summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/dir.c4
-rw-r--r--fs/afs/fs_probe.c39
-rw-r--r--fs/afs/inode.c18
-rw-r--r--fs/afs/internal.h9
-rw-r--r--fs/afs/misc.c52
-rw-r--r--fs/afs/rotate.c53
-rw-r--r--fs/afs/vl_probe.c45
-rw-r--r--fs/afs/vl_rotate.c50
-rw-r--r--fs/aio.c3
-rw-r--r--fs/btrfs/disk-io.c11
-rw-r--r--fs/btrfs/file.c24
-rw-r--r--fs/btrfs/qgroup.c3
-rw-r--r--fs/btrfs/relocation.c1
-rw-r--r--fs/btrfs/send.c11
-rw-r--r--fs/btrfs/super.c1
-rw-r--r--fs/btrfs/tree-checker.c8
-rw-r--r--fs/cachefiles/namei.c8
-rw-r--r--fs/cachefiles/rdwr.c9
-rw-r--r--fs/cachefiles/xattr.c3
-rw-r--r--fs/ceph/super.c4
-rw-r--r--fs/ceph/super.h4
-rw-r--r--fs/cifs/Kconfig2
-rw-r--r--fs/cifs/dir.c2
-rw-r--r--fs/cifs/file.c31
-rw-r--r--fs/cifs/smb2inode.c16
-rw-r--r--fs/cifs/smb2ops.c23
-rw-r--r--fs/cifs/smb2proto.h3
-rw-r--r--fs/dax.c55
-rw-r--r--fs/direct-io.c4
-rw-r--r--fs/exec.c5
-rw-r--r--fs/exportfs/expfs.c3
-rw-r--r--fs/ext2/super.c1
-rw-r--r--fs/ext2/xattr.c2
-rw-r--r--fs/fscache/object.c3
-rw-r--r--fs/fuse/dir.c26
-rw-r--r--fs/fuse/file.c64
-rw-r--r--fs/fuse/fuse_i.h4
-rw-r--r--fs/fuse/inode.c3
-rw-r--r--fs/hfs/btree.c3
-rw-r--r--fs/hfsplus/btree.c3
-rw-r--r--fs/iomap.c9
-rw-r--r--fs/namei.c3
-rw-r--r--fs/nfs/direct.c9
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c6
-rw-r--r--fs/ocfs2/export.c2
-rw-r--r--fs/ocfs2/move_extents.c47
-rw-r--r--fs/overlayfs/dir.c14
-rw-r--r--fs/overlayfs/export.c6
-rw-r--r--fs/overlayfs/inode.c17
-rw-r--r--fs/proc/proc_sysctl.c13
-rw-r--r--fs/pstore/ram.c15
-rw-r--r--fs/read_write.c2
-rw-r--r--fs/splice.c7
-rw-r--r--fs/sysv/inode.c2
-rw-r--r--fs/ubifs/Kconfig16
-rw-r--r--fs/ubifs/lpt.c12
-rw-r--r--fs/ubifs/replay.c72
-rw-r--r--fs/ubifs/sb.c13
-rw-r--r--fs/udf/super.c16
-rw-r--r--fs/udf/unicode.c14
-rw-r--r--fs/userfaultfd.c16
-rw-r--r--fs/xfs/libxfs/xfs_btree.c2
-rw-r--r--fs/xfs/xfs_bmap_util.c4
-rw-r--r--fs/xfs/xfs_qm_bhv.c2
64 files changed, 563 insertions, 369 deletions
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 43dea3b00c29..8a2562e3a316 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -1075,8 +1075,6 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc,
if (fc->ac.error < 0)
return;
- d_drop(new_dentry);
-
inode = afs_iget(fc->vnode->vfs_inode.i_sb, fc->key,
newfid, newstatus, newcb, fc->cbi);
if (IS_ERR(inode)) {
@@ -1090,7 +1088,7 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc,
vnode = AFS_FS_I(inode);
set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
afs_vnode_commit_status(fc, vnode, 0);
- d_add(new_dentry, inode);
+ d_instantiate(new_dentry, inode);
}
/*
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index d049cb459742..fde6b4d4121e 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -61,8 +61,11 @@ void afs_fileserver_probe_result(struct afs_call *call)
afs_io_error(call, afs_io_error_fs_probe_fail);
goto out;
case -ECONNRESET: /* Responded, but call expired. */
+ case -ERFKILL:
+ case -EADDRNOTAVAIL:
case -ENETUNREACH:
case -EHOSTUNREACH:
+ case -EHOSTDOWN:
case -ECONNREFUSED:
case -ETIMEDOUT:
case -ETIME:
@@ -132,12 +135,14 @@ out:
static int afs_do_probe_fileserver(struct afs_net *net,
struct afs_server *server,
struct key *key,
- unsigned int server_index)
+ unsigned int server_index,
+ struct afs_error *_e)
{
struct afs_addr_cursor ac = {
.index = 0,
};
- int ret;
+ bool in_progress = false;
+ int err;
_enter("%pU", &server->uuid);
@@ -151,15 +156,17 @@ static int afs_do_probe_fileserver(struct afs_net *net,
server->probe.rtt = UINT_MAX;
for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) {
- ret = afs_fs_get_capabilities(net, server, &ac, key, server_index,
+ err = afs_fs_get_capabilities(net, server, &ac, key, server_index,
true);
- if (ret != -EINPROGRESS) {
- afs_fs_probe_done(server);
- return ret;
- }
+ if (err == -EINPROGRESS)
+ in_progress = true;
+ else
+ afs_prioritise_error(_e, err, ac.abort_code);
}
- return 0;
+ if (!in_progress)
+ afs_fs_probe_done(server);
+ return in_progress;
}
/*
@@ -169,21 +176,23 @@ int afs_probe_fileservers(struct afs_net *net, struct key *key,
struct afs_server_list *list)
{
struct afs_server *server;
- int i, ret;
+ struct afs_error e;
+ bool in_progress = false;
+ int i;
+ e.error = 0;
+ e.responded = false;
for (i = 0; i < list->nr_servers; i++) {
server = list->servers[i].server;
if (test_bit(AFS_SERVER_FL_PROBED, &server->flags))
continue;
- if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags)) {
- ret = afs_do_probe_fileserver(net, server, key, i);
- if (ret)
- return ret;
- }
+ if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags) &&
+ afs_do_probe_fileserver(net, server, key, i, &e))
+ in_progress = true;
}
- return 0;
+ return in_progress ? 0 : e.error;
}
/*
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 4c6d8e1112c2..6b17d3620414 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -382,7 +382,7 @@ void afs_zap_data(struct afs_vnode *vnode)
int afs_validate(struct afs_vnode *vnode, struct key *key)
{
time64_t now = ktime_get_real_seconds();
- bool valid = false;
+ bool valid;
int ret;
_enter("{v={%llx:%llu} fl=%lx},%x",
@@ -402,15 +402,21 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
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;
- } else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) &&
- vnode->cb_expires_at - 10 > now) {
+ (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) ||
+ vnode->cb_expires_at - 10 <= now)) {
+ valid = false;
+ } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) ||
+ vnode->cb_expires_at - 10 <= now) {
+ valid = false;
+ } else {
valid = true;
}
} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
valid = true;
+ } else {
+ vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
+ vnode->cb_v_break = vnode->volume->cb_v_break;
+ valid = false;
}
read_sequnlock_excl(&vnode->cb_lock);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5da3b09b7518..8871b9e8645f 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -696,6 +696,14 @@ struct afs_interface {
};
/*
+ * Error prioritisation and accumulation.
+ */
+struct afs_error {
+ short error; /* Accumulated error */
+ bool responded; /* T if server responded */
+};
+
+/*
* Cursor for iterating over a server's address list.
*/
struct afs_addr_cursor {
@@ -1015,6 +1023,7 @@ static inline void __afs_stat(atomic_t *s)
* misc.c
*/
extern int afs_abort_to_error(u32);
+extern void afs_prioritise_error(struct afs_error *, int, u32);
/*
* mntpt.c
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 700a5fa7f4ec..bbb1fd51b019 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -118,3 +118,55 @@ int afs_abort_to_error(u32 abort_code)
default: return -EREMOTEIO;
}
}
+
+/*
+ * Select the error to report from a set of errors.
