aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/affs/amigaffs.c3
-rw-r--r--fs/aio.c3
-rw-r--r--fs/autofs4/root.c4
-rw-r--r--fs/autofs4/waitq.c6
-rw-r--r--fs/bio.c2
-rw-r--r--fs/block_dev.c6
-rw-r--r--fs/btrfs/extent-tree.c20
-rw-r--r--fs/buffer.c10
-rw-r--r--fs/ceph/addr.c38
-rw-r--r--fs/ceph/caps.c32
-rw-r--r--fs/ceph/file.c8
-rw-r--r--fs/ceph/ioctl.c6
-rw-r--r--fs/ceph/mds_client.c33
-rw-r--r--fs/ceph/mds_client.h6
-rw-r--r--fs/ceph/mdsmap.c12
-rw-r--r--fs/ceph/strings.c4
-rw-r--r--fs/ceph/super.c7
-rw-r--r--fs/ceph/super.h10
-rw-r--r--fs/ceph/xattr.c214
-rw-r--r--fs/cifs/inode.c3
-rw-r--r--fs/coredump.c2
-rw-r--r--fs/dcache.c9
-rw-r--r--fs/dlm/lock.c18
-rw-r--r--fs/dlm/lockspace.c1
-rw-r--r--fs/dlm/lowcomms.c11
-rw-r--r--fs/dlm/recover.c52
-rw-r--r--fs/ecryptfs/messaging.c6
-rw-r--r--fs/exec.c10
-rw-r--r--fs/exportfs/expfs.c3
-rw-r--r--fs/ext4/inode.c8
-rw-r--r--fs/fat/fat.h2
-rw-r--r--fs/fat/inode.c77
-rw-r--r--fs/fat/nfs.c3
-rw-r--r--fs/fs-writeback.c60
-rw-r--r--fs/fscache/cookie.c11
-rw-r--r--fs/hfsplus/Makefile4
-rw-r--r--fs/hfsplus/attributes.c399
-rw-r--r--fs/hfsplus/bfind.c93
-rw-r--r--fs/hfsplus/bnode.c8
-rw-r--r--fs/hfsplus/brec.c23
-rw-r--r--fs/hfsplus/btree.c8
-rw-r--r--fs/hfsplus/catalog.c36
-rw-r--r--fs/hfsplus/dir.c55
-rw-r--r--fs/hfsplus/extents.c4
-rw-r--r--fs/hfsplus/hfsplus_fs.h52
-rw-r--r--fs/hfsplus/hfsplus_raw.h68
-rw-r--r--fs/hfsplus/inode.c18
-rw-r--r--fs/hfsplus/ioctl.c108
-rw-r--r--fs/hfsplus/super.c56
-rw-r--r--fs/hfsplus/unicode.c7
-rw-r--r--fs/hfsplus/xattr.c709
-rw-r--r--fs/hfsplus/xattr.h60
-rw-r--r--fs/hfsplus/xattr_security.c104
-rw-r--r--fs/hfsplus/xattr_trusted.c63
-rw-r--r--fs/hfsplus/xattr_user.c63
-rw-r--r--fs/inode.c19
-rw-r--r--fs/lockd/clntlock.c14
-rw-r--r--fs/lockd/clntproc.c6
-rw-r--r--fs/lockd/host.c30
-rw-r--r--fs/lockd/mon.c1
-rw-r--r--fs/lockd/svcsubs.c9
-rw-r--r--fs/nfs/cache_lib.c12
-rw-r--r--fs/nfs/cache_lib.h2
-rw-r--r--fs/nfs/client.c1
-rw-r--r--fs/nfs/dns_resolve.c67
-rw-r--r--fs/nfs/nfs4client.c14
-rw-r--r--fs/nfs/nfs4filelayoutdev.c1
-rw-r--r--fs/nfs/nfs4namespace.c1
-rw-r--r--fs/nfs/pnfs_dev.c9
-rw-r--r--fs/nfs/super.c1
-rw-r--r--fs/nfsd/cache.h17
-rw-r--r--fs/nfsd/export.c16
-rw-r--r--fs/nfsd/fault_inject.c2
-rw-r--r--fs/nfsd/nfs4idmap.c16
-rw-r--r--fs/nfsd/nfs4proc.c7
-rw-r--r--fs/nfsd/nfs4recover.c6
-rw-r--r--fs/nfsd/nfs4state.c101
-rw-r--r--fs/nfsd/nfs4xdr.c21
-rw-r--r--fs/nfsd/nfscache.c353
-rw-r--r--fs/nfsd/nfsctl.c81
-rw-r--r--fs/nfsd/nfssvc.c6
-rw-r--r--fs/nfsd/xdr4.h2
-rw-r--r--fs/notify/fsnotify.c3
-rw-r--r--fs/notify/inode_mark.c19
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c1
-rw-r--r--fs/notify/inotify/inotify_user.c24
-rw-r--r--fs/notify/vfsmount_mark.c19
-rw-r--r--fs/ocfs2/cluster/tcp.c32
-rw-r--r--fs/ocfs2/dcache.c3
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c6
-rw-r--r--fs/ocfs2/suballoc.c7
-rw-r--r--fs/ocfs2/suballoc.h2
-rw-r--r--fs/ocfs2/xattr.c2
-rw-r--r--fs/proc/base.c3
-rw-r--r--fs/proc/generic.c27
-rw-r--r--fs/proc/inode.c5
-rw-r--r--fs/proc/internal.h3
-rw-r--r--fs/proc/kcore.c3
-rw-r--r--fs/proc/proc_devtree.c13
-rw-r--r--fs/proc/proc_sysctl.c19
-rw-r--r--fs/proc/vmcore.c35
-rw-r--r--fs/seq_file.c40
-rw-r--r--fs/super.c8
-rw-r--r--fs/sysfs/bin.c3
-rw-r--r--fs/xfs/xfs_log_recover.c3
105 files changed, 2847 insertions, 886 deletions
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index eb82ee53ee0..d9a43674cb9 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -125,9 +125,8 @@ static void
affs_fix_dcache(struct inode *inode, u32 entry_ino)
{
struct dentry *dentry;
- struct hlist_node *p;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
if (entry_ino == (u32)(long)dentry->d_fsdata) {
dentry->d_fsdata = (void *)inode->i_ino;
break;
diff --git a/fs/aio.c b/fs/aio.c
index 064bfbe3756..3f941f2a305 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -591,11 +591,10 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
struct mm_struct *mm = current->mm;
struct kioctx *ctx, *ret = NULL;
- struct hlist_node *n;
rcu_read_lock();
- hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
+ hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) {
/*
* RCU protects us against accessing freed memory but
* we have to be careful not to get a reference when the
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 230bd2aad4f..9bd16255dd9 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -383,8 +383,10 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
goto done;
}
} else {
- if (!simple_empty(dentry))
+ if (!simple_empty(dentry)) {
+ spin_unlock(&sbi->fs_lock);
goto done;
+ }
}
ino->flags |= AUTOFS_INF_PENDING;
spin_unlock(&sbi->fs_lock);
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 03bc1d347d8..3db70dae40d 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -42,10 +42,8 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
while (wq) {
nwq = wq->next;
wq->status = -ENOENT; /* Magic is gone - report failure */
- if (wq->name.name) {
- kfree(wq->name.name);
- wq->name.name = NULL;
- }
+ kfree(wq->name.name);
+ wq->name.name = NULL;
wq->wait_ctr--;
wake_up_interruptible(&wq->queue);
wq = nwq;
diff --git a/fs/bio.c b/fs/bio.c
index b96fc6ce485..bb5768f59b3 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1428,6 +1428,8 @@ void bio_endio(struct bio *bio, int error)
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
+ trace_block_bio_complete(bio, error);
+
if (bio->bi_end_io)
bio->bi_end_io(bio, error);
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 53f5fae5cfb..aea605c98ba 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1033,7 +1033,9 @@ void bd_set_size(struct block_device *bdev, loff_t size)
{
unsigned bsize = bdev_logical_block_size(bdev);
- bdev->bd_inode->i_size = size;
+ mutex_lock(&bdev->bd_inode->i_mutex);
+ i_size_write(bdev->bd_inode, size);
+ mutex_unlock(&bdev->bd_inode->i_mutex);
while (bsize < PAGE_CACHE_SIZE) {
if (size & bsize)
break;
@@ -1118,7 +1120,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
}
}
- if (!ret && !bdev->bd_openers) {
+ if (!ret) {
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
bdi = blk_get_backing_dev_info(bdev);
if (bdi == NULL)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1e59ed575cc..cf54bdfee33 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3689,20 +3689,6 @@ static int can_overcommit(struct btrfs_root *root,
return 0;
}
-static int writeback_inodes_sb_nr_if_idle_safe(struct super_block *sb,
- unsigned long nr_pages,
- enum wb_reason reason)
-{
- if (!writeback_in_progress(sb->s_bdi) &&
- down_read_trylock(&sb->s_umount)) {
- writeback_inodes_sb_nr(sb, nr_pages, reason);
- up_read(&sb->s_umount);
- return 1;
- }
-
- return 0;
-}
-
/*
* shrink metadata reservation for delalloc
*/
@@ -3735,9 +3721,9 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
while (delalloc_bytes && loops < 3) {
max_reclaim = min(delalloc_bytes, to_reclaim);
nr_pages = max_reclaim >> PAGE_CACHE_SHIFT;
- writeback_inodes_sb_nr_if_idle_safe(root->fs_info->sb,
- nr_pages,
- WB_REASON_FS_FREE_SPACE);
+ try_to_writeback_inodes_sb_nr(root->fs_info->sb,
+ nr_pages,
+ WB_REASON_FS_FREE_SPACE);
/*
* We need to wait for the async pages to actually start before
diff --git a/fs/buffer.c b/fs/buffer.c
index 8e18281b407..b4dcb34c963 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -41,6 +41,7 @@
#include <linux/bitops.h>
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
+#include <trace/events/block.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
@@ -53,6 +54,13 @@ void init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private)
}
EXPORT_SYMBOL(init_buffer);
+inline void touch_buffer(struct buffer_head *bh)
+{
+ trace_block_touch_buffer(bh);
+ mark_page_accessed(bh->b_page);
+}
+EXPORT_SYMBOL(touch_buffer);
+
static int sleep_on_buffer(void *word)
{
io_schedule();
@@ -1113,6 +1121,8 @@ void mark_buffer_dirty(struct buffer_head *bh)
{
WARN_ON_ONCE(!buffer_uptodate(bh));
+ trace_block_dirty_buffer(bh);
+
/*
* Very *carefully* optimize the it-is-already-dirty case.
*
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index d4f81edd9a5..a60ea977af6 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -236,16 +236,10 @@ static int ceph_readpage(struct file *filp, struct page *page)
static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
{
struct inode *inode = req->r_inode;
- struct ceph_osd_reply_head *replyhead;
- int rc, bytes;
+ int rc = req->r_result;
+ int bytes = le32_to_cpu(msg->hdr.data_len);
int i;
- /* parse reply */
- replyhead = msg->front.iov_base;
- WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
- rc = le32_to_cpu(replyhead->result);
- bytes = le32_to_cpu(msg->hdr.data_len);
-
dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
/* unlock all pages, zeroing any data we didn't read */
@@ -315,7 +309,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, 0,
ci->i_truncate_seq, ci->i_truncate_size,
- NULL, false, 1, 0);
+ NULL, false, 0);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -492,8 +486,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
&ci->i_layout, snapc,
page_off, len,
ci->i_truncate_seq, ci->i_truncate_size,
- &inode->i_mtime,
- &page, 1, 0, 0, true);
+ &inode->i_mtime, &page, 1);
if (err < 0) {
dout("writepage setting page/mapping error %d %p\n", err, page);
SetPageError(page);
@@ -554,27 +547,18 @@ static void writepages_finish(struct ceph_osd_request *req,
struct ceph_msg *msg)
{
struct inode *inode = req->r_inode;
- struct ceph_osd_reply_head *replyhead;
- struct ceph_osd_op *op;
struct ceph_inode_info *ci = ceph_inode(inode);
unsigned wrote;
struct page *page;
int i;
struct ceph_snap_context *snapc = req->r_snapc;
struct address_space *mapping = inode->i_mapping;
- __s32 rc = -EIO;
- u64 bytes = 0;
+ int rc = req->r_result;
+ u64 bytes = le64_to_cpu(req->r_request_ops[0].extent.length);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
long writeback_stat;
unsigned issued = ceph_caps_issued(ci);
- /* parse reply */
- replyhead = msg->front.iov_base;
- WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
- op = (void *)(replyhead + 1);
- rc = le32_to_cpu(replyhead->result);
- bytes = le64_to_cpu(op->extent.length);
-
if (rc >= 0) {
/*
* Assume we wrote the pages we originally sent. The
@@ -741,8 +725,6 @@ retry:
struct page *page;
int want;
u64 offset, len;
- struct ceph_osd_request_head *reqhead;
- struct ceph_osd_op *op;
long writeback_stat;
next = 0;
@@ -838,7 +820,7 @@ get_more_pages:
snapc, do_sync,
ci->i_truncate_seq,
ci->i_truncate_size,
- &inode->i_mtime, true, 1, 0);
+ &inode->i_mtime, true, 0);
if (IS_ERR(req)) {
rc = PTR_ERR(req);
@@ -906,10 +888,8 @@ get_more_pages:
/* revise final length, page count */
req->r_num_pages = locked_pages;
- reqhead = req->r_request->front.iov_base;
- op = (void *)(reqhead + 1);
- op->extent.length = cpu_to_le64(len);
- op->payload_len = cpu_to_le32(len);
+ req->r_request_ops[0].extent.length = cpu_to_le64(len);
+ req->r_request_ops[0].payload_len = cpu_to_le32(len);
req->r_request->hdr.data_len = cpu_to_le32(len);
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index ae2be696eb5..78e2f575247 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -611,8 +611,16 @@ retry:
if (flags & CEPH_CAP_FLAG_AUTH)
ci->i_auth_cap = cap;
- else if (ci->i_auth_cap == cap)
+ else if (ci->i_auth_cap == cap) {
ci->i_auth_cap = NULL;
+ spin_lock(&mdsc->cap_dirty_lock);
+ if (!list_empty(&ci->i_dirty_item)) {
+ dout(" moving %p to cap_dirty_migrating\n", inode);
+ list_move(&ci->i_dirty_item,
+ &mdsc->cap_dirty_migrating);
+ }
+ spin_unlock(&mdsc->cap_dirty_lock);
+ }
dout("add_cap inode %p (%llx.%llx) cap %p %s now %s seq %d mds%d\n",
inode, ceph_vinop(inode), cap, ceph_cap_string(issued),
@@ -1460,7 +1468,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
struct ceph_mds_client *mdsc = fsc->mdsc;
struct inode *inode = &ci->vfs_inode;
struct ceph_cap *cap;
- int file_wanted, used;
+ int file_wanted, used, cap_used;
int took_snap_rwsem = 0; /* true if mdsc->snap_rwsem held */
int issued, implemented, want, retain, revoking, flushing = 0;
int mds = -1; /* keep track of how far we've gone through i_caps list
@@ -1563,9 +1571,14 @@ retry_locked:
/* NOTE: no side-effects allowed, until we take s_mutex */
+ cap_used = used;
+ if (ci->i_auth_cap && cap != ci->i_auth_cap)
+ cap_used &= ~ci->i_auth_cap->issued;
+
revoking = cap->implemented & ~cap->issued;
- dout(" mds%d cap %p issued %s implemented %s revoking %s\n",
+ dout(" mds%d cap %p used %s issued %s implemented %s revoking %s\n",
cap->mds, cap, ceph_cap_string(cap->issued),
+ ceph_cap_string(cap_used),
ceph_cap_string(cap->implemented),
ceph_cap_string(revoking));
@@ -1593,7 +1606,7 @@ retry_locked:
}
/* completed revocation? going down and there are no caps? */
- if (revoking && (revoking & used) == 0) {
+ if (revoking && (revoking & cap_used) == 0) {
dout("completed revocation of %s\n",
ceph_cap_string(cap->implemented & ~cap->issued));
goto ack;
@@ -1670,8 +1683,8 @@ ack:
sent++;
/* __send_cap drops i_ceph_lock */
- delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, used, want,
- retain, flushing, NULL);
+ delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, cap_used,
+ want, retain, flushing, NULL);
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
@@ -2417,7 +2430,9 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
dout("mds wanted %s -> %s\n",
ceph_cap_string(le32_to_cpu(grant->wanted)),
ceph_cap_string(wanted));
- grant->wanted = cpu_to_le32(wanted);
+ /* imported cap may not have correct mds_wanted */
+ if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT)
+ check_caps = 1;
}
cap->seq = seq;
@@ -2821,6 +2836,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
(unsigned)seq);
+ if (op == CEPH_CAP_OP_IMPORT)
+ ceph_add_cap_releases(mdsc, session);
+
/* lookup ino */
inode = ceph_find_inode(sb, vino);
ci = ceph_inode(inode);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 11b57c2c8f1..bf338d9b67e 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -243,6 +243,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
+ if (err)
+ goto out_err;
+
err = ceph_handle_snapdir(req, dentry, err);
if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
@@ -263,6 +266,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
err = finish_no_open(file, dn);
} else {
dout("atomic_open finish_open on dn %p\n", dn);
+ if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+ *opened |= FILE_CREATED;
+ }
err = finish_open(file, dentry, ceph_open, opened);
}
@@ -535,7 +541,7 @@ more:
ci->i_snap_realm->cached_context,
do_sync,
ci->i_truncate_seq, ci->i_truncate_size,
- &mtime, false, 2, page_align);
+ &mtime, false, page_align);
if (IS_ERR(req))
return PTR_ERR(req);
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index f5ed767806d..4a989345b37 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -185,7 +185,6 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
&ceph_sb_to_client(inode->i_sb)->client->osdc;
u64 len = 1, olen;
u64 tmp;
- struct ceph_object_layout ol;
struct ceph_pg pgid;
int r;
@@ -194,7 +193,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
return -EFAULT;
down_read(&osdc->map_sem);
- r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len,
+ r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len,
&dl.object_no, &dl.object_offset,
&olen);
if (r < 0)
@@ -209,10 +208,9 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
ceph_ino(inode), dl.object_no);
- ceph_calc_object_layout(&ol, dl.object_name, &ci->i_layout,
+ ceph_calc_object_layout(&pgid, dl.object_name, &ci->i_layout,
osdc->osdmap);
- pgid = ol.ol_pgid;
dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
if (dl.osd >= 0) {
struct ceph_entity_addr *a =
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 7a3dfe0a9a8..442880d099c 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -233,6 +233,30 @@ bad:
}
/*
+ * parse create results
+ */
+static int parse_reply_info_create(void **p, void *end,
+ struct ceph_mds_reply_info_parsed *info,
+ int features)
+{
+ if (features & CEPH_FEATURE_REPLY_CREATE_INODE) {
+ if (*p == end) {
+ info->has_create_ino = false;
+ } else {
+ info->has_create_ino = true;
+ info->ino = ceph_decode_64(p);
+ }
+ }
+
+ if (unlikely(*p != end))
+ goto bad;
+ return 0;
+
+bad:
+ return -EIO;
+}
+
+/*
* parse extra results
*/
static int parse_reply_info_extra(void **p, void *end,
@@ -241,8 +265,12 @@ static int parse_reply_info_extra(void **p, void *end,
{
if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
return parse_reply_info_filelock(p, end, info, features);
- else
+ else if (info->head->op == CEPH_MDS_OP_READDIR)
return parse_reply_info_dir(p, end, info, features);
+ else if (info->head->op == CEPH_MDS_OP_CREATE)
+ return parse_reply_info_create(p, end, info, features);
+ else
+ return -EIO;
}
/*
@@ -2170,7 +2198,8 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
mutex_lock(&req->r_fill_mutex);
err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
if (err == 0) {
- if (result == 0 && req->r_op != CEPH_MDS_OP_GETFILELOCK &&
+ if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
+ req->r_op == CEPH_MDS_OP_LSSNAP) &&
rinfo->dir_nr)
ceph_readdir_prepopulate(req, req->r_session);
ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index ff4188bf619..c2a19fbbe51 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -74,6 +74,12 @@ struct ceph_mds_reply_info_parsed {
struct ceph_mds_reply_info_in *dir_in;
u8 dir_complete, dir_end;
};
+
+ /* for create results */
+ struct {
+ bool has_create_ino;
+ u64 ino;
+ };
};
/* encoded blob describing snapshot contexts for certain
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 73b7d44e8a3..0d3c9240c61 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -59,6 +59,10 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
return ERR_PTR(-ENOMEM);
ceph_decode_16_safe(p, end, version, bad);
+ if (version > 3) {
+ pr_warning("got mdsmap version %d > 3, failing", version);
+ goto bad;
+ }
ceph_decode_need(p, end, 8*sizeof(u32) + sizeof(u64), bad);
m->m_epoch = ceph_decode_32(p);
@@ -144,13 +148,13 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
/* pg_pools */
ceph_decode_32_safe(p, end, n, bad);
m->m_num_data_pg_pools = n;
- m->m_data_pg_pools = kcalloc(n, sizeof(u32), GFP_NOFS);
+ m->m_data_pg_pools = kcalloc(n, sizeof(u64), GFP_NOFS);
if (!m->m_data_pg_pools)
goto badmem;
- ceph_decode_need(p, end, sizeof(u32)*(n+1), bad);
+ ceph_decode_need(p, end, sizeof(u64)*(n+1), bad);
for (i = 0; i < n; i++)
- m->m_data_pg_pools[i] = ceph_decode_32(p);
- m->m_cas_pg_pool = ceph_decode_32(p);
+ m->m_data_pg_pools[i] = ceph_decode_64(p);
+ m->m_cas_pg_pool = ceph_decode_64(p);
/* ok, we don't care about the rest. */
dout("mdsmap_decode success epoch %u\n", m->m_epoch);
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
index cd5097d7c80..89fa4a940a0 100644
--- a/fs/ceph/strings.c
+++ b/fs/ceph/strings.c
@@ -15,6 +15,7 @@ const char *ceph_mds_state_name(int s)
case CEPH_MDS_STATE_BOOT: return "up:boot";
case CEPH_MDS_STATE_STANDBY: return "up:standby";
case CEPH_MDS_STATE_STANDBY_REPLAY: return "up:standby-replay";
+ case CEPH_MDS_STATE_REPLAYONCE: return "up:oneshot-replay";
case CEPH_MDS_STATE_CREATING: return "up:creating";
case CEPH_MDS_STATE_STARTING: return "up:starting";
/* up and in */
@@ -50,10 +51,13 @@ const char *ceph_mds_op_name(int op)
case CEPH_MDS_OP_LOOKUP: return "lookup";
case CEPH_MDS_OP_LOOKUPHASH: return "lookuphash";
case CEPH_MDS_OP_LOOKUPPARENT: return "lookupparent";
+ case CEPH_MDS_OP_LOOKUPINO: return "lookupino";
case CEPH_MDS_OP_GETATTR: return "getattr";
case CEPH_MDS_OP_SETXATTR: return "setxattr";
case CEPH_MDS_OP_SETATTR: return "setattr";
case CEPH_MDS_OP_RMXATTR: return "rmxattr";
+ case CEPH_MDS_OP_SETLAYOUT: return "setlayou";
+ case CEPH_MDS_OP_SETDIRLAYOUT: return "setdirlayout";
case CEPH_MDS_OP_READDIR: return "readdir";
case CEPH_MDS_OP_MKNOD: return "mknod";
case CEPH_MDS_OP_LINK: return "link";
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index e86aa994812..9fe17c6c287 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -71,8 +71,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
/*
* express utilization in terms of large blocks to avoid
* overflow on 32-bit machines.
+ *
+ * NOTE: for the time being, we make bsize == frsize to humor
+ * not-yet-ancient versions of glibc that are broken.
+ * Someday, we will probably want to report a real block
+ * size... whatever that may mean for a network file system!
