain_cachesize = min_t(unsigned int,
+ longest_chain_cachesize,
+ atomic_read(&num_drc_entries));
}
return ret;
@@ -403,6 +410,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
vers = rqstp->rq_vers,
proc = rqstp->rq_proc;
__wsum csum;
+ u32 hash = nfsd_cache_hash(xid);
+ struct nfsd_drc_bucket *b = &drc_hashtbl[hash];
unsigned long age;
int type = rqstp->rq_cachetype;
int rtn = RC_DOIT;
@@ -420,16 +429,16 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
* preallocate an entry.
*/
rp = nfsd_reply_cache_alloc();
- spin_lock(&cache_lock);
+ spin_lock(&b->cache_lock);
if (likely(rp)) {
- ++num_drc_entries;
+ atomic_inc(&num_drc_entries);
drc_mem_usage += sizeof(*rp);
}
/* go ahead and prune the cache */
- prune_cache_entries();
+ prune_bucket(b);
- found = nfsd_cache_search(rqstp, csum);
+ found = nfsd_cache_search(b, rqstp, csum);
if (found) {
if (likely(rp))
nfsd_reply_cache_free_locked(rp);
@@ -454,8 +463,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
rp->c_len = rqstp->rq_arg.len;
rp->c_csum = csum;
- hash_refile(rp);
- lru_put_end(rp);
+ lru_put_end(b, rp);
/* release any buffer */
if (rp->c_type == RC_REPLBUFF) {
@@ -465,14 +473,14 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
}
rp->c_type = RC_NOCACHE;
out:
- spin_unlock(&cache_lock);
+ spin_unlock(&b->cache_lock);
return rtn;
found_entry:
nfsdstats.rchits++;
/* We found a matching entry which is either in progress or done. */
age = jiffies - rp->c_timestamp;
- lru_put_end(rp);
+ lru_put_end(b, rp);
rtn = RC_DROPIT;
/* Request being processed or excessive rexmits */
@@ -527,18 +535,23 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
{
struct svc_cacherep *rp = rqstp->rq_cacherep;
struct kvec *resv = &rqstp->rq_res.head[0], *cachv;
+ u32 hash;
+ struct nfsd_drc_bucket *b;
int len;
size_t bufsize = 0;
if (!rp)
return;
+ hash = nfsd_cache_hash(rp->c_xid);
+ b = &drc_hashtbl[hash];
+
len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
len >>= 2;
/* Don't cache excessive amounts of data and XDR failures */
if (!statp || len > (256 >> 2)) {
- nfsd_reply_cache_free(rp);
+ nfsd_reply_cache_free(b, rp);
return;
}
@@ -553,23 +566,23 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
bufsize = len << 2;
cachv->iov_base = kmalloc(bufsize, GFP_KERNEL);
if (!cachv->iov_base) {
- nfsd_reply_cache_free(rp);
+ nfsd_reply_cache_free(b, rp);
return;
}
cachv->iov_len = bufsize;
memcpy(cachv->iov_base, statp, bufsize);
break;
case RC_NOCACHE:
- nfsd_reply_cache_free(rp);
+ nfsd_reply_cache_free(b, rp);
return;
}
- spin_lock(&cache_lock);
+ spin_lock(&b->cache_lock);
drc_mem_usage += bufsize;
- lru_put_end(rp);
+ lru_put_end(b, rp);
rp->c_secure = rqstp->rq_secure;
rp->c_type = cachetype;
rp->c_state = RC_DONE;
- spin_unlock(&cache_lock);
+ spin_unlock(&b->cache_lock);
return;
}
@@ -600,9 +613,9 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
*/
static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
{
- spin_lock(&cache_lock);
seq_printf(m, "max entries: %u\n", max_drc_entries);
- seq_printf(m, "num entries: %u\n", num_drc_entries);
+ seq_printf(m, "num entries: %u\n",
+ atomic_read(&num_drc_entries));
seq_printf(m, "hash buckets: %u\n", 1 << maskbits);
seq_printf(m, "mem usage: %u\n", drc_mem_usage);
seq_printf(m, "cache hits: %u\n", nfsdstats.rchits);
@@ -611,7 +624,6 @@ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
seq_printf(m, "payload misses: %u\n", payload_misses);
seq_printf(m, "longest chain len: %u\n", longest_chain);
seq_printf(m, "cachesize at longest: %u\n", longest_chain_cachesize);
- spin_unlock(&cache_lock);
return 0;
}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 4e042105fb6e..ca73ca79a0ee 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -49,6 +49,7 @@ enum {
NFSD_Leasetime,
NFSD_Gracetime,
NFSD_RecoveryDir,
+ NFSD_V4EndGrace,
#endif
};
@@ -68,6 +69,7 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size);
static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
+static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size);
#endif
static ssize_t (*write_op[])(struct file *, char *, size_t) = {
@@ -84,6 +86,7 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = {
[NFSD_Leasetime] = write_leasetime,
[NFSD_Gracetime] = write_gracetime,
[NFSD_RecoveryDir] = write_recoverydir,
+ [NFSD_V4EndGrace] = write_v4_end_grace,
#endif
};
@@ -1077,6 +1080,47 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
return rv;
}
+/**
+ * write_v4_end_grace - release grace period for nfsd's v4.x lock manager
+ *
+ * Input:
+ * buf: ignored
+ * size: zero
+ * OR
+ *
+ * Input:
+ * buf: any value
+ * size: non-zero length of C string in @buf
+ * Output:
+ * passed-in buffer filled with "Y" or "N" with a newline
+ * and NULL-terminated C string. This indicates whether
+ * the grace period has ended in the current net
+ * namespace. Return code is the size in bytes of the
+ * string. Writing a string that starts with 'Y', 'y', or
+ * '1' to the file will end the grace period for nfsd's v4
+ * lock manager.
+ */
+static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size)
+{
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ if (size > 0) {
+ switch(buf[0]) {
+ case 'Y':
+ case 'y':
+ case '1':
+ nfsd4_end_grace(nn);
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%c\n",
+ nn->grace_ended ? 'Y' : 'N');
+}
+
#endif
/*----------------------------------------------------------------------------*/
@@ -1110,6 +1154,7 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
[NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR},
[NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR},
+ [NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO},
#endif
/* last one */ {""}
};
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 847daf37e566..747f3b95bd11 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -251,7 +251,7 @@ void nfsd_lockd_shutdown(void);
#define nfserr_deleg_revoked cpu_to_be32(NFS4ERR_DELEG_REVOKED)
#define nfserr_partner_notsupp cpu_to_be32(NFS4ERR_PARTNER_NOTSUPP)
#define nfserr_partner_no_auth cpu_to_be32(NFS4ERR_PARTNER_NO_AUTH)
-#define nfserr_metadata_notsupp cpu_to_be32(NFS4ERR_METADATA_NOTSUPP)
+#define nfserr_union_notsupp cpu_to_be32(NFS4ERR_UNION_NOTSUPP)
#define nfserr_offload_denied cpu_to_be32(NFS4ERR_OFFLOAD_DENIED)
#define nfserr_wrong_lfs cpu_to_be32(NFS4ERR_WRONG_LFS)
#define nfserr_badlabel cpu_to_be32(NFS4ERR_BADLABEL)
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index e883a5868be6..88026fc6a981 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -209,8 +209,10 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
* fix that case easily.