+ */
+void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code)
+{
+ switch (error) {
+ case 0:
+ return;
+ default:
+ if (e->error == -ETIMEDOUT ||
+ e->error == -ETIME)
+ return;
+ case -ETIMEDOUT:
+ case -ETIME:
+ if (e->error == -ENOMEM ||
+ e->error == -ENONET)
+ return;
+ case -ENOMEM:
+ case -ENONET:
+ if (e->error == -ERFKILL)
+ return;
+ case -ERFKILL:
+ if (e->error == -EADDRNOTAVAIL)
+ return;
+ case -EADDRNOTAVAIL:
+ if (e->error == -ENETUNREACH)
+ return;
+ case -ENETUNREACH:
+ if (e->error == -EHOSTUNREACH)
+ return;
+ case -EHOSTUNREACH:
+ if (e->error == -EHOSTDOWN)
+ return;
+ case -EHOSTDOWN:
+ if (e->error == -ECONNREFUSED)
+ return;
+ case -ECONNREFUSED:
+ if (e->error == -ECONNRESET)
+ return;
+ case -ECONNRESET: /* Responded, but call expired. */
+ if (e->responded)
+ return;
+ e->error = error;
+ return;
+
+ case -ECONNABORTED:
+ e->responded = true;
+ e->error = afs_abort_to_error(abort_code);
+ return;
+ }
+}
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 00504254c1c2..c3ae324781f8 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -136,7 +136,8 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
struct afs_addr_list *alist;
struct afs_server *server;
struct afs_vnode *vnode = fc->vnode;
- u32 rtt, abort_code;
+ struct afs_error e;
+ u32 rtt;
int error = fc->ac.error, i;
_enter("%lx[%d],%lx[%d],%d,%d",
@@ -306,8 +307,11 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
if (fc->error != -EDESTADDRREQ)
goto iterate_address;
/* Fall through */
+ case -ERFKILL:
+ case -EADDRNOTAVAIL:
case -ENETUNREACH:
case -EHOSTUNREACH:
+ case -EHOSTDOWN:
case -ECONNREFUSED:
_debug("no conn");
fc->error = error;
@@ -446,50 +450,15 @@ no_more_servers:
if (fc->flags & AFS_FS_CURSOR_VBUSY)
goto restart_from_beginning;
- abort_code = 0;
- error = -EDESTADDRREQ;
+ e.error = -EDESTADDRREQ;
+ e.responded = false;
for (i = 0; i < fc->server_list->nr_servers; i++) {
struct afs_server *s = fc->server_list->servers[i].server;
- int probe_error = READ_ONCE(s->probe.error);
- switch (probe_error) {
- case 0:
- continue;
- default:
- if (error == -ETIMEDOUT ||
- error == -ETIME)
- continue;
- case -ETIMEDOUT:
- case -ETIME:
- if (error == -ENOMEM ||
- error == -ENONET)
- continue;
- case -ENOMEM:
- case -ENONET:
- if (error == -ENETUNREACH)
- continue;
- case -ENETUNREACH:
- if (error == -EHOSTUNREACH)
- continue;
- case -EHOSTUNREACH:
- if (error == -ECONNREFUSED)
- continue;
- case -ECONNREFUSED:
- if (error == -ECONNRESET)
- continue;
- case -ECONNRESET: /* Responded, but call expired. */
- if (error == -ECONNABORTED)
- continue;
- case -ECONNABORTED:
- abort_code = s->probe.abort_code;
- error = probe_error;
- continue;
- }
+ afs_prioritise_error(&e, READ_ONCE(s->probe.error),
+ s->probe.abort_code);
}
- if (error == -ECONNABORTED)
- error = afs_abort_to_error(abort_code);
-
failed_set_error:
fc->error = error;
failed:
@@ -553,8 +522,11 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc)
_leave(" = f [abort]");
return false;
+ case -ERFKILL:
+ case -EADDRNOTAVAIL:
case -ENETUNREACH:
case -EHOSTUNREACH:
+ case -EHOSTDOWN:
case -ECONNREFUSED:
case -ETIMEDOUT:
case -ETIME:
@@ -633,6 +605,7 @@ int afs_end_vnode_operation(struct afs_fs_cursor *fc)
struct afs_net *net = afs_v2net(fc->vnode);
if (fc->error == -EDESTADDRREQ ||
+ fc->error == -EADDRNOTAVAIL ||
fc->error == -ENETUNREACH ||
fc->error == -EHOSTUNREACH)
afs_dump_edestaddrreq(fc);
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index c0f616bd70cb..f0b032976487 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -61,8 +61,11 @@ void afs_vlserver_probe_result(struct afs_call *call)
afs_io_error(call, afs_io_error_vl_probe_fail);
goto out;
case -ECONNRESET: /* Responded, but call expired. */
+ case -ERFKILL:
+ case -EADDRNOTAVAIL:
case -ENETUNREACH:
case -EHOSTUNREACH:
+ case -EHOSTDOWN:
case -ECONNREFUSED:
case -ETIMEDOUT:
case -ETIME:
@@ -129,15 +132,17 @@ out:
* Probe all of a vlserver's addresses to find out the best route and to
* query its capabilities.
*/
-static int afs_do_probe_vlserver(struct afs_net *net,
- struct afs_vlserver *server,
- struct key *key,
- unsigned int server_index)
+static bool afs_do_probe_vlserver(struct afs_net *net,
+ struct afs_vlserver *server,
+ struct key *key,
+ unsigned int server_index,
+ struct afs_error *_e)
{
struct afs_addr_cursor ac = {
.index = 0,
};
- int ret;
+ bool in_progress = false;
+ int err;
_enter("%s", server->name);
@@ -151,15 +156,17 @@ static int afs_do_probe_vlserver(struct afs_net *net,
server->probe.rtt = UINT_MAX;
for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) {
- ret = afs_vl_get_capabilities(net, &ac, key, server,
+ err = afs_vl_get_capabilities(net, &ac, key, server,
server_index, true);
- if (ret != -EINPROGRESS) {
- afs_vl_probe_done(server);
- return ret;
- }
+ if (err == -EINPROGRESS)
+ in_progress = true;
+ else
+ afs_prioritise_error(_e, err, ac.abort_code);
}
- return 0;
+ if (!in_progress)
+ afs_vl_probe_done(server);
+ return in_progress;
}
/*
@@ -169,21 +176,23 @@ int afs_send_vl_probes(struct afs_net *net, struct key *key,
struct afs_vlserver_list *vllist)
{
struct afs_vlserver *server;
- int i, ret;
+ struct afs_error e;
+ bool in_progress = false;
+ int i;
+ e.error = 0;
+ e.responded = false;
for (i = 0; i < vllist->nr_servers; i++) {
server = vllist->servers[i].server;
if (test_bit(AFS_VLSERVER_FL_PROBED, &server->flags))
continue;
- if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags)) {
- ret = afs_do_probe_vlserver(net, server, key, i);
- if (ret)
- return ret;
- }
+ if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags) &&
+ afs_do_probe_vlserver(net, server, key, i, &e))
+ in_progress = true;
}
- return 0;
+ return in_progress ? 0 : e.error;
}
/*
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index b64a284b99d2..7adde83a0648 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -71,8 +71,9 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
{
struct afs_addr_list *alist;
struct afs_vlserver *vlserver;
+ struct afs_error e;
u32 rtt;
- int error = vc->ac.error, abort_code, i;
+ int error = vc->ac.error, i;
_enter("%lx[%d],%lx[%d],%d,%d",
vc->untried, vc->index,
@@ -119,8 +120,11 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
goto failed;
}
+ case -ERFKILL:
+ case -EADDRNOTAVAIL:
case -ENETUNREACH:
case -EHOSTUNREACH:
+ case -EHOSTDOWN:
case -ECONNREFUSED:
case -ETIMEDOUT:
case -ETIME:
@@ -235,50 +239,15 @@ no_more_servers:
if (vc->flags & AFS_VL_CURSOR_RETRY)
goto restart_from_beginning;
- abort_code = 0;
- error = -EDESTADDRREQ;
+ e.error = -EDESTADDRREQ;
+ e.responded = false;
for (i = 0; i < vc->server_list->nr_servers; i++) {
struct afs_vlserver *s = vc->server_list->servers[i].server;
- int probe_error = READ_ONCE(s->probe.error);
- switch (probe_error) {
- case 0:
- continue;
- default:
- if (error == -ETIMEDOUT ||
- error == -ETIME)
- continue;
- case -ETIMEDOUT:
- case -ETIME:
- if (error == -ENOMEM ||
- error == -ENONET)
- continue;
- case -ENOMEM:
- case -ENONET:
- if (error == -ENETUNREACH)
- continue;
- case -ENETUNREACH:
- if (error == -EHOSTUNREACH)
- continue;
- case -EHOSTUNREACH:
- if (error == -ECONNREFUSED)
- continue;
- case -ECONNREFUSED:
- if (error == -ECONNRESET)
- continue;
- case -ECONNRESET: /* Responded, but call expired. */
- if (error == -ECONNABORTED)
- continue;
- case -ECONNABORTED:
- abort_code = s->probe.abort_code;
- error = probe_error;
- continue;
- }
+ afs_prioritise_error(&e, READ_ONCE(s->probe.error),
+ s->probe.abort_code);
}
- if (error == -ECONNABORTED)
- error = afs_abort_to_error(abort_code);
-
failed_set_error:
vc->error = error;
failed:
@@ -341,6 +310,7 @@ int afs_end_vlserver_operation(struct afs_vl_cursor *vc)
struct afs_net *net = vc->cell->net;
if (vc->error == -EDESTADDRREQ ||
+ vc->error == -EADDRNOTAVAIL ||
vc->error == -ENETUNREACH ||
vc->error == -EHOSTUNREACH)
afs_vl_dump_edestaddrreq(vc);
diff --git a/fs/aio.c b/fs/aio.c
index 301e6314183b..aac9659381d2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -45,6 +45,7 @@
#include <asm/kmap_types.h>
#include <linux/uaccess.h>
+#include <linux/nospec.h>
#include "internal.h"
@@ -1038,6 +1039,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
if (!table || id >= table->nr)
goto out;
+ id = array_index_nospec(id, table->nr);
ctx = rcu_dereference(table->table[id]);
if (ctx && ctx->user_id == ctx_id) {
if (percpu_ref_tryget_live(&ctx->users))
@@ -1436,6 +1438,7 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
ret = ioprio_check_cap(iocb->aio_reqprio);
if (ret) {
pr_debug("aio ioprio check cap error: %d\n", ret);
+ fput(req->ki_filp);
return ret;
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3f0b6d1936e8..6d776717d8b3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -477,9 +477,9 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
int mirror_num = 0;
int failed_mirror = 0;
- clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
while (1) {
+ clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
mirror_num);
if (!ret) {
@@ -493,15 +493,6 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
break;
}
- /*
- * This buffer's crc is fine, but its contents are corrupted, so
- * there is no reason to read the other copies, they won't be
- * any less wrong.
