summaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/addr.c9
-rw-r--r--fs/ceph/crypto.c2
-rw-r--r--fs/ceph/debugfs.c14
-rw-r--r--fs/ceph/dir.c20
-rw-r--r--fs/ceph/file.c54
-rw-r--r--fs/ceph/inode.c100
-rw-r--r--fs/ceph/io.c100
-rw-r--r--fs/ceph/io.h8
-rw-r--r--fs/ceph/ioctl.c17
-rw-r--r--fs/ceph/locks.c5
-rw-r--r--fs/ceph/mds_client.c196
-rw-r--r--fs/ceph/mds_client.h18
-rw-r--r--fs/ceph/mdsmap.c14
-rw-r--r--fs/ceph/super.c18
-rw-r--r--fs/ceph/super.h18
15 files changed, 396 insertions, 197 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8b202d789e93..322ed268f14a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1264,7 +1264,9 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping,
0,
gfp_flags);
if (IS_ERR(pages[index])) {
- if (PTR_ERR(pages[index]) == -EINVAL) {
+ int err = PTR_ERR(pages[index]);
+
+ if (err == -EINVAL) {
pr_err_client(cl, "inode->i_blkbits=%hhu\n",
inode->i_blkbits);
}
@@ -1273,7 +1275,7 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping,
BUG_ON(ceph_wbc->locked_pages == 0);
pages[index] = NULL;
- return PTR_ERR(pages[index]);
+ return err;
}
} else {
pages[index] = &folio->page;
@@ -1687,6 +1689,7 @@ get_more_pages:
process_folio_batch:
rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc);
+ ceph_shift_unused_folios_left(&ceph_wbc.fbatch);
if (rc)
goto release_folios;
@@ -1695,8 +1698,6 @@ process_folio_batch:
goto release_folios;
if (ceph_wbc.processed_in_fbatch) {
- ceph_shift_unused_folios_left(&ceph_wbc.fbatch);
-
if (folio_batch_count(&ceph_wbc.fbatch) == 0 &&
ceph_wbc.locked_pages < ceph_wbc.max_pages) {
doutc(cl, "reached end fbatch, trying for more\n");
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index cab722619207..7026e794813c 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -133,6 +133,8 @@ static const union fscrypt_policy *ceph_get_dummy_policy(struct super_block *sb)
}
static struct fscrypt_operations ceph_fscrypt_ops = {
+ .inode_info_offs = (int)offsetof(struct ceph_inode_info, i_crypt_info) -
+ (int)offsetof(struct ceph_inode_info, netfs.inode),
.needs_bounce_pages = 1,
.get_context = ceph_crypt_get_context,
.set_context = ceph_crypt_set_context,
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index fdd404fc8112..f3fe786b4143 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -55,8 +55,6 @@ static int mdsc_show(struct seq_file *s, void *p)
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct rb_node *rp;
- int pathlen = 0;
- u64 pathbase;
char *path;
mutex_lock(&mdsc->mutex);
@@ -81,8 +79,8 @@ static int mdsc_show(struct seq_file *s, void *p)
if (req->r_inode) {
seq_printf(s, " #%llx", ceph_ino(req->r_inode));
} else if (req->r_dentry) {
- path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen,
- &pathbase, 0);
+ struct ceph_path_info path_info;
+ path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
if (IS_ERR(path))
path = NULL;
spin_lock(&req->r_dentry->d_lock);
@@ -91,7 +89,7 @@ static int mdsc_show(struct seq_file *s, void *p)
req->r_dentry,
path ? path : "");
spin_unlock(&req->r_dentry->d_lock);
- ceph_mdsc_free_path(path, pathlen);
+ ceph_mdsc_free_path_info(&path_info);
} else if (req->r_path1) {
seq_printf(s, " #%llx/%s", req->r_ino1.ino,
req->r_path1);
@@ -100,8 +98,8 @@ static int mdsc_show(struct seq_file *s, void *p)
}
if (req->r_old_dentry) {
- path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &pathlen,
- &pathbase, 0);
+ struct ceph_path_info path_info;
+ path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0);
if (IS_ERR(path))
path = NULL;
spin_lock(&req->r_old_dentry->d_lock);
@@ -111,7 +109,7 @@ static int mdsc_show(struct seq_file *s, void *p)
req->r_old_dentry,
path ? path : "");
spin_unlock(&req->r_old_dentry->d_lock);
- ceph_mdsc_free_path(path, pathlen);
+ ceph_mdsc_free_path_info(&path_info);
} else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) {
if (req->r_ino2.ino)
seq_printf(s, " #%llx/%s", req->r_ino2.ino,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 8478e7e75df6..d18c0eaef9b7 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1260,8 +1260,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
spin_unlock(&fsc->async_unlink_conflict_lock);
spin_lock(&dentry->d_lock);
- di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK;
- wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT);
+ clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags);
spin_unlock(&dentry->d_lock);
synchronize_rcu();
@@ -1271,10 +1270,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
/* If op failed, mark everyone involved for errors */
if (result) {
- int pathlen = 0;
- u64 base = 0;
- char *path = ceph_mdsc_build_path(mdsc, dentry, &pathlen,
- &base, 0);
+ struct ceph_path_info path_info = {0};
+ char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
/* mark error on parent + clear complete */
mapping_set_error(req->r_parent->i_mapping, result);
@@ -1288,8 +1285,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
mapping_set_error(req->r_old_inode->i_mapping, result);
pr_warn_client(cl, "failure path=(%llx)%s result=%d!\n",
- base, IS_ERR(path) ? "<<bad>>" : path, result);
- ceph_mdsc_free_path(path, pathlen);
+ path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result);
+ ceph_mdsc_free_path_info(&path_info);
}
out:
iput(req->r_old_inode);
@@ -1347,8 +1344,6 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
int err = -EROFS;
int op;
char *path;
- int pathlen;
- u64 pathbase;
if (ceph_snap(dir) == CEPH_SNAPDIR) {
/* rmdir .snap/foo is RMSNAP */
@@ -1367,14 +1362,15 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
if (!dn) {
try_async = false;
} else {
- path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0);
+ struct ceph_path_info path_info;
+ path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
if (IS_ERR(path)) {
try_async = false;
err = 0;
} else {