*/
buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
+ buf->f_frsize = 1 << CEPH_BLOCK_SHIFT;
buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
buf->f_bfree = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
@@ -80,7 +86,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_files = le64_to_cpu(st.num_objects);
buf->f_ffree = -1;
buf->f_namelen = NAME_MAX;
- buf->f_frsize = PAGE_CACHE_SIZE;
/* leave fsid little-endian, regardless of host endianness */
fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index f053bbd1886..c7b309723dc 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -21,7 +21,7 @@
/* large granularity for statfs utilization stats to facilitate
* large volume sizes on 32-bit machines. */
-#define CEPH_BLOCK_SHIFT 20 /* 1 MB */
+#define CEPH_BLOCK_SHIFT 22 /* 4 MB */
#define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT)
#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */
@@ -798,13 +798,7 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
/* file.c */
extern const struct file_operations ceph_file_fops;
extern const struct address_space_operations ceph_aops;
-extern int ceph_copy_to_page_vector(struct page **pages,
- const char *data,
- loff_t off, size_t len);
-extern int ceph_copy_from_page_vector(struct page **pages,
- char *data,
- loff_t off, size_t len);
-extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 2c2ae5be990..9b6b2b6dd16 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -29,9 +29,94 @@ struct ceph_vxattr {
size_t name_size; /* strlen(name) + 1 (for '\0') */
size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
size_t size);
- bool readonly;
+ bool readonly, hidden;
+ bool (*exists_cb)(struct ceph_inode_info *ci);
};
+/* layouts */
+
+static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
+{
+ size_t s;
+ char *p = (char *)&ci->i_layout;
+
+ for (s = 0; s < sizeof(ci->i_layout); s++, p++)
+ if (*p)
+ return true;
+ return false;
+}
+
+static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
+ size_t size)
+{
+ int ret;
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_osd_client *osdc = &fsc->client->osdc;
+ s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+ const char *pool_name;
+
+ dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
+ down_read(&osdc->map_sem);
+ pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
+ if (pool_name)
+ ret = snprintf(val, size,
+ "stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%s",
+ (unsigned long long)ceph_file_layout_su(ci->i_layout),
+ (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
+ (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
+ pool_name);
+ else
+ ret = snprintf(val, size,
+ "stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%lld",
+ (unsigned long long)ceph_file_layout_su(ci->i_layout),
+ (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
+ (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
+ (unsigned long long)pool);
+
+ up_read(&osdc->map_sem);
+ return ret;
+}
+
+static size_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ return snprintf(val, size, "%lld",
+ (unsigned long long)ceph_file_layout_su(ci->i_layout));
+}
+
+static size_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ return snprintf(val, size, "%lld",
+ (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout));
+}
+
+static size_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ return snprintf(val, size, "%lld",
+ (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
+}
+
+static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ int ret;
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_osd_client *osdc = &fsc->client->osdc;
+ s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+ const char *pool_name;
+
+ down_read(&osdc->map_sem);
+ pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
+ if (pool_name)
+ ret = snprintf(val, size, "%s", pool_name);
+ else
+ ret = snprintf(val, size, "%lld", (unsigned long long)pool);
+ up_read(&osdc->map_sem);
+ return ret;
+}
+
/* directories */
static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
@@ -83,17 +168,43 @@ static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
(long)ci->i_rctime.tv_nsec);
}
-#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
-#define XATTR_NAME_CEPH(_type, _name) \
- { \
- .name = CEPH_XATTR_NAME(_type, _name), \
- .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
- .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
- .readonly = true, \
- }
+#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
+#define CEPH_XATTR_NAME2(_type, _name, _name2) \
+ XATTR_CEPH_PREFIX #_type "." #_name "." #_name2
+
+#define XATTR_NAME_CEPH(_type, _name) \
+ { \
+ .name = CEPH_XATTR_NAME(_type, _name), \
+ .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
+ .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
+ .readonly = true, \
+ .hidden = false, \
+ .exists_cb = NULL, \
+ }
+#define XATTR_LAYOUT_FIELD(_type, _name, _field) \
+ { \
+ .name = CEPH_XATTR_NAME2(_type, _name, _field), \
+ .name_size = sizeof (CEPH_XATTR_NAME2(_type, _name, _field)), \
+ .getxattr_cb = ceph_vxattrcb_ ## _name ## _ ## _field, \
+ .readonly = false, \
+ .hidden = true, \
+ .exists_cb = ceph_vxattrcb_layout_exists, \
+ }
static struct ceph_vxattr ceph_dir_vxattrs[] = {
+ {
+ .name = "ceph.dir.layout",
+ .name_size = sizeof("ceph.dir.layout"),
+ .getxattr_cb = ceph_vxattrcb_layout,
+ .readonly = false,
+ .hidden = false,
+ .exists_cb = ceph_vxattrcb_layout_exists,
+ },
+ XATTR_LAYOUT_FIELD(dir, layout, stripe_unit),
+ XATTR_LAYOUT_FIELD(dir, layout, stripe_count),
+ XATTR_LAYOUT_FIELD(dir, layout, object_size),
+ XATTR_LAYOUT_FIELD(dir, layout, pool),
XATTR_NAME_CEPH(dir, entries),
XATTR_NAME_CEPH(dir, files),
XATTR_NAME_CEPH(dir, subdirs),
@@ -102,35 +213,26 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
XATTR_NAME_CEPH(dir, rsubdirs),
XATTR_NAME_CEPH(dir, rbytes),
XATTR_NAME_CEPH(dir, rctime),
- { 0 } /* Required table terminator */
+ { .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_dir_vxattrs_name_size; /* total size of all names */
/* files */
-static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
- size_t size)
-{
- int ret;
-
- ret = snprintf(val, size,
- "chunk_bytes=%lld\nstripe_count=%lld\nobject_size=%lld\n",
- (unsigned long long)ceph_file_layout_su(ci->i_layout),
- (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
- (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
- return ret;
-}
-
static struct ceph_vxattr ceph_file_vxattrs[] = {
- XATTR_NAME_CEPH(file, layout),
- /* The following extended attribute name is deprecated */
{
- .name = XATTR_CEPH_PREFIX "layout",
- .name_size = sizeof (XATTR_CEPH_PREFIX "layout"),
- .getxattr_cb = ceph_vxattrcb_file_layout,
- .readonly = true,
+ .name = "ceph.file.layout",
+ .name_size = sizeof("ceph.file.layout"),
+ .getxattr_cb = ceph_vxattrcb_layout,
+ .readonly = false,
+ .hidden = false,
+ .exists_cb = ceph_vxattrcb_layout_exists,
},
- { 0 } /* Required table terminator */
+ XATTR_LAYOUT_FIELD(file, layout, stripe_unit),
+ XATTR_LAYOUT_FIELD(file, layout, stripe_count),
+ XATTR_LAYOUT_FIELD(file, layout, object_size),
+ XATTR_LAYOUT_FIELD(file, layout, pool),
+ { .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_file_vxattrs_name_size; /* total size of all names */
@@ -164,7 +266,8 @@ static size_t __init vxattrs_name_size(struct ceph_vxattr *vxattrs)
size_t size = 0;
for (vxattr = vxattrs; vxattr->name; vxattr++)
- size += vxattr->name_size;
+ if (!vxattr->hidden)
+ size += vxattr->name_size;
return size;
}
@@ -572,13 +675,17 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
if (!ceph_is_valid_xattr(name))
return -ENODATA;
- /* let's see if a virtual xattr was requested */
- vxattr = ceph_match_vxattr(inode, name);
-
spin_lock(&ci->i_ceph_lock);
dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
ci->i_xattrs.version, ci->i_xattrs.index_version);
+ /* let's see if a virtual xattr was requested */
+ vxattr = ceph_match_vxattr(inode, name);
+ if (vxattr && !(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
+ err = vxattr->getxattr_cb(ci, value, size);
+ goto out;
+ }
+
if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
(ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
goto get_xattr;
@@ -592,11 +699,6 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
spin_lock(&ci->i_ceph_lock);
- if (vxattr && vxattr->readonly) {
- err = vxattr->getxattr_cb(ci, value, size);
- goto out;
- }
-
err = __build_xattrs(inode);
if (err < 0)
goto out;
@@ -604,11 +706,8 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
get_xattr:
err = -ENODATA; /* == ENOATTR */
xattr = __get_xattr(ci, name);
- if (!xattr) {
- if (vxattr)
- err = vxattr->getxattr_cb(ci, value, size);
+ if (!xattr)
goto out;
- }
err = -ERANGE;
if (size && size < xattr->val_len)
@@ -664,23 +763,30 @@ list_xattr:
vir_namelen = ceph_vxattrs_name_size(vxattrs);
/* adding 1 byte per each variable due to the null termination */
- namelen = vir_namelen + ci->i_xattrs.names_size + ci->i_xattrs.count;
+ namelen = ci->i_xattrs.names_size + ci->i_xattrs.count;
err = -ERANGE;
- if (size && namelen > size)
+ if (size && vir_namelen + namelen > size)
goto out;
- err = namelen;
+ err = namelen + vir_namelen;
if (size == 0)
goto out;
names = __copy_xattr_names(ci, names);
/* virtual xattr names, too */
- if (vxattrs)
+ err = namelen;
+ if (vxattrs) {
for (i = 0; vxattrs[i].name; i++) {
- len = sprintf(names, "%s", vxattrs[i].name);
- names += len + 1;
+ if (!vxattrs[i].hidden &&
+ !(vxattrs[i].exists_cb &&
+ !vxattrs[i].exists_cb(ci))) {
+ len = sprintf(names, "%s", vxattrs[i].name);
+ names += len + 1;
+ err += len + 1;
+ }
}
+ }
out:
spin_unlock(&ci->i_ceph_lock);
@@ -782,6 +888,10 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
if (vxattr && vxattr->readonly)
return -EOPNOTSUPP;
+ /* pass any unhandled ceph.* xattrs through to the MDS */
+ if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
+ goto do_sync_unlocked;
+
/* preallocate memory for xattr name, value, index node */
err = -ENOMEM;
newname = kmemdup(name, name_len + 1, GFP_NOFS);
@@ -838,6 +948,7 @@ retry:
do_sync:
spin_unlock(&ci->i_ceph_lock);
+do_sync_unlocked:
err = ceph_sync_setxattr(dentry, name, value, size, flags);
out:
kfree(newname);
@@ -892,6 +1003,10 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
if (vxattr && vxattr->readonly)
return -EOPNOTSUPP;
+ /* pass any unhandled ceph.* xattrs through to the MDS */
+ if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
+ goto do_sync_unlocked;
+
err = -ENOMEM;
spin_lock(&ci->i_ceph_lock);
retry:
@@ -931,6 +1046,7 @@ retry:
return err;
do_sync:
spin_unlock(&ci->i_ceph_lock);
+do_sync_unlocked:
err = ceph_send_removexattr(dentry, name);
out:
return err;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index d2a833999bc..83f2606c76d 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -816,10 +816,9 @@ static bool
inode_has_hashed_dentries(struct inode *inode)
{
struct dentry *dentry;
- struct hlist_node *p;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
spin_unlock(&inode->i_lock);
return true;
diff --git a/fs/coredump.c b/fs/coredump.c
index 69baf903d3b..c6479658d48 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -501,7 +501,7 @@ void do_coredump(siginfo_t *siginfo)
* so we dump it as root in mode 2, and only into a controlled
* environment (pipe handler or fully qualified path).
*/
- if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) {
+ if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) {
/* Setuid core dump mode */
flag = O_EXCL; /* Stop rewrite attacks */
cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */
diff --git a/fs/dcache.c b/fs/dcache.c
index 68220dd0c13..fbfae008ba4 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -675,11 +675,10 @@ EXPORT_SYMBOL(dget_parent);
static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
struct dentry *alias, *discon_alias;
- struct hlist_node *p;
again:
discon_alias = NULL;
- hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
@@ -730,10 +729,9 @@ EXPORT_SYMBOL(d_find_alias);
void d_prune_aliases(struct inode *inode)
{
struct dentry *dentry;
- struct hlist_node *p;
restart:
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_count) {
__dget_dlock(dentry);
@@ -1443,14 +1441,13 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
int len = entry->d_name.len;
const char *name = entry->d_name.name;
unsigned int hash = entry->d_name.hash;
- struct hlist_node *p;
if (!inode) {
__d_instantiate(entry, NULL);
return NULL;
}
- hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index f7501651762..1b1146670c4 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1183,7 +1183,7 @@ static void detach_lkb(struct dlm_lkb *lkb)
static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
{
struct dlm_lkb *lkb;
- int rv, id;
+ int rv;
lkb = dlm_allocate_lkb(ls);
if (!lkb)
@@ -1199,19 +1199,13 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
mutex_init(&lkb->lkb_cb_mutex);
INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work);
- retry:
- rv = idr_pre_get(&ls->ls_lkbidr, GFP_NOFS);
- if (!rv)
- return -ENOMEM;
-
+ idr_preload(GFP_NOFS);
spin_lock(&ls->ls_lkbidr_spin);
- rv = idr_get_new_above(&ls->ls_lkbidr, lkb, 1, &id);
- if (!rv)
- lkb->lkb_id = id;
+ rv = idr_alloc(&ls->ls_lkbidr, lkb, 1, 0, GFP_NOWAIT);
+ if (rv >= 0)
+ lkb->lkb_id = rv;
spin_unlock(&ls->ls_lkbidr_spin);
-
- if (rv == -EAGAIN)
- goto retry;
+ idr_preload_end();
if (rv < 0) {
log_error(ls, "create_lkb idr error %d", rv);
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 2e99fb0c973..3ca79d3253b 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -796,7 +796,6 @@ static int release_lockspace(struct dlm_ls *ls, int force)
*/
idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls);
- idr_remove_all(&ls->ls_lkbidr);
idr_destroy(&ls->ls_lkbidr);
/*
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index dd87a31bcc2..4f5ad246582 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -177,12 +177,11 @@ static inline int nodeid_hash(int nodeid)
static struct connection *__find_con(int nodeid)
{
int r;
- struct hlist_node *h;
struct connection *con;
r = nodeid_hash(nodeid);
- hlist_for_each_entry(con, h, &connection_hash[r], list) {
+ hlist_for_each_entry(con, &connection_hash[r], list) {
if (con->nodeid == nodeid)
return con;
}
@@ -232,13 +231,12 @@ static struct connection *__nodeid2con(int nodeid, gfp_t alloc)
static void foreach_conn(void (*conn_func)(struct connection *c))
{
int i;
- struct hlist_node *h, *n;
+ struct hlist_node *n;
struct connection *con;
for (i = 0; i < CONN_HASH_SIZE; i++) {
- hlist_for_each_entry_safe(con, h, n, &connection_hash[i], list){
+ hlist_for_each_entry_safe(con, n, &connection_hash[i], list)
conn_func(con);
- }
}
}
@@ -257,13 +255,12 @@ static struct connection *nodeid2con(int nodeid, gfp_t allocation)
static struct connection *assoc2con(int assoc_id)
{
int i;
- struct hlist_node *h;
struct connection *con;
mutex_lock(&connections_lock);
for (i = 0 ; i < CONN_HASH_SIZE; i++) {
- hlist_for_each_entry(con, h, &connection_hash[i], list) {
+ hlist_for_each_entry(con, &connection_hash[i], list) {
if (con->sctp_assoc == assoc_id) {
mutex_unlock(&connections_lock);
return con;
diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c
index aedea28a86a..a6bc63f6e31 100644
--- a/fs/dlm/recover.c
+++ b/fs/dlm/recover.c
@@ -305,27 +305,26 @@ static int recover_idr_empty(struct dlm_ls *ls)
static int recover_idr_add(struct dlm_rsb *r)
{
struct dlm_ls *ls = r->res_ls;
- int rv, id;
-
- rv = idr_pre_get(&ls->ls_recover_idr, GFP_NOFS);
- if (!rv)
- return -ENOMEM;
+ int rv;
+ idr_preload(GFP_NOFS);
spin_lock(&ls->ls_recover_idr_lock);
if (r->res_id) {
- spin_unlock(&ls->ls_recover_idr_lock);
- return -1;
- }
- rv = idr_get_new_above(&ls->ls_recover_idr, r, 1, &id);
- if (rv) {
- spin_unlock(&ls->ls_recover_idr_lock);
- return rv;
+ rv = -1;
+ goto out_unlock;
}
- r->res_id = id;
+ rv = idr_alloc(&ls->ls_recover_idr, r, 1, 0, GFP_NOWAIT);
+ if (rv < 0)
+ goto out_unlock;
+
+ r->res_id = rv;
ls->ls_recover_list_count++;
dlm_hold_rsb(r);
+ rv = 0;
+out_unlock:
spin_unlock(&ls->ls_recover_idr_lock);
- return 0;
+ idr_preload_end();
+ return rv;
}
static void recover_idr_del(struct dlm_rsb *r)
@@ -351,24 +350,21 @@ static struct dlm_rsb *recover_idr_find(struct dlm_ls *ls, uint64_t id)
return r;
}
-static int recover_idr_clear_rsb(int id, void *p, void *data)
+static void recover_idr_clear(struct dlm_ls *ls)
{
- struct dlm_ls *ls = data;
- struct dlm_rsb *r = p;
+ struct dlm_rsb *r;
+ int id;
- r->res_id = 0;
- r->res_recover_locks_count = 0;
- ls->ls_recover_list_count--;
+ spin_lock(&ls->ls_recover_idr_lock);
- dlm_put_rsb(r);
- return 0;
-}
+ idr_for_each_entry(&ls->ls_recover_idr, r, id) {
+ idr_remove(&ls->ls_recover_idr, id);
+ r->res_id = 0;
+ r->res_recover_locks_count = 0;
+ ls->ls_recover_list_count--;
-static void recover_idr_clear(struct dlm_ls *ls)
-{
- spin_lock(&ls->ls_recover_idr_lock);
- idr_for_each(&ls->ls_recover_idr, recover_idr_clear_rsb, ls);
- idr_remove_all(&ls->ls_recover_idr);
+ dlm_put_rsb(r);
+ }
if (ls->ls_recover_list_count != 0) {
log_error(ls, "warning: recover_list_count %d",
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 5fa2471796c..8d7a577ae49 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -115,10 +115,9 @@ void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx)
*/
int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon)
{
- struct hlist_node *elem;
int rc;
- hlist_for_each_entry(*daemon, elem,
+ hlist_for_each_entry(*daemon,
&ecryptfs_daemon_hash[ecryptfs_current_euid_hash()],
euid_chain) {
if (uid_eq((*daemon)->file->f_cred->euid, current_euid())) {
@@ -445,7 +444,6 @@ void ecryptfs_release_messaging(void)
mutex_unlock(&ecryptfs_msg_ctx_lists_mux);
}
if (ecryptfs_daemon_hash) {
- struct hlist_node *elem;
struct ecryptfs_daemon *daemon;
int i;
@@ -453,7 +451,7 @@ void ecryptfs_release_messaging(void)
for (i = 0; i < (1 << ecryptfs_hash_bits); i++) {
int rc;
- hlist_for_each_entry(daemon, elem,
+ hlist_for_each_entry(daemon,
&ecryptfs_daemon_hash[i],
euid_chain) {
rc = ecryptfs_exorcise_daemon(daemon);
diff --git a/fs/exec.c b/fs/exec.c
index 864c50df660..a96a4885bbb 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1111,7 +1111,7 @@ void setup_new_exec(struct linux_binprm * bprm)
current->sas_ss_sp = current->sas_ss_size = 0;
if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))
- set_dumpable(current->mm, SUID_DUMPABLE_ENABLED);
+ set_dumpable(current->mm, SUID_DUMP_USER);
else
set_dumpable(current->mm, suid_dumpable);
@@ -1639,17 +1639,17 @@ EXPORT_SYMBOL(set_binfmt);
void set_dumpable(struct mm_struct *mm, int value)
{
switch (value) {
- case SUID_DUMPABLE_DISABLED:
+ case SUID_DUMP_DISABLE:
clear_bit(MMF_DUMPABLE, &mm->flags);
smp_wmb();
clear_bit(MMF_DUMP_SECURELY, &mm->flags);
break;
- case SUID_DUMPABLE_ENABLED:
+ case SUID_DUMP_USER:
set_bit(MMF_DUMPABLE, &mm->flags);
smp_wmb();
clear_bit(MMF_DUMP_SECURELY, &mm->flags);
break;
- case SUID_DUMPABLE_SAFE:
+ case SUID_DUMP_ROOT:
set_bit(MMF_DUMP_SECURELY, &mm->flags);
smp_wmb();
set_bit(MMF_DUMPABLE, &mm->flags);
@@ -1662,7 +1662,7 @@ int __get_dumpable(unsigned long mm_flags)
int ret;
ret = mm_flags & MMF_DUMPABLE_MASK;
- return (ret > SUID_DUMPABLE_ENABLED) ? SUID_DUMPABLE_SAFE : ret;
+ return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret;
}
int get_dumpable(struct mm_struct *mm)
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 5df4bb4aab1..262fc994098 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -44,14 +44,13 @@ find_acceptable_alias(struct dentry *result,
{
struct dentry *dentry, *toput = NULL;
struct inode *inode;
- struct hlist_node *p;
if (acceptable(context, result))
return result;
inode = result->d_inode;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
dget(dentry);
spin_unlock(&inode->i_lock);
if (toput)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9c4f4b1c97f..9ea0cde3fa9 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2512,12 +2512,8 @@ static int ext4_nonda_switch(struct super_block *sb)
/*
* Start pushing delalloc when 1/2 of free blocks are dirty.
*/
- if (dirty_blocks && (free_blocks < 2 * dirty_blocks) &&
- !writeback_in_progress(sb->s_bdi) &&
- down_read_trylock(&sb->s_umount)) {
- writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
- up_read(&sb->s_umount);
- }
+ if (dirty_blocks && (free_blocks < 2 * dirty_blocks))
+ try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 12701a56775..e9cc3f0d58e 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -95,6 +95,8 @@ struct msdos_sb_info {
spinlock_t dir_hash_lock;
struct hlist_head dir_hashtable[FAT_HASH_SIZE];
+
+ unsigned int dirty; /* fs state before mount */
};
#define FAT_CACHE_VALID 0 /* special case for valid cache */
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index f8f491677a4..acf6e479b44 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -341,12 +341,11 @@ struct inode *fat_iget(struct super_block *sb, loff_t i_pos)
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);
- struct hlist_node *_p;
struct msdos_inode_info *i;
struct inode *inode = NULL;
spin_lock(&sbi->inode_hash_lock);
- hlist_for_each_entry(i, _p, head, i_fat_hash) {
+ hlist_for_each_entry(i, head, i_fat_hash) {
BUG_ON(i->vfs_inode.i_sb != sb);
if (i->i_pos != i_pos)
continue;
@@ -488,10 +487,59 @@ static void fat_evict_inode(struct inode *inode)
fat_detach(inode);
}
+static void fat_set_state(struct super_block *sb,
+ unsigned int set, unsigned int force)
+{
+ struct buffer_head *bh;
+ struct fat_boot_sector *b;
+ struct msdos_sb_info *sbi = sb->s_fs_info;
+
+ /* do not change any thing if mounted read only */
+ if ((sb->s_flags & MS_RDONLY) && !force)
+ return;
+
+ /* do not change state if fs was dirty */
+ if (sbi->dirty) {
+ /* warn only on set (mount). */
+ if (set)
+ fat_msg(sb, KERN_WARNING, "Volume was not properly "
+ "unmounted. Some data may be corrupt. "
+ "Please run fsck.");
+ return;
+ }
+
+ bh = sb_bread(sb, 0);
+ if (bh == NULL) {
+ fat_msg(sb, KERN_ERR, "unable to read boot sector "
+ "to mark fs as dirty");
+ return;
+ }
+
+ b = (struct fat_boot_sector *) bh->b_data;
+
+ if (sbi->fat_bits == 32) {
+ if (set)
+ b->fat32.state |= FAT_STATE_DIRTY;
+ else
+ b->fat32.state &= ~FAT_STATE_DIRTY;
+ } else /* fat 16 and 12 */ {
+ if (set)
+ b->fat16.state |= FAT_STATE_DIRTY;
+ else
+ b->fat16.state &= ~FAT_STATE_DIRTY;
+ }
+
+ mark_buffer_dirty(bh);
+ sync_dirty_buffer(bh);
+ brelse(bh);
+}
+
static void fat_put_super(struct super_block *sb)
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
+ fat_set_state(sb, 0, 0);
+
iput(sbi->fsinfo_inode);
iput(sbi->fat_inode);
@@ -566,8 +614,18 @@ static void __exit fat_destroy_inodecache(void)
static int fat_remount(struct super_block *sb, int *flags, char *data)
{
+ int new_rdonly;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
*flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
+
+ /* make sure we update state on remount. */
+ new_rdonly = *flags & MS_RDONLY;
+ if (new_rdonly != (sb->s_flags & MS_RDONLY)) {
+ if (new_rdonly)
+ fat_set_state(sb, 0, 0);
+ else
+ fat_set_state(sb, 1, 1);
+ }
return 0;
}
@@ -1298,17 +1356,17 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
sbi->prev_free = FAT_START_ENT;
sb->s_maxbytes = 0xffffffff;
- if (!sbi->fat_length && b->fat32_length) {
+ if (!sbi->fat_length && b->fat32.length) {
struct fat_boot_fsinfo *fsinfo;
struct buffer_head *fsinfo_bh;
/* Must be FAT32 */
sbi->fat_bits = 32;
- sbi->fat_length = le32_to_cpu(b->fat32_length);
- sbi->root_cluster = le32_to_cpu(b->root_cluster);
+ sbi->fat_length = le32_to_cpu(b->fat32.length);
+ sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster);
/* MC - if info_sector is 0, don't multiply by 0 */
- sbi->fsinfo_sector = le16_to_cpu(b->info_sector);
+ sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector);
if (sbi->fsinfo_sector == 0)
sbi->fsinfo_sector = 1;
@@ -1362,6 +1420,12 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
if (sbi->fat_bits != 32)
sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12;
+ /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */
+ if (sbi->fat_bits == 32)
+ sbi->dirty = b->fat32.state & FAT_STATE_DIRTY;
+ else /* fat 16 or 12 */
+ sbi->dirty = b->fat16.state & FAT_STATE_DIRTY;
+
/* check that FAT table does not overflow */
fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT);
@@ -1456,6 +1520,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
"the device does not support discard");
}
+ fat_set_state(sb, 1, 0);
return 0;
out_invalid:
diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c
index ef4b5faba87..499c10438ca 100644
--- a/fs/fat/nfs.c
+++ b/fs/fat/nfs.c
@@ -21,13 +21,12 @@ static struct inode *fat_dget(struct super_block *sb, int i_logstart)
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
struct hlist_head *head;
- struct hlist_node *_p;
struct msdos_inode_info *i;
struct inode *inode = NULL;
head = sbi->dir_hashtable + fat_dir_hash(i_logstart);
spin_lock(&sbi->dir_hash_lock);
- hlist_for_each_entry(i, _p, head, i_dir_hash) {
+ hlist_for_each_entry(i, head, i_dir_hash) {
BUG_ON(i->vfs_inode.i_sb != sb);
if (i->i_logstart != i_logstart)
continue;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 310972b72a6..21f46fb3a10 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -318,8 +318,14 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
- if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
- return inode->i_sb->s_op->write_inode(inode, wbc);
+ int ret;
+
+ if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) {
+ trace_writeback_write_inode_start(inode, wbc);
+ ret = inode->i_sb->s_op->write_inode(inode, wbc);
+ trace_writeback_write_inode(inode, wbc);
+ return ret;
+ }
return 0;
}
@@ -450,6 +456,8 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
WARN_ON(!(inode->i_state & I_SYNC));
+ trace_writeback_single_inode_start(inode, wbc, nr_to_write);
+
ret = do_writepages(mapping, wbc);
/*
@@ -1150,8 +1158,12 @@ void __mark_inode_dirty(struct inode *inode, int flags)
* dirty the inode itself
*/
if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+ trace_writeback_dirty_inode_start(inode, flags);
+
if (sb->s_op->dirty_inode)
sb->s_op->dirty_inode(inode, flags);
+
+ trace_writeback_dirty_inode(inode, flags);
}
/*
@@ -1332,47 +1344,43 @@ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
EXPORT_SYMBOL(writeback_inodes_sb);
/**
- * writeback_inodes_sb_if_idle - start writeback if none underway
+ * try_to_writeback_inodes_sb_nr - try to start writeback if none underway
* @sb: the superblock
- * @reason: reason why some writeback work was initiated
+ * @nr: the number of pages to write
+ * @reason: the reason of writeback
*
- * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Invoke writeback_inodes_sb_nr if no writeback is currently underway.