- */
- if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags) ||
- ret == -EUCLEAN)
- break;
-
num_copies = btrfs_num_copies(fs_info,
eb->start, eb->len);
if (num_copies == 1)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a3c22e16509b..58e93bce3036 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2089,6 +2089,30 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
atomic_inc(&root->log_batch);
/*
+ * Before we acquired the inode's lock, someone may have dirtied more
+ * pages in the target range. We need to make sure that writeback for
+ * any such pages does not start while we are logging the inode, because
+ * if it does, any of the following might happen when we are not doing a
+ * full inode sync:
+ *
+ * 1) We log an extent after its writeback finishes but before its
+ * checksums are added to the csum tree, leading to -EIO errors
+ * when attempting to read the extent after a log replay.
+ *
+ * 2) We can end up logging an extent before its writeback finishes.
+ * Therefore after the log replay we will have a file extent item
+ * pointing to an unwritten extent (and no data checksums as well).
+ *
+ * So trigger writeback for any eventual new dirty pages and then we
+ * wait for all ordered extents to complete below.
+ */
+ ret = start_ordered_ops(inode, start, end);
+ if (ret) {
+ inode_unlock(inode);
+ goto out;
+ }
+
+ /*
* We have to do this here to avoid the priority inversion of waiting on
* IO of a lower priority task while holding a transaciton open.
*/
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 45868fd76209..f70825af6438 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2659,7 +2659,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
int i;
u64 *i_qgroups;
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *quota_root = fs_info->quota_root;
+ struct btrfs_root *quota_root;
struct btrfs_qgroup *srcgroup;
struct btrfs_qgroup *dstgroup;
u32 level_size = 0;
@@ -2669,6 +2669,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
goto out;
+ quota_root = fs_info->quota_root;
if (!quota_root) {
ret = -EINVAL;
goto out;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 924116f654a1..a3f75b8926d4 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3959,6 +3959,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
restart:
if (update_backref_cache(trans, &rc->backref_cache)) {
btrfs_end_transaction(trans);
+ trans = NULL;
continue;
}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 094cc1444a90..5be83b5a1b43 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3340,7 +3340,8 @@ static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m)
kfree(m);
}
-static void tail_append_pending_moves(struct pending_dir_move *moves,
+static void tail_append_pending_moves(struct send_ctx *sctx,
+ struct pending_dir_move *moves,
struct list_head *stack)
{
if (list_empty(&moves->list)) {
@@ -3351,6 +3352,10 @@ static void tail_append_pending_moves(struct pending_dir_move *moves,
list_add_tail(&moves->list, stack);
list_splice_tail(&list, stack);
}
+ if (!RB_EMPTY_NODE(&moves->node)) {
+ rb_erase(&moves->node, &sctx->pending_dir_moves);
+ RB_CLEAR_NODE(&moves->node);
+ }
}
static int apply_children_dir_moves(struct send_ctx *sctx)
@@ -3365,7 +3370,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx)
return 0;
INIT_LIST_HEAD(&stack);
- tail_append_pending_moves(pm, &stack);
+ tail_append_pending_moves(sctx, pm, &stack);
while (!list_empty(&stack)) {
pm = list_first_entry(&stack, struct pending_dir_move, list);
@@ -3376,7 +3381,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx)
goto out;
pm = get_pending_dir_moves(sctx, parent_ino);
if (pm)
- tail_append_pending_moves(pm, &stack);
+ tail_append_pending_moves(sctx, pm, &stack);
}
return 0;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index cbc9d0d2c12d..645fc81e2a94 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2237,6 +2237,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
vol = memdup_user((void __user *)arg, sizeof(*vol));
if (IS_ERR(vol))
return PTR_ERR(vol);
+ vol->name[BTRFS_PATH_NAME_MAX] = '\0';
switch (cmd) {
case BTRFS_IOC_SCAN_DEV:
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index efcf89a8ba44..1a4e2b101ef2 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -389,13 +389,11 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info,
/*
* Here we don't really care about alignment since extent allocator can
- * handle it. We care more about the size, as if one block group is
- * larger than maximum size, it's must be some obvious corruption.
+ * handle it. We care more about the size.
*/
- if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+ if (key->offset == 0) {
block_group_err(fs_info, leaf, slot,
- "invalid block group size, have %llu expect (0, %llu]",
- key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+ "invalid block group size 0");
return -EUCLEAN;
}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 95983c744164..1645fcfd9691 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -244,11 +244,13 @@ wait_for_old_object:
ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags));
- cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_retry);
+ cache->cache.ops->put_object(&xobject->fscache,
+ (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_retry);
goto try_again;
requeue:
- cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo);
+ cache->cache.ops->put_object(&xobject->fscache,
+ (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_timeo);
_leave(" = -ETIMEDOUT");
return -ETIMEDOUT;
}
@@ -336,7 +338,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
try_again:
/* first step is to make up a grave dentry in the graveyard */
sprintf(nbuffer, "%08x%08x",
- (uint32_t) get_seconds(),
+ (uint32_t) ktime_get_real_seconds(),
(uint32_t) atomic_inc_return(&cache->gravecounter));
/* do the multiway lock magic */
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 40f7595aad10..8a577409d030 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -535,7 +535,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
netpage->index, cachefiles_gfp);
if (ret < 0) {
if (ret == -EEXIST) {
+ put_page(backpage);
+ backpage = NULL;
put_page(netpage);
+ netpage = NULL;
fscache_retrieval_complete(op, 1);
continue;
}
@@ -608,7 +611,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
netpage->index, cachefiles_gfp);
if (ret < 0) {
if (ret == -EEXIST) {
+ put_page(backpage);
+ backpage = NULL;
put_page(netpage);
+ netpage = NULL;
fscache_retrieval_complete(op, 1);
continue;
}
@@ -962,11 +968,8 @@ void cachefiles_uncache_page(struct fscache_object *_object, struct page *page)
__releases(&object->fscache.cookie->lock)
{
struct cachefiles_object *object;
- struct cachefiles_cache *cache;
object = container_of(_object, struct cachefiles_object, fscache);
- cache = container_of(object->fscache.cache,
- struct cachefiles_cache, cache);
_enter("%p,{%lu}", object, page->index);
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index 0a29a00aed2e..511e6c68156a 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -135,7 +135,8 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object,
struct dentry *dentry = object->dentry;
int ret;
- ASSERT(dentry);
+ if (!dentry)
+ return -ESTALE;
_enter("%p,#%d", object, auxdata->len);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index b5ecd6f50360..4e9a7cc488da 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -563,8 +563,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",noacl");
#endif
- if (fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM)
- seq_puts(m, ",nocopyfrom");
+ if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0)
+ seq_puts(m, ",copyfrom");
if (fsopt->mds_namespace)
seq_show_option(m, "mds_namespace", fsopt->mds_namespace);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index c005a5400f2e..79a265ba9200 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -42,7 +42,9 @@
#define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */
#define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */
-#define CEPH_MOUNT_OPT_DEFAULT CEPH_MOUNT_OPT_DCACHE
+#define CEPH_MOUNT_OPT_DEFAULT \
+ (CEPH_MOUNT_OPT_DCACHE | \
+ CEPH_MOUNT_OPT_NOCOPYFROM)
#define ceph_set_mount_opt(fsc, opt) \
(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index abcd78e332fe..85dadb93c992 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -133,7 +133,7 @@ config CIFS_XATTR
config CIFS_POSIX
bool "CIFS POSIX Extensions"
- depends on CIFS_XATTR
+ depends on CIFS && CIFS_ALLOW_INSECURE_LEGACY && CIFS_XATTR
help
Enabling this option will cause the cifs client to attempt to
negotiate a newer dialect with servers, such as Samba 3.0.5
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 3713d22b95a7..907e85d65bb4 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -174,7 +174,7 @@ cifs_bp_rename_retry:
cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath);
memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1);
- full_path[dfsplen] = '\\';
+ full_path[dfsplen] = dirsep;
for (i = 0; i < pplen-1; i++)
if (full_path[dfsplen+1+i] == '/')
full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 74c33d5fafc8..c9bc56b1baac 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2541,14 +2541,13 @@ static int
cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
struct cifs_aio_ctx *ctx)
{
- int wait_retry = 0;
unsigned int wsize, credits;
int rc;
struct TCP_Server_Info *server =
tlink_tcon(wdata->cfile->tlink)->ses->server;
/*
- * Try to resend this wdata, waiting for credits up to 3 seconds.
+ * Wait for credits to resend this wdata.