err = ceph_mds_check_access(mdsc, path, MAY_WRITE);
}
- ceph_mdsc_free_path(path, pathlen);
+ ceph_mdsc_free_path_info(&path_info);
dput(dn);
/* For none EACCES cases will let the MDS do the mds auth check */
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c02f100f8552..99b30f784ee2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -368,8 +368,6 @@ int ceph_open(struct inode *inode, struct file *file)
int flags, fmode, wanted;
struct dentry *dentry;
char *path;
- int pathlen;
- u64 pathbase;
bool do_sync = false;
int mask = MAY_READ;
@@ -399,14 +397,15 @@ int ceph_open(struct inode *inode, struct file *file)
if (!dentry) {
do_sync = true;
} else {
- path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0);
+ struct ceph_path_info path_info;
+ path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
if (IS_ERR(path)) {
do_sync = true;
err = 0;
} else {
err = ceph_mds_check_access(mdsc, path, mask);
}
- ceph_mdsc_free_path(path, pathlen);
+ ceph_mdsc_free_path_info(&path_info);
dput(dentry);
/* For none EACCES cases will let the MDS do the mds auth check */
@@ -580,8 +579,7 @@ static void wake_async_create_waiters(struct inode *inode,
spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) {
- ci->i_ceph_flags &= ~CEPH_I_ASYNC_CREATE;
- wake_up_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT);
+ clear_and_wake_up_bit(CEPH_ASYNC_CREATE_BIT, &ci->i_ceph_flags);
if (ci->i_ceph_flags & CEPH_I_ASYNC_CHECK_CAPS) {
ci->i_ceph_flags &= ~CEPH_I_ASYNC_CHECK_CAPS;
@@ -614,15 +612,13 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
mapping_set_error(req->r_parent->i_mapping, result);
if (result) {
- int pathlen = 0;
- u64 base = 0;
- char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen,
- &base, 0);
+ struct ceph_path_info path_info = {0};
+ char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
pr_warn_client(cl,
"async create failure path=(%llx)%s result=%d!\n",
- base, IS_ERR(path) ? "<<bad>>" : path, result);
- ceph_mdsc_free_path(path, pathlen);
+ path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result);
+ ceph_mdsc_free_path_info(&path_info);
ceph_dir_clear_complete(req->r_parent);
if (!d_unhashed(dentry))
@@ -765,8 +761,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
}
spin_lock(&dentry->d_lock);
- di->flags &= ~CEPH_DENTRY_ASYNC_CREATE;
- wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT);
+ clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_CREATE_BIT, &di->flags);
spin_unlock(&dentry->d_lock);
return ret;
@@ -791,8 +786,6 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
int mask;
int err;
char *path;
- int pathlen;
- u64 pathbase;
doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n",
dir, ceph_vinop(dir), dentry, dentry,
@@ -814,7 +807,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
if (!dn) {
try_async = false;
} else {
- path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0);
+ struct ceph_path_info path_info;
+ path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
if (IS_ERR(path)) {
try_async = false;
err = 0;
@@ -826,7 +820,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
mask |= MAY_WRITE;
err = ceph_mds_check_access(mdsc, path, mask);
}
- ceph_mdsc_free_path(path, pathlen);
+ ceph_mdsc_free_path_info(&path_info);
dput(dn);
/* For none EACCES cases will let the MDS do the mds auth check */
@@ -2125,10 +2119,10 @@ again:
if (ceph_inode_is_shutdown(inode))
return -ESTALE;
- if (direct_lock)
- ceph_start_io_direct(inode);
- else
- ceph_start_io_read(inode);
+ ret = direct_lock ? ceph_start_io_direct(inode) :
+ ceph_start_io_read(inode);
+ if (ret)
+ return ret;
if (!(fi->flags & CEPH_F_SYNC) && !direct_lock)
want |= CEPH_CAP_FILE_CACHE;
@@ -2281,7 +2275,9 @@ static ssize_t ceph_splice_read(struct file *in, loff_t *ppos,
(fi->flags & CEPH_F_SYNC))
return copy_splice_read(in, ppos, pipe, len, flags);
- ceph_start_io_read(inode);
+ ret = ceph_start_io_read(inode);
+ if (ret)
+ return ret;
want = CEPH_CAP_FILE_CACHE;
if (fi->fmode & CEPH_FILE_MODE_LAZY)
@@ -2360,10 +2356,10 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
direct_lock = true;
retry_snap:
- if (direct_lock)
- ceph_start_io_direct(inode);
- else
- ceph_start_io_write(inode);
+ err = direct_lock ? ceph_start_io_direct(inode) :
+ ceph_start_io_write(inode);
+ if (err)
+ goto out_unlocked;
if (iocb->ki_flags & IOCB_APPEND) {
err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
@@ -2882,7 +2878,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
struct ceph_object_id src_oid, dst_oid;
struct ceph_osd_client *osdc;
struct ceph_osd_request *req;
- size_t bytes = 0;
+ ssize_t bytes = 0;
u64 src_objnum, src_objoff, dst_objnum, dst_objoff;
u32 src_objlen, dst_objlen;
u32 object_size = src_ci->i_layout.object_size;
@@ -2932,7 +2928,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
"OSDs don't support copy-from2; disabling copy offload\n");
}
doutc(cl, "returned %d\n", ret);
- if (!bytes)
+ if (bytes <= 0)
bytes = ret;
goto out;
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index fc543075b827..a6e260d9e420 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -55,6 +55,52 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
return 0;
}
+/*
+ * Check if the parent inode matches the vino from directory reply info
+ */
+static inline bool ceph_vino_matches_parent(struct inode *parent,
+ struct ceph_vino vino)
+{
+ return ceph_ino(parent) == vino.ino && ceph_snap(parent) == vino.snap;
+}
+
+/*
+ * Validate that the directory inode referenced by @req->r_parent matches the
+ * inode number and snapshot id contained in the reply's directory record. If
+ * they do not match – which can theoretically happen if the parent dentry was
+ * moved between the time the request was issued and the reply arrived – fall
+ * back to looking up the correct inode in the inode cache.