* Returns 1 if writeback was started, 0 if not.
*/
-int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason)
+int try_to_writeback_inodes_sb_nr(struct super_block *sb,
+ unsigned long nr,
+ enum wb_reason reason)
{
- if (!writeback_in_progress(sb->s_bdi)) {
- down_read(&sb->s_umount);
- writeback_inodes_sb(sb, reason);
- up_read(&sb->s_umount);
+ if (writeback_in_progress(sb->s_bdi))
return 1;
- } else
+
+ if (!down_read_trylock(&sb->s_umount))
return 0;
+
+ writeback_inodes_sb_nr(sb, nr, reason);
+ up_read(&sb->s_umount);
+ return 1;
}
-EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
+EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr);
/**
- * writeback_inodes_sb_nr_if_idle - start writeback if none underway
+ * try_to_writeback_inodes_sb - try to start writeback if none underway
* @sb: the superblock
- * @nr: the number of pages to write
* @reason: reason why some writeback work was initiated
*
- * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Implement by try_to_writeback_inodes_sb_nr()
* Returns 1 if writeback was started, 0 if not.
*/
-int writeback_inodes_sb_nr_if_idle(struct super_block *sb,
- unsigned long nr,
- enum wb_reason reason)
+int try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
{
- if (!writeback_in_progress(sb->s_bdi)) {
- down_read(&sb->s_umount);
- writeback_inodes_sb_nr(sb, nr, reason);
- up_read(&sb->s_umount);
- return 1;
- } else
- return 0;
+ return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
}
-EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
+EXPORT_SYMBOL(try_to_writeback_inodes_sb);
/**
* sync_inodes_sb - sync sb inode pages
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 8dcb114758e..e2cba1f60c2 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -237,13 +237,12 @@ static int fscache_alloc_object(struct fscache_cache *cache,
struct fscache_cookie *cookie)
{
struct fscache_object *object;
- struct hlist_node *_n;
int ret;
_enter("%p,%p{%s}", cache, cookie, cookie->def->name);
spin_lock(&cookie->lock);
- hlist_for_each_entry(object, _n, &cookie->backing_objects,
+ hlist_for_each_entry(object, &cookie->backing_objects,
cookie_link) {
if (object->cache == cache)
goto object_already_extant;
@@ -311,7 +310,6 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
{
struct fscache_object *p;
struct fscache_cache *cache = object->cache;
- struct hlist_node *_n;
int ret;
_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
@@ -321,7 +319,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
/* there may be multiple initial creations of this object, but we only
* want one */
ret = -EEXIST;
- hlist_for_each_entry(p, _n, &cookie->backing_objects, cookie_link) {
+ hlist_for_each_entry(p, &cookie->backing_objects, cookie_link) {
if (p->cache == object->cache) {
if (p->state >= FSCACHE_OBJECT_DYING)
ret = -ENOBUFS;
@@ -331,7 +329,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
/* pin the parent object */
spin_lock_nested(&cookie->parent->lock, 1);
- hlist_for_each_entry(p, _n, &cookie->parent->backing_objects,
+ hlist_for_each_entry(p, &cookie->parent->backing_objects,
cookie_link) {
if (p->cache == object->cache) {
if (p->state >= FSCACHE_OBJECT_DYING) {
@@ -435,7 +433,6 @@ EXPORT_SYMBOL(__fscache_wait_on_invalidate);
void __fscache_update_cookie(struct fscache_cookie *cookie)
{
struct fscache_object *object;
- struct hlist_node *_p;
fscache_stat(&fscache_n_updates);
@@ -452,7 +449,7 @@ void __fscache_update_cookie(struct fscache_cookie *cookie)
spin_lock(&cookie->lock);
/* update the index entry on disk in each cache backing this cookie */
- hlist_for_each_entry(object, _p,
+ hlist_for_each_entry(object,
&cookie->backing_objects, cookie_link) {
fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
}
diff --git a/fs/hfsplus/Makefile b/fs/hfsplus/Makefile
index 3cc0df73015..09d278bb7b9 100644
--- a/fs/hfsplus/Makefile
+++ b/fs/hfsplus/Makefile
@@ -5,5 +5,5 @@
obj-$(CONFIG_HFSPLUS_FS) += hfsplus.o
hfsplus-objs := super.o options.o inode.o ioctl.o extents.o catalog.o dir.o btree.o \
- bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o
-
+ bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o \
+ attributes.o xattr.o xattr_user.o xattr_security.o xattr_trusted.o
diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c
new file mode 100644
index 00000000000..8d691f12471
--- /dev/null
+++ b/fs/hfsplus/attributes.c
@@ -0,0 +1,399 @@
+/*
+ * linux/fs/hfsplus/attributes.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handling of records in attributes tree
+ */
+
+#include "hfsplus_fs.h"
+#include "hfsplus_raw.h"
+
+static struct kmem_cache *hfsplus_attr_tree_cachep;
+
+int hfsplus_create_attr_tree_cache(void)
+{
+ if (hfsplus_attr_tree_cachep)
+ return -EEXIST;
+
+ hfsplus_attr_tree_cachep =
+ kmem_cache_create("hfsplus_attr_cache",
+ sizeof(hfsplus_attr_entry), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!hfsplus_attr_tree_cachep)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void hfsplus_destroy_attr_tree_cache(void)
+{
+ kmem_cache_destroy(hfsplus_attr_tree_cachep);
+}
+
+int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *k1,
+ const hfsplus_btree_key *k2)
+{
+ __be32 k1_cnid, k2_cnid;
+
+ k1_cnid = k1->attr.cnid;
+ k2_cnid = k2->attr.cnid;
+ if (k1_cnid != k2_cnid)
+ return be32_to_cpu(k1_cnid) < be32_to_cpu(k2_cnid) ? -1 : 1;
+
+ return hfsplus_strcmp(
+ (const struct hfsplus_unistr *)&k1->attr.key_name,
+ (const struct hfsplus_unistr *)&k2->attr.key_name);
+}
+
+int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key,
+ u32 cnid, const char *name)
+{
+ int len;
+
+ memset(key, 0, sizeof(struct hfsplus_attr_key));
+ key->attr.cnid = cpu_to_be32(cnid);
+ if (name) {
+ len = strlen(name);
+ if (len > HFSPLUS_ATTR_MAX_STRLEN) {
+ printk(KERN_ERR "hfs: invalid xattr name's length\n");
+ return -EINVAL;
+ }
+ hfsplus_asc2uni(sb,
+ (struct hfsplus_unistr *)&key->attr.key_name,
+ HFSPLUS_ATTR_MAX_STRLEN, name, len);
+ len = be16_to_cpu(key->attr.key_name.length);
+ } else {
+ key->attr.key_name.length = 0;
+ len = 0;
+ }
+
+ /* The length of the key, as stored in key_len field, does not include
+ * the size of the key_len field itself.
+ * So, offsetof(hfsplus_attr_key, key_name) is a trick because
+ * it takes into consideration key_len field (__be16) of
+ * hfsplus_attr_key structure instead of length field (__be16) of
+ * hfsplus_attr_unistr structure.
+ */
+ key->key_len =
+ cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) +
+ 2 * len);
+
+ return 0;
+}
+
+void hfsplus_attr_build_key_uni(hfsplus_btree_key *key,
+ u32 cnid,
+ struct hfsplus_attr_unistr *name)
+{
+ int ustrlen;
+
+ memset(key, 0, sizeof(struct hfsplus_attr_key));
+ ustrlen = be16_to_cpu(name->length);
+ key->attr.cnid = cpu_to_be32(cnid);
+ key->attr.key_name.length = cpu_to_be16(ustrlen);
+ ustrlen *= 2;
+ memcpy(key->attr.key_name.unicode, name->unicode, ustrlen);
+
+ /* The length of the key, as stored in key_len field, does not include
+ * the size of the key_len field itself.
+ * So, offsetof(hfsplus_attr_key, key_name) is a trick because
+ * it takes into consideration key_len field (__be16) of
+ * hfsplus_attr_key structure instead of length field (__be16) of
+ * hfsplus_attr_unistr structure.
+ */
+ key->key_len =
+ cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) +
+ ustrlen);
+}
+
+hfsplus_attr_entry *hfsplus_alloc_attr_entry(void)
+{
+ return kmem_cache_alloc(hfsplus_attr_tree_cachep, GFP_KERNEL);
+}
+
+void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry)
+{
+ if (entry)
+ kmem_cache_free(hfsplus_attr_tree_cachep, entry);
+}
+
+#define HFSPLUS_INVALID_ATTR_RECORD -1
+
+static int hfsplus_attr_build_record(hfsplus_attr_entry *entry, int record_type,
+ u32 cnid, const void *value, size_t size)
+{
+ if (record_type == HFSPLUS_ATTR_FORK_DATA) {
+ /*
+ * Mac OS X supports only inline data attributes.
+ * Do nothing
+ */
+ memset(entry, 0, sizeof(*entry));
+ return sizeof(struct hfsplus_attr_fork_data);
+ } else if (record_type == HFSPLUS_ATTR_EXTENTS) {
+ /*
+ * Mac OS X supports only inline data attributes.
+ * Do nothing.
+ */
+ memset(entry, 0, sizeof(*entry));
+ return sizeof(struct hfsplus_attr_extents);
+ } else if (record_type == HFSPLUS_ATTR_INLINE_DATA) {
+ u16 len;
+
+ memset(entry, 0, sizeof(struct hfsplus_attr_inline_data));
+ entry->inline_data.record_type = cpu_to_be32(record_type);
+ if (size <= HFSPLUS_MAX_INLINE_DATA_SIZE)
+ len = size;
+ else
+ return HFSPLUS_INVALID_ATTR_RECORD;
+ entry->inline_data.length = cpu_to_be16(len);
+ memcpy(entry->inline_data.raw_bytes, value, len);
+ /*
+ * Align len on two-byte boundary.
+ * It needs to add pad byte if we have odd len.
+ */
+ len = round_up(len, 2);
+ return offsetof(struct hfsplus_attr_inline_data, raw_bytes) +
+ len;
+ } else /* invalid input */
+ memset(entry, 0, sizeof(*entry));
+
+ return HFSPLUS_INVALID_ATTR_RECORD;
+}
+
+int hfsplus_find_attr(struct super_block *sb, u32 cnid,
+ const char *name, struct hfs_find_data *fd)
+{
+ int err = 0;
+
+ dprint(DBG_ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid);
+
+ if (!HFSPLUS_SB(sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ if (name) {
+ err = hfsplus_attr_build_key(sb, fd->search_key, cnid, name);
+ if (err)
+ goto failed_find_attr;
+ err = hfs_brec_find(fd, hfs_find_rec_by_key);
+ if (err)
+ goto failed_find_attr;
+ } else {
+ err = hfsplus_attr_build_key(sb, fd->search_key, cnid, NULL);
+ if (err)
+ goto failed_find_attr;
+ err = hfs_brec_find(fd, hfs_find_1st_rec_by_cnid);
+ if (err)
+ goto failed_find_attr;
+ }
+
+failed_find_attr:
+ return err;
+}
+
+int hfsplus_attr_exists(struct inode *inode, const char *name)
+{
+ int err = 0;
+ struct super_block *sb = inode->i_sb;
+ struct hfs_find_data fd;
+
+ if (!HFSPLUS_SB(sb)->attr_tree)
+ return 0;
+
+ err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd);
+ if (err)
+ return 0;
+
+ err = hfsplus_find_attr(sb, inode->i_ino, name, &fd);
+ if (err)
+ goto attr_not_found;
+
+ hfs_find_exit(&fd);
+ return 1;
+
+attr_not_found:
+ hfs_find_exit(&fd);
+ return 0;
+}
+
+int hfsplus_create_attr(struct inode *inode,
+ const char *name,
+ const void *value, size_t size)
+{
+ struct super_block *sb = inode->i_sb;
+ struct hfs_find_data fd;
+ hfsplus_attr_entry *entry_ptr;
+ int entry_size;
+ int err;
+
+ dprint(DBG_ATTR_MOD, "create_attr: %s,%ld\n",
+ name ? name : NULL, inode->i_ino);
+
+ if (!HFSPLUS_SB(sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ entry_ptr = hfsplus_alloc_attr_entry();
+ if (!entry_ptr)
+ return -ENOMEM;
+
+ err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd);
+ if (err)
+ goto failed_init_create_attr;
+
+ if (name) {
+ err = hfsplus_attr_build_key(sb, fd.search_key,
+ inode->i_ino, name);
+ if (err)
+ goto failed_create_attr;
+ } else {
+ err = -EINVAL;
+ goto failed_create_attr;
+ }
+
+ /* Mac OS X supports only inline data attributes. */
+ entry_size = hfsplus_attr_build_record(entry_ptr,
+ HFSPLUS_ATTR_INLINE_DATA,
+ inode->i_ino,
+ value, size);
+ if (entry_size == HFSPLUS_INVALID_ATTR_RECORD) {
+ err = -EINVAL;
+ goto failed_create_attr;
+ }
+
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
+ if (err != -ENOENT) {
+ if (!err)
+ err = -EEXIST;
+ goto failed_create_attr;
+ }
+
+ err = hfs_brec_insert(&fd, entry_ptr, entry_size);
+ if (err)
+ goto failed_create_attr;
+
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY);
+
+failed_create_attr:
+ hfs_find_exit(&fd);
+
+failed_init_create_attr:
+ hfsplus_destroy_attr_entry(entry_ptr);
+ return err;
+}
+
+static int __hfsplus_delete_attr(struct inode *inode, u32 cnid,
+ struct hfs_find_data *fd)
+{
+ int err = 0;
+ __be32 found_cnid, record_type;
+
+ hfs_bnode_read(fd->bnode, &found_cnid,
+ fd->keyoffset +
+ offsetof(struct hfsplus_attr_key, cnid),
+ sizeof(__be32));
+ if (cnid != be32_to_cpu(found_cnid))
+ return -ENOENT;
+
+ hfs_bnode_read(fd->bnode, &record_type,
+ fd->entryoffset, sizeof(record_type));
+
+ switch (be32_to_cpu(record_type)) {
+ case HFSPLUS_ATTR_INLINE_DATA:
+ /* All is OK. Do nothing. */
+ break;
+ case HFSPLUS_ATTR_FORK_DATA:
+ case HFSPLUS_ATTR_EXTENTS:
+ printk(KERN_ERR "hfs: only inline data xattr are supported\n");
+ return -EOPNOTSUPP;
+ default:
+ printk(KERN_ERR "hfs: invalid extended attribute record\n");
+ return -ENOENT;
+ }
+
+ err = hfs_brec_remove(fd);
+ if (err)
+ return err;
+
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY);
+ return err;
+}
+
+int hfsplus_delete_attr(struct inode *inode, const char *name)
+{
+ int err = 0;
+ struct super_block *sb = inode->i_sb;
+ struct hfs_find_data fd;
+
+ dprint(DBG_ATTR_MOD, "delete_attr: %s,%ld\n",
+ name ? name : NULL, inode->i_ino);
+
+ if (!HFSPLUS_SB(sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd);
+ if (err)
+ return err;
+
+ if (name) {
+ err = hfsplus_attr_build_key(sb, fd.search_key,
+ inode->i_ino, name);
+ if (err)
+ goto out;
+ } else {
+ printk(KERN_ERR "hfs: invalid extended attribute name\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
+ if (err)
+ goto out;
+
+ err = __hfsplus_delete_attr(inode, inode->i_ino, &fd);
+ if (err)
+ goto out;
+
+out:
+ hfs_find_exit(&fd);
+ return err;
+}
+
+int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid)
+{
+ int err = 0;
+ struct hfs_find_data fd;
+
+ dprint(DBG_ATTR_MOD, "delete_all_attrs: %d\n", cnid);
+
+ if (!HFSPLUS_SB(dir->i_sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ err = hfs_find_init(HFSPLUS_SB(dir->i_sb)->attr_tree, &fd);
+ if (err)
+ return err;
+
+ for (;;) {
+ err = hfsplus_find_attr(dir->i_sb, cnid, NULL, &fd);
+ if (err) {
+ if (err != -ENOENT)
+ printk(KERN_ERR "hfs: xattr search failed.\n");
+ goto end_delete_all;
+ }
+
+ err = __hfsplus_delete_attr(dir, cnid, &fd);
+ if (err)
+ goto end_delete_all;
+ }
+
+end_delete_all:
+ hfs_find_exit(&fd);
+ return err;
+}
diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
index 5d799c13205..d73c98d1ee9 100644
--- a/fs/hfsplus/bfind.c
+++ b/fs/hfsplus/bfind.c
@@ -24,7 +24,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
fd->key = ptr + tree->max_key_len + 2;
dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n",
tree->cnid, __builtin_return_address(0));
- mutex_lock(&tree->tree_lock);
+ switch (tree->cnid) {
+ case HFSPLUS_CAT_CNID:
+ mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
+ break;
+ case HFSPLUS_EXT_CNID:
+ mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
+ break;
+ case HFSPLUS_ATTR_CNID:
+ mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
+ break;
+ default:
+ BUG();
+ }
return 0;
}
@@ -38,15 +50,73 @@ void hfs_find_exit(struct hfs_find_data *fd)
fd->tree = NULL;
}
-/* Find the record in bnode that best matches key (not greater than...)*/
-int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
+int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode,
+ struct hfs_find_data *fd,
+ int *begin,
+ int *end,
+ int *cur_rec)
+{
+ __be32 cur_cnid, search_cnid;
+
+ if (bnode->tree->cnid == HFSPLUS_EXT_CNID) {
+ cur_cnid = fd->key->ext.cnid;
+ search_cnid = fd->search_key->ext.cnid;
+ } else if (bnode->tree->cnid == HFSPLUS_CAT_CNID) {
+ cur_cnid = fd->key->cat.parent;
+ search_cnid = fd->search_key->cat.parent;
+ } else if (bnode->tree->cnid == HFSPLUS_ATTR_CNID) {
+ cur_cnid = fd->key->attr.cnid;
+ search_cnid = fd->search_key->attr.cnid;
+ } else
+ BUG();
+
+ if (cur_cnid == search_cnid) {
+ (*end) = (*cur_rec);
+ if ((*begin) == (*end))
+ return 1;
+ } else {
+ if (be32_to_cpu(cur_cnid) < be32_to_cpu(search_cnid))
+ (*begin) = (*cur_rec) + 1;
+ else
+ (*end) = (*cur_rec) - 1;
+ }
+
+ return 0;
+}
+
+int hfs_find_rec_by_key(struct hfs_bnode *bnode,
+ struct hfs_find_data *fd,
+ int *begin,
+ int *end,
+ int *cur_rec)
{
int cmpval;
+
+ cmpval = bnode->tree->keycmp(fd->key, fd->search_key);
+ if (!cmpval) {
+ (*end) = (*cur_rec);
+ return 1;
+ }
+ if (cmpval < 0)
+ (*begin) = (*cur_rec) + 1;
+ else
+ *(end) = (*cur_rec) - 1;
+
+ return 0;
+}
+
+/* Find the record in bnode that best matches key (not greater than...)*/
+int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd,
+ search_strategy_t rec_found)
+{
u16 off, len, keylen;
int rec;
int b, e;
int res;
+ if (!rec_found)
+ BUG();
+
b = 0;
e = bnode->num_recs - 1;
res = -ENOENT;
@@ -59,17 +129,12 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
goto fail;
}
hfs_bnode_read(bnode, fd->key, off, keylen);
- cmpval = bnode->tree->keycmp(fd->key, fd->search_key);
- if (!cmpval) {
- e = rec;
+ if (rec_found(bnode, fd, &b, &e, &rec)) {
res = 0;
goto done;
}
- if (cmpval < 0)
- b = rec + 1;
- else
- e = rec - 1;
} while (b <= e);
+
if (rec != e && e >= 0) {
len = hfs_brec_lenoff(bnode, e, &off);
keylen = hfs_brec_keylen(bnode, e);
@@ -79,19 +144,21 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
}
hfs_bnode_read(bnode, fd->key, off, keylen);
}
+
done:
fd->record = e;
fd->keyoffset = off;
fd->keylength = keylen;
fd->entryoffset = off + keylen;
fd->entrylength = len - keylen;
+
fail:
return res;
}
/* Traverse a B*Tree from the root to a leaf finding best fit to key */
/* Return allocated copy of node found, set recnum to best record */
-int hfs_brec_find(struct hfs_find_data *fd)
+int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare)
{
struct hfs_btree *tree;
struct hfs_bnode *bnode;
@@ -122,7 +189,7 @@ int hfs_brec_find(struct hfs_find_data *fd)
goto invalid;
bnode->parent = parent;
- res = __hfs_brec_find(bnode, fd);
+ res = __hfs_brec_find(bnode, fd, do_key_compare);
if (!height)
break;
if (fd->record < 0)
@@ -149,7 +216,7 @@ int hfs_brec_read(struct hfs_find_data *fd, void *rec, int rec_len)
{
int res;
- res = hfs_brec_find(fd);
+ res = hfs_brec_find(fd, hfs_find_rec_by_key);
if (res)
return res;
if (fd->entrylength > rec_len)
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index 1c42cc5b899..f31ac6f404f 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -62,7 +62,8 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off)
tree = node->tree;
if (node->type == HFS_NODE_LEAF ||
- tree->attributes & HFS_TREE_VARIDXKEYS)
+ tree->attributes & HFS_TREE_VARIDXKEYS ||
+ node->tree->cnid == HFSPLUS_ATTR_CNID)
key_len = hfs_bnode_read_u16(node, off) + 2;
else
key_len = tree->max_key_len + 2;
@@ -314,7 +315,8 @@ void hfs_bnode_dump(struct hfs_bnode *node)
if (i && node->type == HFS_NODE_INDEX) {
int tmp;
- if (node->tree->attributes & HFS_TREE_VARIDXKEYS)
+ if (node->tree->attributes & HFS_TREE_VARIDXKEYS ||
+ node->tree->cnid == HFSPLUS_ATTR_CNID)
tmp = hfs_bnode_read_u16(node, key_off) + 2;
else
tmp = node->tree->max_key_len + 2;
@@ -646,6 +648,8 @@ void hfs_bnode_put(struct hfs_bnode *node)
if (test_bit(HFS_BNODE_DELETED, &node->flags)) {
hfs_bnode_unhash(node);
spin_unlock(&tree->hash_lock);
+ hfs_bnode_clear(node, 0,
+ PAGE_CACHE_SIZE * tree->pages_per_bnode);
hfs_bmap_free(node);
hfs_bnode_free(node);
return;
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 2a734cfccc9..298d4e45604 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -36,7 +36,8 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec)
return 0;
if ((node->type == HFS_NODE_INDEX) &&
- !(node->tree->attributes & HFS_TREE_VARIDXKEYS)) {
+ !(node->tree->attributes & HFS_TREE_VARIDXKEYS) &&
+ (node->tree->cnid != HFSPLUS_ATTR_CNID)) {
retval = node->tree->max_key_len + 2;
} else {
recoff = hfs_bnode_read_u16(node,
@@ -151,12 +152,13 @@ skip:
/* get index key */
hfs_bnode_read_key(new_node, fd->search_key, 14);
- __hfs_brec_find(fd->bnode, fd);
+ __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key);
hfs_bnode_put(new_node);
new_node = NULL;
- if (tree->attributes & HFS_TREE_VARIDXKEYS)
+ if ((tree->attributes & HFS_TREE_VARIDXKEYS) ||
+ (tree->cnid == HFSPLUS_ATTR_CNID))
key_len = be16_to_cpu(fd->search_key->key_len) + 2;
else {
fd->search_key->key_len =
@@ -201,7 +203,7 @@ again:
hfs_bnode_put(node);
node = fd->bnode = parent;
- __hfs_brec_find(node, fd);
+ __hfs_brec_find(node, fd, hfs_find_rec_by_key);
goto again;
}
hfs_bnode_write_u16(node,
@@ -367,12 +369,13 @@ again:
parent = hfs_bnode_find(tree, node->parent);
if (IS_ERR(parent))
return PTR_ERR(parent);
- __hfs_brec_find(parent, fd);
+ __hfs_brec_find(parent, fd, hfs_find_rec_by_key);
hfs_bnode_dump(parent);
rec = fd->record;
/* size difference between old and new key */
- if (tree->attributes & HFS_TREE_VARIDXKEYS)
+ if ((tree->attributes & HFS_TREE_VARIDXKEYS) ||
+ (tree->cnid == HFSPLUS_ATTR_CNID))
newkeylen = hfs_bnode_read_u16(node, 14) + 2;
else
fd->keylength = newkeylen = tree->max_key_len + 2;
@@ -427,7 +430,7 @@ skip:
hfs_bnode_read_key(new_node, fd->search_key, 14);
cnid = cpu_to_be32(new_node->this);
- __hfs_brec_find(fd->bnode, fd);
+ __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key);
hfs_brec_insert(fd, &cnid, sizeof(cnid));
hfs_bnode_put(fd->bnode);
hfs_bnode_put(new_node);
@@ -495,13 +498,15 @@ static int hfs_btree_inc_height(struct hfs_btree *tree)
/* insert old root idx into new root */
node->parent = tree->root;
if (node->type == HFS_NODE_LEAF ||
- tree->attributes & HFS_TREE_VARIDXKEYS)
+ tree->attributes & HFS_TREE_VARIDXKEYS ||
+ tree->cnid == HFSPLUS_ATTR_CNID)
key_size = hfs_bnode_read_u16(node, 14) + 2;
else
key_size = tree->max_key_len + 2;
hfs_bnode_copy(new_node, 14, node, 14, key_size);
- if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) {
+ if (!(tree->attributes & HFS_TREE_VARIDXKEYS) &&
+ (tree->cnid != HFSPLUS_ATTR_CNID)) {
key_size = tree->max_key_len + 2;
hfs_bnode_write_u16(new_node, 14, tree->max_key_len);
}
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 685d07d0ed1..efb689c21a9 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -98,6 +98,14 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
}
break;
+ case HFSPLUS_ATTR_CNID:
+ if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) {
+ printk(KERN_ERR "hfs: invalid attributes max_key_len %d\n",
+ tree->max_key_len);
+ goto fail_page;
+ }
+ tree->keycmp = hfsplus_attr_bin_cmp_key;
+ break;
default:
printk(KERN_ERR "hfs: unknown B*Tree requested\n");
goto fail_page;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 798d9c4c5e7..840d71edd19 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -45,7 +45,8 @@ void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
key->cat.parent = cpu_to_be32(parent);
if (str) {
- hfsplus_asc2uni(sb, &key->cat.name, str->name, str->len);
+ hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
+ str->name, str->len);
len = be16_to_cpu(key->cat.name.length);
} else {
key->cat.name.length = 0;
@@ -167,7 +168,8 @@ static int hfsplus_fill_cat_thread(struct super_block *sb,
entry->type = cpu_to_be16(type);
entry->thread.reserved = 0;
entry->thread.parentID = cpu_to_be32(parentid);
- hfsplus_asc2uni(sb, &entry->thread.nodeName, str->name, str->len);
+ hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
+ str->name, str->len);
return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2;
}
@@ -198,7 +200,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
hfsplus_cat_build_key_uni(fd->search_key,
be32_to_cpu(tmp.thread.parentID),
&tmp.thread.nodeName);
- return hfs_brec_find(fd);
+ return hfs_brec_find(fd, hfs_find_rec_by_key);
}
int hfsplus_create_cat(u32 cnid, struct inode *dir,
@@ -221,7 +223,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
S_ISDIR(inode->i_mode) ?
HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD,
dir->i_ino, str);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
if (!err)
err = -EEXIST;
@@ -233,7 +235,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
entry_size = hfsplus_cat_build_record(&entry, cnid, inode);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
/* panic? */
if (!err)
@@ -253,7 +255,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
err1:
hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
- if (!hfs_brec_find(&fd))
+ if (!hfs_brec_find(&fd, hfs_find_rec_by_key))
hfs_brec_remove(&fd);
err2:
hfs_find_exit(&fd);
@@ -279,7 +281,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
int len;
hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -296,7 +298,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
} else
hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -326,7 +328,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
goto out;
hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -337,6 +339,12 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
dir->i_size--;
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
+
+ if (type == HFSPLUS_FILE || type == HFSPLUS_FOLDER) {
+ if (HFSPLUS_SB(sb)->attr_tree)
+ hfsplus_delete_all_attrs(dir, cnid);
+ }
+
out:
hfs_find_exit(&fd);
@@ -363,7 +371,7 @@ int hfsplus_rename_cat(u32 cnid,
/* find the old dir entry and read the data */
hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
- err = hfs_brec_find(&src_fd);
+ err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
if (err)
goto out;
if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) {
@@ -376,7 +384,7 @@ int hfsplus_rename_cat(u32 cnid,
/* create new dir entry with the data from the old entry */
hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
- err = hfs_brec_find(&dst_fd);
+ err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
if (!err)
err = -EEXIST;
@@ -391,7 +399,7 @@ int hfsplus_rename_cat(u32 cnid,
/* finally remove the old entry */
hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
- err = hfs_brec_find(&src_fd);
+ err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
if (err)
goto out;
err = hfs_brec_remove(&src_fd);
@@ -402,7 +410,7 @@ int hfsplus_rename_cat(u32 cnid,
/* remove old thread entry */
hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL);
- err = hfs_brec_find(&src_fd);
+ err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
if (err)
goto out;
type = hfs_bnode_read_u16(src_fd.bnode, src_fd.entryoffset);
@@ -414,7 +422,7 @@ int hfsplus_rename_cat(u32 cnid,
hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL);
entry_size = hfsplus_fill_cat_thread(sb, &entry, type,
dst_dir->i_ino, dst_name);
- err = hfs_brec_find(&dst_fd);
+ err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
if (!err)
err = -EEXIST;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 074e0458924..031c24e5052 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -15,6 +15,7 @@
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
+#include "xattr.h"
static inline void hfsplus_instantiate(struct dentry *dentry,
struct inode *inode, u32 cnid)
@@ -138,7 +139,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
if (err)
return err;
hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -421,6 +422,15 @@ static int hfsplus_symlink(struct inode *dir, struct dentry *dentry,
if (res)
goto out_err;
+ res = hfsplus_init_inode_security(inode, dir, &dentry->d_name);
+ if (res == -EOPNOTSUPP)
+ res = 0; /* Operation is not supported. */
+ else if (res) {
+ /* Try to delete anyway without error analysis. */
+ hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name);
+ goto out_err;
+ }
+
hfsplus_instantiate(dentry, inode, inode->i_ino);
mark_inode_dirty(inode);
goto out;
@@ -450,15 +460,26 @@ static int hfsplus_mknod(struct inode *dir, struct dentry *dentry,
init_special_inode(inode, mode, rdev);
res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
- if (res) {
- clear_nlink(inode);
- hfsplus_delete_inode(inode);
- iput(inode);
- goto out;
+ if (res)
+ goto failed_mknod;
+
+ res = hfsplus_init_inode_security(inode, dir, &dentry->d_name);
+ if (res == -EOPNOTSUPP)
+ res = 0; /* Operation is not supported. */
+ else if (res) {
+ /* Try to delete anyway without error analysis. */
+ hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name);
+ goto failed_mknod;
}
hfsplus_instantiate(dentry, inode, inode->i_ino);
mark_inode_dirty(inode);
+ goto out;
+
+failed_mknod:
+ clear_nlink(inode);
+ hfsplus_delete_inode(inode);
+ iput(inode);
out:
mutex_unlock(&sbi->vh_mutex);
return res;
@@ -499,15 +520,19 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
}
const struct inode_operations hfsplus_dir_inode_operations = {
- .lookup = hfsplus_lookup,
- .create = hfsplus_create,
- .link = hfsplus_link,
- .unlink = hfsplus_unlink,
- .mkdir = hfsplus_mkdir,
- .rmdir = hfsplus_rmdir,
- .symlink = hfsplus_symlink,
- .mknod = hfsplus_mknod,
- .rename = hfsplus_rename,
+ .lookup = hfsplus_lookup,
+ .create = hfsplus_create,
+ .link = hfsplus_link,
+ .unlink = hfsplus_unlink,
+ .mkdir = hfsplus_mkdir,
+ .rmdir = hfsplus_rmdir,
+ .symlink = hfsplus_symlink,
+ .mknod = hfsplus_mknod,
+ .rename = hfsplus_rename,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = hfsplus_listxattr,
+ .removexattr = hfsplus_removexattr,
};
const struct file_operations hfsplus_dir_operations = {
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index eba76eab6d6..a94f0f779d5 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -95,7 +95,7 @@ static void __hfsplus_ext_write_extent(struct inode *inode,
HFSPLUS_IS_RSRC(inode) ?
HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
- res = hfs_brec_find(fd);
+ res = hfs_brec_find(fd, hfs_find_rec_by_key);
if (hip->extent_state & HFSPLUS_EXT_NEW) {
if (res != -ENOENT)
return;
@@ -154,7 +154,7 @@ static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd,
hfsplus_ext_build_key(fd->search_key, cnid, block, type);
fd->key->ext.cnid = 0;
- res = hfs_brec_find(fd);
+ res = hfs_brec_find(fd, hfs_find_rec_by_key);
if (res && res != -ENOENT)
return res;
if (fd->key->ext.cnid != fd->search_key->ext.cnid ||
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index a6da86b1b4c..05b11f36024 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -23,6 +23,7 @@
#define DBG_SUPER 0x00000010
#define DBG_EXTENT 0x00000020
#define DBG_BITMAP 0x00000040
+#define DBG_ATTR_MOD 0x00000080
#if 0
#define DBG_MASK (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD)
@@ -46,6 +47,13 @@ typedef int (*btree_keycmp)(const hfsplus_btree_key *,
#define NODE_HASH_SIZE 256
+/* B-tree mutex nested subclasses */
+enum hfsplus_btree_mutex_classes {
+ CATALOG_BTREE_MUTEX,
+ EXTENTS_BTREE_MUTEX,
+ ATTR_BTREE_MUTEX,
+};
+
/* An HFS+ BTree held in memory */
struct hfs_btree {
struct super_block *sb;
@@ -223,6 +231,7 @@ struct hfsplus_inode_info {
#define HFSPLUS_I_CAT_DIRTY 1 /* has changes in the catalog tree */
#define HFSPLUS_I_EXT_DIRTY 2 /* has changes in the extent tree */
#define HFSPLUS_I_ALLOC_DIRTY 3 /* has changes in the allocation file */
+#define HFSPLUS_I_ATTR_DIRTY 4 /* has changes in the attributes tree */
#define HFSPLUS_IS_RSRC(inode) \
test_bit(HFSPLUS_I_RSRC, &HFSPLUS_I(inode)->flags)
@@ -302,7 +311,7 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb)
#define hfs_brec_remove hfsplus_brec_remove
#define hfs_find_init hfsplus_find_init
#define hfs_find_exit hfsplus_find_exit
-#define __hfs_brec_find __hplusfs_brec_find
+#define __hfs_brec_find __hfsplus_brec_find
#define hfs_brec_find hfsplus_brec_find
#define hfs_brec_read hfsplus_brec_read
#define hfs_brec_goto hfsplus_brec_goto
@@ -324,10 +333,33 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb)
*/
#define HFSPLUS_IOC_BLESS _IO('h', 0x80)
+typedef int (*search_strategy_t)(struct hfs_bnode *,
+ struct hfs_find_data *,
+ int *, int *, int *);
+
/*
* Functions in any *.c used in other files
*/
+/* attributes.c */
+int hfsplus_create_attr_tree_cache(void);
+void hfsplus_destroy_attr_tree_cache(void);
+hfsplus_attr_entry *hfsplus_alloc_attr_entry(void);
+void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p);
+int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *,
+ const hfsplus_btree_key *);
+int hfsplus_attr_build_key(struct super_block *, hfsplus_btree_key *,
+ u32, const char *);
+void hfsplus_attr_build_key_uni(hfsplus_btree_key *key,
+ u32 cnid,
+ struct hfsplus_attr_unistr *name);
+int hfsplus_find_attr(struct super_block *, u32,
+ const char *, struct hfs_find_data *);
+int hfsplus_attr_exists(struct inode *inode, const char *name);
+int hfsplus_create_attr(struct inode *, const char *, const void *, size_t);
+int hfsplus_delete_attr(struct inode *, const char *);
+int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid);
+
/* bitmap.c */
int hfsplus_block_allocate(struct super_block *, u32, u32, u32 *);
int hfsplus_block_free(struct super_block *, u32, u32);
@@ -369,8 +401,15 @@ int hfs_brec_remove(struct hfs_find_data *);
/* bfind.c */
int hfs_find_init(struct hfs_btree *, struct hfs_find_data *);
void hfs_find_exit(struct hfs_find_data *);
-int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *);
-int hfs_brec_find(struct hfs_find_data *);
+int hfs_find_1st_rec_by_cnid(struct hfs_bnode *,
+ struct hfs_find_data *,
+ int *, int *, int *);
+int hfs_find_rec_by_key(struct hfs_bnode *,
+ struct hfs_find_data *,
+ int *, int *, int *);
+int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *,
+ search_strategy_t);
+int hfs_brec_find(struct hfs_find_data *, search_strategy_t);
int hfs_brec_read(struct hfs_find_data *, void *, int);
int hfs_brec_goto(struct hfs_find_data *, int);
@@ -417,11 +456,6 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
/* ioctl.c */
long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
-int hfsplus_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size);
-ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size);
/* options.c */
int hfsplus_parse_options(char *, struct hfsplus_sb_info *);
@@ -446,7 +480,7 @@ int hfsplus_strcmp(const struct hfsplus_unistr *,
int hfsplus_uni2asc(struct super_block *,
const struct hfsplus_unistr *, char *, int *);
int hfsplus_asc2uni(struct super_block *,
- struct hfsplus_unistr *, const char *, int);
+ struct hfsplus_unistr *, int, const char *, int);
int hfsplus_hash_dentry(const struct dentry *dentry,
const struct inode *inode, struct qstr *str);
int hfsplus_compare_dentry(const struct dentry *parent,
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 921967e5abb..452ede01b03 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -52,13 +52,23 @@
typedef __be32 hfsplus_cnid;
typedef __be16 hfsplus_unichr;
+#define HFSPLUS_MAX_STRLEN 255
+#define HFSPLUS_ATTR_MAX_STRLEN 127
+
/* A "string" as used in filenames, etc. */
struct hfsplus_unistr {
__be16 length;
- hfsplus_unichr unicode[255];
+ hfsplus_unichr unicode[HFSPLUS_MAX_STRLEN];
} __packed;
-#define HFSPLUS_MAX_STRLEN 255
+/*
+ * A "string" is used in attributes file
+ * for name of extended attribute
+ */
+struct hfsplus_attr_unistr {
+ __be16 length;
+ hfsplus_unichr unicode[HFSPLUS_ATTR_MAX_STRLEN];
+} __packed;
/* POSIX permissions */
struct hfsplus_perm {
@@ -291,6 +301,8 @@ struct hfsplus_cat_file {
/* File attribute bits */
#define HFSPLUS_FILE_LOCKED 0x0001
#define HFSPLUS_FILE_THREAD_EXISTS 0x0002
+#define HFSPLUS_XATTR_EXISTS 0x0004
+#define HFSPLUS_ACL_EXISTS 0x0008
/* HFS+ catalog thread (part of a cat_entry) */
struct hfsplus_cat_thread {
@@ -327,11 +339,63 @@ struct hfsplus_ext_key {
#define HFSPLUS_EXT_KEYLEN sizeof(struct hfsplus_ext_key)
+#define HFSPLUS_XATTR_FINDER_INFO_NAME "com.apple.FinderInfo"
+#define HFSPLUS_XATTR_ACL_NAME "com.apple.system.Security"
+
+#define HFSPLUS_ATTR_INLINE_DATA 0x10
+#define HFSPLUS_ATTR_FORK_DATA 0x20
+#define HFSPLUS_ATTR_EXTENTS 0x30
+
+/* HFS+ attributes tree key */
+struct hfsplus_attr_key {
+ __be16 key_len;
+ __be16 pad;
+ hfsplus_cnid cnid;
+ __be32 start_block;
+ struct hfsplus_attr_unistr key_name;
+} __packed;
+
+#define HFSPLUS_ATTR_KEYLEN sizeof(struct hfsplus_attr_key)
+
+/* HFS+ fork data attribute */
+struct hfsplus_attr_fork_data {
+ __be32 record_type;
+ __be32 reserved;
+ struct hfsplus_fork_raw the_fork;
+} __packed;
+
+/* HFS+ extension attribute */
+struct hfsplus_attr_extents {
+ __be32 record_type;
+ __be32 reserved;
+ struct hfsplus_extent extents;
+} __packed;
+
+#define HFSPLUS_MAX_INLINE_DATA_SIZE 3802
+
+/* HFS+ attribute inline data */
+struct hfsplus_attr_inline_data {
+ __be32 record_type;
+ __be32 reserved1;
+ u8 reserved2[6];
+ __be16 length;
+ u8 raw_bytes[HFSPLUS_MAX_INLINE_DATA_SIZE];
+} __packed;
+
+/* A data record in the attributes tree */
+typedef union {
+ __be32 record_type;
+ struct hfsplus_attr_fork_data fork_data;
+ struct hfsplus_attr_extents extents;
+ struct hfsplus_attr_inline_data inline_data;
+} __packed hfsplus_attr_entry;
+
/* HFS+ generic BTree key */
typedef union {
__be16 key_len;
struct hfsplus_cat_key cat;
struct hfsplus_ext_key ext;
+ struct hfsplus_attr_key attr;
} __packed hfsplus_btree_key;
#endif
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index dcd05be5344..160ccc9cdb4 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -17,6 +17,7 @@
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
+#include "xattr.h"
static int hfsplus_readpage(struct file *file, struct page *page)
{
@@ -348,6 +349,18 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
error = error2;
}
+ if (test_and_clear_bit(HFSPLUS_I_ATTR_DIRTY, &hip->flags)) {
+ if (sbi->attr_tree) {
+ error2 =
+ filemap_write_and_wait(
+ sbi->attr_tree->inode->i_mapping);
+ if (!error)
+ error = error2;
+ } else {
+ printk(KERN_ERR "hfs: sync non-existent attributes tree\n");
+ }
+ }
+
if (test_and_clear_bit(HFSPLUS_I_ALLOC_DIRTY, &hip->flags)) {
error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping);
if (!error)
@@ -365,9 +378,10 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
static const struct inode_operations hfsplus_file_inode_operations = {
.lookup = hfsplus_file_lookup,
.setattr = hfsplus_setattr,
- .setxattr = hfsplus_setxattr,
- .getxattr = hfsplus_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = hfsplus_listxattr,
+ .removexattr = hfsplus_removexattr,
};
static const struct file_operations hfsplus_file_operations = {
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index e3c4c420942..d3ff5cc317d 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -16,7 +16,6 @@
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/sched.h>
-#include <linux/xattr.h>
#include <asm/uaccess.h>
#include "hfsplus_fs.h"
@@ -151,110 +150,3 @@ long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return -ENOTTY;
}
}
-
-int hfsplus_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
-{
- struct inode *inode = dentry->d_inode;
- struct hfs_find_data fd;
- hfsplus_cat_entry entry;
- struct hfsplus_cat_file *file;
- int res;
-
- if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
- return -EOPNOTSUPP;
-
- res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
- if (res)
- return res;
- res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
- if (res)
- goto out;
- hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
- sizeof(struct hfsplus_cat_file));
- file = &entry.file;
-
- if (!strcmp(name, "hfs.type")) {
- if (size == 4)
- memcpy(&file->user_info.fdType, value, 4);
- else
- res = -ERANGE;
- } else if (!strcmp(name, "hfs.creator")) {
- if (size == 4)
- memcpy(&file->user_info.fdCreator, value, 4);
- else
- res = -ERANGE;
- } else
- res = -EOPNOTSUPP;
- if (!res) {
- hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
- sizeof(struct hfsplus_cat_file));
- hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
- }
-out:
- hfs_find_exit(&fd);
- return res;
-}
-
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size)
-{
- struct inode *inode = dentry->d_inode;
- struct hfs_find_data fd;
- hfsplus_cat_entry entry;
- struct hfsplus_cat_file *file;
- ssize_t res = 0;
-
- if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
- return -EOPNOTSUPP;
-
- if (size) {
- res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
- if (res)
- return res;
- res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
- if (res)
- goto out;
- hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
- sizeof(struct hfsplus_cat_file));
- }
- file = &entry.file;
-
- if (!strcmp(name, "hfs.type")) {
- if (size >= 4) {
- memcpy(value, &file->user_info.fdType, 4);
- res = 4;
- } else
- res = size ? -ERANGE : 4;
- } else if (!strcmp(name, "hfs.creator")) {
- if (size >= 4) {
- memcpy(value, &file->user_info.fdCreator, 4);
- res = 4;
- } else
- res = size ? -ERANGE : 4;
- } else
- res = -EOPNOTSUPP;
-out:
- if (size)
- hfs_find_exit(&fd);
- return res;
-}
-
-#define HFSPLUS_ATTRLIST_SIZE (sizeof("hfs.creator")+sizeof("hfs.type"))
-
-ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
- struct inode *inode = dentry->d_inode;
-
- if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
- return -EOPNOTSUPP;
-
- if (!buffer || !size)
- return HFSPLUS_ATTRLIST_SIZE;
- if (size < HFSPLUS_ATTRLIST_SIZE)
- return -ERANGE;
- strcpy(buffer, "hfs.type");
- strcpy(buffer + sizeof("hfs.type"), "hfs.creator");
-
- return HFSPLUS_ATTRLIST_SIZE;
-}
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 796198d2655..974c26f96fa 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -20,6 +20,7 @@ static struct inode *hfsplus_alloc_inode(struct super_block *sb);
static void hfsplus_destroy_inode(struct inode *inode);
#include "hfsplus_fs.h"
+#include "xattr.h"
static int hfsplus_system_read_inode(struct inode *inode)
{
@@ -118,6 +119,7 @@ static int hfsplus_system_write_inode(struct inode *inode)
case HFSPLUS_ATTR_CNID:
fork = &vhdr->attr_file;
tree = sbi->attr_tree;
+ break;
default:
return -EIO;
}
@@ -191,6 +193,12 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait)
error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping);
if (!error)
error = error2;
+ if (sbi->attr_tree) {
+ error2 =
+ filemap_write_and_wait(sbi->attr_tree->inode->i_mapping);
+ if (!error)
+ error = error2;
+ }
error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping);
if (!error)
error = error2;
@@ -281,6 +289,7 @@ static void hfsplus_put_super(struct super_block *sb)
hfsplus_sync_fs(sb, 1);
}
+ hfs_btree_close(sbi->attr_tree);
hfs_btree_close(sbi->cat_tree);
hfs_btree_close(sbi->ext_tree);
iput(sbi->alloc_file);
@@ -477,12 +486,20 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
printk(KERN_ERR "hfs: failed to load catalog file\n");
goto out_close_ext_tree;
}
+ if (vhdr->attr_file.total_blocks != 0) {
+ sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID);
+ if (!sbi->attr_tree) {
+ printk(KERN_ERR "hfs: failed to load attributes file\n");
+ goto out_close_cat_tree;
+ }
+ }
+ sb->s_xattr = hfsplus_xattr_handlers;
inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID);
if (IS_ERR(inode)) {
printk(KERN_ERR "hfs: failed to load allocation file\n");
err = PTR_ERR(inode);
- goto out_close_cat_tree;
+ goto out_close_attr_tree;
}
sbi->alloc_file = inode;
@@ -542,10 +559,27 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
}
err = hfsplus_create_cat(sbi->hidden_dir->i_ino, root,
&str, sbi->hidden_dir);
- mutex_unlock(&sbi->vh_mutex);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->vh_mutex);
+ goto out_put_hidden_dir;
+ }
+
+ err = hfsplus_init_inode_security(sbi->hidden_dir,
+ root, &str);
+ if (err == -EOPNOTSUPP)
+ err = 0; /* Operation is not supported. */
+ else if (err) {
+ /*
+ * Try to delete anyway without
+ * error analysis.
+ */
+ hfsplus_delete_cat(sbi->hidden_dir->i_ino,
+ root, &str);
+ mutex_unlock(&sbi->vh_mutex);
goto out_put_hidden_dir;
+ }
+ mutex_unlock(&sbi->vh_mutex);
hfsplus_mark_inode_dirty(sbi->hidden_dir,
HFSPLUS_I_CAT_DIRTY);
}
@@ -562,6 +596,8 @@ out_put_root:
sb->s_root = NULL;
out_put_alloc_file:
iput(sbi->alloc_file);
+out_close_attr_tree:
+ hfs_btree_close(sbi->attr_tree);
out_close_cat_tree:
hfs_btree_close(sbi->cat_tree);
out_close_ext_tree:
@@ -635,9 +671,20 @@ static int __init init_hfsplus_fs(void)
hfsplus_init_once);
if (!hfsplus_inode_cachep)
return -ENOMEM;
+ err = hfsplus_create_attr_tree_cache();
+ if (err)
+ goto destroy_inode_cache;
err = register_filesystem(&hfsplus_fs_type);
if (err)
- kmem_cache_destroy(hfsplus_inode_cachep);
+ goto destroy_attr_tree_cache;
+ return 0;
+
+destroy_attr_tree_cache:
+ hfsplus_destroy_attr_tree_cache();
+
+destroy_inode_cache:
+ kmem_cache_destroy(hfsplus_inode_cachep);
+
return err;
}
@@ -650,6 +697,7 @@ static void __exit exit_hfsplus_fs(void)
* destroy cache.
*/
rcu_barrier();
+ hfsplus_destroy_attr_tree_cache();
kmem_cache_destroy(hfsplus_inode_cachep);
}
diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index a32998f29f0..2c2e47dcfdd 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -295,7 +295,8 @@ static inline u16 *decompose_unichar(wchar_t uc, int *size)
return hfsplus_decompose_table + (off / 4);
}
-int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
+int hfsplus_asc2uni(struct super_block *sb,
+ struct hfsplus_unistr *ustr, int max_unistr_len,
const char *astr, int len)
{
int size, dsize, decompose;
@@ -303,7 +304,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
wchar_t c;
decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
- while (outlen < HFSPLUS_MAX_STRLEN && len > 0) {
+ while (outlen < max_unistr_len && len > 0) {
size = asc2unichar(sb, astr, len, &c);
if (decompose)
@@ -311,7 +312,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
else
dstr = NULL;
if (dstr) {
- if (outlen + dsize > HFSPLUS_MAX_STRLEN)
+ if (outlen + dsize > max_unistr_len)
break;
do {
ustr->unicode[outlen++] = cpu_to_be16(*dstr++);
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
new file mode 100644
index 00000000000..e8a4b0815c6
--- /dev/null
+++ b/fs/hfsplus/xattr.c
@@ -0,0 +1,709 @@
+/*
+ * linux/fs/hfsplus/xattr.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Logic of processing extended attributes
+ */
+
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+const struct xattr_handler *hfsplus_xattr_handlers[] = {
+ &hfsplus_xattr_osx_handler,
+ &hfsplus_xattr_user_handler,
+ &hfsplus_xattr_trusted_handler,
+ &hfsplus_xattr_security_handler,
+ NULL
+};
+
+static int strcmp_xattr_finder_info(const char *name)
+{
+ if (name) {
+ return strncmp(name, HFSPLUS_XATTR_FINDER_INFO_NAME,
+ sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME));
+ }
+ return -1;
+}
+
+static int strcmp_xattr_acl(const char *name)
+{
+ if (name) {
+ return strncmp(name, HFSPLUS_XATTR_ACL_NAME,
+ sizeof(HFSPLUS_XATTR_ACL_NAME));
+ }
+ return -1;
+}
+
+static inline int is_known_namespace(const char *name)
+{
+ if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) &&
+ strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
+ strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) &&
+ strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN))
+ return false;
+
+ return true;
+}
+
+static int can_set_xattr(struct inode *inode, const char *name,
+ const void *value, size_t value_len)
+{
+ if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+ return -EOPNOTSUPP; /* TODO: implement ACL support */
+
+ if (!strncmp(name, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN)) {
+ /*
+ * This makes sure that we aren't trying to set an
+ * attribute in a different namespace by prefixing it
+ * with "osx."
