summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/v9fs.c2
-rw-r--r--fs/9p/vfs_file.c4
-rw-r--r--fs/Kconfig9
-rw-r--r--fs/block_dev.c22
-rw-r--r--fs/btrfs/compression.c5
-rw-r--r--fs/btrfs/extent_io.c22
-rw-r--r--fs/btrfs/inode.c33
-rw-r--r--fs/btrfs/reflink.c6
-rw-r--r--fs/btrfs/zlib.c5
-rw-r--r--fs/btrfs/zstd.c5
-rw-r--r--fs/buffer.c36
-rw-r--r--fs/ceph/Kconfig1
-rw-r--r--fs/ceph/addr.c626
-rw-r--r--fs/ceph/cache.c125
-rw-r--r--fs/ceph/cache.h101
-rw-r--r--fs/ceph/caps.c27
-rw-r--r--fs/ceph/debugfs.c12
-rw-r--r--fs/ceph/dir.c34
-rw-r--r--fs/ceph/export.c12
-rw-r--r--fs/ceph/file.c52
-rw-r--r--fs/ceph/inode.c36
-rw-r--r--fs/ceph/io.c2
-rw-r--r--fs/ceph/mds_client.c20
-rw-r--r--fs/ceph/mds_client.h1
-rw-r--r--fs/ceph/metric.c62
-rw-r--r--fs/ceph/metric.h56
-rw-r--r--fs/ceph/snap.c2
-rw-r--r--fs/ceph/super.h32
-rw-r--r--fs/ceph/xattr.c7
-rw-r--r--fs/configfs/configfs_internal.h4
-rw-r--r--fs/configfs/dir.c4
-rw-r--r--fs/configfs/file.c4
-rw-r--r--fs/configfs/inode.c4
-rw-r--r--fs/configfs/item.c4
-rw-r--r--fs/configfs/mount.c4
-rw-r--r--fs/configfs/symlink.c4
-rw-r--r--fs/dax.c8
-rw-r--r--fs/ecryptfs/crypto.c25
-rw-r--r--fs/ecryptfs/debug.c4
-rw-r--r--fs/ecryptfs/dentry.c2
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h2
-rw-r--r--fs/ecryptfs/file.c4
-rw-r--r--fs/ecryptfs/inode.c11
-rw-r--r--fs/ecryptfs/keystore.c15
-rw-r--r--fs/ecryptfs/kthread.c3
-rw-r--r--fs/ecryptfs/main.c30
-rw-r--r--fs/ecryptfs/messaging.c14
-rw-r--r--fs/ecryptfs/miscdev.c3
-rw-r--r--fs/ecryptfs/mmap.c11
-rw-r--r--fs/ecryptfs/read_write.c4
-rw-r--r--fs/ecryptfs/super.c8
-rw-r--r--fs/eventpoll.c6
-rw-r--r--fs/fat/fatent.c2
-rw-r--r--fs/gfs2/glock.c3
-rw-r--r--fs/hpfs/hpfs.h3
-rw-r--r--fs/hugetlbfs/inode.c9
-rw-r--r--fs/inode.c9
-rw-r--r--fs/io_uring.c69
-rw-r--r--fs/iomap/buffered-io.c7
-rw-r--r--fs/isofs/rock.c1
-rw-r--r--fs/locks.c3
-rw-r--r--fs/nfs/callback_proc.c17
-rw-r--r--fs/nfs/client.c20
-rw-r--r--fs/nfs/delegation.c29
-rw-r--r--fs/nfs/delegation.h3
-rw-r--r--fs/nfs/dir.c36
-rw-r--r--fs/nfs/export.c15
-rw-r--r--fs/nfs/file.c2
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c2
-rw-r--r--fs/nfs/fs_context.c66
-rw-r--r--fs/nfs/inode.c418
-rw-r--r--fs/nfs/internal.h2
-rw-r--r--fs/nfs/io.c2
-rw-r--r--fs/nfs/mount_clnt.c14
-rw-r--r--fs/nfs/nfs3acl.c2
-rw-r--r--fs/nfs/nfs3xdr.c5
-rw-r--r--fs/nfs/nfs42proc.c77
-rw-r--r--fs/nfs/nfs42xattr.c2
-rw-r--r--fs/nfs/nfs4file.c4
-rw-r--r--fs/nfs/nfs4proc.c264
-rw-r--r--fs/nfs/nfs4renewd.c6
-rw-r--r--fs/nfs/nfs4state.c8
-rw-r--r--fs/nfs/nfs4trace.h47
-rw-r--r--fs/nfs/nfs4xdr.c66
-rw-r--r--fs/nfs/nfstrace.c1
-rw-r--r--fs/nfs/nfstrace.h22
-rw-r--r--fs/nfs/pagelist.c4
-rw-r--r--fs/nfs/pnfs.c11
-rw-r--r--fs/nfs/proc.c1
-rw-r--r--fs/nfs/super.c6
-rw-r--r--fs/nfs/write.c7
-rw-r--r--fs/nfsd/Kconfig2
-rw-r--r--fs/nfsd/nfs4proc.c6
-rw-r--r--fs/nfsd/nfs4state.c415
-rw-r--r--fs/nfsd/nfs4xdr.c6
-rw-r--r--fs/nfsd/nfsctl.c1
-rw-r--r--fs/nfsd/nfssvc.c8
-rw-r--r--fs/nfsd/state.h3
-rw-r--r--fs/nfsd/xdr4.h6
-rw-r--r--fs/nilfs2/cpfile.c2
-rw-r--r--fs/nilfs2/ioctl.c4
-rw-r--r--fs/nilfs2/segment.c4
-rw-r--r--fs/nilfs2/the_nilfs.c2
-rw-r--r--fs/ocfs2/acl.c4
-rw-r--r--fs/ocfs2/acl.h4
-rw-r--r--fs/ocfs2/alloc.c4
-rw-r--r--fs/ocfs2/alloc.h4
-rw-r--r--fs/ocfs2/aops.c4
-rw-r--r--fs/ocfs2/aops.h4
-rw-r--r--fs/ocfs2/blockcheck.c4
-rw-r--r--fs/ocfs2/blockcheck.h4
-rw-r--r--fs/ocfs2/buffer_head_io.c4
-rw-r--r--fs/ocfs2/buffer_head_io.h4
-rw-r--r--fs/ocfs2/cluster/heartbeat.c4
-rw-r--r--fs/ocfs2/cluster/heartbeat.h4
-rw-r--r--fs/ocfs2/cluster/masklog.c4
-rw-r--r--fs/ocfs2/cluster/masklog.h4
-rw-r--r--fs/ocfs2/cluster/netdebug.c4
-rw-r--r--fs/ocfs2/cluster/nodemanager.c4
-rw-r--r--fs/ocfs2/cluster/nodemanager.h4
-rw-r--r--fs/ocfs2/cluster/ocfs2_heartbeat.h4
-rw-r--r--fs/ocfs2/cluster/ocfs2_nodemanager.h4
-rw-r--r--fs/ocfs2/cluster/quorum.c4
-rw-r--r--fs/ocfs2/cluster/quorum.h4
-rw-r--r--fs/ocfs2/cluster/sys.c4
-rw-r--r--fs/ocfs2/cluster/sys.h4
-rw-r--r--fs/ocfs2/cluster/tcp.c4
-rw-r--r--fs/ocfs2/cluster/tcp.h4
-rw-r--r--fs/ocfs2/cluster/tcp_internal.h4
-rw-r--r--fs/ocfs2/dcache.c4
-rw-r--r--fs/ocfs2/dcache.h4
-rw-r--r--fs/ocfs2/dir.c4
-rw-r--r--fs/ocfs2/dir.h4
-rw-r--r--fs/ocfs2/dlm/dlmapi.h4
-rw-r--r--fs/ocfs2/dlm/dlmast.c4
-rw-r--r--fs/ocfs2/dlm/dlmcommon.h4
-rw-r--r--fs/ocfs2/dlm/dlmconvert.c4
-rw-r--r--fs/ocfs2/dlm/dlmconvert.h4
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c4
-rw-r--r--fs/ocfs2/dlm/dlmdebug.h4
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c4
-rw-r--r--fs/ocfs2/dlm/dlmdomain.h4
-rw-r--r--fs/ocfs2/dlm/dlmlock.c4
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c4
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c4
-rw-r--r--fs/ocfs2/dlm/dlmthread.c4
-rw-r--r--fs/ocfs2/dlm/dlmunlock.c4
-rw-r--r--fs/ocfs2/dlmfs/dlmfs.c4
-rw-r--r--fs/ocfs2/dlmfs/userdlm.c4
-rw-r--r--fs/ocfs2/dlmfs/userdlm.h4
-rw-r--r--fs/ocfs2/dlmglue.c4
-rw-r--r--fs/ocfs2/dlmglue.h4
-rw-r--r--fs/ocfs2/export.c4
-rw-r--r--fs/ocfs2/export.h4
-rw-r--r--fs/ocfs2/extent_map.c4
-rw-r--r--fs/ocfs2/extent_map.h4
-rw-r--r--fs/ocfs2/file.c4
-rw-r--r--fs/ocfs2/file.h4
-rw-r--r--fs/ocfs2/filecheck.c4
-rw-r--r--fs/ocfs2/filecheck.h4
-rw-r--r--fs/ocfs2/heartbeat.c4
-rw-r--r--fs/ocfs2/heartbeat.h4
-rw-r--r--fs/ocfs2/inode.c4
-rw-r--r--fs/ocfs2/inode.h4
-rw-r--r--fs/ocfs2/journal.c4
-rw-r--r--fs/ocfs2/journal.h4
-rw-r--r--fs/ocfs2/localalloc.c4
-rw-r--r--fs/ocfs2/localalloc.h4
-rw-r--r--fs/ocfs2/locks.c4
-rw-r--r--fs/ocfs2/locks.h4
-rw-r--r--fs/ocfs2/mmap.c4
-rw-r--r--fs/ocfs2/move_extents.c4
-rw-r--r--fs/ocfs2/move_extents.h4
-rw-r--r--fs/ocfs2/namei.c4
-rw-r--r--fs/ocfs2/namei.h4
-rw-r--r--fs/ocfs2/ocfs1_fs_compat.h4
-rw-r--r--fs/ocfs2/ocfs2.h4
-rw-r--r--fs/ocfs2/ocfs2_fs.h4
-rw-r--r--fs/ocfs2/ocfs2_ioctl.h4
-rw-r--r--fs/ocfs2/ocfs2_lockid.h4
-rw-r--r--fs/ocfs2/ocfs2_lockingver.h4
-rw-r--r--fs/ocfs2/refcounttree.c4
-rw-r--r--fs/ocfs2/refcounttree.h4
-rw-r--r--fs/ocfs2/reservations.c4
-rw-r--r--fs/ocfs2/reservations.h4
-rw-r--r--fs/ocfs2/resize.c4
-rw-r--r--fs/ocfs2/resize.h4
-rw-r--r--fs/ocfs2/slot_map.c4
-rw-r--r--fs/ocfs2/slot_map.h4
-rw-r--r--fs/ocfs2/stack_o2cb.c4
-rw-r--r--fs/ocfs2/stack_user.c4
-rw-r--r--fs/ocfs2/stackglue.c4
-rw-r--r--fs/ocfs2/stackglue.h4
-rw-r--r--fs/ocfs2/suballoc.c4
-rw-r--r--fs/ocfs2/suballoc.h4
-rw-r--r--fs/ocfs2/super.c4
-rw-r--r--fs/ocfs2/super.h4
-rw-r--r--fs/ocfs2/symlink.c4
-rw-r--r--fs/ocfs2/symlink.h4
-rw-r--r--fs/ocfs2/sysfile.c4
-rw-r--r--fs/ocfs2/sysfile.h4
-rw-r--r--fs/ocfs2/uptodate.c4
-rw-r--r--fs/ocfs2/uptodate.h4
-rw-r--r--fs/ocfs2/xattr.c4
-rw-r--r--fs/ocfs2/xattr.h4
-rw-r--r--fs/proc/generic.c13
-rw-r--r--fs/proc/inode.c18
-rw-r--r--fs/proc/proc_sysctl.c2
-rw-r--r--fs/proc/task_mmu.c3
-rw-r--r--fs/reiserfs/procfs.c10
-rw-r--r--fs/unicode/.gitignore4
-rw-r--r--fs/userfaultfd.c149
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c34
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c17
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c4
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h12
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_sb.c16
-rw-r--r--fs/xfs/scrub/agheader.c7
-rw-r--r--fs/xfs/scrub/fscounters.c40
-rw-r--r--fs/xfs/xfs_aops.c2
-rw-r--r--fs/xfs/xfs_fsops.c2
-rw-r--r--fs/xfs/xfs_inode_item.c8
-rw-r--r--fs/xfs/xfs_inode_item_recover.c6
-rw-r--r--fs/xfs/xfs_log.c10
-rw-r--r--fs/xfs/xfs_mount.c15
-rw-r--r--fs/xfs/xfs_mount.h6
-rw-r--r--fs/xfs/xfs_ondisk.h4
-rw-r--r--fs/xfs/xfs_reflink.c3
-rw-r--r--fs/xfs/xfs_trans.c10
-rw-r--r--fs/xfs/xfs_trans.h15
231 files changed, 2127 insertions, 1952 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 39def020a074..cdb99507ef33 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -583,7 +583,7 @@ static struct attribute *v9fs_attrs[] = {
NULL,
};
-static struct attribute_group v9fs_attr_group = {
+static const struct attribute_group v9fs_attr_group = {
.attrs = v9fs_attrs,
};
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 649f04f112dc..59c32c9b799f 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -86,8 +86,8 @@ int v9fs_file_open(struct inode *inode, struct file *file)
* to work.
*/
writeback_fid = v9fs_writeback_fid(file_dentry(file));
- if (IS_ERR(fid)) {
- err = PTR_ERR(fid);
+ if (IS_ERR(writeback_fid)) {
+ err = PTR_ERR(writeback_fid);
mutex_unlock(&v9inode->v_mutex);
goto out_error;
}
diff --git a/fs/Kconfig b/fs/Kconfig
index 97e7b77c9309..141a856c50e7 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -223,10 +223,13 @@ config TMPFS_INODE64
If unsure, say N.
+config ARCH_SUPPORTS_HUGETLBFS
+ def_bool n
+
config HUGETLBFS
bool "HugeTLB file system support"
depends on X86 || IA64 || SPARC64 || (S390 && 64BIT) || \
- SYS_SUPPORTS_HUGETLBFS || BROKEN
+ ARCH_SUPPORTS_HUGETLBFS || BROKEN
help
hugetlbfs is a filesystem backing for HugeTLB pages, based on
ramfs. For architectures that support it, say Y here and read
@@ -335,8 +338,8 @@ config NFS_COMMON
default y
config NFS_V4_2_SSC_HELPER
- tristate
- default y if NFS_V4=y || NFS_FS=y
+ bool
+ default y if NFS_V4_2
source "net/sunrpc/Kconfig"
source "fs/ceph/Kconfig"
diff --git a/fs/block_dev.c b/fs/block_dev.c
index a5244e08b6c8..b8abccd03e5d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -79,7 +79,7 @@ static void kill_bdev(struct block_device *bdev)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
- if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
+ if (mapping_empty(mapping))
return;
invalidate_bh_lrus();
@@ -1677,6 +1677,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
struct blk_plug plug;
+ size_t shorted = 0;
ssize_t ret;
if (bdev_read_only(I_BDEV(bd_inode)))
@@ -1694,12 +1695,17 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
return -EOPNOTSUPP;
- iov_iter_truncate(from, size - iocb->ki_pos);
+ size -= iocb->ki_pos;
+ if (iov_iter_count(from) > size) {
+ shorted = iov_iter_count(from) - size;
+ iov_iter_truncate(from, size);
+ }
blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
+ iov_iter_reexpand(from, iov_iter_count(from) + shorted);
blk_finish_plug(&plug);
return ret;
}
@@ -1711,13 +1717,21 @@ ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
loff_t pos = iocb->ki_pos;
+ size_t shorted = 0;
+ ssize_t ret;
if (pos >= size)
return 0;
size -= pos;
- iov_iter_truncate(to, size);
- return generic_file_read_iter(iocb, to);
+ if (iov_iter_count(to) > size) {
+ shorted = iov_iter_count(to) - size;
+ iov_iter_truncate(to, size);
+ }
+
+ ret = generic_file_read_iter(iocb, to);
+ iov_iter_reexpand(to, iov_iter_count(to) + shorted);
+ return ret;
}
EXPORT_SYMBOL_GPL(blkdev_read_iter);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 17f93fd28f7e..2bea01d23a5b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -591,16 +591,13 @@ static noinline int add_ra_bio_pages(struct inode *inode,
free_extent_map(em);
if (page->index == end_index) {
- char *userpage;
size_t zero_offset = offset_in_page(isize);
if (zero_offset) {
int zeros;
zeros = PAGE_SIZE - zero_offset;
- userpage = kmap_atomic(page);
- memset(userpage + zero_offset, 0, zeros);
+ memzero_page(page, zero_offset, zeros);
flush_dcache_page(page);
- kunmap_atomic(userpage);
}
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f2d1bb234377..074a78a202b8 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3421,15 +3421,12 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
}
if (page->index == last_byte >> PAGE_SHIFT) {
- char *userpage;
size_t zero_offset = offset_in_page(last_byte);
if (zero_offset) {
iosize = PAGE_SIZE - zero_offset;
- userpage = kmap_atomic(page);
- memset(userpage + zero_offset, 0, iosize);
+ memzero_page(page, zero_offset, iosize);
flush_dcache_page(page);
- kunmap_atomic(userpage);
}
}
begin_page_read(fs_info, page);
@@ -3438,14 +3435,11 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
u64 disk_bytenr;
if (cur >= last_byte) {
- char *userpage;
struct extent_state *cached = NULL;
iosize = PAGE_SIZE - pg_offset;
- userpage = kmap_atomic(page);
- memset(userpage + pg_offset, 0, iosize);
+ memzero_page(page, pg_offset, iosize);
flush_dcache_page(page);
- kunmap_atomic(userpage);
set_extent_uptodate(tree, cur, cur + iosize - 1,
&cached, GFP_NOFS);
unlock_extent_cached(tree, cur,
@@ -3528,13 +3522,10 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
/* we've found a hole, just zero and go on */
if (block_start == EXTENT_MAP_HOLE) {
- char *userpage;
struct extent_state *cached = NULL;
- userpage = kmap_atomic(page);
- memset(userpage + pg_offset, 0, iosize);
+ memzero_page(page, pg_offset, iosize);
flush_dcache_page(page);
- kunmap_atomic(userpage);
set_extent_uptodate(tree, cur, cur + iosize - 1,
&cached, GFP_NOFS);
@@ -3845,12 +3836,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
}
if (page->index == end_index) {
- char *userpage;
-
- userpage = kmap_atomic(page);
- memset(userpage + pg_offset, 0,
- PAGE_SIZE - pg_offset);
- kunmap_atomic(userpage);
+ memzero_page(page, pg_offset, PAGE_SIZE - pg_offset);
flush_dcache_page(page);
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b21d491b3adc..4af336008b12 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -646,17 +646,12 @@ again:
if (!ret) {
unsigned long offset = offset_in_page(total_compressed);
struct page *page = pages[nr_pages - 1];
- char *kaddr;
/* zero the tail end of the last page, we might be
* sending it down to disk
*/
- if (offset) {
- kaddr = kmap_atomic(page);
- memset(kaddr + offset, 0,
- PAGE_SIZE - offset);
- kunmap_atomic(kaddr);
- }
+ if (offset)
+ memzero_page(page, offset, PAGE_SIZE - offset);
will_compress = 1;
}
}
@@ -4833,7 +4828,6 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
- char *kaddr;
bool only_release_metadata = false;
u32 blocksize = fs_info->sectorsize;
pgoff_t index = from >> PAGE_SHIFT;
@@ -4925,15 +4919,13 @@ again:
if (offset != blocksize) {
if (!len)
len = blocksize - offset;
- kaddr = kmap(page);
if (front)
- memset(kaddr + (block_start - page_offset(page)),
- 0, offset);
+ memzero_page(page, (block_start - page_offset(page)),
+ offset);
else
- memset(kaddr + (block_start - page_offset(page)) + offset,
- 0, len);
+ memzero_page(page, (block_start - page_offset(page)) + offset,
+ len);
flush_dcache_page(page);
- kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
@@ -6832,11 +6824,9 @@ static noinline int uncompress_inline(struct btrfs_path *path,
* cover that region here.
*/
- if (max_size + pg_offset < PAGE_SIZE) {
- char *map = kmap(page);
- memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset);
- kunmap(page);
- }
+ if (max_size + pg_offset < PAGE_SIZE)
+ memzero_page(page, pg_offset + max_size,
+ PAGE_SIZE - max_size - pg_offset);
kfree(tmp);
return ret;
}
@@ -8506,7 +8496,6 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
- char *kaddr;
unsigned long zero_start;
loff_t size;
vm_fault_t ret;
@@ -8620,10 +8609,8 @@ again:
zero_start = PAGE_SIZE;
if (zero_start != PAGE_SIZE) {
- kaddr = kmap(page);
- memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start);
+ memzero_page(page, zero_start, PAGE_SIZE - zero_start);
flush_dcache_page(page);
- kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index f4ec06b53aa0..3928ecc40d7b 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -129,12 +129,8 @@ static int copy_inline_to_page(struct btrfs_inode *inode,
* So what's in the range [500, 4095] corresponds to zeroes.
*/
if (datal < block_size) {
- char *map;
-
- map = kmap(page);
- memset(map + datal, 0, block_size - datal);
+ memzero_page(page, datal, block_size - datal);
flush_dcache_page(page);
- kunmap(page);
}
SetPageUptodate(page);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index d524acf7b3e5..c3fa7d3fa770 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -375,7 +375,6 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
unsigned long bytes_left;
unsigned long total_out = 0;
unsigned long pg_offset = 0;
- char *kaddr;
destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes_left = destlen;
@@ -455,9 +454,7 @@ next:
* end of the inline extent (destlen) to the end of the page
*/
if (pg_offset < destlen) {
- kaddr = kmap_atomic(dest_page);
- memset(kaddr + pg_offset, 0, destlen - pg_offset);
- kunmap_atomic(kaddr);
+ memzero_page(dest_page, pg_offset, destlen - pg_offset);
}
return ret;
}
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 8e9626d63976..3e26b466476a 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -631,7 +631,6 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in,
size_t ret2;
unsigned long total_out = 0;
unsigned long pg_offset = 0;
- char *kaddr;
stream = ZSTD_initDStream(
ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
@@ -696,9 +695,7 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in,
ret = 0;
finish:
if (pg_offset < destlen) {
- kaddr = kmap_atomic(dest_page);
- memset(kaddr + pg_offset, 0, destlen - pg_offset);
- kunmap_atomic(kaddr);
+ memzero_page(dest_page, pg_offset, destlen - pg_offset);
}
return ret;
}
diff --git a/fs/buffer.c b/fs/buffer.c
index c2e052c0fc5d..ea48c01fb76b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1260,6 +1260,15 @@ static void bh_lru_install(struct buffer_head *bh)
int i;
check_irqs_on();
+ /*
+ * the refcount of buffer_head in bh_lru prevents dropping the
+ * attached page(i.e., try_to_free_buffers) so it could cause
+ * failing page migration.
+ * Skip putting upcoming bh into bh_lru until migration is done.
+ */
+ if (lru_cache_disabled())
+ return;
+
bh_lru_lock();
b = this_cpu_ptr(&bh_lrus);
@@ -1400,6 +1409,15 @@ __bread_gfp(struct block_device *bdev, sector_t block,
}
EXPORT_SYMBOL(__bread_gfp);
+static void __invalidate_bh_lrus(struct bh_lru *b)
+{
+ int i;
+
+ for (i = 0; i < BH_LRU_SIZE; i++) {
+ brelse(b->bhs[i]);
+ b->bhs[i] = NULL;
+ }
+}
/*
* invalidate_bh_lrus() is called rarely - but not only at unmount.
* This doesn't race because it runs in each cpu either in irq
@@ -1408,16 +1426,12 @@ EXPORT_SYMBOL(__bread_gfp);
static void invalidate_bh_lru(void *arg)
{
struct bh_lru *b = &get_cpu_var(bh_lrus);
- int i;
- for (i = 0; i < BH_LRU_SIZE; i++) {
- brelse(b->bhs[i]);
- b->bhs[i] = NULL;
- }
+ __invalidate_bh_lrus(b);
put_cpu_var(bh_lrus);
}
-static bool has_bh_in_lru(int cpu, void *dummy)
+bool has_bh_in_lru(int cpu, void *dummy)
{
struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
int i;
@@ -1436,6 +1450,16 @@ void invalidate_bh_lrus(void)
}
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
+void invalidate_bh_lrus_cpu(int cpu)
+{
+ struct bh_lru *b;
+
+ bh_lru_lock();
+ b = per_cpu_ptr(&bh_lrus, cpu);
+ __invalidate_bh_lrus(b);
+ bh_lru_unlock();
+}
+
void set_bh_page(struct buffer_head *bh,
struct page *page, unsigned long offset)
{
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 471e40156065..94df854147d3 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -6,6 +6,7 @@ config CEPH_FS
select LIBCRC32C
select CRYPTO_AES
select CRYPTO
+ select NETFS_SUPPORT
default n
help
Choose Y or M here to include support for mounting the
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 26e66436f005..c1570fada3d8 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -12,6 +12,7 @@
#include <linux/signal.h>
#include <linux/iversion.h>
#include <linux/ktime.h>
+#include <linux/netfs.h>
#include "super.h"
#include "mds_client.h"
@@ -61,6 +62,9 @@
(CONGESTION_ON_THRESH(congestion_kb) - \
(CONGESTION_ON_THRESH(congestion_kb) >> 2))
+static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
+ struct page *page, void **_fsdata);
+
static inline struct ceph_snap_context *page_snap_context(struct page *page)
{
if (PagePrivate(page))
@@ -124,8 +128,7 @@ static int ceph_set_page_dirty(struct page *page)
* PagePrivate so that we get invalidatepage callback.
*/
BUG_ON(PagePrivate(page));
- page->private = (unsigned long)snapc;
- SetPagePrivate(page);
+ attach_page_private(page, snapc);
ret = __set_page_dirty_nobuffers(page);
WARN_ON(!PageLocked(page));
@@ -144,19 +147,19 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
{
struct inode *inode;
struct ceph_inode_info *ci;
- struct ceph_snap_context *snapc = page_snap_context(page);
+ struct ceph_snap_context *snapc;
+
+ wait_on_page_fscache(page);
inode = page->mapping->host;
ci = ceph_inode(inode);
- if (offset != 0 || length != PAGE_SIZE) {
+ if (offset != 0 || length != thp_size(page)) {
dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n",
inode, page, page->index, offset, length);
return;
}
- ceph_invalidate_fscache_page(inode, page);
-
WARN_ON(!PageLocked(page));
if (!PagePrivate(page))
return;
@@ -164,333 +167,222 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
dout("%p invalidatepage %p idx %lu full dirty page\n",
inode, page, page->index);
+ snapc = detach_page_private(page);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc);
- page->private = 0;
- ClearPagePrivate(page);
}
-static int ceph_releasepage(struct page *page, gfp_t g)
+static int ceph_releasepage(struct page *page, gfp_t gfp)
{
dout("%p releasepage %p idx %lu (%sdirty)\n", page->mapping->host,
page, page->index, PageDirty(page) ? "" : "not ");
- /* Can we release the page from the cache? */
- if (!ceph_release_fscache_page(page, g))
- return 0;
-
+ if (PageFsCache(page)) {
+ if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS))
+ return 0;
+ wait_on_page_fscache(page);
+ }
return !PagePrivate(page);
}
-/* read a single page, without unlocking it. */
-static int ceph_do_readpage(struct file *filp, struct page *page)
+static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq)
{
- struct inode *inode = file_inode(filp);
+ struct inode *inode = rreq->mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- struct ceph_osd_client *osdc = &fsc->client->osdc;
- struct ceph_osd_request *req;
- struct ceph_vino vino = ceph_vino(inode);
- int err = 0;
- u64 off = page_offset(page);
- u64 len = PAGE_SIZE;
-
- if (off >= i_size_read(inode)) {
- zero_user_segment(page, 0, PAGE_SIZE);
- SetPageUptodate(page);
- return 0;
- }
-
- if (ci->i_inline_version != CEPH_INLINE_NONE) {
- /*
- * Uptodate inline data should have been added
- * into page cache while getting Fcr caps.
- */
- if (off == 0)
- return -EINVAL;
- zero_user_segment(page, 0, PAGE_SIZE);
- SetPageUptodate(page);
- return 0;
- }
-
- err = ceph_readpage_from_fscache(inode, page);
- if (err == 0)
- return -EINPROGRESS;
-
- dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n",
- vino.ino, vino.snap, filp, off, len, page, page->index);
- req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len, 0, 1,
- CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, NULL,
- ci->i_truncate_seq, ci->i_truncate_size,
- false);
- if (IS_ERR(req))
- return PTR_ERR(req);
+ struct ceph_file_layout *lo = &ci->i_layout;
+ u32 blockoff;
+ u64 blockno;
- osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false);
+ /* Expand the start downward */
+ blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
+ rreq->start = blockno * lo->stripe_unit;
+ rreq->len += blockoff;
- err = ceph_osdc_start_request(osdc, req, false);
- if (!err)
- err = ceph_osdc_wait_request(osdc, req);
-
- ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
- req->r_end_latency, err);
-
- ceph_osdc_put_request(req);
- dout("readpage result %d\n", err);
-
- if (err == -ENOENT)
- err = 0;
- if (err < 0) {
- ceph_fscache_readpage_cancel(inode, page);
- if (err == -EBLOCKLISTED)
- fsc->blocklisted = true;
- goto out;
- }
- if (err < PAGE_SIZE)
- /* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_SIZE);
- else
- flush_dcache_page(page);
-
- SetPageUptodate(page);
- ceph_readpage_to_fscache(inode, page);
-
-out:
- return err < 0 ? err : 0;
+ /* Now, round up the length to the next block */
+ rreq->len = roundup(rreq->len, lo->stripe_unit);
}
-static int ceph_readpage(struct file *filp, struct page *page)
+static bool ceph_netfs_clamp_length(struct netfs_read_subrequest *subreq)
{
- int r = ceph_do_readpage(filp, page);
- if (r != -EINPROGRESS)
- unlock_page(page);
- else
- r = 0;
- return r;
+ struct inode *inode = subreq->rreq->mapping->host;
+ struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ u64 objno, objoff;
+ u32 xlen;
+
+ /* Truncate the extent at the end of the current block */
+ ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
+ &objno, &objoff, &xlen);
+ subreq->len = min(xlen, fsc->mount_options->rsize);
+ return true;
}
-/*
- * Finish an async read(ahead) op.
- */
-static void finish_read(struct ceph_osd_request *req)
+static void finish_netfs_read(struct ceph_osd_request *req)
{
- struct inode *inode = req->r_inode;
- struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- struct ceph_osd_data *osd_data;
- int rc = req->r_result <= 0 ? req->r_result : 0;
- int bytes = req->r_result >= 0 ? req->r_result : 0;
+ struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
+ struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
+ struct netfs_read_subrequest *subreq = req->r_priv;
int num_pages;
- int i;
+ int err = req->r_result;
- dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
- if (rc == -EBLOCKLISTED)
- ceph_inode_to_client(inode)->blocklisted = true;
+ ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency,
+ req->r_end_latency, err);
- /* unlock all pages, zeroing any data we didn't read */
- osd_data = osd_req_op_extent_osd_data(req, 0);
- BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
- num_pages = calc_pages_for((u64)osd_data->alignment,
- (u64)osd_data->length);
- for (i = 0; i < num_pages; i++) {
- struct page *page = osd_data->pages[i];
-
- if (rc < 0 && rc != -ENOENT) {
- ceph_fscache_readpage_cancel(inode, page);
- goto unlock;
- }
- if (bytes < (int)PAGE_SIZE) {
- /* zero (remainder of) page */
- int s = bytes < 0 ? 0 : bytes;
- zero_user_segment(page, s, PAGE_SIZE);
- }
- dout("finish_read %p uptodate %p idx %lu\n", inode, page,
- page->index);
- flush_dcache_page(page);
- SetPageUptodate(page);
- ceph_readpage_to_fscache(inode, page);
-unlock:
- unlock_page(page);
- put_page(page);
- bytes -= PAGE_SIZE;
- }
+ dout("%s: result %d subreq->len=%zu i_size=%lld\n", __func__, req->r_result,
+ subreq->len, i_size_read(req->r_inode));
- ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
- req->r_end_latency, rc);
+ /* no object means success but no data */
+ if (err == -ENOENT)
+ err = 0;
+ else if (err == -EBLOCKLISTED)
+ fsc->blocklisted = true;
+
+ if (err >= 0 && err < subreq->len)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+
+ netfs_subreq_terminated(subreq, err, true);
- kfree(osd_data->pages);
+ num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
+ ceph_put_page_vector(osd_data->pages, num_pages, false);
+ iput(req->r_inode);
}
-/*
- * start an async read(ahead) operation. return nr_pages we submitted
- * a read for on success, or negative error code.
