summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig1
-rw-r--r--fs/affs/namei.c15
-rw-r--r--fs/afs/addr_list.c25
-rw-r--r--fs/afs/callback.c84
-rw-r--r--fs/afs/cmservice.c67
-rw-r--r--fs/afs/dir.c54
-rw-r--r--fs/afs/file.c2
-rw-r--r--fs/afs/flock.c6
-rw-r--r--fs/afs/fsclient.c31
-rw-r--r--fs/afs/inode.c19
-rw-r--r--fs/afs/internal.h25
-rw-r--r--fs/afs/rotate.c20
-rw-r--r--fs/afs/rxrpc.c18
-rw-r--r--fs/afs/security.c7
-rw-r--r--fs/afs/server.c21
-rw-r--r--fs/afs/server_list.c7
-rw-r--r--fs/afs/super.c4
-rw-r--r--fs/afs/write.c2
-rw-r--r--fs/aio.c4
-rw-r--r--fs/befs/linuxvfs.c17
-rw-r--r--fs/btrfs/ctree.c22
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/disk-io.c26
-rw-r--r--fs/btrfs/inode.c32
-rw-r--r--fs/btrfs/props.c12
-rw-r--r--fs/btrfs/tree-log.c144
-rw-r--r--fs/btrfs/volumes.c9
-rw-r--r--fs/cachefiles/namei.c10
-rw-r--r--fs/cifs/Kconfig2
-rw-r--r--fs/cramfs/inode.c2
-rw-r--r--fs/dax.c115
-rw-r--r--fs/dcache.c22
-rw-r--r--fs/ecryptfs/inode.c3
-rw-r--r--fs/ext2/inode.c10
-rw-r--r--fs/ext2/namei.c6
-rw-r--r--fs/ext4/namei.c6
-rw-r--r--fs/f2fs/namei.c12
-rw-r--r--fs/hfsplus/super.c1
-rw-r--r--fs/jffs2/dir.c12
-rw-r--r--fs/jfs/namei.c12
-rw-r--r--fs/kernfs/mount.c1
-rw-r--r--fs/nfsd/vfs.c22
-rw-r--r--fs/nilfs2/namei.c6
-rw-r--r--fs/ocfs2/cluster/heartbeat.c11
-rw-r--r--fs/orangefs/namei.c9
-rw-r--r--fs/proc/array.c25
-rw-r--r--fs/proc/base.c8
-rw-r--r--fs/reiserfs/namei.c12
-rw-r--r--fs/seq_file.c5
-rw-r--r--fs/super.c30
-rw-r--r--fs/sysfs/mount.c6
-rw-r--r--fs/udf/namei.c6
-rw-r--r--fs/ufs/namei.c6
-rw-r--r--fs/xfs/xfs_file.c72
-rw-r--r--fs/xfs/xfs_inode.h16
-rw-r--r--fs/xfs/xfs_ioctl.c8
-rw-r--r--fs/xfs/xfs_iops.c16
-rw-r--r--fs/xfs/xfs_pnfs.c15
-rw-r--r--fs/xfs/xfs_pnfs.h5
59 files changed, 776 insertions, 392 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index bc821a86d965..1e050e012eb9 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -38,6 +38,7 @@ config FS_DAX
bool "Direct Access (DAX) support"
depends on MMU
depends on !(ARM || MIPS || SPARC)
+ select DEV_PAGEMAP_OPS if (ZONE_DEVICE && !FS_DAX_LIMITED)
select FS_IOMAP
select DAX
help
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index d8aa0ae3d037..41c5749f4db7 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -201,14 +201,16 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
struct super_block *sb = dir->i_sb;
struct buffer_head *bh;
struct inode *inode = NULL;
+ struct dentry *res;
pr_debug("%s(\"%pd\")\n", __func__, dentry);
affs_lock_dir(dir);
bh = affs_find_entry(dir, dentry);
- affs_unlock_dir(dir);
- if (IS_ERR(bh))
+ if (IS_ERR(bh)) {
+ affs_unlock_dir(dir);
return ERR_CAST(bh);
+ }
if (bh) {
u32 ino = bh->b_blocknr;
@@ -222,11 +224,12 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
}
affs_brelse(bh);
inode = affs_iget(sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
}
- d_add(dentry, inode);
- return NULL;
+ res = d_splice_alias(inode, dentry);
+ if (!IS_ERR_OR_NULL(res))
+ res->d_fsdata = dentry->d_fsdata;
+ affs_unlock_dir(dir);
+ return res;
}
int
diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index 3bedfed608a2..7587fb665ff1 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -121,7 +121,7 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
p = text;
do {
struct sockaddr_rxrpc *srx = &alist->addrs[alist->nr_addrs];
- char tdelim = delim;
+ const char *q, *stop;
if (*p == delim) {
p++;
@@ -130,28 +130,33 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
if (*p == '[') {
p++;
- tdelim = ']';
+ q = memchr(p, ']', end - p);
+ } else {
+ for (q = p; q < end; q++)
+ if (*q == '+' || *q == delim)
+ break;
}
- if (in4_pton(p, end - p,
+ if (in4_pton(p, q - p,
(u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3],
- tdelim, &p)) {
+ -1, &stop)) {
srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- } else if (in6_pton(p, end - p,
+ } else if (in6_pton(p, q - p,
srx->transport.sin6.sin6_addr.s6_addr,
- tdelim, &p)) {
+ -1, &stop)) {
/* Nothing to do */
} else {
goto bad_address;
}
- if (tdelim == ']') {
- if (p == end || *p != ']')
- goto bad_address;
+ if (stop != q)
+ goto bad_address;
+
+ p = q;
+ if (q < end && *q == ']')
p++;
- }
if (p < end) {
if (*p == '+') {
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index abd9a84f4e88..571437dcb252 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -23,36 +23,55 @@
/*
* Set up an interest-in-callbacks record for a volume on a server and
* register it with the server.
- * - Called with volume->server_sem held.
+ * - Called with vnode->io_lock held.
*/
int afs_register_server_cb_interest(struct afs_vnode *vnode,
- struct afs_server_entry *entry)
+ struct afs_server_list *slist,
+ unsigned int index)
{
- struct afs_cb_interest *cbi = entry->cb_interest, *vcbi, *new, *x;
+ struct afs_server_entry *entry = &slist->servers[index];
+ struct afs_cb_interest *cbi, *vcbi, *new, *old;
struct afs_server *server = entry->server;
again:
+ if (vnode->cb_interest &&
+ likely(vnode->cb_interest == entry->cb_interest))
+ return 0;
+
+ read_lock(&slist->lock);
+ cbi = afs_get_cb_interest(entry->cb_interest);
+ read_unlock(&slist->lock);
+
vcbi = vnode->cb_interest;
if (vcbi) {
- if (vcbi == cbi)
+ if (vcbi == cbi) {
+ afs_put_cb_interest(afs_v2net(vnode), cbi);
return 0;
+ }
+ /* Use a new interest in the server list for the same server
+ * rather than an old one that's still attached to a vnode.