+ */
+ if (is_known_namespace(name + XATTR_MAC_OSX_PREFIX_LEN))
+ return -EOPNOTSUPP;
+
+ return 0;
+ }
+
+ /*
+ * Don't allow setting an attribute in an unknown namespace.
+ */
+ if (strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) &&
+ strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) &&
+ strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+int __hfsplus_setxattr(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ int err = 0;
+ struct hfs_find_data cat_fd;
+ hfsplus_cat_entry entry;
+ u16 cat_entry_flags, cat_entry_type;
+ u16 folder_finderinfo_len = sizeof(struct DInfo) +
+ sizeof(struct DXInfo);
+ u16 file_finderinfo_len = sizeof(struct FInfo) +
+ sizeof(struct FXInfo);
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ err = can_set_xattr(inode, name, value, size);
+ if (err)
+ return err;
+
+ if (strncmp(name, XATTR_MAC_OSX_PREFIX,
+ XATTR_MAC_OSX_PREFIX_LEN) == 0)
+ name += XATTR_MAC_OSX_PREFIX_LEN;
+
+ if (value == NULL) {
+ value = "";
+ size = 0;
+ }
+
+ err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return err;
+ }
+
+ err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: catalog searching failed\n");
+ goto end_setxattr;
+ }
+
+ if (!strcmp_xattr_finder_info(name)) {
+ if (flags & XATTR_CREATE) {
+ printk(KERN_ERR "hfs: xattr exists yet\n");
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ hfs_bnode_read(cat_fd.bnode, &entry, cat_fd.entryoffset,
+ sizeof(hfsplus_cat_entry));
+ if (be16_to_cpu(entry.type) == HFSPLUS_FOLDER) {
+ if (size == folder_finderinfo_len) {
+ memcpy(&entry.folder.user_info, value,
+ folder_finderinfo_len);
+ hfs_bnode_write(cat_fd.bnode, &entry,
+ cat_fd.entryoffset,
+ sizeof(struct hfsplus_cat_folder));
+ hfsplus_mark_inode_dirty(inode,
+ HFSPLUS_I_CAT_DIRTY);
+ } else {
+ err = -ERANGE;
+ goto end_setxattr;
+ }
+ } else if (be16_to_cpu(entry.type) == HFSPLUS_FILE) {
+ if (size == file_finderinfo_len) {
+ memcpy(&entry.file.user_info, value,
+ file_finderinfo_len);
+ hfs_bnode_write(cat_fd.bnode, &entry,
+ cat_fd.entryoffset,
+ sizeof(struct hfsplus_cat_file));
+ hfsplus_mark_inode_dirty(inode,
+ HFSPLUS_I_CAT_DIRTY);
+ } else {
+ err = -ERANGE;
+ goto end_setxattr;
+ }
+ } else {
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ goto end_setxattr;
+ }
+
+ if (!HFSPLUS_SB(inode->i_sb)->attr_tree) {
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+
+ if (hfsplus_attr_exists(inode, name)) {
+ if (flags & XATTR_CREATE) {
+ printk(KERN_ERR "hfs: xattr exists yet\n");
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ err = hfsplus_delete_attr(inode, name);
+ if (err)
+ goto end_setxattr;
+ err = hfsplus_create_attr(inode, name, value, size);
+ if (err)
+ goto end_setxattr;
+ } else {
+ if (flags & XATTR_REPLACE) {
+ printk(KERN_ERR "hfs: cannot replace xattr\n");
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ err = hfsplus_create_attr(inode, name, value, size);
+ if (err)
+ goto end_setxattr;
+ }
+
+ cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset);
+ if (cat_entry_type == HFSPLUS_FOLDER) {
+ cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode,
+ cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags));
+ cat_entry_flags |= HFSPLUS_XATTR_EXISTS;
+ if (!strcmp_xattr_acl(name))
+ cat_entry_flags |= HFSPLUS_ACL_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags),
+ cat_entry_flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else if (cat_entry_type == HFSPLUS_FILE) {
+ cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode,
+ cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags));
+ cat_entry_flags |= HFSPLUS_XATTR_EXISTS;
+ if (!strcmp_xattr_acl(name))
+ cat_entry_flags |= HFSPLUS_ACL_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags),
+ cat_entry_flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else {
+ printk(KERN_ERR "hfs: invalid catalog entry type\n");
+ err = -EIO;
+ goto end_setxattr;
+ }
+
+end_setxattr:
+ hfs_find_exit(&cat_fd);
+ return err;
+}
+
+static inline int is_osx_xattr(const char *xattr_name)
+{
+ return !is_known_namespace(xattr_name);
+}
+
+static int name_len(const char *xattr_name, int xattr_name_len)
+{
+ int len = xattr_name_len + 1;
+
+ if (is_osx_xattr(xattr_name))
+ len += XATTR_MAC_OSX_PREFIX_LEN;
+
+ return len;
+}
+
+static int copy_name(char *buffer, const char *xattr_name, int name_len)
+{
+ int len = name_len;
+ int offset = 0;
+
+ if (is_osx_xattr(xattr_name)) {
+ strncpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN);
+ offset += XATTR_MAC_OSX_PREFIX_LEN;
+ len += XATTR_MAC_OSX_PREFIX_LEN;
+ }
+
+ strncpy(buffer + offset, xattr_name, name_len);
+ memset(buffer + offset + name_len, 0, 1);
+ len += 1;
+
+ return len;
+}
+
+static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry,
+ void *value, size_t size)
+{
+ ssize_t res = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ u16 entry_type;
+ u16 folder_rec_len = sizeof(struct DInfo) + sizeof(struct DXInfo);
+ u16 file_rec_len = sizeof(struct FInfo) + sizeof(struct FXInfo);
+ u16 record_len = max(folder_rec_len, file_rec_len);
+ u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)];
+ u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)];
+
+ if (size >= record_len) {
+ res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
+ if (res) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return res;
+ }
+ res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
+ if (res)
+ goto end_getxattr_finder_info;
+ entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset);
+
+ if (entry_type == HFSPLUS_FOLDER) {
+ hfs_bnode_read(fd.bnode, folder_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, user_info),
+ folder_rec_len);
+ memcpy(value, folder_finder_info, folder_rec_len);
+ res = folder_rec_len;
+ } else if (entry_type == HFSPLUS_FILE) {
+ hfs_bnode_read(fd.bnode, file_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, user_info),
+ file_rec_len);
+ memcpy(value, file_finder_info, file_rec_len);
+ res = file_rec_len;
+ } else {
+ res = -EOPNOTSUPP;
+ goto end_getxattr_finder_info;
+ }
+ } else
+ res = size ? -ERANGE : record_len;
+
+end_getxattr_finder_info:
+ if (size >= record_len)
+ hfs_find_exit(&fd);
+ return res;
+}
+
+ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ void *value, size_t size)
+{
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ hfsplus_attr_entry *entry;
+ __be32 xattr_record_type;
+ u32 record_type;
+ u16 record_length = 0;
+ ssize_t res = 0;
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ if (strncmp(name, XATTR_MAC_OSX_PREFIX,
+ XATTR_MAC_OSX_PREFIX_LEN) == 0) {
+ /* skip "osx." prefix */
+ name += XATTR_MAC_OSX_PREFIX_LEN;
+ /*
+ * Don't allow retrieving properly prefixed attributes
+ * by prepending them with "osx."
+ */
+ if (is_known_namespace(name))
+ return -EOPNOTSUPP;
+ }
+
+ if (!strcmp_xattr_finder_info(name))
+ return hfsplus_getxattr_finder_info(dentry, value, size);
+
+ if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
+ return -EOPNOTSUPP;
+
+ entry = hfsplus_alloc_attr_entry();
+ if (!entry) {
+ printk(KERN_ERR "hfs: can't allocate xattr entry\n");
+ return -ENOMEM;
+ }
+
+ res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd);
+ if (res) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ goto failed_getxattr_init;
+ }
+
+ res = hfsplus_find_attr(inode->i_sb, inode->i_ino, name, &fd);
+ if (res) {
+ if (res == -ENOENT)
+ res = -ENODATA;
+ else
+ printk(KERN_ERR "hfs: xattr searching failed\n");
+ goto out;
+ }
+
+ hfs_bnode_read(fd.bnode, &xattr_record_type,
+ fd.entryoffset, sizeof(xattr_record_type));
+ record_type = be32_to_cpu(xattr_record_type);
+ if (record_type == HFSPLUS_ATTR_INLINE_DATA) {
+ record_length = hfs_bnode_read_u16(fd.bnode,
+ fd.entryoffset +
+ offsetof(struct hfsplus_attr_inline_data,
+ length));
+ if (record_length > HFSPLUS_MAX_INLINE_DATA_SIZE) {
+ printk(KERN_ERR "hfs: invalid xattr record size\n");
+ res = -EIO;
+ goto out;
+ }
+ } else if (record_type == HFSPLUS_ATTR_FORK_DATA ||
+ record_type == HFSPLUS_ATTR_EXTENTS) {
+ printk(KERN_ERR "hfs: only inline data xattr are supported\n");
+ res = -EOPNOTSUPP;
+ goto out;
+ } else {
+ printk(KERN_ERR "hfs: invalid xattr record\n");
+ res = -EIO;
+ goto out;
+ }
+
+ if (size) {
+ hfs_bnode_read(fd.bnode, entry, fd.entryoffset,
+ offsetof(struct hfsplus_attr_inline_data,
+ raw_bytes) + record_length);
+ }
+
+ if (size >= record_length) {
+ memcpy(value, entry->inline_data.raw_bytes, record_length);
+ res = record_length;
+ } else
+ res = size ? -ERANGE : record_length;
+
+out:
+ hfs_find_exit(&fd);
+
+failed_getxattr_init:
+ hfsplus_destroy_attr_entry(entry);
+ return res;
+}
+
+static inline int can_list(const char *xattr_name)
+{
+ if (!xattr_name)
+ return 0;
+
+ return strncmp(xattr_name, XATTR_TRUSTED_PREFIX,
+ XATTR_TRUSTED_PREFIX_LEN) ||
+ capable(CAP_SYS_ADMIN);
+}
+
+static ssize_t hfsplus_listxattr_finder_info(struct dentry *dentry,
+ char *buffer, size_t size)
+{
+ ssize_t res = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ u16 entry_type;
+ u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)];
+ u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)];
+ unsigned long len, found_bit;
+ int xattr_name_len, symbols_count;
+
+ res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
+ if (res) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return res;
+ }
+
+ res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
+ if (res)
+ goto end_listxattr_finder_info;
+
+ entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset);
+ if (entry_type == HFSPLUS_FOLDER) {
+ len = sizeof(struct DInfo) + sizeof(struct DXInfo);
+ hfs_bnode_read(fd.bnode, folder_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, user_info),
+ len);
+ found_bit = find_first_bit((void *)folder_finder_info, len*8);
+ } else if (entry_type == HFSPLUS_FILE) {
+ len = sizeof(struct FInfo) + sizeof(struct FXInfo);
+ hfs_bnode_read(fd.bnode, file_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, user_info),
+ len);
+ found_bit = find_first_bit((void *)file_finder_info, len*8);
+ } else {
+ res = -EOPNOTSUPP;
+ goto end_listxattr_finder_info;
+ }
+
+ if (found_bit >= (len*8))
+ res = 0;
+ else {
+ symbols_count = sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME) - 1;
+ xattr_name_len =
+ name_len(HFSPLUS_XATTR_FINDER_INFO_NAME, symbols_count);
+ if (!buffer || !size) {
+ if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME))
+ res = xattr_name_len;
+ } else if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME)) {
+ if (size < xattr_name_len)
+ res = -ERANGE;
+ else {
+ res = copy_name(buffer,
+ HFSPLUS_XATTR_FINDER_INFO_NAME,
+ symbols_count);
+ }
+ }
+ }
+
+end_listxattr_finder_info:
+ hfs_find_exit(&fd);
+
+ return res;
+}
+
+ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+ ssize_t err;
+ ssize_t res = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ u16 key_len = 0;
+ struct hfsplus_attr_key attr_key;
+ char strbuf[HFSPLUS_ATTR_MAX_STRLEN +
+ XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
+ int xattr_name_len;
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ res = hfsplus_listxattr_finder_info(dentry, buffer, size);
+ if (res < 0)
+ return res;
+ else if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
+ return (res == 0) ? -EOPNOTSUPP : res;
+
+ err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd);
+ if (err) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return err;
+ }
+
+ err = hfsplus_find_attr(inode->i_sb, inode->i_ino, NULL, &fd);
+ if (err) {
+ if (err == -ENOENT) {
+ if (res == 0)
+ res = -ENODATA;
+ goto end_listxattr;
+ } else {
+ res = err;
+ goto end_listxattr;
+ }
+ }
+
+ for (;;) {
+ key_len = hfs_bnode_read_u16(fd.bnode, fd.keyoffset);
+ if (key_len == 0 || key_len > fd.tree->max_key_len) {
+ printk(KERN_ERR "hfs: invalid xattr key length: %d\n",
+ key_len);
+ res = -EIO;
+ goto end_listxattr;
+ }
+
+ hfs_bnode_read(fd.bnode, &attr_key,
+ fd.keyoffset, key_len + sizeof(key_len));
+
+ if (be32_to_cpu(attr_key.cnid) != inode->i_ino)
+ goto end_listxattr;
+
+ xattr_name_len = HFSPLUS_ATTR_MAX_STRLEN;
+ if (hfsplus_uni2asc(inode->i_sb,
+ (const struct hfsplus_unistr *)&fd.key->attr.key_name,
+ strbuf, &xattr_name_len)) {
+ printk(KERN_ERR "hfs: unicode conversion failed\n");
+ res = -EIO;
+ goto end_listxattr;
+ }
+
+ if (!buffer || !size) {
+ if (can_list(strbuf))
+ res += name_len(strbuf, xattr_name_len);
+ } else if (can_list(strbuf)) {
+ if (size < (res + name_len(strbuf, xattr_name_len))) {
+ res = -ERANGE;
+ goto end_listxattr;
+ } else
+ res += copy_name(buffer + res,
+ strbuf, xattr_name_len);
+ }
+
+ if (hfs_brec_goto(&fd, 1))
+ goto end_listxattr;
+ }
+
+end_listxattr:
+ hfs_find_exit(&fd);
+ return res;
+}
+
+int hfsplus_removexattr(struct dentry *dentry, const char *name)
+{
+ int err = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data cat_fd;
+ u16 flags;
+ u16 cat_entry_type;
+ int is_xattr_acl_deleted = 0;
+ int is_all_xattrs_deleted = 0;
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
+ return -EOPNOTSUPP;
+
+ err = can_set_xattr(inode, name, NULL, 0);
+ if (err)
+ return err;
+
+ if (strncmp(name, XATTR_MAC_OSX_PREFIX,
+ XATTR_MAC_OSX_PREFIX_LEN) == 0)
+ name += XATTR_MAC_OSX_PREFIX_LEN;
+
+ if (!strcmp_xattr_finder_info(name))
+ return -EOPNOTSUPP;
+
+ err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return err;
+ }
+
+ err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: catalog searching failed\n");
+ goto end_removexattr;
+ }
+
+ err = hfsplus_delete_attr(inode, name);
+ if (err)
+ goto end_removexattr;
+
+ is_xattr_acl_deleted = !strcmp_xattr_acl(name);
+ is_all_xattrs_deleted = !hfsplus_attr_exists(inode, NULL);
+
+ if (!is_xattr_acl_deleted && !is_all_xattrs_deleted)
+ goto end_removexattr;
+
+ cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset);
+
+ if (cat_entry_type == HFSPLUS_FOLDER) {
+ flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags));
+ if (is_xattr_acl_deleted)
+ flags &= ~HFSPLUS_ACL_EXISTS;
+ if (is_all_xattrs_deleted)
+ flags &= ~HFSPLUS_XATTR_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags),
+ flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else if (cat_entry_type == HFSPLUS_FILE) {
+ flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags));
+ if (is_xattr_acl_deleted)
+ flags &= ~HFSPLUS_ACL_EXISTS;
+ if (is_all_xattrs_deleted)
+ flags &= ~HFSPLUS_XATTR_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags),
+ flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else {
+ printk(KERN_ERR "hfs: invalid catalog entry type\n");
+ err = -EIO;
+ goto end_removexattr;
+ }
+
+end_removexattr:
+ hfs_find_exit(&cat_fd);
+ return err;
+}
+
+static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN +
+ XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
+ strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN +
+ XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
+ strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+const struct xattr_handler hfsplus_xattr_osx_handler = {
+ .prefix = XATTR_MAC_OSX_PREFIX,
+ .list = hfsplus_osx_listxattr,
+ .get = hfsplus_osx_getxattr,
+ .set = hfsplus_osx_setxattr,
+};
diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h
new file mode 100644
index 00000000000..847b695b984
--- /dev/null
+++ b/fs/hfsplus/xattr.h
@@ -0,0 +1,60 @@
+/*
+ * linux/fs/hfsplus/xattr.h
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Logic of processing extended attributes
+ */
+
+#ifndef _LINUX_HFSPLUS_XATTR_H
+#define _LINUX_HFSPLUS_XATTR_H
+
+#include <linux/xattr.h>
+
+extern const struct xattr_handler hfsplus_xattr_osx_handler;
+extern const struct xattr_handler hfsplus_xattr_user_handler;
+extern const struct xattr_handler hfsplus_xattr_trusted_handler;
+/*extern const struct xattr_handler hfsplus_xattr_acl_access_handler;*/
+/*extern const struct xattr_handler hfsplus_xattr_acl_default_handler;*/
+extern const struct xattr_handler hfsplus_xattr_security_handler;
+
+extern const struct xattr_handler *hfsplus_xattr_handlers[];
+
+int __hfsplus_setxattr(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags);
+
+static inline int hfsplus_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ return __hfsplus_setxattr(dentry->d_inode, name, value, size, flags);
+}
+
+ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ void *value, size_t size);
+
+ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size);
+
+int hfsplus_removexattr(struct dentry *dentry, const char *name);
+
+int hfsplus_init_security(struct inode *inode, struct inode *dir,
+ const struct qstr *qstr);
+
+static inline int hfsplus_init_acl(struct inode *inode, struct inode *dir)
+{
+ /*TODO: implement*/
+ return 0;
+}
+
+static inline int hfsplus_init_inode_security(struct inode *inode,
+ struct inode *dir,
+ const struct qstr *qstr)
+{
+ int err;
+
+ err = hfsplus_init_acl(inode, dir);
+ if (!err)
+ err = hfsplus_init_security(inode, dir, qstr);
+ return err;
+}
+
+#endif
diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
new file mode 100644
index 00000000000..83b842f113c
--- /dev/null
+++ b/fs/hfsplus/xattr_security.c
@@ -0,0 +1,104 @@
+/*
+ * linux/fs/hfsplus/xattr_trusted.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for storing security labels as extended attributes.
+ */
+
+#include <linux/security.h>
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+static int hfsplus_security_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_SECURITY_PREFIX);
+ strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_security_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_SECURITY_PREFIX);
+ strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+static int hfsplus_initxattrs(struct inode *inode,
+ const struct xattr *xattr_array,
+ void *fs_info)
+{
+ const struct xattr *xattr;
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t xattr_name_len;
+ int err = 0;
+
+ for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+ xattr_name_len = strlen(xattr->name);
+
+ if (xattr_name_len == 0)
+ continue;
+
+ if (xattr_name_len + XATTR_SECURITY_PREFIX_LEN >
+ HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_SECURITY_PREFIX);
+ strcpy(xattr_name +
+ XATTR_SECURITY_PREFIX_LEN, xattr->name);
+ memset(xattr_name +
+ XATTR_SECURITY_PREFIX_LEN + xattr_name_len, 0, 1);
+
+ err = __hfsplus_setxattr(inode, xattr_name,
+ xattr->value, xattr->value_len, 0);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+int hfsplus_init_security(struct inode *inode, struct inode *dir,
+ const struct qstr *qstr)
+{
+ return security_inode_init_security(inode, dir, qstr,
+ &hfsplus_initxattrs, NULL);
+}
+
+const struct xattr_handler hfsplus_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .list = hfsplus_security_listxattr,
+ .get = hfsplus_security_getxattr,
+ .set = hfsplus_security_setxattr,
+};
diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c
new file mode 100644
index 00000000000..426cee27754
--- /dev/null
+++ b/fs/hfsplus/xattr_trusted.c
@@ -0,0 +1,63 @@
+/*
+ * linux/fs/hfsplus/xattr_trusted.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for trusted extended attributes.
+ */
+
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_TRUSTED_PREFIX);
+ strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_TRUSTED_PREFIX);
+ strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+const struct xattr_handler hfsplus_xattr_trusted_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .list = hfsplus_trusted_listxattr,
+ .get = hfsplus_trusted_getxattr,
+ .set = hfsplus_trusted_setxattr,
+};
diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c
new file mode 100644
index 00000000000..e34016561ae
--- /dev/null
+++ b/fs/hfsplus/xattr_user.c
@@ -0,0 +1,63 @@
+/*
+ * linux/fs/hfsplus/xattr_user.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for user extended attributes.
+ */
+
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+static int hfsplus_user_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_USER_PREFIX);
+ strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_user_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_USER_PREFIX);
+ strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+const struct xattr_handler hfsplus_xattr_user_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .list = hfsplus_user_listxattr,
+ .get = hfsplus_user_getxattr,
+ .set = hfsplus_user_setxattr,
+};
diff --git a/fs/inode.c b/fs/inode.c
index 67880e60439..f5f7c06c36f 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -798,11 +798,10 @@ static struct inode *find_inode(struct super_block *sb,
int (*test)(struct inode *, void *),
void *data)
{
- struct hlist_node *node;
struct inode *inode = NULL;
repeat:
- hlist_for_each_entry(inode, node, head, i_hash) {
+ hlist_for_each_entry(inode, head, i_hash) {
spin_lock(&inode->i_lock);
if (inode->i_sb != sb) {
spin_unlock(&inode->i_lock);
@@ -830,11 +829,10 @@ repeat:
static struct inode *find_inode_fast(struct super_block *sb,
struct hlist_head *head, unsigned long ino)
{
- struct hlist_node *node;
struct inode *inode = NULL;
repeat:
- hlist_for_each_entry(inode, node, head, i_hash) {
+ hlist_for_each_entry(inode, head, i_hash) {
spin_lock(&inode->i_lock);
if (inode->i_ino != ino) {
spin_unlock(&inode->i_lock);
@@ -1132,11 +1130,10 @@ EXPORT_SYMBOL(iget_locked);
static int test_inode_iunique(struct super_block *sb, unsigned long ino)
{
struct hlist_head *b = inode_hashtable + hash(sb, ino);
- struct hlist_node *node;
struct inode *inode;
spin_lock(&inode_hash_lock);
- hlist_for_each_entry(inode, node, b, i_hash) {
+ hlist_for_each_entry(inode, b, i_hash) {
if (inode->i_ino == ino && inode->i_sb == sb) {
spin_unlock(&inode_hash_lock);
return 0;
@@ -1291,10 +1288,9 @@ int insert_inode_locked(struct inode *inode)
struct hlist_head *head = inode_hashtable + hash(sb, ino);
while (1) {
- struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_hash_lock);
- hlist_for_each_entry(old, node, head, i_hash) {
+ hlist_for_each_entry(old, head, i_hash) {
if (old->i_ino != ino)
continue;
if (old->i_sb != sb)
@@ -1306,7 +1302,7 @@ int insert_inode_locked(struct inode *inode)
}
break;
}
- if (likely(!node)) {
+ if (likely(!old)) {
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW;
hlist_add_head(&inode->i_hash, head);
@@ -1334,11 +1330,10 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
while (1) {
- struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_hash_lock);
- hlist_for_each_entry(old, node, head, i_hash) {
+ hlist_for_each_entry(old, head, i_hash) {
if (old->i_sb != sb)
continue;
if (!test(old, data))
@@ -1350,7 +1345,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
}
break;
}
- if (likely(!node)) {
+ if (likely(!old)) {
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW;
hlist_add_head(&inode->i_hash, head);
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index a2717408c47..0796c45d0d4 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -11,7 +11,7 @@
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/nfs_fs.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
#include <linux/kthread.h>
@@ -220,10 +220,19 @@ reclaimer(void *ptr)
{
struct nlm_host *host = (struct nlm_host *) ptr;
struct nlm_wait *block;
+ struct nlm_rqst *req;
struct file_lock *fl, *next;
u32 nsmstate;
struct net *net = host->net;
+ req = kmalloc(sizeof(*req), GFP_KERNEL);
+ if (!req) {
+ printk(KERN_ERR "lockd: reclaimer unable to alloc memory."