+ *
+ * A reference is *always* returned. Callers that receive a different inode
+ * than the original @parent are responsible for dropping the extra reference
+ * once the reply has been processed.
+ */
+static struct inode *ceph_get_reply_dir(struct super_block *sb,
+ struct inode *parent,
+ struct ceph_mds_reply_info_parsed *rinfo)
+{
+ struct ceph_vino vino;
+
+ if (unlikely(!rinfo->diri.in))
+ return parent; /* nothing to compare against */
+
+ /* If we didn't have a cached parent inode to begin with, just bail out. */
+ if (!parent)
+ return NULL;
+
+ vino.ino = le64_to_cpu(rinfo->diri.in->ino);
+ vino.snap = le64_to_cpu(rinfo->diri.in->snapid);
+
+ if (likely(ceph_vino_matches_parent(parent, vino)))
+ return parent; /* matches – use the original reference */
+
+ /* Mismatch – this should be rare. Emit a WARN and obtain the correct inode. */
+ WARN_ONCE(1, "ceph: reply dir mismatch (parent valid %llx.%llx reply %llx.%llx)\n",
+ ceph_ino(parent), ceph_snap(parent), vino.ino, vino.snap);
+
+ return ceph_get_inode(sb, vino, NULL);
+}
+
/**
* ceph_new_inode - allocate a new inode in advance of an expected create
* @dir: parent directory for new inode
@@ -665,6 +711,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_work_mask = 0;
memset(&ci->i_btime, '\0', sizeof(ci->i_btime));
#ifdef CONFIG_FS_ENCRYPTION
+ ci->i_crypt_info = NULL;
ci->fscrypt_auth = NULL;
ci->fscrypt_auth_len = 0;
#endif
@@ -1523,6 +1570,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
struct ceph_vino tvino, dvino;
struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
struct ceph_client *cl = fsc->client;
+ struct inode *parent_dir = NULL;
int err = 0;
doutc(cl, "%p is_dentry %d is_target %d\n", req,
@@ -1536,10 +1584,17 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
}
if (rinfo->head->is_dentry) {
- struct inode *dir = req->r_parent;
-
- if (dir) {
- err = ceph_fill_inode(dir, NULL, &rinfo->diri,
+ /*
+ * r_parent may be stale, in cases when R_PARENT_LOCKED is not set,
+ * so we need to get the correct inode
+ */
+ parent_dir = ceph_get_reply_dir(sb, req->r_parent, rinfo);
+ if (unlikely(IS_ERR(parent_dir))) {
+ err = PTR_ERR(parent_dir);
+ goto done;
+ }
+ if (parent_dir) {
+ err = ceph_fill_inode(parent_dir, NULL, &rinfo->diri,
rinfo->dirfrag, session, -1,
&req->r_caps_reservation);
if (err < 0)
@@ -1548,14 +1603,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
WARN_ON_ONCE(1);
}
- if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME &&
+ if (parent_dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME &&
test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
bool is_nokey = false;
struct qstr dname;
struct dentry *dn, *parent;
struct fscrypt_str oname = FSTR_INIT(NULL, 0);
- struct ceph_fname fname = { .dir = dir,
+ struct ceph_fname fname = { .dir = parent_dir,
.name = rinfo->dname,
.ctext = rinfo->altname,
.name_len = rinfo->dname_len,
@@ -1564,10 +1619,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
BUG_ON(!rinfo->head->is_target);
BUG_ON(req->r_dentry);
- parent = d_find_any_alias(dir);
+ parent = d_find_any_alias(parent_dir);
BUG_ON(!parent);
- err = ceph_fname_alloc_buffer(dir, &oname);
+ err = ceph_fname_alloc_buffer(parent_dir, &oname);
if (err < 0) {
dput(parent);
goto done;
@@ -1576,7 +1631,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
err = ceph_fname_to_usr(&fname, NULL, &oname, &is_nokey);
if (err < 0) {
dput(parent);
- ceph_fname_free_buffer(dir, &oname);
+ ceph_fname_free_buffer(parent_dir, &oname);
goto done;
}
dname.name = oname.name;
@@ -1595,7 +1650,7 @@ retry_lookup:
dname.len, dname.name, dn);
if (!dn) {
dput(parent);
- ceph_fname_free_buffer(dir, &oname);
+ ceph_fname_free_buffer(parent_dir, &oname);
err = -ENOMEM;
goto done;
}
@@ -1610,12 +1665,12 @@ retry_lookup:
ceph_snap(d_inode(dn)) != tvino.snap)) {
doutc(cl, " dn %p points to wrong inode %p\n",
dn, d_inode(dn));
- ceph_dir_clear_ordered(dir);
+ ceph_dir_clear_ordered(parent_dir);
d_delete(dn);
dput(dn);
goto retry_lookup;
}
- ceph_fname_free_buffer(dir, &oname);
+ ceph_fname_free_buffer(parent_dir, &oname);
req->r_dentry = dn;
dput(parent);
@@ -1739,6 +1794,11 @@ retry_lookup:
goto done;
}
+ if (unlikely(!in)) {
+ err = -EINVAL;
+ goto done;
+ }
+
/* attach proper inode */
if (d_really_is_negative(dn)) {
ceph_dir_clear_ordered(dir);
@@ -1774,6 +1834,12 @@ retry_lookup:
doutc(cl, " linking snapped dir %p to dn %p\n", in,
req->r_dentry);
ceph_dir_clear_ordered(dir);
+
+ if (unlikely(!in)) {
+ err = -EINVAL;
+ goto done;
+ }
+
ihold(in);
err = splice_dentry(&req->r_dentry, in);
if (err < 0)
@@ -1794,6 +1860,9 @@ retry_lookup:
&dvino, ptvino);
}
done:
+ /* Drop extra ref from ceph_get_reply_dir() if it returned a new inode */
+ if (unlikely(!IS_ERR_OR_NULL(parent_dir) && parent_dir != req->r_parent))