+ */
if (cbi && vcbi->server == cbi->server) {
write_seqlock(&vnode->cb_lock);
- vnode->cb_interest = afs_get_cb_interest(cbi);
+ old = vnode->cb_interest;
+ vnode->cb_interest = cbi;
write_sequnlock(&vnode->cb_lock);
- afs_put_cb_interest(afs_v2net(vnode), cbi);
+ afs_put_cb_interest(afs_v2net(vnode), old);
return 0;
}
+ /* Re-use the one attached to the vnode. */
if (!cbi && vcbi->server == server) {
- afs_get_cb_interest(vcbi);
- x = cmpxchg(&entry->cb_interest, cbi, vcbi);
- if (x != cbi) {
- cbi = x;
- afs_put_cb_interest(afs_v2net(vnode), vcbi);
+ write_lock(&slist->lock);
+ if (entry->cb_interest) {
+ write_unlock(&slist->lock);
+ afs_put_cb_interest(afs_v2net(vnode), cbi);
goto again;
}
+
+ entry->cb_interest = cbi;
+ write_unlock(&slist->lock);
return 0;
}
}
@@ -72,13 +91,16 @@ again:
list_add_tail(&new->cb_link, &server->cb_interests);
write_unlock(&server->cb_break_lock);
- x = cmpxchg(&entry->cb_interest, cbi, new);
- if (x == cbi) {
+ write_lock(&slist->lock);
+ if (!entry->cb_interest) {
+ entry->cb_interest = afs_get_cb_interest(new);
cbi = new;
+ new = NULL;
} else {
- cbi = x;
- afs_put_cb_interest(afs_v2net(vnode), new);
+ cbi = afs_get_cb_interest(entry->cb_interest);
}
+ write_unlock(&slist->lock);
+ afs_put_cb_interest(afs_v2net(vnode), new);
}
ASSERT(cbi);
@@ -88,11 +110,14 @@ again:
*/
write_seqlock(&vnode->cb_lock);
- vnode->cb_interest = afs_get_cb_interest(cbi);
+ old = vnode->cb_interest;
+ vnode->cb_interest = cbi;
vnode->cb_s_break = cbi->server->cb_s_break;
+ vnode->cb_v_break = vnode->volume->cb_v_break;
clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
write_sequnlock(&vnode->cb_lock);
+ afs_put_cb_interest(afs_v2net(vnode), old);
return 0;
}
@@ -171,13 +196,24 @@ static void afs_break_one_callback(struct afs_server *server,
if (cbi->vid != fid->vid)
continue;
- data.volume = NULL;
- data.fid = *fid;
- inode = ilookup5_nowait(cbi->sb, fid->vnode, afs_iget5_test, &data);
- if (inode) {
- vnode = AFS_FS_I(inode);
- afs_break_callback(vnode);
- iput(inode);
+ if (fid->vnode == 0 && fid->unique == 0) {
+ /* The callback break applies to an entire volume. */
+ struct afs_super_info *as = AFS_FS_S(cbi->sb);
+ struct afs_volume *volume = as->volume;
+
+ write_lock(&volume->cb_break_lock);
+ volume->cb_v_break++;
+ write_unlock(&volume->cb_break_lock);
+ } else {
+ data.volume = NULL;
+ data.fid = *fid;
+ inode = ilookup5_nowait(cbi->sb, fid->vnode,
+ afs_iget5_test, &data);
+ if (inode) {
+ vnode = AFS_FS_I(inode);
+ afs_break_callback(vnode);
+ iput(inode);
+ }
}
}
@@ -195,6 +231,8 @@ void afs_break_callbacks(struct afs_server *server, size_t count,
ASSERT(server != NULL);
ASSERTCMP(count, <=, AFSCBMAX);
+ /* TODO: Sort the callback break list by volume ID */
+
for (; count > 0; callbacks++, count--) {
_debug("- Fid { vl=%08x n=%u u=%u } CB { v=%u x=%u t=%u }",
callbacks->fid.vid,
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 357de908df3a..c332c95a6940 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -133,21 +133,10 @@ bool afs_cm_incoming_call(struct afs_call *call)
}
/*
- * clean up a cache manager call
+ * Clean up a cache manager call.
*/
static void afs_cm_destructor(struct afs_call *call)
{
- _enter("");
-
- /* Break the callbacks here so that we do it after the final ACK is
- * received. The step number here must match the final number in
- * afs_deliver_cb_callback().
- */
- if (call->unmarshall == 5) {
- ASSERT(call->cm_server && call->count && call->request);
- afs_break_callbacks(call->cm_server, call->count, call->request);
- }
-
kfree(call->buffer);
call->buffer = NULL;
}
@@ -161,14 +150,14 @@ static void SRXAFSCB_CallBack(struct work_struct *work)
_enter("");
- /* be sure to send the reply *before* attempting to spam the AFS server
- * with FSFetchStatus requests on the vnodes with broken callbacks lest
- * the AFS server get into a vicious cycle of trying to break further
- * callbacks because it hadn't received completion of the CBCallBack op
- * yet */
- afs_send_empty_reply(call);
+ /* We need to break the callbacks before sending the reply as the
+ * server holds up change visibility till it receives our reply so as
+ * to maintain cache coherency.
+ */
+ if (call->cm_server)
+ afs_break_callbacks(call->cm_server, call->count, call->request);
- afs_break_callbacks(call->cm_server, call->count, call->request);
+ afs_send_empty_reply(call);
afs_put_call(call);
_leave("");
}
@@ -180,7 +169,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
{
struct afs_callback_break *cb;
struct sockaddr_rxrpc srx;
- struct afs_server *server;
__be32 *bp;
int ret, loop;
@@ -267,15 +255,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
call->offset = 0;
call->unmarshall++;
-
- /* Record that the message was unmarshalled successfully so
- * that the call destructor can know do the callback breaking
- * work, even if the final ACK isn't received.
- *
- * If the step number changes, then afs_cm_destructor() must be
- * updated also.
- */
- call->unmarshall++;
case 5:
break;
}
@@ -286,10 +265,9 @@ static int afs_deliver_cb_callback(struct afs_call *call)
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ call->cm_server = afs_find_server(call->net, &srx);
+ if (!call->cm_server)
+ trace_afs_cm_no_server(call, &srx);
return afs_queue_call_work(call);
}
@@ -303,7 +281,8 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
_enter("{%p}", call->cm_server);
- afs_init_callback_state(call->cm_server);
+ if (call->cm_server)
+ afs_init_callback_state(call->cm_server);
afs_send_empty_reply(call);
afs_put_call(call);
_leave("");
@@ -315,7 +294,6 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
{
struct sockaddr_rxrpc srx;
- struct afs_server *server;
int ret;
_enter("");
@@ -328,10 +306,9 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ call->cm_server = afs_find_server(call->net, &srx);
+ if (!call->cm_server)
+ trace_afs_cm_no_server(call, &srx);
return afs_queue_call_work(call);
}
@@ -341,8 +318,6 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
*/
static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
{
- struct sockaddr_rxrpc srx;
- struct afs_server *server;
struct afs_uuid *r;
unsigned loop;
__be32 *b;
@@ -398,11 +373,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ rcu_read_lock();
+ call->cm_server = afs_find_server_by_uuid(call->net, call->request);
+ rcu_read_unlock();
+ if (!call->cm_server)
+ trace_afs_cm_no_server_u(call, call->request);
return afs_queue_call_work(call);
}
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 5889f70d4d27..7d623008157f 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -180,6 +180,7 @@ static int afs_dir_open(struct inode *inode, struct file *file)
* get reclaimed during the iteration.
*/
static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
+ __acquires(&dvnode->validate_lock)
{
struct afs_read *req;
loff_t i_size;
@@ -261,18 +262,21 @@ retry:
/* If we're going to reload, we need to lock all the pages to prevent
* races.
*/
- if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
- ret = -ERESTARTSYS;
- for (i = 0; i < req->nr_pages; i++)
- if (lock_page_killable(req->pages[i]) < 0)
- goto error_unlock;
+ ret = -ERESTARTSYS;
+ if (down_read_killable(&dvnode->validate_lock) < 0)
+ goto error;
- if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
- goto success;
+ if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+ goto success;
+
+ up_read(&dvnode->validate_lock);
+ if (down_write_killable(&dvnode->validate_lock) < 0)
+ goto error;
+ if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
ret = afs_fetch_data(dvnode, key, req);
if (ret < 0)
- goto error_unlock_all;
+ goto error_unlock;
task_io_account_read(PAGE_SIZE * req->nr_pages);
@@ -284,33 +288,26 @@ retry:
for (i = 0; i < req->nr_pages; i++)
if (!afs_dir_check_page(dvnode, req->pages[i],
req->actual_len))
- goto error_unlock_all;
+ goto error_unlock;
// TODO: Trim excess pages
set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags);
}
+ downgrade_write(&dvnode->validate_lock);
success:
- i = req->nr_pages;
- while (i > 0)
- unlock_page(req->pages[--i]);
return req;
-error_unlock_all:
- i = req->nr_pages;
error_unlock:
- while (i > 0)
- unlock_page(req->pages[--i]);
+ up_write(&dvnode->validate_lock);
error:
afs_put_read(req);
_leave(" = %d", ret);
return ERR_PTR(ret);
content_has_grown:
- i = req->nr_pages;
- while (i > 0)
- unlock_page(req->pages[--i]);
+ up_write(&dvnode->validate_lock);
afs_put_read(req);
goto retry;
}
@@ -473,6 +470,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
}
out:
+ up_read(&dvnode->validate_lock);
afs_put_read(req);
_leave(" = %d", ret);
return ret;
@@ -1143,7 +1141,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
&newfid, &newstatus, &newcb);
}
@@ -1213,7 +1211,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_remove(&fc, dentry->d_name.name, true,
data_version);
}
@@ -1316,7 +1314,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_remove(&fc, dentry->d_name.name, false,
data_version);
}
@@ -1373,7 +1371,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
&newfid, &newstatus, &newcb);
}
@@ -1443,8 +1441,8 @@ static int afs_link(struct dentry *from, struct inode *dir,
}
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
- fc.cb_break_2 = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
+ fc.cb_break_2 = afs_calc_vnode_cb_break(vnode);
afs_fs_link(&fc, vnode, dentry->d_name.name, data_version);
}
@@ -1512,7 +1510,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_symlink(&fc, dentry->d_name.name,
content, data_version,
&newfid, &newstatus);
@@ -1588,8 +1586,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
while (afs_select_fileserver(&fc)) {
- fc.cb_break = orig_dvnode->cb_break + orig_dvnode->cb_s_break;
- fc.cb_break_2 = new_dvnode->cb_break + new_dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode);
+ fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode);
afs_fs_rename(&fc, old_dentry->d_name.name,
new_dvnode, new_dentry->d_name.name,
orig_data_version, new_data_version);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index c24c08016dd9..7d4f26198573 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -238,7 +238,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_fetch_data(&fc, desc);
}
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 7a0e017070ec..dc62d15a964b 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -86,7 +86,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key,
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_set_lock(&fc, type);
}
@@ -117,7 +117,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_current_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_extend_lock(&fc);
}
@@ -148,7 +148,7 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_current_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_release_lock(&fc);
}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index efacdb7c1dee..b273e1d60478 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -134,6 +134,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
struct afs_read *read_req)
{
const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp;
+ bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus);
u64 data_version, size;
u32 type, abort_code;
u8 flags = 0;
@@ -142,13 +143,32 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
if (vnode)
write_seqlock(&vnode->cb_lock);
+ abort_code = ntohl(xdr->abort_code);
+
if (xdr->if_version != htonl(AFS_FSTATUS_VERSION)) {
+ if (xdr->if_version == htonl(0) &&
+ abort_code != 0 &&
+ inline_error) {
+ /* The OpenAFS fileserver has a bug in FS.InlineBulkStatus
+ * whereby it doesn't set the interface version in the error
+ * case.