*/
struct cred *new = prepare_creds();
- if (!new)
- return nfserrno(-ENOMEM);
+ if (!new) {
+ error = nfserrno(-ENOMEM);
+ goto out;
+ }
new->cap_effective =
cap_raise_nfsd_set(new->cap_effective,
new->cap_permitted);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 4a89e00d7461..0a47c6a6b301 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -62,16 +62,21 @@ typedef struct {
(s)->si_generation
struct nfsd4_callback {
- void *cb_op;
struct nfs4_client *cb_clp;
struct list_head cb_per_client;
u32 cb_minorversion;
struct rpc_message cb_msg;
- const struct rpc_call_ops *cb_ops;
+ struct nfsd4_callback_ops *cb_ops;
struct work_struct cb_work;
bool cb_done;
};
+struct nfsd4_callback_ops {
+ void (*prepare)(struct nfsd4_callback *);
+ int (*done)(struct nfsd4_callback *, struct rpc_task *);
+ void (*release)(struct nfsd4_callback *);
+};
+
/*
* A core object that represents a "common" stateid. These are generally
* embedded within the different (more specific) stateid objects and contain
@@ -127,6 +132,9 @@ struct nfs4_delegation {
struct nfsd4_callback dl_recall;
};
+#define cb_to_delegation(cb) \
+ container_of(cb, struct nfs4_delegation, dl_recall)
+
/* client delegation callback info */
struct nfs4_cb_conn {
/* SETCLIENTID info */
@@ -306,6 +314,7 @@ struct nfs4_client {
#define NFSD4_CLIENT_STABLE (2) /* client on stable storage */
#define NFSD4_CLIENT_RECLAIM_COMPLETE (3) /* reclaim_complete done */
#define NFSD4_CLIENT_CONFIRMED (4) /* client is confirmed */
+#define NFSD4_CLIENT_UPCALL_LOCK (5) /* upcall serialization */
#define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \
1 << NFSD4_CLIENT_CB_KILL)
unsigned long cl_flags;
@@ -517,6 +526,13 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
#define RD_STATE 0x00000010
#define WR_STATE 0x00000020
+enum nfsd4_cb_op {
+ NFSPROC4_CLNT_CB_NULL = 0,
+ NFSPROC4_CLNT_CB_RECALL,
+ NFSPROC4_CLNT_CB_SEQUENCE,
+};
+
+
struct nfsd4_compound_state;
struct nfsd_net;
@@ -531,12 +547,12 @@ extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
extern __be32 nfs4_check_open_reclaim(clientid_t *clid,
struct nfsd4_compound_state *cstate, struct nfsd_net *nn);
extern int set_callback_cred(void);
-void nfsd4_run_cb_null(struct work_struct *w);
-void nfsd4_run_cb_recall(struct work_struct *w);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
-extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
+extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
+ struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
+extern void nfsd4_run_cb(struct nfsd4_callback *cb);
extern int nfsd4_create_callback_queue(void);
extern void nfsd4_destroy_callback_queue(void);
extern void nfsd4_shutdown_callback(struct nfs4_client *);
@@ -545,13 +561,16 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
struct nfsd_net *nn);
extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
+/* grace period management */
+void nfsd4_end_grace(struct nfsd_net *nn);
+
/* nfs4recover operations */
extern int nfsd4_client_tracking_init(struct net *net);
extern void nfsd4_client_tracking_exit(struct net *net);
extern void nfsd4_client_record_create(struct nfs4_client *clp);
extern void nfsd4_client_record_remove(struct nfs4_client *clp);
extern int nfsd4_client_record_check(struct nfs4_client *clp);
-extern void nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time);
+extern void nfsd4_record_grace_done(struct nfsd_net *nn);
/* nfs fault injection functions */
#ifdef CONFIG_NFSD_FAULT_INJECTION
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index f501a9b5c9df..965cffd17a0c 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -445,6 +445,16 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
if (err)
goto out;
size_change = 1;
+
+ /*
+ * RFC5661, Section 18.30.4:
+ * Changing the size of a file with SETATTR indirectly
+ * changes the time_modify and change attributes.
+ *
+ * (and similar for the older RFCs)
+ */
+ if (iap->ia_size != i_size_read(inode))
+ iap->ia_valid |= ATTR_MTIME;
}
iap->ia_valid |= ATTR_CTIME;
@@ -649,6 +659,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
{
struct path path;
struct inode *inode;
+ struct file *file;
int flags = O_RDONLY|O_LARGEFILE;
__be32 err;
int host_err = 0;
@@ -703,19 +714,25 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
else
flags = O_WRONLY|O_LARGEFILE;
}
- *filp = dentry_open(&path, flags, current_cred());
- if (IS_ERR(*filp)) {
- host_err = PTR_ERR(*filp);
- *filp = NULL;
- } else {
- host_err = ima_file_check(*filp, may_flags);
- if (may_flags & NFSD_MAY_64BIT_COOKIE)
- (*filp)->f_mode |= FMODE_64BITHASH;
- else
- (*filp)->f_mode |= FMODE_32BITHASH;
+ file = dentry_open(&path, flags, current_cred());
+ if (IS_ERR(file)) {
+ host_err = PTR_ERR(file);
+ goto out_nfserr;
}
+ host_err = ima_file_check(file, may_flags);
+ if (host_err) {
+ nfsd_close(file);
+ goto out_nfserr;
+ }
+
+ if (may_flags & NFSD_MAY_64BIT_COOKIE)
+ file->f_mode |= FMODE_64BITHASH;
+ else
+ file->f_mode |= FMODE_32BITHASH;
+
+ *filp = file;
out_nfserr:
err = nfserrno(host_err);
out:
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 465e7799742a..5720e9457f33 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -428,6 +428,17 @@ struct nfsd4_reclaim_complete {
u32 rca_one_fs;
};
+struct nfsd4_seek {
+ /* request */
+ stateid_t seek_stateid;
+ loff_t seek_offset;
+ u32 seek_whence;
+
+ /* response */
+ u32 seek_eof;
+ loff_t seek_pos;
+};
+
struct nfsd4_op {
int opnum;
__be32 status;
@@ -473,6 +484,9 @@ struct nfsd4_op {
struct nfsd4_reclaim_complete reclaim_complete;
struct nfsd4_test_stateid test_stateid;
struct nfsd4_free_stateid free_stateid;
+
+ /* NFSv4.2 */
+ struct nfsd4_seek seek;
} u;
struct nfs4_replay * replay;
};
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 6252b173a465..d071e7f23de2 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -24,6 +24,7 @@
#include <linux/buffer_head.h>
#include <linux/gfp.h>
#include <linux/mpage.h>
+#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/aio.h>
#include "nilfs.h"
@@ -219,10 +220,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
static int nilfs_set_page_dirty(struct page *page)
{
+ struct inode *inode = page->mapping->host;
int ret = __set_page_dirty_nobuffers(page);
if (page_has_buffers(page)) {
- struct inode *inode = page->mapping->host;
unsigned nr_dirty = 0;
struct buffer_head *bh, *head;
@@ -245,6 +246,10 @@ static int nilfs_set_page_dirty(struct page *page)
if (nr_dirty)
nilfs_set_file_dirty(inode, nr_dirty);
+ } else if (ret) {
+ unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ nilfs_set_file_dirty(inode, nr_dirty);
}
return ret;
}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b13992a41bd9..c991616acca9 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -78,7 +78,7 @@ static int create_fd(struct fsnotify_group *group,
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- client_fd = get_unused_fd();
+ client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
if (client_fd < 0)
return client_fd;
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 85e7d2b431d9..9c0898c4cfe1 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -23,9 +23,6 @@ extern int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group, struct vfsmount *mnt,
int allow_dups);
-/* final kfree of a group */
-extern void fsnotify_final_destroy_group(struct fsnotify_group *group);
-
/* vfsmount specific destruction of a mark */
extern void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark);
/* inode specific destruction of a mark */
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ad1995980456..d16b62cb2854 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -31,7 +31,7 @@
/*
* Final freeing of a group
*/
-void fsnotify_final_destroy_group(struct fsnotify_group *group)
+static void fsnotify_final_destroy_group(struct fsnotify_group *group)
{
if (group->ops->free_group_priv)
group->ops->free_group_priv(group);
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 0f88bc0b4e6c..7d888d77d59a 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -165,8 +165,10 @@ static void inotify_free_group_priv(struct fsnotify_group *group)
/* ideally the idr is empty and we won't hit the BUG in the callback */
idr_for_each(&group->inotify_data.idr, idr_callback, group);
idr_destroy(&group->inotify_data.idr);
- atomic_dec(&group->inotify_data.user->inotify_devs);
- free_uid(group->inotify_data.user);
+ if (group->inotify_data.user) {
+ atomic_dec(&group->inotify_data.user->inotify_devs);
+ free_uid(group->inotify_data.user);
+ }
}
static void inotify_free_event(struct fsnotify_event *fsn_event)
diff --git a/fs/ntfs/debug.c b/fs/ntfs/debug.c
index dd6103cc93c1..825a54e8f490 100644
--- a/fs/ntfs/debug.c
+++ b/fs/ntfs/debug.c
@@ -112,7 +112,7 @@ void __ntfs_error(const char *function, const struct super_block *sb,
/* If 1, output debug messages, and if 0, don't. */
int debug_msgs = 0;
-void __ntfs_debug (const char *file, int line, const char *function,
+void __ntfs_debug(const char *file, int line, const char *function,
const char *fmt, ...)