- */
-static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx,
- struct list_head *page_list, int max)
+static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
{
- struct ceph_osd_client *osdc =
- &ceph_inode_to_client(inode)->client->osdc;
+ struct netfs_read_request *rreq = subreq->rreq;
+ struct inode *inode = rreq->mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct page *page = lru_to_page(page_list);
- struct ceph_vino vino;
+ struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_osd_request *req;
- u64 off;
- u64 len;
- int i;
+ struct ceph_vino vino = ceph_vino(inode);
+ struct iov_iter iter;
struct page **pages;
- pgoff_t next_index;
- int nr_pages = 0;
- int got = 0;
- int ret = 0;
-
- if (!rw_ctx) {
- /* caller of readpages does not hold buffer and read caps
- * (fadvise, madvise and readahead cases) */
- int want = CEPH_CAP_FILE_CACHE;
- ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want,
- true, &got);
- if (ret < 0) {
- dout("start_read %p, error getting cap\n", inode);
- } else if (!(got & want)) {
- dout("start_read %p, no cache cap\n", inode);
- ret = 0;
- }
- if (ret <= 0) {
- if (got)
- ceph_put_cap_refs(ci, got);
- while (!list_empty(page_list)) {
- page = lru_to_page(page_list);
- list_del(&page->lru);
- put_page(page);
- }
- return ret;
- }
- }
-
- off = (u64) page_offset(page);
+ size_t page_off;
+ int err = 0;
+ u64 len = subreq->len;
- /* count pages */
- next_index = page->index;
- list_for_each_entry_reverse(page, page_list, lru) {
- if (page->index != next_index)
- break;
- nr_pages++;
- next_index++;
- if (max && nr_pages == max)
- break;
- }
- len = nr_pages << PAGE_SHIFT;
- dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages,
- off, len);
- vino = ceph_vino(inode);
- req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
- 0, 1, CEPH_OSD_OP_READ,
- CEPH_OSD_FLAG_READ, NULL,
- ci->i_truncate_seq, ci->i_truncate_size,
- false);
+ req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
+ 0, 1, CEPH_OSD_OP_READ,
+ CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
+ NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
if (IS_ERR(req)) {
- ret = PTR_ERR(req);
+ err = PTR_ERR(req);
+ req = NULL;
goto out;
}
- /* build page vector */
- nr_pages = calc_pages_for(0, len);
- pages = kmalloc_array(nr_pages, sizeof(*pages), GFP_KERNEL);
- if (!pages) {
- ret = -ENOMEM;
- goto out_put;
- }
- for (i = 0; i < nr_pages; ++i) {
- page = list_entry(page_list->prev, struct page, lru);
- BUG_ON(PageLocked(page));
- list_del(&page->lru);
-
- dout("start_read %p adding %p idx %lu\n", inode, page,
- page->index);
- if (add_to_page_cache_lru(page, &inode->i_data, page->index,
- GFP_KERNEL)) {
- ceph_fscache_uncache_page(inode, page);
- put_page(page);
- dout("start_read %p add_to_page_cache failed %p\n",
- inode, page);
- nr_pages = i;
- if (nr_pages > 0) {
- len = nr_pages << PAGE_SHIFT;
- osd_req_op_extent_update(req, 0, len);
- break;
- }
- goto out_pages;
- }
- pages[i] = page;
+ dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
+ iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
+ err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
+ if (err < 0) {
+ dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
+ goto out;
}
+
+ /* should always give us a page-aligned read */
+ WARN_ON_ONCE(page_off);
+ len = err;
+
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
- req->r_callback = finish_read;
+ req->r_callback = finish_netfs_read;
+ req->r_priv = subreq;
req->r_inode = inode;
+ ihold(inode);
- dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len);
- ret = ceph_osdc_start_request(osdc, req, false);
- if (ret < 0)
- goto out_pages;
+ err = ceph_osdc_start_request(req->r_osdc, req, false);
+ if (err)
+ iput(inode);
+out:
ceph_osdc_put_request(req);
+ if (err)
+ netfs_subreq_terminated(subreq, err, false);
+ dout("%s: result %d\n", __func__, err);
+}
- /* After adding locked pages to page cache, the inode holds cache cap.
- * So we can drop our cap refs. */
- if (got)
- ceph_put_cap_refs(ci, got);
+static void ceph_init_rreq(struct netfs_read_request *rreq, struct file *file)
+{
+}
- return nr_pages;
+static void ceph_readahead_cleanup(struct address_space *mapping, void *priv)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ int got = (uintptr_t)priv;
-out_pages:
- for (i = 0; i < nr_pages; ++i) {
- ceph_fscache_readpage_cancel(inode, pages[i]);
- unlock_page(pages[i]);
- }
- ceph_put_page_vector(pages, nr_pages, false);
-out_put:
- ceph_osdc_put_request(req);
-out:
if (got)
ceph_put_cap_refs(ci, got);
- return ret;
}
+const struct netfs_read_request_ops ceph_netfs_read_ops = {
+ .init_rreq = ceph_init_rreq,
+ .is_cache_enabled = ceph_is_cache_enabled,
+ .begin_cache_operation = ceph_begin_cache_operation,
+ .issue_op = ceph_netfs_issue_op,
+ .expand_readahead = ceph_netfs_expand_readahead,
+ .clamp_length = ceph_netfs_clamp_length,
+ .check_write_begin = ceph_netfs_check_write_begin,
+ .cleanup = ceph_readahead_cleanup,
+};
-/*
- * Read multiple pages. Leave pages we don't read + unlock in page_list;
- * the caller (VM) cleans them up.
- */
-static int ceph_readpages(struct file *file, struct address_space *mapping,
- struct list_head *page_list, unsigned nr_pages)
+/* read a single page, without unlocking it. */
+static int ceph_readpage(struct file *file, struct page *page)
{
struct inode *inode = file_inode(file);
- struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- struct ceph_file_info *fi = file->private_data;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_vino vino = ceph_vino(inode);
+ u64 off = page_offset(page);
+ u64 len = thp_size(page);
+
+ if (ci->i_inline_version != CEPH_INLINE_NONE) {
+ /*
+ * Uptodate inline data should have been added
+ * into page cache while getting Fcr caps.
+ */
+ if (off == 0) {
+ unlock_page(page);
+ return -EINVAL;
+ }
+ zero_user_segment(page, 0, thp_size(page));
+ SetPageUptodate(page);
+ unlock_page(page);
+ return 0;
+ }
+
+ dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n",
+ vino.ino, vino.snap, file, off, len, page, page->index);
+
+ return netfs_readpage(file, page, &ceph_netfs_read_ops, NULL);
+}
+
+static void ceph_readahead(struct readahead_control *ractl)
+{
+ struct inode *inode = file_inode(ractl->file);
+ struct ceph_file_info *fi = ractl->file->private_data;
struct ceph_rw_context *rw_ctx;
- int rc = 0;
- int max = 0;
+ int got = 0;
+ int ret = 0;
if (ceph_inode(inode)->i_inline_version != CEPH_INLINE_NONE)
- return -EINVAL;
+ return;
- rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list,
- &nr_pages);
+ rw_ctx = ceph_find_rw_context(fi);
+ if (!rw_ctx) {
+ /*
+ * readahead callers do not necessarily hold Fcb caps
+ * (e.g. fadvise, madvise).
+ */
+ int want = CEPH_CAP_FILE_CACHE;
- if (rc == 0)
- goto out;
+ ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got);
+ if (ret < 0)
+ dout("start_read %p, error getting cap\n", inode);
+ else if (!(got & want))
+ dout("start_read %p, no cache cap\n", inode);
- rw_ctx = ceph_find_rw_context(fi);
- max = fsc->mount_options->rsize >> PAGE_SHIFT;
- dout("readpages %p file %p ctx %p nr_pages %d max %d\n",
- inode, file, rw_ctx, nr_pages, max);
- while (!list_empty(page_list)) {
- rc = start_read(inode, rw_ctx, page_list, max);
- if (rc < 0)
- goto out;
+ if (ret <= 0)
+ return;
}
-out:
- ceph_fscache_readpages_cancel(inode, page_list);
-
- dout("readpages %p file %p ret %d\n", inode, file, rc);
- return rc;
+ netfs_readahead(ractl, &ceph_netfs_read_ops, (void *)(uintptr_t)got);
}
struct ceph_writeback_ctl
@@ -585,8 +477,8 @@ static u64 get_writepages_data_length(struct inode *inode,
spin_unlock(&ci->i_ceph_lock);
WARN_ON(!found);
}
- if (end > page_offset(page) + PAGE_SIZE)
- end = page_offset(page) + PAGE_SIZE;
+ if (end > page_offset(page) + thp_size(page))
+ end = page_offset(page) + thp_size(page);
return end > start ? end - start : 0;
}
@@ -604,7 +496,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
struct ceph_snap_context *snapc, *oldest;
loff_t page_off = page_offset(page);
int err;
- loff_t len = PAGE_SIZE;
+ loff_t len = thp_size(page);
struct ceph_writeback_ctl ceph_wbc;
struct ceph_osd_client *osdc = &fsc->client->osdc;
struct ceph_osd_request *req;
@@ -632,7 +524,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
/* is this a partial page at end of file? */
if (page_off >= ceph_wbc.i_size) {
dout("%p page eof %llu\n", page, ceph_wbc.i_size);
- page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE);
+ page->mapping->a_ops->invalidatepage(page, 0, thp_size(page));
return 0;
}
@@ -658,7 +550,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
}
/* it may be a short write due to an object boundary */
- WARN_ON_ONCE(len > PAGE_SIZE);
+ WARN_ON_ONCE(len > thp_size(page));
osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false);
dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
@@ -667,7 +559,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
if (!err)
err = ceph_osdc_wait_request(osdc, req);
- ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+ ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, err);
ceph_osdc_put_request(req);
@@ -695,8 +587,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
dout("writepage cleaned page %p\n", page);
err = 0; /* vfs expects us to return 0 */
}
- page->private = 0;
- ClearPagePrivate(page);
+ oldest = detach_page_private(page);
+ WARN_ON_ONCE(oldest != snapc);
end_page_writeback(page);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc); /* page's reference */
@@ -755,7 +647,7 @@ static void writepages_finish(struct ceph_osd_request *req)
ceph_clear_error_write(ci);
}
- ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+ ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, rc);
/*
@@ -788,11 +680,9 @@ static void writepages_finish(struct ceph_osd_request *req)
clear_bdi_congested(inode_to_bdi(inode),
BLK_RW_ASYNC);
- ceph_put_snap_context(page_snap_context(page));
- page->private = 0;
- ClearPagePrivate(page);
- dout("unlocking %p\n", page);
+ ceph_put_snap_context(detach_page_private(page));
end_page_writeback(page);
+ dout("unlocking %p\n", page);
if (remove_page)
generic_error_remove_page(inode->i_mapping,
@@ -949,7 +839,7 @@ get_more_pages:
page_offset(page) >= i_size_read(inode)) &&
clear_page_dirty_for_io(page))
mapping->a_ops->invalidatepage(page,
- 0, PAGE_SIZE);
+ 0, thp_size(page));
unlock_page(page);
continue;
}
@@ -1038,7 +928,7 @@ get_more_pages:
pages[locked_pages++] = page;
pvec.pages[i] = NULL;
- len += PAGE_SIZE;
+ len += thp_size(page);
}
/* did we get anything? */
@@ -1087,7 +977,7 @@ new_request:
BUG_ON(IS_ERR(req));
}
BUG_ON(len < page_offset(pages[locked_pages - 1]) +
- PAGE_SIZE - offset);
+ thp_size(page) - offset);
req->r_callback = writepages_finish;
req->r_inode = inode;
@@ -1117,7 +1007,7 @@ new_request:
}
set_page_writeback(pages[i]);
- len += PAGE_SIZE;
+ len += thp_size(page);
}
if (ceph_wbc.size_stable) {
@@ -1126,7 +1016,7 @@ new_request:
/* writepages_finish() clears writeback pages
* according to the data length, so make sure
* data length covers all locked pages */
- u64 min_len = len + 1 - PAGE_SIZE;
+ u64 min_len = len + 1 - thp_size(page);
len = get_writepages_data_length(inode, pages[i - 1],
offset);
len = max(len, min_len);
@@ -1302,6 +1192,31 @@ ceph_find_incompatible(struct page *page)
return NULL;
}
+static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
+ struct page *page, void **_fsdata)
+{
+ struct inode *inode = file_inode(file);
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_snap_context *snapc;
+
+ snapc = ceph_find_incompatible(page);
+ if (snapc) {
+ int r;
+
+ unlock_page(page);
+ put_page(page);
+ if (IS_ERR(snapc))
+ return PTR_ERR(snapc);
+
+ ceph_queue_writeback(inode);
+ r = wait_event_killable(ci->i_cap_wq,
+ context_is_writeable_or_written(inode, snapc));
+ ceph_put_snap_context(snapc);
+ return r == 0 ? -EAGAIN : r;
+ }
+ return 0;
+}
+
/*
* We are only allowed to write into/dirty the page if the page is
* clean, or already dirty within the same snap context.
@@ -1312,75 +1227,47 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_snap_context *snapc;
struct page *page = NULL;
pgoff_t index = pos >> PAGE_SHIFT;
- int pos_in_page = pos & ~PAGE_MASK;
- int r = 0;
+ int r;
- dout("write_begin file %p inode %p page %p %d~%d\n", file, inode, page, (int)pos, (int)len);
-
- for (;;) {
+ /*
+ * Uninlining should have already been done and everything updated, EXCEPT
+ * for inline_version sent to the MDS.
+ */
+ if (ci->i_inline_version != CEPH_INLINE_NONE) {
page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page) {
- r = -ENOMEM;
- break;
- }
-
- snapc = ceph_find_incompatible(page);
- if (snapc) {
- if (IS_ERR(snapc)) {
- r = PTR_ERR(snapc);
- break;
- }
- unlock_page(page);
- put_page(page);
- page = NULL;
- ceph_queue_writeback(inode);
- r = wait_event_killable(ci->i_cap_wq,
- context_is_writeable_or_written(inode, snapc));
- ceph_put_snap_context(snapc);
- if (r != 0)
- break;
- continue;
- }
-
- if (PageUptodate(page)) {
- dout(" page %p already uptodate\n", page);
- break;
- }
+ if (!page)
+ return -ENOMEM;
/*
- * In some cases we don't need to read at all:
- * - full page write
- * - write that lies completely beyond EOF
- * - write that covers the the page from start to EOF or beyond it
+ * The inline_version on a new inode is set to 1. If that's the
+ * case, then the page is brand new and isn't yet Uptodate.
*/
- if ((pos_in_page == 0 && len == PAGE_SIZE) ||
- (pos >= i_size_read(inode)) ||
- (pos_in_page == 0 && (pos + len) >= i_size_read(inode))) {
- zero_user_segments(page, 0, pos_in_page,
- pos_in_page + len, PAGE_SIZE);
- break;
+ r = 0;
+ if (index == 0 && ci->i_inline_version != 1) {
+ if (!PageUptodate(page)) {
+ WARN_ONCE(1, "ceph: write_begin called on still-inlined inode (inline_version %llu)!\n",
+ ci->i_inline_version);
+ r = -EINVAL;
+ }
+ goto out;
}
-
- /*
- * We need to read it. If we get back -EINPROGRESS, then the page was
- * handed off to fscache and it will be unlocked when the read completes.
- * Refind the page in that case so we can reacquire the page lock. Otherwise
- * we got a hard error or the read was completed synchronously.
- */
- r = ceph_do_readpage(file, page);
- if (r != -EINPROGRESS)
- break;
+ zero_user_segment(page, 0, thp_size(page));
+ SetPageUptodate(page);
+ goto out;
}
+ r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &page, NULL,
+ &ceph_netfs_read_ops, NULL);
+out:
+ if (r == 0)
+ wait_on_page_fscache(page);
if (r < 0) {
- if (page) {
- unlock_page(page);
+ if (page)
put_page(page);
- }
} else {
+ WARN_ON_ONCE(!PageLocked(page));
*pagep = page;
}
return r;
@@ -1438,7 +1325,7 @@ static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter)
const struct address_space_operations ceph_aops = {
.readpage = ceph_readpage,
- .readpages = ceph_readpages,
+ .readahead = ceph_readahead,
.writepage = ceph_writepage,
.writepages = ceph_writepages_start,
.write_begin = ceph_write_begin,
@@ -1470,7 +1357,6 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
struct inode *inode = file_inode(vma->vm_file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = vma->vm_file->private_data;
- struct page *pinned_page = NULL;
loff_t off = (loff_t)vmf->pgoff << PAGE_SHIFT;
int want, got, err;
sigset_t oldset;
@@ -1478,21 +1364,20 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
ceph_block_sigs(&oldset);
- dout("filemap_fault %p %llx.%llx %llu~%zd trying to get caps\n",
- inode, ceph_vinop(inode), off, (size_t)PAGE_SIZE);
+ dout("filemap_fault %p %llx.%llx %llu trying to get caps\n",
+ inode, ceph_vinop(inode), off);
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_CACHE;
got = 0;
- err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_RD, want, -1,
- &got, &pinned_page);
+ err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_RD, want, -1, &got);
if (err < 0)
goto out_restore;
- dout("filemap_fault %p %llu~%zd got cap refs on %s\n",
- inode, off, (size_t)PAGE_SIZE, ceph_cap_string(got));
+ dout("filemap_fault %p %llu got cap refs on %s\n",
+ inode, off, ceph_cap_string(got));
if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
ci->i_inline_version == CEPH_INLINE_NONE) {
@@ -1500,14 +1385,11 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
ceph_add_rw_context(fi, &rw_ctx);
ret = filemap_fault(vmf);
ceph_del_rw_context(fi, &rw_ctx);
- dout("filemap_fault %p %llu~%zd drop cap refs %s ret %x\n",
- inode, off, (size_t)PAGE_SIZE,
- ceph_cap_string(got), ret);
+ dout("filemap_fault %p %llu drop cap refs %s ret %x\n",
+ inode, off, ceph_cap_string(got), ret);
} else
err = -EAGAIN;
- if (pinned_page)
- put_page(pinned_page);
ceph_put_cap_refs(ci, got);
if (err != -EAGAIN)
@@ -1542,8 +1424,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
vmf->page = page;
ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
out_inline:
- dout("filemap_fault %p %llu~%zd read inline data ret %x\n",
- inode, off, (size_t)PAGE_SIZE, ret);
+ dout("filemap_fault %p %llu read inline data ret %x\n",
+ inode, off, ret);
}
out_restore:
ceph_restore_sigs(&oldset);
@@ -1553,9 +1435,6 @@ out_restore:
return ret;
}
-/*
- * Reuse write_begin here for simplicity.
- */
static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
@@ -1591,10 +1470,10 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
goto out_free;
}
- if (off + PAGE_SIZE <= size)
- len = PAGE_SIZE;
+ if (off + thp_size(page) <= size)
+ len = thp_size(page);
else
- len = size & ~PAGE_MASK;
+ len = offset_in_thp(page, size);
dout("page_mkwrite %p %llx.%llx %llu~%zd getting caps i_size %llu\n",
inode, ceph_vinop(inode), off, len, size);
@@ -1604,8 +1483,7 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
want = CEPH_CAP_FILE_BUFFER;
got = 0;
- err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_WR, want, off + len,
- &got, NULL);
+ err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_WR, want, off + len, &got);
if (err < 0)
goto out_free;
@@ -1832,7 +1710,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, req);
- ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+ ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, err);
out_put:
@@ -2057,6 +1935,10 @@ int ceph_pool_perm_check(struct inode *inode, int need)
s64 pool;
int ret, flags;
+ /* Only need to do this for regular files */
+ if (!S_ISREG(inode->i_mode))
+ return 0;
+
if (ci->i_vino.snap != CEPH_NOSNAP) {
/*
* Pool permission check needs to write to the first object.
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 2f5cb6bc78e1..9cfadbb86568 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -173,7 +173,6 @@ void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
ci->fscache = NULL;
- fscache_uncache_all_inode_pages(cookie, &ci->vfs_inode);
fscache_relinquish_cookie(cookie, &ci->i_vino, false);
}
@@ -194,7 +193,6 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
dout("fscache_file_set_cookie %p %p disabling cache\n",
inode, filp);
fscache_disable_cookie(ci->fscache, &ci->i_vino, false);
- fscache_uncache_all_inode_pages(ci->fscache, inode);
} else {
fscache_enable_cookie(ci->fscache, &ci->i_vino, i_size_read(inode),
ceph_fscache_can_enable, inode);
@@ -205,108 +203,6 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
}
}
-static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error)
-{
- if (!error)
- SetPageUptodate(page);
-
- unlock_page(page);
-}
-
-static inline bool cache_valid(struct ceph_inode_info *ci)
-{
- return ci->i_fscache_gen == ci->i_rdcache_gen;
-}
-
-
-/* Atempt to read from the fscache,
- *
- * This function is called from the readpage_nounlock context. DO NOT attempt to
- * unlock the page here (or in the callback).
- */
-int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
-{
- struct ceph_inode_info *ci = ceph_inode(inode);
- int ret;
-
- if (!cache_valid(ci))
- return -ENOBUFS;
-
- ret = fscache_read_or_alloc_page(ci->fscache, page,
- ceph_readpage_from_fscache_complete, NULL,
- GFP_KERNEL);
-
- switch (ret) {
- case 0: /* Page found */
- dout("page read submitted\n");
- return 0;
- case -ENOBUFS: /* Pages were not found, and can't be */
- case -ENODATA: /* Pages were not found */
- dout("page/inode not in cache\n");
- return ret;
- default:
- dout("%s: unknown error ret = %i\n", __func__, ret);
- return ret;
- }
-}
-
-int ceph_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
-{
- struct ceph_inode_info *ci = ceph_inode(inode);
- int ret;
-
- if (!cache_valid(ci))
- return -ENOBUFS;
-
- ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
- ceph_readpage_from_fscache_complete,
- NULL, mapping_gfp_mask(mapping));
-
- switch (ret) {
- case 0: /* All pages found */
- dout("all-page read submitted\n");
- return 0;
- case -ENOBUFS: /* Some pages were not found, and can't be */
- case -ENODATA: /* some pages were not found */
- dout("page/inode not in cache\n");
- return ret;
- default:
- dout("%s: unknown error ret = %i\n", __func__, ret);
- return ret;
- }
-}
-
-void ceph_readpage_to_fscache(struct inode *inode, struct page *page)
-{
- struct ceph_inode_info *ci = ceph_inode(inode);
- int ret;
-
- if (!PageFsCache(page))
- return;
-
- if (!cache_valid(ci))
- return;
-
- ret = fscache_write_page(ci->fscache, page, i_size_read(inode),
- GFP_KERNEL);
- if (ret)
- fscache_uncache_page(ci->fscache, page);
-}
-
-void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
-{
- struct ceph_inode_info *ci = ceph_inode(inode);
-
- if (!PageFsCache(page))
- return;
-
- fscache_wait_on_page_write(ci->fscache, page);
- fscache_uncache_page(ci->fscache, page);
-}
-
void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
{
if (fscache_cookie_valid(fsc->fscache)) {
@@ -329,24 +225,3 @@ void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
}
fsc->fscache = NULL;
}
-
-/*
- * caller should hold CEPH_CAP_FILE_{RD,CACHE}
- */
-void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
-{
- if (cache_valid(ci))
- return;
-
- /* resue i_truncate_mutex. There should be no pending
- * truncate while the caller holds CEPH_CAP_FILE_RD */
- mutex_lock(&ci->i_truncate_mutex);
- if (!cache_valid(ci)) {
- if (fscache_check_consistency(ci->fscache, &ci->i_vino))
- fscache_invalidate(ci->fscache);
- spin_lock(&ci->i_ceph_lock);
- ci->i_fscache_gen = ci->i_rdcache_gen;
- spin_unlock(&ci->i_ceph_lock);
- }
- mutex_unlock(&ci->i_truncate_mutex);
-}
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 89dbdd1eb14a..1409d6149281 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -9,6 +9,8 @@
#ifndef _CEPH_CACHE_H
#define _CEPH_CACHE_H
+#include <linux/netfs.h>
+
#ifdef CONFIG_CEPH_FSCACHE
extern struct fscache_netfs ceph_cache_netfs;
@@ -29,54 +31,37 @@ int ceph_readpages_from_fscache(struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages);
-void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
-void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
{
ci->fscache = NULL;
- ci->i_fscache_gen = 0;
}
-static inline void ceph_fscache_invalidate(struct inode *inode)
+static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci)
{
- fscache_invalidate(ceph_inode(inode)->fscache);
+ return ci->fscache;
}
-static inline void ceph_fscache_uncache_page(struct inode *inode,
- struct page *page)
+static inline void ceph_fscache_invalidate(struct inode *inode)
{
- struct ceph_inode_info *ci = ceph_inode(inode);
- return fscache_uncache_page(ci->fscache, page);
+ fscache_invalidate(ceph_inode(inode)->fscache);
}
-static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
+static inline bool ceph_is_cache_enabled(struct inode *inode)
{
- struct inode* inode = page->mapping->host;
- struct ceph_inode_info *ci = ceph_inode(inode);
- return fscache_maybe_release_page(ci->fscache, page, gfp);
-}
+ struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(inode));
-static inline void ceph_fscache_readpage_cancel(struct inode *inode,
- struct page *page)
-{
- struct ceph_inode_info *ci = ceph_inode(inode);
- if (fscache_cookie_valid(ci->fscache) && PageFsCache(page))
- __fscache_uncache_page(ci->fscache, page);
+ if (!cookie)
+ return false;
+ return fscache_cookie_enabled(cookie);
}
-static inline void ceph_fscache_readpages_cancel(struct inode *inode,
- struct list_head *pages)
+static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq)
{
- struct ceph_inode_info *ci = ceph_inode(inode);
- return fscache_readpages_cancel(ci->fscache, pages);
-}
+ struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode));
-static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
-{
- ci->i_fscache_gen = ci->i_rdcache_gen - 1;
+ return fscache_begin_read_operation(rreq, cookie);
}
-
#else
static inline int ceph_fscache_register(void)
@@ -102,6 +87,11 @@ static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
{
}
+static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci)
+{
+ return NULL;
+}
+
static inline void ceph_fscache_register_inode_cookie(struct inode *inode)
{
}
@@ -115,62 +105,19 @@ static inline void ceph_fscache_file_set_cookie(struct inode *inode,
{
}
-static inline void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
-{
-}
-
-static inline void ceph_fscache_uncache_page(struct inode *inode,
- struct page *pages)
-{
-}
-
-static inline int ceph_readpage_from_fscache(struct inode* inode,
- struct page *page)
-{
- return -ENOBUFS;
-}
-
-static inline int ceph_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
-{
- return -ENOBUFS;
-}
-
-static inline void ceph_readpage_to_fscache(struct inode *inode,
- struct page *page)
-{
-}
-
static inline void ceph_fscache_invalidate(struct inode *inode)
{
}
-static inline void ceph_invalidate_fscache_page(struct inode *inode,
- struct page *page)
+static inline bool ceph_is_cache_enabled(struct inode *inode)
{
+ return false;
}
-static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
-{
- return 1;
-}
-
-static inline void ceph_fscache_readpage_cancel(struct inode *inode,
- struct page *page)
-{
-}
-
-static inline void ceph_fscache_readpages_cancel(struct inode *inode,
- struct list_head *pages)
-{
-}
-
-static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
+static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq)
{
+ return -ENOBUFS;
}
-
#endif
-#endif
+#endif /* _CEPH_CACHE_H */
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 3c03fa37cac4..a5e93b185515 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1390,7 +1390,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
arg->flush_tid = flush_tid;
arg->oldest_flush_tid = oldest_flush_tid;
- arg->size = inode->i_size;
+ arg->size = i_size_read(inode);
ci->i_reported_size = arg->size;
arg->max_size = ci->i_wanted_max_size;
if (cap == ci->i_auth_cap) {
@@ -1867,6 +1867,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
u32 invalidating_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
+ ceph_fscache_invalidate(inode);
invalidate_mapping_pages(&inode->i_data, 0, -1);
spin_lock(&ci->i_ceph_lock);
@@ -1884,7 +1885,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
bool __ceph_should_report_size(struct ceph_inode_info *ci)
{
- loff_t size = ci->vfs_inode.i_size;
+ loff_t size = i_size_read(&ci->vfs_inode);
/* mds will adjust max size according to the reported size */
if (ci->i_flushing_caps & CEPH_CAP_FILE_WR)
return false;
@@ -2730,10 +2731,6 @@ again:
*got = need | want;
else
*got = need;
- if (S_ISREG(inode->i_mode) &&
- (need & CEPH_CAP_FILE_RD) &&
- !(*got & CEPH_CAP_FILE_CACHE))
- ceph_disable_fscache_readpage(ci);
ceph_take_cap_refs(ci, *got, true);
ret = 1;
}
@@ -2858,8 +2855,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
* due to a small max_size, make sure we check_max_size (and possibly
* ask the mds) so we don't get hung up indefinitely.
*/
-int ceph_get_caps(struct file *filp, int need, int want,
- loff_t endoff, int *got, struct page **pinned_page)
+int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got)
{
struct ceph_file_info *fi = filp->private_data;
struct inode *inode = file_inode(filp);
@@ -2957,11 +2953,11 @@ int ceph_get_caps(struct file *filp, int need, int want,
struct page *page =
find_get_page(inode->i_mapping, 0);
if (page) {
- if (PageUptodate(page)) {
- *pinned_page = page;
- break;
- }
+ bool uptodate = PageUptodate(page);
+
put_page(page);
+ if (uptodate)
+ break;
}
/*
* drop cap refs first because getattr while
@@ -2983,11 +2979,6 @@ int ceph_get_caps(struct file *filp, int need, int want,
}
break;
}
-
- if (S_ISREG(ci->vfs_inode.i_mode) &&
- (_got & CEPH_CAP_FILE_RD) && (_got & CEPH_CAP_FILE_CACHE))
- ceph_fscache_revalidate_cookie(ci);
-
*got = _got;
return 0;
}
@@ -3308,7 +3299,7 @@ static void handle_cap_grant(struct inode *inode,
dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
inode, cap, session->s_mds, seq, ceph_cap_string(newcaps));
dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
- inode->i_size);
+ i_size_read(inode));
/*
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 66989c880adb..425f3356332a 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -162,34 +162,34 @@ static int metric_show(struct seq_file *s, void *p)
seq_printf(s, "item total avg_lat(us) min_lat(us) max_lat(us) stdev(us)\n");
seq_printf(s, "-----------------------------------------------------------------------------------\n");
- spin_lock(&m->read_latency_lock);
+ spin_lock(&m->read_metric_lock);
total = m->total_reads;
sum = m->read_latency_sum;
avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
min = m->read_latency_min;
max = m->read_latency_max;
sq = m->read_latency_sq_sum;
- spin_unlock(&m->read_latency_lock);
+ spin_unlock(&m->read_metric_lock);
CEPH_METRIC_SHOW("read", total, avg, min, max, sq);
- spin_lock(&m->write_latency_lock);
+ spin_lock(&m->write_metric_lock);
total = m->total_writes;
sum = m->write_latency_sum;
avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
min = m->write_latency_min;
max = m->write_latency_max;
sq = m->write_latency_sq_sum;
- spin_unlock(&m->write_latency_lock);
+ spin_unlock(&m->write_metric_lock);
CEPH_METRIC_SHOW("write", total, avg, min, max, sq);
- spin_lock(&m->metadata_latency_lock);
+ spin_lock(&m->metadata_metric_lock);
total = m->total_metadatas;
sum = m->metadata_latency_sum;
avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
min = m->metadata_latency_min;
max = m->metadata_latency_max;
sq = m->metadata_latency_sq_sum;
- spin_unlock(&m->metadata_latency_lock);
+ spin_unlock(&m->metadata_metric_lock);
CEPH_METRIC_SHOW("metadata", total, avg, min, max, sq);
seq_printf(s, "\n");
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index f7a790ed62c4..5624fae7a603 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -631,10 +631,12 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
switch (whence) {
case SEEK_CUR:
offset += file->f_pos;
+ break;
case SEEK_SET:
break;
case SEEK_END:
retval = -EOPNOTSUPP;
+ goto out;
default:
goto out;
}
@@ -665,8 +667,8 @@ out:
/*
* Handle lookups for the hidden .snap directory.