+ */
+ status->abort_code = abort_code;
+ ret = 0;
+ goto out;
+ }
+
pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version));
goto bad;
}
+ if (abort_code != 0 && inline_error) {
+ status->abort_code = abort_code;
+ ret = 0;
+ goto out;
+ }
+
type = ntohl(xdr->type);
- abort_code = ntohl(xdr->abort_code);
switch (type) {
case AFS_FTYPE_FILE:
case AFS_FTYPE_DIR:
@@ -165,13 +185,6 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
}
status->type = type;
break;
- case AFS_FTYPE_INVALID:
- if (abort_code != 0) {
- status->abort_code = abort_code;
- ret = 0;
- goto out;
- }
- /* Fall through */
default:
goto bad;
}
@@ -248,7 +261,7 @@ static void xdr_decode_AFSCallBack(struct afs_call *call,
write_seqlock(&vnode->cb_lock);
- if (call->cb_break == (vnode->cb_break + cbi->server->cb_s_break)) {
+ if (call->cb_break == afs_cb_break_sum(vnode, cbi)) {
vnode->cb_version = ntohl(*bp++);
cb_expiry = ntohl(*bp++);
vnode->cb_type = ntohl(*bp++);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 06194cfe9724..479b7fdda124 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -108,7 +108,7 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_fetch_file_status(&fc, NULL, new_inode);
}
@@ -393,15 +393,18 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
read_seqlock_excl(&vnode->cb_lock);
if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
- if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break) {
+ if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break ||
+ vnode->cb_v_break != vnode->volume->cb_v_break) {
vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
+ vnode->cb_v_break = vnode->volume->cb_v_break;
+ valid = false;
} else if (vnode->status.type == AFS_FTYPE_DIR &&
test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) &&
vnode->cb_expires_at - 10 > now) {
- valid = true;
+ valid = true;
} else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) &&
vnode->cb_expires_at - 10 > now) {
- valid = true;
+ valid = true;
}
} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
valid = true;
@@ -415,7 +418,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
if (valid)
goto valid;
- mutex_lock(&vnode->validate_lock);
+ down_write(&vnode->validate_lock);
/* if the promise has expired, we need to check the server again to get
* a new promise - note that if the (parent) directory's metadata was
@@ -444,13 +447,13 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
* different */
if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
afs_zap_data(vnode);
- mutex_unlock(&vnode->validate_lock);
+ up_write(&vnode->validate_lock);
valid:
_leave(" = 0");
return 0;
error_unlock:
- mutex_unlock(&vnode->validate_lock);
+ up_write(&vnode->validate_lock);
_leave(" = %d", ret);
return ret;
}
@@ -574,7 +577,7 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_setattr(&fc, attr);
}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index f8086ec95e24..e3f8a46663db 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -396,6 +396,7 @@ struct afs_server {
#define AFS_SERVER_FL_PROBED 5 /* The fileserver has been probed */
#define AFS_SERVER_FL_PROBING 6 /* Fileserver is being probed */
#define AFS_SERVER_FL_NO_IBULK 7 /* Fileserver doesn't support FS.InlineBulkStatus */
+#define AFS_SERVER_FL_MAY_HAVE_CB 8 /* May have callbacks on this fileserver */
atomic_t usage;
u32 addr_version; /* Address list version */
@@ -433,6 +434,7 @@ struct afs_server_list {
unsigned short index; /* Server currently in use */
unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */
unsigned int seq; /* Set to ->servers_seq when installed */
+ rwlock_t lock;
struct afs_server_entry servers[];
};
@@ -459,6 +461,9 @@ struct afs_volume {
rwlock_t servers_lock; /* Lock for ->servers */
unsigned int servers_seq; /* Incremented each time ->servers changes */
+ unsigned cb_v_break; /* Break-everything counter. */
+ rwlock_t cb_break_lock;
+
afs_voltype_t type; /* type of volume */
short error;
char type_force; /* force volume type (suppress R/O -> R/W) */
@@ -494,7 +499,7 @@ struct afs_vnode {
#endif
struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */
struct mutex io_lock; /* Lock for serialising I/O on this mutex */
- struct mutex validate_lock; /* lock for validating this vnode */
+ struct rw_semaphore validate_lock; /* lock for validating this vnode */
spinlock_t wb_lock; /* lock for wb_keys */
spinlock_t lock; /* waitqueue/flags lock */
unsigned long flags;
@@ -519,6 +524,7 @@ struct afs_vnode {
/* outstanding callback notification on this file */
struct afs_cb_interest *cb_interest; /* Server on which this resides */
unsigned int cb_s_break; /* Mass break counter on ->server */
+ unsigned int cb_v_break; /* Mass break counter on ->volume */
unsigned int cb_break; /* Break counter on vnode */
seqlock_t cb_lock; /* Lock for ->cb_interest, ->status, ->cb_*break */
@@ -648,16 +654,29 @@ extern void afs_init_callback_state(struct afs_server *);
extern void afs_break_callback(struct afs_vnode *);
extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*);
-extern int afs_register_server_cb_interest(struct afs_vnode *, struct afs_server_entry *);
+extern int afs_register_server_cb_interest(struct afs_vnode *,
+ struct afs_server_list *, unsigned int);
extern void afs_put_cb_interest(struct afs_net *, struct afs_cb_interest *);
extern void afs_clear_callback_interests(struct afs_net *, struct afs_server_list *);
static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest *cbi)
{
- refcount_inc(&cbi->usage);
+ if (cbi)
+ refcount_inc(&cbi->usage);
return cbi;
}
+static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
+{
+ return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break;
+}
+
+static inline unsigned int afs_cb_break_sum(struct afs_vnode *vnode,
+ struct afs_cb_interest *cbi)
+{
+ return vnode->cb_break + cbi->server->cb_s_break + vnode->volume->cb_v_break;
+}
+
/*
* cell.c
*/
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index ac0feac9d746..e065bc0768e6 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -179,7 +179,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
*/
if (fc->flags & AFS_FS_CURSOR_VNOVOL) {
fc->ac.error = -EREMOTEIO;
- goto failed;
+ goto next_server;
}
write_lock(&vnode->volume->servers_lock);
@@ -201,7 +201,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
*/
if (vnode->volume->servers == fc->server_list) {
fc->ac.error = -EREMOTEIO;
- goto failed;
+ goto next_server;
}
/* Try again */
@@ -350,8 +350,8 @@ use_server:
* break request before we've finished decoding the reply and
* installing the vnode.