{
struct va_format vaf;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index f5ec1ce7a532..643faa44f22b 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1,7 +1,7 @@
/*
* file.c - NTFS kernel file operations. Part of the Linux-NTFS project.
*
- * Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.
+ * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
*
* This program/include file is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as published
@@ -410,7 +410,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
BUG_ON(!nr_pages);
err = nr = 0;
do {
- pages[nr] = find_lock_page(mapping, index);
+ pages[nr] = find_get_page_flags(mapping, index, FGP_LOCK |
+ FGP_ACCESSED);
if (!pages[nr]) {
if (!*cached_page) {
*cached_page = page_cache_alloc(mapping);
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 6c3296e546c3..9e1e112074fb 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -3208,7 +3208,7 @@ static void __exit exit_ntfs_fs(void)
}
MODULE_AUTHOR("Anton Altaparmakov <anton@tuxera.com>");
-MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.");
+MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.");
MODULE_VERSION(NTFS_VERSION);
MODULE_LICENSE("GPL");
#ifdef DEBUG
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 4a231a166cf8..1ef547e49373 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1481,8 +1481,16 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
handle_t *handle;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
+ handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto out;
+ }
+
page = find_or_create_page(mapping, 0, GFP_NOFS);
if (!page) {
+ ocfs2_commit_trans(osb, handle);
ret = -ENOMEM;
mlog_errno(ret);
goto out;
@@ -1494,13 +1502,6 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
wc->w_pages[0] = wc->w_target_page = page;
wc->w_num_pages = 1;
- handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto out;
- }
-
ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 73039295d0d1..d13385448168 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -2572,6 +2572,25 @@ int o2hb_check_node_heartbeating(u8 node_num)
}
EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating);
+int o2hb_check_node_heartbeating_no_sem(u8 node_num)
+{
+ unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+ unsigned long flags;
+
+ spin_lock_irqsave(&o2hb_live_lock, flags);
+ o2hb_fill_node_map_from_callback(testing_map, sizeof(testing_map));
+ spin_unlock_irqrestore(&o2hb_live_lock, flags);
+ if (!test_bit(node_num, testing_map)) {
+ mlog(ML_HEARTBEAT,
+ "node (%u) does not have heartbeating enabled.\n",
+ node_num);
+ return 0;
+ }
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating_no_sem);
+
int o2hb_check_node_heartbeating_from_callback(u8 node_num)
{
unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index 00ad8e8fea51..3ef5137dc362 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -80,6 +80,7 @@ void o2hb_fill_node_map(unsigned long *map,
void o2hb_exit(void);
int o2hb_init(void);
int o2hb_check_node_heartbeating(u8 node_num);
+int o2hb_check_node_heartbeating_no_sem(u8 node_num);
int o2hb_check_node_heartbeating_from_callback(u8 node_num);
int o2hb_check_local_node_heartbeating(void);
void o2hb_stop_all_regions(void);
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 73ba81928bce..27d1242c8383 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -185,29 +185,13 @@ static const struct seq_operations nst_seq_ops = {
static int nst_fop_open(struct inode *inode, struct file *file)
{
struct o2net_send_tracking *dummy_nst;
- struct seq_file *seq;
- int ret;
- dummy_nst = kmalloc(sizeof(struct o2net_send_tracking), GFP_KERNEL);
- if (dummy_nst == NULL) {
- ret = -ENOMEM;
- goto out;
- }
- dummy_nst->st_task = NULL;
-
- ret = seq_open(file, &nst_seq_ops);
- if (ret)
- goto out;
-
- seq = file->private_data;
- seq->private = dummy_nst;
+ dummy_nst = __seq_open_private(file, &nst_seq_ops, sizeof(*dummy_nst));
+ if (!dummy_nst)
+ return -ENOMEM;
o2net_debug_add_nst(dummy_nst);
- dummy_nst = NULL;
-
-out:
- kfree(dummy_nst);
- return ret;
+ return 0;
}
static int nst_fop_release(struct inode *inode, struct file *file)
@@ -412,33 +396,27 @@ static const struct seq_operations sc_seq_ops = {
.show = sc_seq_show,
};
-static int sc_common_open(struct file *file, struct o2net_sock_debug *sd)
+static int sc_common_open(struct file *file, int ctxt)
{
+ struct o2net_sock_debug *sd;
struct o2net_sock_container *dummy_sc;
- struct seq_file *seq;
- int ret;
- dummy_sc = kmalloc(sizeof(struct o2net_sock_container), GFP_KERNEL);
- if (dummy_sc == NULL) {
- ret = -ENOMEM;
- goto out;
- }
- dummy_sc->sc_page = NULL;
+ dummy_sc = kzalloc(sizeof(*dummy_sc), GFP_KERNEL);
+ if (!dummy_sc)
+ return -ENOMEM;
- ret = seq_open(file, &sc_seq_ops);
- if (ret)
- goto out;
+ sd = __seq_open_private(file, &sc_seq_ops, sizeof(*sd));
+ if (!sd) {
+ kfree(dummy_sc);
+ return -ENOMEM;
+ }
- seq = file->private_data;
- seq->private = sd;
+ sd->dbg_ctxt = ctxt;
sd->dbg_sock = dummy_sc;
- o2net_debug_add_sc(dummy_sc);
- dummy_sc = NULL;
+ o2net_debug_add_sc(dummy_sc);
-out:
- kfree(dummy_sc);
- return ret;
+ return 0;
}
static int sc_fop_release(struct inode *inode, struct file *file)
@@ -453,16 +431,7 @@ static int sc_fop_release(struct inode *inode, struct file *file)
static int stats_fop_open(struct inode *inode, struct file *file)
{
- struct o2net_sock_debug *sd;
-
- sd = kmalloc(sizeof(struct o2net_sock_debug), GFP_KERNEL);
- if (sd == NULL)
- return -ENOMEM;
-
- sd->dbg_ctxt = SHOW_SOCK_STATS;
- sd->dbg_sock = NULL;
-
- return sc_common_open(file, sd);
+ return sc_common_open(file, SHOW_SOCK_STATS);
}
static const struct file_operations stats_seq_fops = {
@@ -474,16 +443,7 @@ static const struct file_operations stats_seq_fops = {
static int sc_fop_open(struct inode *inode, struct file *file)
{
- struct o2net_sock_debug *sd;
-
- sd = kmalloc(sizeof(struct o2net_sock_debug), GFP_KERNEL);
- if (sd == NULL)
- return -ENOMEM;
-
- sd->dbg_ctxt = SHOW_SOCK_CONTAINERS;
- sd->dbg_sock = NULL;
-
- return sc_common_open(file, sd);
+ return sc_common_open(file, SHOW_SOCK_CONTAINERS);
}
static const struct file_operations sc_seq_fops = {
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index ea34952f9496..97de0fbd9f78 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -536,7 +536,7 @@ static void o2net_set_nn_state(struct o2net_node *nn,
if (nn->nn_persistent_error || nn->nn_sc_valid)
wake_up(&nn->nn_sc_wq);
- if (!was_err && nn->nn_persistent_error) {
+ if (was_valid && !was_err && nn->nn_persistent_error) {
o2quo_conn_err(o2net_num_from_nn(nn));
queue_delayed_work(o2net_wq, &nn->nn_still_up,
msecs_to_jiffies(O2NET_QUORUM_DELAY_MS));
@@ -1601,7 +1601,15 @@ static void o2net_start_connect(struct work_struct *work)
struct sockaddr_in myaddr = {0, }, remoteaddr = {0, };
int ret = 0, stop;
unsigned int timeout;
+ unsigned int noio_flag;
+ /*
+ * sock_create allocates the sock with GFP_KERNEL. We must set
+ * per-process flag PF_MEMALLOC_NOIO so that all allocations done
+ * by this process are done as if GFP_NOIO was specified. So we
+ * are not reentering filesystem while doing memory reclaim.