*/
-int ceph_handle_snapdir(struct ceph_mds_request *req,
- struct dentry *dentry, int err)
+struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
+ struct dentry *dentry, int err)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
struct inode *parent = d_inode(dentry->d_parent); /* we hold i_mutex */
@@ -674,18 +676,17 @@ int ceph_handle_snapdir(struct ceph_mds_request *req,
/* .snap dir? */
if (err == -ENOENT &&
ceph_snap(parent) == CEPH_NOSNAP &&
- strcmp(dentry->d_name.name,
- fsc->mount_options->snapdir_name) == 0) {
+ strcmp(dentry->d_name.name, fsc->mount_options->snapdir_name) == 0) {
+ struct dentry *res;
struct inode *inode = ceph_get_snapdir(parent);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
- dout("ENOENT on snapdir %p '%pd', linking to snapdir %p\n",
- dentry, dentry, inode);
- BUG_ON(!d_unhashed(dentry));
- d_add(dentry, inode);
- err = 0;
+
+ res = d_splice_alias(inode, dentry);
+ dout("ENOENT on snapdir %p '%pd', linking to snapdir %p. Spliced dentry %p\n",
+ dentry, dentry, inode, res);
+ if (res)
+ dentry = res;
}
- return err;
+ return dentry;
}
/*
@@ -741,6 +742,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_mds_request *req;
+ struct dentry *res;
int op;
int mask;
int err;
@@ -791,7 +793,13 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
req->r_parent = dir;
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
err = ceph_mdsc_do_request(mdsc, NULL, req);
- err = ceph_handle_snapdir(req, dentry, err);
+ res = ceph_handle_snapdir(req, dentry, err);
+ if (IS_ERR(res)) {
+ err = PTR_ERR(res);
+ } else {
+ dentry = res;
+ err = 0;
+ }
dentry = ceph_finish_lookup(req, dentry, err);
ceph_mdsc_put_request(req); /* will dput(dentry) */
dout("lookup result=%p\n", dentry);
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index f22156ee7306..65540a4429b2 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -129,6 +129,10 @@ static struct inode *__lookup_inode(struct super_block *sb, u64 ino)
vino.ino = ino;
vino.snap = CEPH_NOSNAP;
+
+ if (ceph_vino_is_reserved(vino))
+ return ERR_PTR(-ESTALE);
+
inode = ceph_find_inode(sb, vino);
if (!inode) {
struct ceph_mds_request *req;
@@ -178,8 +182,10 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
return ERR_CAST(inode);
/* We need LINK caps to reliably check i_nlink */
err = ceph_do_getattr(inode, CEPH_CAP_LINK_SHARED, false);
- if (err)
+ if (err) {
+ iput(inode);
return ERR_PTR(err);
+ }
/* -ESTALE if inode as been unlinked and no file is open */
if ((inode->i_nlink == 0) && (atomic_read(&inode->i_count) == 1)) {
iput(inode);
@@ -212,6 +218,10 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
vino.ino = sfh->ino;
vino.snap = sfh->snapid;
}
+
+ if (ceph_vino_is_reserved(vino))
+ return ERR_PTR(-ESTALE);
+
inode = ceph_find_inode(sb, vino);
if (inode)
return d_obtain_alias(inode);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 209535d5b8d3..77fc037d5beb 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -739,9 +739,12 @@ retry:
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
- err = ceph_handle_snapdir(req, dentry, err);
- if (err)
+ dentry = ceph_handle_snapdir(req, dentry, err);
+ if (IS_ERR(dentry)) {
+ err = PTR_ERR(dentry);
goto out_req;
+ }
+ err = 0;
if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
@@ -892,7 +895,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
if (!ret)
ret = ceph_osdc_wait_request(osdc, req);
- ceph_update_read_latency(&fsc->mdsc->metric,
+ ceph_update_read_metrics(&fsc->mdsc->metric,
req->r_start_latency,
req->r_end_latency,
ret);
@@ -1034,16 +1037,6 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
dout("ceph_aio_complete_req %p rc %d bytes %u\n",
inode, rc, osd_data->bvec_pos.iter.bi_size);
- /* r_start_latency == 0 means the request was not submitted */
- if (req->r_start_latency) {
- if (aio_req->write)
- ceph_update_write_latency(metric, req->r_start_latency,
- req->r_end_latency, rc);
- else
- ceph_update_read_latency(metric, req->r_start_latency,
- req->r_end_latency, rc);
- }
-
if (rc == -EOLDSNAPC) {
struct ceph_aio_work *aio_work;
BUG_ON(!aio_req->write);
@@ -1086,6 +1079,16 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
}
}
+ /* r_start_latency == 0 means the request was not submitted */
+ if (req->r_start_latency) {
+ if (aio_req->write)
+ ceph_update_write_metrics(metric, req->r_start_latency,
+ req->r_end_latency, rc);
+ else
+ ceph_update_read_metrics(metric, req->r_start_latency,
+ req->r_end_latency, rc);
+ }
+
put_bvecs(osd_data->bvec_pos.bvecs, osd_data->num_bvecs,
aio_req->should_dirty);
ceph_osdc_put_request(req);
@@ -1290,10 +1293,10 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
if (write)
- ceph_update_write_latency(metric, req->r_start_latency,
+ ceph_update_write_metrics(metric, req->r_start_latency,
req->r_end_latency, ret);
else
- ceph_update_read_latency(metric, req->r_start_latency,
+ ceph_update_read_metrics(metric, req->r_start_latency,
req->r_end_latency, ret);
size = i_size_read(inode);
@@ -1467,7 +1470,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
if (!ret)
ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
- ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+ ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, ret);
out:
ceph_osdc_put_request(req);
@@ -1510,7 +1513,6 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
size_t len = iov_iter_count(to);
struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
- struct page *pinned_page = NULL;
bool direct_lock = iocb->ki_flags & IOCB_DIRECT;
ssize_t ret;
int want, got = 0;
@@ -1529,8 +1531,7 @@ again:
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_CACHE;
- ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1,
- &got, &pinned_page);
+ ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1, &got);
if (ret < 0) {
if (iocb->ki_flags & IOCB_DIRECT)
ceph_end_io_direct(inode);
@@ -1571,10 +1572,6 @@ again:
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
- if (pinned_page) {
- put_page(pinned_page);
- pinned_page = NULL;
- }
ceph_put_cap_refs(ci, got);
if (direct_lock)
@@ -1753,8 +1750,7 @@ retry_snap:
else
want = CEPH_CAP_FILE_BUFFER;
got = 0;
- err = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, pos + count,
- &got, NULL);
+ err = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, pos + count, &got);
if (err < 0)
goto out;
@@ -2083,7 +2079,7 @@ static long ceph_fallocate(struct file *file, int mode,
else
want = CEPH_CAP_FILE_BUFFER;
- ret = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, endoff, &got, NULL);
+ ret = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, endoff, &got);
if (ret < 0)
goto unlock;
@@ -2121,7 +2117,7 @@ static int get_rd_wr_caps(struct file *src_filp, int *src_got,
retry_caps:
ret = ceph_get_caps(dst_filp, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER,
- dst_endoff, dst_got, NULL);
+ dst_endoff, dst_got);
if (ret < 0)
return ret;
@@ -2143,7 +2139,7 @@ retry_caps:
return ret;
}
ret = ceph_get_caps(src_filp, CEPH_CAP_FILE_RD,
- CEPH_CAP_FILE_SHARED, -1, src_got, NULL);
+ CEPH_CAP_FILE_SHARED, -1, src_got);
if (ret < 0)
return ret;
/*... drop src_ci caps too, and retry */
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 689e3ffd29d7..e1c63adb196d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -56,6 +56,9 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
{
struct inode *inode;
+ if (ceph_vino_is_reserved(vino))
+ return ERR_PTR(-EREMOTEIO);
+
inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare,
ceph_set_ino_cb, &vino);
if (!inode)
@@ -99,14 +102,15 @@ struct inode *ceph_get_snapdir(struct inode *parent)
inode->i_mtime = parent->i_mtime;
inode->i_ctime = parent->i_ctime;
inode->i_atime = parent->i_atime;
- inode->i_op = &ceph_snapdir_iops;
- inode->i_fop = &ceph_snapdir_fops;
- ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
ci->i_rbytes = 0;
ci->i_btime = ceph_inode(parent)->i_btime;
- if (inode->i_state & I_NEW)
+ if (inode->i_state & I_NEW) {
+ inode->i_op = &ceph_snapdir_iops;
+ inode->i_fop = &ceph_snapdir_fops;
+ ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
unlock_new_inode(inode);
+ }
return inode;
}
@@ -628,10 +632,11 @@ int ceph_fill_file_size(struct inode *inode, int issued,
{
struct ceph_inode_info *ci = ceph_inode(inode);
int queue_trunc = 0;
+ loff_t isize = i_size_read(inode);
if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
- (truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {
- dout("size %lld -> %llu\n", inode->i_size, size);
+ (truncate_seq == ci->i_truncate_seq && size > isize)) {
+ dout("size %lld -> %llu\n", isize, size);
if (size > 0 && S_ISDIR(inode->i_mode)) {
pr_err("fill_file_size non-zero size for directory\n");
size = 0;
@@ -925,6 +930,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
ci->i_rfiles = le64_to_cpu(info->rfiles);
ci->i_rsubdirs = le64_to_cpu(info->rsubdirs);
ci->i_dir_pin = iinfo->dir_pin;
+ ci->i_rsnaps = iinfo->rsnaps;
ceph_decode_timespec64(&ci->i_rctime, &info->rctime);
}
}
@@ -1818,7 +1824,7 @@ bool ceph_inode_set_size(struct inode *inode, loff_t size)
bool ret;
spin_lock(&ci->i_ceph_lock);
- dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
+ dout("set_size %p %llu -> %llu\n", inode, i_size_read(inode), size);
i_size_write(inode, size);
inode->i_blocks = calc_inode_blocks(size);
@@ -1894,6 +1900,7 @@ static void ceph_do_invalidate_pages(struct inode *inode)
orig_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
+ ceph_fscache_invalidate(inode);
if (invalidate_inode_pages2(inode->i_mapping) < 0) {
pr_err("invalidate_pages %p fails\n", inode);
}
@@ -2124,20 +2131,19 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
}
}
if (ia_valid & ATTR_SIZE) {
- dout("setattr %p size %lld -> %lld\n", inode,
- inode->i_size, attr->ia_size);
- if ((issued & CEPH_CAP_FILE_EXCL) &&
- attr->ia_size > inode->i_size) {
+ loff_t isize = i_size_read(inode);
+
+ dout("setattr %p size %lld -> %lld\n", inode, isize, attr->ia_size);
+ if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size > isize) {
i_size_write(inode, attr->ia_size);
inode->i_blocks = calc_inode_blocks(attr->ia_size);
ci->i_reported_size = attr->ia_size;
dirtied |= CEPH_CAP_FILE_EXCL;
ia_valid |= ATTR_MTIME;
} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
- attr->ia_size != inode->i_size) {
+ attr->ia_size != isize) {
req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
- req->r_args.setattr.old_size =
- cpu_to_le64(inode->i_size);
+ req->r_args.setattr.old_size = cpu_to_le64(isize);
mask |= CEPH_SETATTR_SIZE;
release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
@@ -2247,7 +2253,7 @@ int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
return err;
if ((attr->ia_valid & ATTR_SIZE) &&
- attr->ia_size > max(inode->i_size, fsc->max_file_size))
+ attr->ia_size > max(i_size_read(inode), fsc->max_file_size))
return -EFBIG;
if ((attr->ia_valid & ATTR_SIZE) &&
diff --git a/fs/ceph/io.c b/fs/ceph/io.c
index 97602ea92ff4..c456509b31c3 100644
--- a/fs/ceph/io.c
+++ b/fs/ceph/io.c
@@ -118,7 +118,7 @@ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
}
/**
- * ceph_end_io_direct - declare the file is being used for direct i/o
+ * ceph_start_io_direct - declare the file is being used for direct i/o
* @inode: file inode
*
* Declare that a direct I/O operation is about to start, and ensure
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d87bd852ed96..e5af591d3bd4 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -176,6 +176,13 @@ static int parse_reply_info_in(void **p, void *end,
memset(&info->snap_btime, 0, sizeof(info->snap_btime));
}
+ /* snapshot count, remains zero for v<=3 */
+ if (struct_v >= 4) {
+ ceph_decode_64_safe(p, end, info->rsnaps, bad);
+ } else {
+ info->rsnaps = 0;
+ }
+
*p = end;
} else {
if (features & CEPH_FEATURE_MDS_INLINE_DATA) {
@@ -214,7 +221,7 @@ static int parse_reply_info_in(void **p, void *end,
}
info->dir_pin = -ENODATA;
- /* info->snap_btime remains zero */
+ /* info->snap_btime and info->rsnaps remain zero */
}
return 0;
bad:
@@ -433,6 +440,13 @@ static int ceph_parse_deleg_inos(void **p, void *end,
ceph_decode_64_safe(p, end, start, bad);
ceph_decode_64_safe(p, end, len, bad);
+
+ /* Don't accept a delegation of system inodes */
+ if (start < CEPH_INO_SYSTEM_BASE) {
+ pr_warn_ratelimited("ceph: ignoring reserved inode range delegation (start=0x%llx len=0x%llx)\n",
+ start, len);
+ continue;
+ }
while (len--) {
int err = xa_insert(&s->s_delegated_inos, ino = start++,
DELEGATED_INO_AVAILABLE,
@@ -3306,7 +3320,7 @@ out_err:
/* kick calling process */
complete_request(mdsc, req);
- ceph_update_metadata_latency(&mdsc->metric, req->r_start_latency,
+ ceph_update_metadata_metrics(&mdsc->metric, req->r_start_latency,
req->r_end_latency, err);
out:
ceph_mdsc_put_request(req);
@@ -3780,7 +3794,7 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap,
rec.v1.cap_id = cpu_to_le64(cap->cap_id);
rec.v1.wanted = cpu_to_le32(__ceph_caps_wanted(ci));
rec.v1.issued = cpu_to_le32(cap->issued);
- rec.v1.size = cpu_to_le64(inode->i_size);
+ rec.v1.size = cpu_to_le64(i_size_read(inode));
ceph_encode_timespec64(&rec.v1.mtime, &inode->i_mtime);
ceph_encode_timespec64(&rec.v1.atime, &inode->i_atime);
rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index eaa7c5422116..15c11a0f2caf 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -88,6 +88,7 @@ struct ceph_mds_reply_info_in {
s32 dir_pin;
struct ceph_timespec btime;
struct ceph_timespec snap_btime;
+ u64 rsnaps;
u64 change_attr;
};
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 5ec94bd4c1de..28b6b42ad677 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -17,6 +17,9 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
struct ceph_metric_write_latency *write;
struct ceph_metric_metadata_latency *meta;
struct ceph_metric_dlease *dlease;
+ struct ceph_opened_files *files;
+ struct ceph_pinned_icaps *icaps;
+ struct ceph_opened_inodes *inodes;
struct ceph_client_metric *m = &mdsc->metric;
u64 nr_caps = atomic64_read(&m->total_caps);
struct ceph_msg *msg;
@@ -26,7 +29,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
s32 len;
len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write)
- + sizeof(*meta) + sizeof(*dlease);
+ + sizeof(*meta) + sizeof(*dlease) + sizeof(*files)
+ + sizeof(*icaps) + sizeof(*inodes);
msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
if (!msg) {
@@ -95,6 +99,38 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
dlease->total = cpu_to_le64(atomic64_read(&m->total_dentries));
items++;
+ sum = percpu_counter_sum(&m->total_inodes);
+
+ /* encode the opened files metric */
+ files = (struct ceph_opened_files *)(dlease + 1);
+ files->type = cpu_to_le32(CLIENT_METRIC_TYPE_OPENED_FILES);
+ files->ver = 1;
+ files->compat = 1;
+ files->data_len = cpu_to_le32(sizeof(*files) - 10);
+ files->opened_files = cpu_to_le64(atomic64_read(&m->opened_files));
+ files->total = cpu_to_le64(sum);
+ items++;
+
+ /* encode the pinned icaps metric */
+ icaps = (struct ceph_pinned_icaps *)(files + 1);
+ icaps->type = cpu_to_le32(CLIENT_METRIC_TYPE_PINNED_ICAPS);
+ icaps->ver = 1;
+ icaps->compat = 1;
+ icaps->data_len = cpu_to_le32(sizeof(*icaps) - 10);
+ icaps->pinned_icaps = cpu_to_le64(nr_caps);
+ icaps->total = cpu_to_le64(sum);
+ items++;
+
+ /* encode the opened inodes metric */
+ inodes = (struct ceph_opened_inodes *)(icaps + 1);
+ inodes->type = cpu_to_le32(CLIENT_METRIC_TYPE_OPENED_INODES);
+ inodes->ver = 1;
+ inodes->compat = 1;
+ inodes->data_len = cpu_to_le32(sizeof(*inodes) - 10);
+ inodes->opened_inodes = cpu_to_le64(percpu_counter_sum(&m->opened_inodes));
+ inodes->total = cpu_to_le64(sum);
+ items++;
+
put_unaligned_le32(items, &head->num);
msg->front.iov_len = len;
msg->hdr.version = cpu_to_le16(1);
@@ -183,21 +219,21 @@ int ceph_metric_init(struct ceph_client_metric *m)
if (ret)
goto err_i_caps_mis;
- spin_lock_init(&m->read_latency_lock);
+ spin_lock_init(&m->read_metric_lock);
m->read_latency_sq_sum = 0;
m->read_latency_min = KTIME_MAX;
m->read_latency_max = 0;
m->total_reads = 0;
m->read_latency_sum = 0;
- spin_lock_init(&m->write_latency_lock);
+ spin_lock_init(&m->write_metric_lock);
m->write_latency_sq_sum = 0;
m->write_latency_min = KTIME_MAX;
m->write_latency_max = 0;
m->total_writes = 0;
m->write_latency_sum = 0;
- spin_lock_init(&m->metadata_latency_lock);
+ spin_lock_init(&m->metadata_metric_lock);
m->metadata_latency_sq_sum = 0;
m->metadata_latency_min = KTIME_MAX;
m->metadata_latency_max = 0;
@@ -274,7 +310,7 @@ static inline void __update_latency(ktime_t *totalp, ktime_t *lsump,
*sq_sump += sq;
}
-void ceph_update_read_latency(struct ceph_client_metric *m,
+void ceph_update_read_metrics(struct ceph_client_metric *m,
ktime_t r_start, ktime_t r_end,
int rc)
{
@@ -283,14 +319,14 @@ void ceph_update_read_latency(struct ceph_client_metric *m,
if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT))
return;
- spin_lock(&m->read_latency_lock);
+ spin_lock(&m->read_metric_lock);
__update_latency(&m->total_reads, &m->read_latency_sum,
&m->read_latency_min, &m->read_latency_max,
&m->read_latency_sq_sum, lat);
- spin_unlock(&m->read_latency_lock);
+ spin_unlock(&m->read_metric_lock);
}
-void ceph_update_write_latency(struct ceph_client_metric *m,
+void ceph_update_write_metrics(struct ceph_client_metric *m,
ktime_t r_start, ktime_t r_end,
int rc)
{
@@ -299,14 +335,14 @@ void ceph_update_write_latency(struct ceph_client_metric *m,
if (unlikely(rc && rc != -ETIMEDOUT))
return;
- spin_lock(&m->write_latency_lock);
+ spin_lock(&m->write_metric_lock);
__update_latency(&m->total_writes, &m->write_latency_sum,
&m->write_latency_min, &m->write_latency_max,
&m->write_latency_sq_sum, lat);
- spin_unlock(&m->write_latency_lock);
+ spin_unlock(&m->write_metric_lock);
}
-void ceph_update_metadata_latency(struct ceph_client_metric *m,
+void ceph_update_metadata_metrics(struct ceph_client_metric *m,
ktime_t r_start, ktime_t r_end,
int rc)
{
@@ -315,9 +351,9 @@ void ceph_update_metadata_latency(struct ceph_client_metric *m,
if (unlikely(rc && rc != -ENOENT))
return;
- spin_lock(&m->metadata_latency_lock);
+ spin_lock(&m->metadata_metric_lock);
__update_latency(&m->total_metadatas, &m->metadata_latency_sum,
&m->metadata_latency_min, &m->metadata_latency_max,
&m->metadata_latency_sq_sum, lat);
- spin_unlock(&m->metadata_latency_lock);
+ spin_unlock(&m->metadata_metric_lock);
}
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index af6038ff39d4..e984eb2bb14b 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -14,8 +14,11 @@ enum ceph_metric_type {
CLIENT_METRIC_TYPE_WRITE_LATENCY,
CLIENT_METRIC_TYPE_METADATA_LATENCY,
CLIENT_METRIC_TYPE_DENTRY_LEASE,
+ CLIENT_METRIC_TYPE_OPENED_FILES,
+ CLIENT_METRIC_TYPE_PINNED_ICAPS,
+ CLIENT_METRIC_TYPE_OPENED_INODES,
- CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
+ CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_OPENED_INODES,
};
/*
@@ -28,6 +31,9 @@ enum ceph_metric_type {
CLIENT_METRIC_TYPE_WRITE_LATENCY, \
CLIENT_METRIC_TYPE_METADATA_LATENCY, \
CLIENT_METRIC_TYPE_DENTRY_LEASE, \
+ CLIENT_METRIC_TYPE_OPENED_FILES, \
+ CLIENT_METRIC_TYPE_PINNED_ICAPS, \
+ CLIENT_METRIC_TYPE_OPENED_INODES, \
\
CLIENT_METRIC_TYPE_MAX, \
}
@@ -94,6 +100,42 @@ struct ceph_metric_dlease {
__le64 total;
} __packed;
+/* metric opened files header */
+struct ceph_opened_files {
+ __le32 type; /* ceph metric type */
+
+ __u8 ver;
+ __u8 compat;
+
+ __le32 data_len; /* length of sizeof(opened_files + total) */
+ __le64 opened_files;
+ __le64 total;
+} __packed;
+
+/* metric pinned i_caps header */
+struct ceph_pinned_icaps {
+ __le32 type; /* ceph metric type */
+
+ __u8 ver;
+ __u8 compat;
+
+ __le32 data_len; /* length of sizeof(pinned_icaps + total) */
+ __le64 pinned_icaps;
+ __le64 total;
+} __packed;
+
+/* metric opened inodes header */
+struct ceph_opened_inodes {
+ __le32 type; /* ceph metric type */
+
+ __u8 ver;
+ __u8 compat;
+
+ __le32 data_len; /* length of sizeof(opened_inodes + total) */
+ __le64 opened_inodes;
+ __le64 total;
+} __packed;
+
struct ceph_metric_head {
__le32 num; /* the number of metrics that will be sent */
} __packed;
@@ -108,21 +150,21 @@ struct ceph_client_metric {
struct percpu_counter i_caps_hit;
struct percpu_counter i_caps_mis;
- spinlock_t read_latency_lock;
+ spinlock_t read_metric_lock;
u64 total_reads;
ktime_t read_latency_sum;
ktime_t read_latency_sq_sum;
ktime_t read_latency_min;
ktime_t read_latency_max;
- spinlock_t write_latency_lock;
+ spinlock_t write_metric_lock;
u64 total_writes;
ktime_t write_latency_sum;
ktime_t write_latency_sq_sum;
ktime_t write_latency_min;
ktime_t write_latency_max;
- spinlock_t metadata_latency_lock;
+ spinlock_t metadata_metric_lock;
u64 total_metadatas;
ktime_t metadata_latency_sum;
ktime_t metadata_latency_sq_sum;
@@ -162,13 +204,13 @@ static inline void ceph_update_cap_mis(struct ceph_client_metric *m)
percpu_counter_inc(&m->i_caps_mis);
}
-extern void ceph_update_read_latency(struct ceph_client_metric *m,
+extern void ceph_update_read_metrics(struct ceph_client_metric *m,
ktime_t r_start, ktime_t r_end,
int rc);
-extern void ceph_update_write_latency(struct ceph_client_metric *m,
+extern void ceph_update_write_metrics(struct ceph_client_metric *m,
ktime_t r_start, ktime_t r_end,
int rc);
-extern void ceph_update_metadata_latency(struct ceph_client_metric *m,
+extern void ceph_update_metadata_metrics(struct ceph_client_metric *m,
ktime_t r_start, ktime_t r_end,
int rc);
#endif /* _FS_CEPH_MDS_METRIC_H */
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 0728b01d4d43..4ce18055d931 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -605,7 +605,7 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
BUG_ON(capsnap->writing);
- capsnap->size = inode->i_size;
+ capsnap->size = i_size_read(inode);
capsnap->mtime = inode->i_mtime;
capsnap->atime = inode->i_atime;
capsnap->ctime = inode->i_ctime;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index c48bb30c8d70..db80d89556b1 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -21,6 +21,7 @@
#include <linux/ceph/libceph.h>
#ifdef CONFIG_CEPH_FSCACHE
+#define FSCACHE_USE_NEW_IO_API
#include <linux/fscache.h>
#endif
@@ -333,7 +334,7 @@ struct ceph_inode_info {
/* for dirs */
struct timespec64 i_rctime;
- u64 i_rbytes, i_rfiles, i_rsubdirs;
+ u64 i_rbytes, i_rfiles, i_rsubdirs, i_rsnaps;
u64 i_files, i_subdirs;
/* quotas */
@@ -427,7 +428,6 @@ struct ceph_inode_info {
#ifdef CONFIG_CEPH_FSCACHE
struct fscache_cookie *fscache;
- u32 i_fscache_gen;
#endif
errseq_t i_meta_err;
@@ -529,10 +529,34 @@ static inline int ceph_ino_compare(struct inode *inode, void *data)
ci->i_vino.snap == pvino->snap;
}
+/*
+ * The MDS reserves a set of inodes for its own usage. These should never
+ * be accessible by clients, and so the MDS has no reason to ever hand these
+ * out. The range is CEPH_MDS_INO_MDSDIR_OFFSET..CEPH_INO_SYSTEM_BASE.
+ *
+ * These come from src/mds/mdstypes.h in the ceph sources.
+ */
+#define CEPH_MAX_MDS 0x100
+#define CEPH_NUM_STRAY 10
+#define CEPH_MDS_INO_MDSDIR_OFFSET (1 * CEPH_MAX_MDS)
+#define CEPH_INO_SYSTEM_BASE ((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY))
+
+static inline bool ceph_vino_is_reserved(const struct ceph_vino vino)
+{
+ if (vino.ino < CEPH_INO_SYSTEM_BASE &&
+ vino.ino >= CEPH_MDS_INO_MDSDIR_OFFSET) {
+ WARN_RATELIMIT(1, "Attempt to access reserved inode number 0x%llx", vino.ino);
+ return true;
+ }
+ return false;
+}
static inline struct inode *ceph_find_inode(struct super_block *sb,
struct ceph_vino vino)
{
+ if (ceph_vino_is_reserved(vino))
+ return NULL;
+
/*
* NB: The hashval will be run through the fs/inode.c hash function
* anyway, so there is no need to squash the inode number down to
@@ -1156,7 +1180,7 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
int mds, int drop, int unless);
extern int ceph_get_caps(struct file *filp, int need, int want,
- loff_t endoff, int *got, struct page **pinned_page);
+ loff_t endoff, int *got);
extern int ceph_try_get_caps(struct inode *inode,
int need, int want, bool nonblock, int *got);
@@ -1193,7 +1217,7 @@ extern const struct dentry_operations ceph_dentry_ops;
extern loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order);
extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry);
-extern int ceph_handle_snapdir(struct ceph_mds_request *req,
+extern struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *dentry, int err);
extern struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
struct dentry *dentry, int err);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 02f59bcb4f27..1242db8d3444 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -233,6 +233,12 @@ static ssize_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val,
return ceph_fmt_xattr(val, size, "%lld", ci->i_rsubdirs);
}
+static ssize_t ceph_vxattrcb_dir_rsnaps(struct ceph_inode_info *ci, char *val,
+ size_t size)
+{
+ return ceph_fmt_xattr(val, size, "%lld", ci->i_rsnaps);
+}
+
static ssize_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val,
size_t size)
{
@@ -384,6 +390,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
XATTR_RSTAT_FIELD(dir, rentries),
XATTR_RSTAT_FIELD(dir, rfiles),
XATTR_RSTAT_FIELD(dir, rsubdirs),
+ XATTR_RSTAT_FIELD(dir, rsnaps),
XATTR_RSTAT_FIELD(dir, rbytes),
XATTR_RSTAT_FIELD(dir, rctime),
{
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index 9a3aed249692..c0395363eab9 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset:8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* configfs_internal.h - Internal stuff for configfs
*
* Based on sysfs:
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index b6098e02e20b..ac5e0c0e9181 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dir.c - Operations for configfs directories.
*
* Based on sysfs:
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index da8351d1e455..e26060dae70a 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* file.c - operations for regular (text) files.
*
* Based on sysfs:
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 42c348bb2903..eb5ec3e46283 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* inode.c - basic inode and dentry operations.
*
* Based on sysfs:
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index 704a4356f137..254170a82aa3 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* item.c - library routines for handling generic config items
*
* Based on kobject:
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 0c6e8cf61953..c2d820063ec4 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* mount.c - operations for initializing and mounting configfs.
*
* Based on sysfs:
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 77c854364e60..0623c3edcfb9 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* symlink.c - operations for configfs symlinks.
*
* Based on sysfs:
diff --git a/fs/dax.c b/fs/dax.c
index b3d27fdc6775..69216241392f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -525,7 +525,7 @@ retry:
dax_disassociate_entry(entry, mapping, false);
xas_store(xas, NULL); /* undo the PMD join */
dax_wake_entry(xas, entry, true);
- mapping->nrexceptional--;
+ mapping->nrpages -= PG_PMD_NR;
entry = NULL;
xas_set(xas, index);
}
@@ -541,7 +541,7 @@ retry:
dax_lock_entry(xas, entry);
if (xas_error(xas))
goto out_unlock;
- mapping->nrexceptional++;
+ mapping->nrpages += 1UL << order;
}
out_unlock:
@@ -661,7 +661,7 @@ static int __dax_invalidate_entry(struct address_space *mapping,
goto out;
dax_disassociate_entry(entry, mapping, trunc);
xas_store(&xas, NULL);
- mapping->nrexceptional--;
+ mapping->nrpages -= 1UL << dax_entry_order(entry);
ret = 1;
out:
put_unlocked_entry(&xas, entry);
@@ -965,7 +965,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
- if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+ if (mapping_empty(mapping) || wbc->sync_mode != WB_SYNC_ALL)
return 0;
trace_dax_writeback_range(inode, xas.xa_index, end_index);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 943e523f4c9d..345f8061e3b4 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 1997-2004 Erez Zadok
@@ -350,7 +350,7 @@ out:
return rc;
}
-/**
+/*
* lower_offset_for_page
*
* Convert an eCryptfs page index into a lower byte offset
@@ -535,7 +535,7 @@ int ecryptfs_decrypt_page(struct page *page)
rc = crypt_extent(crypt_stat, page, page,
extent_offset, DECRYPT);
if (rc) {
- printk(KERN_ERR "%s: Error encrypting extent; "
+ printk(KERN_ERR "%s: Error decrypting extent; "
"rc = [%d]\n", __func__, rc);
goto out;
}
@@ -627,9 +627,8 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat)
}
}
-/**
+/*
* ecryptfs_compute_root_iv
- * @crypt_stats
*
* On error, sets the root IV to all 0's.
*/
@@ -1370,7 +1369,7 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
return rc;
}
-/**
+/*
* ecryptfs_read_metadata
*
* Common entry point for reading file metadata. From here, we could
@@ -1448,7 +1447,7 @@ out:
return rc;
}
-/**
+/*
* ecryptfs_encrypt_filename - encrypt filename
*
* CBC-encrypts the filename. We do not want to encrypt the same
@@ -1590,11 +1589,10 @@ out:
struct kmem_cache *ecryptfs_key_tfm_cache;
static struct list_head key_tfm_list;
-struct mutex key_tfm_list_mutex;
+DEFINE_MUTEX(key_tfm_list_mutex);
int __init ecryptfs_init_crypto(void)
{
- mutex_init(&key_tfm_list_mutex);
INIT_LIST_HEAD(&key_tfm_list);
return 0;
}
@@ -1877,10 +1875,11 @@ out:
/**
* ecryptfs_encrypt_and_encode_filename - converts a plaintext file name to cipher text
- * @crypt_stat: The crypt_stat struct associated with the file anem to encode
+ * @encoded_name: The encrypted name
+ * @encoded_name_size: Length of the encrypted name
+ * @mount_crypt_stat: The crypt_stat struct associated with the file name to encode
* @name: The plaintext name
- * @length: The length of the plaintext
- * @encoded_name: The encypted name
+ * @name_size: The length of the plaintext name
*
* Encrypts and encodes a filename into something that constitutes a
* valid filename for a filesystem, with printable characters.
@@ -1992,7 +1991,7 @@ static bool is_dot_dotdot(const char *name, size_t name_size)
* ecryptfs_decode_and_decrypt_filename - converts the encoded cipher text name to decoded plaintext
* @plaintext_name: The plaintext name
* @plaintext_name_size: The plaintext name size
- * @ecryptfs_dir_dentry: eCryptfs directory dentry
+ * @sb: Ecryptfs's super_block
* @name: The filename in cipher text
* @name_size: The cipher text name size
*
diff --git a/fs/ecryptfs/debug.c b/fs/ecryptfs/debug.c
index 1f65e99f9a41..cf6d0e8e25a1 100644
--- a/fs/ecryptfs/debug.c
+++ b/fs/ecryptfs/debug.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
* Functions only useful for debugging.
*
@@ -9,7 +9,7 @@
#include "ecryptfs_kernel.h"
-/**
+/*
* ecryptfs_dump_auth_tok - debug function to print auth toks
*
* This function will print the contents of an ecryptfs authentication
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 44606f079efb..acaa0825e9bb 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 1997-2003 Erez Zadok
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 495fb4514d09..5f2b49e13731 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -513,7 +513,7 @@ ecryptfs_dentry_to_lower_path(struct dentry *dentry)
}
#define ecryptfs_printk(type, fmt, arg...) \
- __ecryptfs_printk(type "%s: " fmt, __func__, ## arg);
+ __ecryptfs_printk(type "%s: " fmt, __func__, ## arg)
__printf(1, 2)
void __ecryptfs_printk(const char *fmt, ...);
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 5fb45d865ce5..18d5b91cb573 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 1997-2004 Erez Zadok
@@ -19,7 +19,7 @@
#include <linux/fs_stack.h>
#include "ecryptfs_kernel.h"
-/**
+/*
* ecryptfs_read_update_atime
*
* generic_file_read updates the atime of upper layer inode. But, it
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 0a1ab1db1450..16d50dface59 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 1997-2004 Erez Zadok
@@ -199,7 +199,7 @@ out_lock:
return inode;
}
-/**
+/*
* ecryptfs_initialize_file
*
* Cause the file to be changed from a basic empty file to an ecryptfs
@@ -242,10 +242,8 @@ out:
return rc;
}
-/**
+/*
* ecryptfs_create
- * @dir: The inode of the directory in which to create the file.
- * @dentry: The eCryptfs dentry
* @mode: The mode of the new file.
*
* Creates a new file.
@@ -313,7 +311,7 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
return 0;
}
-/**
+/*
* ecryptfs_lookup_interpose - Dentry interposition for a lookup
*/
static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
@@ -873,6 +871,7 @@ ecryptfs_permission(struct user_namespace *mnt_userns, struct inode *inode,
/**
* ecryptfs_setattr
+ * @mnt_userns: user namespace of the target mount
* @dentry: dentry handle to the inode to modify
* @ia: Structure with flags of what to change and values
*
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index f6a17d259db7..3fe41964c0d8 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
* In-kernel key management code. Includes functions to parse and
* write authentication token-related packets with the underlying
@@ -21,7 +21,7 @@
#include <linux/slab.h>
#include "ecryptfs_kernel.h"
-/**
+/*
* request_key returned an error instead of a valid key address;
* determine the type of error, make appropriate log entries, and
* return an error code.
@@ -536,8 +536,9 @@ out:
/**
* ecryptfs_find_auth_tok_for_sig
+ * @auth_tok_key: key containing the authentication token
* @auth_tok: Set to the matching auth_tok; NULL if not found
- * @crypt_stat: inode crypt_stat crypto context
+ * @mount_crypt_stat: inode crypt_stat crypto context
* @sig: Sig of auth_tok to find
*
* For now, this function simply looks at the registered auth_tok's
@@ -576,7 +577,7 @@ ecryptfs_find_auth_tok_for_sig(
return rc;
}
-/**
+/*
* write_tag_70_packet can gobble a lot of stack space. We stuff most
* of the function's parameters in a kmalloc'd struct to help reduce
* eCryptfs' overall stack usage.
@@ -604,7 +605,7 @@ struct ecryptfs_write_tag_70_packet_silly_stack {
struct shash_desc *hash_desc;
};
-/**
+/*
* write_tag_70_packet - Write encrypted filename (EFN) packet against FNEK
* @filename: NULL-terminated filename string
*
@@ -873,7 +874,7 @@ struct ecryptfs_parse_tag_70_packet_silly_stack {
};
/**
- * parse_tag_70_packet - Parse and process FNEK-encrypted passphrase packet
+ * ecryptfs_parse_tag_70_packet - Parse and process FNEK-encrypted passphrase packet
* @filename: This function kmalloc's the memory for the filename
* @filename_size: This function sets this to the amount of memory
* kmalloc'd for the filename
@@ -1172,7 +1173,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
rc = ecryptfs_cipher_code_to_string(crypt_stat->cipher, cipher_code);
if (rc) {
ecryptfs_printk(KERN_ERR, "Cipher code [%d] is invalid\n",
- cipher_code)
+ cipher_code);
goto out;
}
crypt_stat->flags |= ECRYPTFS_KEY_VALID;
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index a7c903cb01a0..ae4cb4e2e134 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 2008 International Business Machines Corp.
@@ -108,6 +108,7 @@ void ecryptfs_destroy_kthread(void)
* @lower_file: Result of dentry_open by root on lower dentry
* @lower_dentry: Lower dentry for file to open
* @lower_mnt: Lower vfsmount for file to open
+ * @cred: credential to use for this call
*
* This function gets a r/w file opened against the lower dentry.