* Note: we are attempting to resend the whole wdata not in segments
*/
do {
@@ -2556,19 +2555,13 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
server, wdata->bytes, &wsize, &credits);
if (rc)
- break;
+ goto out;
if (wsize < wdata->bytes) {
add_credits_and_wake_if(server, credits, 0);
msleep(1000);
- wait_retry++;
}
- } while (wsize < wdata->bytes && wait_retry < 3);
-
- if (wsize < wdata->bytes) {
- rc = -EBUSY;
- goto out;
- }
+ } while (wsize < wdata->bytes);
rc = -EAGAIN;
while (rc == -EAGAIN) {
@@ -3234,14 +3227,13 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata,
struct list_head *rdata_list,
struct cifs_aio_ctx *ctx)
{
- int wait_retry = 0;
unsigned int rsize, credits;
int rc;
struct TCP_Server_Info *server =
tlink_tcon(rdata->cfile->tlink)->ses->server;
/*
- * Try to resend this rdata, waiting for credits up to 3 seconds.
+ * Wait for credits to resend this rdata.
* Note: we are attempting to resend the whole rdata not in segments
*/
do {
@@ -3249,24 +3241,13 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata,
&rsize, &credits);
if (rc)
- break;
+ goto out;
if (rsize < rdata->bytes) {
add_credits_and_wake_if(server, credits, 0);
msleep(1000);
- wait_retry++;
}
- } while (rsize < rdata->bytes && wait_retry < 3);
-
- /*
- * If we can't find enough credits to send this rdata
- * release the rdata and return failure, this will pass
- * whatever I/O amount we have finished to VFS.
- */
- if (rsize < rdata->bytes) {
- rc = -EBUSY;
- goto out;
- }
+ } while (rsize < rdata->bytes);
rc = -EAGAIN;
while (rc == -EAGAIN) {
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 9e7ef7ec2d70..a8999f930b22 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -97,7 +97,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
goto finished;
- smb2_set_next_command(server, &rqst[num_rqst++]);
+ smb2_set_next_command(server, &rqst[num_rqst++], 0);
/* Operation */
switch (command) {
@@ -111,7 +111,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
SMB2_O_INFO_FILE, 0,
sizeof(struct smb2_file_all_info) +
PATH_MAX * 2, 0, NULL);
- smb2_set_next_command(server, &rqst[num_rqst]);
+ smb2_set_next_command(server, &rqst[num_rqst], 0);
smb2_set_related(&rqst[num_rqst++]);
break;
case SMB2_OP_DELETE:
@@ -127,14 +127,14 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
rqst[num_rqst].rq_iov = si_iov;
rqst[num_rqst].rq_nvec = 1;
- size[0] = 8;
+ size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */
data[0] = &delete_pending[0];
rc = SMB2_set_info_init(tcon, &rqst[num_rqst], COMPOUND_FID,
COMPOUND_FID, current->tgid,
FILE_DISPOSITION_INFORMATION,
SMB2_O_INFO_FILE, 0, data, size);
- smb2_set_next_command(server, &rqst[num_rqst]);
+ smb2_set_next_command(server, &rqst[num_rqst], 1);
smb2_set_related(&rqst[num_rqst++]);
break;
case SMB2_OP_SET_EOF:
@@ -149,7 +149,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
COMPOUND_FID, current->tgid,
FILE_END_OF_FILE_INFORMATION,
SMB2_O_INFO_FILE, 0, data, size);
- smb2_set_next_command(server, &rqst[num_rqst]);
+ smb2_set_next_command(server, &rqst[num_rqst], 0);
smb2_set_related(&rqst[num_rqst++]);
break;
case SMB2_OP_SET_INFO:
@@ -165,7 +165,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
COMPOUND_FID, current->tgid,
FILE_BASIC_INFORMATION,
SMB2_O_INFO_FILE, 0, data, size);
- smb2_set_next_command(server, &rqst[num_rqst]);
+ smb2_set_next_command(server, &rqst[num_rqst], 0);
smb2_set_related(&rqst[num_rqst++]);
break;
case SMB2_OP_RENAME:
@@ -189,7 +189,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
COMPOUND_FID, current->tgid,
FILE_RENAME_INFORMATION,
SMB2_O_INFO_FILE, 0, data, size);
- smb2_set_next_command(server, &rqst[num_rqst]);
+ smb2_set_next_command(server, &rqst[num_rqst], 0);
smb2_set_related(&rqst[num_rqst++]);
break;
case SMB2_OP_HARDLINK:
@@ -213,7 +213,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
COMPOUND_FID, current->tgid,
FILE_LINK_INFORMATION,
SMB2_O_INFO_FILE, 0, data, size);
- smb2_set_next_command(server, &rqst[num_rqst]);
+ smb2_set_next_command(server, &rqst[num_rqst], 0);
smb2_set_related(&rqst[num_rqst++]);
break;
default:
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 225fec1cfa67..e25c7aade98a 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1194,7 +1194,7 @@ smb2_ioctl_query_info(const unsigned int xid,
rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, path);
if (rc)
goto iqinf_exit;
- smb2_set_next_command(ses->server, &rqst[0]);
+ smb2_set_next_command(ses->server, &rqst[0], 0);
/* Query */
memset(&qi_iov, 0, sizeof(qi_iov));
@@ -1208,7 +1208,7 @@ smb2_ioctl_query_info(const unsigned int xid,
qi.output_buffer_length, buffer);
if (rc)
goto iqinf_exit;
- smb2_set_next_command(ses->server, &rqst[1]);
+ smb2_set_next_command(ses->server, &rqst[1], 0);
smb2_set_related(&rqst[1]);
/* Close */
@@ -1761,16 +1761,23 @@ smb2_set_related(struct smb_rqst *rqst)
char smb2_padding[7] = {0, 0, 0, 0, 0, 0, 0};
void
-smb2_set_next_command(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+smb2_set_next_command(struct TCP_Server_Info *server, struct smb_rqst *rqst,
+ bool has_space_for_padding)
{
struct smb2_sync_hdr *shdr;
unsigned long len = smb_rqst_len(server, rqst);
/* SMB headers in a compound are 8 byte aligned. */
if (len & 7) {
- rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding;
- rqst->rq_iov[rqst->rq_nvec].iov_len = 8 - (len & 7);
- rqst->rq_nvec++;
+ if (has_space_for_padding) {
+ len = rqst->rq_iov[rqst->rq_nvec - 1].iov_len;
+ rqst->rq_iov[rqst->rq_nvec - 1].iov_len =
+ (len + 7) & ~7;
+ } else {
+ rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding;
+ rqst->rq_iov[rqst->rq_nvec].iov_len = 8 - (len & 7);
+ rqst->rq_nvec++;
+ }
len = smb_rqst_len(server, rqst);
}
@@ -1820,7 +1827,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, &srch_path);
if (rc)
goto qfs_exit;
- smb2_set_next_command(server, &rqst[0]);
+ smb2_set_next_command(server, &rqst[0], 0);
memset(&qi_iov, 0, sizeof(qi_iov));
rqst[1].rq_iov = qi_iov;
@@ -1833,7 +1840,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
NULL);
if (rc)
goto qfs_exit;
- smb2_set_next_command(server, &rqst[1]);
+ smb2_set_next_command(server, &rqst[1], 0);
smb2_set_related(&rqst[1]);
memset(&close_iov, 0, sizeof(close_iov));
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 9f4e9ed9ce53..2fe78acd7d0c 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -117,7 +117,8 @@ extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server);
extern unsigned long smb_rqst_len(struct TCP_Server_Info *server,
struct smb_rqst *rqst);
extern void smb2_set_next_command(struct TCP_Server_Info *server,
- struct smb_rqst *rqst);
+ struct smb_rqst *rqst,
+ bool has_space_for_padding);
extern void smb2_set_related(struct smb_rqst *rqst);
/*
diff --git a/fs/dax.c b/fs/dax.c
index 9bcce89ea18e..48132eca3761 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -232,6 +232,34 @@ static void *get_unlocked_entry(struct xa_state *xas)
}
}
+/*
+ * The only thing keeping the address space around is the i_pages lock
+ * (it's cycled in clear_inode() after removing the entries from i_pages)
+ * After we call xas_unlock_irq(), we cannot touch xas->xa.
+ */
+static void wait_entry_unlocked(struct xa_state *xas, void *entry)
+{
+ struct wait_exceptional_entry_queue ewait;
+ wait_queue_head_t *wq;
+
+ init_wait(&ewait.wait);
+ ewait.wait.func = wake_exceptional_entry_func;
+
+ wq = dax_entry_waitqueue(xas, entry, &ewait.key);
+ prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
+ xas_unlock_irq(xas);
+ schedule();
+ finish_wait(wq, &ewait.wait);
+
+ /*
+ * Entry lock waits are exclusive. Wake up the next waiter since
+ * we aren't sure we will acquire the entry lock and thus wake
+ * the next waiter up on unlock.
+ */
+ if (waitqueue_active(wq))
+ __wake_up(wq, TASK_NORMAL, 1, &ewait.key);
+}
+
static void put_unlocked_entry(struct xa_state *xas, void *entry)
{
/* If we were the only waiter woken, wake the next one */
@@ -351,21 +379,21 @@ static struct page *dax_busy_page(void *entry)
* @page: The page whose entry we want to lock
*
* Context: Process context.