+ " Locks for %s won't be reclaimed!\n",
+ host->h_name);
+ return 0;
+ }
+
allow_signal(SIGKILL);
down_write(&host->h_rwsem);
@@ -253,7 +262,7 @@ restart:
*/
if (signalled())
continue;
- if (nlmclnt_reclaim(host, fl) != 0)
+ if (nlmclnt_reclaim(host, fl, req) != 0)
continue;
list_add_tail(&fl->fl_u.nfs_fl.list, &host->h_granted);
if (host->h_nsmstate != nsmstate) {
@@ -279,5 +288,6 @@ restart:
/* Release host handle after use */
nlmclnt_release_host(host);
lockd_down(net);
+ kfree(req);
return 0;
}
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 366277190b8..7e529c3c45c 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -618,17 +618,15 @@ out_unlock:
* RECLAIM: Try to reclaim a lock
*/
int
-nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl)
+nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl,
+ struct nlm_rqst *req)
{
- struct nlm_rqst reqst, *req;
int status;
- req = &reqst;
memset(req, 0, sizeof(*req));
locks_init_lock(&req->a_args.lock.fl);
locks_init_lock(&req->a_res.lock.fl);
req->a_host = host;
- req->a_flags = 0;
/* Set up the argument struct */
nlmclnt_setlockargs(req, fl);
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 0e17090c310..969d589c848 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -13,6 +13,7 @@
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
#include <linux/mutex.h>
@@ -32,15 +33,15 @@
static struct hlist_head nlm_server_hosts[NLM_HOST_NRHASH];
static struct hlist_head nlm_client_hosts[NLM_HOST_NRHASH];
-#define for_each_host(host, pos, chain, table) \
+#define for_each_host(host, chain, table) \
for ((chain) = (table); \
(chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \
- hlist_for_each_entry((host), (pos), (chain), h_hash)
+ hlist_for_each_entry((host), (chain), h_hash)
-#define for_each_host_safe(host, pos, next, chain, table) \
+#define for_each_host_safe(host, next, chain, table) \
for ((chain) = (table); \
(chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \
- hlist_for_each_entry_safe((host), (pos), (next), \
+ hlist_for_each_entry_safe((host), (next), \
(chain), h_hash)
static unsigned long nrhosts;
@@ -225,7 +226,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
.net = net,
};
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host;
struct nsm_handle *nsm = NULL;
struct lockd_net *ln = net_generic(net, lockd_net_id);
@@ -237,7 +237,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
mutex_lock(&nlm_host_mutex);
chain = &nlm_client_hosts[nlm_hash_address(sap)];
- hlist_for_each_entry(host, pos, chain, h_hash) {
+ hlist_for_each_entry(host, chain, h_hash) {
if (host->net != net)
continue;
if (!rpc_cmp_addr(nlm_addr(host), sap))
@@ -322,7 +322,6 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
const size_t hostname_len)
{
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host = NULL;
struct nsm_handle *nsm = NULL;
struct sockaddr *src_sap = svc_daddr(rqstp);
@@ -350,7 +349,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
nlm_gc_hosts(net);
chain = &nlm_server_hosts[nlm_hash_address(ni.sap)];
- hlist_for_each_entry(host, pos, chain, h_hash) {
+ hlist_for_each_entry(host, chain, h_hash) {
if (host->net != net)
continue;
if (!rpc_cmp_addr(nlm_addr(host), ni.sap))
@@ -515,10 +514,9 @@ static struct nlm_host *next_host_state(struct hlist_head *cache,
{
struct nlm_host *host;
struct hlist_head *chain;
- struct hlist_node *pos;
mutex_lock(&nlm_host_mutex);
- for_each_host(host, pos, chain, cache) {
+ for_each_host(host, chain, cache) {
if (host->h_nsmhandle == nsm
&& host->h_nsmstate != info->state) {
host->h_nsmstate = info->state;
@@ -570,7 +568,6 @@ void nlm_host_rebooted(const struct nlm_reboot *info)
static void nlm_complain_hosts(struct net *net)
{
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host;
if (net) {
@@ -587,7 +584,7 @@ static void nlm_complain_hosts(struct net *net)
dprintk("lockd: %lu hosts left:\n", nrhosts);
}
- for_each_host(host, pos, chain, nlm_server_hosts) {
+ for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
dprintk(" %s (cnt %d use %d exp %ld net %p)\n",
@@ -600,14 +597,13 @@ void
nlm_shutdown_hosts_net(struct net *net)
{
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host;
mutex_lock(&nlm_host_mutex);
/* First, make all hosts eligible for gc */
dprintk("lockd: nuking all hosts in net %p...\n", net);
- for_each_host(host, pos, chain, nlm_server_hosts) {
+ for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
host->h_expires = jiffies - 1;
@@ -644,11 +640,11 @@ static void
nlm_gc_hosts(struct net *net)
{
struct hlist_head *chain;
- struct hlist_node *pos, *next;
+ struct hlist_node *next;
struct nlm_host *host;
dprintk("lockd: host garbage collection for net %p\n", net);
- for_each_host(host, pos, chain, nlm_server_hosts) {
+ for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
host->h_inuse = 0;
@@ -657,7 +653,7 @@ nlm_gc_hosts(struct net *net)
/* Mark all hosts that hold locks, blocks or shares */
nlmsvc_mark_resources(net);
- for_each_host_safe(host, pos, next, chain, nlm_server_hosts) {
+ for_each_host_safe(host, next, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
if (atomic_read(&host->h_count) || host->h_inuse
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 3c2cfc68363..1812f026960 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -12,6 +12,7 @@
#include <linux/slab.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/xprtsock.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index b3a24b07d98..97e87415b14 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -13,7 +13,7 @@
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/nfsd/nfsfh.h>
#include <linux/nfsd/export.h>
#include <linux/lockd/lockd.h>
@@ -84,7 +84,6 @@ __be32
nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result,
struct nfs_fh *f)
{
- struct hlist_node *pos;
struct nlm_file *file;
unsigned int hash;
__be32 nfserr;
@@ -96,7 +95,7 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result,
/* Lock file table */
mutex_lock(&nlm_file_mutex);
- hlist_for_each_entry(file, pos, &nlm_files[hash], f_list)
+ hlist_for_each_entry(file, &nlm_files[hash], f_list)
if (!nfs_compare_fh(&file->f_handle, f))
goto found;
@@ -248,13 +247,13 @@ static int
nlm_traverse_files(void *data, nlm_host_match_fn_t match,
int (*is_failover_file)(void *data, struct nlm_file *file))
{
- struct hlist_node *pos, *next;
+ struct hlist_node *next;
struct nlm_file *file;
int i, ret = 0;
mutex_lock(&nlm_file_mutex);
for (i = 0; i < FILE_NRHASH; i++) {
- hlist_for_each_entry_safe(file, pos, next, &nlm_files[i], f_list) {
+ hlist_for_each_entry_safe(file, next, &nlm_files[i], f_list) {
if (is_failover_file && !is_failover_file(data, file))
continue;
file->f_count++;
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index 862a2f16db6..5f7b053720e 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -128,10 +128,13 @@ int nfs_cache_register_net(struct net *net, struct cache_detail *cd)
struct super_block *pipefs_sb;
int ret = 0;
+ sunrpc_init_cache_detail(cd);
pipefs_sb = rpc_get_sb_net(net);
if (pipefs_sb) {
ret = nfs_cache_register_sb(pipefs_sb, cd);
rpc_put_sb_net(net);
+ if (ret)
+ sunrpc_destroy_cache_detail(cd);
}
return ret;
}
@@ -151,14 +154,5 @@ void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd)
nfs_cache_unregister_sb(pipefs_sb, cd);
rpc_put_sb_net(net);
}
-}
-
-void nfs_cache_init(struct cache_detail *cd)
-{
- sunrpc_init_cache_detail(cd);
-}
-
-void nfs_cache_destroy(struct cache_detail *cd)
-{
sunrpc_destroy_cache_detail(cd);
}
diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h
index 317db95e37f..4116d2c3f52 100644
--- a/fs/nfs/cache_lib.h
+++ b/fs/nfs/cache_lib.h
@@ -23,8 +23,6 @@ extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void);
extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq);
extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq);
-extern void nfs_cache_init(struct cache_detail *cd);
-extern void nfs_cache_destroy(struct cache_detail *cd);
extern int nfs_cache_register_net(struct net *net, struct cache_detail *cd);
extern void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd);
extern int nfs_cache_register_sb(struct super_block *sb,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 9f3c66438d0..84d8eae203a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -197,7 +197,6 @@ error_0:
EXPORT_SYMBOL_GPL(nfs_alloc_client);
#if IS_ENABLED(CONFIG_NFS_V4)
-/* idr_remove_all is not needed as all id's are removed by nfs_put_client */
void nfs_cleanup_cb_ident_idr(struct net *net)
{
struct nfs_net *nn = net_generic(net, nfs_net_id);
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index ca4b11ec87a..94552709229 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/dns_resolver.h>
#include "dns_resolve.h"
@@ -42,6 +43,7 @@ EXPORT_SYMBOL_GPL(nfs_dns_resolve_name);
#include <linux/seq_file.h>
#include <linux/inet.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/svcauth.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
@@ -142,7 +144,7 @@ static int nfs_dns_upcall(struct cache_detail *cd,
ret = nfs_cache_upcall(cd, key->hostname);
if (ret)
- ret = sunrpc_cache_pipe_upcall(cd, ch, nfs_dns_request);
+ ret = sunrpc_cache_pipe_upcall(cd, ch);
return ret;
}
@@ -351,60 +353,47 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name,
}
EXPORT_SYMBOL_GPL(nfs_dns_resolve_name);
+static struct cache_detail nfs_dns_resolve_template = {
+ .owner = THIS_MODULE,
+ .hash_size = NFS_DNS_HASHTBL_SIZE,
+ .name = "dns_resolve",
+ .cache_put = nfs_dns_ent_put,
+ .cache_upcall = nfs_dns_upcall,
+ .cache_request = nfs_dns_request,
+ .cache_parse = nfs_dns_parse,
+ .cache_show = nfs_dns_show,
+ .match = nfs_dns_match,
+ .init = nfs_dns_ent_init,
+ .update = nfs_dns_ent_update,
+ .alloc = nfs_dns_ent_alloc,
+};
+
+
int nfs_dns_resolver_cache_init(struct net *net)
{
- int err = -ENOMEM;
+ int err;
struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct cache_detail *cd;
- struct cache_head **tbl;
- cd = kzalloc(sizeof(struct cache_detail), GFP_KERNEL);
- if (cd == NULL)
- goto err_cd;
-
- tbl = kzalloc(NFS_DNS_HASHTBL_SIZE * sizeof(struct cache_head *),
- GFP_KERNEL);
- if (tbl == NULL)
- goto err_tbl;
-
- cd->owner = THIS_MODULE,
- cd->hash_size = NFS_DNS_HASHTBL_SIZE,
- cd->hash_table = tbl,
- cd->name = "dns_resolve",
- cd->cache_put = nfs_dns_ent_put,
- cd->cache_upcall = nfs_dns_upcall,
- cd->cache_parse = nfs_dns_parse,
- cd->cache_show = nfs_dns_show,
- cd->match = nfs_dns_match,
- cd->init = nfs_dns_ent_init,
- cd->update = nfs_dns_ent_update,
- cd->alloc = nfs_dns_ent_alloc,
-
- nfs_cache_init(cd);
- err = nfs_cache_register_net(net, cd);
+ nn->nfs_dns_resolve = cache_create_net(&nfs_dns_resolve_template, net);
+ if (IS_ERR(nn->nfs_dns_resolve))
+ return PTR_ERR(nn->nfs_dns_resolve);
+
+ err = nfs_cache_register_net(net, nn->nfs_dns_resolve);
if (err)
goto err_reg;
- nn->nfs_dns_resolve = cd;
return 0;
err_reg:
- nfs_cache_destroy(cd);
- kfree(cd->hash_table);
-err_tbl:
- kfree(cd);
-err_cd:
+ cache_destroy_net(nn->nfs_dns_resolve, net);
return err;
}
void nfs_dns_resolver_cache_destroy(struct net *net)
{
struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct cache_detail *cd = nn->nfs_dns_resolve;
- nfs_cache_unregister_net(net, cd);
- nfs_cache_destroy(cd);
- kfree(cd->hash_table);
- kfree(cd);
+ nfs_cache_unregister_net(net, nn->nfs_dns_resolve);
+ cache_destroy_net(nn->nfs_dns_resolve, net);
}
static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 2e9779b58b7..ac4fc9a8fdb 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -6,6 +6,7 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_idmap.h>
#include <linux/nfs_mount.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/bc_xprt.h>
@@ -29,15 +30,14 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
if (clp->rpc_ops->version != 4 || minorversion != 0)
return ret;
-retry:
- if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
- return -ENOMEM;
+ idr_preload(GFP_KERNEL);
spin_lock(&nn->nfs_client_lock);
- ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+ ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT);
+ if (ret >= 0)
+ clp->cl_cb_ident = ret;
spin_unlock(&nn->nfs_client_lock);
- if (ret == -EAGAIN)
- goto retry;
- return ret;
+ idr_preload_end();
+ return ret < 0 ? ret : 0;
}
#ifdef CONFIG_NFS_V4_1
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index b720064bcd7..1fe284f01f8 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -31,6 +31,7 @@
#include <linux/nfs_fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
+#include <linux/sunrpc/addr.h>
#include "internal.h"
#include "nfs4session.h"
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 1e09eb78543..0dd766079e1 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/vfs.h>
#include <linux/inet.h>
#include "internal.h"
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index d35b62e83ea..6da209bd940 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -77,9 +77,8 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
long hash)
{
struct nfs4_deviceid_node *d;
- struct hlist_node *n;
- hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+ hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node)
if (d->ld == ld && d->nfs_client == clp &&
!memcmp(&d->deviceid, id, sizeof(*id))) {
if (atomic_read(&d->ref))
@@ -248,12 +247,11 @@ static void
_deviceid_purge_client(const struct nfs_client *clp, long hash)
{
struct nfs4_deviceid_node *d;
- struct hlist_node *n;
HLIST_HEAD(tmp);
spin_lock(&nfs4_deviceid_lock);
rcu_read_lock();
- hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+ hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node)
if (d->nfs_client == clp && atomic_read(&d->ref)) {
hlist_del_init_rcu(&d->node);
hlist_add_head(&d->tmpnode, &tmp);
@@ -291,12 +289,11 @@ void
nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
{
struct nfs4_deviceid_node *d;
- struct hlist_node *n;
int i;
rcu_read_lock();
for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){
- hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[i], node)
+ hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[i], node)
if (d->nfs_client == clp)
set_bit(NFS_DEVICEID_INVALID, &d->flags);
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index a9dc5fc2995..17b32b72245 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -31,6 +31,7 @@
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/metrics.h>
#include <linux/sunrpc/xprtsock.h>
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 93cc9d34c45..87fd1410b73 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -12,6 +12,10 @@
/*
* Representation of a reply cache entry.
+ *
+ * Note that we use a sockaddr_in6 to hold the address instead of the more
+ * typical sockaddr_storage. This is for space reasons, since sockaddr_storage
+ * is much larger than a sockaddr_in6.
*/
struct svc_cacherep {
struct hlist_node c_hash;
@@ -20,11 +24,13 @@ struct svc_cacherep {
unsigned char c_state, /* unused, inprog, done */
c_type, /* status, buffer */
c_secure : 1; /* req came from port < 1024 */
- struct sockaddr_in c_addr;
+ struct sockaddr_in6 c_addr;
__be32 c_xid;
u32 c_prot;
u32 c_proc;
u32 c_vers;
+ unsigned int c_len;
+ __wsum c_csum;
unsigned long c_timestamp;
union {
struct kvec u_vec;
@@ -46,8 +52,7 @@ enum {
enum {
RC_DROPIT,
RC_REPLY,
- RC_DOIT,
- RC_INTR
+ RC_DOIT
};
/*
@@ -67,6 +72,12 @@ enum {
*/
#define RC_DELAY (HZ/5)
+/* Cache entries expire after this time period */
+#define RC_EXPIRE (120 * HZ)
+
+/* Checksum this amount of the request */
+#define RC_CSUMLEN (256U)
+
int nfsd_reply_cache_init(void);
void nfsd_reply_cache_shutdown(void);
int nfsd_cache_lookup(struct svc_rqst *);
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 5681c5906f0..5f38ea36e26 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -67,11 +67,6 @@ static void expkey_request(struct cache_detail *cd,
(*bpp)[-1] = '\n';
}
-static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
-{
- return sunrpc_cache_pipe_upcall(cd, h, expkey_request);
-}
-
static struct svc_expkey *svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new,
struct svc_expkey *old);
static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_expkey *);
@@ -245,7 +240,7 @@ static struct cache_detail svc_expkey_cache_template = {
.hash_size = EXPKEY_HASHMAX,
.name = "nfsd.fh",
.cache_put = expkey_put,
- .cache_upcall = expkey_upcall,
+ .cache_request = expkey_request,
.cache_parse = expkey_parse,
.cache_show = expkey_show,
.match = expkey_match,
@@ -315,6 +310,7 @@ static void svc_export_put(struct kref *ref)
path_put(&exp->ex_path);
auth_domain_put(exp->ex_client);
nfsd4_fslocs_free(&exp->ex_fslocs);
+ kfree(exp->ex_uuid);
kfree(exp);
}
@@ -337,11 +333,6 @@ static void svc_export_request(struct cache_detail *cd,
(*bpp)[-1] = '\n';
}
-static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
-{
- return sunrpc_cache_pipe_upcall(cd, h, svc_export_request);
-}
-
static struct svc_export *svc_export_update(struct svc_export *new,
struct svc_export *old);
static struct svc_export *svc_export_lookup(struct svc_export *);
@@ -674,6 +665,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
new->ex_fslocs.locations = NULL;
new->ex_fslocs.locations_count = 0;
new->ex_fslocs.migrated = 0;
+ new->ex_uuid = NULL;
new->cd = item->cd;
}
@@ -715,7 +707,7 @@ static struct cache_detail svc_export_cache_template = {
.hash_size = EXPORT_HASHMAX,
.name = "nfsd.export",
.cache_put = svc_export_put,
- .cache_upcall = svc_export_upcall,
+ .cache_request = svc_export_request,
.cache_parse = svc_export_parse,
.cache_show = svc_export_show,
.match = svc_export_match,
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index 497584c7036..d620e7f8142 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -9,7 +9,7 @@
#include <linux/debugfs.h>
#include <linux/module.h>
#include <linux/nsproxy.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <asm/uaccess.h>
#include "state.h"
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 0ce12346df9..4832fd819f8 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -140,12 +140,6 @@ idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
}
static int
-idtoname_upcall(struct cache_detail *cd, struct cache_head *ch)
-{
- return sunrpc_cache_pipe_upcall(cd, ch, idtoname_request);
-}
-
-static int
idtoname_match(struct cache_head *ca, struct cache_head *cb)
{
struct ent *a = container_of(ca, struct ent, h);
@@ -192,7 +186,7 @@ static struct cache_detail idtoname_cache_template = {
.hash_size = ENT_HASHMAX,
.name = "nfs4.idtoname",
.cache_put = ent_put,
- .cache_upcall = idtoname_upcall,
+ .cache_request = idtoname_request,
.cache_parse = idtoname_parse,
.cache_show = idtoname_show,
.warn_no_listener = warn_no_idmapd,
@@ -321,12 +315,6 @@ nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
}
static int
-nametoid_upcall(struct cache_detail *cd, struct cache_head *ch)
-{
- return sunrpc_cache_pipe_upcall(cd, ch, nametoid_request);
-}
-
-static int
nametoid_match(struct cache_head *ca, struct cache_head *cb)
{
struct ent *a = container_of(ca, struct ent, h);
@@ -365,7 +353,7 @@ static struct cache_detail nametoid_cache_template = {
.hash_size = ENT_HASHMAX,
.name = "nfs4.nametoid",
.cache_put = ent_put,
- .cache_upcall = nametoid_upcall,
+ .cache_request = nametoid_request,
.cache_parse = nametoid_parse,
.cache_show = nametoid_show,
.warn_no_listener = warn_no_idmapd,
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 9d1c5dba2bb..ae73175e6e6 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -993,14 +993,15 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (!buf)
return nfserr_jukebox;
+ p = buf;
status = nfsd4_encode_fattr(&cstate->current_fh,
cstate->current_fh.fh_export,
- cstate->current_fh.fh_dentry, buf,
- &count, verify->ve_bmval,
+ cstate->current_fh.fh_dentry, &p,
+ count, verify->ve_bmval,
rqstp, 0);
/* this means that nfsd4_encode_fattr() ran out of space */
- if (status == nfserr_resource && count == 0)
+ if (status == nfserr_resource)
status = nfserr_not_same;
if (status)
goto out_kfree;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 4914af4a817..899ca26dd19 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1185,6 +1185,12 @@ bin_to_hex_dup(const unsigned char *src, int srclen)
static int
nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net)
{
+ /* XXX: The usermode helper s not working in container yet. */
+ if (net != &init_net) {
+ WARN(1, KERN_ERR "NFSD: attempt to initialize umh client "
+ "tracking in a container!\n");
+ return -EINVAL;
+ }
return nfsd4_umh_cltrack_upcall("init", NULL, NULL);
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9e7103b6e0a..16d39c6c4fb 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -40,7 +40,7 @@
#include <linux/pagemap.h>
#include <linux/ratelimit.h>
#include <linux/sunrpc/svcauth_gss.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include "xdr4.h"
#include "vfs.h"
#include "current_stateid.h"
@@ -261,33 +261,46 @@ static inline int get_new_stid(struct nfs4_stid *stid)
return new_stid;
}
-static void init_stid(struct nfs4_stid *stid, struct nfs4_client *cl, unsigned char type)
+static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
+kmem_cache *slab)
{
- stateid_t *s = &stid->sc_stateid;
+ struct idr *stateids = &cl->cl_stateids;
+ static int min_stateid = 0;
+ struct nfs4_stid *stid;
int new_id;
- stid->sc_type = type;
+ stid = kmem_cache_alloc(slab, GFP_KERNEL);
+ if (!stid)
+ return NULL;
+
+ if (!idr_pre_get(stateids, GFP_KERNEL))
+ goto out_free;
+ if (idr_get_new_above(stateids, stid, min_stateid, &new_id))
+ goto out_free;
stid->sc_client = cl;
- s->si_opaque.so_clid = cl->cl_clientid;
- new_id = get_new_stid(stid);
- s->si_opaque.so_id = (u32)new_id;
+ stid->sc_type = 0;
+ stid->sc_stateid.si_opaque.so_id = new_id;
+ stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
/* Will be incremented before return to client: */
- s->si_generation = 0;
-}
-
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab)
-{
- struct idr *stateids = &cl->cl_stateids;
+ stid->sc_stateid.si_generation = 0;
- if (!idr_pre_get(stateids, GFP_KERNEL))
- return NULL;
/*
- * Note: if we fail here (or any time between now and the time
- * we actually get the new idr), we won't need to undo the idr
- * preallocation, since the idr code caps the number of
- * preallocated entries.
+ * It shouldn't be a problem to reuse an opaque stateid value.
+ * I don't think it is for 4.1. But with 4.0 I worry that, for
+ * example, a stray write retransmission could be accepted by
+ * the server when it should have been rejected. Therefore,
+ * adopt a trick from the sctp code to attempt to maximize the
+ * amount of time until an id is reused, by ensuring they always
+ * "increase" (mod INT_MAX):
*/
- return kmem_cache_alloc(slab, GFP_KERNEL);
+
+ min_stateid = new_id+1;
+ if (min_stateid == INT_MAX)
+ min_stateid = 0;
+ return stid;
+out_free:
+ kfree(stid);
+ return NULL;
}
static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
@@ -316,7 +329,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
if (dp == NULL)
return dp;
- init_stid(&dp->dl_stid, clp, NFS4_DELEG_STID);
+ dp->dl_stid.sc_type = NFS4_DELEG_STID;
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -337,13 +350,21 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
return dp;
}
+static void free_stid(struct nfs4_stid *s, struct kmem_cache *slab)
+{
+ struct idr *stateids = &s->sc_client->cl_stateids;
+
+ idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ kmem_cache_free(slab, s);
+}
+
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
if (atomic_dec_and_test(&dp->dl_count)) {
dprintk("NFSD: freeing dp %p\n",dp);
put_nfs4_file(dp->dl_file);
- kmem_cache_free(deleg_slab, dp);
+ free_stid(&dp->dl_stid, deleg_slab);
num_delegations--;
}
}
@@ -360,9 +381,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
static void unhash_stid(struct nfs4_stid *s)
{
- struct idr *stateids = &s->sc_client->cl_stateids;
-
- idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ s->sc_type = 0;
}
/* Called under the state lock. */
@@ -519,7 +538,7 @@ static void close_generic_stateid(struct nfs4_ol_stateid *stp)
static void free_generic_stateid(struct nfs4_ol_stateid *stp)
{
- kmem_cache_free(stateid_slab, stp);
+ free_stid(&stp->st_stid, stateid_slab);
}
static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -905,7 +924,7 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan,
new = __alloc_session(slotsize, numslots);
if (!new) {
- nfsd4_put_drc_mem(slotsize, fchan->maxreqs);
+ nfsd4_put_drc_mem(slotsize, numslots);
return NULL;
}
init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize, nn);
@@ -1048,7 +1067,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
static inline void
free_client(struct nfs4_client *clp)
{
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id);
lockdep_assert_held(&nn->client_lock);
while (!list_empty(&clp->cl_sessions)) {
@@ -1060,6 +1079,7 @@ free_client(struct nfs4_client *clp)
}
free_svc_cred(&clp->cl_cred);
kfree(clp->cl_name.data);
+ idr_destroy(&clp->cl_stateids);
kfree(clp);
}
@@ -1258,7 +1278,12 @@ static void gen_confirm(struct nfs4_client *clp)
static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
{
- return idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ struct nfs4_stid *ret;
+
+ ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ if (!ret || !ret->sc_type)
+ return NULL;
+ return ret;
}
static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
@@ -1844,11 +1869,12 @@ nfsd4_create_session(struct svc_rqst *rqstp,
/* cache solo and embedded create sessions under the state lock */
nfsd4_cache_create_session(cr_ses, cs_slot, status);
-out:
nfs4_unlock_state();
+out:
dprintk("%s returns %d\n", __func__, ntohl(status));
return status;
out_free_conn:
+ nfs4_unlock_state();
free_conn(conn);
out_free_session:
__free_session(new);
@@ -2443,9 +2469,8 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
struct nfs4_openowner *oo = open->op_openowner;
- struct nfs4_client *clp = oo->oo_owner.so_client;
- init_stid(&stp->st_stid, clp, NFS4_OPEN_STID);
+ stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_lockowners);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
list_add(&stp->st_perfile, &fp->fi_stateids);
@@ -4031,7 +4056,7 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp = nfs4_alloc_stateid(clp);
if (stp == NULL)
return NULL;
- init_stid(&stp->st_stid, clp, NFS4_LOCK_STID);
+ stp->st_stid.sc_type = NFS4_LOCK_STID;
list_add(&stp->st_perfile, &fp->fi_stateids);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
stp->st_stateowner = &lo->lo_owner;
@@ -4913,16 +4938,6 @@ nfs4_state_start_net(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int ret;
- /*
- * FIXME: For now, we hang most of the pernet global stuff off of
- * init_net until nfsd is fully containerized. Eventually, we'll
- * need to pass a net pointer into this function, take a reference
- * to that instead and then do most of the rest of this on a per-net
- * basis.