+ iput(parent_dir);
doutc(cl, "done err=%d\n", err);
return err;
}
@@ -2487,22 +2556,21 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
int truncate_retry = 20; /* The RMW will take around 50ms */
struct dentry *dentry;
char *path;
- int pathlen;
- u64 pathbase;
bool do_sync = false;
dentry = d_find_alias(inode);
if (!dentry) {
do_sync = true;
} else {
- path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0);
+ struct ceph_path_info path_info;
+ path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
if (IS_ERR(path)) {
do_sync = true;
err = 0;
} else {
err = ceph_mds_check_access(mdsc, path, MAY_WRITE);
}
- ceph_mdsc_free_path(path, pathlen);
+ ceph_mdsc_free_path_info(&path_info);
dput(dentry);
/* For none EACCES cases will let the MDS do the mds auth check */
diff --git a/fs/ceph/io.c b/fs/ceph/io.c
index c456509b31c3..2d10f49c93a9 100644
--- a/fs/ceph/io.c
+++ b/fs/ceph/io.c
@@ -21,14 +21,23 @@
/* Call with exclusively locked inode->i_rwsem */
static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
{
+ bool is_odirect;
+
lockdep_assert_held_write(&inode->i_rwsem);
- if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT) {
- spin_lock(&ci->i_ceph_lock);
- ci->i_ceph_flags &= ~CEPH_I_ODIRECT;
- spin_unlock(&ci->i_ceph_lock);
- inode_dio_wait(inode);
+ spin_lock(&ci->i_ceph_lock);
+ /* ensure that bit state is consistent */
+ smp_mb__before_atomic();
+ is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+ if (is_odirect) {
+ clear_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+ /* ensure modified bit is visible */
+ smp_mb__after_atomic();
}
+ spin_unlock(&ci->i_ceph_lock);
+
+ if (is_odirect)
+ inode_dio_wait(inode);
}
/**
@@ -47,20 +56,35 @@ static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
* Note that buffered writes and truncates both take a write lock on
* inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
*/
-void
-ceph_start_io_read(struct inode *inode)
+int ceph_start_io_read(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
+ bool is_odirect;
+ int err;
/* Be an optimist! */
- down_read(&inode->i_rwsem);
- if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT))
- return;
+ err = down_read_killable(&inode->i_rwsem);
+ if (err)
+ return err;
+
+ spin_lock(&ci->i_ceph_lock);
+ /* ensure that bit state is consistent */
+ smp_mb__before_atomic();
+ is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+ spin_unlock(&ci->i_ceph_lock);
+ if (!is_odirect)
+ return 0;
up_read(&inode->i_rwsem);
+
/* Slow path.... */
- down_write(&inode->i_rwsem);
+ err = down_write_killable(&inode->i_rwsem);
+ if (err)
+ return err;
+
ceph_block_o_direct(ci, inode);
downgrade_write(&inode->i_rwsem);
+
+ return 0;
}
/**
@@ -83,11 +107,12 @@ ceph_end_io_read(struct inode *inode)
* Declare that a buffered write operation is about to start, and ensure
* that we block all direct I/O.
*/
-void
-ceph_start_io_write(struct inode *inode)
+int ceph_start_io_write(struct inode *inode)
{
- down_write(&inode->i_rwsem);
- ceph_block_o_direct(ceph_inode(inode), inode);
+ int err = down_write_killable(&inode->i_rwsem);
+ if (!err)
+ ceph_block_o_direct(ceph_inode(inode), inode);
+ return err;
}
/**
@@ -106,12 +131,22 @@ ceph_end_io_write(struct inode *inode)
/* Call with exclusively locked inode->i_rwsem */
static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
{
+ bool is_odirect;
+
lockdep_assert_held_write(&inode->i_rwsem);
- if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)) {
- spin_lock(&ci->i_ceph_lock);
- ci->i_ceph_flags |= CEPH_I_ODIRECT;
- spin_unlock(&ci->i_ceph_lock);
+ spin_lock(&ci->i_ceph_lock);
+ /* ensure that bit state is consistent */
+ smp_mb__before_atomic();
+ is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+ if (!is_odirect) {
+ set_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
+ /* ensure modified bit is visible */
+ smp_mb__after_atomic();
+ }
+ spin_unlock(&ci->i_ceph_lock);
+
+ if (!is_odirect) {
/* FIXME: unmap_mapping_range? */
filemap_write_and_wait(inode->i_mapping);
}
@@ -133,20 +168,35 @@ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
* Note that buffered writes and truncates both take a write lock on
* inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
*/
-void
-ceph_start_io_direct(struct inode *inode)
+int ceph_start_io_direct(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
+ bool is_odirect;
+ int err;
/* Be an optimist! */
- down_read(&inode->i_rwsem);
- if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)
- return;
+ err = down_read_killable(&inode->i_rwsem);
+ if (err)
+ return err;
+
+ spin_lock(&ci->i_ceph_lock);
+ /* ensure that bit state is consistent */
+ smp_mb__before_atomic();
+ is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
+ spin_unlock(&ci->i_ceph_lock);