*/
- fc->ac.error = afs_register_server_cb_interest(
- vnode, &fc->server_list->servers[fc->index]);
+ fc->ac.error = afs_register_server_cb_interest(vnode, fc->server_list,
+ fc->index);
if (fc->ac.error < 0)
goto failed;
@@ -369,8 +369,16 @@ use_server:
if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) {
fc->ac.alist = afs_get_addrlist(alist);
- if (!afs_probe_fileserver(fc))
- goto failed;
+ if (!afs_probe_fileserver(fc)) {
+ switch (fc->ac.error) {
+ case -ENOMEM:
+ case -ERESTARTSYS:
+ case -EINTR:
+ goto failed;
+ default:
+ goto next_server;
+ }
+ }
}
if (!fc->ac.alist)
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 5c6263972ec9..08735948f15d 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -41,6 +41,7 @@ int afs_open_socket(struct afs_net *net)
{
struct sockaddr_rxrpc srx;
struct socket *socket;
+ unsigned int min_level;
int ret;
_enter("");
@@ -60,6 +61,12 @@ int afs_open_socket(struct afs_net *net)
srx.transport.sin6.sin6_family = AF_INET6;
srx.transport.sin6.sin6_port = htons(AFS_CM_PORT);
+ min_level = RXRPC_SECURITY_ENCRYPT;
+ ret = kernel_setsockopt(socket, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL,
+ (void *)&min_level, sizeof(min_level));
+ if (ret < 0)
+ goto error_2;
+
ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
if (ret == -EADDRINUSE) {
srx.transport.sin6.sin6_port = 0;
@@ -482,8 +489,12 @@ static void afs_deliver_to_call(struct afs_call *call)
state = READ_ONCE(call->state);
switch (ret) {
case 0:
- if (state == AFS_CALL_CL_PROC_REPLY)
+ if (state == AFS_CALL_CL_PROC_REPLY) {
+ if (call->cbi)
+ set_bit(AFS_SERVER_FL_MAY_HAVE_CB,
+ &call->cbi->server->flags);
goto call_complete;
+ }
ASSERTCMP(state, >, AFS_CALL_CL_PROC_REPLY);
goto done;
case -EINPROGRESS:
@@ -493,11 +504,6 @@ static void afs_deliver_to_call(struct afs_call *call)
case -ECONNABORTED:
ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
goto done;
- case -ENOTCONN:
- abort_code = RX_CALL_DEAD;
- rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KNC");
- goto local_abort;
case -ENOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
diff --git a/fs/afs/security.c b/fs/afs/security.c
index cea2fff313dc..1992b0ffa543 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -147,8 +147,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
break;
}
- if (cb_break != (vnode->cb_break +
- vnode->cb_interest->server->cb_s_break)) {
+ if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) {
changed = true;
break;
}
@@ -178,7 +177,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
}
}
- if (cb_break != (vnode->cb_break + vnode->cb_interest->server->cb_s_break))
+ if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest))
goto someone_else_changed_it;
/* We need a ref on any permits list we want to copy as we'll have to
@@ -257,7 +256,7 @@ found:
spin_lock(&vnode->lock);
zap = rcu_access_pointer(vnode->permit_cache);
- if (cb_break == (vnode->cb_break + vnode->cb_interest->server->cb_s_break) &&
+ if (cb_break == afs_cb_break_sum(vnode, vnode->cb_interest) &&
zap == permits)
rcu_assign_pointer(vnode->permit_cache, replacement);
else
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 629c74986cff..3af4625e2f8c 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -67,12 +67,6 @@ struct afs_server *afs_find_server(struct afs_net *net,
sizeof(struct in6_addr));
if (diff == 0)
goto found;
- if (diff < 0) {
- // TODO: Sort the list
- //if (i == alist->nr_ipv4)
- // goto not_found;
- break;
- }
}
}
} else {
@@ -87,17 +81,10 @@ struct afs_server *afs_find_server(struct afs_net *net,
(u32 __force)b->sin6_addr.s6_addr32[3]);
if (diff == 0)
goto found;
- if (diff < 0) {
- // TODO: Sort the list
- //if (i == 0)
- // goto not_found;
- break;
- }
}
}
}
- //not_found:
server = NULL;
found:
if (server && !atomic_inc_not_zero(&server->usage))
@@ -395,14 +382,16 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server)
struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
struct afs_addr_cursor ac = {
.alist = alist,
- .addr = &alist->addrs[0],
.start = alist->index,
- .index = alist->index,
+ .index = 0,
+ .addr = &alist->addrs[alist->index],
.error = 0,
};
_enter("%p", server);
- afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+ if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags))
+ afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+
call_rcu(&server->rcu, afs_server_rcu);
afs_dec_servers_outstanding(net);
}
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 0f8dc4c8f07c..8a5760aa5832 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -49,6 +49,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
goto error;
refcount_set(&slist->usage, 1);
+ rwlock_init(&slist->lock);
/* Make sure a records exists for each server in the list. */
for (i = 0; i < vldb->nr_servers; i++) {
@@ -64,9 +65,11 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
goto error_2;
}
- /* Insertion-sort by server pointer */
+ /* Insertion-sort by UUID */
for (j = 0; j < slist->nr_servers; j++)
- if (slist->servers[j].server >= server)
+ if (memcmp(&slist->servers[j].server->uuid,
+ &server->uuid,
+ sizeof(server->uuid)) >= 0)
break;
if (j < slist->nr_servers) {
if (slist->servers[j].server == server) {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 65081ec3c36e..9e5d7966621c 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -590,7 +590,7 @@ static void afs_i_init_once(void *_vnode)
memset(vnode, 0, sizeof(*vnode));
inode_init_once(&vnode->vfs_inode);
mutex_init(&vnode->io_lock);
- mutex_init(&vnode->validate_lock);
+ init_rwsem(&vnode->validate_lock);
spin_lock_init(&vnode->wb_lock);
spin_lock_init(&vnode->lock);
INIT_LIST_HEAD(&vnode->wb_keys);
@@ -688,7 +688,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
if (afs_begin_vnode_operation(&fc, vnode, key)) {
fc.flags |= AFS_FS_CURSOR_NO_VSLEEP;
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_get_volume_status(&fc, &vs);
}
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c164698dc304..8b39e6ebb40b 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -351,7 +351,7 @@ found_key:
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_store_data(&fc, mapping, first, last, offset, to);
}
diff --git a/fs/aio.c b/fs/aio.c
index 88d7927ffbc6..8061d9787e54 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1078,8 +1078,8 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
ctx = rcu_dereference(table->table[id]);
if (ctx && ctx->user_id == ctx_id) {
- percpu_ref_get(&ctx->users);
- ret = ctx;
+ if (percpu_ref_tryget_live(&ctx->users))
+ ret = ctx;
}
out:
rcu_read_unlock();
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index af2832aaeec5..4700b4534439 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -198,23 +198,16 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
if (ret == BEFS_BT_NOT_FOUND) {
befs_debug(sb, "<--- %s %pd not found", __func__, dentry);
- d_add(dentry, NULL);
- return ERR_PTR(-ENOENT);
-
+ inode = NULL;
} else if (ret != BEFS_OK || offset == 0) {
befs_error(sb, "<--- %s Error", __func__);
- return ERR_PTR(-ENODATA);
+ inode = ERR_PTR(-ENODATA);
+ } else {
+ inode = befs_iget(dir->i_sb, (ino_t) offset);
}
-
- inode = befs_iget(dir->i_sb, (ino_t) offset);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
-
- d_add(dentry, inode);
-
befs_debug(sb, "<--- %s", __func__);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
static int
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 3fd44835b386..8c68961925b1 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2436,10 +2436,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
if (p->reada != READA_NONE)
reada_for_search(fs_info, p, level, slot, key->objectid);
- btrfs_release_path(p);
-
ret = -EAGAIN;
- tmp = read_tree_block(fs_info, blocknr, 0, parent_level - 1,
+ tmp = read_tree_block(fs_info, blocknr, gen, parent_level - 1,
&first_key);
if (!IS_ERR(tmp)) {
/*
@@ -2454,6 +2452,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
} else {
ret = PTR_ERR(tmp);
}
+
+ btrfs_release_path(p);
return ret;
}
@@ -5414,12 +5414,24 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
down_read(&fs_info->commit_root_sem);
left_level = btrfs_header_level(left_root->commit_root);
left_root_level = left_level;
- left_path->nodes[left_level] = left_root->commit_root;
+ left_path->nodes[left_level] =
+ btrfs_clone_extent_buffer(left_root->commit_root);
+ if (!left_path->nodes[left_level]) {
+ up_read(&fs_info->commit_root_sem);
+ ret = -ENOMEM;
+ goto out;
+ }
extent_buffer_get(left_path->nodes[left_level]);
right_level = btrfs_header_level(right_root->commit_root);
right_root_level = right_level;
- right_path->nodes[right_level] = right_root->commit_root;
+ right_path->nodes[right_level] =
+ btrfs_clone_extent_buffer(right_root->commit_root);
+ if (!right_path->nodes[right_level]) {
+ up_read(&fs_info->commit_root_sem);
+ ret = -ENOMEM;
+ goto out;
+ }
extent_buffer_get(right_path->nodes[right_level]);
up_read(&fs_info->commit_root_sem);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2771cc56a622..0d422c9908b8 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3182,6 +3182,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
u64 *ram_bytes);
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode);
struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 60caa68c3618..c3504b4d281b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3818,6 +3818,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
btrfs_free_qgroup_config(fs_info);
+ ASSERT(list_empty(&fs_info->delalloc_roots));
if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
btrfs_info(fs_info, "at unmount delalloc count %lld",
@@ -4125,15 +4126,15 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
{
+ /* cleanup FS via transaction */
+ btrfs_cleanup_transaction(fs_info);
+
mutex_lock(&fs_info->cleaner_mutex);
btrfs_run_delayed_iputs(fs_info);
mutex_unlock(&fs_info->cleaner_mutex);
down_write(&fs_info->cleanup_work_sem);
up_write(&fs_info->cleanup_work_sem);
-
- /* cleanup FS via transaction */
- btrfs_cleanup_transaction(fs_info);
}
static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
@@ -4258,19 +4259,23 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
list_splice_init(&root->delalloc_inodes, &splice);
while (!list_empty(&splice)) {
+ struct inode *inode = NULL;
btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
delalloc_inodes);
-
- list_del_init(&btrfs_inode->delalloc_inodes);
- clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
- &btrfs_inode->runtime_flags);
+ __btrfs_del_delalloc_inode(root, btrfs_inode);
spin_unlock(&root->delalloc_lock);
- btrfs_invalidate_inodes(btrfs_inode->root);
-
+ /*
+ * Make sure we get a live inode and that it'll not disappear
+ * meanwhile.