- * Return: %true if the entry was locked or does not need to be locked.
+ * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could
+ * not be locked.
*/
-bool dax_lock_mapping_entry(struct page *page)
+dax_entry_t dax_lock_page(struct page *page)
{
XA_STATE(xas, NULL, 0);
void *entry;
- bool locked;
/* Ensure page->mapping isn't freed while we look at it */
rcu_read_lock();
for (;;) {
struct address_space *mapping = READ_ONCE(page->mapping);
- locked = false;
- if (!dax_mapping(mapping))
+ entry = NULL;
+ if (!mapping || !dax_mapping(mapping))
break;
/*
@@ -375,7 +403,7 @@ bool dax_lock_mapping_entry(struct page *page)
* otherwise we would not have a valid pfn_to_page()
* translation.
*/
- locked = true;
+ entry = (void *)~0UL;
if (S_ISCHR(mapping->host->i_mode))
break;
@@ -389,9 +417,7 @@ bool dax_lock_mapping_entry(struct page *page)
entry = xas_load(&xas);
if (dax_is_locked(entry)) {
rcu_read_unlock();
- entry = get_unlocked_entry(&xas);
- xas_unlock_irq(&xas);
- put_unlocked_entry(&xas, entry);
+ wait_entry_unlocked(&xas, entry);
rcu_read_lock();
continue;
}
@@ -400,23 +426,18 @@ bool dax_lock_mapping_entry(struct page *page)
break;
}
rcu_read_unlock();
- return locked;
+ return (dax_entry_t)entry;
}
-void dax_unlock_mapping_entry(struct page *page)
+void dax_unlock_page(struct page *page, dax_entry_t cookie)
{
struct address_space *mapping = page->mapping;
XA_STATE(xas, &mapping->i_pages, page->index);
- void *entry;
if (S_ISCHR(mapping->host->i_mode))
return;
- rcu_read_lock();
- entry = xas_load(&xas);
- rcu_read_unlock();
- entry = dax_make_entry(page_to_pfn_t(page), dax_is_pmd_entry(entry));
- dax_unlock_entry(&xas, entry);
+ dax_unlock_entry(&xas, (void *)cookie);
}
/*
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 722d17c88edb..41a0e97252ae 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -325,8 +325,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
*/
dio->iocb->ki_pos += transferred;
- if (dio->op == REQ_OP_WRITE)
- ret = generic_write_sync(dio->iocb, transferred);
+ if (ret > 0 && dio->op == REQ_OP_WRITE)
+ ret = generic_write_sync(dio->iocb, ret);
dio->iocb->ki_complete(dio->iocb, ret, 0);
}
diff --git a/fs/exec.c b/fs/exec.c
index acc3a5536384..fc281b738a98 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -62,7 +62,6 @@
#include <linux/oom.h>
#include <linux/compat.h>
#include <linux/vmalloc.h>
-#include <linux/freezer.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -1084,7 +1083,7 @@ static int de_thread(struct task_struct *tsk)
while (sig->notify_count) {
__set_current_state(TASK_KILLABLE);
spin_unlock_irq(lock);
- freezable_schedule();
+ schedule();
if (unlikely(__fatal_signal_pending(tsk)))
goto killed;
spin_lock_irq(lock);
@@ -1112,7 +1111,7 @@ static int de_thread(struct task_struct *tsk)
__set_current_state(TASK_KILLABLE);
write_unlock_irq(&tasklist_lock);
cgroup_threadgroup_change_end(tsk);
- freezable_schedule();
+ schedule();
if (unlikely(__fatal_signal_pending(tsk)))
goto killed;
}
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 645158dc33f1..c69927bed4ef 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -77,7 +77,7 @@ static bool dentry_connected(struct dentry *dentry)
struct dentry *parent = dget_parent(dentry);
dput(dentry);
- if (IS_ROOT(dentry)) {
+ if (dentry == parent) {
dput(parent);
return false;
}
@@ -147,6 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt,
tmp = lookup_one_len_unlocked(nbuf, parent, strlen(nbuf));
if (IS_ERR(tmp)) {
dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
+ err = PTR_ERR(tmp);
goto out_err;
}
if (tmp != dentry) {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index cb91baa4275d..eb11502e3fcd 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -892,6 +892,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (sb->s_magic != EXT2_SUPER_MAGIC)
goto cantfind_ext2;
+ opts.s_mount_opt = 0;
/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
if (def_mount_opts & EXT2_DEFM_DEBUG)
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 62d9a659a8ff..dd8f10db82e9 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -612,9 +612,9 @@ skip_replace:
}
cleanup:
- brelse(bh);
if (!(bh && header == HDR(bh)))
kfree(header);
+ brelse(bh);
up_write(&EXT2_I(inode)->xattr_sem);
return error;
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 9edc920f651f..6d9cb1719de5 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -730,6 +730,9 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob
if (awaken)
wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+ if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
+ wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+
/* Prevent a race with our last child, which has to signal EV_CLEARED
* before dropping our spinlock.
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 47395b0c3b35..e909678afa2d 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1119,8 +1119,10 @@ static int fuse_permission(struct inode *inode, int mask)
if (fc->default_permissions ||
((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
struct fuse_inode *fi = get_fuse_inode(inode);
+ u32 perm_mask = STATX_MODE | STATX_UID | STATX_GID;
- if (time_before64(fi->i_time, get_jiffies_64())) {
+ if (perm_mask & READ_ONCE(fi->inval_mask) ||
+ time_before64(fi->i_time, get_jiffies_64())) {
refreshed = true;
err = fuse_perm_getattr(inode, mask);
@@ -1241,7 +1243,7 @@ static int fuse_dir_open(struct inode *inode, struct file *file)
static int fuse_dir_release(struct inode *inode, struct file *file)
{
- fuse_release_common(file, FUSE_RELEASEDIR);
+ fuse_release_common(file, true);
return 0;
}
@@ -1249,7 +1251,25 @@ static int fuse_dir_release(struct inode *inode, struct file *file)
static int fuse_dir_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
- return fuse_fsync_common(file, start, end, datasync, 1);
+ struct inode *inode = file->f_mapping->host;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ int err;
+
+ if (is_bad_inode(inode))
+ return -EIO;
+
+ if (fc->no_fsyncdir)
+ return 0;
+
+ inode_lock(inode);
+ err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNCDIR);
+ if (err == -ENOSYS) {
+ fc->no_fsyncdir = 1;
+ err = 0;
+ }
+ inode_unlock(inode);
+
+ return err;
}
static long fuse_dir_ioctl(struct file *file, unsigned int cmd,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b52f9baaa3e7..ffaffe18352a 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -89,12 +89,12 @@ static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
iput(req->misc.release.inode);
}
-static void fuse_file_put(struct fuse_file *ff, bool sync)
+static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir)
{
if (refcount_dec_and_test(&ff->count)) {
struct fuse_req *req = ff->reserved_req;
- if (ff->fc->no_open) {
+ if (ff->fc->no_open && !isdir) {
/*
* Drop the release request when client does not
* implement 'open'
@@ -247,10 +247,11 @@ static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode)
req->in.args[0].value = inarg;
}
-void fuse_release_common(struct file *file, int opcode)
+void fuse_release_common(struct file *file, bool isdir)
{
struct fuse_file *ff = file->private_data;
struct fuse_req *req = ff->reserved_req;
+ int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE;
fuse_prepare_release(ff, file->f_flags, opcode);
@@ -272,7 +273,7 @@ void fuse_release_common(struct file *file, int opcode)
* synchronous RELEASE is allowed (and desirable) in this case
* because the server can be trusted not to screw up.