+ if (is_odirect)
+ return 0;
up_read(&inode->i_rwsem);
+
/* Slow path.... */
- down_write(&inode->i_rwsem);
+ err = down_write_killable(&inode->i_rwsem);
+ if (err)
+ return err;
+
ceph_block_buffered(ci, inode);
downgrade_write(&inode->i_rwsem);
+
+ return 0;
}
/**
diff --git a/fs/ceph/io.h b/fs/ceph/io.h
index fa594cd77348..79029825e8b8 100644
--- a/fs/ceph/io.h
+++ b/fs/ceph/io.h
@@ -2,11 +2,13 @@
#ifndef _FS_CEPH_IO_H
#define _FS_CEPH_IO_H
-void ceph_start_io_read(struct inode *inode);
+#include <linux/compiler_attributes.h>
+
+int __must_check ceph_start_io_read(struct inode *inode);
void ceph_end_io_read(struct inode *inode);
-void ceph_start_io_write(struct inode *inode);
+int __must_check ceph_start_io_write(struct inode *inode);
void ceph_end_io_write(struct inode *inode);
-void ceph_start_io_direct(struct inode *inode);
+int __must_check ceph_start_io_direct(struct inode *inode);
void ceph_end_io_direct(struct inode *inode);
#endif /* FS_CEPH_IO_H */
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index e861de3c79b9..15cde055f3da 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -246,21 +246,28 @@ static long ceph_ioctl_lazyio(struct file *file)
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
struct ceph_client *cl = mdsc->fsc->client;
+ bool is_file_already_lazy = false;
+ spin_lock(&ci->i_ceph_lock);
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
- spin_lock(&ci->i_ceph_lock);
fi->fmode |= CEPH_FILE_MODE_LAZY;
ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
__ceph_touch_fmode(ci, mdsc, fi->fmode);
- spin_unlock(&ci->i_ceph_lock);
+ } else {
+ is_file_already_lazy = true;
+ }
+ spin_unlock(&ci->i_ceph_lock);
+
+ if (is_file_already_lazy) {
+ doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode,
+ ceph_vinop(inode));
+ } else {
doutc(cl, "file %p %p %llx.%llx marked lazy\n", file, inode,
ceph_vinop(inode));
ceph_check_caps(ci, 0);
- } else {
- doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode,
- ceph_vinop(inode));
}
+
return 0;
}
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ebf4ac0055dd..dd764f9c64b9 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -221,7 +221,10 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
if (err && err != -ERESTARTSYS)
return err;
- wait_for_completion_killable(&req->r_safe_completion);
+ err = wait_for_completion_killable(&req->r_safe_completion);
+ if (err)
+ return err;
+
return 0;
}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 0f497c39ff82..1740047aef0f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -979,14 +979,15 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
if (mds >= mdsc->max_sessions) {
int newmax = 1 << get_count_order(mds + 1);
struct ceph_mds_session **sa;
+ size_t ptr_size = sizeof(struct ceph_mds_session *);
doutc(cl, "realloc to %d\n", newmax);
- sa = kcalloc(newmax, sizeof(void *), GFP_NOFS);
+ sa = kcalloc(newmax, ptr_size, GFP_NOFS);
if (!sa)
goto fail_realloc;
if (mdsc->sessions) {
memcpy(sa, mdsc->sessions,
- mdsc->max_sessions * sizeof(void *));
+ mdsc->max_sessions * ptr_size);
kfree(mdsc->sessions);
}
mdsc->sessions = sa;
@@ -2221,7 +2222,7 @@ static int trim_caps_cb(struct inode *inode, int mds, void *arg)
int count;
dput(dentry);
d_prune_aliases(inode);
- count = atomic_read(&inode->i_count);
+ count = icount_read(inode);
if (count == 1)
(*remaining)--;
doutc(cl, "%p %llx.%llx cap %p pruned, count now %d\n",
@@ -2532,6 +2533,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
struct ceph_mount_options *opt = req->r_mdsc->fsc->mount_options;
size_t size = sizeof(struct ceph_mds_reply_dir_entry);
unsigned int num_entries;
+ u64 bytes_count;
int order;
spin_lock(&ci->i_ceph_lock);
@@ -2540,7 +2542,11 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
num_entries = max(num_entries, 1U);
num_entries = min(num_entries, opt->max_readdir);
- order = get_order(size * num_entries);
+ bytes_count = (u64)size * num_entries;
+ if (unlikely(bytes_count > ULONG_MAX))
+ bytes_count = ULONG_MAX;
+
+ order = get_order((unsigned long)bytes_count);
while (order >= 0) {
rinfo->dir_entries = (void*)__get_free_pages(GFP_KERNEL |
__GFP_NOWARN |
@@ -2550,7 +2556,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
break;
order--;
}
- if (!rinfo->dir_entries)
+ if (!rinfo->dir_entries || unlikely(order < 0))
return -ENOMEM;
num_entries = (PAGE_SIZE << order) / size;
@@ -2681,8 +2687,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
* ceph_mdsc_build_path - build a path string to a given dentry
* @mdsc: mds client
* @dentry: dentry to which path should be built
- * @plen: returned length of string
- * @pbase: returned base inode number
+ * @path_info: output path, length, base ino+snap, and freepath ownership flag
* @for_wire: is this path going to be sent to the MDS?