*
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index cdf40a54a35d..d66bbd2df191 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 1997-2003 Erez Zadok
@@ -24,7 +24,7 @@
#include <linux/magic.h>
#include "ecryptfs_kernel.h"
-/**
+/*
* Module parameter that defines the ecryptfs_verbosity level.
*/
int ecryptfs_verbosity = 0;
@@ -34,7 +34,7 @@ MODULE_PARM_DESC(ecryptfs_verbosity,
"Initial verbosity level (0 or 1; defaults to "
"0, which is Quiet)");
-/**
+/*
* Module parameter that defines the number of message buffer elements
*/
unsigned int ecryptfs_message_buf_len = ECRYPTFS_DEFAULT_MSG_CTX_ELEMS;
@@ -43,7 +43,7 @@ module_param(ecryptfs_message_buf_len, uint, 0);
MODULE_PARM_DESC(ecryptfs_message_buf_len,
"Number of message buffer elements");
-/**
+/*
* Module parameter that defines the maximum guaranteed amount of time to wait
* for a response from ecryptfsd. The actual sleep time will be, more than
* likely, a small amount greater than this specified value, but only less if
@@ -57,7 +57,7 @@ MODULE_PARM_DESC(ecryptfs_message_wait_timeout,
"sleep while waiting for a message response from "
"userspace");
-/**
+/*
* Module parameter that is an estimate of the maximum number of users
* that will be concurrently using eCryptfs. Set this to the right
* value to balance performance and memory use.
@@ -80,7 +80,7 @@ void __ecryptfs_printk(const char *fmt, ...)
va_end(args);
}
-/**
+/*
* ecryptfs_init_lower_file
* @ecryptfs_dentry: Fully initialized eCryptfs dentry object, with
* the lower dentry and the lower mount set
@@ -221,7 +221,7 @@ static void ecryptfs_init_mount_crypt_stat(
/**
* ecryptfs_parse_options
- * @sb: The ecryptfs super block
+ * @sbi: The ecryptfs super block
* @options: The options passed to the kernel
* @check_ruid: set to 1 if device uid should be checked against the ruid
*
@@ -466,10 +466,10 @@ out:
struct kmem_cache *ecryptfs_sb_info_cache;
static struct file_system_type ecryptfs_fs_type;
-/**
- * ecryptfs_get_sb
- * @fs_type
- * @flags
+/*
+ * ecryptfs_mount
+ * @fs_type: The filesystem type that the superblock should belong to
+ * @flags: The flags associated with the mount
* @dev_name: The path to mount over
* @raw_data: The options passed into the kernel
*/
@@ -492,6 +492,12 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
goto out;
}
+ if (!dev_name) {
+ rc = -EINVAL;
+ err = "Device name cannot be null";
+ goto out;
+ }
+
rc = ecryptfs_parse_options(sbi, raw_data, &check_ruid);
if (rc) {
err = "Error parsing options";
@@ -635,7 +641,7 @@ static struct file_system_type ecryptfs_fs_type = {
};
MODULE_ALIAS_FS("ecryptfs");
-/**
+/*
* inode_info_init_once
*
* Initializes the ecryptfs_inode_info_cache when it is created
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index c0dfd9647627..6318f3500e5c 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 2004-2008 International Business Machines Corp.
@@ -14,10 +14,10 @@
static LIST_HEAD(ecryptfs_msg_ctx_free_list);
static LIST_HEAD(ecryptfs_msg_ctx_alloc_list);
-static struct mutex ecryptfs_msg_ctx_lists_mux;
+static DEFINE_MUTEX(ecryptfs_msg_ctx_lists_mux);
static struct hlist_head *ecryptfs_daemon_hash;
-struct mutex ecryptfs_daemon_hash_mux;
+DEFINE_MUTEX(ecryptfs_daemon_hash_mux);
static int ecryptfs_hash_bits;
#define ecryptfs_current_euid_hash(uid) \
hash_long((unsigned long)from_kuid(&init_user_ns, current_euid()), ecryptfs_hash_bits)
@@ -147,7 +147,7 @@ out:
return rc;
}
-/**
+/*
* ecryptfs_exorcise_daemon - Destroy the daemon struct
*
* Must be called ceremoniously while in possession of
@@ -181,7 +181,8 @@ out:
}
/**
- * ecryptfs_process_reponse
+ * ecryptfs_process_response
+ * @daemon: eCryptfs daemon object
* @msg: The ecryptfs message received; the caller should sanity check
* msg->data_len and free the memory
* @seq: The sequence number of the message; must match the sequence
@@ -250,6 +251,7 @@ out:
* ecryptfs_send_message_locked
* @data: The data to send
* @data_len: The length of data
+ * @msg_type: Type of message
* @msg_ctx: The message context allocated for the send
*
* Must be called with ecryptfs_daemon_hash_mux held.
@@ -359,7 +361,6 @@ int __init ecryptfs_init_messaging(void)
"too large, defaulting to [%d] users\n", __func__,
ecryptfs_number_of_users);
}
- mutex_init(&ecryptfs_daemon_hash_mux);
mutex_lock(&ecryptfs_daemon_hash_mux);
ecryptfs_hash_bits = 1;
while (ecryptfs_number_of_users >> ecryptfs_hash_bits)
@@ -383,7 +384,6 @@ int __init ecryptfs_init_messaging(void)
rc = -ENOMEM;
goto out;
}
- mutex_init(&ecryptfs_msg_ctx_lists_mux);
mutex_lock(&ecryptfs_msg_ctx_lists_mux);
ecryptfs_msg_counter = 0;
for (i = 0; i < ecryptfs_message_buf_len; i++) {
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 742ece22c1d4..4e62c3cef70f 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 2008 International Business Machines Corp.
@@ -312,6 +312,7 @@ out_unlock_daemon:
/**
* ecryptfs_miscdev_response - miscdevess response to message previously sent to daemon
+ * @daemon: eCryptfs daemon object
* @data: Bytes comprising struct ecryptfs_message
* @data_size: sizeof(struct ecryptfs_message) + data len
* @seq: Sequence number for miscdev response packet
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 2f333a40ff4d..392e721b50a3 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
* This is where eCryptfs coordinates the symmetric encryption and
* decryption of the file data as it passes between the lower
@@ -22,7 +22,7 @@
#include <asm/unaligned.h>
#include "ecryptfs_kernel.h"
-/**
+/*
* ecryptfs_get_locked_page
*
* Get one page from cache or lower f/s, return error otherwise.
@@ -41,6 +41,7 @@ struct page *ecryptfs_get_locked_page(struct inode *inode, loff_t index)
/**
* ecryptfs_writepage
* @page: Page that is locked before this call is made
+ * @wbc: Write-back control structure
*
* Returns zero on success; non-zero otherwise
*
@@ -78,7 +79,7 @@ static void strip_xattr_flag(char *page_virt,
}
}
-/**
+/*
* Header Extent:
* Octets 0-7: Unencrypted file size (big-endian)
* Octets 8-15: eCryptfs special marker
@@ -229,7 +230,7 @@ out:
return rc;
}
-/**
+/*
* Called with lower inode mutex held.
*/
static int fill_zeros_to_end_of_page(struct page *page, unsigned int to)
@@ -368,7 +369,7 @@ out:
return rc;
}
-/**
+/*
* ecryptfs_write_inode_size_to_header
*
* Writes the lower file size to the first 8 bytes of the header.
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 0438997ac9d8..60bdcaddcbe5 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 2007 International Business Machines Corp.
@@ -230,6 +230,8 @@ int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
* ecryptfs_read_lower_page_segment
* @page_for_ecryptfs: The page into which data for eCryptfs will be
* written
+ * @page_index: Page index in @page_for_ecryptfs from which to start
+ * writing
* @offset_in_page: Offset in @page_for_ecryptfs from which to start
* writing
* @size: The number of bytes to write into @page_for_ecryptfs
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 6b1853f1c06a..39116af0390f 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 1997-2003 Erez Zadok
@@ -81,7 +81,7 @@ static void ecryptfs_destroy_inode(struct inode *inode)
/**
* ecryptfs_statfs
- * @sb: The ecryptfs super block
+ * @dentry: The ecryptfs dentry
* @buf: The struct kstatfs to fill in with stats
*
* Get the filesystem statistics. Currently, we let this pass right through
@@ -108,7 +108,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf)
/**
* ecryptfs_evict_inode
- * @inode - The ecryptfs inode
+ * @inode: The ecryptfs inode
*
* Called by iput() when the inode reference count reached zero
* and the inode is not hashed anywhere. Used to clear anything
@@ -123,7 +123,7 @@ static void ecryptfs_evict_inode(struct inode *inode)
iput(ecryptfs_inode_to_lower(inode));
}
-/**
+/*
* ecryptfs_show_options
*
* Prints the mount options for a given superblock.
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 73138ea68342..1e596e1d0bba 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -657,6 +657,12 @@ static void ep_done_scan(struct eventpoll *ep,
*/
list_splice(txlist, &ep->rdllist);
__pm_relax(ep->ws);
+
+ if (!list_empty(&ep->rdllist)) {
+ if (waitqueue_active(&ep->wq))
+ wake_up(&ep->wq);
+ }
+
write_unlock_irq(&ep->lock);
}
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index f7e3304b7802..860e884e56e8 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -771,7 +771,7 @@ int fat_trim_fs(struct inode *inode, struct fstrim_range *range)
/*
* FAT data is organized as clusters, trim at the granulary of cluster.
*
- * fstrim_range is in byte, convert vaules to cluster index.
+ * fstrim_range is in byte, convert values to cluster index.
* Treat sectors before data region as all used, not to trim them.
*/
ent_start = max_t(u64, range->start>>sbi->cluster_bits, FAT_START_ENT);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 84c38103aa06..ea7fc5c641c7 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -273,8 +273,7 @@ static void __gfs2_glock_put(struct gfs2_glock *gl)
if (mapping) {
truncate_inode_pages_final(mapping);
if (!gfs2_withdrawn(sdp))
- GLOCK_BUG_ON(gl, mapping->nrpages ||
- mapping->nrexceptional);
+ GLOCK_BUG_ON(gl, !mapping_empty(mapping));
}
trace_gfs2_glock_put(gl);
sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
diff --git a/fs/hpfs/hpfs.h b/fs/hpfs/hpfs.h
index 302f45101a96..d92c4af3e1b4 100644
--- a/fs/hpfs/hpfs.h
+++ b/fs/hpfs/hpfs.h
@@ -356,7 +356,8 @@ struct hpfs_dirent {
u8 no_of_acls; /* number of ACL's (low 3 bits) */
u8 ix; /* code page index (of filename), see
struct code_page_data */
- u8 namelen, name[1]; /* file name */
+ u8 namelen; /* file name length */
+ u8 name[]; /* file name */
/* dnode_secno down; btree down pointer, if present,
follows name on next word boundary, or maybe it
precedes next dirent, which is on a word boundary. */
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 701c82c36138..a2a42335e8fd 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -463,14 +463,11 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
struct address_space *mapping = &inode->i_data;
const pgoff_t start = lstart >> huge_page_shift(h);
const pgoff_t end = lend >> huge_page_shift(h);
- struct vm_area_struct pseudo_vma;
struct pagevec pvec;
pgoff_t next, index;
int i, freed = 0;
bool truncate_op = (lend == LLONG_MAX);
- vma_init(&pseudo_vma, current->mm);
- pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
pagevec_init(&pvec);
next = start;
while (next < end) {
@@ -482,10 +479,9 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
for (i = 0; i < pagevec_count(&pvec); ++i) {
struct page *page = pvec.pages[i];
- u32 hash;
+ u32 hash = 0;
index = page->index;
- hash = hugetlb_fault_mutex_hash(mapping, index);
if (!truncate_op) {
/*
* Only need to hold the fault mutex in the
@@ -493,6 +489,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
* page faults. Races are not possible in the
* case of truncation.
*/
+ hash = hugetlb_fault_mutex_hash(mapping, index);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
}
@@ -1435,7 +1432,7 @@ static int get_hstate_idx(int page_size_log)
if (!h)
return -1;
- return h - hstates;
+ return hstate_index(h);
}
/*
diff --git a/fs/inode.c b/fs/inode.c
index 9e192bea0630..c93500d84264 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -529,7 +529,14 @@ void clear_inode(struct inode *inode)
*/
xa_lock_irq(&inode->i_data.i_pages);
BUG_ON(inode->i_data.nrpages);
- BUG_ON(inode->i_data.nrexceptional);
+ /*
+ * Almost always, mapping_empty(&inode->i_data) here; but there are
+ * two known and long-standing ways in which nodes may get left behind
+ * (when deep radix-tree node allocation failed partway; or when THP
+ * collapse_file() failed). Until those two known cases are cleaned up,
+ * or a cleanup function is called here, do not BUG_ON(!mapping_empty),
+ * nor even WARN_ON(!mapping_empty).
+ */
xa_unlock_irq(&inode->i_data.i_pages);
BUG_ON(!list_empty(&inode->i_data.private_list));
BUG_ON(!(inode->i_state & I_FREEING));
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 360f81395d81..f46acbbeed57 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -251,7 +251,7 @@ struct io_rsrc_data {
struct io_buffer {
struct list_head list;
__u64 addr;
- __s32 len;
+ __u32 len;
__u16 bid;
};
@@ -456,6 +456,7 @@ struct io_ring_ctx {
spinlock_t rsrc_ref_lock;
struct io_rsrc_node *rsrc_node;
struct io_rsrc_node *rsrc_backup_node;
+ struct io_mapped_ubuf *dummy_ubuf;
struct io_restriction restrictions;
@@ -702,7 +703,8 @@ enum {
REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT,
REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT,
- REQ_F_FAIL_LINK_BIT,
+ /* first byte is taken by user flags, shift it to not overlap */
+ REQ_F_FAIL_LINK_BIT = 8,
REQ_F_INFLIGHT_BIT,
REQ_F_CUR_POS_BIT,
REQ_F_NOWAIT_BIT,
@@ -1157,6 +1159,12 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
goto err;
__hash_init(ctx->cancel_hash, 1U << hash_bits);
+ ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL);
+ if (!ctx->dummy_ubuf)
+ goto err;
+ /* set invalid range, so io_import_fixed() fails meeting it */
+ ctx->dummy_ubuf->ubuf = -1UL;
+
if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
goto err;
@@ -1184,6 +1192,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
INIT_LIST_HEAD(&ctx->submit_state.comp.locked_free_list);
return ctx;
err:
+ kfree(ctx->dummy_ubuf);
kfree(ctx->cancel_hash);
kfree(ctx);
return NULL;
@@ -3977,7 +3986,7 @@ static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head)
break;
buf->addr = addr;
- buf->len = pbuf->len;
+ buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT);
buf->bid = bid;
addr += pbuf->len;
bid++;
@@ -6503,14 +6512,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
req->work.creds = NULL;
/* enforce forwards compatibility on users */
- if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
- req->flags = 0;
+ if (unlikely(sqe_flags & ~SQE_VALID_FLAGS))
return -EINVAL;
- }
-
if (unlikely(req->opcode >= IORING_OP_LAST))
return -EINVAL;
-
if (unlikely(!io_check_restriction(ctx, req, sqe_flags)))
return -EACCES;
@@ -7539,6 +7544,7 @@ static void __io_rsrc_put_work(struct io_rsrc_node *ref_node)
io_ring_submit_lock(ctx, lock_ring);
spin_lock_irqsave(&ctx->completion_lock, flags);
io_cqring_fill_event(ctx, prsrc->tag, 0, 0);
+ ctx->cq_extra++;
io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
@@ -8111,11 +8117,13 @@ static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slo
struct io_mapped_ubuf *imu = *slot;
unsigned int i;
- for (i = 0; i < imu->nr_bvecs; i++)
- unpin_user_page(imu->bvec[i].bv_page);
- if (imu->acct_pages)
- io_unaccount_mem(ctx, imu->acct_pages);
- kvfree(imu);
+ if (imu != ctx->dummy_ubuf) {
+ for (i = 0; i < imu->nr_bvecs; i++)
+ unpin_user_page(imu->bvec[i].bv_page);
+ if (imu->acct_pages)
+ io_unaccount_mem(ctx, imu->acct_pages);
+ kvfree(imu);
+ }
*slot = NULL;
}
@@ -8132,7 +8140,7 @@ static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
for (i = 0; i < ctx->nr_user_bufs; i++)
io_buffer_unmap(ctx, &ctx->user_bufs[i]);
kfree(ctx->user_bufs);
- kfree(ctx->buf_data);
+ io_rsrc_data_free(ctx->buf_data);
ctx->user_bufs = NULL;
ctx->buf_data = NULL;
ctx->nr_user_bufs = 0;
@@ -8255,6 +8263,11 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
size_t size;
int ret, pret, nr_pages, i;
+ if (!iov->iov_base) {
+ *pimu = ctx->dummy_ubuf;
+ return 0;
+ }
+
ubuf = (unsigned long) iov->iov_base;
end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
start = ubuf >> PAGE_SHIFT;
@@ -8352,7 +8365,9 @@ static int io_buffer_validate(struct iovec *iov)
* constraints here, we'll -EINVAL later when IO is
* submitted if they are wrong.
*/
- if (!iov->iov_base || !iov->iov_len)
+ if (!iov->iov_base)
+ return iov->iov_len ? -EFAULT : 0;
+ if (!iov->iov_len)
return -EFAULT;
/* arbitrary limit, but we need something */
@@ -8385,7 +8400,7 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
return -ENOMEM;
ret = io_buffers_map_alloc(ctx, nr_args);
if (ret) {
- kfree(data);
+ io_rsrc_data_free(data);
return ret;
}
@@ -8402,6 +8417,10 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
ret = io_buffer_validate(&iov);
if (ret)
break;
+ if (!iov.iov_base && tag) {
+ ret = -EINVAL;
+ break;
+ }
ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i],
&last_hpage);
@@ -8451,12 +8470,16 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
err = io_buffer_validate(&iov);
if (err)
break;
+ if (!iov.iov_base && tag) {
+ err = -EINVAL;
+ break;
+ }
err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage);
if (err)
break;
i = array_index_nospec(offset, ctx->nr_user_bufs);
- if (ctx->user_bufs[i]) {
+ if (ctx->user_bufs[i] != ctx->dummy_ubuf) {
err = io_queue_rsrc_removal(ctx->buf_data, offset,
ctx->rsrc_node, ctx->user_bufs[i]);
if (unlikely(err)) {
@@ -8604,6 +8627,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
if (ctx->hash_map)
io_wq_put_hash(ctx->hash_map);
kfree(ctx->cancel_hash);
+ kfree(ctx->dummy_ubuf);
kfree(ctx);
}
@@ -9607,7 +9631,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
if (ret)
goto err;
/* always set a rsrc node */
- io_rsrc_node_switch_start(ctx);
+ ret = io_rsrc_node_switch_start(ctx);
+ if (ret)
+ goto err;
io_rsrc_node_switch(ctx, NULL);
memset(&p->sq_off, 0, sizeof(p->sq_off));
@@ -10136,6 +10162,13 @@ static int __init io_uring_init(void)
BUILD_BUG_SQE_ELEM(42, __u16, personality);
BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in);
+ BUILD_BUG_ON(sizeof(struct io_uring_files_update) !=
+ sizeof(struct io_uring_rsrc_update));
+ BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) >
+ sizeof(struct io_uring_rsrc_update2));
+ /* should fit into one byte */
+ BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
+
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int));
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 0129e6bab985..f2cd2034a87b 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1134,9 +1134,7 @@ iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
}
void
-iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends,
- void (*merge_private)(struct iomap_ioend *ioend,
- struct iomap_ioend *next))
+iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends)
{
struct iomap_ioend *next;
@@ -1148,8 +1146,6 @@ iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends,
break;
list_move_tail(&next->io_list, &ioend->io_list);
ioend->io_size += next->io_size;
- if (next->io_private && merge_private)
- merge_private(ioend, next);
}
}
EXPORT_SYMBOL_GPL(iomap_ioend_try_merge);
@@ -1236,7 +1232,6 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
ioend->io_inode = inode;
ioend->io_size = 0;
ioend->io_offset = offset;
- ioend->io_private = NULL;
ioend->io_bio = bio;
return ioend;
}
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 94ef92fe806c..4880146babaf 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -767,6 +767,7 @@ repeat:
rs.cont_extent = isonum_733(rr->u.CE.extent);
rs.cont_offset = isonum_733(rr->u.CE.offset);
rs.cont_size = isonum_733(rr->u.CE.size);
+ break;
default:
break;
}
diff --git a/fs/locks.c b/fs/locks.c
index 5c42363aa811..74b2a1dfe8d8 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1808,6 +1808,9 @@ check_conflicting_open(struct file *filp, const long arg, int flags)
if (flags & FL_LAYOUT)
return 0;
+ if (flags & FL_DELEG)
+ /* We leave these checks to the caller */
+ return 0;
if (arg == F_RDLCK)
return inode_is_open_for_write(inode) ? -EAGAIN : 0;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index f7786e00a6a7..ed9d580826f5 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -137,12 +137,12 @@ static struct inode *nfs_layout_find_inode_by_stateid(struct nfs_client *clp,
list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) {
if (!pnfs_layout_is_valid(lo))
continue;
- if (stateid != NULL &&
- !nfs4_stateid_match_other(stateid, &lo->plh_stateid))
+ if (!nfs4_stateid_match_other(stateid, &lo->plh_stateid))
continue;
- if (!nfs_sb_active(server->super))
- continue;
- inode = igrab(lo->plh_inode);
+ if (nfs_sb_active(server->super))
+ inode = igrab(lo->plh_inode);
+ else
+ inode = ERR_PTR(-EAGAIN);
rcu_read_unlock();
if (inode)
return inode;
@@ -176,9 +176,10 @@ static struct inode *nfs_layout_find_inode_by_fh(struct nfs_client *clp,
continue;
if (nfsi->layout != lo)
continue;
- if (!nfs_sb_active(server->super))
- continue;
- inode = igrab(lo->plh_inode);
+ if (nfs_sb_active(server->super))
+ inode = igrab(lo->plh_inode);
+ else
+ inode = ERR_PTR(-EAGAIN);
rcu_read_unlock();
if (inode)
return inode;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index ff5c4d0d6d13..cfeaadf56bf0 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -476,7 +476,6 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
to->to_maxval = to->to_initval;
to->to_exponential = 0;
break;
-#ifndef CONFIG_NFS_DISABLE_UDP_SUPPORT
case XPRT_TRANSPORT_UDP:
if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_UDP_RETRANS;
@@ -487,7 +486,6 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
to->to_maxval = NFS_MAX_UDP_TIMEOUT;
to->to_exponential = 1;
break;
-#endif
default:
BUG();
}
@@ -698,9 +696,18 @@ static int nfs_init_server(struct nfs_server *server,
/* Initialise the client representation from the mount data */
server->flags = ctx->flags;
server->options = ctx->options;
- server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
- NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
- NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
+ server->caps |= NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+
+ switch (clp->rpc_ops->version) {
+ case 2:
+ server->fattr_valid = NFS_ATTR_FATTR_V2;
+ break;
+ case 3:
+ server->fattr_valid = NFS_ATTR_FATTR_V3;
+ break;
+ default:
+ server->fattr_valid = NFS_ATTR_FATTR_V4;
+ }
if (ctx->rsize)
server->rsize = nfs_block_size(ctx->rsize, NULL);
@@ -794,6 +801,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
server->maxfilesize = fsinfo->maxfilesize;
server->time_delta = fsinfo->time_delta;
+ server->change_attr_type = fsinfo->change_attr_type;
server->clone_blksize = fsinfo->clone_blksize;
/* We're airborne Set socket buffersize */
@@ -935,6 +943,8 @@ struct nfs_server *nfs_alloc_server(void)
return NULL;
}
+ server->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED;
+
ida_init(&server->openowner_id);
ida_init(&server->lockowner_id);
pnfs_init_server(server);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 04bf8066980c..e6ec6f09ac6e 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -114,7 +114,7 @@ nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
return ret;
}
/**
- * nfs_have_delegation - check if inode has a delegation, mark it
+ * nfs4_have_delegation - check if inode has a delegation, mark it
* NFS_DELEGATION_REFERENCED if there is one.
* @inode: inode to check
* @flags: delegation types to check for
@@ -481,6 +481,22 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
if (freeme == NULL)
goto out;
add_new:
+ /*
+ * If we didn't revalidate the change attribute before setting
+ * the delegation, then pre-emptively ask for a full attribute
+ * cache revalidation.
+ */
+ spin_lock(&inode->i_lock);
+ if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_CHANGE)
+ nfs_set_cache_invalid(inode,
+ NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
+ NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
+ NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK |
+ NFS_INO_INVALID_OTHER | NFS_INO_INVALID_DATA |
+ NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL |
+ NFS_INO_INVALID_XATTR);
+ spin_unlock(&inode->i_lock);
+
list_add_tail_rcu(&delegation->super_list, &server->delegations);
rcu_assign_pointer(nfsi->delegation, delegation);
delegation = NULL;
@@ -488,11 +504,6 @@ add_new:
atomic_long_inc(&nfs_active_delegations);
trace_nfs4_set_delegation(inode, type);
-
- spin_lock(&inode->i_lock);
- if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME))
- NFS_I(inode)->cache_validity |= NFS_INO_REVAL_FORCED;
- spin_unlock(&inode->i_lock);
out:
spin_unlock(&clp->cl_lock);
if (delegation != NULL)
@@ -674,7 +685,7 @@ void nfs_inode_evict_delegation(struct inode *inode)
}
/**
- * nfs_inode_return_delegation - synchronously return a delegation
+ * nfs4_inode_return_delegation - synchronously return a delegation
* @inode: inode to process
*
* This routine will always flush any dirty data to disk on the
@@ -697,7 +708,7 @@ int nfs4_inode_return_delegation(struct inode *inode)
}
/**
- * nfs_inode_return_delegation_on_close - asynchronously return a delegation
+ * nfs4_inode_return_delegation_on_close - asynchronously return a delegation
* @inode: inode to process
*
* This routine is called on file close in order to determine if the
@@ -811,7 +822,7 @@ void nfs_expire_all_delegations(struct nfs_client *clp)
}
/**
- * nfs_super_return_all_delegations - return delegations for one superblock
+ * nfs_server_return_all_delegations - return delegations for one superblock
* @server: pointer to nfs_server to process
*
*/
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9b00a0b7f832..c19b4fd20781 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -84,8 +84,7 @@ int nfs4_inode_make_writeable(struct inode *inode);
static inline int nfs_have_delegated_attributes(struct inode *inode)
{
- return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) &&
- !(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED);
+ return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ);
}
#endif
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index fc4f490f2d78..1a6d2867fba4 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -866,6 +866,8 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
break;
}
+ verf_arg = verf_res;
+
status = nfs_readdir_page_filler(desc, entry, pages, pglen,
arrays, narrays);
} while (!status && nfs_readdir_page_needs_filling(page));
@@ -927,7 +929,12 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
}
return res;
}
- memcpy(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf));
+ /*
+ * Set the cookie verifier if the page cache was empty
+ */
+ if (desc->page_index == 0)
+ memcpy(nfsi->cookieverf, verf,
+ sizeof(nfsi->cookieverf));
}
res = nfs_readdir_search_array(desc);
if (res == 0) {
@@ -974,10 +981,10 @@ static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
/*
* Once we've found the start of the dirent within a page: fill 'er up...
*/
-static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
+static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
+ const __be32 *verf)
{
struct file *file = desc->file;
- struct nfs_inode *nfsi = NFS_I(file_inode(file));
struct nfs_cache_array *array;
unsigned int i = 0;
@@ -991,7 +998,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
desc->eof = true;
break;
}
- memcpy(desc->verf, nfsi->cookieverf, sizeof(desc->verf));
+ memcpy(desc->verf, verf, sizeof(desc->verf));
if (i < (array->size-1))
desc->dir_cookie = array->array[i+1].cookie;
else
@@ -1048,7 +1055,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
for (i = 0; !desc->eof && i < sz && arrays[i]; i++) {
desc->page = arrays[i];
- nfs_do_filldir(desc);
+ nfs_do_filldir(desc, verf);
}
desc->page = NULL;
@@ -1069,6 +1076,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dentry = file_dentry(file);
struct inode *inode = d_inode(dentry);
+ struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_dir_context *dir_ctx = file->private_data;
struct nfs_readdir_descriptor *desc;
int res;
@@ -1122,7 +1130,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
break;
}
if (res == -ETOOSMALL && desc->plus) {
- clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
+ clear_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
nfs_zap_caches(inode);
desc->page_index = 0;
desc->plus = false;
@@ -1132,7 +1140,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
if (res < 0)
break;
- nfs_do_filldir(desc);
+ nfs_do_filldir(desc, nfsi->cookieverf);
nfs_readdir_page_unlock_and_put_cached(desc);
} while (!desc->eof);
@@ -1703,7 +1711,7 @@ static void nfs_drop_nlink(struct inode *inode)
NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter();
nfs_set_cache_invalid(
inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
- NFS_INO_INVALID_OTHER | NFS_INO_REVAL_FORCED);
+ NFS_INO_INVALID_NLINK);
spin_unlock(&inode->i_lock);
}
@@ -2940,7 +2948,7 @@ static int nfs_execute_ok(struct inode *inode, int mask)
if (S_ISDIR(inode->i_mode))
return 0;
- if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_OTHER)) {
+ if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_MODE)) {
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
ret = __nfs_revalidate_inode(server, inode);
@@ -2998,16 +3006,10 @@ out_notsup:
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
- res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ res = nfs_revalidate_inode(inode, NFS_INO_INVALID_MODE |
+ NFS_INO_INVALID_OTHER);
if (res == 0)
res = generic_permission(&init_user_ns, inode, mask);
goto out;
}
EXPORT_SYMBOL_GPL(nfs_permission);
-
-/*
- * Local variables:
- * version-control: t
- * kept-new-versions: 5
- * End:
- */
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index f2b34cfe286c..37a1a88df771 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -169,19 +169,8 @@ out:
static u64 nfs_fetch_iversion(struct inode *inode)
{
- struct nfs_server *server = NFS_SERVER(inode);
-
- /* Is this the right call?: */
- nfs_revalidate_inode(server, inode);
- /*
- * Also, note we're ignoring any returned error. That seems to be
- * the practice for cache consistency information elsewhere in
- * the server, but I'm not sure why.
- */
- if (server->nfs_client->rpc_ops->version >= 4)
- return inode_peek_iversion_raw(inode);
- else
- return time_to_chattr(&inode->i_ctime);
+ nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
+ return inode_peek_iversion_raw(inode);
}
const struct export_operations nfs_export_ops = {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 16ad5050e046..1fef107961bc 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -105,7 +105,7 @@ static int nfs_revalidate_file_size(struct inode *inode, struct file *filp)
if (filp->f_flags & O_DIRECT)
goto force_reval;
- if (nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE))
+ if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_SIZE))
goto force_reval;
return 0;
force_reval:
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 872112bffcab..d383de00d486 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -106,7 +106,7 @@ static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh)
if (unlikely(!p))
return -ENOBUFS;
fh->size = be32_to_cpup(p++);
- if (fh->size > sizeof(struct nfs_fh)) {
+ if (fh->size > NFS_MAXFHSIZE) {
printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n",
fh->size);
return -EOVERFLOW;
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index a06d213d7689..d95c9a39bc70 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -283,20 +283,40 @@ static int nfs_verify_server_address(struct sockaddr *addr)
return 0;
}
+#ifdef CONFIG_NFS_DISABLE_UDP_SUPPORT
+static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx)
+{
+ return true;
+}
+#else
+static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx)
+{
+ if (ctx->version == 4)
+ return true;
+ return false;
+}
+#endif
+
/*
* Sanity check the NFS transport protocol.
- *
*/
-static void nfs_validate_transport_protocol(struct nfs_fs_context *ctx)
+static int nfs_validate_transport_protocol(struct fs_context *fc,
+ struct nfs_fs_context *ctx)
{
switch (ctx->nfs_server.protocol) {
case XPRT_TRANSPORT_UDP:
+ if (nfs_server_transport_udp_invalid(ctx))
+ goto out_invalid_transport_udp;
+ break;
case XPRT_TRANSPORT_TCP:
case XPRT_TRANSPORT_RDMA:
break;
default:
ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP;
}
+ return 0;
+out_invalid_transport_udp:
+ return nfs_invalf(fc, "NFS: Unsupported transport protocol udp");
}
/*
@@ -305,8 +325,6 @@ static void nfs_validate_transport_protocol(struct nfs_fs_context *ctx)
*/
static void nfs_set_mount_transport_protocol(struct nfs_fs_context *ctx)
{
- nfs_validate_transport_protocol(ctx);
-
if (ctx->mount_server.protocol == XPRT_TRANSPORT_UDP ||
ctx->mount_server.protocol == XPRT_TRANSPORT_TCP)
return;
@@ -932,6 +950,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
struct nfs_fh *mntfh = ctx->mntfh;
struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address;
int extra_flags = NFS_MOUNT_LEGACY_INTERFACE;
+ int ret;
if (data == NULL)
goto out_no_data;
@@ -977,6 +996,15 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
sizeof(mntfh->data) - mntfh->size);
/*
+ * for proto == XPRT_TRANSPORT_UDP, which is what uses
+ * to_exponential, implying shift: limit the shift value
+ * to BITS_PER_LONG (majortimeo is unsigned long)
+ */
+ if (!(data->flags & NFS_MOUNT_TCP)) /* this will be UDP */
+ if (data->retrans >= 64) /* shift value is too large */
+ goto out_invalid_data;
+
+ /*
* Translate to nfs_fs_context, which nfs_fill_super
* can deal with.