*/
- fuse_file_put(ff, ff->fc->destroy_req != NULL);
+ fuse_file_put(ff, ff->fc->destroy_req != NULL, isdir);
}
static int fuse_open(struct inode *inode, struct file *file)
@@ -288,7 +289,7 @@ static int fuse_release(struct inode *inode, struct file *file)
if (fc->writeback_cache)
write_inode_now(inode, 1);
- fuse_release_common(file, FUSE_RELEASE);
+ fuse_release_common(file, false);
/* return value is ignored by VFS */
return 0;
@@ -302,7 +303,7 @@ void fuse_sync_release(struct fuse_file *ff, int flags)
* iput(NULL) is a no-op and since the refcount is 1 and everything's
* synchronous, we are fine with not doing igrab() here"
*/
- fuse_file_put(ff, true);
+ fuse_file_put(ff, true, false);
}
EXPORT_SYMBOL_GPL(fuse_sync_release);
@@ -441,13 +442,30 @@ static int fuse_flush(struct file *file, fl_owner_t id)
}
int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
- int datasync, int isdir)
+ int datasync, int opcode)
{
struct inode *inode = file->f_mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_file *ff = file->private_data;
FUSE_ARGS(args);
struct fuse_fsync_in inarg;
+
+ memset(&inarg, 0, sizeof(inarg));
+ inarg.fh = ff->fh;
+ inarg.fsync_flags = datasync ? 1 : 0;
+ args.in.h.opcode = opcode;
+ args.in.h.nodeid = get_node_id(inode);
+ args.in.numargs = 1;
+ args.in.args[0].size = sizeof(inarg);
+ args.in.args[0].value = &inarg;
+ return fuse_simple_request(fc, &args);
+}
+
+static int fuse_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync)
+{
+ struct inode *inode = file->f_mapping->host;
+ struct fuse_conn *fc = get_fuse_conn(inode);
int err;
if (is_bad_inode(inode))
@@ -479,34 +497,18 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
if (err)
goto out;
- if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir))
+ if (fc->no_fsync)
goto out;
- memset(&inarg, 0, sizeof(inarg));
- inarg.fh = ff->fh;
- inarg.fsync_flags = datasync ? 1 : 0;
- args.in.h.opcode = isdir ? FUSE_FSYNCDIR : FUSE_FSYNC;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 1;
- args.in.args[0].size = sizeof(inarg);
- args.in.args[0].value = &inarg;
- err = fuse_simple_request(fc, &args);
+ err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNC);
if (err == -ENOSYS) {
- if (isdir)
- fc->no_fsyncdir = 1;
- else
- fc->no_fsync = 1;
+ fc->no_fsync = 1;
err = 0;
}
out:
inode_unlock(inode);
- return err;
-}
-static int fuse_fsync(struct file *file, loff_t start, loff_t end,
- int datasync)
-{
- return fuse_fsync_common(file, start, end, datasync, 0);
+ return err;
}
void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
@@ -807,7 +809,7 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
put_page(page);
}
if (req->ff)
- fuse_file_put(req->ff, false);
+ fuse_file_put(req->ff, false, false);
}
static void fuse_send_readpages(struct fuse_req *req, struct file *file)
@@ -1460,7 +1462,7 @@ static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req)
__free_page(req->pages[i]);
if (req->ff)
- fuse_file_put(req->ff, false);
+ fuse_file_put(req->ff, false, false);
}
static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
@@ -1619,7 +1621,7 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc)
ff = __fuse_write_file_get(fc, fi);
err = fuse_flush_times(inode, ff);
if (ff)
- fuse_file_put(ff, 0);
+ fuse_file_put(ff, false, false);
return err;
}
@@ -1940,7 +1942,7 @@ static int fuse_writepages(struct address_space *mapping,
err = 0;
}
if (data.ff)
- fuse_file_put(data.ff, false);
+ fuse_file_put(data.ff, false, false);
kfree(data.orig_pages);
out:
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index e9f712e81c7d..2f2c92e6f8cb 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -822,13 +822,13 @@ void fuse_sync_release(struct fuse_file *ff, int flags);
/**
* Send RELEASE or RELEASEDIR request
*/
-void fuse_release_common(struct file *file, int opcode);
+void fuse_release_common(struct file *file, bool isdir);
/**
* Send FSYNC or FSYNCDIR request
*/
int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
- int datasync, int isdir);
+ int datasync, int opcode);
/**
* Notify poll wakeup
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 0b94b23b02d4..568abed20eb2 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -115,7 +115,7 @@ static void fuse_i_callback(struct rcu_head *head)
static void fuse_destroy_inode(struct inode *inode)
{
struct fuse_inode *fi = get_fuse_inode(inode);
- if (S_ISREG(inode->i_mode)) {
+ if (S_ISREG(inode->i_mode) && !is_bad_inode(inode)) {
WARN_ON(!list_empty(&fi->write_files));
WARN_ON(!list_empty(&fi->queued_writes));
}
@@ -1068,6 +1068,7 @@ void fuse_dev_free(struct fuse_dev *fud)
fuse_conn_put(fc);
}
+ kfree(fud->pq.processing);
kfree(fud);
}
EXPORT_SYMBOL_GPL(fuse_dev_free);
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 98b96ffb95ed..19017d296173 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -338,13 +338,14 @@ void hfs_bmap_free(struct hfs_bnode *node)
nidx -= len * 8;
i = node->next;
- hfs_bnode_put(node);
if (!i) {
/* panic */;
pr_crit("unable to free bnode %u. bmap not found!\n",
node->this);
+ hfs_bnode_put(node);
return;
}
+ hfs_bnode_put(node);
node = hfs_bnode_find(tree, i);
if (IS_ERR(node))
return;
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 236efe51eca6..66774f4cb4fd 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -466,14 +466,15 @@ void hfs_bmap_free(struct hfs_bnode *node)
nidx -= len * 8;
i = node->next;
- hfs_bnode_put(node);
if (!i) {
/* panic */;
pr_crit("unable to free bnode %u. "
"bmap not found!\n",
node->this);
+ hfs_bnode_put(node);
return;
}
+ hfs_bnode_put(node);
node = hfs_bnode_find(tree, i);
if (IS_ERR(node))
return;
diff --git a/fs/iomap.c b/fs/iomap.c
index 3ffb776fbebe..d6bc98ae8d35 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1877,15 +1877,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
dio->wait_for_completion = true;
ret = 0;
}
-
- /*
- * Splicing to pipes can fail on a full pipe. We have to
- * swallow this to make it look like a short IO
- * otherwise the higher splice layers will completely
- * mishandle the error and stop moving data.
- */
- if (ret == -EFAULT)
- ret = 0;
break;
}
pos += ret;
diff --git a/fs/namei.c b/fs/namei.c
index 0cab6494978c..914178cdbe94 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3701,8 +3701,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
if (error)
return error;
- if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
- !ns_capable(dentry->d_sb->s_user_ns, CAP_MKNOD))
+ if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
return -EPERM;
if (!dir->i_op->mknod)
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index aa12c3063bae..33824a0a57bf 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -98,8 +98,11 @@ struct nfs_direct_req {
struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */
struct work_struct work;
int flags;
+ /* for write */
#define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */
#define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */
+ /* for read */
+#define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */
struct nfs_writeverf verf; /* unstable write verifier */
};
@@ -412,7 +415,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
struct nfs_page *req = nfs_list_entry(hdr->pages.next);
struct page *page = req->wb_page;
- if (!PageCompound(page) && bytes < hdr->good_bytes)
+ if (!PageCompound(page) && bytes < hdr->good_bytes &&
+ (dreq->flags == NFS_ODIRECT_SHOULD_DIRTY))
set_page_dirty(page);
bytes += req->wb_bytes;
nfs_list_remove_request(req);
@@ -587,6 +591,9 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
if (!is_sync_kiocb(iocb))
dreq->iocb = iocb;
+ if (iter_is_iovec(iter))
+ dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;
+
nfs_start_io_direct(inode);
NFS_I(inode)->read_io += count;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 74b36ed883ca..310d7500f665 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1733,7 +1733,8 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
if (fh)
hdr->args.fh = fh;
- if (!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
+ if (vers == 4 &&
+ !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
goto out_failed;
/*
@@ -1798,7 +1799,8 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
if (fh)
hdr->args.fh = fh;
- if (!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
+ if (vers == 4 &&
+ !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
goto out_failed;
/*
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 9f88188060db..4bf8d5854b27 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -125,10 +125,10 @@ check_err:
check_gen:
if (handle->ih_generation != inode->i_generation) {
- iput(inode);
trace_ocfs2_get_dentry_generation((unsigned long long)blkno,
handle->ih_generation,
inode->i_generation);
+ iput(inode);
result = ERR_PTR(-ESTALE);
goto bail;
}
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 3f1685d7d43b..1565dd8e8856 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -157,18 +157,14 @@ out:
}
/*
- * lock allocators, and reserving appropriate number of bits for
- * meta blocks and data clusters.
- *
- * in some cases, we don't need to reserve clusters, just let data_ac
- * be NULL.
+ * lock allocator, and reserve appropriate number of bits for
+ * meta blocks.
*/
-static int ocfs2_lock_allocators_move_extents(struct inode *inode,
+static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode,
struct ocfs2_extent_tree *et,
u32 clusters_to_move,
u32 extents_to_split,
struct ocfs2_alloc_context **meta_ac,
- struct ocfs2_alloc_context **data_ac,
int extra_blocks,
int *credits)
{
@@ -193,13 +189,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode,
goto out;
}
- if (data_ac) {
- ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
- }
*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el);
@@ -259,10 +248,10 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
}
}
- ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1,
- &context->meta_ac,
- &context->data_ac,
- extra_blocks, &credits);
+ ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+ *len, 1,
+ &context->meta_ac,
+ extra_blocks, &credits);
if (ret) {
mlog_errno(ret);
goto out;
@@ -285,6 +274,21 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
}
}
+ /*
+ * Make sure ocfs2_reserve_cluster is called after
+ * __ocfs2_flush_truncate_log, otherwise, dead lock may happen.
+ *
+ * If ocfs2_reserve_cluster is called
+ * before __ocfs2_flush_truncate_log, dead lock on global bitmap
+ * may happen.