*
* Build a string that represents the path to the dentry. This is mostly called
@@ -2700,7 +2705,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
* foo/.snap/bar -> foo//bar
*/
char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
- int *plen, u64 *pbase, int for_wire)
+ struct ceph_path_info *path_info, int for_wire)
{
struct ceph_client *cl = mdsc->fsc->client;
struct dentry *cur;
@@ -2810,16 +2815,28 @@ retry:
return ERR_PTR(-ENAMETOOLONG);
}
- *pbase = base;
- *plen = PATH_MAX - 1 - pos;
+ /* Initialize the output structure */
+ memset(path_info, 0, sizeof(*path_info));
+
+ path_info->vino.ino = base;
+ path_info->pathlen = PATH_MAX - 1 - pos;
+ path_info->path = path + pos;
+ path_info->freepath = true;
+
+ /* Set snap from dentry if available */
+ if (d_inode(dentry))
+ path_info->vino.snap = ceph_snap(d_inode(dentry));
+ else
+ path_info->vino.snap = CEPH_NOSNAP;
+
doutc(cl, "on %p %d built %llx '%.*s'\n", dentry, d_count(dentry),
- base, *plen, path + pos);
+ base, PATH_MAX - 1 - pos, path + pos);
return path + pos;
}
static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
- struct inode *dir, const char **ppath, int *ppathlen,
- u64 *pino, bool *pfreepath, bool parent_locked)
+ struct inode *dir, struct ceph_path_info *path_info,
+ bool parent_locked)
{
char *path;
@@ -2828,41 +2845,47 @@ static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry
dir = d_inode_rcu(dentry->d_parent);
if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP &&
!IS_ENCRYPTED(dir)) {
- *pino = ceph_ino(dir);
+ path_info->vino.ino = ceph_ino(dir);
+ path_info->vino.snap = ceph_snap(dir);
rcu_read_unlock();
- *ppath = dentry->d_name.name;
- *ppathlen = dentry->d_name.len;
+ path_info->path = dentry->d_name.name;
+ path_info->pathlen = dentry->d_name.len;
+ path_info->freepath = false;
return 0;
}
rcu_read_unlock();
- path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
+ path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1);
if (IS_ERR(path))
return PTR_ERR(path);
- *ppath = path;
- *pfreepath = true;
+ /*
+ * ceph_mdsc_build_path already fills path_info, including snap handling.
+ */
return 0;
}
-static int build_inode_path(struct inode *inode,
- const char **ppath, int *ppathlen, u64 *pino,
- bool *pfreepath)
+static int build_inode_path(struct inode *inode, struct ceph_path_info *path_info)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
struct dentry *dentry;
char *path;
if (ceph_snap(inode) == CEPH_NOSNAP) {
- *pino = ceph_ino(inode);
- *ppathlen = 0;
+ path_info->vino.ino = ceph_ino(inode);
+ path_info->vino.snap = ceph_snap(inode);
+ path_info->pathlen = 0;
+ path_info->freepath = false;
return 0;
}
dentry = d_find_alias(inode);
- path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
+ path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1);
dput(dentry);
if (IS_ERR(path))
return PTR_ERR(path);
- *ppath = path;
- *pfreepath = true;
+ /*
+ * ceph_mdsc_build_path already fills path_info, including snap from dentry.
+ * Override with inode's snap since that's what this function is for.
+ */
+ path_info->vino.snap = ceph_snap(inode);
return 0;
}
@@ -2872,26 +2895,32 @@ static int build_inode_path(struct inode *inode,
*/
static int set_request_path_attr(struct ceph_mds_client *mdsc, struct inode *rinode,
struct dentry *rdentry, struct inode *rdiri,
- const char *rpath, u64 rino, const char **ppath,
- int *pathlen, u64 *ino, bool *freepath,
+ const char *rpath, u64 rino,
+ struct ceph_path_info *path_info,
bool parent_locked)
{
struct ceph_client *cl = mdsc->fsc->client;
int r = 0;
+ /* Initialize the output structure */
+ memset(path_info, 0, sizeof(*path_info));
+
if (rinode) {
- r = build_inode_path(rinode, ppath, pathlen, ino, freepath);
+ r = build_inode_path(rinode, path_info);
doutc(cl, " inode %p %llx.%llx\n", rinode, ceph_ino(rinode),
ceph_snap(rinode));
} else if (rdentry) {
- r = build_dentry_path(mdsc, rdentry, rdiri, ppath, pathlen, ino,
- freepath, parent_locked);
- doutc(cl, " dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath);
+ r = build_dentry_path(mdsc, rdentry, rdiri, path_info, parent_locked);
+ doutc(cl, " dentry %p %llx/%.*s\n", rdentry, path_info->vino.ino,
+ path_info->pathlen, path_info->path);
} else if (rpath || rino) {
- *ino = rino;
- *ppath = rpath;
- *pathlen = rpath ? strlen(rpath) : 0;
- doutc(cl, " path %.*s\n", *pathlen, rpath);
+ path_info->vino.ino = rino;
+ path_info->vino.snap = CEPH_NOSNAP;
+ path_info->path = rpath;
+ path_info->pathlen = rpath ? strlen(rpath) : 0;
+ path_info->freepath = false;
+
+ doutc(cl, " path %.*s\n", path_info->pathlen, rpath);
}
return r;
@@ -2968,11 +2997,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
struct ceph_client *cl = mdsc->fsc->client;
struct ceph_msg *msg;
struct ceph_mds_request_head_legacy *lhead;
- const char *path1 = NULL;
- const char *path2 = NULL;
- u64 ino1 = 0, ino2 = 0;
- int pathlen1 = 0, pathlen2 = 0;
- bool freepath1 = false, freepath2 = false;
+ struct ceph_path_info path_info1 = {0};
+ struct ceph_path_info path_info2 = {0};
struct dentry *old_dentry = NULL;
int len;
u16 releases;
@@ -2982,25 +3008,49 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
u16 request_head_version = mds_supported_head_version(session);
kuid_t caller_fsuid = req->r_cred->fsuid;
kgid_t caller_fsgid = req->r_cred->fsgid;
+ bool parent_locked = test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry,
- req->r_parent, req->r_path1, req->r_ino1.ino,
- &path1, &pathlen1, &ino1, &freepath1,
- test_bit(CEPH_MDS_R_PARENT_LOCKED,
- &req->r_req_flags));
+ req->r_parent, req->r_path1, req->r_ino1.ino,
+ &path_info1, parent_locked);
if (ret < 0) {
msg = ERR_PTR(ret);
goto out;
}
+ /*
+ * When the parent directory's i_rwsem is *not* locked, req->r_parent may
+ * have become stale (e.g. after a concurrent rename) between the time the
+ * dentry was looked up and now. If we detect that the stored r_parent
+ * does not match the inode number we just encoded for the request, switch
+ * to the correct inode so that the MDS receives a valid parent reference.