*/
@@ -1048,6 +1076,10 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
goto generic;
}
+ ret = nfs_validate_transport_protocol(fc, ctx);
+ if (ret)
+ return ret;
+
ctx->skip_reconfig_option_check = true;
return 0;
@@ -1076,6 +1108,9 @@ out_no_address:
out_invalid_fh:
return nfs_invalf(fc, "NFS: invalid root filehandle");
+
+out_invalid_data:
+ return nfs_invalf(fc, "NFS: invalid binary mount data");
}
#if IS_ENABLED(CONFIG_NFS_V4)
@@ -1146,6 +1181,7 @@ static int nfs4_parse_monolithic(struct fs_context *fc,
{
struct nfs_fs_context *ctx = nfs_fc2context(fc);
struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address;
+ int ret;
char *c;
if (!data) {
@@ -1218,9 +1254,9 @@ static int nfs4_parse_monolithic(struct fs_context *fc,
ctx->acdirmin = data->acdirmin;
ctx->acdirmax = data->acdirmax;
ctx->nfs_server.protocol = data->proto;
- nfs_validate_transport_protocol(ctx);
- if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP)
- goto out_invalid_transport_udp;
+ ret = nfs_validate_transport_protocol(fc, ctx);
+ if (ret)
+ return ret;
done:
ctx->skip_reconfig_option_check = true;
return 0;
@@ -1231,9 +1267,6 @@ out_inval_auth:
out_no_address:
return nfs_invalf(fc, "NFS4: mount program didn't pass remote address");
-
-out_invalid_transport_udp:
- return nfs_invalf(fc, "NFS: Unsupported transport protocol udp");
}
#endif
@@ -1298,6 +1331,10 @@ static int nfs_fs_context_validate(struct fs_context *fc)
if (!nfs_verify_server_address(sap))
goto out_no_address;
+ ret = nfs_validate_transport_protocol(fc, ctx);
+ if (ret)
+ return ret;
+
if (ctx->version == 4) {
if (IS_ENABLED(CONFIG_NFS_V4)) {
if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA)
@@ -1306,9 +1343,6 @@ static int nfs_fs_context_validate(struct fs_context *fc)
port = NFS_PORT;
max_namelen = NFS4_MAXNAMLEN;
max_pathlen = NFS4_MAXPATHLEN;
- nfs_validate_transport_protocol(ctx);
- if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP)
- goto out_invalid_transport_udp;
ctx->flags &= ~(NFS_MOUNT_NONLM | NFS_MOUNT_NOACL |
NFS_MOUNT_VER3 | NFS_MOUNT_LOCAL_FLOCK |
NFS_MOUNT_LOCAL_FCNTL);
@@ -1317,10 +1351,6 @@ static int nfs_fs_context_validate(struct fs_context *fc)
}
} else {
nfs_set_mount_transport_protocol(ctx);
-#ifdef CONFIG_NFS_DISABLE_UDP_SUPPORT
- if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP)
- goto out_invalid_transport_udp;
-#endif
if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA)
port = NFS_RDMA_PORT;
}
@@ -1354,8 +1384,6 @@ out_no_device_name:
out_v4_not_compiled:
nfs_errorf(fc, "NFS: NFSv4 is not compiled into kernel");
return -EPROTONOSUPPORT;
-out_invalid_transport_udp:
- return nfs_invalf(fc, "NFS: Unsupported transport protocol udp");
out_no_address:
return nfs_invalf(fc, "NFS: mount program didn't pass remote address");
out_mountproto_mismatch:
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5a8854de0c19..529c4099f482 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -164,34 +164,19 @@ static int nfs_attribute_timeout(struct inode *inode)
return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
}
-static bool nfs_check_cache_invalid_delegated(struct inode *inode, unsigned long flags)
+static bool nfs_check_cache_flags_invalid(struct inode *inode,
+ unsigned long flags)
{
unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
- /* Special case for the pagecache or access cache */
- if (flags == NFS_INO_REVAL_PAGECACHE &&
- !(cache_validity & NFS_INO_REVAL_FORCED))
- return false;
return (cache_validity & flags) != 0;
}
-static bool nfs_check_cache_invalid_not_delegated(struct inode *inode, unsigned long flags)
-{
- unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
-
- if ((cache_validity & flags) != 0)
- return true;
- if (nfs_attribute_timeout(inode))
- return true;
- return false;
-}
-
bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags)
{
- if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
- return nfs_check_cache_invalid_delegated(inode, flags);
-
- return nfs_check_cache_invalid_not_delegated(inode, flags);
+ if (nfs_check_cache_flags_invalid(inode, flags))
+ return true;
+ return nfs_attribute_cache_expired(inode);
}
EXPORT_SYMBOL_GPL(nfs_check_cache_invalid);
@@ -214,20 +199,21 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
if (have_delegation) {
if (!(flags & NFS_INO_REVAL_FORCED))
- flags &= ~NFS_INO_INVALID_OTHER;
- flags &= ~(NFS_INO_INVALID_CHANGE
- | NFS_INO_INVALID_SIZE
- | NFS_INO_REVAL_PAGECACHE
- | NFS_INO_INVALID_XATTR);
- }
+ flags &= ~(NFS_INO_INVALID_MODE |
+ NFS_INO_INVALID_OTHER |
+ NFS_INO_INVALID_XATTR);
+ flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE);
+ } else if (flags & NFS_INO_REVAL_PAGECACHE)
+ flags |= NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE;
if (!nfs_has_xattr_cache(nfsi))
flags &= ~NFS_INO_INVALID_XATTR;
+ if (flags & NFS_INO_INVALID_DATA)
+ nfs_fscache_invalidate(inode);
if (inode->i_mapping->nrpages == 0)
flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
+ flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED);
nfsi->cache_validity |= flags;
- if (flags & NFS_INO_INVALID_DATA)
- nfs_fscache_invalidate(inode);
}
EXPORT_SYMBOL_GPL(nfs_set_cache_invalid);
@@ -452,6 +438,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
.fattr = fattr
};
struct inode *inode = ERR_PTR(-ENOENT);
+ u64 fattr_supported = NFS_SB(sb)->fattr_valid;
unsigned long hash;
nfs_attr_check_mountpoint(sb, fattr);
@@ -484,8 +471,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
inode->i_mode = fattr->mode;
nfsi->cache_validity = 0;
if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
- && nfs_server_capable(inode, NFS_CAP_MODE))
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+ && (fattr_supported & NFS_ATTR_FATTR_MODE))
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
/* Why so? Because we want revalidate for devices/FIFOs, and
* that's precisely what we have in nfs_file_inode_operations.
*/
@@ -530,15 +517,15 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
nfsi->attr_gencount = fattr->gencount;
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
inode->i_atime = fattr->atime;
- else if (nfs_server_capable(inode, NFS_CAP_ATIME))
+ else if (fattr_supported & NFS_ATTR_FATTR_ATIME)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
if (fattr->valid & NFS_ATTR_FATTR_MTIME)
inode->i_mtime = fattr->mtime;
- else if (nfs_server_capable(inode, NFS_CAP_MTIME))
+ else if (fattr_supported & NFS_ATTR_FATTR_MTIME)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
inode->i_ctime = fattr->ctime;
- else if (nfs_server_capable(inode, NFS_CAP_CTIME))
+ else if (fattr_supported & NFS_ATTR_FATTR_CTIME)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
inode_set_iversion_raw(inode, fattr->change_attr);
@@ -550,29 +537,31 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
nfs_set_cache_invalid(inode, NFS_INO_INVALID_SIZE);
if (fattr->valid & NFS_ATTR_FATTR_NLINK)
set_nlink(inode, fattr->nlink);
- else if (nfs_server_capable(inode, NFS_CAP_NLINK))
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+ else if (fattr_supported & NFS_ATTR_FATTR_NLINK)
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK);
if (fattr->valid & NFS_ATTR_FATTR_OWNER)
inode->i_uid = fattr->uid;
- else if (nfs_server_capable(inode, NFS_CAP_OWNER))
+ else if (fattr_supported & NFS_ATTR_FATTR_OWNER)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
if (fattr->valid & NFS_ATTR_FATTR_GROUP)
inode->i_gid = fattr->gid;
- else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
+ else if (fattr_supported & NFS_ATTR_FATTR_GROUP)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
if (nfs_server_capable(inode, NFS_CAP_XATTR))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
inode->i_blocks = fattr->du.nfs2.blocks;
+ else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED &&
+ fattr->size != 0)
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
/*
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- }
-
- if (nfsi->cache_validity != 0)
- nfsi->cache_validity |= NFS_INO_REVAL_FORCED;
+ } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED &&
+ fattr->size != 0)
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
nfs_setsecurity(inode, fattr, label);
@@ -634,8 +623,7 @@ nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
}
/* Optimization: if the end result is no change, don't RPC */
- attr->ia_valid &= NFS_VALID_ATTRS;
- if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0)
+ if (((attr->ia_valid & NFS_VALID_ATTRS) & ~(ATTR_FILE|ATTR_OPEN)) == 0)
return 0;
trace_nfs_setattr_enter(inode);
@@ -710,12 +698,20 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
spin_lock(&inode->i_lock);
NFS_I(inode)->attr_gencount = fattr->gencount;
if ((attr->ia_valid & ATTR_SIZE) != 0) {
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME |
+ NFS_INO_INVALID_BLOCKS);
nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
nfs_vmtruncate(inode, attr->ia_size);
}
if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_CTIME;
+ if ((attr->ia_valid & ATTR_KILL_SUID) != 0 &&
+ inode->i_mode & S_ISUID)
+ inode->i_mode &= ~S_ISUID;
+ if ((attr->ia_valid & ATTR_KILL_SGID) != 0 &&
+ (inode->i_mode & (S_ISGID | S_IXGRP)) ==
+ (S_ISGID | S_IXGRP))
+ inode->i_mode &= ~S_ISGID;
if ((attr->ia_valid & ATTR_MODE) != 0) {
int mode = attr->ia_mode & S_IALLUGO;
mode |= inode->i_mode & ~S_IALLUGO;
@@ -793,14 +789,28 @@ static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
dput(parent);
}
-static bool nfs_need_revalidate_inode(struct inode *inode)
+static u32 nfs_get_valid_attrmask(struct inode *inode)
{
- if (NFS_I(inode)->cache_validity &
- (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
- return true;
- if (nfs_attribute_cache_expired(inode))
- return true;
- return false;
+ unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+ u32 reply_mask = STATX_INO | STATX_TYPE;
+
+ if (!(cache_validity & NFS_INO_INVALID_ATIME))
+ reply_mask |= STATX_ATIME;
+ if (!(cache_validity & NFS_INO_INVALID_CTIME))
+ reply_mask |= STATX_CTIME;
+ if (!(cache_validity & NFS_INO_INVALID_MTIME))
+ reply_mask |= STATX_MTIME;
+ if (!(cache_validity & NFS_INO_INVALID_SIZE))
+ reply_mask |= STATX_SIZE;
+ if (!(cache_validity & NFS_INO_INVALID_NLINK))
+ reply_mask |= STATX_NLINK;
+ if (!(cache_validity & NFS_INO_INVALID_MODE))
+ reply_mask |= STATX_MODE;
+ if (!(cache_validity & NFS_INO_INVALID_OTHER))
+ reply_mask |= STATX_UID | STATX_GID;
+ if (!(cache_validity & NFS_INO_INVALID_BLOCKS))
+ reply_mask |= STATX_BLOCKS;
+ return reply_mask;
}
int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
@@ -815,9 +825,13 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
trace_nfs_getattr_enter(inode);
+ request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID |
+ STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME |
+ STATX_INO | STATX_SIZE | STATX_BLOCKS;
+
if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
nfs_readdirplus_parent_cache_hit(path->dentry);
- goto out_no_update;
+ goto out_no_revalidate;
}
/* Flush out writes to the server in order to update c/mtime. */
@@ -850,14 +864,24 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
/* Check whether the cached attributes are stale */
do_update |= force_sync || nfs_attribute_cache_expired(inode);
cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
- do_update |= cache_validity &
- (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL);
+ do_update |= cache_validity & NFS_INO_INVALID_CHANGE;
if (request_mask & STATX_ATIME)
do_update |= cache_validity & NFS_INO_INVALID_ATIME;
- if (request_mask & (STATX_CTIME|STATX_MTIME))
- do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE;
+ if (request_mask & STATX_CTIME)
+ do_update |= cache_validity & NFS_INO_INVALID_CTIME;
+ if (request_mask & STATX_MTIME)
+ do_update |= cache_validity & NFS_INO_INVALID_MTIME;
+ if (request_mask & STATX_SIZE)
+ do_update |= cache_validity & NFS_INO_INVALID_SIZE;
+ if (request_mask & STATX_NLINK)
+ do_update |= cache_validity & NFS_INO_INVALID_NLINK;
+ if (request_mask & STATX_MODE)
+ do_update |= cache_validity & NFS_INO_INVALID_MODE;
+ if (request_mask & (STATX_UID | STATX_GID))
+ do_update |= cache_validity & NFS_INO_INVALID_OTHER;
if (request_mask & STATX_BLOCKS)
do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
+
if (do_update) {
/* Update the attribute cache */
if (!(server->flags & NFS_MOUNT_NOAC))
@@ -871,8 +895,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
nfs_readdirplus_parent_cache_hit(path->dentry);
out_no_revalidate:
/* Only return attributes that were revalidated. */
- stat->result_mask &= request_mask;
-out_no_update:
+ stat->result_mask = nfs_get_valid_attrmask(inode) | request_mask;
+
generic_fillattr(&init_user_ns, inode, stat);
stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
if (S_ISDIR(inode->i_mode))
@@ -963,7 +987,6 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
{
struct nfs_inode *nfsi;
struct inode *inode;
- struct nfs_server *server;
if (!(ctx->mode & FMODE_WRITE))
return;
@@ -979,10 +1002,10 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
return;
if (!list_empty(&nfsi->open_files))
return;
- server = NFS_SERVER(inode);
- if (server->flags & NFS_MOUNT_NOCTO)
+ if (NFS_SERVER(inode)->flags & NFS_MOUNT_NOCTO)
return;
- nfs_revalidate_inode(server, inode);
+ nfs_revalidate_inode(inode,
+ NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE);
}
EXPORT_SYMBOL_GPL(nfs_close_context);
@@ -1237,16 +1260,16 @@ int nfs_attribute_cache_expired(struct inode *inode)
/**
* nfs_revalidate_inode - Revalidate the inode attributes
- * @server: pointer to nfs_server struct
* @inode: pointer to inode struct
+ * @flags: cache flags to check
*
* Updates inode attribute information by retrieving the data from the server.
*/
-int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
+int nfs_revalidate_inode(struct inode *inode, unsigned long flags)
{
- if (!nfs_need_revalidate_inode(inode))
+ if (!nfs_check_cache_invalid(inode, flags))
return NFS_STALE(inode) ? -ESTALE : 0;
- return __nfs_revalidate_inode(server, inode);
+ return __nfs_revalidate_inode(NFS_SERVER(inode), inode);
}
EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
@@ -1332,7 +1355,7 @@ out:
bool nfs_mapping_need_revalidate_inode(struct inode *inode)
{
- return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) ||
+ return nfs_check_cache_invalid(inode, NFS_INO_INVALID_CHANGE) ||
NFS_STALE(inode);
}
@@ -1468,8 +1491,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
if (!nfs_file_has_buffered_writers(nfsi)) {
/* Verify a few of the more important attributes */
if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr))
- invalid |= NFS_INO_INVALID_CHANGE
- | NFS_INO_REVAL_PAGECACHE;
+ invalid |= NFS_INO_INVALID_CHANGE;
ts = inode->i_mtime;
if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime))
@@ -1483,28 +1505,21 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
cur_size = i_size_read(inode);
new_isize = nfs_size_to_loff_t(fattr->size);
if (cur_size != new_isize)
- invalid |= NFS_INO_INVALID_SIZE
- | NFS_INO_REVAL_PAGECACHE;
+ invalid |= NFS_INO_INVALID_SIZE;
}
}
/* Have any file permissions changed? */
if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
- invalid |= NFS_INO_INVALID_ACCESS
- | NFS_INO_INVALID_ACL
- | NFS_INO_INVALID_OTHER;
+ invalid |= NFS_INO_INVALID_MODE;
if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid))
- invalid |= NFS_INO_INVALID_ACCESS
- | NFS_INO_INVALID_ACL
- | NFS_INO_INVALID_OTHER;
+ invalid |= NFS_INO_INVALID_OTHER;
if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid))
- invalid |= NFS_INO_INVALID_ACCESS
- | NFS_INO_INVALID_ACL
- | NFS_INO_INVALID_OTHER;
+ invalid |= NFS_INO_INVALID_OTHER;
/* Has the link count changed? */
if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
- invalid |= NFS_INO_INVALID_OTHER;
+ invalid |= NFS_INO_INVALID_NLINK;
ts = inode->i_atime;
if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime))
@@ -1642,41 +1657,142 @@ EXPORT_SYMBOL_GPL(_nfs_display_fhandle);
#endif
/**
- * nfs_inode_attrs_need_update - check if the inode attributes need updating
+ * nfs_inode_attrs_cmp_generic - compare attributes
+ * @fattr: attributes
* @inode: pointer to inode
+ *
+ * Attempt to divine whether or not an RPC call reply carrying stale
+ * attributes got scheduled after another call carrying updated ones.
+ * Note also the check for wraparound of 'attr_gencount'
+ *
+ * The function returns '1' if it thinks the attributes in @fattr are
+ * more recent than the ones cached in @inode. Otherwise it returns
+ * the value '0'.
+ */
+static int nfs_inode_attrs_cmp_generic(const struct nfs_fattr *fattr,
+ const struct inode *inode)
+{
+ unsigned long attr_gencount = NFS_I(inode)->attr_gencount;
+
+ return (long)(fattr->gencount - attr_gencount) > 0 ||
+ (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0;
+}
+
+/**
+ * nfs_inode_attrs_cmp_monotonic - compare attributes
* @fattr: attributes
+ * @inode: pointer to inode
*
* Attempt to divine whether or not an RPC call reply carrying stale
* attributes got scheduled after another call carrying updated ones.
*
- * To do so, the function first assumes that a more recent ctime means
- * that the attributes in fattr are newer, however it also attempt to
- * catch the case where ctime either didn't change, or went backwards
- * (if someone reset the clock on the server) by looking at whether
- * or not this RPC call was started after the inode was last updated.
- * Note also the check for wraparound of 'attr_gencount'
+ * We assume that the server observes monotonic semantics for
+ * the change attribute, so a larger value means that the attributes in
+ * @fattr are more recent, in which case the function returns the
+ * value '1'.
+ * A return value of '0' indicates no measurable change
+ * A return value of '-1' means that the attributes in @inode are
+ * more recent.
+ */
+static int nfs_inode_attrs_cmp_monotonic(const struct nfs_fattr *fattr,
+ const struct inode *inode)
+{
+ s64 diff = fattr->change_attr - inode_peek_iversion_raw(inode);
+ if (diff > 0)
+ return 1;
+ return diff == 0 ? 0 : -1;
+}
+
+/**
+ * nfs_inode_attrs_cmp_strict_monotonic - compare attributes
+ * @fattr: attributes
+ * @inode: pointer to inode
*
- * The function returns 'true' if it thinks the attributes in 'fattr' are
- * more recent than the ones cached in the inode.
+ * Attempt to divine whether or not an RPC call reply carrying stale
+ * attributes got scheduled after another call carrying updated ones.
*
+ * We assume that the server observes strictly monotonic semantics for
+ * the change attribute, so a larger value means that the attributes in
+ * @fattr are more recent, in which case the function returns the
+ * value '1'.
+ * A return value of '-1' means that the attributes in @inode are
+ * more recent or unchanged.
*/
-static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
+static int nfs_inode_attrs_cmp_strict_monotonic(const struct nfs_fattr *fattr,
+ const struct inode *inode)
{
- const struct nfs_inode *nfsi = NFS_I(inode);
+ return nfs_inode_attrs_cmp_monotonic(fattr, inode) > 0 ? 1 : -1;
+}
- return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
- ((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
+/**
+ * nfs_inode_attrs_cmp - compare attributes
+ * @fattr: attributes
+ * @inode: pointer to inode
+ *
+ * This function returns '1' if it thinks the attributes in @fattr are
+ * more recent than the ones cached in @inode. It returns '-1' if
+ * the attributes in @inode are more recent than the ones in @fattr,
+ * and it returns 0 if not sure.
+ */
+static int nfs_inode_attrs_cmp(const struct nfs_fattr *fattr,
+ const struct inode *inode)
+{
+ if (nfs_inode_attrs_cmp_generic(fattr, inode) > 0)
+ return 1;
+ switch (NFS_SERVER(inode)->change_attr_type) {
+ case NFS4_CHANGE_TYPE_IS_UNDEFINED:
+ break;
+ case NFS4_CHANGE_TYPE_IS_TIME_METADATA:
+ if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE))
+ break;
+ return nfs_inode_attrs_cmp_monotonic(fattr, inode);
+ default:
+ if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE))
+ break;
+ return nfs_inode_attrs_cmp_strict_monotonic(fattr, inode);
+ }
+ return 0;
+}
+
+/**
+ * nfs_inode_finish_partial_attr_update - complete a previous inode update
+ * @fattr: attributes
+ * @inode: pointer to inode
+ *
+ * Returns '1' if the last attribute update left the inode cached
+ * attributes in a partially unrevalidated state, and @fattr
+ * matches the change attribute of that partial update.
+ * Otherwise returns '0'.
+ */
+static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr,
+ const struct inode *inode)
+{
+ const unsigned long check_valid =
+ NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
+ NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
+ NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER |
+ NFS_INO_INVALID_NLINK;
+ unsigned long cache_validity = NFS_I(inode)->cache_validity;
+
+ if (!(cache_validity & NFS_INO_INVALID_CHANGE) &&
+ (cache_validity & check_valid) != 0 &&
+ (fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
+ nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0)
+ return 1;
+ return 0;
}
-static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
+static int nfs_refresh_inode_locked(struct inode *inode,
+ struct nfs_fattr *fattr)
{
- int ret;
+ int attr_cmp = nfs_inode_attrs_cmp(fattr, inode);
+ int ret = 0;
trace_nfs_refresh_inode_enter(inode);
- if (nfs_inode_attrs_need_update(inode, fattr))
+ if (attr_cmp > 0 || nfs_inode_finish_partial_attr_update(fattr, inode))
ret = nfs_update_inode(inode, fattr);
- else
+ else if (attr_cmp == 0)
ret = nfs_check_inode_attributes(inode, fattr);
trace_nfs_refresh_inode_exit(inode, ret);
@@ -1761,11 +1877,13 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
*/
int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr)
{
+ int attr_cmp = nfs_inode_attrs_cmp(fattr, inode);
int status;
/* Don't do a WCC update if these attributes are already stale */
- if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
- !nfs_inode_attrs_need_update(inode, fattr)) {
+ if (attr_cmp < 0)
+ return 0;
+ if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !attr_cmp) {
fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE
| NFS_ATTR_FATTR_PRESIZE
| NFS_ATTR_FATTR_PREMTIME
@@ -1839,9 +1957,10 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
*/
static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
- struct nfs_server *server;
+ struct nfs_server *server = NFS_SERVER(inode);
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_isize, new_isize;
+ u64 fattr_supported = server->fattr_valid;
unsigned long invalid = 0;
unsigned long now = jiffies;
unsigned long save_cache_validity;
@@ -1885,7 +2004,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
goto out_err;
}
- server = NFS_SERVER(inode);
/* Update the fsid? */
if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
!nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
@@ -1904,14 +2022,17 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ATIME
| NFS_INO_REVAL_FORCED
- | NFS_INO_REVAL_PAGECACHE
| NFS_INO_INVALID_BLOCKS);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
if (pnfs_layoutcommit_outstanding(inode)) {
- nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATTR;
+ nfsi->cache_validity |=
+ save_cache_validity &
+ (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
+ NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
+ NFS_INO_INVALID_BLOCKS);
cache_revalidated = false;
}
@@ -1928,6 +2049,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
save_cache_validity |= NFS_INO_INVALID_CTIME
| NFS_INO_INVALID_MTIME
| NFS_INO_INVALID_SIZE
+ | NFS_INO_INVALID_BLOCKS
+ | NFS_INO_INVALID_NLINK
+ | NFS_INO_INVALID_MODE
| NFS_INO_INVALID_OTHER;
if (S_ISDIR(inode->i_mode))
nfs_force_lookup_revalidate(inode);
@@ -1940,28 +2064,24 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
attr_changed = true;
}
} else {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_CHANGE
- | NFS_INO_REVAL_PAGECACHE
- | NFS_INO_REVAL_FORCED);
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_CHANGE;
cache_revalidated = false;
}
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
inode->i_mtime = fattr->mtime;
- } else if (server->caps & NFS_CAP_MTIME) {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_MTIME
- | NFS_INO_REVAL_FORCED);
+ } else if (fattr_supported & NFS_ATTR_FATTR_MTIME) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_MTIME;
cache_revalidated = false;
}
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
inode->i_ctime = fattr->ctime;
- } else if (server->caps & NFS_CAP_CTIME) {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_CTIME
- | NFS_INO_REVAL_FORCED);
+ } else if (fattr_supported & NFS_ATTR_FATTR_CTIME) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_CTIME;
cache_revalidated = false;
}
@@ -1985,21 +2105,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
(long long)cur_isize,
(long long)new_isize);
}
+ if (new_isize == 0 &&
+ !(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED |
+ NFS_ATTR_FATTR_BLOCKS_USED))) {
+ fattr->du.nfs3.used = 0;
+ fattr->valid |= NFS_ATTR_FATTR_SPACE_USED;
+ }
} else {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_SIZE
- | NFS_INO_REVAL_PAGECACHE
- | NFS_INO_REVAL_FORCED);
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_SIZE;
cache_revalidated = false;
}
-
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
inode->i_atime = fattr->atime;
- else if (server->caps & NFS_CAP_ATIME) {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_ATIME
- | NFS_INO_REVAL_FORCED);
+ else if (fattr_supported & NFS_ATTR_FATTR_ATIME) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_ATIME;
cache_revalidated = false;
}
@@ -2012,10 +2134,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
| NFS_INO_INVALID_ACL;
attr_changed = true;
}
- } else if (server->caps & NFS_CAP_MODE) {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_OTHER
- | NFS_INO_REVAL_FORCED);
+ } else if (fattr_supported & NFS_ATTR_FATTR_MODE) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_MODE;
cache_revalidated = false;
}
@@ -2026,10 +2147,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_uid = fattr->uid;
attr_changed = true;
}
- } else if (server->caps & NFS_CAP_OWNER) {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_OTHER
- | NFS_INO_REVAL_FORCED);
+ } else if (fattr_supported & NFS_ATTR_FATTR_OWNER) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_OTHER;
cache_revalidated = false;
}
@@ -2040,10 +2160,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_gid = fattr->gid;
attr_changed = true;
}
- } else if (server->caps & NFS_CAP_OWNER_GROUP) {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_OTHER
- | NFS_INO_REVAL_FORCED);
+ } else if (fattr_supported & NFS_ATTR_FATTR_GROUP) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_OTHER;
cache_revalidated = false;
}
@@ -2054,10 +2173,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
set_nlink(inode, fattr->nlink);
attr_changed = true;
}
- } else if (server->caps & NFS_CAP_NLINK) {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_OTHER
- | NFS_INO_REVAL_FORCED);
+ } else if (fattr_supported & NFS_ATTR_FATTR_NLINK) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_NLINK;
cache_revalidated = false;
}
@@ -2066,18 +2184,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
* report the blocks in 512byte units
*/
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
+ } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_BLOCKS;
+ cache_revalidated = false;
+ }
+
+ if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) {
inode->i_blocks = fattr->du.nfs2.blocks;
- else {
- nfsi->cache_validity |= save_cache_validity &
- (NFS_INO_INVALID_BLOCKS
- | NFS_INO_REVAL_FORCED);
+ } else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED) {
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_BLOCKS;
cache_revalidated = false;
}
/* Update attrtimeo value if we're out of the unstable period */
if (attr_changed) {
- invalid &= ~NFS_INO_INVALID_ATTR;
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
@@ -2094,7 +2216,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfsi->attrtimeo_timestamp = now;
}
/* Set the barrier to be more recent than this fattr */
- if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
+ if ((long)(fattr->gencount - nfsi->attr_gencount) > 0)
nfsi->attr_gencount = fattr->gencount;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7395d0977b7d..a36af04188c2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -181,7 +181,7 @@ struct nfs_mount_request {
struct net *net;
};
-extern int nfs_mount(struct nfs_mount_request *info);
+extern int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans);
extern void nfs_umount(const struct nfs_mount_request *info);
/* client.c */
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
index 5088fda9b453..b5551ed8f648 100644
--- a/fs/nfs/io.c
+++ b/fs/nfs/io.c
@@ -104,7 +104,7 @@ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode)
}
/**
- * nfs_end_io_direct - declare the file is being used for direct i/o
+ * nfs_start_io_direct - declare the file is being used for direct i/o
* @inode: file inode
*
* Declare that a direct I/O operation is about to start, and ensure
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index dda5c3e65d8d..c5e3b6b3366a 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -136,14 +136,16 @@ struct mnt_fhstatus {
/**
* nfs_mount - Obtain an NFS file handle for the given host and path
* @info: pointer to mount request arguments
+ * @timeo: deciseconds the mount waits for a response before it retries
+ * @retrans: number of times the mount retries a request
*
- * Uses default timeout parameters specified by underlying transport. On
- * successful return, the auth_flavs list and auth_flav_len will be populated
- * with the list from the server or a faked-up list if the server didn't
- * provide one.
+ * Uses timeout parameters specified by caller. On successful return, the
+ * auth_flavs list and auth_flav_len will be populated with the list from the
+ * server or a faked-up list if the server didn't provide one.
*/
-int nfs_mount(struct nfs_mount_request *info)
+int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans)
{
+ struct rpc_timeout mnt_timeout;
struct mountres result = {
.fh = info->fh,
.auth_count = info->auth_flav_len,
@@ -158,6 +160,7 @@ int nfs_mount(struct nfs_mount_request *info)
.protocol = info->protocol,
.address = info->sap,
.addrsize = info->salen,
+ .timeout = &mnt_timeout,
.servername = info->hostname,
.program = &mnt_program,
.version = info->version,
@@ -177,6 +180,7 @@ int nfs_mount(struct nfs_mount_request *info)
if (info->noresvport)
args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+ nfs_init_timeout_values(&mnt_timeout, info->protocol, timeo, retrans);
mnt_clnt = rpc_create(&args);
if (IS_ERR(mnt_clnt))
goto out_clnt_err;
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index bb386a691e69..9ec560aa4a50 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -65,7 +65,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
if (!nfs_server_capable(inode, NFS_CAP_ACLS))
return ERR_PTR(-EOPNOTSUPP);
- status = nfs_revalidate_inode(server, inode);
+ status = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
if (status < 0)
return ERR_PTR(status);
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index ed1c83738c30..e6eca1d7481b 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -433,7 +433,7 @@ static int decode_nfs_fh3(struct xdr_stream *xdr, struct nfs_fh *fh)
if (unlikely(!p))
return -EIO;
length = be32_to_cpup(p++);
- if (unlikely(length > NFS3_FHSIZE))
+ if (unlikely(length > NFS3_FHSIZE || length == 0))
goto out_toobig;
p = xdr_inline_decode(xdr, length);
if (unlikely(!p))
@@ -442,7 +442,7 @@ static int decode_nfs_fh3(struct xdr_stream *xdr, struct nfs_fh *fh)
memcpy(fh->data, p, length);
return 0;
out_toobig:
- dprintk("NFS: file handle size (%u) too big\n", length);
+ trace_nfs_xdr_bad_filehandle(xdr, NFSERR_BADHANDLE);
return -E2BIG;
}
@@ -2227,6 +2227,7 @@ static int decode_fsinfo3resok(struct xdr_stream *xdr,
/* ignore properties */
result->lease_time = 0;
+ result->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA;
return 0;
}
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 094024b0aca1..a24349512ffe 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -46,11 +46,12 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
{
struct inode *inode = file_inode(filep);
struct nfs_server *server = NFS_SERVER(inode);
+ u32 bitmask[3];
struct nfs42_falloc_args args = {
.falloc_fh = NFS_FH(inode),
.falloc_offset = offset,
.falloc_length = len,
- .falloc_bitmask = nfs4_fattr_bitmap,
+ .falloc_bitmask = bitmask,
};
struct nfs42_falloc_res res = {
.falloc_server = server,
@@ -68,6 +69,10 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
return status;
}
+ memcpy(bitmask, server->cache_consistency_bitmask, sizeof(bitmask));
+ if (server->attr_bitmask[1] & FATTR4_WORD1_SPACE_USED)
+ bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+
res.falloc_fattr = nfs_alloc_fattr();
if (!res.falloc_fattr)
return -ENOMEM;
@@ -75,7 +80,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
status = nfs4_call_sync(server->client, server, msg,
&args.seq_args, &res.seq_res, 0);
if (status == 0)
- status = nfs_post_op_update_inode(inode, res.falloc_fattr);
+ status = nfs_post_op_update_inode_force_wcc(inode,
+ res.falloc_fattr);
kfree(res.falloc_fattr);
return status;
@@ -84,7 +90,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
loff_t offset, loff_t len)
{
- struct nfs_server *server = NFS_SERVER(file_inode(filep));
+ struct inode *inode = file_inode(filep);
+ struct nfs_server *server = NFS_SERVER(inode);
struct nfs4_exception exception = { };
struct nfs_lock_context *lock;
int err;
@@ -93,9 +100,13 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
if (IS_ERR(lock))
return PTR_ERR(lock);
- exception.inode = file_inode(filep);
+ exception.inode = inode;
exception.state = lock->open_context->state;
+ err = nfs_sync_inode(inode);
+ if (err)
+ goto out;
+
do {
err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
if (err == -ENOTSUPP) {
@@ -104,7 +115,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
}
err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
-
+out:
nfs_put_lock_context(lock);
return err;
}
@@ -142,16 +153,13 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
return -EOPNOTSUPP;
inode_lock(inode);
- err = nfs_sync_inode(inode);
- if (err)
- goto out_unlock;
err = nfs42_proc_fallocate(&msg, filep, offset, len);
if (err == 0)
truncate_pagecache_range(inode, offset, (offset + len) -1);
if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
-out_unlock:
+
inode_unlock(inode);
return err;
}
@@ -261,6 +269,33 @@ out:
return status;
}
+/**
+ * nfs42_copy_dest_done - perform inode cache updates after clone/copy offload
+ * @inode: pointer to destination inode
+ * @pos: destination offset
+ * @len: copy length
+ *
+ * Punch a hole in the inode page cache, so that the NFS client will
+ * know to retrieve new data.
+ * Update the file size if necessary, and then mark the inode as having
+ * invalid cached values for change attribute, ctime, mtime and space used.