+ */
+ inode = igrab(&btrfs_inode->vfs_inode);
+ if (inode) {
+ invalidate_inode_pages2(inode->i_mapping);
+ iput(inode);
+ }
spin_lock(&root->delalloc_lock);
}
-
spin_unlock(&root->delalloc_lock);
}
@@ -4286,7 +4291,6 @@ static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info)
while (!list_empty(&splice)) {
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
- list_del_init(&root->delalloc_root);
root = btrfs_grab_fs_root(root);
BUG_ON(!root);
spin_unlock(&fs_info->delalloc_root_lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d241285a0d2a..0b86cf10cf2a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1742,12 +1742,12 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
spin_unlock(&root->delalloc_lock);
}
-static void btrfs_del_delalloc_inode(struct btrfs_root *root,
- struct btrfs_inode *inode)
+
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
- spin_lock(&root->delalloc_lock);
if (!list_empty(&inode->delalloc_inodes)) {
list_del_init(&inode->delalloc_inodes);
clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
@@ -1760,6 +1760,13 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root,
spin_unlock(&fs_info->delalloc_root_lock);
}
}
+}
+
+static void btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode)
+{
+ spin_lock(&root->delalloc_lock);
+ __btrfs_del_delalloc_inode(root, inode);
spin_unlock(&root->delalloc_lock);
}
@@ -6579,8 +6586,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
} else {
btrfs_update_inode(trans, root, inode);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
}
out_unlock:
@@ -6656,8 +6662,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans);
@@ -6802,12 +6807,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
if (err)
goto out_fail_inode;
- d_instantiate(dentry, inode);
- /*
- * mkdir is special. We're unlocking after we call d_instantiate
- * to avoid a race with nfsd calling d_instantiate.
- */
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
drop_on_err = 0;
out_fail:
@@ -9117,7 +9117,8 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
BTRFS_EXTENT_DATA_KEY);
trans->block_rsv = &fs_info->trans_block_rsv;
if (ret != -ENOSPC && ret != -EAGAIN) {
- err = ret;
+ if (ret < 0)
+ err = ret;
break;
}
@@ -10250,8 +10251,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans);
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 53a8c95828e3..dc6140013ae8 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -380,6 +380,7 @@ static int prop_compression_apply(struct inode *inode,
const char *value,
size_t len)
{
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
int type;
if (len == 0) {
@@ -390,14 +391,17 @@ static int prop_compression_apply(struct inode *inode,
return 0;
}
- if (!strncmp("lzo", value, 3))
+ if (!strncmp("lzo", value, 3)) {
type = BTRFS_COMPRESS_LZO;
- else if (!strncmp("zlib", value, 4))
+ btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+ } else if (!strncmp("zlib", value, 4)) {
type = BTRFS_COMPRESS_ZLIB;
- else if (!strncmp("zstd", value, len))
+ } else if (!strncmp("zstd", value, len)) {
type = BTRFS_COMPRESS_ZSTD;
- else
+ btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
+ } else {
return -EINVAL;
+ }
BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 43758e30aa7a..8f23a94dab77 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4320,6 +4320,110 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
return ret;
}
+/*
+ * Log all prealloc extents beyond the inode's i_size to make sure we do not
+ * lose them after doing a fast fsync and replaying the log. We scan the
+ * subvolume's root instead of iterating the inode's extent map tree because
+ * otherwise we can log incorrect extent items based on extent map conversion.
+ * That can happen due to the fact that extent maps are merged when they
+ * are not in the extent map tree's list of modified extents.
+ */
+static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct btrfs_path *path)
+{
+ struct btrfs_root *root = inode->root;
+ struct btrfs_key key;
+ const u64 i_size = i_size_read(&inode->vfs_inode);
+ const u64 ino = btrfs_ino(inode);
+ struct btrfs_path *dst_path = NULL;
+ u64 last_extent = (u64)-1;
+ int ins_nr = 0;
+ int start_slot;
+ int ret;
+
+ if (!(inode->flags & BTRFS_INODE_PREALLOC))
+ return 0;
+
+ key.objectid = ino;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = i_size;
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ if (ins_nr > 0) {
+ ret = copy_items(trans, inode, dst_path, path,
+ &last_extent, start_slot,
+ ins_nr, 1, 0);
+ if (ret < 0)
+ goto out;
+ ins_nr = 0;
+ }
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid > ino)
+ break;
+ if (WARN_ON_ONCE(key.objectid < ino) ||
+ key.type < BTRFS_EXTENT_DATA_KEY ||
+ key.offset < i_size) {
+ path->slots[0]++;
+ continue;
+ }
+ if (last_extent == (u64)-1) {
+ last_extent = key.offset;
+ /*
+ * Avoid logging extent items logged in past fsync calls
+ * and leading to duplicate keys in the log tree.
+ */
+ do {
+ ret = btrfs_truncate_inode_items(trans,
+ root->log_root,
+ &inode->vfs_inode,
+ i_size,
+ BTRFS_EXTENT_DATA_KEY);
+ } while (ret == -EAGAIN);
+ if (ret)
+ goto out;
+ }
+ if (ins_nr == 0)
+ start_slot = slot;
+ ins_nr++;
+ path->slots[0]++;
+ if (!dst_path) {
+ dst_path = btrfs_alloc_path();
+ if (!dst_path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ }
+ if (ins_nr > 0) {
+ ret = copy_items(trans, inode, dst_path, path, &last_extent,
+ start_slot, ins_nr, 1, 0);
+ if (ret > 0)
+ ret = 0;
+ }
+out:
+ btrfs_release_path(path);
+ btrfs_free_path(dst_path);
+ return ret;
+}
+
static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_inode *inode,
@@ -4362,6 +4466,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
if (em->generation <= test_gen)
continue;
+ /* We log prealloc extents beyond eof later. */
+ if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
+ em->start >= i_size_read(&inode->vfs_inode))
+ continue;
+
if (em->start < logged_start)
logged_start = em->start;
if ((em->start + em->len - 1) > logged_end)
@@ -4374,31 +4483,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
num++;
}
- /*
- * Add all prealloc extents beyond the inode's i_size to make sure we
- * don't lose them after doing a fast fsync and replaying the log.
- */
- if (inode->flags & BTRFS_INODE_PREALLOC) {
- struct rb_node *node;
-
- for (node = rb_last(&tree->map); node; node = rb_prev(node)) {
- em = rb_entry(node, struct extent_map, rb_node);
- if (em->start < i_size_read(&inode->vfs_inode))
- break;
- if (!list_empty(&em->list))
- continue;
- /* Same as above loop. */
- if (++num > 32768) {
- list_del_init(&tree->modified_extents);
- ret = -EFBIG;
- goto process;
- }
- refcount_inc(&em->refs);
- set_bit(EXTENT_FLAG_LOGGING, &em->flags);
- list_add_tail(&em->list, &extents);
- }
- }
-
list_sort(NULL, &extents, extent_cmp);
btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
/*
@@ -4443,6 +4527,9 @@ process:
up_write(&inode->dio_sem);
btrfs_release_path(path);
+ if (!ret)
+ ret = btrfs_log_prealloc_extents(trans, inode, path);
+
return ret;
}
@@ -4827,6 +4914,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
struct extent_map_tree *em_tree = &inode->extent_tree;
u64 logged_isize = 0;
bool need_log_inode_item = true;
+ bool xattrs_logged = false;
path = btrfs_alloc_path();
if (!path)
@@ -5128,6 +5216,7 @@ next_key:
err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
if (err)
goto out_unlock;
+ xattrs_logged = true;
if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
btrfs_release_path(path);
btrfs_release_path(dst_path);
@@ -5140,6 +5229,11 @@ log_extents:
btrfs_release_path(dst_path);
if (need_log_inode_item) {
err = log_inode_item(trans, log, dst_path, inode);
+ if (!err && !xattrs_logged) {
+ err = btrfs_log_all_xattrs(trans, root, inode, path,
+ dst_path);
+ btrfs_release_path(path);
+ }
if (err)
goto out_unlock;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 292266f6ab9c..be3fc701f389 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4052,6 +4052,15 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
return 0;
}
+ /*
+ * A ro->rw remount sequence should continue with the paused balance
+ * regardless of who pauses it, system or the user as of now, so set
+ * the resume flag.