+ */
+ if (!parent_locked && req->r_parent && path_info1.vino.ino &&
+ ceph_ino(req->r_parent) != path_info1.vino.ino) {
+ struct inode *old_parent = req->r_parent;
+ struct inode *correct_dir = ceph_get_inode(mdsc->fsc->sb, path_info1.vino, NULL);
+ if (!IS_ERR(correct_dir)) {
+ WARN_ONCE(1, "ceph: r_parent mismatch (had %llx wanted %llx) - updating\n",
+ ceph_ino(old_parent), path_info1.vino.ino);
+ /*
+ * Transfer CEPH_CAP_PIN from the old parent to the new one.
+ * The pin was taken earlier in ceph_mdsc_submit_request().
+ */
+ ceph_put_cap_refs(ceph_inode(old_parent), CEPH_CAP_PIN);
+ iput(old_parent);
+ req->r_parent = correct_dir;
+ ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+ }
+ }
+
/* If r_old_dentry is set, then assume that its parent is locked */
if (req->r_old_dentry &&
!(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED))
old_dentry = req->r_old_dentry;
ret = set_request_path_attr(mdsc, NULL, old_dentry,
- req->r_old_dentry_dir,
- req->r_path2, req->r_ino2.ino,
- &path2, &pathlen2, &ino2, &freepath2, true);
+ req->r_old_dentry_dir,
+ req->r_path2, req->r_ino2.ino,
+ &path_info2, true);
if (ret < 0) {
msg = ERR_PTR(ret);
goto out_free1;
@@ -3031,7 +3081,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
/* filepaths */
len += 2 * (1 + sizeof(u32) + sizeof(u64));
- len += pathlen1 + pathlen2;
+ len += path_info1.pathlen + path_info2.pathlen;
/* cap releases */
len += sizeof(struct ceph_mds_request_release) *
@@ -3039,9 +3089,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
!!req->r_old_inode_drop + !!req->r_old_dentry_drop);
if (req->r_dentry_drop)
- len += pathlen1;
+ len += path_info1.pathlen;
if (req->r_old_dentry_drop)
- len += pathlen2;
+ len += path_info2.pathlen;
/* MClientRequest tail */
@@ -3154,8 +3204,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
lhead->ino = cpu_to_le64(req->r_deleg_ino);
lhead->args = req->r_args;
- ceph_encode_filepath(&p, end, ino1, path1);
- ceph_encode_filepath(&p, end, ino2, path2);
+ ceph_encode_filepath(&p, end, path_info1.vino.ino, path_info1.path);
+ ceph_encode_filepath(&p, end, path_info2.vino.ino, path_info2.path);
/* make note of release offset, in case we need to replay */
req->r_request_release_offset = p - msg->front.iov_base;
@@ -3218,11 +3268,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
msg->hdr.data_off = cpu_to_le16(0);
out_free2:
- if (freepath2)
- ceph_mdsc_free_path((char *)path2, pathlen2);
+ ceph_mdsc_free_path_info(&path_info2);
out_free1:
- if (freepath1)
- ceph_mdsc_free_path((char *)path1, pathlen1);
+ ceph_mdsc_free_path_info(&path_info1);
out:
return msg;
out_err:
@@ -4579,24 +4627,20 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
struct ceph_pagelist *pagelist = recon_state->pagelist;
struct dentry *dentry;
struct ceph_cap *cap;
- char *path;
- int pathlen = 0, err;
- u64 pathbase;
+ struct ceph_path_info path_info = {0};
+ int err;
u64 snap_follows;
dentry = d_find_primary(inode);
if (dentry) {
/* set pathbase to parent dir when msg_version >= 2 */
- path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase,
+ char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info,
recon_state->msg_version >= 2);
dput(dentry);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out_err;
}
- } else {
- path = NULL;
- pathbase = 0;
}
spin_lock(&ci->i_ceph_lock);
@@ -4629,7 +4673,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci));
rec.v2.issued = cpu_to_le32(cap->issued);
rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
- rec.v2.pathbase = cpu_to_le64(pathbase);
+ rec.v2.pathbase = cpu_to_le64(path_info.vino.ino);
rec.v2.flock_len = (__force __le32)
((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1);
} else {
@@ -4644,7 +4688,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
ts = inode_get_atime(inode);
ceph_encode_timespec64(&rec.v1.atime, &ts);
rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
- rec.v1.pathbase = cpu_to_le64(pathbase);
+ rec.v1.pathbase = cpu_to_le64(path_info.vino.ino);
}
if (list_empty(&ci->i_cap_snaps)) {
@@ -4706,7 +4750,7 @@ encode_again:
sizeof(struct ceph_filelock);
rec.v2.flock_len = cpu_to_le32(struct_len);
- struct_len += sizeof(u32) + pathlen + sizeof(rec.v2);
+ struct_len += sizeof(u32) + path_info.pathlen + sizeof(rec.v2);
if (struct_v >= 2)
struct_len += sizeof(u64); /* snap_follows */
@@ -4730,7 +4774,7 @@ encode_again:
ceph_pagelist_encode_8(pagelist, 1);
ceph_pagelist_encode_32(pagelist, struct_len);
}
- ceph_pagelist_encode_string(pagelist, path, pathlen);
+ ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen);
ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2));
ceph_locks_to_pagelist(flocks, pagelist,
num_fcntl_locks, num_flock_locks);
@@ -4741,17 +4785,17 @@ out_freeflocks:
} else {
err = ceph_pagelist_reserve(pagelist,
sizeof(u64) + sizeof(u32) +
- pathlen + sizeof(rec.v1));
+ path_info.pathlen + sizeof(rec.v1));
if (err)
goto out_err;
ceph_pagelist_encode_64(pagelist, ceph_ino(inode));
- ceph_pagelist_encode_string(pagelist, path, pathlen);
+ ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen);
ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1));
}
out_err:
- ceph_mdsc_free_path(path, pathlen);
+ ceph_mdsc_free_path_info(&path_info);
if (!err)
recon_state->nr_caps++;
return err;
@@ -5611,11 +5655,19 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc,
u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid);
u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid);
struct ceph_client *cl = mdsc->fsc->client;