+ *
+ */
+ ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac);
+ if (ret) {
+ mlog_errno(ret);
+ goto out_unlock_mutex;
+ }
+
handle = ocfs2_start_trans(osb, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
@@ -617,9 +621,10 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
}
}
- ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
- &context->meta_ac,
- NULL, extra_blocks, &credits);
+ ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+ len, 1,
+ &context->meta_ac,
+ extra_blocks, &credits);
if (ret) {
mlog_errno(ret);
goto out;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index c6289147c787..82c129bfe58d 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -651,6 +651,18 @@ static int ovl_symlink(struct inode *dir, struct dentry *dentry,
return ovl_create_object(dentry, S_IFLNK, 0, link);
}
+static int ovl_set_link_redirect(struct dentry *dentry)
+{
+ const struct cred *old_cred;
+ int err;
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ err = ovl_set_redirect(dentry, false);
+ revert_creds(old_cred);
+
+ return err;
+}
+
static int ovl_link(struct dentry *old, struct inode *newdir,
struct dentry *new)
{
@@ -670,7 +682,7 @@ static int ovl_link(struct dentry *old, struct inode *newdir,
goto out_drop_write;
if (ovl_is_metacopy_dentry(old)) {
- err = ovl_set_redirect(old, false);
+ err = ovl_set_link_redirect(old);
if (err)
goto out_drop_write;
}
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 8fa37cd7818a..54e5d17d7f3e 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -754,9 +754,8 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb,
goto out;
}
- /* Otherwise, get a connected non-upper dir or disconnected non-dir */
- if (d_is_dir(origin.dentry) &&
- (origin.dentry->d_flags & DCACHE_DISCONNECTED)) {
+ /* Find origin.dentry again with ovl_acceptable() layer check */
+ if (d_is_dir(origin.dentry)) {
dput(origin.dentry);
origin.dentry = NULL;
err = ovl_check_origin_fh(ofs, fh, true, NULL, &stack);
@@ -769,6 +768,7 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb,
goto out_err;
}
+ /* Get a connected non-upper dir or disconnected non-dir */
dentry = ovl_get_dentry(sb, NULL, &origin, index);
out:
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 6bcc9dedc342..3b7ed5d2279c 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -286,22 +286,13 @@ int ovl_permission(struct inode *inode, int mask)
if (err)
return err;
- /* No need to do any access on underlying for special files */
- if (special_file(realinode->i_mode))
- return 0;
-
- /* No need to access underlying for execute */
- mask &= ~MAY_EXEC;
- if ((mask & (MAY_READ | MAY_WRITE)) == 0)
- return 0;
-
- /* Lower files get copied up, so turn write access into read */
- if (!upperinode && mask & MAY_WRITE) {
+ old_cred = ovl_override_creds(inode->i_sb);
+ if (!upperinode &&
+ !special_file(realinode->i_mode) && mask & MAY_WRITE) {
mask &= ~(MAY_WRITE | MAY_APPEND);
+ /* Make sure mounter can read file for copy up later */
mask |= MAY_READ;
}
-
- old_cred = ovl_override_creds(inode->i_sb);
err = inode_permission(realinode, mask);
revert_creds(old_cred);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 89921a0d2ebb..4d598a399bbf 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -464,7 +464,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
inode = new_inode(sb);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOMEM);
inode->i_ino = get_next_ino();
@@ -474,8 +474,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
if (unlikely(head->unregistering)) {
spin_unlock(&sysctl_lock);
iput(inode);
- inode = NULL;
- goto out;
+ return ERR_PTR(-ENOENT);
}
ei->sysctl = head;
ei->sysctl_entry = table;
@@ -500,7 +499,6 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
if (root->set_ownership)
root->set_ownership(head, table, &inode->i_uid, &inode->i_gid);
-out:
return inode;
}
@@ -549,10 +547,11 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- err = ERR_PTR(-ENOMEM);
inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
- if (!inode)
+ if (IS_ERR(inode)) {
+ err = ERR_CAST(inode);
goto out;
+ }
d_set_d_op(dentry, &proc_sys_dentry_operations);
err = d_splice_alias(inode, dentry);
@@ -685,7 +684,7 @@ static bool proc_sys_fill_cache(struct file *file,
if (d_in_lookup(child)) {
struct dentry *res;
inode = proc_sys_make_inode(dir->d_sb, head, table);
- if (!inode) {
+ if (IS_ERR(inode)) {
d_lookup_done(child);
dput(child);
return false;
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index ffcff6516e89..e02a9039b5ea 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -816,17 +816,14 @@ static int ramoops_probe(struct platform_device *pdev)
cxt->pstore.data = cxt;
/*
- * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we
- * have to handle dumps, we must have at least record_size buffer. And
- * for ftrace, bufsize is irrelevant (if bufsize is 0, buf will be
- * ZERO_SIZE_PTR).
+ * Since bufsize is only used for dmesg crash dumps, it
+ * must match the size of the dprz record (after PRZ header
+ * and ECC bytes have been accounted for).
*/
- if (cxt->console_size)
- cxt->pstore.bufsize = 1024; /* LOG_LINE_MAX */
- cxt->pstore.bufsize = max(cxt->record_size, cxt->pstore.bufsize);
- cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL);
+ cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size;
+ cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL);
if (!cxt->pstore.buf) {
- pr_err("cannot allocate pstore buffer\n");
+ pr_err("cannot allocate pstore crash dump buffer\n");
err = -ENOMEM;
goto fail_clear;
}
diff --git a/fs/read_write.c b/fs/read_write.c
index 4dae0399c75a..58f30537c47a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1956,7 +1956,7 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
struct inode *inode_out = file_inode(file_out);
loff_t ret;
- WARN_ON_ONCE(remap_flags);
+ WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
diff --git a/fs/splice.c b/fs/splice.c
index 3553f1956508..de2ede048473 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -945,11 +945,16 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
sd->flags &= ~SPLICE_F_NONBLOCK;
more = sd->flags & SPLICE_F_MORE;
+ WARN_ON_ONCE(pipe->nrbufs != 0);
+
while (len) {
size_t read_len;
loff_t pos = sd->pos, prev_pos = pos;
- ret = do_splice_to(in, &pos, pipe, len, flags);
+ /* Don't try to read more the pipe has space for. */
+ read_len = min_t(size_t, len,
+ (pipe->buffers - pipe->nrbufs) << PAGE_SHIFT);
+ ret = do_splice_to(in, &pos, pipe, read_len, flags);
if (unlikely(ret <= 0))
goto out_release;
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 499a20a5a010..273736f41be3 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -275,7 +275,7 @@ static int __sysv_write_inode(struct inode *inode, int wait)
}
}
brelse(bh);
- return 0;
+ return err;
}
int sysv_write_inode(struct inode *inode, struct writeback_control *wbc)
diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig
index 529856fbccd0..bc1e082d921d 100644
--- a/fs/ubifs/Kconfig
+++ b/fs/ubifs/Kconfig
@@ -12,9 +12,10 @@ config UBIFS_FS
help
UBIFS is a file system for flash devices which works on top of UBI.
+if UBIFS_FS
+
config UBIFS_FS_ADVANCED_COMPR
bool "Advanced compression options"
- depends on UBIFS_FS
help
This option allows to explicitly choose which compressions, if any,
are enabled in UBIFS. Removing compressors means inability to read
@@ -24,7 +25,6 @@ config UBIFS_FS_ADVANCED_COMPR
config UBIFS_FS_LZO
bool "LZO compression support" if UBIFS_FS_ADVANCED_COMPR
- depends on UBIFS_FS
default y
help
LZO compressor is generally faster than zlib but compresses worse.
@@ -32,14 +32,12 @@ config UBIFS_FS_LZO
config UBIFS_FS_ZLIB
bool "ZLIB compression support" if UBIFS_FS_ADVANCED_COMPR
- depends on UBIFS_FS
default y
help
Zlib compresses better than LZO but it is slower. Say 'Y' if unsure.
config UBIFS_ATIME_SUPPORT
- bool "Access time support" if UBIFS_FS
- depends on UBIFS_FS
+ bool "Access time support"
default n
help
Originally UBIFS did not support atime, because it looked like a bad idea due
@@ -54,7 +52,6 @@ config UBIFS_ATIME_SUPPORT
config UBIFS_FS_XATTR
bool "UBIFS XATTR support"
- depends on UBIFS_FS
default y
help
Saying Y here includes support for extended attributes (xattrs).
@@ -65,7 +62,7 @@ config UBIFS_FS_XATTR
config UBIFS_FS_ENCRYPTION
bool "UBIFS Encryption"
- depends on UBIFS_FS && UBIFS_FS_XATTR && BLOCK
+ depends on UBIFS_FS_XATTR && BLOCK
select FS_ENCRYPTION
default n
help
@@ -76,7 +73,7 @@ config UBIFS_FS_ENCRYPTION
config UBIFS_FS_SECURITY
bool "UBIFS Security Labels"
- depends on UBIFS_FS && UBIFS_FS_XATTR
+ depends on UBIFS_FS_XATTR
default y
help
Security labels provide an access control facility to support Linux
@@ -89,6 +86,7 @@ config UBIFS_FS_SECURITY
config UBIFS_FS_AUTHENTICATION
bool "UBIFS authentication support"
+ depends on KEYS
select CRYPTO_HMAC
help
Enable authentication support for UBIFS. This feature offers protection
@@ -96,3 +94,5 @@ config UBIFS_FS_AUTHENTICATION
If you say yes here you should also select a hashing algorithm such as
sha256, these are not selected automatically since there are many
different options.