+ */
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl->flags |= BTRFS_BALANCE_RESUME;
+ spin_unlock(&fs_info->balance_lock);
+
tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
return PTR_ERR_OR_ZERO(tsk);
}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 0daa1e3fe0df..ab0bbe93b398 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -572,6 +572,11 @@ lookup_again:
if (ret < 0)
goto create_error;
+ if (unlikely(d_unhashed(next))) {
+ dput(next);
+ inode_unlock(d_inode(dir));
+ goto lookup_again;
+ }
ASSERT(d_backing_inode(next));
_debug("mkdir -> %p{%p{ino=%lu}}",
@@ -764,6 +769,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
/* search the current directory for the element name */
inode_lock(d_inode(dir));
+retry:
start = jiffies;
subdir = lookup_one_len(dirname, dir, strlen(dirname));
cachefiles_hist(cachefiles_lookup_histogram, start);
@@ -793,6 +799,10 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
if (ret < 0)
goto mkdir_error;
+ if (unlikely(d_unhashed(subdir))) {
+ dput(subdir);
+ goto retry;
+ }
ASSERT(d_backing_inode(subdir));
_debug("mkdir -> %p{%p{ino=%lu}}",
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 5f132d59dfc2..d61e2de8d0eb 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -197,7 +197,7 @@ config CIFS_SMB311
config CIFS_SMB_DIRECT
bool "SMB Direct support (Experimental)"
- depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y
+ depends on CIFS=m && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND_ADDR_TRANS=y
help
Enables SMB Direct experimental support for SMB 3.0, 3.02 and 3.1.1.
SMB Direct allows transferring SMB packets over RDMA. If unsure,
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 017b0ab19bc4..124b093d14e5 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -492,7 +492,7 @@ static void cramfs_kill_sb(struct super_block *sb)
{
struct cramfs_sb_info *sbi = CRAMFS_SB(sb);
- if (IS_ENABLED(CCONFIG_CRAMFS_MTD) && sb->s_mtd) {
+ if (IS_ENABLED(CONFIG_CRAMFS_MTD) && sb->s_mtd) {
if (sbi && sbi->mtd_point_size)
mtd_unpoint(sb->s_mtd, 0, sbi->mtd_point_size);
kill_mtd_super(sb);
diff --git a/fs/dax.c b/fs/dax.c
index 34a2d435ae4b..1f5f14a2ce4c 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -351,6 +351,19 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
}
}
+static struct page *dax_busy_page(void *entry)
+{
+ unsigned long pfn;
+
+ for_each_mapped_pfn(entry, pfn) {
+ struct page *page = pfn_to_page(pfn);
+
+ if (page_ref_count(page) > 1)
+ return page;
+ }
+ return NULL;
+}
+
/*
* Find radix tree entry at given index. If it points to an exceptional entry,
* return it with the radix tree entry locked. If the radix tree doesn't
@@ -492,6 +505,90 @@ restart:
return entry;
}
+/**
+ * dax_layout_busy_page - find first pinned page in @mapping
+ * @mapping: address space to scan for a page with ref count > 1
+ *
+ * DAX requires ZONE_DEVICE mapped pages. These pages are never
+ * 'onlined' to the page allocator so they are considered idle when
+ * page->count == 1. A filesystem uses this interface to determine if
+ * any page in the mapping is busy, i.e. for DMA, or other
+ * get_user_pages() usages.
+ *
+ * It is expected that the filesystem is holding locks to block the
+ * establishment of new mappings in this address_space. I.e. it expects
+ * to be able to run unmap_mapping_range() and subsequently not race
+ * mapping_mapped() becoming true.
+ */
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+ pgoff_t indices[PAGEVEC_SIZE];
+ struct page *page = NULL;
+ struct pagevec pvec;
+ pgoff_t index, end;
+ unsigned i;
+
+ /*
+ * In the 'limited' case get_user_pages() for dax is disabled.
+ */
+ if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+ return NULL;
+
+ if (!dax_mapping(mapping) || !mapping_mapped(mapping))
+ return NULL;
+
+ pagevec_init(&pvec);
+ index = 0;
+ end = -1;
+
+ /*
+ * If we race get_user_pages_fast() here either we'll see the
+ * elevated page count in the pagevec_lookup and wait, or
+ * get_user_pages_fast() will see that the page it took a reference
+ * against is no longer mapped in the page tables and bail to the
+ * get_user_pages() slow path. The slow path is protected by
+ * pte_lock() and pmd_lock(). New references are not taken without
+ * holding those locks, and unmap_mapping_range() will not zero the
+ * pte or pmd without holding the respective lock, so we are
+ * guaranteed to either see new references or prevent new
+ * references from being established.
+ */
+ unmap_mapping_range(mapping, 0, 0, 1);
+
+ while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE),
+ indices)) {
+ for (i = 0; i < pagevec_count(&pvec); i++) {
+ struct page *pvec_ent = pvec.pages[i];
+ void *entry;
+
+ index = indices[i];
+ if (index >= end)
+ break;
+
+ if (!radix_tree_exceptional_entry(pvec_ent))
+ continue;
+
+ xa_lock_irq(&mapping->i_pages);
+ entry = get_unlocked_mapping_entry(mapping, index, NULL);
+ if (entry)
+ page = dax_busy_page(entry);
+ put_unlocked_mapping_entry(mapping, index, entry);
+ xa_unlock_irq(&mapping->i_pages);
+ if (page)
+ break;
+ }
+ pagevec_remove_exceptionals(&pvec);
+ pagevec_release(&pvec);
+ index++;
+
+ if (page)
+ break;
+ }
+ return page;
+}
+EXPORT_SYMBOL_GPL(dax_layout_busy_page);
+
static int __dax_invalidate_mapping_entry(struct address_space *mapping,
pgoff_t index, bool trunc)
{
@@ -912,7 +1009,6 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
unsigned long vaddr = vmf->address;
int ret = VM_FAULT_NOPAGE;
struct page *zero_page;
- void *entry2;
pfn_t pfn;
zero_page = ZERO_PAGE(0);
@@ -922,13 +1018,8 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
}
pfn = page_to_pfn_t(zero_page);
- entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
- RADIX_DAX_ZERO_PAGE, false);
- if (IS_ERR(entry2)) {
- ret = VM_FAULT_SIGBUS;
- goto out;
- }
-
+ dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
+ false);
vm_insert_mixed(vmf->vma, vaddr, pfn);
out:
trace_dax_load_hole(inode, vmf, ret);
@@ -1243,10 +1334,6 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
0, write && !sync);
- if (IS_ERR(entry)) {
- error = PTR_ERR(entry);
- goto error_finish_iomap;
- }
/*
* If we are doing synchronous page fault and inode needs fsync,
@@ -1330,8 +1417,6 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
pfn = page_to_pfn_t(zero_page);
ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
- if (IS_ERR(ret))
- goto fallback;
ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (!pmd_none(*(vmf->pmd))) {
@@ -1453,8 +1538,6 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
RADIX_DAX_PMD, write && !sync);
- if (IS_ERR(entry))
- goto finish_iomap;
/*
* If we are doing synchronous page fault and inode needs fsync,
diff --git a/fs/dcache.c b/fs/dcache.c
index 86d2de63461e..2acfc69878f5 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1899,6 +1899,28 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
}
EXPORT_SYMBOL(d_instantiate);
+/*
+ * This should be equivalent to d_instantiate() + unlock_new_inode(),
+ * with lockdep-related part of unlock_new_inode() done before
+ * anything else. Use that instead of open-coding d_instantiate()/
+ * unlock_new_inode() combinations.
+ */
+void d_instantiate_new(struct dentry *entry, struct inode *inode)
+{
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
+ BUG_ON(!inode);
+ lockdep_annotate_inode_mutex_key(inode);
+ security_d_instantiate(entry, inode);
+ spin_lock(&inode->i_lock);
+ __d_instantiate(entry, inode);
+ WARN_ON(!(inode->i_state & I_NEW));
+ inode->i_state &= ~I_NEW;
+ smp_mb();
+ wake_up_bit(&inode->i_state, __I_NEW);
+ spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(d_instantiate_new);
+
/**
* d_instantiate_no_diralias - instantiate a non-aliased dentry
* @entry: dentry to complete
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 97d17eaeba07..49121e5a8de2 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -283,8 +283,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
iget_failed(ecryptfs_inode);
goto out;
}
- unlock_new_inode(ecryptfs_inode);
- d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+ d_instantiate_new(ecryptfs_dentry, ecryptfs_inode);
out:
return rc;
}
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 1e01fabef130..71635909df3b 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1264,21 +1264,11 @@ do_indirects:
static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
{
- /*
- * XXX: it seems like a bug here that we don't allow
- * IS_APPEND inode to have blocks-past-i_size trimmed off.