+ */
+ noio_flag = memalloc_noio_save();
/* if we're greater we initiate tx, otherwise we accept */
if (o2nm_this_node() <= o2net_num_from_nn(nn))
goto out;
@@ -1710,6 +1718,7 @@ out:
if (mynode)
o2nm_node_put(mynode);
+ memalloc_noio_restore(noio_flag);
return;
}
@@ -1721,7 +1730,8 @@ static void o2net_connect_expired(struct work_struct *work)
spin_lock(&nn->nn_lock);
if (!nn->nn_sc_valid) {
printk(KERN_NOTICE "o2net: No connection established with "
- "node %u after %u.%u seconds, giving up.\n",
+ "node %u after %u.%u seconds, check network and"
+ " cluster configuration.\n",
o2net_num_from_nn(nn),
o2net_idle_timeout() / 1000,
o2net_idle_timeout() % 1000);
@@ -1835,6 +1845,15 @@ static int o2net_accept_one(struct socket *sock, int *more)
struct o2nm_node *local_node = NULL;
struct o2net_sock_container *sc = NULL;
struct o2net_node *nn;
+ unsigned int noio_flag;
+
+ /*
+ * sock_create_lite allocates the sock with GFP_KERNEL. We must set
+ * per-process flag PF_MEMALLOC_NOIO so that all allocations done
+ * by this process are done as if GFP_NOIO was specified. So we
+ * are not reentering filesystem while doing memory reclaim.
+ */
+ noio_flag = memalloc_noio_save();
BUG_ON(sock == NULL);
*more = 0;
@@ -1951,6 +1970,8 @@ out:
o2nm_node_put(local_node);
if (sc)
sc_put(sc);
+
+ memalloc_noio_restore(noio_flag);
return ret;
}
@@ -2146,17 +2167,13 @@ int o2net_init(void)
o2quo_init();
if (o2net_debugfs_init())
- return -ENOMEM;
+ goto out;
o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL);
o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
o2net_keep_resp = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
- if (!o2net_hand || !o2net_keep_req || !o2net_keep_resp) {
- kfree(o2net_hand);
- kfree(o2net_keep_req);
- kfree(o2net_keep_resp);
- return -ENOMEM;
- }
+ if (!o2net_hand || !o2net_keep_req || !o2net_keep_resp)
+ goto out;
o2net_hand->protocol_version = cpu_to_be64(O2NET_PROTOCOL_VERSION);
o2net_hand->connector_id = cpu_to_be64(1);
@@ -2181,6 +2198,14 @@ int o2net_init(void)
}
return 0;
+
+out:
+ kfree(o2net_hand);
+ kfree(o2net_keep_req);
+ kfree(o2net_keep_resp);
+
+ o2quo_exit();
+ return -ENOMEM;
}
void o2net_exit(void)
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 18f13c2e4a10..149eb556b8c6 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -647,41 +647,30 @@ static const struct seq_operations debug_lockres_ops = {
static int debug_lockres_open(struct inode *inode, struct file *file)
{
struct dlm_ctxt *dlm = inode->i_private;
- int ret = -ENOMEM;
- struct seq_file *seq;
- struct debug_lockres *dl = NULL;
+ struct debug_lockres *dl;
+ void *buf;
- dl = kzalloc(sizeof(struct debug_lockres), GFP_KERNEL);
- if (!dl) {
- mlog_errno(ret);
+ buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!buf)
goto bail;
- }
- dl->dl_len = PAGE_SIZE;
- dl->dl_buf = kmalloc(dl->dl_len, GFP_KERNEL);
- if (!dl->dl_buf) {
- mlog_errno(ret);
- goto bail;
- }
+ dl = __seq_open_private(file, &debug_lockres_ops, sizeof(*dl));
+ if (!dl)
+ goto bailfree;
- ret = seq_open(file, &debug_lockres_ops);
- if (ret) {
- mlog_errno(ret);
- goto bail;
- }
-
- seq = file->private_data;
- seq->private = dl;
+ dl->dl_len = PAGE_SIZE;
+ dl->dl_buf = buf;
dlm_grab(dlm);
dl->dl_ctxt = dlm;
return 0;
+
+bailfree:
+ kfree(buf);
bail:
- if (dl)
- kfree(dl->dl_buf);
- kfree(dl);
- return ret;
+ mlog_errno(-ENOMEM);
+ return -ENOMEM;
}
static int debug_lockres_release(struct inode *inode, struct file *file)
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 3fcf205ee900..02d315fef432 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -839,7 +839,7 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data,
* to back off and try again. This gives heartbeat a chance
* to catch up.
*/
- if (!o2hb_check_node_heartbeating(query->node_idx)) {
+ if (!o2hb_check_node_heartbeating_no_sem(query->node_idx)) {
mlog(0, "node %u is not in our live map yet\n",
query->node_idx);
@@ -1975,24 +1975,22 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
dlm = kzalloc(sizeof(*dlm), GFP_KERNEL);
if (!dlm) {
- mlog_errno(-ENOMEM);
+ ret = -ENOMEM;
+ mlog_errno(ret);
goto leave;
}
dlm->name = kstrdup(domain, GFP_KERNEL);
if (dlm->name == NULL) {
- mlog_errno(-ENOMEM);
- kfree(dlm);
- dlm = NULL;
+ ret = -ENOMEM;
+ mlog_errno(ret);
goto leave;
}
dlm->lockres_hash = (struct hlist_head **)dlm_alloc_pagevec(DLM_HASH_PAGES);
if (!dlm->lockres_hash) {
- mlog_errno(-ENOMEM);
- kfree(dlm->name);
- kfree(dlm);
- dlm = NULL;
+ ret = -ENOMEM;
+ mlog_errno(ret);
goto leave;
}
@@ -2002,11 +2000,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
dlm->master_hash = (struct hlist_head **)
dlm_alloc_pagevec(DLM_HASH_PAGES);
if (!dlm->master_hash) {
- mlog_errno(-ENOMEM);
- dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
- kfree(dlm->name);
- kfree(dlm);
- dlm = NULL;
+ ret = -ENOMEM;
+ mlog_errno(ret);
goto leave;
}
@@ -2017,14 +2012,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
dlm->node_num = o2nm_this_node();
ret = dlm_create_debugfs_subroot(dlm);
- if (ret < 0) {
- dlm_free_pagevec((void **)dlm->master_hash, DLM_HASH_PAGES);
- dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
- kfree(dlm->name);
- kfree(dlm);
- dlm = NULL;
+ if (ret < 0)
goto leave;
- }
spin_lock_init(&dlm->spinlock);
spin_lock_init(&dlm->master_lock);
@@ -2085,6 +2074,19 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
atomic_read(&dlm->dlm_refs.refcount));
leave:
+ if (ret < 0 && dlm) {
+ if (dlm->master_hash)
+ dlm_free_pagevec((void **)dlm->master_hash,
+ DLM_HASH_PAGES);
+
+ if (dlm->lockres_hash)
+ dlm_free_pagevec((void **)dlm->lockres_hash,
+ DLM_HASH_PAGES);
+
+ kfree(dlm->name);
+ kfree(dlm);
+ dlm = NULL;
+ }
return dlm;
}
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 3ec906ef5d9a..215e41abf101 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -625,9 +625,6 @@ struct dlm_lock_resource *dlm_new_lockres(struct dlm_ctxt *dlm,
return res;
error:
- if (res && res->lockname.name)
- kmem_cache_free(dlm_lockname_cache, (void *)res->lockname.name);
-
if (res)
kmem_cache_free(dlm_lockres_cache, res);
return NULL;
@@ -655,12 +652,9 @@ void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm,
clear_bit(bit, res->refmap);
}
-
-void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