+ */
+static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len)
+{
+ loff_t newsize = pos + len;
+ loff_t end = newsize - 1;
+
+ truncate_pagecache_range(inode, pos, end);
+ spin_lock(&inode->i_lock);
+ if (newsize > i_size_read(inode))
+ i_size_write(inode, newsize);
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+ NFS_INO_INVALID_CTIME |
+ NFS_INO_INVALID_MTIME |
+ NFS_INO_INVALID_BLOCKS);
+ spin_unlock(&inode->i_lock);
+}
+
static ssize_t _nfs42_proc_copy(struct file *src,
struct nfs_lock_context *src_lock,
struct file *dst,
@@ -354,19 +389,8 @@ static ssize_t _nfs42_proc_copy(struct file *src,
goto out;
}
- truncate_pagecache_range(dst_inode, pos_dst,
- pos_dst + res->write_res.count);
- spin_lock(&dst_inode->i_lock);
- nfs_set_cache_invalid(
- dst_inode, NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED |
- NFS_INO_INVALID_SIZE | NFS_INO_INVALID_ATTR |
- NFS_INO_INVALID_DATA);
- spin_unlock(&dst_inode->i_lock);
- spin_lock(&src_inode->i_lock);
- nfs_set_cache_invalid(src_inode, NFS_INO_REVAL_PAGECACHE |
- NFS_INO_REVAL_FORCED |
- NFS_INO_INVALID_ATIME);
- spin_unlock(&src_inode->i_lock);
+ nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count);
+ nfs_invalidate_atime(src_inode);
status = res->write_res.count;
out:
if (args->sync)
@@ -659,7 +683,10 @@ static loff_t _nfs42_proc_llseek(struct file *filep,
if (status)
return status;
- return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
+ if (whence == SEEK_DATA && res.sr_eof)
+ return -NFS4ERR_NXIO;
+ else
+ return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
}
loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
@@ -1044,8 +1071,10 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
status = nfs4_call_sync(server->client, server, msg,
&args.seq_args, &res.seq_res, 0);
- if (status == 0)
+ if (status == 0) {
+ nfs42_copy_dest_done(dst_inode, dst_offset, count);
status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
+ }
kfree(res.dst_fattr);
return status;
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index 6c2ce799150f..1c4d2a05b401 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -168,7 +168,7 @@ nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry)
* make it easier to copy the value after an RPC, even if
* the value will not be passed up to application (e.g.
* for a 'query' getxattr with NULL buffer).
- * @len: Length of the value. Can be 0 for zero-length attribues.
+ * @len: Length of the value. Can be 0 for zero-length attributes.
* @value and @pages will be NULL if @len is 0.
*/
static struct nfs4_xattr_entry *
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 441a2fa073c8..57b3821d975a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -420,9 +420,7 @@ static const struct nfs4_ssc_client_ops nfs4_ssc_clnt_ops_tbl = {
*/
void nfs42_ssc_register_ops(void)
{
-#ifdef CONFIG_NFSD_V4
nfs42_ssc_register(&nfs4_ssc_clnt_ops_tbl);
-#endif
}
/**
@@ -433,9 +431,7 @@ void nfs42_ssc_register_ops(void)
*/
void nfs42_ssc_unregister_ops(void)
{
-#ifdef CONFIG_NFSD_V4
nfs42_ssc_unregister(&nfs4_ssc_clnt_ops_tbl);
-#endif
}
#endif /* CONFIG_NFS_V4_2 */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c65c4b41e2c1..87d04f2c9385 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -108,9 +108,10 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
const struct cred *, bool);
#endif
-static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
- struct nfs_server *server,
- struct nfs4_label *label);
+static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ],
+ const __u32 *src, struct inode *inode,
+ struct nfs_server *server,
+ struct nfs4_label *label);
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
static inline struct nfs4_label *
@@ -263,6 +264,7 @@ const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
| FATTR4_WORD1_FS_LAYOUT_TYPES,
FATTR4_WORD2_LAYOUT_BLKSIZE
| FATTR4_WORD2_CLONE_BLKSIZE
+ | FATTR4_WORD2_CHANGE_ATTR_TYPE
| FATTR4_WORD2_XATTR_SUPPORT
};
@@ -283,7 +285,7 @@ const u32 nfs4_fs_locations_bitmap[3] = {
};
static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
- struct inode *inode)
+ struct inode *inode, unsigned long flags)
{
unsigned long cache_validity;
@@ -291,22 +293,20 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
if (!inode || !nfs4_have_delegation(inode, FMODE_READ))
return;
- cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
- if (!(cache_validity & NFS_INO_REVAL_FORCED))
- cache_validity &= ~(NFS_INO_INVALID_CHANGE
- | NFS_INO_INVALID_SIZE);
+ cache_validity = READ_ONCE(NFS_I(inode)->cache_validity) | flags;
+ /* Remove the attributes over which we have full control */
+ dst[1] &= ~FATTR4_WORD1_RAWDEV;
if (!(cache_validity & NFS_INO_INVALID_SIZE))
dst[0] &= ~FATTR4_WORD0_SIZE;
if (!(cache_validity & NFS_INO_INVALID_CHANGE))
dst[0] &= ~FATTR4_WORD0_CHANGE;
-}
-static void nfs4_bitmap_copy_adjust_setattr(__u32 *dst,
- const __u32 *src, struct inode *inode)
-{
- nfs4_bitmap_copy_adjust(dst, src, inode);
+ if (!(cache_validity & NFS_INO_INVALID_MODE))
+ dst[1] &= ~FATTR4_WORD1_MODE;
+ if (!(cache_validity & NFS_INO_INVALID_OTHER))
+ dst[1] &= ~(FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP);
}
static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dentry,
@@ -1169,14 +1169,26 @@ int nfs4_call_sync(struct rpc_clnt *clnt,
static void
nfs4_inc_nlink_locked(struct inode *inode)
{
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+ NFS_INO_INVALID_CTIME |
+ NFS_INO_INVALID_NLINK);
inc_nlink(inode);
}
static void
+nfs4_inc_nlink(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ nfs4_inc_nlink_locked(inode);
+ spin_unlock(&inode->i_lock);
+}
+
+static void
nfs4_dec_nlink_locked(struct inode *inode)
{
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+ NFS_INO_INVALID_CTIME |
+ NFS_INO_INVALID_NLINK);
drop_nlink(inode);
}
@@ -1186,11 +1198,23 @@ nfs4_update_changeattr_locked(struct inode *inode,
unsigned long timestamp, unsigned long cache_validity)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ u64 change_attr = inode_peek_iversion_raw(inode);
cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
- if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(inode)) {
- nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE;
+ switch (NFS_SERVER(inode)->change_attr_type) {
+ case NFS4_CHANGE_TYPE_IS_UNDEFINED:
+ break;
+ case NFS4_CHANGE_TYPE_IS_TIME_METADATA:
+ if ((s64)(change_attr - cinfo->after) > 0)
+ goto out;
+ break;
+ default:
+ if ((s64)(change_attr - cinfo->after) >= 0)
+ goto out;
+ }
+
+ if (cinfo->atomic && cinfo->before == change_attr) {
nfsi->attrtimeo_timestamp = jiffies;
} else {
if (S_ISDIR(inode->i_mode)) {
@@ -1202,7 +1226,7 @@ nfs4_update_changeattr_locked(struct inode *inode,
cache_validity |= NFS_INO_REVAL_PAGECACHE;
}
- if (cinfo->before != inode_peek_iversion_raw(inode))
+ if (cinfo->before != change_attr)
cache_validity |= NFS_INO_INVALID_ACCESS |
NFS_INO_INVALID_ACL |
NFS_INO_INVALID_XATTR;
@@ -1210,8 +1234,9 @@ nfs4_update_changeattr_locked(struct inode *inode,
inode_set_iversion_raw(inode, cinfo->after);
nfsi->read_cache_jiffies = timestamp;
nfsi->attr_gencount = nfs_inc_attr_generation_counter();
- nfs_set_cache_invalid(inode, cache_validity);
nfsi->cache_validity &= ~NFS_INO_INVALID_CHANGE;
+out:
+ nfs_set_cache_invalid(inode, cache_validity);
}
void
@@ -3344,12 +3369,17 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
.inode = inode,
.stateid = &arg.stateid,
};
+ unsigned long adjust_flags = NFS_INO_INVALID_CHANGE;
int err;
+ if (sattr->ia_valid & (ATTR_MODE | ATTR_KILL_SUID | ATTR_KILL_SGID))
+ adjust_flags |= NFS_INO_INVALID_MODE;
+ if (sattr->ia_valid & (ATTR_UID | ATTR_GID))
+ adjust_flags |= NFS_INO_INVALID_OTHER;
+
do {
- nfs4_bitmap_copy_adjust_setattr(bitmask,
- nfs4_bitmask(server, olabel),
- inode);
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, olabel),
+ inode, adjust_flags);
err = _nfs4_do_setattr(inode, &arg, &res, cred, ctx);
switch (err) {
@@ -3591,6 +3621,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
struct nfs4_closedata *calldata = data;
struct nfs4_state *state = calldata->state;
struct inode *inode = calldata->inode;
+ struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layout_hdr *lo;
bool is_rdonly, is_wronly, is_rdwr;
int call_close = 0;
@@ -3647,8 +3678,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
if (calldata->arg.fmode == 0 || calldata->arg.fmode == FMODE_READ) {
/* Close-to-open cache consistency revalidation */
if (!nfs4_have_delegation(inode, FMODE_READ)) {
- calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
- nfs4_bitmask_adjust(calldata->arg.bitmask, inode, NFS_SERVER(inode), NULL);
+ nfs4_bitmask_set(calldata->arg.bitmask_store,
+ server->cache_consistency_bitmask,
+ inode, server, NULL);
+ calldata->arg.bitmask = calldata->arg.bitmask_store;
} else
calldata->arg.bitmask = NULL;
}
@@ -3835,12 +3868,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
res.attr_bitmask[2] &= FATTR4_WORD2_NFS42_MASK;
}
memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
- server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS|
- NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
- NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|
- NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
- NFS_CAP_CTIME|NFS_CAP_MTIME|
- NFS_CAP_SECURITY_LABEL);
+ server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS |
+ NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL);
+ server->fattr_valid = NFS_ATTR_FATTR_V4;
if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
server->caps |= NFS_CAP_ACLS;
@@ -3848,25 +3878,29 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
server->caps |= NFS_CAP_HARDLINKS;
if (res.has_symlinks != 0)
server->caps |= NFS_CAP_SYMLINKS;
- if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID)
- server->caps |= NFS_CAP_FILEID;
- if (res.attr_bitmask[1] & FATTR4_WORD1_MODE)
- server->caps |= NFS_CAP_MODE;
- if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS)
- server->caps |= NFS_CAP_NLINK;
- if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER)
- server->caps |= NFS_CAP_OWNER;
- if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP)
- server->caps |= NFS_CAP_OWNER_GROUP;
- if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS)
- server->caps |= NFS_CAP_ATIME;
- if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA)
- server->caps |= NFS_CAP_CTIME;
- if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)
- server->caps |= NFS_CAP_MTIME;
+ if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID;
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_MODE;
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_NLINK;
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_OWNER))
+ server->fattr_valid &= ~(NFS_ATTR_FATTR_OWNER |
+ NFS_ATTR_FATTR_OWNER_NAME);
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP))
+ server->fattr_valid &= ~(NFS_ATTR_FATTR_GROUP |
+ NFS_ATTR_FATTR_GROUP_NAME);
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_SPACE_USED))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_SPACE_USED;
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_ATIME;
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_CTIME;
+ if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME;
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
- if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL)
- server->caps |= NFS_CAP_SECURITY_LABEL;
+ if (!(res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_V4_SECURITY_LABEL;
#endif
memcpy(server->attr_bitmask_nl, res.attr_bitmask,
sizeof(server->attr_bitmask));
@@ -4154,8 +4188,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
if (inode && (server->flags & NFS_MOUNT_SOFTREVAL))
task_flags |= RPC_TASK_TIMEOUT;
- nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode);
-
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode, 0);
nfs_fattr_init(fattr);
nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
return nfs4_do_call_sync(server->client, server, &msg,
@@ -4582,11 +4615,11 @@ _nfs4_proc_remove(struct inode *dir, const struct qstr *name, u32 ftype)
status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
if (status == 0) {
spin_lock(&dir->i_lock);
- nfs4_update_changeattr_locked(dir, &res.cinfo, timestamp,
- NFS_INO_INVALID_DATA);
/* Removing a directory decrements nlink in the parent */
if (ftype == NF4DIR && dir->i_nlink > 2)
nfs4_dec_nlink_locked(dir);
+ nfs4_update_changeattr_locked(dir, &res.cinfo, timestamp,
+ NFS_INO_INVALID_DATA);
spin_unlock(&dir->i_lock);
}
return status;
@@ -4715,11 +4748,11 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
/* Note: If we moved a directory, nlink will change */
nfs4_update_changeattr(old_dir, &res->old_cinfo,
res->old_fattr->time_start,
- NFS_INO_INVALID_OTHER |
+ NFS_INO_INVALID_NLINK |
NFS_INO_INVALID_DATA);
nfs4_update_changeattr(new_dir, &res->new_cinfo,
res->new_fattr->time_start,
- NFS_INO_INVALID_OTHER |
+ NFS_INO_INVALID_NLINK |
NFS_INO_INVALID_DATA);
} else
nfs4_update_changeattr(old_dir, &res->old_cinfo,
@@ -4761,12 +4794,13 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct
}
nfs4_inode_make_writeable(inode);
- nfs4_bitmap_copy_adjust_setattr(bitmask, nfs4_bitmask(server, res.label), inode);
-
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.label), inode,
+ NFS_INO_INVALID_CHANGE);
status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
if (!status) {
nfs4_update_changeattr(dir, &res.cinfo, res.fattr->time_start,
NFS_INO_INVALID_DATA);
+ nfs4_inc_nlink(inode);
status = nfs_post_op_update_inode(inode, res.fattr);
if (!status)
nfs_setsecurity(inode, res.fattr, res.label);
@@ -4844,12 +4878,12 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
&data->arg.seq_args, &data->res.seq_res, 1);
if (status == 0) {
spin_lock(&dir->i_lock);
- nfs4_update_changeattr_locked(dir, &data->res.dir_cinfo,
- data->res.fattr->time_start,
- NFS_INO_INVALID_DATA);
/* Creating a directory bumps nlink in the parent */
if (data->arg.ftype == NF4DIR)
nfs4_inc_nlink_locked(dir);
+ nfs4_update_changeattr_locked(dir, &data->res.dir_cinfo,
+ data->res.fattr->time_start,
+ NFS_INO_INVALID_DATA);
spin_unlock(&dir->i_lock);
status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label);
}
@@ -5416,37 +5450,39 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr)
return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
}
-static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
- struct nfs_server *server,
- struct nfs4_label *label)
+static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src,
+ struct inode *inode, struct nfs_server *server,
+ struct nfs4_label *label)
{
-
unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+ unsigned int i;
- if ((cache_validity & NFS_INO_INVALID_DATA) ||
- (cache_validity & NFS_INO_REVAL_PAGECACHE) ||
- (cache_validity & NFS_INO_REVAL_FORCED) ||
- (cache_validity & NFS_INO_INVALID_OTHER))
- nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode);
+ memcpy(bitmask, src, sizeof(*bitmask) * NFS4_BITMASK_SZ);
+ if (cache_validity & NFS_INO_INVALID_CHANGE)
+ bitmask[0] |= FATTR4_WORD0_CHANGE;
if (cache_validity & NFS_INO_INVALID_ATIME)
bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
+ if (cache_validity & NFS_INO_INVALID_MODE)
+ bitmask[1] |= FATTR4_WORD1_MODE;
if (cache_validity & NFS_INO_INVALID_OTHER)
- bitmask[1] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
- FATTR4_WORD1_OWNER_GROUP |
- FATTR4_WORD1_NUMLINKS;
+ bitmask[1] |= FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP;
+ if (cache_validity & NFS_INO_INVALID_NLINK)
+ bitmask[1] |= FATTR4_WORD1_NUMLINKS;
if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL)
bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
- if (cache_validity & NFS_INO_INVALID_CHANGE)
- bitmask[0] |= FATTR4_WORD0_CHANGE;
if (cache_validity & NFS_INO_INVALID_CTIME)
bitmask[1] |= FATTR4_WORD1_TIME_METADATA;
if (cache_validity & NFS_INO_INVALID_MTIME)
bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
- if (cache_validity & NFS_INO_INVALID_SIZE)
- bitmask[0] |= FATTR4_WORD0_SIZE;
if (cache_validity & NFS_INO_INVALID_BLOCKS)
bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+
+ if (cache_validity & NFS_INO_INVALID_SIZE)
+ bitmask[0] |= FATTR4_WORD0_SIZE;
+
+ for (i = 0; i < NFS4_BITMASK_SZ; i++)
+ bitmask[i] &= server->attr_bitmask[i];
}
static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
@@ -5459,8 +5495,10 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
hdr->args.bitmask = NULL;
hdr->res.fattr = NULL;
} else {
- hdr->args.bitmask = server->cache_consistency_bitmask;
- nfs4_bitmask_adjust(hdr->args.bitmask, hdr->inode, server, NULL);
+ nfs4_bitmask_set(hdr->args.bitmask_store,
+ server->cache_consistency_bitmask,
+ hdr->inode, server, NULL);
+ hdr->args.bitmask = hdr->args.bitmask_store;
}
if (!hdr->pgio_done_cb)
@@ -5858,7 +5896,7 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
if (!nfs4_server_supports_acls(server))
return -EOPNOTSUPP;
- ret = nfs_revalidate_inode(server, inode);
+ ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
if (ret < 0)
return ret;
if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
@@ -6502,8 +6540,10 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
data->args.fhandle = &data->fh;
data->args.stateid = &data->stateid;
- data->args.bitmask = server->cache_consistency_bitmask;
- nfs4_bitmask_adjust(data->args.bitmask, inode, server, NULL);
+ nfs4_bitmask_set(data->args.bitmask_store,
+ server->cache_consistency_bitmask, inode, server,
+ NULL);
+ data->args.bitmask = data->args.bitmask_store;
nfs_copy_fh(&data->fh, NFS_FH(inode));
nfs4_stateid_copy(&data->stateid, stateid);
data->res.fattr = &data->fattr;
@@ -7250,22 +7290,22 @@ nfs4_retry_setlk_simple(struct nfs4_state *state, int cmd,
#ifdef CONFIG_NFS_V4_1
struct nfs4_lock_waiter {
- struct task_struct *task;
struct inode *inode;
- struct nfs_lowner *owner;
+ struct nfs_lowner owner;
+ wait_queue_entry_t wait;
};
static int
nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, void *key)
{
- int ret;
- struct nfs4_lock_waiter *waiter = wait->private;
+ struct nfs4_lock_waiter *waiter =
+ container_of(wait, struct nfs4_lock_waiter, wait);
/* NULL key means to wake up everyone */
if (key) {
struct cb_notify_lock_args *cbnl = key;
struct nfs_lowner *lowner = &cbnl->cbnl_owner,
- *wowner = waiter->owner;
+ *wowner = &waiter->owner;
/* Only wake if the callback was for the same owner. */
if (lowner->id != wowner->id || lowner->s_dev != wowner->s_dev)
@@ -7276,53 +7316,45 @@ nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, vo
return 0;
}
- /* override "private" so we can use default_wake_function */
- wait->private = waiter->task;
- ret = woken_wake_function(wait, mode, flags, key);
- if (ret)
- list_del_init(&wait->entry);
- wait->private = waiter;
- return ret;
+ return woken_wake_function(wait, mode, flags, key);
}
static int
nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
- int status = -ERESTARTSYS;
struct nfs4_lock_state *lsp = request->fl_u.nfs4_fl.owner;
struct nfs_server *server = NFS_SERVER(state->inode);
struct nfs_client *clp = server->nfs_client;
wait_queue_head_t *q = &clp->cl_lock_waitq;
- struct nfs_lowner owner = { .clientid = clp->cl_clientid,
- .id = lsp->ls_seqid.owner_id,
- .s_dev = server->s_dev };
- struct nfs4_lock_waiter waiter = { .task = current,
- .inode = state->inode,
- .owner = &owner};
- wait_queue_entry_t wait;
+ struct nfs4_lock_waiter waiter = {
+ .inode = state->inode,
+ .owner = { .clientid = clp->cl_clientid,
+ .id = lsp->ls_seqid.owner_id,
+ .s_dev = server->s_dev },
+ };
+ int status;
/* Don't bother with waitqueue if we don't expect a callback */
if (!test_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags))
return nfs4_retry_setlk_simple(state, cmd, request);
- init_wait(&wait);
- wait.private = &waiter;
- wait.func = nfs4_wake_lock_waiter;
+ init_wait(&waiter.wait);
+ waiter.wait.func = nfs4_wake_lock_waiter;
+ add_wait_queue(q, &waiter.wait);
- while(!signalled()) {
- add_wait_queue(q, &wait);
+ do {
status = nfs4_proc_setlk(state, cmd, request);
- if ((status != -EAGAIN) || IS_SETLK(cmd)) {
- finish_wait(q, &wait);
+ if (status != -EAGAIN || IS_SETLK(cmd))
break;
- }
status = -ERESTARTSYS;
freezer_do_not_count();
- wait_woken(&wait, TASK_INTERRUPTIBLE, NFS4_LOCK_MAXTIMEOUT);
+ wait_woken(&waiter.wait, TASK_INTERRUPTIBLE,
+ NFS4_LOCK_MAXTIMEOUT);
freezer_count();
- finish_wait(q, &wait);
- }
+ } while (!signalled());
+
+ remove_wait_queue(q, &waiter.wait);
return status;
}
@@ -7615,7 +7647,7 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler,
return -EACCES;
}
- ret = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
if (ret)
return ret;
@@ -7646,7 +7678,7 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len)
return 0;
}
- ret = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
if (ret)
return ret;
@@ -10427,9 +10459,3 @@ const struct xattr_handler *nfs4_xattr_handlers[] = {
#endif
NULL
};
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index ff876dda7f06..db3811af0796 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -149,9 +149,3 @@ void nfs4_set_lease_period(struct nfs_client *clp,
/* Cap maximum reconnect timeout at 1/2 lease period */
rpc_set_connect_timeout(clp->cl_rpcclient, lease, lease >> 1);
}
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 3a51351bdc6a..f22818a80c2c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -645,7 +645,7 @@ void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head)
}
/**
- * nfs4_purge_state_owners - Release all cached state owners
+ * nfs4_free_state_owners - Release all cached state owners
* @head: resulting list of state owners
*
* Frees a list of state owners that was generated by
@@ -2695,9 +2695,3 @@ static int nfs4_run_state_manager(void *ptr)
module_put_and_exit(0);
return 0;
}
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 48d761e593fb..2ef75caad6da 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -666,7 +666,42 @@ TRACE_EVENT(nfs4_state_mgr_failed,
)
)
-TRACE_EVENT(nfs4_xdr_status,
+TRACE_EVENT(nfs4_xdr_bad_operation,
+ TP_PROTO(
+ const struct xdr_stream *xdr,
+ u32 op,
+ u32 expected
+ ),
+
+ TP_ARGS(xdr, op, expected),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, task_id)
+ __field(unsigned int, client_id)
+ __field(u32, xid)
+ __field(u32, op)
+ __field(u32, expected)
+ ),
+
+ TP_fast_assign(
+ const struct rpc_rqst *rqstp = xdr->rqst;
+ const struct rpc_task *task = rqstp->rq_task;
+
+ __entry->task_id = task->tk_pid;
+ __entry->client_id = task->tk_client->cl_clid;
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ __entry->op = op;
+ __entry->expected = expected;
+ ),
+
+ TP_printk(
+ "task:%u@%d xid=0x%08x operation=%u, expected=%u",
+ __entry->task_id, __entry->client_id, __entry->xid,
+ __entry->op, __entry->expected
+ )
+);
+
+DECLARE_EVENT_CLASS(nfs4_xdr_event,
TP_PROTO(
const struct xdr_stream *xdr,
u32 op,
@@ -701,6 +736,16 @@ TRACE_EVENT(nfs4_xdr_status,
__entry->op
)
);
+#define DEFINE_NFS4_XDR_EVENT(name) \
+ DEFINE_EVENT(nfs4_xdr_event, name, \
+ TP_PROTO( \
+ const struct xdr_stream *xdr, \
+ u32 op, \
+ u32 error \
+ ), \
+ TP_ARGS(xdr, op, error))
+DEFINE_NFS4_XDR_EVENT(nfs4_xdr_status);
+DEFINE_NFS4_XDR_EVENT(nfs4_xdr_bad_filehandle);
DECLARE_EVENT_CLASS(nfs4_cb_error_class,
TP_PROTO(
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index ac6b79ee9355..a8cff19c6f00 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -144,7 +144,17 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
* layout types will be returned.
*/
#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + \
- nfs4_fattr_bitmap_maxsz + 4 + 8 + 5)
+ nfs4_fattr_bitmap_maxsz + 1 + \
+ 1 /* lease time */ + \
+ 2 /* max filesize */ + \
+ 2 /* max read */ + \
+ 2 /* max write */ + \
+ nfstime4_maxsz /* time delta */ + \
+ 5 /* fs layout types */ + \
+ 1 /* layout blksize */ + \
+ 1 /* clone blksize */ + \
+ 1 /* change attr type */ + \
+ 1 /* xattr support */)
#define encode_renew_maxsz (op_encode_hdr_maxsz + 3)
#define decode_renew_maxsz (op_decode_hdr_maxsz)
#define encode_setclientid_maxsz \
@@ -3200,9 +3210,7 @@ out_status:
*nfs_retval = nfs4_stat_to_errno(nfserr);
return true;
out_bad_operation:
- dprintk("nfs: Server returned operation"
- " %d but we issued a request for %d\n",
- opnum, expected);
+ trace_nfs4_xdr_bad_operation(xdr, opnum, expected);
*nfs_retval = -EREMOTEIO;
return false;
out_overflow:
@@ -3487,8 +3495,11 @@ static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, stru
if (unlikely(!p))
return -EIO;
len = be32_to_cpup(p);
- if (len > NFS4_FHSIZE)
- return -EIO;
+ if (len > NFS4_FHSIZE || len == 0) {
+ trace_nfs4_xdr_bad_filehandle(xdr, OP_READDIR,
+ NFS4ERR_BADHANDLE);
+ return -EREMOTEIO;
+ }
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
return -EIO;
@@ -4837,6 +4848,32 @@ static int decode_attr_clone_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
return 0;
}
+static int decode_attr_change_attr_type(struct xdr_stream *xdr,
+ uint32_t *bitmap,
+ enum nfs4_change_attr_type *res)
+{
+ u32 tmp = NFS4_CHANGE_TYPE_IS_UNDEFINED;
+
+ dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
+ if (bitmap[2] & FATTR4_WORD2_CHANGE_ATTR_TYPE) {
+ if (xdr_stream_decode_u32(xdr, &tmp))
+ return -EIO;
+ bitmap[2] &= ~FATTR4_WORD2_CHANGE_ATTR_TYPE;
+ }
+
+ switch(tmp) {
+ case NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR:
+ case NFS4_CHANGE_TYPE_IS_VERSION_COUNTER:
+ case NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS:
+ case NFS4_CHANGE_TYPE_IS_TIME_METADATA:
+ *res = tmp;
+ break;
+ default:
+ *res = NFS4_CHANGE_TYPE_IS_UNDEFINED;
+ }
+ return 0;
+}
+
static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
{
unsigned int savep;
@@ -4885,6 +4922,11 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
if (status)
goto xdr_error;
+ status = decode_attr_change_attr_type(xdr, bitmap,
+ &fsinfo->change_attr_type);
+ if (status)
+ goto xdr_error;
+
status = decode_attr_xattrsupport(xdr, bitmap,
&fsinfo->xattr_support);
if (status)
@@ -4913,8 +4955,10 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh)
if (unlikely(!p))
return -EIO;
len = be32_to_cpup(p);
- if (len > NFS4_FHSIZE)
- return -EIO;
+ if (len > NFS4_FHSIZE || len == 0) {
+ trace_nfs4_xdr_bad_filehandle(xdr, OP_GETFH, NFS4ERR_BADHANDLE);
+ return -EREMOTEIO;
+ }
fh->size = len;
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
@@ -7629,9 +7673,3 @@ const struct rpc_version nfs_version4 = {
.procs = nfs4_procedures,
.counts = nfs_version4_counts,
};
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/fs/nfs/nfstrace.c b/fs/nfs/nfstrace.c
index a90b363500c2..5d1bfccbb4da 100644
--- a/fs/nfs/nfstrace.c
+++ b/fs/nfs/nfstrace.c
@@ -12,3 +12,4 @@
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_xdr_status);
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_xdr_bad_filehandle);
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 5a59dcdce0b2..eb1ef3462e84 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -45,6 +45,11 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_CTIME);
TRACE_DEFINE_ENUM(NFS_INO_INVALID_MTIME);
TRACE_DEFINE_ENUM(NFS_INO_INVALID_SIZE);
TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
+TRACE_DEFINE_ENUM(NFS_INO_DATA_INVAL_DEFER);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_BLOCKS);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_XATTR);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_NLINK);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE);
#define nfs_show_cache_validity(v) \
__print_flags(v, "|", \
@@ -60,7 +65,11 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
{ NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \
{ NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \
{ NFS_INO_INVALID_OTHER, "INVALID_OTHER" }, \
- { NFS_INO_INVALID_XATTR, "INVALID_XATTR" })
+ { NFS_INO_DATA_INVAL_DEFER, "DATA_INVAL_DEFER" }, \
+ { NFS_INO_INVALID_BLOCKS, "INVALID_BLOCKS" }, \
+ { NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \
+ { NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \
+ { NFS_INO_INVALID_MODE, "INVALID_MODE" })
TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS);
TRACE_DEFINE_ENUM(NFS_INO_STALE);
@@ -1392,7 +1401,7 @@ TRACE_DEFINE_ENUM(NFSERR_JUKEBOX);
{ NFSERR_BADTYPE, "BADTYPE" }, \
{ NFSERR_JUKEBOX, "JUKEBOX" })
-TRACE_EVENT(nfs_xdr_status,
+DECLARE_EVENT_CLASS(nfs_xdr_event,
TP_PROTO(
const struct xdr_stream *xdr,
int error
@@ -1434,6 +1443,15 @@ TRACE_EVENT(nfs_xdr_status,
nfs_show_status(__entry->error)
)
);
+#define DEFINE_NFS_XDR_EVENT(name) \
+ DEFINE_EVENT(nfs_xdr_event, name, \
+ TP_PROTO( \
+ const struct xdr_stream *xdr, \
+ int error \
+ ), \
+ TP_ARGS(xdr, error))
+DEFINE_NFS_XDR_EVENT(nfs_xdr_status);
+DEFINE_NFS_XDR_EVENT(nfs_xdr_bad_filehandle);
#endif /* _TRACE_NFS_H */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 78c9c4bdef2b..6c20b28d9d7c 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -577,7 +577,7 @@ static void nfs_clear_request(struct nfs_page *req)
}
/**
- * nfs_release_request - Release the count on an NFS read/write request
+ * nfs_free_request - Release the count on an NFS read/write request
* @req: request to release
*
* Note: Should never be called with the spinlock held!
@@ -1152,7 +1152,7 @@ nfs_pageio_cleanup_request(struct nfs_pageio_descriptor *desc,
}
/**
- * nfs_pageio_add_request - Attempt to coalesce a request into a page list.
+ * __nfs_pageio_add_request - Attempt to coalesce a request into a page list.
* @desc: destination io descriptor
* @req: request
*
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 102b66e0bdef..03e0b34c4a64 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1344,7 +1344,7 @@ _pnfs_return_layout(struct inode *ino)
}
valid_layout = pnfs_layout_is_valid(lo);
pnfs_clear_layoutcommit(ino, &tmp_list);
- pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL, 0);
+ pnfs_mark_matching_lsegs_return(lo, &tmp_list, NULL, 0);
if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
struct pnfs_layout_range range = {
@@ -2410,9 +2410,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
.iomode = IOMODE_ANY,
.length = NFS4_MAX_UINT64,
};
- pnfs_set_plh_return_info(lo, IOMODE_ANY, 0);
- pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
- &range, 0);
+ pnfs_mark_matching_lsegs_return(lo, &free_me, &range, 0);
goto out_forget;
} else {
/* We have a completely new layout */
@@ -2468,6 +2466,9 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
assert_spin_locked(&lo->plh_inode->i_lock);
+ if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+ tmp_list = &lo->plh_return_segs;
+
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
if (pnfs_match_lseg_recall(lseg, return_range, seq)) {
dprintk("%s: marking lseg %p iomode %d "
@@ -2475,6 +2476,8 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
lseg, lseg->pls_range.iomode,
lseg->pls_range.offset,
lseg->pls_range.length);
+ if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+ tmp_list = &lo->plh_return_segs;
if (mark_lseg_invalid(lseg, tmp_list))
continue;
remaining++;
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 73ab7c59d3a7..ea19dbf12301 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -91,6 +91,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
info->dtpref = fsinfo.tsize;
info->maxfilesize = 0x7FFFFFFF;
info->lease_time = 0;
+ info->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA;
return 0;
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 4aaa1f5dd381..19a212f9725d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -116,16 +116,12 @@ static void unregister_nfs4_fs(void)
#ifdef CONFIG_NFS_V4_2
static void nfs_ssc_register_ops(void)
{
-#ifdef CONFIG_NFSD_V4
nfs_ssc_register(&nfs_ssc_clnt_ops_tbl);
-#endif
}
static void nfs_ssc_unregister_ops(void)
{
-#ifdef CONFIG_NFSD_V4
nfs_ssc_unregister(&nfs_ssc_clnt_ops_tbl);
-#endif
}
#endif /* CONFIG_NFS_V4_2 */
@@ -867,7 +863,7 @@ static int nfs_request_mount(struct fs_context *fc,
* Now ask the mount server to map our export path
* to a file handle.
*/
- status = nfs_mount(&request);
+ status = nfs_mount(&request, ctx->timeo, ctx->retrans);
if (status != 0) {
dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
request.hostname, status);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f05a90338a76..3bf82178166a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -764,9 +764,6 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
* with invalidate/truncate.
*/
spin_lock(&mapping->private_lock);
- if (!nfs_have_writebacks(inode) &&
- NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
- inode_inc_iversion_raw(inode);
if (likely(!PageSwapCache(req->wb_page))) {
set_bit(PG_MAPPED, &req->wb_flags);
SetPagePrivate(req->wb_page);
@@ -1293,7 +1290,7 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode,
if (nfs_have_delegated_attributes(inode))
goto out;
if (nfsi->cache_validity &
- (NFS_INO_REVAL_PAGECACHE | NFS_INO_INVALID_SIZE))
+ (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE))
return false;
smp_rmb();
if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags) && pagelen != 0)
@@ -1604,7 +1601,7 @@ static int nfs_writeback_done(struct rpc_task *task,
/* Deal with the suid/sgid bit corner case */
if (nfs_should_remove_suid(inode)) {
spin_lock(&inode->i_lock);
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
spin_unlock(&inode->i_lock);
}
return 0;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 5fa38ad9e7e3..f229172652be 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -138,7 +138,7 @@ config NFSD_FLEXFILELAYOUT
config NFSD_V4_2_INTER_SSC
bool "NFSv4.2 inter server to server COPY"
- depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
+ depends on NFSD_V4 && NFS_V4_2
help
This option enables support for NFSv4.2 inter server to
server copy where the destination server calls the NFSv4.2
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index daf43b980d4b..f4ce93d7f26e 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -3317,9 +3317,3 @@ const struct svc_version nfsd_version4 = {
.vs_rpcb_optnl = true,
.vs_need_cong_ctrl = true,
};
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7698172ac0c7..b517a8794400 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -354,6 +354,124 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
.release = nfsd4_cb_notify_lock_release,
};
+/*
+ * We store the NONE, READ, WRITE, and BOTH bits separately in the
+ * st_{access,deny}_bmap field of the stateid, in order to track not
+ * only what share bits are currently in force, but also what
+ * combinations of share bits previous opens have used. This allows us
+ * to enforce the recommendation of rfc 3530 14.2.19 that the server
+ * return an error if the client attempt to downgrade to a combination
+ * of share bits not explicable by closing some of its previous opens.