+
+endif # UBIFS_FS
diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c
index d1d5e96350dd..b0c5f06128b5 100644
--- a/fs/ubifs/lpt.c
+++ b/fs/ubifs/lpt.c
@@ -1675,6 +1675,12 @@ int ubifs_lpt_calc_hash(struct ubifs_info *c, u8 *hash)
if (!ubifs_authenticated(c))
return 0;
+ if (!c->nroot) {
+ err = ubifs_read_nnode(c, NULL, 0);
+ if (err)
+ return err;
+ }
+
desc = ubifs_hash_get_desc(c);
if (IS_ERR(desc))
return PTR_ERR(desc);
@@ -1685,12 +1691,6 @@ int ubifs_lpt_calc_hash(struct ubifs_info *c, u8 *hash)
goto out;
}
- if (!c->nroot) {
- err = ubifs_read_nnode(c, NULL, 0);
- if (err)
- return err;
- }
-
cnode = (struct ubifs_cnode *)c->nroot;
while (cnode) {
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 75f961c4c044..0a0e65c07c6d 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -213,6 +213,38 @@ static int trun_remove_range(struct ubifs_info *c, struct replay_entry *r)
}
/**
+ * inode_still_linked - check whether inode in question will be re-linked.
+ * @c: UBIFS file-system description object
+ * @rino: replay entry to test
+ *
+ * O_TMPFILE files can be re-linked, this means link count goes from 0 to 1.
+ * This case needs special care, otherwise all references to the inode will
+ * be removed upon the first replay entry of an inode with link count 0
+ * is found.
+ */
+static bool inode_still_linked(struct ubifs_info *c, struct replay_entry *rino)
+{
+ struct replay_entry *r;
+
+ ubifs_assert(c, rino->deletion);
+ ubifs_assert(c, key_type(c, &rino->key) == UBIFS_INO_KEY);
+
+ /*
+ * Find the most recent entry for the inode behind @rino and check
+ * whether it is a deletion.
+ */
+ list_for_each_entry_reverse(r, &c->replay_list, list) {
+ ubifs_assert(c, r->sqnum >= rino->sqnum);
+ if (key_inum(c, &r->key) == key_inum(c, &rino->key))
+ return r->deletion == 0;
+
+ }
+
+ ubifs_assert(c, 0);
+ return false;
+}
+
+/**
* apply_replay_entry - apply a replay entry to the TNC.
* @c: UBIFS file-system description object
* @r: replay entry to apply
@@ -239,6 +271,11 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r)
{
ino_t inum = key_inum(c, &r->key);
+ if (inode_still_linked(c, r)) {
+ err = 0;
+ break;
+ }
+
err = ubifs_tnc_remove_ino(c, inum);
break;
}
@@ -533,6 +570,28 @@ static int is_last_bud(struct ubifs_info *c, struct ubifs_bud *bud)
return data == 0xFFFFFFFF;
}
+/* authenticate_sleb_hash and authenticate_sleb_hmac are split out for stack usage */
+static int authenticate_sleb_hash(struct ubifs_info *c, struct shash_desc *log_hash, u8 *hash)
+{
+ SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm);
+
+ hash_desc->tfm = c->hash_tfm;
+ hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ ubifs_shash_copy_state(c, log_hash, hash_desc);
+ return crypto_shash_final(hash_desc, hash);
+}
+
+static int authenticate_sleb_hmac(struct ubifs_info *c, u8 *hash, u8 *hmac)
+{
+ SHASH_DESC_ON_STACK(hmac_desc, c->hmac_tfm);
+
+ hmac_desc->tfm = c->hmac_tfm;
+ hmac_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ return crypto_shash_digest(hmac_desc, hash, c->hash_len, hmac);
+}
+
/**
* authenticate_sleb - authenticate one scan LEB
* @c: UBIFS file-system description object
@@ -574,21 +633,12 @@ static int authenticate_sleb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
if (snod->type == UBIFS_AUTH_NODE) {
struct ubifs_auth_node *auth = snod->node;
- SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm);
- SHASH_DESC_ON_STACK(hmac_desc, c->hmac_tfm);
-
- hash_desc->tfm = c->hash_tfm;
- hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- ubifs_shash_copy_state(c, log_hash, hash_desc);
- err = crypto_shash_final(hash_desc, hash);
+ err = authenticate_sleb_hash(c, log_hash, hash);
if (err)
goto out;
- hmac_desc->tfm = c->hmac_tfm;
- hmac_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- err = crypto_shash_digest(hmac_desc, hash, c->hash_len,
- hmac);
+ err = authenticate_sleb_hmac(c, hash, hmac);
if (err)
goto out;
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 75a69dd26d6e..3da90c951c23 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -63,6 +63,17 @@
/* Default time granularity in nanoseconds */
#define DEFAULT_TIME_GRAN 1000000000
+static int get_default_compressor(struct ubifs_info *c)
+{
+ if (ubifs_compr_present(c, UBIFS_COMPR_LZO))
+ return UBIFS_COMPR_LZO;
+
+ if (ubifs_compr_present(c, UBIFS_COMPR_ZLIB))
+ return UBIFS_COMPR_ZLIB;
+
+ return UBIFS_COMPR_NONE;
+}
+
/**
* create_default_filesystem - format empty UBI volume.
* @c: UBIFS file-system description object
@@ -207,7 +218,7 @@ static int create_default_filesystem(struct ubifs_info *c)
if (c->mount_opts.override_compr)
sup->default_compr = cpu_to_le16(c->mount_opts.compr_type);
else
- sup->default_compr = cpu_to_le16(UBIFS_COMPR_LZO);
+ sup->default_compr = cpu_to_le16(get_default_compressor(c));
generate_random_uuid(sup->uuid);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 8f2f56d9a1bb..e3d684ea3203 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -827,16 +827,20 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
ret = udf_dstrCS0toChar(sb, outstr, 31, pvoldesc->volIdent, 32);
- if (ret < 0)
- goto out_bh;
-
- strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret);
+ if (ret < 0) {
+ strcpy(UDF_SB(sb)->s_volume_ident, "InvalidName");
+ pr_warn("incorrect volume identification, setting to "
+ "'InvalidName'\n");
+ } else {
+ strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret);
+ }
udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident);
ret = udf_dstrCS0toChar(sb, outstr, 127, pvoldesc->volSetIdent, 128);
- if (ret < 0)
+ if (ret < 0) {
+ ret = 0;
goto out_bh;
-
+ }
outstr[ret] = 0;
udf_debug("volSetIdent[] = '%s'\n", outstr);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index 45234791fec2..5fcfa96463eb 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -351,6 +351,11 @@ try_again:
return u_len;
}
+/*
+ * Convert CS0 dstring to output charset. Warning: This function may truncate
+ * input string if it is too long as it is used for informational strings only
+ * and it is better to truncate the string than to refuse mounting a media.
+ */
int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len,
const uint8_t *ocu_i, int i_len)
{
@@ -359,9 +364,12 @@ int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len,
if (i_len > 0) {
s_len = ocu_i[i_len - 1];
if (s_len >= i_len) {
- pr_err("incorrect dstring lengths (%d/%d)\n",
- s_len, i_len);
- return -EINVAL;
+ pr_warn("incorrect dstring lengths (%d/%d),"
+ " truncating\n", s_len, i_len);
+ s_len = i_len - 1;
+ /* 2-byte encoding? Need to round properly... */
+ if (ocu_i[0] == 16)
+ s_len -= (s_len - 1) & 2;
}
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 356d2b8568c1..7a85e609fc27 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1361,6 +1361,19 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
ret = -EINVAL;
if (!vma_can_userfault(cur))
goto out_unlock;
+
+ /*
+ * UFFDIO_COPY will fill file holes even without
+ * PROT_WRITE. This check enforces that if this is a
+ * MAP_SHARED, the process has write permission to the backing
+ * file. If VM_MAYWRITE is set it also enforces that on a
+ * MAP_SHARED vma: there is no F_WRITE_SEAL and no further
+ * F_WRITE_SEAL can be taken until the vma is destroyed.
+ */
+ ret = -EPERM;
+ if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
+ goto out_unlock;
+
/*
* If this vma contains ending address, and huge pages
* check alignment.
@@ -1406,6 +1419,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
BUG_ON(!vma_can_userfault(vma));
BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
vma->vm_userfaultfd_ctx.ctx != ctx);
+ WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
/*
* Nothing to do: this vma is already registered into this
@@ -1560,6 +1574,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
if (!vma->vm_userfaultfd_ctx.ctx)
goto skip;
+ WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
+
if (vma->vm_start > start)
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 34c6d7bd4d18..bbdae2b4559f 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -330,7 +330,7 @@ xfs_btree_sblock_verify_crc(
if (xfs_sb_version_hascrc(&mp->m_sb)) {
if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.s.bb_lsn)))
- return __this_address;
+ return false;
return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF);
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 404e581f1ea1..1ee8c5539fa4 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1126,9 +1126,9 @@ xfs_free_file_space(
* page could be mmap'd and iomap_zero_range doesn't do that for us.
* Writeback of the eof page will do this, albeit clumsily.
*/
- if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) {
+ if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
- (offset + len) & ~PAGE_MASK, LLONG_MAX);
+ round_down(offset + len, PAGE_SIZE), LLONG_MAX);
}
return error;
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 73a1d77ec187..3091e4bc04ef 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -40,7 +40,7 @@ xfs_fill_statvfs_from_dquot(
statp->f_files = limit;
statp->f_ffree =
(statp->f_files > dqp->q_res_icount) ?
- (statp->f_ffree - dqp->q_res_icount) : 0;
+ (statp->f_files - dqp->q_res_icount) : 0;
}
}