struct dlm_lock_resource *res)
{
- assert_spin_locked(&res->spinlock);
-
res->inflight_locks++;
mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name,
@@ -668,6 +662,13 @@ void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
__builtin_return_address(0));
}
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
+{
+ assert_spin_locked(&res->spinlock);
+ __dlm_lockres_grab_inflight_ref(dlm, res);
+}
+
void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
struct dlm_lock_resource *res)
{
@@ -894,10 +895,8 @@ lookup:
/* finally add the lockres to its hash bucket */
__dlm_insert_lockres(dlm, res);
- /* Grab inflight ref to pin the resource */
- spin_lock(&res->spinlock);
- dlm_lockres_grab_inflight_ref(dlm, res);
- spin_unlock(&res->spinlock);
+ /* since this lockres is new it doesn't not require the spinlock */
+ __dlm_lockres_grab_inflight_ref(dlm, res);
/* get an extra ref on the mle in case this is a BLOCK
* if so, the creator of the BLOCK may try to put the last
@@ -2037,6 +2036,10 @@ kill:
"and killing the other node now! This node is OK and can continue.\n");
__dlm_print_one_lock_resource(res);
spin_unlock(&res->spinlock);
+ spin_lock(&dlm->master_lock);
+ if (mle)
+ __dlm_put_mle(mle);
+ spin_unlock(&dlm->master_lock);
spin_unlock(&dlm->spinlock);
*ret_data = (void *)res;
dlm_put(dlm);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 45067faf5695..3365839d2971 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1710,9 +1710,12 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
BUG();
} else
__dlm_lockres_grab_inflight_worker(dlm, res);
- } else /* put.. incase we are not the master */
+ spin_unlock(&res->spinlock);
+ } else {
+ /* put.. incase we are not the master */
+ spin_unlock(&res->spinlock);
dlm_lockres_put(res);
- spin_unlock(&res->spinlock);
+ }
}
spin_unlock(&dlm->spinlock);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 52cfe99ae056..21262f2b1654 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2892,37 +2892,24 @@ static int ocfs2_dlm_debug_release(struct inode *inode, struct file *file)
static int ocfs2_dlm_debug_open(struct inode *inode, struct file *file)
{
- int ret;
struct ocfs2_dlm_seq_priv *priv;
- struct seq_file *seq;
struct ocfs2_super *osb;
- priv = kzalloc(sizeof(struct ocfs2_dlm_seq_priv), GFP_KERNEL);
+ priv = __seq_open_private(file, &ocfs2_dlm_seq_ops, sizeof(*priv));
if (!priv) {
- ret = -ENOMEM;
- mlog_errno(ret);
- goto out;
+ mlog_errno(-ENOMEM);
+ return -ENOMEM;
}
+
osb = inode->i_private;
ocfs2_get_dlm_debug(osb->osb_dlm_debug);
priv->p_dlm_debug = osb->osb_dlm_debug;
INIT_LIST_HEAD(&priv->p_iter_res.l_debug_list);
- ret = seq_open(file, &ocfs2_dlm_seq_ops);
- if (ret) {
- kfree(priv);
- mlog_errno(ret);
- goto out;
- }
-
- seq = file->private_data;
- seq->private = priv;
-
ocfs2_add_lockres_tracking(&priv->p_iter_res,
priv->p_dlm_debug);
-out:
- return ret;
+ return 0;
}
static const struct file_operations ocfs2_dlm_debug_fops = {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 2930e231f3f9..682732f3f0d8 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -760,7 +760,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
struct address_space *mapping = inode->i_mapping;
struct page *page;
unsigned long index = abs_from >> PAGE_CACHE_SHIFT;
- handle_t *handle = NULL;
+ handle_t *handle;
int ret = 0;
unsigned zero_from, zero_to, block_start, block_end;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
@@ -769,11 +769,17 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
BUG_ON(abs_from & (inode->i_blkbits - 1));
+ handle = ocfs2_zero_start_ordered_transaction(inode, di_bh);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+
page = find_or_create_page(mapping, index, GFP_NOFS);
if (!page) {
ret = -ENOMEM;
mlog_errno(ret);
- goto out;
+ goto out_commit_trans;
}
/* Get the offsets within the page that we want to zero */
@@ -805,15 +811,6 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
goto out_unlock;
}
- if (!handle) {
- handle = ocfs2_zero_start_ordered_transaction(inode,
- di_bh);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- handle = NULL;
- break;
- }
- }
/* must not update i_size! */
ret = block_commit_write(page, block_start + 1,
@@ -824,27 +821,29 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
ret = 0;
}
+ /*
+ * fs-writeback will release the dirty pages without page lock
+ * whose offset are over inode size, the release happens at
+ * block_write_full_page().
+ */
+ i_size_write(inode, abs_to);
+ inode->i_blocks = ocfs2_inode_sector_count(inode);
+ di->i_size = cpu_to_le64((u64)i_size_read(inode));
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+ di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+ di->i_mtime_nsec = di->i_ctime_nsec;
if (handle) {
- /*
- * fs-writeback will release the dirty pages without page lock
- * whose offset are over inode size, the release happens at
- * block_write_full_page().
- */
- i_size_write(inode, abs_to);
- inode->i_blocks = ocfs2_inode_sector_count(inode);
- di->i_size = cpu_to_le64((u64)i_size_read(inode));
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
- di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
- di->i_mtime_nsec = di->i_ctime_nsec;
ocfs2_journal_dirty(handle, di_bh);
ocfs2_update_inode_fsync_trans(handle, inode, 1);
- ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
}
out_unlock:
unlock_page(page);
page_cache_release(page);
+out_commit_trans:
+ if (handle)
+ ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
out:
return ret;
}
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index a6c991c0fc98..a9b76de46047 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -162,7 +162,7 @@ static inline blkcnt_t ocfs2_inode_sector_count(struct inode *inode)
{
int c_to_s_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits - 9;
- return (blkcnt_t)(OCFS2_I(inode)->ip_clusters << c_to_s_bits);
+ return (blkcnt_t)OCFS2_I(inode)->ip_clusters << c_to_s_bits;
}
/* Validate that a bh contains a valid inode */
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 6219aaadeb08..74caffeeee1d 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -404,7 +404,7 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode,
* 'vict_blkno' was out of the valid range.