+ const char *fs_name = mdsc->fsc->mount_options->mds_namespace;
const char *spath = mdsc->fsc->mount_options->server_path;
bool gid_matched = false;
u32 gid, tlen, len;
int i, j;
+ doutc(cl, "fsname check fs_name=%s match.fs_name=%s\n",
+ fs_name, auth->match.fs_name ? auth->match.fs_name : "");
+ if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) {
+ /* fsname mismatch, try next one */
+ return 0;
+ }
+
doutc(cl, "match.uid %lld\n", auth->match.uid);
if (auth->match.uid != MDS_AUTH_UID_ANY) {
if (auth->match.uid != caller_uid)
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 3e2a6fa7c19a..0428a5eaf28c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -617,14 +617,24 @@ extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath,
extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
-static inline void ceph_mdsc_free_path(char *path, int len)
+/*
+ * Structure to group path-related output parameters for build_*_path functions
+ */
+struct ceph_path_info {
+ const char *path;
+ int pathlen;
+ struct ceph_vino vino;
+ bool freepath;
+};
+
+static inline void ceph_mdsc_free_path_info(const struct ceph_path_info *path_info)
{
- if (!IS_ERR_OR_NULL(path))
- __putname(path - (PATH_MAX - 1 - len));
+ if (path_info && path_info->freepath && !IS_ERR_OR_NULL(path_info->path))
+ __putname((char *)path_info->path - (PATH_MAX - 1 - path_info->pathlen));
}
extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc,
- struct dentry *dentry, int *plen, u64 *base,
+ struct dentry *dentry, struct ceph_path_info *path_info,
int for_wire);
extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 8109aba66e02..2c7b151a7c95 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -353,10 +353,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
__decode_and_drop_type(p, end, u8, bad_ext);
}
if (mdsmap_ev >= 8) {
+ u32 fsname_len;
/* enabled */
ceph_decode_8_safe(p, end, m->m_enabled, bad_ext);
/* fs_name */
- ceph_decode_skip_string(p, end, bad_ext);
+ ceph_decode_32_safe(p, end, fsname_len, bad_ext);
+
+ /* validate fsname against mds_namespace */
+ if (!namespace_equals(mdsc->fsc->mount_options, *p,
+ fsname_len)) {
+ pr_warn_client(cl, "fsname %*pE doesn't match mds_namespace %s\n",
+ (int)fsname_len, (char *)*p,
+ mdsc->fsc->mount_options->mds_namespace);
+ goto bad;
+ }
+ /* skip fsname after validation */
+ ceph_decode_skip_n(p, end, fsname_len, bad);
}
/* damaged */
if (mdsmap_ev >= 9) {
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c3eb651862c5..ad0cf177e75a 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -246,20 +246,6 @@ static void canonicalize_path(char *path)
path[j] = '\0';
}
-/*
- * Check if the mds namespace in ceph_mount_options matches
- * the passed in namespace string. First time match (when
- * ->mds_namespace is NULL) is treated specially, since
- * ->mds_namespace needs to be initialized by the caller.
- */
-static int namespace_equals(struct ceph_mount_options *fsopt,
- const char *namespace, size_t len)
-{
- return !(fsopt->mds_namespace &&
- (strlen(fsopt->mds_namespace) != len ||
- strncmp(fsopt->mds_namespace, namespace, len)));
-}
-
static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end,
struct fs_context *fc)
{
@@ -862,7 +848,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
fsc->inode_wq = alloc_workqueue("ceph-inode", WQ_UNBOUND, 0);
if (!fsc->inode_wq)
goto fail_client;
- fsc->cap_wq = alloc_workqueue("ceph-cap", 0, 1);
+ fsc->cap_wq = alloc_workqueue("ceph-cap", WQ_PERCPU, 1);
if (!fsc->cap_wq)
goto fail_inode_wq;
@@ -1042,7 +1028,7 @@ static const struct super_operations ceph_super_ops = {
.alloc_inode = ceph_alloc_inode,
.free_inode = ceph_free_inode,
.write_inode = ceph_write_inode,
- .drop_inode = generic_delete_inode,
+ .drop_inode = inode_just_drop,
.evict_inode = ceph_evict_inode,
.sync_fs = ceph_sync_fs,
.put_super = ceph_put_super,
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index cf176aab0f82..a1f781c46b41 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -104,6 +104,20 @@ struct ceph_mount_options {
struct fscrypt_dummy_policy dummy_enc_policy;
};
+/*
+ * Check if the mds namespace in ceph_mount_options matches
+ * the passed in namespace string. First time match (when
+ * ->mds_namespace is NULL) is treated specially, since
+ * ->mds_namespace needs to be initialized by the caller.
+ */
+static inline int namespace_equals(struct ceph_mount_options *fsopt,
+ const char *namespace, size_t len)
+{
+ return !(fsopt->mds_namespace &&
+ (strlen(fsopt->mds_namespace) != len ||
+ strncmp(fsopt->mds_namespace, namespace, len)));
+}
+
/* mount state */
enum {
CEPH_MOUNT_MOUNTING,
@@ -463,6 +477,7 @@ struct ceph_inode_info {
unsigned long i_work_mask;
#ifdef CONFIG_FS_ENCRYPTION
+ struct fscrypt_inode_info *i_crypt_info;
u32 fscrypt_auth_len;
u32 fscrypt_file_len;
u8 *fscrypt_auth;
@@ -638,7 +653,8 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
#define CEPH_I_FLUSH_SNAPS (1 << 8) /* need flush snapss */
#define CEPH_I_ERROR_WRITE (1 << 9) /* have seen write errors */
#define CEPH_I_ERROR_FILELOCK (1 << 10) /* have seen file lock errors */
-#define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */
+#define CEPH_I_ODIRECT_BIT (11) /* inode in direct I/O mode */
+#define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT)
#define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */
#define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT)
#define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */
generated by cgit (git 2.34.1) at 2025-10-12 14:53:02 +0000