- */
- if (net != &init_net)
- return -EINVAL;
-
ret = nfs4_state_create_net(net);
if (ret)
return ret;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 8ca6d17f6cf..01168865dd3 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2024,12 +2024,11 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
* Note: @fhp can be NULL; in this case, we might have to compose the filehandle
* ourselves.
*
- * @countp is the buffer size in _words_; upon successful return this becomes
- * replaced with the number of words written.
+ * countp is the buffer size in _words_
*/
__be32
nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval,
+ struct dentry *dentry, __be32 **buffer, int count, u32 *bmval,
struct svc_rqst *rqstp, int ignore_crossmnt)
{
u32 bmval0 = bmval[0];
@@ -2038,12 +2037,12 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
struct kstat stat;
struct svc_fh tempfh;
struct kstatfs statfs;
- int buflen = *countp << 2;
+ int buflen = count << 2;
__be32 *attrlenp;
u32 dummy;
u64 dummy64;
u32 rdattr_err = 0;
- __be32 *p = buffer;
+ __be32 *p = *buffer;
__be32 status;
int err;
int aclsupport = 0;
@@ -2447,7 +2446,7 @@ out_acl:
}
*attrlenp = htonl((char *)p - (char *)attrlenp - 4);
- *countp = p - buffer;
+ *buffer = p;
status = nfs_ok;
out:
@@ -2459,7 +2458,6 @@ out_nfserr:
status = nfserrno(err);
goto out;
out_resource:
- *countp = 0;
status = nfserr_resource;
goto out;
out_serverfault:
@@ -2478,7 +2476,7 @@ static inline int attributes_need_mount(u32 *bmval)
static __be32
nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
- const char *name, int namlen, __be32 *p, int *buflen)
+ const char *name, int namlen, __be32 **p, int buflen)
{
struct svc_export *exp = cd->rd_fhp->fh_export;
struct dentry *dentry;
@@ -2584,10 +2582,9 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */
p = xdr_encode_array(p, name, namlen); /* name length & name */
- nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, p, &buflen);
+ nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, &p, buflen);
switch (nfserr) {
case nfs_ok:
- p += buflen;
break;
case nfserr_resource:
nfserr = nfserr_toosmall;
@@ -2714,10 +2711,8 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2);
nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry,
- resp->p, &buflen, getattr->ga_bmval,
+ &resp->p, buflen, getattr->ga_bmval,
resp->rqstp, 0);
- if (!nfserr)
- resp->p += buflen;
return nfserr;
}
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 2cbac34a55d..62c1ee128ae 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -9,22 +9,22 @@
*/
#include <linux/slab.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/highmem.h>
+#include <net/checksum.h>
#include "nfsd.h"
#include "cache.h"
-/* Size of reply cache. Common values are:
- * 4.3BSD: 128
- * 4.4BSD: 256
- * Solaris2: 1024
- * DEC Unix: 512-4096
- */
-#define CACHESIZE 1024
+#define NFSDDBG_FACILITY NFSDDBG_REPCACHE
+
#define HASHSIZE 64
static struct hlist_head * cache_hash;
static struct list_head lru_head;
-static int cache_disabled = 1;
+static struct kmem_cache *drc_slab;
+static unsigned int num_drc_entries;
+static unsigned int max_drc_entries;
/*
* Calculate the hash index from an XID.
@@ -37,6 +37,14 @@ static inline u32 request_hash(u32 xid)
}
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
+static void cache_cleaner_func(struct work_struct *unused);
+static int nfsd_reply_cache_shrink(struct shrinker *shrink,
+ struct shrink_control *sc);
+
+struct shrinker nfsd_reply_cache_shrinker = {
+ .shrink = nfsd_reply_cache_shrink,
+ .seeks = 1,
+};
/*
* locking for the reply cache:
@@ -44,30 +52,86 @@ static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
* Otherwise, it when accessing _prev or _next, the lock must be held.
*/
static DEFINE_SPINLOCK(cache_lock);
+static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
-int nfsd_reply_cache_init(void)
+/*
+ * Put a cap on the size of the DRC based on the amount of available
+ * low memory in the machine.
+ *
+ * 64MB: 8192
+ * 128MB: 11585
+ * 256MB: 16384
+ * 512MB: 23170
+ * 1GB: 32768
+ * 2GB: 46340
+ * 4GB: 65536
+ * 8GB: 92681
+ * 16GB: 131072
+ *
+ * ...with a hard cap of 256k entries. In the worst case, each entry will be
+ * ~1k, so the above numbers should give a rough max of the amount of memory
+ * used in k.
+ */
+static unsigned int
+nfsd_cache_size_limit(void)
+{
+ unsigned int limit;
+ unsigned long low_pages = totalram_pages - totalhigh_pages;
+
+ limit = (16 * int_sqrt(low_pages)) << (PAGE_SHIFT-10);
+ return min_t(unsigned int, limit, 256*1024);
+}
+
+static struct svc_cacherep *
+nfsd_reply_cache_alloc(void)
{
struct svc_cacherep *rp;
- int i;
- INIT_LIST_HEAD(&lru_head);
- i = CACHESIZE;
- while (i) {
- rp = kmalloc(sizeof(*rp), GFP_KERNEL);
- if (!rp)
- goto out_nomem;
- list_add(&rp->c_lru, &lru_head);
+ rp = kmem_cache_alloc(drc_slab, GFP_KERNEL);
+ if (rp) {
rp->c_state = RC_UNUSED;
rp->c_type = RC_NOCACHE;
+ INIT_LIST_HEAD(&rp->c_lru);
INIT_HLIST_NODE(&rp->c_hash);
- i--;
}
+ return rp;
+}
+
+static void
+nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
+{
+ if (rp->c_type == RC_REPLBUFF)
+ kfree(rp->c_replvec.iov_base);
+ hlist_del(&rp->c_hash);
+ list_del(&rp->c_lru);
+ --num_drc_entries;
+ kmem_cache_free(drc_slab, rp);
+}
+
+static void
+nfsd_reply_cache_free(struct svc_cacherep *rp)
+{
+ spin_lock(&cache_lock);
+ nfsd_reply_cache_free_locked(rp);
+ spin_unlock(&cache_lock);
+}
+
+int nfsd_reply_cache_init(void)
+{
+ register_shrinker(&nfsd_reply_cache_shrinker);
+ drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
+ 0, 0, NULL);
+ if (!drc_slab)
+ goto out_nomem;
- cache_hash = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
+ cache_hash = kcalloc(HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
if (!cache_hash)
goto out_nomem;
- cache_disabled = 0;
+ INIT_LIST_HEAD(&lru_head);
+ max_drc_entries = nfsd_cache_size_limit();
+ num_drc_entries = 0;
+
return 0;
out_nomem:
printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
@@ -79,27 +143,33 @@ void nfsd_reply_cache_shutdown(void)
{
struct svc_cacherep *rp;
+ unregister_shrinker(&nfsd_reply_cache_shrinker);
+ cancel_delayed_work_sync(&cache_cleaner);
+
while (!list_empty(&lru_head)) {
rp = list_entry(lru_head.next, struct svc_cacherep, c_lru);
- if (rp->c_state == RC_DONE && rp->c_type == RC_REPLBUFF)
- kfree(rp->c_replvec.iov_base);
- list_del(&rp->c_lru);
- kfree(rp);
+ nfsd_reply_cache_free_locked(rp);
}
- cache_disabled = 1;
-
kfree (cache_hash);
cache_hash = NULL;
+
+ if (drc_slab) {
+ kmem_cache_destroy(drc_slab);
+ drc_slab = NULL;
+ }
}
/*
- * Move cache entry to end of LRU list
+ * Move cache entry to end of LRU list, and queue the cleaner to run if it's
+ * not already scheduled.
*/
static void
lru_put_end(struct svc_cacherep *rp)
{
+ rp->c_timestamp = jiffies;
list_move_tail(&rp->c_lru, &lru_head);
+ schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
}
/*
@@ -112,83 +182,214 @@ hash_refile(struct svc_cacherep *rp)
hlist_add_head(&rp->c_hash, cache_hash + request_hash(rp->c_xid));
}
+static inline bool
+nfsd_cache_entry_expired(struct svc_cacherep *rp)
+{
+ return rp->c_state != RC_INPROG &&
+ time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
+}
+
+/*
+ * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
+ * Also prune the oldest ones when the total exceeds the max number of entries.
+ */
+static void
+prune_cache_entries(void)
+{
+ struct svc_cacherep *rp, *tmp;
+
+ list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
+ if (!nfsd_cache_entry_expired(rp) &&
+ num_drc_entries <= max_drc_entries)
+ break;
+ nfsd_reply_cache_free_locked(rp);
+ }
+
+ /*
+ * Conditionally rearm the job. If we cleaned out the list, then
+ * cancel any pending run (since there won't be any work to do).
+ * Otherwise, we rearm the job or modify the existing one to run in
+ * RC_EXPIRE since we just ran the pruner.
+ */
+ if (list_empty(&lru_head))
+ cancel_delayed_work(&cache_cleaner);
+ else
+ mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
+}
+
+static void
+cache_cleaner_func(struct work_struct *unused)
+{
+ spin_lock(&cache_lock);
+ prune_cache_entries();
+ spin_unlock(&cache_lock);
+}
+
+static int
+nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned int num;
+
+ spin_lock(&cache_lock);
+ if (sc->nr_to_scan)
+ prune_cache_entries();
+ num = num_drc_entries;
+ spin_unlock(&cache_lock);
+
+ return num;
+}
+
+/*
+ * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+ */
+static __wsum
+nfsd_cache_csum(struct svc_rqst *rqstp)
+{
+ int idx;
+ unsigned int base;
+ __wsum csum;
+ struct xdr_buf *buf = &rqstp->rq_arg;
+ const unsigned char *p = buf->head[0].iov_base;
+ size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
+ RC_CSUMLEN);
+ size_t len = min(buf->head[0].iov_len, csum_len);
+
+ /* rq_arg.head first */
+ csum = csum_partial(p, len, 0);
+ csum_len -= len;
+
+ /* Continue into page array */
+ idx = buf->page_base / PAGE_SIZE;
+ base = buf->page_base & ~PAGE_MASK;
+ while (csum_len) {
+ p = page_address(buf->pages[idx]) + base;
+ len = min_t(size_t, PAGE_SIZE - base, csum_len);
+ csum = csum_partial(p, len, csum);
+ csum_len -= len;
+ base = 0;
+ ++idx;
+ }
+ return csum;
+}
+
+/*
+ * Search the request hash for an entry that matches the given rqstp.
+ * Must be called with cache_lock held. Returns the found entry or
+ * NULL on failure.
+ */
+static struct svc_cacherep *
+nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
+{
+ struct svc_cacherep *rp;
+ struct hlist_head *rh;
+ __be32 xid = rqstp->rq_xid;
+ u32 proto = rqstp->rq_prot,
+ vers = rqstp->rq_vers,
+ proc = rqstp->rq_proc;
+
+ rh = &cache_hash[request_hash(xid)];
+ hlist_for_each_entry(rp, rh, c_hash) {
+ if (xid == rp->c_xid && proc == rp->c_proc &&
+ proto == rp->c_prot && vers == rp->c_vers &&
+ rqstp->rq_arg.len == rp->c_len && csum == rp->c_csum &&
+ rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) &&
+ rpc_get_port(svc_addr(rqstp)) == rpc_get_port((struct sockaddr *)&rp->c_addr))
+ return rp;
+ }
+ return NULL;
+}
+
/*
* Try to find an entry matching the current call in the cache. When none
- * is found, we grab the oldest unlocked entry off the LRU list.
- * Note that no operation within the loop may sleep.
+ * is found, we try to grab the oldest expired entry off the LRU list. If
+ * a suitable one isn't there, then drop the cache_lock and allocate a
+ * new one, then search again in case one got inserted while this thread
+ * didn't hold the lock.
*/
int
nfsd_cache_lookup(struct svc_rqst *rqstp)
{
- struct hlist_node *hn;
- struct hlist_head *rh;
- struct svc_cacherep *rp;
+ struct svc_cacherep *rp, *found;
__be32 xid = rqstp->rq_xid;
u32 proto = rqstp->rq_prot,
vers = rqstp->rq_vers,
proc = rqstp->rq_proc;
+ __wsum csum;
unsigned long age;
int type = rqstp->rq_cachetype;
int rtn;
rqstp->rq_cacherep = NULL;
- if (cache_disabled || type == RC_NOCACHE) {
+ if (type == RC_NOCACHE) {
nfsdstats.rcnocache++;
return RC_DOIT;
}
+ csum = nfsd_cache_csum(rqstp);
+
spin_lock(&cache_lock);
rtn = RC_DOIT;
- rh = &cache_hash[request_hash(xid)];
- hlist_for_each_entry(rp, hn, rh, c_hash) {
- if (rp->c_state != RC_UNUSED &&
- xid == rp->c_xid && proc == rp->c_proc &&
- proto == rp->c_prot && vers == rp->c_vers &&
- time_before(jiffies, rp->c_timestamp + 120*HZ) &&
- memcmp((char*)&rqstp->rq_addr, (char*)&rp->c_addr, sizeof(rp->c_addr))==0) {
- nfsdstats.rchits++;
- goto found_entry;
+ rp = nfsd_cache_search(rqstp, csum);
+ if (rp)
+ goto found_entry;
+
+ /* Try to use the first entry on the LRU */
+ if (!list_empty(&lru_head)) {
+ rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
+ if (nfsd_cache_entry_expired(rp) ||
+ num_drc_entries >= max_drc_entries) {
+ lru_put_end(rp);
+ prune_cache_entries();
+ goto setup_entry;
}
}
- nfsdstats.rcmisses++;
- /* This loop shouldn't take more than a few iterations normally */
- {
- int safe = 0;
- list_for_each_entry(rp, &lru_head, c_lru) {
- if (rp->c_state != RC_INPROG)
- break;
- if (safe++ > CACHESIZE) {
- printk("nfsd: loop in repcache LRU list\n");
- cache_disabled = 1;
- goto out;
- }
+ /* Drop the lock and allocate a new entry */
+ spin_unlock(&cache_lock);
+ rp = nfsd_reply_cache_alloc();
+ if (!rp) {
+ dprintk("nfsd: unable to allocate DRC entry!\n");
+ return RC_DOIT;
}
+ spin_lock(&cache_lock);
+ ++num_drc_entries;
+
+ /*
+ * Must search again just in case someone inserted one
+ * after we dropped the lock above.
+ */
+ found = nfsd_cache_search(rqstp, csum);
+ if (found) {
+ nfsd_reply_cache_free_locked(rp);
+ rp = found;
+ goto found_entry;
}
- /* All entries on the LRU are in-progress. This should not happen */
- if (&rp->c_lru == &lru_head) {
- static int complaints;
-
- printk(KERN_WARNING "nfsd: all repcache entries locked!\n");
- if (++complaints > 5) {
- printk(KERN_WARNING "nfsd: disabling repcache.\n");
- cache_disabled = 1;
- }
- goto out;
- }
+ /*
+ * We're keeping the one we just allocated. Are we now over the
+ * limit? Prune one off the tip of the LRU in trade for the one we
+ * just allocated if so.
+ */
+ if (num_drc_entries >= max_drc_entries)
+ nfsd_reply_cache_free_locked(list_first_entry(&lru_head,
+ struct svc_cacherep, c_lru));
+setup_entry:
+ nfsdstats.rcmisses++;
rqstp->rq_cacherep = rp;
rp->c_state = RC_INPROG;
rp->c_xid = xid;
rp->c_proc = proc;
- memcpy(&rp->c_addr, svc_addr_in(rqstp), sizeof(rp->c_addr));
+ rpc_copy_addr((struct sockaddr *)&rp->c_addr, svc_addr(rqstp));
+ rpc_set_port((struct sockaddr *)&rp->c_addr, rpc_get_port(svc_addr(rqstp)));
rp->c_prot = proto;
rp->c_vers = vers;
- rp->c_timestamp = jiffies;
+ rp->c_len = rqstp->rq_arg.len;
+ rp->c_csum = csum;
hash_refile(rp);
+ lru_put_end(rp);
/* release any buffer */
if (rp->c_type == RC_REPLBUFF) {
@@ -201,9 +402,9 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
return rtn;
found_entry:
+ nfsdstats.rchits++;
/* We found a matching entry which is either in progress or done. */
age = jiffies - rp->c_timestamp;
- rp->c_timestamp = jiffies;
lru_put_end(rp);
rtn = RC_DROPIT;
@@ -232,7 +433,7 @@ found_entry:
break;
default:
printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type);
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free_locked(rp);
}
goto out;
@@ -257,11 +458,11 @@ found_entry:
void
nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
{
- struct svc_cacherep *rp;
+ struct svc_cacherep *rp = rqstp->rq_cacherep;
struct kvec *resv = &rqstp->rq_res.head[0], *cachv;
int len;
- if (!(rp = rqstp->rq_cacherep) || cache_disabled)
+ if (!rp)
return;
len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
@@ -269,7 +470,7 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
/* Don't cache excessive amounts of data and XDR failures */
if (!statp || len > (256 >> 2)) {
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free(rp);
return;
}
@@ -283,21 +484,21 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
cachv = &rp->c_replvec;
cachv->iov_base = kmalloc(len << 2, GFP_KERNEL);
if (!cachv->iov_base) {
- spin_lock(&cache_lock);
- rp->c_state = RC_UNUSED;
- spin_unlock(&cache_lock);
+ nfsd_reply_cache_free(rp);
return;
}
cachv->iov_len = len << 2;
memcpy(cachv->iov_base, statp, len << 2);
break;
+ case RC_NOCACHE:
+ nfsd_reply_cache_free(rp);
+ return;
}
spin_lock(&cache_lock);
lru_put_end(rp);
rp->c_secure = rqstp->rq_secure;
rp->c_type = cachetype;
rp->c_state = RC_DONE;
- rp->c_timestamp = jiffies;
spin_unlock(&cache_lock);
return;
}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 2db7021b01a..13a21c8fca4 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -10,7 +10,7 @@
#include <linux/sunrpc/svcsock.h>
#include <linux/lockd/lockd.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/sunrpc/gss_krb5_enctypes.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
@@ -125,11 +125,11 @@ static const struct file_operations transaction_ops = {
.llseek = default_llseek,
};
-static int exports_open(struct inode *inode, struct file *file)
+static int exports_net_open(struct net *net, struct file *file)
{
int err;
struct seq_file *seq;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
err = seq_open(file, &nfs_exports_op);
if (err)
@@ -140,8 +140,26 @@ static int exports_open(struct inode *inode, struct file *file)
return 0;
}
-static const struct file_operations exports_operations = {
- .open = exports_open,
+static int exports_proc_open(struct inode *inode, struct file *file)
+{
+ return exports_net_open(current->nsproxy->net_ns, file);
+}
+
+static const struct file_operations exports_proc_operations = {
+ .open = exports_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+ .owner = THIS_MODULE,
+};
+
+static int exports_nfsd_open(struct inode *inode, struct file *file)
+{
+ return exports_net_open(inode->i_sb->s_fs_info, file);
+}
+
+static const struct file_operations exports_nfsd_operations = {
+ .open = exports_nfsd_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
@@ -220,6 +238,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
struct sockaddr *sap = (struct sockaddr *)&address;
size_t salen = sizeof(address);
char *fo_path;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
/* sanity check */
if (size == 0)
@@ -232,7 +251,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
if (qword_get(&buf, fo_path, size) < 0)
return -EINVAL;
- if (rpc_pton(&init_net, fo_path, size, sap, salen) == 0)
+ if (rpc_pton(net, fo_path, size, sap, salen) == 0)
return -EINVAL;
return nlmsvc_unlock_all_by_ip(sap);
@@ -317,6 +336,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
int len;
struct auth_domain *dom;
struct knfsd_fh fh;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
if (size == 0)
return -EINVAL;
@@ -352,7 +372,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
if (!dom)
return -ENOMEM;
- len = exp_rootfh(&init_net, dom, path, &fh, maxsize);
+ len = exp_rootfh(net, dom, path, &fh, maxsize);
auth_domain_put(dom);
if (len)
return len;
@@ -396,7 +416,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
int rv;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
if (size > 0) {
int newthreads;
@@ -447,7 +467,7 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
int len;
int npools;
int *nthreads;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
npools = nfsd_nrpools(net);
@@ -510,7 +530,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
unsigned minor;
ssize_t tlen = 0;
char *sep;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (size>0) {
@@ -534,7 +554,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
else
num = simple_strtol(vers, &minorp, 0);
if (*minorp == '.') {
- if (num < 4)
+ if (num != 4)
return -EINVAL;
minor = simple_strtoul(minorp+1, NULL, 0);
if (minor == 0)
@@ -792,7 +812,7 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size,
static ssize_t write_ports(struct file *file, char *buf, size_t size)
{
ssize_t rv;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
rv = __write_ports(file, buf, size, net);
@@ -827,7 +847,7 @@ int nfsd_max_blksize;
static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (size > 0) {
@@ -923,7 +943,8 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
*/
static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
{
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn);
}
@@ -939,7 +960,8 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
*/
static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
{
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}
@@ -995,7 +1017,8 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
{
ssize_t rv;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
rv = __write_recoverydir(file, buf, size, nn);
@@ -1013,7 +1036,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
{
static struct tree_descr nfsd_files[] = {
- [NFSD_List] = {"exports", &exports_operations, S_IRUGO},
+ [NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO},
[NFSD_Export_features] = {"export_features",
&export_features_operations, S_IRUGO},
[NFSD_FO_UnlockIP] = {"unlock_ip",
@@ -1037,20 +1060,35 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
#endif
/* last one */ {""}
};
- return simple_fill_super(sb, 0x6e667364, nfsd_files);
+ struct net *net = data;
+ int ret;
+
+ ret = simple_fill_super(sb, 0x6e667364, nfsd_files);
+ if (ret)
+ return ret;
+ sb->s_fs_info = get_net(net);
+ return 0;
}
static struct dentry *nfsd_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- return mount_single(fs_type, flags, data, nfsd_fill_super);
+ return mount_ns(fs_type, flags, current->nsproxy->net_ns, nfsd_fill_super);
+}
+
+static void nfsd_umount(struct super_block *sb)
+{
+ struct net *net = sb->s_fs_info;
+
+ kill_litter_super(sb);
+ put_net(net);
}
static struct file_system_type nfsd_fs_type = {
.owner = THIS_MODULE,
.name = "nfsd",
.mount = nfsd_mount,
- .kill_sb = kill_litter_super,
+ .kill_sb = nfsd_umount,
};
#ifdef CONFIG_PROC_FS
@@ -1061,7 +1099,8 @@ static int create_proc_exports_entry(void)
entry = proc_mkdir("fs/nfs", NULL);
if (!entry)
return -ENOMEM;
- entry = proc_create("exports", 0, entry, &exports_operations);
+ entry = proc_create("exports", 0, entry,
+ &exports_proc_operations);
if (!entry)
return -ENOMEM;
return 0;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index be7af509930..262df5ccbf5 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -652,7 +652,6 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
/* Check whether we have this call in the cache. */
switch (nfsd_cache_lookup(rqstp)) {
- case RC_INTR:
case RC_DROPIT:
return 0;
case RC_REPLY:
@@ -703,8 +702,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
{
int ret;
- struct net *net = &init_net;
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
mutex_lock(&nfsd_mutex);
if (nn->nfsd_serv == NULL) {
@@ -721,7 +719,7 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file)
int nfsd_pool_stats_release(struct inode *inode, struct file *file)
{
int ret = seq_release(inode, file);
- struct net *net = &init_net;
+ struct net *net = inode->i_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
/* this function really, really should have been called svc_put() */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 0889bfb43dc..546f8983ecf 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -563,7 +563,7 @@ __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op);
__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 *buffer, int *countp,
+ struct dentry *dentry, __be32 **buffer, int countp,
u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *,
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 6baadb5a843..4bb21d67d9b 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -52,7 +52,6 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
void __fsnotify_update_child_dentry_flags(struct inode *inode)
{
struct dentry *alias;
- struct hlist_node *p;
int watched;
if (!S_ISDIR(inode->i_mode))
@@ -64,7 +63,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
spin_lock(&inode->i_lock);
/* run all of the dentries associated with this inode. Since this is a
* directory, there damn well better only be one item on this list */
- hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
struct dentry *child;
/* run all of the children of the original inode and fix their
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index f31e90fc050..74825be65b7 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -36,12 +36,11 @@
static void fsnotify_recalc_inode_mask_locked(struct inode *inode)
{
struct fsnotify_mark *mark;
- struct hlist_node *pos;
__u32 new_mask = 0;
assert_spin_locked(&inode->i_lock);
- hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list)
+ hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list)
new_mask |= mark->mask;
inode->i_fsnotify_mask = new_mask;
}
@@ -87,11 +86,11 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
void fsnotify_clear_marks_by_inode(struct inode *inode)
{
struct fsnotify_mark *mark, *lmark;
- struct hlist_node *pos, *n;
+ struct hlist_node *n;
LIST_HEAD(free_list);
spin_lock(&inode->i_lock);
- hlist_for_each_entry_safe(mark, pos, n, &inode->i_fsnotify_marks, i.i_list) {
+ hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, i.i_list) {
list_add(&mark->i.free_i_list, &free_list);
hlist_del_init_rcu(&mark->i.i_list);
fsnotify_get_mark(mark);