+ *
+ * XXX: This enforcement is actually incomplete, since we don't keep
+ * track of access/deny bit combinations; so, e.g., we allow:
+ *
+ * OPEN allow read, deny write
+ * OPEN allow both, deny none
+ * DOWNGRADE allow read, deny none
+ *
+ * which we should reject.
+ */
+static unsigned int
+bmap_to_share_mode(unsigned long bmap)
+{
+ int i;
+ unsigned int access = 0;
+
+ for (i = 1; i < 4; i++) {
+ if (test_bit(i, &bmap))
+ access |= i;
+ }
+ return access;
+}
+
+/* set share access for a given stateid */
+static inline void
+set_access(u32 access, struct nfs4_ol_stateid *stp)
+{
+ unsigned char mask = 1 << access;
+
+ WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
+ stp->st_access_bmap |= mask;
+}
+
+/* clear share access for a given stateid */
+static inline void
+clear_access(u32 access, struct nfs4_ol_stateid *stp)
+{
+ unsigned char mask = 1 << access;
+
+ WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
+ stp->st_access_bmap &= ~mask;
+}
+
+/* test whether a given stateid has access */
+static inline bool
+test_access(u32 access, struct nfs4_ol_stateid *stp)
+{
+ unsigned char mask = 1 << access;
+
+ return (bool)(stp->st_access_bmap & mask);
+}
+
+/* set share deny for a given stateid */
+static inline void
+set_deny(u32 deny, struct nfs4_ol_stateid *stp)
+{
+ unsigned char mask = 1 << deny;
+
+ WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
+ stp->st_deny_bmap |= mask;
+}
+
+/* clear share deny for a given stateid */
+static inline void
+clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
+{
+ unsigned char mask = 1 << deny;
+
+ WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
+ stp->st_deny_bmap &= ~mask;
+}
+
+/* test whether a given stateid is denying specific access */
+static inline bool
+test_deny(u32 deny, struct nfs4_ol_stateid *stp)
+{
+ unsigned char mask = 1 << deny;
+
+ return (bool)(stp->st_deny_bmap & mask);
+}
+
+static int nfs4_access_to_omode(u32 access)
+{
+ switch (access & NFS4_SHARE_ACCESS_BOTH) {
+ case NFS4_SHARE_ACCESS_READ:
+ return O_RDONLY;
+ case NFS4_SHARE_ACCESS_WRITE:
+ return O_WRONLY;
+ case NFS4_SHARE_ACCESS_BOTH:
+ return O_RDWR;
+ }
+ WARN_ON_ONCE(1);
+ return O_RDONLY;
+}
+
+static inline int
+access_permit_read(struct nfs4_ol_stateid *stp)
+{
+ return test_access(NFS4_SHARE_ACCESS_READ, stp) ||
+ test_access(NFS4_SHARE_ACCESS_BOTH, stp) ||
+ test_access(NFS4_SHARE_ACCESS_WRITE, stp);
+}
+
+static inline int
+access_permit_write(struct nfs4_ol_stateid *stp)
+{
+ return test_access(NFS4_SHARE_ACCESS_WRITE, stp) ||
+ test_access(NFS4_SHARE_ACCESS_BOTH, stp);
+}
+
static inline struct nfs4_stateowner *
nfs4_get_stateowner(struct nfs4_stateowner *sop)
{
@@ -543,14 +661,12 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername)
#define FILE_HASH_BITS 8
#define FILE_HASH_SIZE (1 << FILE_HASH_BITS)
-static unsigned int nfsd_fh_hashval(struct knfsd_fh *fh)
+static unsigned int file_hashval(struct svc_fh *fh)
{
- return jhash2(fh->fh_base.fh_pad, XDR_QUADLEN(fh->fh_size), 0);
-}
+ struct inode *inode = d_inode(fh->fh_dentry);
-static unsigned int file_hashval(struct knfsd_fh *fh)
-{
- return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1);
+ /* XXX: why not (here & in file cache) use inode? */
+ return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS);
}
static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
@@ -1153,108 +1269,6 @@ static unsigned int clientstr_hashval(struct xdr_netobj name)
}
/*
- * We store the NONE, READ, WRITE, and BOTH bits separately in the
- * st_{access,deny}_bmap field of the stateid, in order to track not
- * only what share bits are currently in force, but also what
- * combinations of share bits previous opens have used. This allows us
- * to enforce the recommendation of rfc 3530 14.2.19 that the server
- * return an error if the client attempt to downgrade to a combination
- * of share bits not explicable by closing some of its previous opens.
- *
- * XXX: This enforcement is actually incomplete, since we don't keep
- * track of access/deny bit combinations; so, e.g., we allow:
- *
- * OPEN allow read, deny write
- * OPEN allow both, deny none
- * DOWNGRADE allow read, deny none
- *
- * which we should reject.
- */
-static unsigned int
-bmap_to_share_mode(unsigned long bmap) {
- int i;
- unsigned int access = 0;
-
- for (i = 1; i < 4; i++) {
- if (test_bit(i, &bmap))
- access |= i;
- }
- return access;
-}
-
-/* set share access for a given stateid */
-static inline void
-set_access(u32 access, struct nfs4_ol_stateid *stp)
-{
- unsigned char mask = 1 << access;
-
- WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
- stp->st_access_bmap |= mask;
-}
-
-/* clear share access for a given stateid */
-static inline void
-clear_access(u32 access, struct nfs4_ol_stateid *stp)
-{
- unsigned char mask = 1 << access;
-
- WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
- stp->st_access_bmap &= ~mask;
-}
-
-/* test whether a given stateid has access */
-static inline bool
-test_access(u32 access, struct nfs4_ol_stateid *stp)
-{
- unsigned char mask = 1 << access;
-
- return (bool)(stp->st_access_bmap & mask);
-}
-
-/* set share deny for a given stateid */
-static inline void
-set_deny(u32 deny, struct nfs4_ol_stateid *stp)
-{
- unsigned char mask = 1 << deny;
-
- WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
- stp->st_deny_bmap |= mask;
-}
-
-/* clear share deny for a given stateid */
-static inline void
-clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
-{
- unsigned char mask = 1 << deny;
-
- WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
- stp->st_deny_bmap &= ~mask;
-}
-
-/* test whether a given stateid is denying specific access */
-static inline bool
-test_deny(u32 deny, struct nfs4_ol_stateid *stp)
-{
- unsigned char mask = 1 << deny;
-
- return (bool)(stp->st_deny_bmap & mask);
-}
-
-static int nfs4_access_to_omode(u32 access)
-{
- switch (access & NFS4_SHARE_ACCESS_BOTH) {
- case NFS4_SHARE_ACCESS_READ:
- return O_RDONLY;
- case NFS4_SHARE_ACCESS_WRITE:
- return O_WRONLY;
- case NFS4_SHARE_ACCESS_BOTH:
- return O_RDWR;
- }
- WARN_ON_ONCE(1);
- return O_RDONLY;
-}
-
-/*
* A stateid that had a deny mode associated with it is being released
* or downgraded. Recalculate the deny mode on the file.
*/
@@ -3125,6 +3139,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out_nolock;
}
new->cl_mach_cred = true;
+ break;
case SP4_NONE:
break;
default: /* checked by xdr code */
@@ -4072,7 +4087,7 @@ static struct nfs4_file *nfsd4_alloc_file(void)
}
/* OPEN Share state helper functions */
-static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
+static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval,
struct nfs4_file *fp)
{
lockdep_assert_held(&state_lock);
@@ -4082,12 +4097,14 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
INIT_LIST_HEAD(&fp->fi_stateids);
INIT_LIST_HEAD(&fp->fi_delegations);
INIT_LIST_HEAD(&fp->fi_clnt_odstate);
- fh_copy_shallow(&fp->fi_fhandle, fh);
+ fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle);
fp->fi_deleg_file = NULL;
fp->fi_had_conflict = false;
fp->fi_share_deny = 0;
memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
memset(fp->fi_access, 0, sizeof(fp->fi_access));
+ fp->fi_aliased = false;
+ fp->fi_inode = d_inode(fh->fh_dentry);
#ifdef CONFIG_NFSD_PNFS
INIT_LIST_HEAD(&fp->fi_lo_states);
atomic_set(&fp->fi_lo_recalls, 0);
@@ -4426,13 +4443,13 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
/* search file_hashtbl[] for file */
static struct nfs4_file *
-find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
+find_file_locked(struct svc_fh *fh, unsigned int hashval)
{
struct nfs4_file *fp;
hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash,
lockdep_is_held(&state_lock)) {
- if (fh_match(&fp->fi_fhandle, fh)) {
+ if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) {
if (refcount_inc_not_zero(&fp->fi_ref))
return fp;
}
@@ -4440,8 +4457,32 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
return NULL;
}
-struct nfs4_file *
-find_file(struct knfsd_fh *fh)
+static struct nfs4_file *insert_file(struct nfs4_file *new, struct svc_fh *fh,
+ unsigned int hashval)
+{
+ struct nfs4_file *fp;
+ struct nfs4_file *ret = NULL;
+ bool alias_found = false;
+
+ spin_lock(&state_lock);
+ hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash,
+ lockdep_is_held(&state_lock)) {
+ if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) {
+ if (refcount_inc_not_zero(&fp->fi_ref))
+ ret = fp;
+ } else if (d_inode(fh->fh_dentry) == fp->fi_inode)
+ fp->fi_aliased = alias_found = true;
+ }
+ if (likely(ret == NULL)) {
+ nfsd4_init_file(fh, hashval, new);
+ new->fi_aliased = alias_found;
+ ret = new;
+ }
+ spin_unlock(&state_lock);
+ return ret;
+}
+
+static struct nfs4_file * find_file(struct svc_fh *fh)
{
struct nfs4_file *fp;
unsigned int hashval = file_hashval(fh);
@@ -4453,7 +4494,7 @@ find_file(struct knfsd_fh *fh)
}
static struct nfs4_file *
-find_or_add_file(struct nfs4_file *new, struct knfsd_fh *fh)
+find_or_add_file(struct nfs4_file *new, struct svc_fh *fh)
{
struct nfs4_file *fp;
unsigned int hashval = file_hashval(fh);
@@ -4464,15 +4505,7 @@ find_or_add_file(struct nfs4_file *new, struct knfsd_fh *fh)
if (fp)
return fp;
- spin_lock(&state_lock);
- fp = find_file_locked(fh, hashval);
- if (likely(fp == NULL)) {
- nfsd4_init_file(fh, hashval, new);
- fp = new;
- }
- spin_unlock(&state_lock);
-
- return fp;
+ return insert_file(new, fh, hashval);
}
/*
@@ -4485,7 +4518,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
struct nfs4_file *fp;
__be32 ret = nfs_ok;
- fp = find_file(&current_fh->fh_handle);
+ fp = find_file(current_fh);
if (!fp)
return ret;
/* Check for conflicting share reservations */
@@ -4880,6 +4913,11 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
if (nf)
nfsd_file_put(nf);
+ status = nfserrno(nfsd_open_break_lease(cur_fh->fh_dentry->d_inode,
+ access));
+ if (status)
+ goto out_put_access;
+
status = nfsd4_truncate(rqstp, cur_fh, open);
if (status)
goto out_put_access;
@@ -4951,6 +4989,65 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
return fl;
}
+static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
+ struct nfs4_file *fp)
+{
+ struct nfs4_ol_stateid *st;
+ struct file *f = fp->fi_deleg_file->nf_file;
+ struct inode *ino = locks_inode(f);
+ int writes;
+
+ writes = atomic_read(&ino->i_writecount);
+ if (!writes)
+ return 0;
+ /*
+ * There could be multiple filehandles (hence multiple
+ * nfs4_files) referencing this file, but that's not too
+ * common; let's just give up in that case rather than
+ * trying to go look up all the clients using that other
+ * nfs4_file as well:
+ */
+ if (fp->fi_aliased)
+ return -EAGAIN;
+ /*
+ * If there's a close in progress, make sure that we see it
+ * clear any fi_fds[] entries before we see it decrement
+ * i_writecount:
+ */
+ smp_mb__after_atomic();
+
+ if (fp->fi_fds[O_WRONLY])
+ writes--;
+ if (fp->fi_fds[O_RDWR])
+ writes--;
+ if (writes > 0)
+ return -EAGAIN; /* There may be non-NFSv4 writers */
+ /*
+ * It's possible there are non-NFSv4 write opens in progress,
+ * but if they haven't incremented i_writecount yet then they
+ * also haven't called break lease yet; so, they'll break this
+ * lease soon enough. So, all that's left to check for is NFSv4
+ * opens:
+ */
+ spin_lock(&fp->fi_lock);
+ list_for_each_entry(st, &fp->fi_stateids, st_perfile) {
+ if (st->st_openstp == NULL /* it's an open */ &&
+ access_permit_write(st) &&
+ st->st_stid.sc_client != clp) {
+ spin_unlock(&fp->fi_lock);
+ return -EAGAIN;
+ }
+ }
+ spin_unlock(&fp->fi_lock);
+ /*
+ * There's a small chance that we could be racing with another
+ * NFSv4 open. However, any open that hasn't added itself to
+ * the fi_stateids list also hasn't called break_lease yet; so,
+ * they'll break this lease soon enough.
+ */
+ return 0;
+}
+
static struct nfs4_delegation *
nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
@@ -4970,9 +5067,12 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
nf = find_readable_file(fp);
if (!nf) {
- /* We should always have a readable file here */
- WARN_ON_ONCE(1);
- return ERR_PTR(-EBADF);
+ /*
+ * We probably could attempt another open and get a read
+ * delegation, but for now, don't bother until the
+ * client actually sends us one.
+ */
+ return ERR_PTR(-EAGAIN);
}
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
@@ -5007,6 +5107,9 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
locks_free_lock(fl);
if (status)
goto out_clnt_odstate;
+ status = nfsd4_check_conflicting_opens(clp, fp);
+ if (status)
+ goto out_unlock;
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
@@ -5088,17 +5191,6 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
goto out_no_deleg;
if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
goto out_no_deleg;
- /*
- * Also, if the file was opened for write or
- * create, there's a good chance the client's
- * about to write to it, resulting in an
- * immediate recall (since we don't support
- * write delegations):
- */
- if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
- goto out_no_deleg;
- if (open->op_create == NFS4_OPEN_CREATE)
- goto out_no_deleg;
break;
default:
goto out_no_deleg;
@@ -5161,7 +5253,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
* and check for delegations in the process of being recalled.
* If not found, create the nfs4_file struct
*/
- fp = find_or_add_file(open->op_file, &current_fh->fh_handle);
+ fp = find_or_add_file(open->op_file, current_fh);
if (fp != open->op_file) {
status = nfs4_check_deleg(cl, open, &dp);
if (status)
@@ -5502,21 +5594,6 @@ static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
return nfs_ok;
}
-static inline int
-access_permit_read(struct nfs4_ol_stateid *stp)
-{
- return test_access(NFS4_SHARE_ACCESS_READ, stp) ||
- test_access(NFS4_SHARE_ACCESS_BOTH, stp) ||
- test_access(NFS4_SHARE_ACCESS_WRITE, stp);
-}
-
-static inline int
-access_permit_write(struct nfs4_ol_stateid *stp)
-{
- return test_access(NFS4_SHARE_ACCESS_WRITE, stp) ||
- test_access(NFS4_SHARE_ACCESS_BOTH, stp);
-}
-
static
__be32 nfs4_check_openmode(struct nfs4_ol_stateid *stp, int flags)
{
@@ -6288,15 +6365,6 @@ out:
return status;
}
-static inline u64
-end_offset(u64 start, u64 len)
-{
- u64 end;
-
- end = start + len;
- return end >= start ? end: NFS4_MAX_UINT64;
-}
-
/* last octet in a range */
static inline u64
last_byte_offset(u64 start, u64 len)
@@ -6865,11 +6933,20 @@ out:
static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock)
{
struct nfsd_file *nf;
- __be32 err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf);
- if (!err) {
- err = nfserrno(vfs_test_lock(nf->nf_file, lock));
- nfsd_file_put(nf);
- }
+ __be32 err;
+
+ err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf);
+ if (err)
+ return err;
+ fh_lock(fhp); /* to block new leases till after test_lock: */
+ err = nfserrno(nfsd_open_break_lease(fhp->fh_dentry->d_inode,
+ NFSD_MAY_READ));
+ if (err)
+ goto out;
+ err = nfserrno(vfs_test_lock(nf->nf_file, lock));
+out:
+ fh_unlock(fhp);
+ nfsd_file_put(nf);
return err;
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index e0f06d3cbd44..7abeccb975b2 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -5448,9 +5448,3 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p)
nfsd4_sequence_done(resp);
return 1;
}
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 853bf50a2a9b..c2c3d9077dc5 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1166,6 +1166,7 @@ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode)
inode->i_fop = &simple_dir_operations;
inode->i_op = &simple_dir_inode_operations;
inc_nlink(inode);
+ break;
default:
break;
}
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 82ba034fa579..dd5d69921676 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -308,7 +308,7 @@ static int nfsd_init_socks(struct net *net, const struct cred *cred)
static int nfsd_users = 0;
-static int nfsd_startup_generic(int nrservs)
+static int nfsd_startup_generic(void)
{
int ret;
@@ -374,7 +374,7 @@ void nfsd_reset_boot_verifier(struct nfsd_net *nn)
write_sequnlock(&nn->boot_lock);
}
-static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cred)
+static int nfsd_startup_net(struct net *net, const struct cred *cred)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int ret;
@@ -382,7 +382,7 @@ static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cre
if (nn->nfsd_net_up)
return 0;
- ret = nfsd_startup_generic(nrservs);
+ ret = nfsd_startup_generic();
if (ret)
return ret;
ret = nfsd_init_socks(net, cred);
@@ -790,7 +790,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
nfsd_up_before = nn->nfsd_net_up;
- error = nfsd_startup_net(nrservs, net, cred);
+ error = nfsd_startup_net(net, cred);
if (error)
goto out_destroy;
error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 54cab651ac1d..e73bdbb1634a 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -516,6 +516,8 @@ struct nfs4_clnt_odstate {
*/
struct nfs4_file {
refcount_t fi_ref;
+ struct inode * fi_inode;
+ bool fi_aliased;
spinlock_t fi_lock;
struct hlist_node fi_hash; /* hash on fi_fhandle */
struct list_head fi_stateids;
@@ -669,7 +671,6 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name
struct xdr_netobj princhash, struct nfsd_net *nn);
extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
-struct nfs4_file *find_file(struct knfsd_fh *fh);
void put_nfs4_file(struct nfs4_file *fi);
extern void nfs4_put_copy(struct nfsd4_copy *copy);
extern struct nfsd4_copy *
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index fe540a3415c6..a7c425254fee 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -866,9 +866,3 @@ struct nfsd4_operation {
#endif
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index 025fb082575a..ce144776b4ef 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -293,7 +293,7 @@ void nilfs_cpfile_put_checkpoint(struct inode *cpfile, __u64 cno,
* nilfs_cpfile_delete_checkpoints - delete checkpoints
* @cpfile: inode of checkpoint file
* @start: start checkpoint number
- * @end: end checkpoint numer
+ * @end: end checkpoint number
*
* Description: nilfs_cpfile_delete_checkpoints() deletes the checkpoints in
* the period from @start to @end, excluding @end itself. The checkpoints
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 3fcb9357bbfd..640ac8fe891e 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1043,7 +1043,7 @@ out:
* @inode: inode object
* @argp: pointer on argument from userspace
*
- * Decription: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
+ * Description: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
* checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
* performs the actual trim operation.
*
@@ -1085,7 +1085,7 @@ static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
* @inode: inode object
* @argp: pointer on argument from userspace
*
- * Decription: nilfs_ioctl_set_alloc_range() function defines lower limit
+ * Description: nilfs_ioctl_set_alloc_range() function defines lower limit
* of segments in bytes and upper limit of segments in bytes.
* The NILFS_IOCTL_SET_ALLOC_RANGE is used by nilfs_resize utility.
*
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index cd4da9535aed..686c8ee7b29c 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2214,7 +2214,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err)
* nilfs_construct_segment - construct a logical segment
* @sb: super block
*
- * Return Value: On success, 0 is retured. On errors, one of the following
+ * Return Value: On success, 0 is returned. On errors, one of the following
* negative error code is returned.
*
* %-EROFS - Read only filesystem.
@@ -2251,7 +2251,7 @@ int nilfs_construct_segment(struct super_block *sb)
* @start: start byte offset
* @end: end byte offset (inclusive)
*
- * Return Value: On success, 0 is retured. On errors, one of the following
+ * Return Value: On success, 0 is returned. On errors, one of the following
* negative error code is returned.
*
* %-EROFS - Read only filesystem.
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 221a1cc597f0..8b7b01a380ce 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -195,7 +195,7 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs,
/**
* load_nilfs - load and recover the nilfs
* @nilfs: the_nilfs structure to be released
- * @sb: super block isntance used to recover past segment
+ * @sb: super block instance used to recover past segment
*
* load_nilfs() searches and load the latest super root,
* attaches the last segment, and does recovery if needed.
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 5259badabb56..5c72a7e6d6c5 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* acl.c
*
* Copyright (C) 2004, 2008 Oracle. All rights reserved.
diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h
index 4e86450917b2..f59d8d0a61fa 100644
--- a/fs/ocfs2/acl.h
+++ b/fs/ocfs2/acl.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* acl.h
*
* Copyright (C) 2004, 2008 Oracle. All rights reserved.
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 78710788c237..e032f2e2c2c5 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* alloc.c
*
* Extent allocs and frees
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index 7f973dd76dbc..4af7abaa6e40 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* alloc.h
*
* Function prototypes
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index ad20403b383f..1294925ac94a 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 70ed4382750d..3a520117fa59 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2002, 2004, 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/blockcheck.c b/fs/ocfs2/blockcheck.c
index dabfef9c2bc0..863a5316030b 100644
--- a/fs/ocfs2/blockcheck.c
+++ b/fs/ocfs2/blockcheck.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* blockcheck.c
*
* Checksum and ECC codes for the OCFS2 userspace library.
diff --git a/fs/ocfs2/blockcheck.h b/fs/ocfs2/blockcheck.h
index 8f17d2c85f40..d0578e98ee8d 100644
--- a/fs/ocfs2/blockcheck.h
+++ b/fs/ocfs2/blockcheck.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* blockcheck.h
*
* Checksum and ECC codes for the OCFS2 userspace library.
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index f0b104e483d8..e7758778abef 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* io.c
*
* Buffer cache handling
diff --git a/fs/ocfs2/buffer_head_io.h b/fs/ocfs2/buffer_head_io.h
index 1c5e533fba04..2d51649fc090 100644
--- a/fs/ocfs2/buffer_head_io.h
+++ b/fs/ocfs2/buffer_head_io.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2_buffer_head.h
*
* Buffer cache handling functions defined
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 12a7590601dd..e829c2595543 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2004, 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index beed31ea86cf..1d4100abf6f8 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* heartbeat.h
*
* Function prototypes
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index 1d696c96b8b2..810d32815593 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2004, 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index 446e452ac7a6..b73fc42e46ff 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 667a5c5e1f66..7524994e3199 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* netdebug.c
*
* debug functionality for o2net
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index 7a7640c59f3c..bb82e6b1ff4e 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2004, 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h
index 3e0006631cc4..3490e77a952d 100644
--- a/fs/ocfs2/cluster/nodemanager.h
+++ b/fs/ocfs2/cluster/nodemanager.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* nodemanager.h
*
* Function prototypes
diff --git a/fs/ocfs2/cluster/ocfs2_heartbeat.h b/fs/ocfs2/cluster/ocfs2_heartbeat.h
index 760d850be11e..6088c9f974dd 100644
--- a/fs/ocfs2/cluster/ocfs2_heartbeat.h
+++ b/fs/ocfs2/cluster/ocfs2_heartbeat.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2_heartbeat.h
*
* On-disk structures for ocfs2_heartbeat
diff --git a/fs/ocfs2/cluster/ocfs2_nodemanager.h b/fs/ocfs2/cluster/ocfs2_nodemanager.h
index 21ad307419a8..c9a0b77443e7 100644
--- a/fs/ocfs2/cluster/ocfs2_nodemanager.h
+++ b/fs/ocfs2/cluster/ocfs2_nodemanager.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2_nodemanager.h
*
* Header describing the interface between userspace and the kernel
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index cea739be77c4..189c111bc371 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- *
- * vim: noexpandtab sw=8 ts=8 sts=0:
+/*
*
* Copyright (C) 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/cluster/quorum.h b/fs/ocfs2/cluster/quorum.h
index 6d45ce8b18a1..d64bf4482a4a 100644
--- a/fs/ocfs2/cluster/quorum.h
+++ b/fs/ocfs2/cluster/quorum.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/cluster/sys.c b/fs/ocfs2/cluster/sys.c
index d6067c3d84c1..022f716c74ff 100644
--- a/fs/ocfs2/cluster/sys.c
+++ b/fs/ocfs2/cluster/sys.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* sys.c
*
* OCFS2 cluster sysfs interface
diff --git a/fs/ocfs2/cluster/sys.h b/fs/ocfs2/cluster/sys.h
index ce380517cf17..70aaba65317e 100644
--- a/fs/ocfs2/cluster/sys.h
+++ b/fs/ocfs2/cluster/sys.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* sys.h
*
* Function prototypes for o2cb sysfs interface
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 3bd8119bed5e..f660c0dbdb63 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- *
- * vim: noexpandtab sw=8 ts=8 sts=0:
+/*
*
* Copyright (C) 2004 Oracle. All rights reserved.
*
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index 736338f45c59..a75b551d31c7 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* tcp.h
*
* Function prototypes
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index e6a2b9dfcd16..601c99bd2611 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* Copyright (C) 2005 Oracle. All rights reserved.
*/
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 42a61eecdacd..04fc8344063a 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dcache.c
*
* dentry cache handling code
diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h
index 3686a52ba143..7f246c5692d8 100644
--- a/fs/ocfs2/dcache.h
+++ b/fs/ocfs2/dcache.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dcache.h
*
* Function prototypes
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index bdfba9db558a..bd8d534f11cb 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dir.c
*
* Creates, reads, walks and deletes directory-nodes
diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h
index e3e7d5dd29e8..4b9f5a12c7d2 100644
--- a/fs/ocfs2/dir.h
+++ b/fs/ocfs2/dir.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dir.h
*
* Function prototypes
diff --git a/fs/ocfs2/dlm/dlmapi.h b/fs/ocfs2/dlm/dlmapi.h
index 6456c0fbcbb2..bae60ca2672a 100644
--- a/fs/ocfs2/dlm/dlmapi.h
+++ b/fs/ocfs2/dlm/dlmapi.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmapi.h
*
* externally exported dlm interfaces
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index 70a10764f249..c681ba957932 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmast.c
*
* AST and BAST functionality for local and remote nodes
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 58d57e25d384..fd2022712167 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmcommon.h
*
* Copyright (C) 2004 Oracle. All rights reserved.
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 6051edc33aef..450d46eefab3 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmconvert.c
*
* underlying calls for lock conversion
diff --git a/fs/ocfs2/dlm/dlmconvert.h b/fs/ocfs2/dlm/dlmconvert.h
index 12d9c28bc52f..1f371716513b 100644
--- a/fs/ocfs2/dlm/dlmconvert.h
+++ b/fs/ocfs2/dlm/dlmconvert.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmconvert.h
*
* Copyright (C) 2004 Oracle. All rights reserved.
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 4b8b41d23e91..d442cf5dda8a 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmdebug.c
*
* debug functionality for the dlm
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index f8fd8680a4b6..e08f7357e7ec 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmdebug.h
*
* Copyright (C) 2008 Oracle. All rights reserved.
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 357cfc702ce3..9f90fc9551e1 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmdomain.c
*
* defines domain join / leave apis
diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h
index 7c21664d23d0..815abe30ad09 100644
--- a/fs/ocfs2/dlm/dlmdomain.h
+++ b/fs/ocfs2/dlm/dlmdomain.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmdomain.h
*
* Copyright (C) 2004 Oracle. All rights reserved.
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 83f0760e4fba..041fd1791ae7 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmlock.c
*
* underlying calls for lock creation
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index f105746063ed..4960a6de768d 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmmod.c
*
* standalone DLM module
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index afc51736686c..0e7aad1b11cc 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmrecovery.c
*
* recovery stuff
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 5ccc4ff0b82a..c350bd4df770 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmthread.c
*
* standalone DLM module
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index dcb17ca8ae74..61103b2d69fb 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmunlock.c
*
* underlying calls for unlocking locks
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index b2870f1a31df..fa0a14f199eb 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmfs.c
*
* Code which implements the kernel side of a minimal userspace
diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c
index 339f098d9592..29f183a15798 100644
--- a/fs/ocfs2/dlmfs/userdlm.c
+++ b/fs/ocfs2/dlmfs/userdlm.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* userdlm.c
*
* Code which implements the kernel side of a minimal userspace
diff --git a/fs/ocfs2/dlmfs/userdlm.h b/fs/ocfs2/dlmfs/userdlm.h
index 0558ae768200..47ba18eac423 100644
--- a/fs/ocfs2/dlmfs/userdlm.h
+++ b/fs/ocfs2/dlmfs/userdlm.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* userdlm.h
*
* Userspace dlm defines
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 0fbe8bf7190f..48fd369c29a4 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmglue.c
*
* Code which implements an OCFS2 specific interface to our DLM.
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index b8fbed25df89..e5da5809ed95 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* dlmglue.h
*
* description here
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 69ed278dd84d..eaa8c80ace3c 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* export.c
*
* Functions to facilitate NFS exporting
diff --git a/fs/ocfs2/export.h b/fs/ocfs2/export.h
index d485da0c3439..636357400505 100644
--- a/fs/ocfs2/export.h
+++ b/fs/ocfs2/export.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* export.h
*
* Function prototypes
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 7b93e9c766f6..70a768b623cf 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* extent_map.c
*
* Block/Cluster mapping functions
diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h
index e5464f6cee8a..bc4ed59fb925 100644
--- a/fs/ocfs2/extent_map.h
+++ b/fs/ocfs2/extent_map.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* extent_map.h
*
* In-memory file extent mappings for OCFS2.
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index db8a6265b749..f17c3d33fb18 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* file.c
*
* File open, close, extend, truncate
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 8536cec5f122..71db8f3aa027 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* file.h
*
* Function prototypes
diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c
index 50f11bfdc8c2..90b8d300c1ee 100644
--- a/fs/ocfs2/filecheck.c
+++ b/fs/ocfs2/filecheck.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* filecheck.c
*
* Code which implements online file check.
diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h
index 4d006777ac54..d3bcb8bcfeb0 100644
--- a/fs/ocfs2/filecheck.h
+++ b/fs/ocfs2/filecheck.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* filecheck.h
*
* Online file check.
diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c
index 60c5f995d30c..9099d8fc7599 100644
--- a/fs/ocfs2/heartbeat.c
+++ b/fs/ocfs2/heartbeat.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* heartbeat.c
*
* Register ourselves with the heartbaet service, keep our node maps
diff --git a/fs/ocfs2/heartbeat.h b/fs/ocfs2/heartbeat.h
index 5fedb2d35dc0..f1f8b1802fe4 100644
--- a/fs/ocfs2/heartbeat.h
+++ b/fs/ocfs2/heartbeat.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* heartbeat.h
*
* Function prototypes
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 7c9dfd50c1c1..bc8f32fab964 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* inode.c
*
* vfs' aops, fops, dops and iops
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 51a4f7197987..82b28fdacc7e 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* inode.h
*
* Function prototypes
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index db52e843002a..4e589ce2fce6 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* journal.c
*
* Defines functions of journalling api
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index bfe611ed1b1d..d158acb8b38a 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* journal.h
*
* Defines journalling api and structures.
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index fc8252a28cb1..5f6bacbeef6b 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* localalloc.c
*
* Node local data allocation
diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h
index e8a5cea48639..08f925b7ec6d 100644
--- a/fs/ocfs2/localalloc.h
+++ b/fs/ocfs2/localalloc.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* localalloc.h
*
* Function prototypes
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index 7edc4e5c7c2c..fab7c6a4a7d0 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* locks.c
*
* Userspace file locking support
diff --git a/fs/ocfs2/locks.h b/fs/ocfs2/locks.h
index 389fe1fce3a5..b52de3947d5f 100644
--- a/fs/ocfs2/locks.h
+++ b/fs/ocfs2/locks.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* locks.h
*
* Function prototypes for Userspace file locking support
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 25cabbfe87fc..1834f26522ed 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* mmap.c
*
* Code to deal with the mess that is clustered mmap.
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 758d9661ef1e..192cad0662d8 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* move_extents.c
*
* Copyright (C) 2011 Oracle. All rights reserved.
diff --git a/fs/ocfs2/move_extents.h b/fs/ocfs2/move_extents.h
index 28cac43892c5..987f9e559f30 100644
--- a/fs/ocfs2/move_extents.h
+++ b/fs/ocfs2/move_extents.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* move_extents.h
*
* Copyright (C) 2011 Oracle. All rights reserved.
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 05ced86580d1..2c46ff6ba4ea 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* namei.c
*
* Create and rename file, directory, symlinks
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index cc091ed02b4a..9cc891eb874e 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* namei.h
*
* Function prototypes
diff --git a/fs/ocfs2/ocfs1_fs_compat.h b/fs/ocfs2/ocfs1_fs_compat.h
index 01ae48c4834d..6dbcf3d467fb 100644
--- a/fs/ocfs2/ocfs1_fs_compat.h
+++ b/fs/ocfs2/ocfs1_fs_compat.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs1_fs_compat.h
*
* OCFS1 volume header definitions. OCFS2 creates valid but unmountable
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7993d527edae..bb62cc2e0211 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2.h
*
* Defines macros and structures used in OCFS2
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 19137c6d087b..638d875eccc7 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2_fs.h
*
* On-disk structures for OCFS2.
diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h
index 273616bd4f19..9680797bc531 100644
--- a/fs/ocfs2/ocfs2_ioctl.h
+++ b/fs/ocfs2/ocfs2_ioctl.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2_ioctl.h
*
* Defines OCFS2 ioctls.
diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h
index b4be84956bc1..8ac357ce6a30 100644
--- a/fs/ocfs2/ocfs2_lockid.h
+++ b/fs/ocfs2/ocfs2_lockid.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2_lockid.h
*
* Defines OCFS2 lockid bits.
diff --git a/fs/ocfs2/ocfs2_lockingver.h b/fs/ocfs2/ocfs2_lockingver.h
index 5c9c105b33ee..31a5e1619e7f 100644
--- a/fs/ocfs2/ocfs2_lockingver.h
+++ b/fs/ocfs2/ocfs2_lockingver.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* ocfs2_lockingver.h
*
* Defines OCFS2 Locking version values.