*/
if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
- (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) <<
+ (vict_blkno >= ((u64)le32_to_cpu(ac_dinode->id1.bitmap1.i_total) <<
bits_per_unit))) {
ret = -EINVAL;
goto out;
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 13a8537d8e8b..720aa389e0ea 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -591,7 +591,7 @@ static int ocfs2_control_release(struct inode *inode, struct file *file)
*/
ocfs2_control_this_node = -1;
running_proto.pv_major = 0;
- running_proto.pv_major = 0;
+ running_proto.pv_minor = 0;
}
out:
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index ddb662b32447..4142546aedae 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2532,6 +2532,7 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
kfree(osb->journal);
kfree(osb->local_alloc_copy);
kfree(osb->uuid_str);
+ kfree(osb->vol_label);
ocfs2_put_dlm_debug(osb->osb_dlm_debug);
memset(osb, 0, sizeof(struct ocfs2_super));
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index baf852b648ad..950100e326a1 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -376,37 +376,6 @@ static const struct file_operations proc_lstats_operations = {
#endif
-#ifdef CONFIG_CGROUPS
-static int cgroup_open(struct inode *inode, struct file *file)
-{
- struct pid *pid = PROC_I(inode)->pid;
- return single_open(file, proc_cgroup_show, pid);
-}
-
-static const struct file_operations proc_cgroup_operations = {
- .open = cgroup_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-#endif
-
-#ifdef CONFIG_PROC_PID_CPUSET
-
-static int cpuset_open(struct inode *inode, struct file *file)
-{
- struct pid *pid = PROC_I(inode)->pid;
- return single_open(file, proc_cpuset_show, pid);
-}
-
-static const struct file_operations proc_cpuset_operations = {
- .open = cpuset_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-#endif
-
static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
@@ -632,29 +601,35 @@ static const struct file_operations proc_single_file_operations = {
.release = single_release,
};
-static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
+
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
{
- struct task_struct *task = get_proc_task(file_inode(file));
- struct mm_struct *mm;
+ struct task_struct *task = get_proc_task(inode);
+ struct mm_struct *mm = ERR_PTR(-ESRCH);
- if (!task)
- return -ESRCH;
+ if (task) {
+ mm = mm_access(task, mode);
+ put_task_struct(task);
- mm = mm_access(task, mode);
- put_task_struct(task);
+ if (!IS_ERR_OR_NULL(mm)) {
+ /* ensure this mm_struct can't be freed */
+ atomic_inc(&mm->mm_count);
+ /* but do not pin its memory */
+ mmput(mm);
+ }
+ }
+
+ return mm;
+}
+
+static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
+{
+ struct mm_struct *mm = proc_mem_open(inode, mode);
if (IS_ERR(mm))
return PTR_ERR(mm);
- if (mm) {
- /* ensure this mm_struct can't be freed */
- atomic_inc(&mm->mm_count);
- /* but do not pin its memory */
- mmput(mm);
- }
-
file->private_data = mm;
-
return 0;
}
@@ -2573,10 +2548,10 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("latency", S_IRUGO, proc_lstats_operations),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
- REG("cpuset", S_IRUGO, proc_cpuset_operations),
+ ONE("cpuset", S_IRUGO, proc_cpuset_show),
#endif
#ifdef CONFIG_CGROUPS
- REG("cgroup", S_IRUGO, proc_cgroup_operations),
+ ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
ONE("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
@@ -2919,10 +2894,10 @@ static const struct pid_entry tid_base_stuff[] = {
REG("latency", S_IRUGO, proc_lstats_operations),
#endif
#ifdef CONFIG_PROC_PID_CPUSET
- REG("cpuset", S_IRUGO, proc_cpuset_operations),
+ ONE("cpuset", S_IRUGO, proc_cpuset_show),
#endif
#ifdef CONFIG_CGROUPS
- REG("cgroup", S_IRUGO, proc_cgroup_operations),
+ ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
ONE("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 7da13e49128a..aa7a0ee182e1 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -268,8 +268,9 @@ extern int proc_remount(struct super_block *, int *, char *);
* task_[no]mmu.c
*/
struct proc_maps_private {
- struct pid *pid;
+ struct inode *inode;
struct task_struct *task;
+ struct mm_struct *mm;
#ifdef CONFIG_MMU
struct vm_area_struct *tail_vma;
#endif
@@ -278,6 +279,8 @@ struct proc_maps_private {
#endif
};
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
+
extern const struct file_operations proc_pid_maps_operations;
extern const struct file_operations proc_tid_maps_operations;
extern const struct file_operations proc_pid_numa_maps_operations;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 6df8d0722c97..91a4e6426321 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -610,8 +610,10 @@ static void __init proc_kcore_text_init(void)
struct kcore_list kcore_modules;
static void __init add_modules_range(void)
{
- kclist_add(&kcore_modules, (void *)MODULES_VADDR,
+ if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
+ kclist_add(&kcore_modules, (void *)MODULES_VADDR,
MODULES_END - MODULES_VADDR, KCORE_VMALLOC);
+ }
}
#else
static void __init add_modules_range(void)
diff --git a/fs/proc/page.c b/fs/proc/page.c
index e647c55275d9..1e3187da1fed 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -133,6 +133,9 @@ u64 stable_page_flags(struct page *page)
if (PageBuddy(page))
u |= 1 << KPF_BUDDY;
+ if (PageBalloon(page))
+ u |= 1 << KPF_BALLOON;
+
u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
u |= kpf_copy_bit(k, KPF_SLAB, PG_slab);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dfc791c42d64..b7a7dc963a35 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -87,32 +87,14 @@ unsigned long task_statm(struct mm_struct *mm,
#ifdef CONFIG_NUMA
/*
- * These functions are for numa_maps but called in generic **maps seq_file
- * ->start(), ->stop() ops.
- *
- * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
- * Each mempolicy object is controlled by reference counting. The problem here
- * is how to avoid accessing dead mempolicy object.
- *
- * Because we're holding mmap_sem while reading seq_file, it's safe to access
- * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
- *
- * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
- * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
- * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
- * gurantee the task never exits under us. But taking task_lock() around
- * get_vma_plicy() causes lock order problem.
- *
- * To access task->mempolicy without lock, we hold a reference count of an
- * object pointed by task->mempolicy and remember it. This will guarantee
- * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
+ * Save get_task_policy() for show_numa_map().
*/
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
struct task_struct *task = priv->task;
task_lock(task);
- priv->task_mempolicy = task->mempolicy;
+ priv->task_mempolicy = get_task_policy(task);
mpol_get(priv->task_mempolicy);
task_unlock(task);
}
@@ -129,124 +111,154 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
}
#endif
-static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
+static void vma_stop(struct proc_maps_private *priv)
{
- if (vma && vma != priv->tail_vma) {
- struct mm_struct *mm = vma->vm_mm;
- release_task_mempolicy(priv);
- up_read(&mm->mmap_sem);
- mmput(mm);
- }
+ struct mm_struct *mm = priv->mm;
+
+ release_task_mempolicy(priv);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+}
+
+static struct vm_area_struct *
+m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma)
+{
+ if (vma == priv->tail_vma)
+ return NULL;
+ return vma->vm_next ?: priv->tail_vma;
+}
+
+static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma)
+{
+ if (m->count < m->size) /* vma is copied successfully */
+ m->version = m_next_vma(m->private, vma) ? vma->vm_start : -1UL;
}
-static void *m_start(struct seq_file *m, loff_t *pos)
+static void *m_start(struct seq_file *m, loff_t *ppos)
{
struct proc_maps_private *priv = m->private;
unsigned long last_addr = m->version;
struct mm_struct *mm;
- struct vm_area_struct *vma, *tail_vma = NULL;
- loff_t l = *pos;
-
- /* Clear the per syscall fields in priv */
- priv->task = NULL;
- priv->tail_vma = NULL;
-
- /*
- * We remember last_addr rather than next_addr to hit with
- * vmacache most of the time. We have zero last_addr at
- * the beginning and also after lseek. We will have -1 last_addr
- * after the end of the vmas.
- */
+ struct vm_area_struct *vma;
+ unsigned int pos = *ppos;
+ /* See m_cache_vma(). Zero at the start or after lseek. */
if (last_addr == -1UL)
return NULL;
- priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+ priv->task = get_proc_task(priv->inode);
if (!priv->task)
return ERR_PTR(-ESRCH);
- mm = mm_access(priv->task, PTRACE_MODE_READ);
- if (!mm || IS_ERR(mm))
- return mm;
- down_read(&mm->mmap_sem);
+ mm = priv->mm;
+ if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+ return NULL;
- tail_vma = get_gate_vma(priv->task->mm);
- priv->tail_vma = tail_vma;
+ down_read(&mm->mmap_sem);
hold_task_mempolicy(priv);
- /* Start with last addr hint */
- vma = find_vma(mm, last_addr);
- if (last_addr && vma) {
- vma = vma->vm_next;
- goto out;
+ priv->tail_vma = get_gate_vma(mm);
+
+ if (last_addr) {
+ vma = find_vma(mm, last_addr);
+ if (vma && (vma = m_next_vma(priv, vma)))
+ return vma;
}
- /*
- * Check the vma index is within the range and do
- * sequential scan until m_index.