@@ -129,11 +128,10 @@ static struct fsnotify_mark *fsnotify_find_inode_mark_locked(
struct inode *inode)
{
struct fsnotify_mark *mark;
- struct hlist_node *pos;
assert_spin_locked(&inode->i_lock);
- hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list) {
+ hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) {
if (mark->group == group) {
fsnotify_get_mark(mark);
return mark;
@@ -194,8 +192,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group, struct inode *inode,
int allow_dups)
{
- struct fsnotify_mark *lmark;
- struct hlist_node *node, *last = NULL;
+ struct fsnotify_mark *lmark, *last = NULL;
int ret = 0;
mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
@@ -214,8 +211,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
}
/* should mark be in the middle of the current list? */
- hlist_for_each_entry(lmark, node, &inode->i_fsnotify_marks, i.i_list) {
- last = node;
+ hlist_for_each_entry(lmark, &inode->i_fsnotify_marks, i.i_list) {
+ last = lmark;
if ((lmark->group == group) && !allow_dups) {
ret = -EEXIST;
@@ -235,7 +232,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
BUG_ON(last == NULL);
/* mark should be the last entry. last is the current last entry */
- hlist_add_after_rcu(last, &mark->i.i_list);
+ hlist_add_after_rcu(&last->i.i_list, &mark->i.i_list);
out:
fsnotify_recalc_inode_mask_locked(inode);
spin_unlock(&inode->i_lock);
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 871569c7d60..4216308b81b 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -197,7 +197,6 @@ static void inotify_free_group_priv(struct fsnotify_group *group)
{
/* ideally the idr is empty and we won't hit the BUG in the callback */
idr_for_each(&group->inotify_data.idr, idr_callback, group);
- idr_remove_all(&group->inotify_data.idr);
idr_destroy(&group->inotify_data.idr);
atomic_dec(&group->inotify_data.user->inotify_devs);
free_uid(group->inotify_data.user);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 07f7a92fe88..e0f7c1241a6 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -364,22 +364,20 @@ static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
{
int ret;
- do {
- if (unlikely(!idr_pre_get(idr, GFP_KERNEL)))
- return -ENOMEM;
+ idr_preload(GFP_KERNEL);
+ spin_lock(idr_lock);
- spin_lock(idr_lock);
- ret = idr_get_new_above(idr, i_mark, *last_wd + 1,
- &i_mark->wd);
+ ret = idr_alloc(idr, i_mark, *last_wd + 1, 0, GFP_NOWAIT);
+ if (ret >= 0) {
/* we added the mark to the idr, take a reference */
- if (!ret) {
- *last_wd = i_mark->wd;
- fsnotify_get_mark(&i_mark->fsn_mark);
- }
- spin_unlock(idr_lock);
- } while (ret == -EAGAIN);
+ i_mark->wd = ret;
+ *last_wd = i_mark->wd;
+ fsnotify_get_mark(&i_mark->fsn_mark);
+ }
- return ret;
+ spin_unlock(idr_lock);
+ idr_preload_end();
+ return ret < 0 ? ret : 0;
}
static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group *group,
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index 4df58b8ea64..68ca5a8704b 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -33,12 +33,12 @@
void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
{
struct fsnotify_mark *mark, *lmark;
- struct hlist_node *pos, *n;
+ struct hlist_node *n;
struct mount *m = real_mount(mnt);
LIST_HEAD(free_list);
spin_lock(&mnt->mnt_root->d_lock);
- hlist_for_each_entry_safe(mark, pos, n, &m->mnt_fsnotify_marks, m.m_list) {
+ hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, m.m_list) {
list_add(&mark->m.free_m_list, &free_list);
hlist_del_init_rcu(&mark->m.m_list);
fsnotify_get_mark(mark);
@@ -71,12 +71,11 @@ static void fsnotify_recalc_vfsmount_mask_locked(struct vfsmount *mnt)
{
struct mount *m = real_mount(mnt);
struct fsnotify_mark *mark;
- struct hlist_node *pos;
__u32 new_mask = 0;
assert_spin_locked(&mnt->mnt_root->d_lock);
- hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list)
+ hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list)
new_mask |= mark->mask;
m->mnt_fsnotify_mask = new_mask;
}
@@ -114,11 +113,10 @@ static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_
{
struct mount *m = real_mount(mnt);
struct fsnotify_mark *mark;
- struct hlist_node *pos;
assert_spin_locked(&mnt->mnt_root->d_lock);
- hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list) {
+ hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) {
if (mark->group == group) {
fsnotify_get_mark(mark);
return mark;
@@ -153,8 +151,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
int allow_dups)
{
struct mount *m = real_mount(mnt);
- struct fsnotify_mark *lmark;
- struct hlist_node *node, *last = NULL;
+ struct fsnotify_mark *lmark, *last = NULL;
int ret = 0;
mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
@@ -173,8 +170,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
}
/* should mark be in the middle of the current list? */
- hlist_for_each_entry(lmark, node, &m->mnt_fsnotify_marks, m.m_list) {
- last = node;
+ hlist_for_each_entry(lmark, &m->mnt_fsnotify_marks, m.m_list) {
+ last = lmark;
if ((lmark->group == group) && !allow_dups) {
ret = -EEXIST;
@@ -194,7 +191,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
BUG_ON(last == NULL);
/* mark should be the last entry. last is the current last entry */
- hlist_add_after_rcu(last, &mark->m.m_list);
+ hlist_add_after_rcu(&last->m.m_list, &mark->m.m_list);
out:
fsnotify_recalc_vfsmount_mask_locked(mnt);
spin_unlock(&mnt->mnt_root->d_lock);
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 0d2bf566e39..aa88bd8bced 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -304,28 +304,22 @@ static u8 o2net_num_from_nn(struct o2net_node *nn)
static int o2net_prep_nsw(struct o2net_node *nn, struct o2net_status_wait *nsw)
{
- int ret = 0;
-
- do {
- if (!idr_pre_get(&nn->nn_status_idr, GFP_ATOMIC)) {
- ret = -EAGAIN;
- break;
- }
- spin_lock(&nn->nn_lock);
- ret = idr_get_new(&nn->nn_status_idr, nsw, &nsw->ns_id);
- if (ret == 0)
- list_add_tail(&nsw->ns_node_item,
- &nn->nn_status_list);
- spin_unlock(&nn->nn_lock);
- } while (ret == -EAGAIN);
+ int ret;
- if (ret == 0) {
- init_waitqueue_head(&nsw->ns_wq);
- nsw->ns_sys_status = O2NET_ERR_NONE;
- nsw->ns_status = 0;
+ spin_lock(&nn->nn_lock);
+ ret = idr_alloc(&nn->nn_status_idr, nsw, 0, 0, GFP_ATOMIC);
+ if (ret >= 0) {
+ nsw->ns_id = ret;
+ list_add_tail(&nsw->ns_node_item, &nn->nn_status_list);
}
+ spin_unlock(&nn->nn_lock);
+ if (ret < 0)
+ return ret;
- return ret;
+ init_waitqueue_head(&nsw->ns_wq);
+ nsw->ns_sys_status = O2NET_ERR_NONE;
+ nsw->ns_status = 0;
+ return 0;
}
static void o2net_complete_nsw_locked(struct o2net_node *nn,
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 8db4b58b2e4..ef999729e27 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -169,11 +169,10 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode,
u64 parent_blkno,
int skip_unhashed)
{
- struct hlist_node *p;
struct dentry *dentry;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
trace_ocfs2_find_local_alias(dentry->d_name.len,
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 01ebfd0bdad..eeac97bb3bf 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2083,7 +2083,6 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
u8 dead_node, u8 new_master)
{
int i;
- struct hlist_node *hash_iter;
struct hlist_head *bucket;
struct dlm_lock_resource *res, *next;
@@ -2114,7 +2113,7 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
* if necessary */
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_lockres_hash(dlm, i);
- hlist_for_each_entry(res, hash_iter, bucket, hash_node) {
+ hlist_for_each_entry(res, bucket, hash_node) {
if (!(res->state & DLM_LOCK_RES_RECOVERING))
continue;
@@ -2273,7 +2272,6 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
{
- struct hlist_node *iter;
struct dlm_lock_resource *res;
int i;
struct hlist_head *bucket;
@@ -2299,7 +2297,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
*/
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_lockres_hash(dlm, i);
- hlist_for_each_entry(res, iter, bucket, hash_node) {
+ hlist_for_each_entry(res, bucket, hash_node) {
/* always prune any $RECOVERY entries for dead nodes,
* otherwise hangs can occur during later recovery */
if (dlm_is_recovery_lock(res->lockname.name,
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f169da4624f..b7e74b580c0 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -642,7 +642,7 @@ ocfs2_block_group_alloc_discontig(handle_t *handle,
* cluster groups will be staying in cache for the duration of
* this operation.
*/
- ac->ac_allow_chain_relink = 0;
+ ac->ac_disable_chain_relink = 1;
/* Claim the first region */
status = ocfs2_block_group_claim_bits(osb, handle, ac, min_bits,
@@ -1823,7 +1823,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
* Do this *after* figuring out how many bits we're taking out
* of our target group.
*/
- if (ac->ac_allow_chain_relink &&
+ if (!ac->ac_disable_chain_relink &&
(prev_group_bh) &&
(ocfs2_block_group_reasonably_empty(bg, res->sr_bits))) {
status = ocfs2_relink_block_group(handle, alloc_inode,
@@ -1928,7 +1928,6 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
victim = ocfs2_find_victim_chain(cl);
ac->ac_chain = victim;
- ac->ac_allow_chain_relink = 1;
status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
res, &bits_left);
@@ -1947,7 +1946,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
* searching each chain in order. Don't allow chain relinking
* because we only calculate enough journal credits for one
* relink per alloc. */
- ac->ac_allow_chain_relink = 0;
+ ac->ac_disable_chain_relink = 1;
for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) {
if (i == victim)
continue;
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b8afabfeede..a36d0aa5091 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -49,7 +49,7 @@ struct ocfs2_alloc_context {
/* these are used by the chain search */
u16 ac_chain;
- int ac_allow_chain_relink;
+ int ac_disable_chain_relink;
group_search_t *ac_group_search;
u64 ac_last_group;
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 0ba9ea1e796..2e3ea308c14 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -7189,7 +7189,7 @@ int ocfs2_init_security_and_acl(struct inode *dir,
struct buffer_head *dir_bh = NULL;
ret = ocfs2_init_security_get(inode, dir, qstr, NULL);
- if (!ret) {
+ if (ret) {
mlog_errno(ret);
goto leave;
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index f3b133d7991..69078c7cef1 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -73,6 +73,7 @@
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
+#include <linux/printk.h>
#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
@@ -952,7 +953,7 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
* /proc/pid/oom_adj is provided for legacy purposes, ask users to use
* /proc/pid/oom_score_adj instead.
*/
- printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+ pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
current->comm, task_pid_nr(current), task_pid_nr(task),
task_pid_nr(task));
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 2983dc52ca2..4b3b3ffb52f 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -15,6 +15,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/printk.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/idr.h>
@@ -132,11 +133,8 @@ __proc_file_read(struct file *file, char __user *buf, size_t nbytes,
}
if (start == NULL) {
- if (n > PAGE_SIZE) {
- printk(KERN_ERR
- "proc_file_read: Apparent buffer overflow!\n");
+ if (n > PAGE_SIZE) /* Apparent buffer overflow */
n = PAGE_SIZE;
- }
n -= *ppos;
if (n <= 0)
break;
@@ -144,26 +142,19 @@ __proc_file_read(struct file *file, char __user *buf, size_t nbytes,
n = count;
start = page + *ppos;
} else if (start < page) {
- if (n > PAGE_SIZE) {
- printk(KERN_ERR
- "proc_file_read: Apparent buffer overflow!\n");
+ if (n > PAGE_SIZE) /* Apparent buffer overflow */
n = PAGE_SIZE;
- }
if (n > count) {
/*
* Don't reduce n because doing so might
* cut off part of a data block.
*/
- printk(KERN_WARNING
- "proc_file_read: Read count exceeded\n");
+ pr_warn("proc_file_read: count exceeded\n");
}
} else /* start >= page */ {
unsigned long startoff = (unsigned long)(start - page);
- if (n > (PAGE_SIZE - startoff)) {
- printk(KERN_ERR
- "proc_file_read: Apparent buffer overflow!\n");
+ if (n > (PAGE_SIZE - startoff)) /* buffer overflow? */
n = PAGE_SIZE - startoff;
- }
if (n > count)
n = count;
}
@@ -569,7 +560,7 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
for (tmp = dir->subdir; tmp; tmp = tmp->next)
if (strcmp(tmp->name, dp->name) == 0) {
- WARN(1, KERN_WARNING "proc_dir_entry '%s/%s' already registered\n",
+ WARN(1, "proc_dir_entry '%s/%s' already registered\n",
dir->name, dp->name);
break;
}
@@ -830,9 +821,9 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
if (S_ISDIR(de->mode))
parent->nlink--;
de->nlink = 0;
- WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
- "'%s/%s', leaking at least '%s'\n", __func__,
- de->parent->name, de->name, de->subdir->name);
+ WARN(de->subdir, "%s: removing non-empty directory "
+ "'%s/%s', leaking at least '%s'\n", __func__,
+ de->parent->name, de->name, de->subdir->name);
pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 70322e1a4f0..a86aebc9ba7 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -13,6 +13,7 @@
#include <linux/stat.h>
#include <linux/completion.h>
#include <linux/poll.h>
+#include <linux/printk.h>
#include <linux/file.h>
#include <linux/limits.h>
#include <linux/init.h>
@@ -495,13 +496,13 @@ int proc_fill_super(struct super_block *s)
pde_get(&proc_root);
root_inode = proc_get_inode(s, &proc_root);
if (!root_inode) {
- printk(KERN_ERR "proc_fill_super: get root inode failed\n");
+ pr_err("proc_fill_super: get root inode failed\n");
return -ENOMEM;
}
s->s_root = d_make_root(root_inode);
if (!s->s_root) {
- printk(KERN_ERR "proc_fill_super: allocate dentry failed\n");
+ pr_err("proc_fill_super: allocate dentry failed\n");
return -ENOMEM;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 252544c0520..85ff3a4598b 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -11,6 +11,7 @@
#include <linux/sched.h>
#include <linux/proc_fs.h>
+#include <linux/binfmts.h>
struct ctl_table_header;
struct mempolicy;
@@ -108,7 +109,7 @@ static inline int task_dumpable(struct task_struct *task)
if (mm)
dumpable = get_dumpable(mm);
task_unlock(task);
- if (dumpable == SUID_DUMPABLE_ENABLED)
+ if (dumpable == SUID_DUMP_USER)
return 1;
return 0;
}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e96d4f18ca3..eda6f017f27 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -17,6 +17,7 @@
#include <linux/elfcore.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
+#include <linux/printk.h>
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/slab.h>
@@ -619,7 +620,7 @@ static int __init proc_kcore_init(void)
proc_root_kcore = proc_create("kcore", S_IRUSR, NULL,
&proc_kcore_operations);
if (!proc_root_kcore) {
- printk(KERN_ERR "couldn't create /proc/kcore\n");
+ pr_err("couldn't create /proc/kcore\n");
return 0; /* Always returns 0. */
}
/* Store text area if it's special */
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index de20ec480fa..30b590f5bd3 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -8,6 +8,7 @@
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/printk.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/of.h>
@@ -110,8 +111,8 @@ void proc_device_tree_update_prop(struct proc_dir_entry *pde,
if (ent->data == oldprop)
break;
if (ent == NULL) {
- printk(KERN_WARNING "device-tree: property \"%s\" "
- " does not exist\n", oldprop->name);
+ pr_warn("device-tree: property \"%s\" does not exist\n",
+ oldprop->name);
} else {
ent->data = newprop;
ent->size = newprop->length;
@@ -153,8 +154,8 @@ static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de,
realloc:
fixed_name = kmalloc(fixup_len, GFP_KERNEL);
if (fixed_name == NULL) {
- printk(KERN_ERR "device-tree: Out of memory trying to fixup "
- "name \"%s\"\n", name);
+ pr_err("device-tree: Out of memory trying to fixup "
+ "name \"%s\"\n", name);
return name;
}
@@ -175,8 +176,8 @@ retry:
goto retry;
}
- printk(KERN_WARNING "device-tree: Duplicate name in %s, "
- "renamed to \"%s\"\n", np->full_name, fixed_name);
+ pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
+ np->full_name, fixed_name);
return fixed_name;
}
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 612df79cc6a..ac05f33a0dd 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -5,6 +5,7 @@
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/proc_fs.h>
+#include <linux/printk.h>
#include <linux/security.h>
#include <linux/sched.h>
#include <linux/namei.h>
@@ -57,7 +58,7 @@ static void sysctl_print_dir(struct ctl_dir *dir)
{
if (dir->header.parent)
sysctl_print_dir(dir->header.parent);
- printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname);
+ pr_cont("%s/", dir->header.ctl_table[0].procname);
}
static int namecmp(const char *name1, int len1, const char *name2, int len2)
@@ -134,9 +135,9 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
else if (cmp > 0)
p = &(*p)->rb_right;
else {
- printk(KERN_ERR "sysctl duplicate entry: ");
+ pr_err("sysctl duplicate entry: ");
sysctl_print_dir(head->parent);
- printk(KERN_CONT "/%s\n", entry->procname);
+ pr_cont("/%s\n", entry->procname);
return -EEXIST;
}
}
@@ -927,9 +928,9 @@ found:
subdir->header.nreg++;
failed:
if (unlikely(IS_ERR(subdir))) {
- printk(KERN_ERR "sysctl could not get directory: ");
+ pr_err("sysctl could not get directory: ");
sysctl_print_dir(dir);
- printk(KERN_CONT "/%*.*s %ld\n",
+ pr_cont("/%*.*s %ld\n",
namelen, namelen, name, PTR_ERR(subdir));
}
drop_sysctl_table(&dir->header);
@@ -995,8 +996,8 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n",
- path, table->procname, &vaf);
+ pr_err("sysctl table check failed: %s/%s %pV\n",
+ path, table->procname, &vaf);
va_end(args);
return -EINVAL;
@@ -1510,9 +1511,9 @@ static void put_links(struct ctl_table_header *header)
drop_sysctl_table(link_head);
}
else {
- printk(KERN_ERR "sysctl link missing during unregister: ");
+ pr_err("sysctl link missing during unregister: ");
sysctl_print_dir(parent);
- printk(KERN_CONT "/%s\n", name);
+ pr_cont("/%s\n", name);
}
}
}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 0d5071d2998..b870f740ab5 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -15,6 +15,7 @@
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/highmem.h>
+#include <linux/printk.h>
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/crash_dump.h>
@@ -175,15 +176,15 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
start = map_offset_to_paddr(*fpos, &vmcore_list, &curr_m);
if (!curr_m)
return -EINVAL;
- if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
- tsz = buflen;
-
- /* Calculate left bytes in current memory segment. */
- nr_bytes = (curr_m->size - (start - curr_m->paddr));
- if (tsz > nr_bytes)
- tsz = nr_bytes;
while (buflen) {
+ tsz = min_t(size_t, buflen, PAGE_SIZE - (start & ~PAGE_MASK));
+
+ /* Calculate left bytes in current memory segment. */
+ nr_bytes = (curr_m->size - (start - curr_m->paddr));
+ if (tsz > nr_bytes)
+ tsz = nr_bytes;
+
tmp = read_from_oldmem(buffer, tsz, &start, 1);
if (tmp < 0)
return tmp;
@@ -198,12 +199,6 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
struct vmcore, list);
start = curr_m->paddr;
}
- if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
- tsz = buflen;
- /* Calculate left bytes in current memory segment. */
- nr_bytes = (curr_m->size - (start - curr_m->paddr));
- if (tsz > nr_bytes)
- tsz = nr_bytes;
}
return acc;
}
@@ -553,8 +548,7 @@ static int __init parse_crash_elf64_headers(void)
ehdr.e_ehsize != sizeof(Elf64_Ehdr) ||
ehdr.e_phentsize != sizeof(Elf64_Phdr) ||
ehdr.e_phnum == 0) {
- printk(KERN_WARNING "Warning: Core image elf header is not"
- "sane\n");
+ pr_warn("Warning: Core image elf header is not sane\n");
return -EINVAL;
}
@@ -609,8 +603,7 @@ static int __init parse_crash_elf32_headers(void)
ehdr.e_ehsize != sizeof(Elf32_Ehdr) ||
ehdr.e_phentsize != sizeof(Elf32_Phdr) ||
ehdr.e_phnum == 0) {
- printk(KERN_WARNING "Warning: Core image elf header is not"
- "sane\n");
+ pr_warn("Warning: Core image elf header is not sane\n");
return -EINVAL;
}
@@ -653,8 +646,7 @@ static int __init parse_crash_elf_headers(void)
if (rc < 0)
return rc;
if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
- printk(KERN_WARNING "Warning: Core image elf header"
- " not found\n");
+ pr_warn("Warning: Core image elf header not found\n");
return -EINVAL;
}
@@ -673,8 +665,7 @@ static int __init parse_crash_elf_headers(void)
/* Determine vmcore size. */
vmcore_size = get_vmcore_size_elf32(elfcorebuf);
} else {
- printk(KERN_WARNING "Warning: Core image elf header is not"
- " sane\n");
+ pr_warn("Warning: Core image elf header is not sane\n");
return -EINVAL;
}
return 0;
@@ -690,7 +681,7 @@ static int __init vmcore_init(void)
return rc;
rc = parse_crash_elf_headers();
if (rc) {
- printk(KERN_WARNING "Kdump: vmcore not initialized\n");
+ pr_warn("Kdump: vmcore not initialized\n");
return rc;
}
diff --git a/fs/seq_file.c b/fs/seq_file.c
index f2bc3dfd0b8..15c6304bab7 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -308,27 +308,27 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence)
mutex_lock(&m->lock);
m->version = file->f_version;
switch (whence) {
- case 1:
- offset += file->f_pos;
- case 0:
- if (offset < 0)
- break;
- retval = offset;
- if (offset != m->read_pos) {
- while ((retval=traverse(m, offset)) == -EAGAIN)
- ;
- if (retval) {
- /* with extreme prejudice... */
- file->f_pos = 0;
- m->read_pos = 0;
- m->version = 0;
- m->index = 0;
- m->count = 0;
- } else {
- m->read_pos = offset;
- retval = file->f_pos = offset;
- }
+ case SEEK_CUR:
+ offset += file->f_pos;
+ case SEEK_SET:
+ if (offset < 0)
+ break;
+ retval = offset;
+ if (offset != m->read_pos) {
+ while ((retval = traverse(m, offset)) == -EAGAIN)
+ ;
+ if (retval) {
+ /* with extreme prejudice... */
+ file->f_pos = 0;
+ m->read_pos = 0;
+ m->version = 0;
+ m->index = 0;
+ m->count = 0;
+ } else {
+ m->read_pos = offset;
+ retval = file->f_pos = offset;
}
+ }
}
file->f_version = m->version;
mutex_unlock(&m->lock);
diff --git a/fs/super.c b/fs/super.c
index 12f12371216..7465d436420 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -447,14 +447,13 @@ struct super_block *sget(struct file_system_type *type,
void *data)
{
struct super_block *s = NULL;
- struct hlist_node *node;
struct super_block *old;
int err;
retry:
spin_lock(&sb_lock);
if (test) {
- hlist_for_each_entry(old, node, &type->fs_supers, s_instances) {
+ hlist_for_each_entry(old, &type->fs_supers, s_instances) {
if (!test(old, data))
continue;
if (!grab_super(old))
@@ -554,10 +553,9 @@ void iterate_supers_type(struct file_system_type *type,
void (*f)(struct super_block *, void *), void *arg)
{
struct super_block *sb, *p = NULL;
- struct hlist_node *node;
spin_lock(&sb_lock);
- hlist_for_each_entry(sb, node, &type->fs_supers, s_instances) {
+ hlist_for_each_entry(sb, &type->fs_supers, s_instances) {
sb->s_count++;
spin_unlock(&sb_lock);
@@ -842,7 +840,7 @@ int get_anon_bdev(dev_t *p)
else if (error)
return -EAGAIN;
- if ((dev & MAX_IDR_MASK) == (1 << MINORBITS)) {
+ if (dev == (1 << MINORBITS)) {
spin_lock(&unnamed_dev_lock);
ida_remove(&unnamed_dev_ida, dev);
if (unnamed_dev_start > dev)
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
index 2ce9a5db6ab..15c68f9489a 100644
--- a/fs/sysfs/bin.c
+++ b/fs/sysfs/bin.c
@@ -461,14 +461,13 @@ const struct file_operations bin_fops = {
void unmap_bin_file(struct sysfs_dirent *attr_sd)
{
struct bin_buffer *bb;
- struct hlist_node *tmp;
if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR)
return;
mutex_lock(&sysfs_bin_lock);
- hlist_for_each_entry(bb, tmp, &attr_sd->s_bin_attr.buffers, list) {
+ hlist_for_each_entry(bb, &attr_sd->s_bin_attr.buffers, list) {
struct inode *inode = file_inode(bb->file);
unmap_mapping_range(inode->i_mapping, 0, 0, 1);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 96fcbb85ff8..d1dba7ce75a 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1442,9 +1442,8 @@ xlog_recover_find_tid(
xlog_tid_t tid)
{
xlog_recover_t *trans;
- struct hlist_node *n;
- hlist_for_each_entry(trans, n, head, r_list) {
+ hlist_for_each_entry(trans, head, r_list) {
if (trans->r_log_tid == tid)
return trans;
}