- * review and fix this.
- *
- * Also would be nice to be able to handle IO errors and such,
- * but that's probably too much to ask.
- */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return;
if (ext2_inode_is_fast_symlink(inode))
return;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
- return;
dax_sem_down_write(EXT2_I(inode));
__ext2_truncate_blocks(inode, offset);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 55f7caadb093..152453a91877 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -41,8 +41,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ext2_add_link(dentry, inode);
if (!err) {
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -255,8 +254,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
if (err)
goto out_fail;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out:
return err;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b1f21e3a0763..4a09063ce1d2 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2411,8 +2411,7 @@ static int ext4_add_nondir(handle_t *handle,
int err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
drop_nlink(inode);
@@ -2651,8 +2650,7 @@ out_clear_inode:
err = ext4_mark_inode_dirty(handle, dir);
if (err)
goto out_clear_inode;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index d5098efe577c..75e37fd720b2 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -294,8 +294,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
alloc_nid_done(sbi, ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
@@ -597,8 +596,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
err = page_symlink(inode, disk_link.name, disk_link.len);
err_out:
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
/*
* Let's flush symlink data in order to avoid broken symlink as much as
@@ -661,8 +659,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
alloc_nid_done(sbi, inode->i_ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
@@ -713,8 +710,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
alloc_nid_done(sbi, inode->i_ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 513c357c734b..a6c0f54c48c3 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -588,6 +588,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
return 0;
out_put_hidden_dir:
+ cancel_delayed_work_sync(&sbi->sync_work);
iput(sbi->hidden_dir);
out_put_root:
dput(sb->s_root);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 0a754f38462e..e5a6deb38e1e 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -209,8 +209,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
__func__, inode->i_ino, inode->i_mode, inode->i_nlink,
f->inocache->pino_nlink, inode->i_mapping->nrpages);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -430,8 +429,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -575,8 +573,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -747,8 +744,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index b41596d71858..56c3fcbfe80e 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -178,8 +178,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -313,8 +312,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -1059,8 +1057,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -1447,8 +1444,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out1:
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 26dd9a50f383..ff2716f9322e 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -316,6 +316,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
info->root = root;
info->ns = ns;
+ INIT_LIST_HEAD(&info->node);
sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags,
&init_user_ns, info);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 2410b093a2e6..b0555d7d8200 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1201,6 +1201,28 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
break;
case S_IFDIR:
host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
+ if (!host_err && unlikely(d_unhashed(dchild))) {
+ struct dentry *d;
+ d = lookup_one_len(dchild->d_name.name,
+ dchild->d_parent,
+ dchild->d_name.len);
+ if (IS_ERR(d)) {
+ host_err = PTR_ERR(d);
+ break;
+ }
+ if (unlikely(d_is_negative(d))) {
+ dput(d);
+ err = nfserr_serverfault;
+ goto out;
+ }
+ dput(resfhp->fh_dentry);
+ resfhp->fh_dentry = dget(d);
+ err = fh_update(resfhp);
+ dput(dchild);
+ dchild = d;
+ if (err)
+ goto out;
+ }
break;
case S_IFCHR:
case S_IFBLK:
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1a2894aa0194..dd52d3f82e8d 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -46,8 +46,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
int err = nilfs_add_link(dentry, inode);
if (!err) {
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -243,8 +242,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out_fail;
nilfs_mark_inode_dirty(inode);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 91a8889abf9b..ea8c551bcd7e 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -570,16 +570,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
current_page, vec_len, vec_start);
len = bio_add_page(bio, page, vec_len, vec_start);
- if (len != vec_len) {
- mlog(ML_ERROR, "Adding page[%d] to bio failed, "
- "page %p, len %d, vec_len %u, vec_start %u, "
- "bi_sector %llu\n", current_page, page, len,
- vec_len, vec_start,
- (unsigned long long)bio->bi_iter.bi_sector);
- bio_put(bio);
- bio = ERR_PTR(-EIO);
- return bio;
- }
+ if (len != vec_len) break;
cs += vec_len / (PAGE_SIZE/spp);
vec_start = 0;
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index 6e3134e6d98a..1b5707c44c3f 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -75,8 +75,7 @@ static int orangefs_create(struct inode *dir,
get_khandle_from_ino(inode),
dentry);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -332,8 +331,7 @@ static int orangefs_symlink(struct inode *dir,
"Assigned symlink inode new number of %pU\n",
get_khandle_from_ino(inode));
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -402,8 +400,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
"Assigned dir inode new number of %pU\n",
get_khandle_from_ino(inode));
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ae2c807fd719..72391b3f6927 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -85,6 +85,7 @@
#include <linux/delayacct.h>
#include <linux/seq_file.h>
#include <linux/pid_namespace.h>
+#include <linux/prctl.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/string_helpers.h>
@@ -335,6 +336,30 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
#ifdef CONFIG_SECCOMP
seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
#endif
+ seq_printf(m, "\nSpeculation_Store_Bypass:\t");
+ switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
+ case -EINVAL:
+ seq_printf(m, "unknown");
+ break;
+ case PR_SPEC_NOT_AFFECTED:
+ seq_printf(m, "not vulnerable");
+ break;
+ case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
+ seq_printf(m, "thread force mitigated");
+ break;
+ case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
+ seq_printf(m, "thread mitigated");
+ break;
+ case PR_SPEC_PRCTL | PR_SPEC_ENABLE:
+ seq_printf(m, "thread vulnerable");
+ break;
+ case PR_SPEC_DISABLE:
+ seq_printf(m, "globally mitigated");
+ break;
+ default:
+ seq_printf(m, "vulnerable");
+ break;
+ }
seq_putc(m, '\n');
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1b2ede6abcdf..1a76d751cf3c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -261,7 +261,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
* Inherently racy -- command line shares address space
* with code and data.
*/
- rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+ rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON);
if (rv <= 0)
goto out_free_page;
@@ -279,7 +279,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
int nr_read;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
@@ -325,7 +325,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
bool final;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
@@ -946,7 +946,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
- retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);
+ retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
if (retval <= 0) {
ret = retval;
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index bd39a998843d..5089dac02660 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -687,8 +687,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
@@ -771,8 +770,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
goto out_failed;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
@@ -871,8 +869,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
/* the above add_entry did not update dir's stat data */
reiserfs_update_sd(&th, dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
reiserfs_write_unlock(dir->i_sb);
@@ -1187,8 +1184,7 @@ static int reiserfs_symlink(struct inode *parent_dir,
goto out_failed;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
reiserfs_write_unlock(parent_dir->i_sb);
diff --git a/fs/seq_file.c b/fs/seq_file.c
index c6c27f1f9c98..4cc090b50cc5 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -709,11 +709,6 @@ void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter,
if (m->count + width >= m->size)
goto overflow;
- if (num < 10) {
- m->buf[m->count++] = num + '0';
- return;
- }
-
len = num_to_str(m->buf + m->count, m->size - m->count, num, width);
if (!len)
goto overflow;
diff --git a/fs/super.c b/fs/super.c
index 122c402049a2..4b5b562176d0 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -121,13 +121,23 @@ static unsigned long super_cache_count(struct shrinker *shrink,
sb = container_of(shrink, struct super_block, s_shrink);
/*
- * Don't call trylock_super as it is a potential
- * scalability bottleneck. The counts could get updated
- * between super_cache_count and super_cache_scan anyway.
- * Call to super_cache_count with shrinker_rwsem held
- * ensures the safety of call to list_lru_shrink_count() and
- * s_op->nr_cached_objects().
+ * We don't call trylock_super() here as it is a scalability bottleneck,
+ * so we're exposed to partial setup state. The shrinker rwsem does not
+ * protect filesystem operations backing list_lru_shrink_count() or
+ * s_op->nr_cached_objects(). Counts can change between
+ * super_cache_count and super_cache_scan, so we really don't need locks
+ * here.
+ *
+ * However, if we are currently mounting the superblock, the underlying
+ * filesystem might be in a state of partial construction and hence it
+ * is dangerous to access it. trylock_super() uses a SB_BORN check to
+ * avoid this situation, so do the same here. The memory barrier is
+ * matched with the one in mount_fs() as we don't hold locks here.
*/
+ if (!(sb->s_flags & SB_BORN))
+ return 0;
+ smp_rmb();
+
if (sb->s_op && sb->s_op->nr_cached_objects)
total_objects = sb->s_op->nr_cached_objects(sb, sc);
@@ -1272,6 +1282,14 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
sb = root->d_sb;
BUG_ON(!sb);
WARN_ON(!sb->s_bdi);
+
+ /*
+ * Write barrier is for super_cache_count(). We place it before setting
+ * SB_BORN as the data dependency between the two functions is the
+ * superblock structure contents that we just set up, not the SB_BORN
+ * flag.