- */
- vma = NULL;
- if ((unsigned long)l < mm->map_count) {
- vma = mm->mmap;
- while (l-- && vma)
+ m->version = 0;
+ if (pos < mm->map_count) {
+ for (vma = mm->mmap; pos; pos--) {
+ m->version = vma->vm_start;
vma = vma->vm_next;
- goto out;
+ }
+ return vma;
}
- if (l != mm->map_count)
- tail_vma = NULL; /* After gate vma */
-
-out:
- if (vma)
- return vma;
+ /* we do not bother to update m->version in this case */
+ if (pos == mm->map_count && priv->tail_vma)
+ return priv->tail_vma;
- release_task_mempolicy(priv);
- /* End of vmas has been reached */
- m->version = (tail_vma != NULL)? 0: -1UL;
- up_read(&mm->mmap_sem);
- mmput(mm);
- return tail_vma;
+ vma_stop(priv);
+ return NULL;
}
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
struct proc_maps_private *priv = m->private;
- struct vm_area_struct *vma = v;
- struct vm_area_struct *tail_vma = priv->tail_vma;
+ struct vm_area_struct *next;
(*pos)++;
- if (vma && (vma != tail_vma) && vma->vm_next)
- return vma->vm_next;
- vma_stop(priv, vma);
- return (vma != tail_vma)? tail_vma: NULL;
+ next = m_next_vma(priv, v);
+ if (!next)
+ vma_stop(priv);
+ return next;
}
static void m_stop(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
- struct vm_area_struct *vma = v;
- if (!IS_ERR(vma))
- vma_stop(priv, vma);
- if (priv->task)
+ if (!IS_ERR_OR_NULL(v))
+ vma_stop(priv);
+ if (priv->task) {
put_task_struct(priv->task);
+ priv->task = NULL;
+ }
+}
+
+static int proc_maps_open(struct inode *inode, struct file *file,
+ const struct seq_operations *ops, int psize)
+{
+ struct proc_maps_private *priv = __seq_open_private(file, ops, psize);
+
+ if (!priv)
+ return -ENOMEM;
+
+ priv->inode = inode;
+ priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+ if (IS_ERR(priv->mm)) {
+ int err = PTR_ERR(priv->mm);
+
+ seq_release_private(inode, file);
+ return err;
+ }
+
+ return 0;
+}
+
+static int proc_map_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct proc_maps_private *priv = seq->private;
+
+ if (priv->mm)
+ mmdrop(priv->mm);
+
+ return seq_release_private(inode, file);
}
static int do_maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
- struct proc_maps_private *priv;
- int ret = -ENOMEM;
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (priv) {
- priv->pid = proc_pid(inode);
- ret = seq_open(file, ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = priv;
- } else {
- kfree(priv);
- }
+ return proc_maps_open(inode, file, ops,
+ sizeof(struct proc_maps_private));
+}
+
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+ struct vm_area_struct *vma, bool is_pid)
+{
+ struct inode *inode = priv->inode;
+ struct task_struct *task;
+ pid_t ret = 0;
+
+ rcu_read_lock();
+ task = pid_task(proc_pid(inode), PIDTYPE_PID);
+ if (task) {
+ task = task_of_stack(task, vma, is_pid);
+ if (task)
+ ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
}
+ rcu_read_unlock();
+
return ret;
}
@@ -256,7 +268,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
vm_flags_t flags = vma->vm_flags;
unsigned long ino = 0;
unsigned long long pgoff = 0;
@@ -321,8 +332,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
goto done;
}
- tid = vm_is_stack(task, vma, is_pid);
-
+ tid = pid_of_stack(priv, vma, is_pid);
if (tid != 0) {
/*
* Thread stack in /proc/PID/task/TID/maps or
@@ -349,15 +359,8 @@ done:
static int show_map(struct seq_file *m, void *v, int is_pid)
{
- struct vm_area_struct *vma = v;
- struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
-
- show_map_vma(m, vma, is_pid);
-
- if (m->count < m->size) /* vma is copied successfully */
- m->version = (vma != get_gate_vma(task->mm))
- ? vma->vm_start : 0;
+ show_map_vma(m, v, is_pid);
+ m_cache_vma(m, v);
return 0;
}
@@ -399,14 +402,14 @@ const struct file_operations proc_pid_maps_operations = {
.open = pid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
const struct file_operations proc_tid_maps_operations = {
.open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
/*
@@ -583,8 +586,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
static int show_smap(struct seq_file *m, void *v, int is_pid)
{
- struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
struct mm_walk smaps_walk = {
@@ -637,10 +638,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
mss.nonlinear >> 10);
show_smap_vma_flags(m, vma);
-
- if (m->count < m->size) /* vma is copied successfully */
- m->version = (vma != get_gate_vma(task->mm))
- ? vma->vm_start : 0;
+ m_cache_vma(m, vma);
return 0;
}
@@ -682,14 +680,14 @@ const struct file_operations proc_pid_smaps_operations = {
.open = pid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
const struct file_operations proc_tid_smaps_operations = {
.open = tid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
/*
@@ -931,23 +929,32 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
while (addr < end) {
struct vm_area_struct *vma = find_vma(walk->mm, addr);
pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
- unsigned long vm_end;
-
- if (!vma) {
- vm_end = end;
- } else {
- vm_end = min(end, vma->vm_end);
- if (vma->vm_flags & VM_SOFTDIRTY)
- pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+ /* End of address space hole, which we mark as non-present. */
+ unsigned long hole_end;
+
+ if (vma)
+ hole_end = min(end, vma->vm_start);
+ else
+ hole_end = end;
+
+ for (; addr < hole_end; addr += PAGE_SIZE) {
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ goto out;
}
- for (; addr < vm_end; addr += PAGE_SIZE) {
+ if (!vma)
+ break;
+
+ /* Addresses in the VMA. */
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+ for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
err = add_to_pagemap(addr, &pme, pm);
if (err)
goto out;
}
}
-
out:
return err;
}
@@ -1020,7 +1027,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
spinlock_t *ptl;
pte_t *pte;
int err = 0;
- pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
@@ -1034,6 +1040,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
for (; addr != end; addr += PAGE_SIZE) {
unsigned long offset;
+ pagemap_entry_t pme;
offset = (addr & ~PAGEMAP_WALK_MASK) >>
PAGE_SHIFT;
@@ -1048,32 +1055,51 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (pmd_trans_unstable(pmd))
return 0;
- for (; addr != end; addr += PAGE_SIZE) {
- int flags2;
-
- /* check to see if we've left 'vma' behind
- * and need a new, higher one */
- if (vma && (addr >= vma->vm_end)) {
- vma = find_vma(walk->mm, addr);
- if (vma && (vma->vm_flags & VM_SOFTDIRTY))
- flags2 = __PM_SOFT_DIRTY;
- else
- flags2 = 0;
- pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
+
+ while (1) {
+ /* End of address space hole, which we mark as non-present. */
+ unsigned long hole_end;
+
+ if (vma)
+ hole_end = min(end, vma->vm_start);
+ else
+ hole_end = end;
+
+ for (; addr < hole_end; addr += PAGE_SIZE) {
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ return err;
}
- /* check that 'vma' actually covers this address,
- * and that it isn't a huge page vma */
- if (vma && (vma->vm_start <= addr) &&
- !is_vm_hugetlb_page(vma)) {
+ if (!vma || vma->vm_start >= end)
+ break;
+ /*
+ * We can't possibly be in a hugetlb VMA. In general,
+ * for a mm_walk with a pmd_entry and a hugetlb_entry,
+ * the pmd_entry can only be called on addresses in a
+ * hugetlb if the walk starts in a non-hugetlb VMA and
+ * spans a hugepage VMA. Since pagemap_read walks are
+ * PMD-sized and PMD-aligned, this will never be true.