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index c19a463fac55..7f6355cbb587 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* refcounttree.c
*
* Copyright (C) 2009 Oracle. All rights reserved.
diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h
index 0b9014495726..8197a94feec0 100644
--- a/fs/ocfs2/refcounttree.h
+++ b/fs/ocfs2/refcounttree.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* refcounttree.h
*
* Copyright (C) 2009 Oracle. All rights reserved.
diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c
index bf3842e34fb9..769e466887b0 100644
--- a/fs/ocfs2/reservations.c
+++ b/fs/ocfs2/reservations.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* reservations.c
*
* Allocation reservations implementation
diff --git a/fs/ocfs2/reservations.h b/fs/ocfs2/reservations.h
index 6ac88122896d..677c50663595 100644
--- a/fs/ocfs2/reservations.h
+++ b/fs/ocfs2/reservations.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* reservations.h
*
* Allocation reservations function prototypes and structures.
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index 24eb52f9059c..d65d43c61857 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* resize.c
*
* volume resize.
diff --git a/fs/ocfs2/resize.h b/fs/ocfs2/resize.h
index 0af0c023042c..4990637219ef 100644
--- a/fs/ocfs2/resize.h
+++ b/fs/ocfs2/resize.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* resize.h
*
* Function prototypes
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 4da0e4b1e79b..0b0ae3ebb0cf 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* slot_map.c
*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
diff --git a/fs/ocfs2/slot_map.h b/fs/ocfs2/slot_map.h
index 93b53e73f0f7..a43644570b53 100644
--- a/fs/ocfs2/slot_map.h
+++ b/fs/ocfs2/slot_map.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* slotmap.h
*
* description here
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index f70012038383..88f75f7f02d7 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* stack_o2cb.c
*
* Code which interfaces ocfs2 with the o2cb stack.
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 7397064c3f35..85a47621e0c0 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* stack_user.c
*
* Code which interfaces ocfs2 with fs/dlm and a userspace stack.
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 8d33ebc6b6fc..d50e8b8dfea4 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* stackglue.c
*
* Code which implements an OCFS2 specific interface to underlying
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index e9d26cbeb3b8..3636847fae19 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* stackglue.h
*
* Glue to the underlying cluster stack.
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 8c8cf7f4eb34..8521942f5af2 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* suballoc.c
*
* metadata alloc and free
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 50b36250beb6..5805a03d100b 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* suballoc.h
*
* Defines sub allocator api
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 079f8826993e..c86bd4e60e20 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* super.c
*
* load/unload driver, mount/dismount volumes
diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h
index 76facaf63336..8312651135b9 100644
--- a/fs/ocfs2/super.h
+++ b/fs/ocfs2/super.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* super.h
*
* Function prototypes
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index 94cfacc9bad7..f755a4985821 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -1,6 +1,4 @@
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* linux/cluster/ssi/cfs/symlink.c
*
* This program is free software; you can redistribute it and/or
diff --git a/fs/ocfs2/symlink.h b/fs/ocfs2/symlink.h
index 167094d1e5aa..ffcf0210545c 100644
--- a/fs/ocfs2/symlink.h
+++ b/fs/ocfs2/symlink.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* symlink.h
*
* Function prototypes
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index bb701c4e449f..53a945da873b 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* sysfile.c
*
* Initialize, read, write, etc. system files.
diff --git a/fs/ocfs2/sysfile.h b/fs/ocfs2/sysfile.h
index a83dd962fccb..2b38c75990fd 100644
--- a/fs/ocfs2/sysfile.h
+++ b/fs/ocfs2/sysfile.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* sysfile.h
*
* Function prototypes
diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c
index 580852ba05c4..09854925fa5c 100644
--- a/fs/ocfs2/uptodate.c
+++ b/fs/ocfs2/uptodate.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* uptodate.c
*
* Tracking the up-to-date-ness of a local buffer_head with respect to
diff --git a/fs/ocfs2/uptodate.h b/fs/ocfs2/uptodate.h
index 77a30cae4879..85d94134001b 100644
--- a/fs/ocfs2/uptodate.h
+++ b/fs/ocfs2/uptodate.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* uptodate.h
*
* Cluster uptodate tracking
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 36ae47a4aef6..dd784eb0cd7c 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* xattr.c
*
* Copyright (C) 2004, 2008 Oracle. All rights reserved.
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
index 9c80382da1f5..00308b57f64f 100644
--- a/fs/ocfs2/xattr.h
+++ b/fs/ocfs2/xattr.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
* xattr.h
*
* Copyright (C) 2004, 2008 Oracle. All rights reserved.
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index bc86aa87cc41..5b78739e60e4 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -166,15 +166,8 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
const char *cp = name, *next;
struct proc_dir_entry *de;
- de = *ret;
- if (!de)
- de = &proc_root;
-
- while (1) {
- next = strchr(cp, '/');
- if (!next)
- break;
-
+ de = *ret ?: &proc_root;
+ while ((next = strchr(cp, '/')) != NULL) {
de = pde_subdir_find(de, cp, next - cp);
if (!de) {
WARN(1, "name '%s'\n", name);
@@ -756,7 +749,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
while (1) {
next = pde_subdir_first(de);
if (next) {
- if (unlikely(pde_is_permanent(root))) {
+ if (unlikely(pde_is_permanent(next))) {
write_unlock(&proc_subdir_lock);
WARN(1, "removing permanent /proc entry '%s/%s'",
next->parent->name, next->name);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index bde6b6f69852..599eb724ff2d 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -273,25 +273,15 @@ void proc_entry_rundown(struct proc_dir_entry *de)
spin_unlock(&de->pde_unload_lock);
}
-static loff_t pde_lseek(struct proc_dir_entry *pde, struct file *file, loff_t offset, int whence)
-{
- typeof_member(struct proc_ops, proc_lseek) lseek;
-
- lseek = pde->proc_ops->proc_lseek;
- if (!lseek)
- lseek = default_llseek;
- return lseek(file, offset, whence);
-}
-
static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
loff_t rv = -EINVAL;
if (pde_is_permanent(pde)) {
- return pde_lseek(pde, file, offset, whence);
+ return pde->proc_ops->proc_lseek(file, offset, whence);
} else if (use_pde(pde)) {
- rv = pde_lseek(pde, file, offset, whence);
+ rv = pde->proc_ops->proc_lseek(file, offset, whence);
unuse_pde(pde);
}
return rv;
@@ -493,7 +483,6 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
static int proc_reg_open(struct inode *inode, struct file *file)
{
- struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
typeof_member(struct proc_ops, proc_open) open;
@@ -507,9 +496,6 @@ static int proc_reg_open(struct inode *inode, struct file *file)
return rv;
}
- if (fs_info->pidonly == PROC_PIDONLY_ON)
- return -ENOENT;
-
/*
* Ensure that
* 1) PDE's ->release hook will be called no matter what
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 66c7dd11bd7c..dea0f5ee540c 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1563,7 +1563,7 @@ err_register_leaves:
}
/**
- * register_sysctl_table_path - register a sysctl table hierarchy
+ * register_sysctl_paths - register a sysctl table hierarchy
* @path: The path to the directory the sysctl table is in.
* @table: the top-level table structure
*
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e862cab69583..fc9784544b24 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -661,6 +661,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_PKEY_BIT4)] = "",
#endif
#endif /* CONFIG_ARCH_HAS_PKEYS */
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+ [ilog2(VM_UFFD_MINOR)] = "ui",
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
};
size_t i;
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 155b82870333..4a7cb16e9345 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -488,13 +488,3 @@ int reiserfs_proc_info_global_done(void)
* (available at http://www.namesys.com/legalese.html)
*
*/
-
-/*
- * Make Linus happy.
- * Local variables:
- * c-indentation-style: "K&R"
- * mode-name: "LC"
- * c-basic-offset: 8
- * tab-width: 8
- * End:
- */
diff --git a/fs/unicode/.gitignore b/fs/unicode/.gitignore
index 9b2467e77b2d..361294571ab0 100644
--- a/fs/unicode/.gitignore
+++ b/fs/unicode/.gitignore
@@ -1,3 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
-mkutf8data
-utf8data.h
+/mkutf8data
+/utf8data.h
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 0be8cdd4425a..14f92285d04f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/mm.h>
+#include <linux/mmu_notifier.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
@@ -196,24 +197,21 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
msg_init(&msg);
msg.event = UFFD_EVENT_PAGEFAULT;
msg.arg.pagefault.address = address;
+ /*
+ * These flags indicate why the userfault occurred:
+ * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
+ * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault.
+ * - Neither of these flags being set indicates a MISSING fault.
+ *
+ * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write
+ * fault. Otherwise, it was a read fault.
+ */
if (flags & FAULT_FLAG_WRITE)
- /*
- * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
- * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE
- * was not set in a UFFD_EVENT_PAGEFAULT, it means it
- * was a read fault, otherwise if set it means it's
- * a write fault.
- */
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
if (reason & VM_UFFD_WP)
- /*
- * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
- * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was
- * not set in a UFFD_EVENT_PAGEFAULT, it means it was
- * a missing fault, otherwise if set it means it's a
- * write protect fault.
- */
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
+ if (reason & VM_UFFD_MINOR)
+ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR;
if (features & UFFD_FEATURE_THREAD_ID)
msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
return msg;
@@ -400,8 +398,10 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
BUG_ON(ctx->mm != mm);
- VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
- VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));
+ /* Any unrecognized flag is a bug. */
+ VM_BUG_ON(reason & ~__VM_UFFD_FLAGS);
+ /* 0 or > 1 flags set is a bug; we expect exactly 1. */
+ VM_BUG_ON(!reason || (reason & (reason - 1)));
if (ctx->features & UFFD_FEATURE_SIGBUS)
goto out;
@@ -611,7 +611,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
for (vma = mm->mmap; vma; vma = vma->vm_next)
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ vma->vm_flags &= ~__VM_UFFD_FLAGS;
}
mmap_write_unlock(mm);
@@ -643,7 +643,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ vma->vm_flags &= ~__VM_UFFD_FLAGS;
return 0;
}
@@ -725,7 +725,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
} else {
/* Drop uffd context if remap feature not enabled */
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ vma->vm_flags &= ~__VM_UFFD_FLAGS;
}
}
@@ -866,12 +866,12 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
- !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+ !!(vma->vm_flags & __VM_UFFD_FLAGS));
if (vma->vm_userfaultfd_ctx.ctx != ctx) {
prev = vma;
continue;
}
- new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+ new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
new_flags, vma->anon_vma,
vma->vm_file, vma->vm_pgoff,
@@ -1261,9 +1261,19 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
unsigned long vm_flags)
{
/* FIXME: add WP support to hugetlbfs and shmem */
- return vma_is_anonymous(vma) ||
- ((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
- !(vm_flags & VM_UFFD_WP));
+ if (vm_flags & VM_UFFD_WP) {
+ if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
+ return false;
+ }
+
+ if (vm_flags & VM_UFFD_MINOR) {
+ /* FIXME: Add minor fault interception for shmem. */
+ if (!is_vm_hugetlb_page(vma))
+ return false;
+ }
+
+ return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
+ vma_is_shmem(vma);
}
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
@@ -1289,14 +1299,19 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
ret = -EINVAL;
if (!uffdio_register.mode)
goto out;
- if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
- UFFDIO_REGISTER_MODE_WP))
+ if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES)
goto out;
vm_flags = 0;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
vm_flags |= VM_UFFD_MISSING;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
vm_flags |= VM_UFFD_WP;
+ if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+ goto out;
+#endif
+ vm_flags |= VM_UFFD_MINOR;
+ }
ret = validate_range(mm, &uffdio_register.range.start,
uffdio_register.range.len);
@@ -1340,7 +1355,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
- !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+ !!(cur->vm_flags & __VM_UFFD_FLAGS));
/* check not compatible vmas */
ret = -EINVAL;
@@ -1420,8 +1435,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
- new_flags = (vma->vm_flags &
- ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags;
+ new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
@@ -1449,6 +1463,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx.ctx = ctx;
+ if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
+ hugetlb_unshare_all_pmds(vma);
+
skip:
prev = vma;
start = vma->vm_end;
@@ -1470,6 +1487,10 @@ out_unlock:
if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
+ /* CONTINUE ioctl is only supported for MINOR ranges. */
+ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR))
+ ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE);
+
/*
* Now that we scanned all vmas we can already tell
* userland which ioctls methods are guaranteed to
@@ -1540,7 +1561,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
- !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+ !!(cur->vm_flags & __VM_UFFD_FLAGS));
/*
* Check not compatible vmas, not strictly required
@@ -1591,7 +1612,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
}
- new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+ new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
@@ -1823,6 +1844,66 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
return ret;
}
+static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
+{
+ __s64 ret;
+ struct uffdio_continue uffdio_continue;
+ struct uffdio_continue __user *user_uffdio_continue;
+ struct userfaultfd_wake_range range;
+
+ user_uffdio_continue = (struct uffdio_continue __user *)arg;
+
+ ret = -EAGAIN;
+ if (READ_ONCE(ctx->mmap_changing))
+ goto out;
+
+ ret = -EFAULT;
+ if (copy_from_user(&uffdio_continue, user_uffdio_continue,
+ /* don't copy the output fields */
+ sizeof(uffdio_continue) - (sizeof(__s64))))
+ goto out;
+
+ ret = validate_range(ctx->mm, &uffdio_continue.range.start,
+ uffdio_continue.range.len);
+ if (ret)
+ goto out;
+
+ ret = -EINVAL;
+ /* double check for wraparound just in case. */
+ if (uffdio_continue.range.start + uffdio_continue.range.len <=
+ uffdio_continue.range.start) {
+ goto out;
+ }
+ if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE)
+ goto out;
+
+ if (mmget_not_zero(ctx->mm)) {
+ ret = mcopy_continue(ctx->mm, uffdio_continue.range.start,
+ uffdio_continue.range.len,
+ &ctx->mmap_changing);
+ mmput(ctx->mm);
+ } else {
+ return -ESRCH;
+ }
+
+ if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+ return -EFAULT;
+ if (ret < 0)
+ goto out;
+
+ /* len == 0 would wake all */
+ BUG_ON(!ret);
+ range.len = ret;
+ if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) {
+ range.start = uffdio_continue.range.start;
+ wake_userfault(ctx, &range);
+ }
+ ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN;
+
+out:
+ return ret;
+}
+
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
@@ -1859,6 +1940,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
goto err_out;
/* report all available features and ioctls to userland */
uffdio_api.features = UFFD_API_FEATURES;
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+ uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS;
+#endif
uffdio_api.ioctls = UFFD_API_IOCTLS;
ret = -EFAULT;
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
@@ -1907,6 +1991,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
case UFFDIO_WRITEPROTECT:
ret = userfaultfd_writeprotect(ctx, arg);
break;
+ case UFFDIO_CONTINUE:
+ ret = userfaultfd_continue(ctx, arg);
+ break;
}
return ret;
}
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 6c5f8d10589c..e32a1833d523 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -253,7 +253,8 @@ xfs_ag_resv_init(
xfs_agnumber_t agno = pag->pag_agno;
xfs_extlen_t ask;
xfs_extlen_t used;
- int error = 0;
+ int error = 0, error2;
+ bool has_resv = false;
/* Create the metadata reservation. */
if (pag->pag_meta_resv.ar_asked == 0) {
@@ -291,6 +292,8 @@ xfs_ag_resv_init(
if (error)
goto out;
}
+ if (ask)
+ has_resv = true;
}
/* Create the RMAPBT metadata reservation */
@@ -304,19 +307,28 @@ xfs_ag_resv_init(
error = __xfs_ag_resv_init(pag, XFS_AG_RESV_RMAPBT, ask, used);
if (error)
goto out;
+ if (ask)
+ has_resv = true;
}
-#ifdef DEBUG
- /* need to read in the AGF for the ASSERT below to work */
- error = xfs_alloc_pagf_init(pag->pag_mount, tp, pag->pag_agno, 0);
- if (error)
- return error;
-
- ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
- xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <=
- pag->pagf_freeblks + pag->pagf_flcount);
-#endif
out:
+ /*
+ * Initialize the pagf if we have at least one active reservation on the
+ * AG. This may have occurred already via reservation calculation, but
+ * fall back to an explicit init to ensure the in-core allocbt usage
+ * counters are initialized as soon as possible. This is important
+ * because filesystems with large perag reservations are susceptible to
+ * free space reservation problems that the allocbt counter is used to
+ * address.
+ */
+ if (has_resv) {
+ error2 = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, 0);
+ if (error2)
+ return error2;
+ ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
+ xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <=
+ pag->pagf_freeblks + pag->pagf_flcount);
+ }
return error;
}
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index aaa19101bb2a..82b7cbb1f24f 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -718,7 +718,6 @@ xfs_alloc_update_counters(
agbp->b_pag->pagf_freeblks += len;
be32_add_cpu(&agf->agf_freeblks, len);
- xfs_trans_agblocks_delta(tp, len);
if (unlikely(be32_to_cpu(agf->agf_freeblks) >
be32_to_cpu(agf->agf_length))) {
xfs_buf_mark_corrupt(agbp);
@@ -2739,7 +2738,6 @@ xfs_alloc_get_freelist(
pag = agbp->b_pag;
ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, -1);
- xfs_trans_agflist_delta(tp, -1);
pag->pagf_flcount--;
logflags = XFS_AGF_FLFIRST | XFS_AGF_FLCOUNT;
@@ -2846,7 +2844,6 @@ xfs_alloc_put_freelist(
pag = agbp->b_pag;
ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, 1);
- xfs_trans_agflist_delta(tp, 1);
pag->pagf_flcount++;
logflags = XFS_AGF_FLLAST | XFS_AGF_FLCOUNT;
@@ -3036,6 +3033,7 @@ xfs_alloc_read_agf(
struct xfs_agf *agf; /* ag freelist header */
struct xfs_perag *pag; /* per allocation group data */
int error;
+ int allocbt_blks;
trace_xfs_alloc_read_agf(mp, agno);
@@ -3066,6 +3064,19 @@ xfs_alloc_read_agf(
pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
pag->pagf_init = 1;
pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
+
+ /*
+ * Update the in-core allocbt counter. Filter out the rmapbt
+ * subset of the btreeblks counter because the rmapbt is managed
+ * by perag reservation. Subtract one for the rmapbt root block
+ * because the rmap counter includes it while the btreeblks
+ * counter only tracks non-root blocks.
+ */
+ allocbt_blks = pag->pagf_btreeblks;
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb))
+ allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1;
+ if (allocbt_blks > 0)
+ atomic64_add(allocbt_blks, &mp->m_allocbt_blks);
}
#ifdef DEBUG
else if (!XFS_FORCED_SHUTDOWN(mp)) {
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 8e01231b308e..a43e4c50e69b 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -71,9 +71,9 @@ xfs_allocbt_alloc_block(
return 0;
}
+ atomic64_inc(&cur->bc_mp->m_allocbt_blks);
xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agno, bno, 1, false);
- xfs_trans_agbtree_delta(cur->bc_tp, 1);
new->s = cpu_to_be32(bno);
*stat = 1;
@@ -95,9 +95,9 @@ xfs_allocbt_free_block(
if (error)
return error;
+ atomic64_dec(&cur->bc_mp->m_allocbt_blks);
xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
- xfs_trans_agbtree_delta(cur->bc_tp, -1);
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 8bd00da6d2a4..3e15ea29fb8d 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -368,10 +368,10 @@ static inline int xfs_ilog_fdata(int w)
* directly mirrors the xfs_dinode structure as it must contain all the same
* information.
*/
-typedef uint64_t xfs_ictimestamp_t;
+typedef uint64_t xfs_log_timestamp_t;
/* Legacy timestamp encoding format. */
-struct xfs_legacy_ictimestamp {
+struct xfs_log_legacy_timestamp {
int32_t t_sec; /* timestamp seconds */
int32_t t_nsec; /* timestamp nanoseconds */
};
@@ -393,9 +393,9 @@ struct xfs_log_dinode {
uint16_t di_projid_hi; /* higher part of owner's project id */
uint8_t di_pad[6]; /* unused, zeroed space */
uint16_t di_flushiter; /* incremented on flush */
- xfs_ictimestamp_t di_atime; /* time last accessed */
- xfs_ictimestamp_t di_mtime; /* time last modified */
- xfs_ictimestamp_t di_ctime; /* time created/inode modified */
+ xfs_log_timestamp_t di_atime; /* time last accessed */
+ xfs_log_timestamp_t di_mtime; /* time last modified */
+ xfs_log_timestamp_t di_ctime; /* time created/inode modified */
xfs_fsize_t di_size; /* number of bytes in file */
xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */
xfs_extlen_t di_extsize; /* basic/minimum extent size for file */
@@ -420,7 +420,7 @@ struct xfs_log_dinode {
uint8_t di_pad2[12]; /* more padding for future expansion */
/* fields only written to during inode creation */
- xfs_ictimestamp_t di_crtime; /* time created */
+ xfs_log_timestamp_t di_crtime; /* time created */
xfs_ino_t di_ino; /* inode number */
uuid_t di_uuid; /* UUID of the filesystem */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index beb81c84a937..9f5bcbd834c3 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -103,7 +103,6 @@ xfs_rmapbt_alloc_block(
xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agno, bno, 1,
false);
- xfs_trans_agbtree_delta(cur->bc_tp, 1);
new->s = cpu_to_be32(bno);
be32_add_cpu(&agf->agf_rmap_blocks, 1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
@@ -136,7 +135,6 @@ xfs_rmapbt_free_block(
xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
- xfs_trans_agbtree_delta(cur->bc_tp, -1);
pag = cur->bc_ag.agbp->b_pag;
xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 60e6d255e5e2..dfbbcbd448c1 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -926,9 +926,19 @@ xfs_log_sb(
struct xfs_mount *mp = tp->t_mountp;
struct xfs_buf *bp = xfs_trans_getsb(tp);
- mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
- mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
- mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+ /*
+ * Lazy sb counters don't update the in-core superblock so do that now.
+ * If this is at unmount, the counters will be exactly correct, but at
+ * any other time they will only be ballpark correct because of
+ * reservations that have been taken out percpu counters. If we have an
+ * unclean shutdown, this will be corrected by log recovery rebuilding
+ * the counters from the AGF block counts.
+ */
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb)) {
+ mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+ mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
+ mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+ }
xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 749faa17f8e2..7a2f9b5f2db5 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -416,6 +416,10 @@ xchk_agf_xref_btreeblks(
xfs_agblock_t btreeblks;
int error;
+ /* agf_btreeblks didn't exist before lazysbcount */
+ if (!xfs_sb_version_haslazysbcount(&sc->mp->m_sb))
+ return;
+
/* Check agf_rmap_blocks; set up for agf_btreeblks check */
if (sc->sa.rmap_cur) {
error = xfs_btree_count_blocks(sc->sa.rmap_cur, &blocks);
@@ -581,7 +585,8 @@ xchk_agf(
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
if (pag->pagf_flcount != be32_to_cpu(agf->agf_flcount))
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
- if (pag->pagf_btreeblks != be32_to_cpu(agf->agf_btreeblks))
+ if (xfs_sb_version_haslazysbcount(&sc->mp->m_sb) &&
+ pag->pagf_btreeblks != be32_to_cpu(agf->agf_btreeblks))
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
xfs_perag_put(pag);
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 7b4386c78fbf..f1d1a8c58853 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -13,6 +13,7 @@
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_health.h"
+#include "xfs_btree.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
@@ -143,6 +144,35 @@ xchk_setup_fscounters(
return xchk_trans_alloc(sc, 0);
}
+/* Count free space btree blocks manually for pre-lazysbcount filesystems. */
+static int
+xchk_fscount_btreeblks(
+ struct xfs_scrub *sc,
+ struct xchk_fscounters *fsc,
+ xfs_agnumber_t agno)
+{
+ xfs_extlen_t blocks;
+ int error;
+
+ error = xchk_ag_init(sc, agno, &sc->sa);
+ if (error)
+ return error;
+
+ error = xfs_btree_count_blocks(sc->sa.bno_cur, &blocks);
+ if (error)
+ goto out_free;
+ fsc->fdblocks += blocks - 1;
+
+ error = xfs_btree_count_blocks(sc->sa.cnt_cur, &blocks);
+ if (error)
+ goto out_free;
+ fsc->fdblocks += blocks - 1;
+
+out_free:
+ xchk_ag_free(sc, &sc->sa);
+ return error;
+}
+
/*
* Calculate what the global in-core counters ought to be from the incore
* per-AG structure. Callers can compare this to the actual in-core counters
@@ -182,7 +212,15 @@ retry:
/* Add up the free/freelist/bnobt/cntbt blocks */
fsc->fdblocks += pag->pagf_freeblks;
fsc->fdblocks += pag->pagf_flcount;
- fsc->fdblocks += pag->pagf_btreeblks;
+ if (xfs_sb_version_haslazysbcount(&sc->mp->m_sb)) {
+ fsc->fdblocks += pag->pagf_btreeblks;
+ } else {
+ error = xchk_fscount_btreeblks(sc, fsc, agno);
+ if (error) {
+ xfs_perag_put(pag);
+ break;
+ }
+ }
/*
* Per-AG reservations are taken out of the incore counters,
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 9b08db45ce85..826caa6b4a5a 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -146,7 +146,7 @@ xfs_end_io(
while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
io_list))) {
list_del_init(&ioend->io_list);
- iomap_ioend_try_merge(ioend, &tmp, NULL);
+ iomap_ioend_try_merge(ioend, &tmp);
xfs_end_ioend(ioend);
}
}
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index b33c894b6cf3..be9cf88d2ad7 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -69,8 +69,6 @@ xfs_resizefs_init_new_ags(
if (error)
return error;
- xfs_trans_agblocks_delta(tp, id->nfree);
-
if (delta) {
*lastag_extended = true;
error = xfs_ag_extend_space(mp, tp, id, delta);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index c1b32680f71c..6764d12342da 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -299,18 +299,18 @@ xfs_inode_item_format_attr_fork(
* Convert an incore timestamp to a log timestamp. Note that the log format
* specifies host endian format!
*/
-static inline xfs_ictimestamp_t
+static inline xfs_log_timestamp_t
xfs_inode_to_log_dinode_ts(
struct xfs_inode *ip,
const struct timespec64 tv)
{
- struct xfs_legacy_ictimestamp *lits;
- xfs_ictimestamp_t its;
+ struct xfs_log_legacy_timestamp *lits;
+ xfs_log_timestamp_t its;
if (xfs_inode_has_bigtime(ip))
return xfs_inode_encode_bigtime(tv);
- lits = (struct xfs_legacy_ictimestamp *)&its;
+ lits = (struct xfs_log_legacy_timestamp *)&its;
lits->t_sec = tv.tv_sec;
lits->t_nsec = tv.tv_nsec;
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index cb44f7653f03..7b79518b6c20 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -125,17 +125,17 @@ static inline bool xfs_log_dinode_has_bigtime(const struct xfs_log_dinode *ld)
static inline xfs_timestamp_t
xfs_log_dinode_to_disk_ts(
struct xfs_log_dinode *from,
- const xfs_ictimestamp_t its)
+ const xfs_log_timestamp_t its)
{
struct xfs_legacy_timestamp *lts;
- struct xfs_legacy_ictimestamp *lits;
+ struct xfs_log_legacy_timestamp *lits;
xfs_timestamp_t ts;
if (xfs_log_dinode_has_bigtime(from))
return cpu_to_be64(its);
lts = (struct xfs_legacy_timestamp *)&ts;
- lits = (struct xfs_legacy_ictimestamp *)&its;
+ lits = (struct xfs_log_legacy_timestamp *)&its;
lts->t_sec = cpu_to_be32(lits->t_sec);
lts->t_nsec = cpu_to_be32(lits->t_nsec);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 06041834daa3..c19a82adea1e 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -355,13 +355,15 @@ xfs_log_writable(
struct xfs_mount *mp)
{
/*
- * Never write to the log on norecovery mounts, if the block device is
- * read-only, or if the filesystem is shutdown. Read-only mounts still
- * allow internal writes for log recovery and unmount purposes, so don't
- * restrict that case here.
+ * Do not write to the log on norecovery mounts, if the data or log
+ * devices are read-only, or if the filesystem is shutdown. Read-only
+ * mounts allow internal writes for log recovery and unmount purposes,
+ * so don't restrict that case.
*/
if (mp->m_flags & XFS_MOUNT_NORECOVERY)
return false;
+ if (xfs_readonly_buftarg(mp->m_ddev_targp))
+ return false;
if (xfs_readonly_buftarg(mp->m_log->l_targ))
return false;
if (XFS_FORCED_SHUTDOWN(mp))
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index cb1e2c4702c3..bdfee1943796 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1188,6 +1188,7 @@ xfs_mod_fdblocks(
int64_t lcounter;
long long res_used;
s32 batch;
+ uint64_t set_aside;
if (delta > 0) {
/*
@@ -1227,8 +1228,20 @@ xfs_mod_fdblocks(
else
batch = XFS_FDBLOCKS_BATCH;
+ /*
+ * Set aside allocbt blocks because these blocks are tracked as free
+ * space but not available for allocation. Technically this means that a
+ * single reservation cannot consume all remaining free space, but the
+ * ratio of allocbt blocks to usable free blocks should be rather small.
+ * The tradeoff without this is that filesystems that maintain high
+ * perag block reservations can over reserve physical block availability
+ * and fail physical allocation, which leads to much more serious
+ * problems (i.e. transaction abort, pagecache discards, etc.) than
+ * slightly premature -ENOSPC.
+ */
+ set_aside = mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
percpu_counter_add_batch(&mp->m_fdblocks, delta, batch);
- if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside,
+ if (__percpu_counter_compare(&mp->m_fdblocks, set_aside,
XFS_FDBLOCKS_BATCH) >= 0) {
/* we had space! */
return 0;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 81829d19596e..bb67274ee23f 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -170,6 +170,12 @@ typedef struct xfs_mount {
* extents or anything related to the rt device.
*/
struct percpu_counter m_delalloc_blks;
+ /*
+ * Global count of allocation btree blocks in use across all AGs. Only
+ * used when perag reservation is enabled. Helps prevent block
+ * reservation from attempting to reserve allocation btree blocks.
+ */
+ atomic64_t m_allocbt_blks;
struct radix_tree_root m_perag_tree; /* per-ag accounting info */
spinlock_t m_perag_lock; /* lock for m_perag_tree */
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index 0aa87c210104..25991923c1a8 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -126,8 +126,8 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode, 176);
XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28);
- XFS_CHECK_STRUCT_SIZE(xfs_ictimestamp_t, 8);
- XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_ictimestamp, 8);
+ XFS_CHECK_STRUCT_SIZE(xfs_log_timestamp_t, 8);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_log_legacy_timestamp, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52);
XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56);
XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 4dd4af6ac2ef..060695d6d56a 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1522,7 +1522,8 @@ xfs_reflink_unshare(
if (error)
goto out;
- error = filemap_write_and_wait_range(inode->i_mapping, offset, len);
+ error = filemap_write_and_wait_range(inode->i_mapping, offset,
+ offset + len - 1);
if (error)
goto out;
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index bcc978011869..586f2992b789 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -488,13 +488,6 @@ xfs_trans_apply_sb_deltas(
sbp = bp->b_addr;
/*
- * Check that superblock mods match the mods made to AGF counters.
- */
- ASSERT((tp->t_fdblocks_delta + tp->t_res_fdblocks_delta) ==
- (tp->t_ag_freeblks_delta + tp->t_ag_flist_delta +
- tp->t_ag_btree_delta));
-
- /*
* Only update the superblock counters if we are logging them
*/
if (!xfs_sb_version_haslazysbcount(&(tp->t_mountp->m_sb))) {
@@ -629,6 +622,9 @@ xfs_trans_unreserve_and_mod_sb(
/* apply remaining deltas */
spin_lock(&mp->m_sb_lock);
+ mp->m_sb.sb_fdblocks += tp->t_fdblocks_delta + tp->t_res_fdblocks_delta;
+ mp->m_sb.sb_icount += idelta;
+ mp->m_sb.sb_ifree += ifreedelta;
mp->m_sb.sb_frextents += rtxdelta;
mp->m_sb.sb_dblocks += tp->t_dblocks_delta;
mp->m_sb.sb_agcount += tp->t_agcount_delta;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 9dd745cf77c9..ee42d98d9011 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -140,11 +140,6 @@ typedef struct xfs_trans {
int64_t t_res_fdblocks_delta; /* on-disk only chg */
int64_t t_frextents_delta;/* superblock freextents chg*/
int64_t t_res_frextents_delta; /* on-disk only chg */
-#if defined(DEBUG) || defined(XFS_WARN)
- int64_t t_ag_freeblks_delta; /* debugging counter */
- int64_t t_ag_flist_delta; /* debugging counter */
- int64_t t_ag_btree_delta; /* debugging counter */
-#endif
int64_t t_dblocks_delta;/* superblock dblocks change */
int64_t t_agcount_delta;/* superblock agcount change */
int64_t t_imaxpct_delta;/* superblock imaxpct change */
@@ -165,16 +160,6 @@ typedef struct xfs_trans {
*/
#define xfs_trans_set_sync(tp) ((tp)->t_flags |= XFS_TRANS_SYNC)
-#if defined(DEBUG) || defined(XFS_WARN)
-#define xfs_trans_agblocks_delta(tp, d) ((tp)->t_ag_freeblks_delta += (int64_t)d)
-#define xfs_trans_agflist_delta(tp, d) ((tp)->t_ag_flist_delta += (int64_t)d)
-#define xfs_trans_agbtree_delta(tp, d) ((tp)->t_ag_btree_delta += (int64_t)d)
-#else
-#define xfs_trans_agblocks_delta(tp, d)
-#define xfs_trans_agflist_delta(tp, d)
-#define xfs_trans_agbtree_delta(tp, d)
-#endif
-
/*
* XFS transaction mechanism exported interfaces.
*/