+ */
+ smp_wmb();
sb->s_flags |= SB_BORN;
error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index b428d317ae92..92682fcc41f6 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -25,7 +25,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
{
struct dentry *root;
void *ns;
- bool new_sb;
+ bool new_sb = false;
if (!(flags & SB_KERNMOUNT)) {
if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
@@ -35,9 +35,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
root = kernfs_mount_ns(fs_type, flags, sysfs_root,
SYSFS_MAGIC, &new_sb, ns);
- if (IS_ERR(root) || !new_sb)
+ if (!new_sb)
kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
- else if (new_sb)
+ else if (!IS_ERR(root))
root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
return root;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 0458dd47e105..c586026508db 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -622,8 +622,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
if (fibh.sbh != fibh.ebh)
brelse(fibh.ebh);
brelse(fibh.sbh);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
@@ -733,8 +732,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inc_nlink(dir);
dir->i_ctime = dir->i_mtime = current_time(dir);
mark_inode_dirty(dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
if (fibh.sbh != fibh.ebh)
brelse(fibh.ebh);
brelse(fibh.sbh);
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 32545cd00ceb..d5f43ba76c59 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -39,8 +39,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ufs_add_link(dentry, inode);
if (!err) {
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -193,8 +192,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
if (err)
goto out_fail;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
out_fail:
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e70fb8ccecea..19b0c3e0e232 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -312,7 +312,7 @@ restart:
if (error <= 0)
return error;
- error = xfs_break_layouts(inode, iolock);
+ error = xfs_break_layouts(inode, iolock, BREAK_WRITE);
if (error)
return error;
@@ -718,6 +718,69 @@ buffered:
return ret;
}
+static void
+xfs_wait_dax_page(
+ struct inode *inode,
+ bool *did_unlock)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+
+ *did_unlock = true;
+ xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
+ schedule();
+ xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+}
+
+static int
+xfs_break_dax_layouts(
+ struct inode *inode,
+ uint iolock,
+ bool *did_unlock)
+{
+ struct page *page;
+
+ ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
+
+ page = dax_layout_busy_page(inode->i_mapping);
+ if (!page)
+ return 0;
+
+ return ___wait_var_event(&page->_refcount,
+ atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
+ 0, 0, xfs_wait_dax_page(inode, did_unlock));
+}
+
+int
+xfs_break_layouts(
+ struct inode *inode,
+ uint *iolock,
+ enum layout_break_reason reason)
+{
+ bool retry;
+ int error;
+
+ ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+ do {
+ retry = false;
+ switch (reason) {
+ case BREAK_UNMAP:
+ error = xfs_break_dax_layouts(inode, *iolock, &retry);
+ if (error || retry)
+ break;
+ /* fall through */
+ case BREAK_WRITE:
+ error = xfs_break_leased_layouts(inode, iolock, &retry);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ error = -EINVAL;
+ }
+ } while (error == 0 && retry);
+
+ return error;
+}
+
#define XFS_FALLOC_FL_SUPPORTED \
(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \
@@ -734,7 +797,7 @@ xfs_file_fallocate(
struct xfs_inode *ip = XFS_I(inode);
long error;
enum xfs_prealloc_flags flags = 0;
- uint iolock = XFS_IOLOCK_EXCL;
+ uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
loff_t new_size = 0;
bool do_file_insert = false;
@@ -744,13 +807,10 @@ xfs_file_fallocate(
return -EOPNOTSUPP;
xfs_ilock(ip, iolock);
- error = xfs_break_layouts(inode, &iolock);
+ error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
if (error)
goto out_unlock;
- xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
- iolock |= XFS_MMAPLOCK_EXCL;
-
if (mode & FALLOC_FL_PUNCH_HOLE) {
error = xfs_free_file_space(ip, offset, len);
if (error)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1eebc53df7d7..e5b849815ce1 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -379,6 +379,20 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
>> XFS_ILOCK_SHIFT)
/*
+ * Layouts are broken in the BREAK_WRITE case to ensure that
+ * layout-holders do not collide with local writes. Additionally,
+ * layouts are broken in the BREAK_UNMAP case to make sure the
+ * layout-holder has a consistent view of the file's extent map. While
+ * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases,
+ * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to
+ * go idle.
+ */
+enum layout_break_reason {
+ BREAK_WRITE,
+ BREAK_UNMAP,
+};
+
+/*
* For multiple groups support: if S_ISGID bit is set in the parent
* directory, group of new file is set to that of the parent, and
* new subdirectory gets S_ISGID bit from parent.
@@ -443,6 +457,8 @@ enum xfs_prealloc_flags {
int xfs_update_prealloc_flags(struct xfs_inode *ip,
enum xfs_prealloc_flags flags);
+int xfs_break_layouts(struct inode *inode, uint *iolock,
+ enum layout_break_reason reason);
/* from xfs_iops.c */
extern void xfs_setup_inode(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 89fb1eb80aae..91e73d663099 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -39,7 +39,6 @@
#include "xfs_icache.h"
#include "xfs_symlink.h"
#include "xfs_trans.h"
-#include "xfs_pnfs.h"
#include "xfs_acl.h"
#include "xfs_btree.h"
#include <linux/fsmap.h>
@@ -614,7 +613,7 @@ xfs_ioc_space(
struct xfs_inode *ip = XFS_I(inode);
struct iattr iattr;
enum xfs_prealloc_flags flags = 0;
- uint iolock = XFS_IOLOCK_EXCL;
+ uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
int error;
/*
@@ -644,13 +643,10 @@ xfs_ioc_space(
return error;
xfs_ilock(ip, iolock);
- error = xfs_break_layouts(inode, &iolock);
+ error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
if (error)
goto out_unlock;
- xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
- iolock |= XFS_MMAPLOCK_EXCL;
-
switch (bf->l_whence) {
case 0: /*SEEK_SET*/
break;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index a3ed3c811dfa..ce0c1f9466a8 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -37,7 +37,6 @@
#include "xfs_da_btree.h"
#include "xfs_dir2.h"
#include "xfs_trans_space.h"
-#include "xfs_pnfs.h"
#include "xfs_iomap.h"
#include <linux/capability.h>
@@ -1030,14 +1029,19 @@ xfs_vn_setattr(
int error;
if (iattr->ia_valid & ATTR_SIZE) {
- struct xfs_inode *ip = XFS_I(d_inode(dentry));
- uint iolock = XFS_IOLOCK_EXCL;
+ struct inode *inode = d_inode(dentry);
+ struct xfs_inode *ip = XFS_I(inode);
+ uint iolock;
- error = xfs_break_layouts(d_inode(dentry), &iolock);
- if (error)
+ xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+ iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
+
+ error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
+ if (error) {
+ xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
return error;
+ }
- xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
error = xfs_vn_setattr_size(dentry, iattr);
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
} else {
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index aa6c5c193f45..f44c3599527d 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -31,19 +31,20 @@
* rules in the page fault path we don't bother.
*/
int
-xfs_break_layouts(
+xfs_break_leased_layouts(
struct inode *inode,
- uint *iolock)
+ uint *iolock,
+ bool *did_unlock)
{
struct xfs_inode *ip = XFS_I(inode);
int error;
- ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
-
while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
xfs_iunlock(ip, *iolock);
+ *did_unlock = true;
error = break_layout(inode, true);
- *iolock = XFS_IOLOCK_EXCL;
+ *iolock &= ~XFS_IOLOCK_SHARED;
+ *iolock |= XFS_IOLOCK_EXCL;
xfs_ilock(ip, *iolock);
}
@@ -120,8 +121,8 @@ xfs_fs_map_blocks(
* Lock out any other I/O before we flush and invalidate the pagecache,
* and then hand out a layout to the remote system. This is very
* similar to direct I/O, except that the synchronization is much more
- * complicated. See the comment near xfs_break_layouts for a detailed
- * explanation.
+ * complicated. See the comment near xfs_break_leased_layouts
+ * for a detailed explanation.
*/
xfs_ilock(ip, XFS_IOLOCK_EXCL);
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
index bf45951e28fe..940c6c2ad88c 100644
--- a/fs/xfs/xfs_pnfs.h
+++ b/fs/xfs/xfs_pnfs.h
@@ -9,10 +9,11 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps,
struct iattr *iattr);
-int xfs_break_layouts(struct inode *inode, uint *iolock);
+int xfs_break_leased_layouts(struct inode *inode, uint *iolock,
+ bool *did_unlock);
#else
static inline int
-xfs_break_layouts(struct inode *inode, uint *iolock)
+xfs_break_leased_layouts(struct inode *inode, uint *iolock, bool *did_unlock)
{
return 0;
}