+ */
+ BUG_ON(is_vm_hugetlb_page(vma));
+
+ /* Addresses in the VMA. */
+ for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
+ pagemap_entry_t pme;
pte = pte_offset_map(pmd, addr);
pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
- /* unmap before userspace copy */
pte_unmap(pte);
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ return err;
}
- err = add_to_pagemap(addr, &pme, pm);
- if (err)
- return err;
+
+ if (addr == end)
+ break;
+
+ vma = find_vma(walk->mm, addr);
}
cond_resched();
@@ -1406,7 +1432,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
struct vm_area_struct *vma = v;
struct numa_maps *md = &numa_priv->md;
struct file *file = vma->vm_file;
- struct task_struct *task = proc_priv->task;
struct mm_struct *mm = vma->vm_mm;
struct mm_walk walk = {};
struct mempolicy *pol;
@@ -1426,9 +1451,13 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
walk.private = md;
walk.mm = mm;
- pol = get_vma_policy(task, vma, vma->vm_start);
- mpol_to_str(buffer, sizeof(buffer), pol);
- mpol_cond_put(pol);
+ pol = __get_vma_policy(vma, vma->vm_start);
+ if (pol) {
+ mpol_to_str(buffer, sizeof(buffer), pol);
+ mpol_cond_put(pol);
+ } else {
+ mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy);
+ }
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
@@ -1438,7 +1467,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_puts(m, " heap");
} else {
- pid_t tid = vm_is_stack(task, vma, is_pid);
+ pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
if (tid != 0) {
/*
* Thread stack in /proc/PID/task/TID/maps or
@@ -1486,9 +1515,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
seq_printf(m, " N%d=%lu", nid, md->node[nid]);
out:
seq_putc(m, '\n');
-
- if (m->count < m->size)
- m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+ m_cache_vma(m, vma);
return 0;
}
@@ -1519,20 +1546,8 @@ static const struct seq_operations proc_tid_numa_maps_op = {
static int numa_maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
- struct numa_maps_private *priv;
- int ret = -ENOMEM;
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (priv) {
- priv->proc_maps.pid = proc_pid(inode);
- ret = seq_open(file, ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = priv;
- } else {
- kfree(priv);
- }
- }
- return ret;
+ return proc_maps_open(inode, file, ops,
+ sizeof(struct numa_maps_private));
}
static int pid_numa_maps_open(struct inode *inode, struct file *file)
@@ -1549,13 +1564,13 @@ const struct file_operations proc_pid_numa_maps_operations = {
.open = pid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
const struct file_operations proc_tid_numa_maps_operations = {
.open = tid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = proc_map_release,
};
#endif /* CONFIG_NUMA */
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 678455d2d683..599ec2e20104 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,6 +123,25 @@ unsigned long task_statm(struct mm_struct *mm,
return size;
}
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+ struct vm_area_struct *vma, bool is_pid)
+{
+ struct inode *inode = priv->inode;
+ struct task_struct *task;
+ pid_t ret = 0;
+
+ rcu_read_lock();
+ task = pid_task(proc_pid(inode), PIDTYPE_PID);
+ if (task) {
+ task = task_of_stack(task, vma, is_pid);
+ if (task)
+ ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
/*
* display a single VMA to a sequenced file
*/
@@ -163,7 +182,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
seq_pad(m, ' ');
seq_path(m, &file->f_path, "");
} else if (mm) {
- pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+ pid_t tid = pid_of_stack(priv, vma, is_pid);
if (tid != 0) {
seq_pad(m, ' ');
@@ -212,22 +231,22 @@ static void *m_start(struct seq_file *m, loff_t *pos)
loff_t n = *pos;
/* pin the task and mm whilst we play with them */
- priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+ priv->task = get_proc_task(priv->inode);
if (!priv->task)
return ERR_PTR(-ESRCH);
- mm = mm_access(priv->task, PTRACE_MODE_READ);
- if (!mm || IS_ERR(mm)) {
- put_task_struct(priv->task);
- priv->task = NULL;
- return mm;
- }
- down_read(&mm->mmap_sem);
+ mm = priv->mm;
+ if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+ return NULL;
+ down_read(&mm->mmap_sem);
/* start from the Nth VMA */
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
if (n-- == 0)
return p;
+
+ up_read(&mm->mmap_sem);
+ mmput(mm);
return NULL;
}
@@ -235,11 +254,13 @@ static void m_stop(struct seq_file *m, void *_vml)
{
struct proc_maps_private *priv = m->private;
+ if (!IS_ERR_OR_NULL(_vml)) {
+ up_read(&priv->mm->mmap_sem);
+ mmput(priv->mm);
+ }
if (priv->task) {
- struct mm_struct *mm = priv->task->mm;
- up_read(&mm->mmap_sem);
- mmput(mm);
put_task_struct(priv->task);
+ priv->task = NULL;
}
}
@@ -269,20 +290,33 @@ static int maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
struct proc_maps_private *priv;
- int ret = -ENOMEM;
-
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (priv) {
- priv->pid = proc_pid(inode);
- ret = seq_open(file, ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
- m->private = priv;
- } else {
- kfree(priv);
- }
+
+ priv = __seq_open_private(file, ops, sizeof(*priv));
+ if (!priv)
+ return -ENOMEM;
+
+ priv->inode = inode;
+ priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+ if (IS_ERR(priv->mm)) {
+ int err = PTR_ERR(priv->mm);
+
+ seq_release_private(inode, file);
+ return err;
}
- return ret;
+
+ return 0;
+}
+
+
+static int map_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct proc_maps_private *priv = seq->private;
+
+ if (priv->mm)
+ mmdrop(priv->mm);
+
+ return seq_release_private(inode, file);
}
static int pid_maps_open(struct inode *inode, struct file *file)
@@ -299,13 +333,13 @@ const struct file_operations proc_pid_maps_operations = {
.open = pid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = map_release,
};
const struct file_operations proc_tid_maps_operations = {
.open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = map_release,
};
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index f2d0eee9d1f1..8b663b2d9562 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2725,7 +2725,7 @@ static int __init dquot_init(void)
panic("Cannot create dquot hash table");
for (i = 0; i < _DQST_DQSTAT_LAST; i++) {
- ret = percpu_counter_init(&dqstats.counter[i], 0);
+ ret = percpu_counter_init(&dqstats.counter[i], 0, GFP_KERNEL);
if (ret)
panic("Cannot create dquot stat counters");
}
diff --git a/fs/stack.c b/fs/stack.c
index 5b5388250e29..a54e33ed10f1 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -44,7 +44,7 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src)
* include/linux/fs.h). We don't necessarily hold i_mutex when this
* is called, so take i_lock for that case.
*
- * And if CONFIG_LBADF (on 32-bit), continue our effort to keep the
+ * And if CONFIG_LBDAF (on 32-bit), continue our effort to keep the
* two halves of i_blocks in sync despite SMP or PREEMPT: use i_lock
* for that case too, and do both at once by combining the tests.
*
diff --git a/fs/super.c b/fs/super.c
index b9a214d2fe98..1b836107acee 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -175,7 +175,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
goto fail;
for (i = 0; i < SB_FREEZE_LEVELS; i++) {
- if (percpu_counter_init(&s->s_writers.counter[i], 0) < 0)
+ if (percpu_counter_init(&s->s_writers.counter[i], 0,
+ GFP_KERNEL) < 0)
goto fail;
lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],
&type->s_writers_key[i], 0);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 80c350216ea8..b46ffa94372a 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -333,8 +333,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
spin_lock_irq(&ctx->wqh.lock);
if (!timerfd_canceled(ctx)) {
ctx->ticks = ticks;
- if (ticks)
- wake_up_locked(&ctx->wqh);
+ wake_up_locked(&ctx->wqh);
} else
ret = -ECANCELED;
spin_unlock_irq(&ctx->wqh.lock);
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index a9cc75ffa925..7caa01652888 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -298,7 +298,10 @@ cg_found:
ufsi->i_oeftflag = 0;
ufsi->i_dir_start_lookup = 0;
memset(&ufsi->i_u1, 0, sizeof(ufsi->i_u1));
- insert_inode_hash(inode);
+ if (insert_inode_locked(inode) < 0) {
+ err = -EIO;
+ goto failed;
+ }
mark_inode_dirty(inode);
if (uspi->fs_magic == UFS2_MAGIC) {
@@ -337,6 +340,7 @@ cg_found:
fail_remove_inode:
unlock_ufs(sb);
clear_nlink(inode);
+ unlock_new_inode(inode);
iput(inode);
UFSD("EXIT (FAILED): err %d\n", err);
return ERR_PTR(err);
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 2df62a73f20c..fd65deb4b5f0 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -38,10 +38,12 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ufs_add_link(dentry, inode);
if (!err) {
+ unlock_new_inode(inode);
d_instantiate(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput(inode);
return err;
}
@@ -155,6 +157,7 @@ out_notlocked:
out_fail:
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput(inode);
goto out;
}
@@ -210,6 +213,7 @@ out:
out_fail:
inode_dec_link_count(inode);
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput (inode);
inode_dec_link_count(dir);
unlock_ufs(dir->i_sb);