@@ -839,13 +839,6 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
goto out;
}
- err = ceph_pre_init_acls(dir, &mode, &as_ctx);
- if (err < 0)
- goto out;
- err = ceph_security_init_secctx(dentry, mode, &as_ctx);
- if (err < 0)
- goto out;
-
dout("mknod in dir %p dentry %p mode 0%ho rdev %d\n",
dir, dentry, mode, rdev);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
@@ -853,6 +846,14 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
err = PTR_ERR(req);
goto out;
}
+
+ req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+ if (IS_ERR(req->r_new_inode)) {
+ err = PTR_ERR(req->r_new_inode);
+ req->r_new_inode = NULL;
+ goto out_req;
+ }
+
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
req->r_parent = dir;
@@ -868,6 +869,7 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
+out_req:
ceph_mdsc_put_request(req);
out:
if (!err)
@@ -890,6 +892,7 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_mds_request *req;
struct ceph_acl_sec_ctx as_ctx = {};
+ umode_t mode = S_IFLNK | 0777;
int err;
if (ceph_snap(dir) != CEPH_NOSNAP)
@@ -900,21 +903,24 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
goto out;
}
- err = ceph_security_init_secctx(dentry, S_IFLNK | 0777, &as_ctx);
- if (err < 0)
- goto out;
-
dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
+
+ req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+ if (IS_ERR(req->r_new_inode)) {
+ err = PTR_ERR(req->r_new_inode);
+ req->r_new_inode = NULL;
+ goto out_req;
+ }
+
req->r_path2 = kstrdup(dest, GFP_KERNEL);
if (!req->r_path2) {
err = -ENOMEM;
- ceph_mdsc_put_request(req);
- goto out;
+ goto out_req;
}
req->r_parent = dir;
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
@@ -929,6 +935,7 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
+out_req:
ceph_mdsc_put_request(req);
out:
if (err)
@@ -963,13 +970,6 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out;
}
- mode |= S_IFDIR;
- err = ceph_pre_init_acls(dir, &mode, &as_ctx);
- if (err < 0)
- goto out;
- err = ceph_security_init_secctx(dentry, mode, &as_ctx);
- if (err < 0)
- goto out;
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req)) {
@@ -977,6 +977,14 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out;
}
+ mode |= S_IFDIR;
+ req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+ if (IS_ERR(req->r_new_inode)) {
+ err = PTR_ERR(req->r_new_inode);
+ req->r_new_inode = NULL;
+ goto out_req;
+ }
+
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
req->r_parent = dir;
@@ -993,6 +1001,7 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
!req->r_reply_info.head->is_target &&
!req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
+out_req:
ceph_mdsc_put_request(req);
out:
if (!err)
@@ -565,7 +565,8 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
ceph_mdsc_release_dir_caps(req);
}
-static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
+static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
+ struct dentry *dentry,
struct file *file, umode_t mode,
struct ceph_mds_request *req,
struct ceph_acl_sec_ctx *as_ctx,
@@ -576,17 +577,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
struct ceph_mds_reply_inode in = { };
struct ceph_mds_reply_info_in iinfo = { .in = &in };
struct ceph_inode_info *ci = ceph_inode(dir);
- struct inode *inode;
struct timespec64 now;
struct ceph_vino vino = { .ino = req->r_deleg_ino,
.snap = CEPH_NOSNAP };
ktime_get_real_ts64(&now);
- inode = ceph_get_inode(dentry->d_sb, vino);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
-
iinfo.inline_version = CEPH_INLINE_NONE;
iinfo.change_attr = 1;
ceph_encode_timespec64(&iinfo.btime, &now);
@@ -622,8 +618,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
ceph_dir_clear_complete(dir);
if (!d_unhashed(dentry))
d_drop(dentry);
- if (inode->i_state & I_NEW)
- discard_new_inode(inode);
+ discard_new_inode(inode);
} else {
struct dentry *dn;
@@ -663,6 +658,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
+ struct inode *new_inode = NULL;
struct dentry *dn;
struct ceph_acl_sec_ctx as_ctx = {};
bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
@@ -675,21 +671,21 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
if (dentry->d_name.len > NAME_MAX)
return -ENAMETOOLONG;
-
+retry:
if (flags & O_CREAT) {
if (ceph_quota_is_max_files_exceeded(dir))
return -EDQUOT;
- err = ceph_pre_init_acls(dir, &mode, &as_ctx);
- if (err < 0)
- return err;
- err = ceph_security_init_secctx(dentry, mode, &as_ctx);
- if (err < 0)
+
+ new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
+ if (IS_ERR(new_inode)) {
+ err = PTR_ERR(new_inode);
goto out_ctx;
+ }
} else if (!d_in_lookup(dentry)) {
/* If it's not being looked up, it's negative */
return -ENOENT;
}
-retry:
+
/* do the open */
req = prepare_open_request(dir->i_sb, flags, mode);
if (IS_ERR(req)) {
@@ -713,21 +709,38 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
req->r_pagelist = as_ctx.pagelist;
as_ctx.pagelist = NULL;
}
- if (try_async &&
- (req->r_dir_caps =
- try_prep_async_create(dir, dentry, &lo,
- &req->r_deleg_ino))) {
+
+ if (try_async && (req->r_dir_caps =
+ try_prep_async_create(dir, dentry, &lo, &req->r_deleg_ino))) {
+ struct ceph_vino vino = { .ino = req->r_deleg_ino,
+ .snap = CEPH_NOSNAP };
+
set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL);
req->r_callback = ceph_async_create_cb;
+
+ /* Hash inode before RPC */
+ new_inode = ceph_get_inode(dir->i_sb, vino, new_inode);
+ if (IS_ERR(new_inode)) {
+ err = PTR_ERR(new_inode);
+ new_inode = NULL;
+ goto out_req;
+ }
+ WARN_ON_ONCE(!(new_inode->i_state & I_NEW));
+
err = ceph_mdsc_submit_request(mdsc, dir, req);
if (!err) {
- err = ceph_finish_async_create(dir, dentry,
+ err = ceph_finish_async_create(dir, new_inode, dentry,
file, mode, req,
&as_ctx, &lo);
+ new_inode = NULL;
} else if (err == -EJUKEBOX) {
restore_deleg_ino(dir, req->r_deleg_ino);
ceph_mdsc_put_request(req);
+ discard_new_inode(new_inode);
+ ceph_release_acl_sec_ctx(&as_ctx);
+ memset(&as_ctx, 0, sizeof(as_ctx));
+ new_inode = NULL;
try_async = false;
goto retry;
}
@@ -736,6 +749,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
}
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
+ req->r_new_inode = new_inode;
+ new_inode = NULL;
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
@@ -773,6 +788,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
}
out_req:
ceph_mdsc_put_request(req);
+ iput(new_inode);
out_ctx:
ceph_release_acl_sec_ctx(&as_ctx);
dout("atomic_open result=%d\n", err);
@@ -52,15 +52,67 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
return 0;
}
-struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
+/**
+ * ceph_new_inode - allocate a new inode in advance of an expected create
+ * @dir: parent directory for new inode
+ * @mode: mode of new inode
+ */
+struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
+ umode_t *mode, struct ceph_acl_sec_ctx *as_ctx)
{
+ int err;
struct inode *inode;
- inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare,
- ceph_set_ino_cb, &vino);
+ inode = new_inode_pseudo(dir->i_sb);
if (!inode)
return ERR_PTR(-ENOMEM);
+ if (!S_ISLNK(*mode)) {
+ err = ceph_pre_init_acls(dir, mode, as_ctx);
+ if (err < 0)
+ goto out_err;
+ }
+
+ err = ceph_security_init_secctx(dentry, *mode, as_ctx);
+ if (err < 0)
+ goto out_err;
+
+ inode->i_state = 0;
+ inode->i_mode = *mode;
+ return inode;
+out_err:
+ iput(inode);
+ return ERR_PTR(err);
+}
+
+/**
+ * ceph_get_inode - find or create/hash a new inode
+ * @sb: superblock to search and allocate in
+ * @vino: vino to search for
+ * @new: optional new inode to insert if one isn't found (may be NULL)
+ *
+ * Search for or insert a new inode into the hash for the given vino, and return a
+ * reference to it. If new is non-NULL, its reference is consumed.
+ */
+struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino, struct inode *new)
+{
+ struct inode *inode;
+
+ if (new) {
+ inode = inode_insert5(new, (unsigned long)vino.ino, ceph_ino_compare,
+ ceph_set_ino_cb, &vino);
+ if (inode != new)
+ iput(new);
+ } else {
+ inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare,
+ ceph_set_ino_cb, &vino);
+ }
+
+ if (!inode) {
+ dout("No inode found for %llx.%llx\n", vino.ino, vino.snap);
+ return ERR_PTR(-ENOMEM);
+ }
+
dout("get_inode on %llu=%llx.%llx got %p new %d\n", ceph_present_inode(inode),
ceph_vinop(inode), inode, !!(inode->i_state & I_NEW));
return inode;
@@ -75,7 +127,7 @@ struct inode *ceph_get_snapdir(struct inode *parent)
.ino = ceph_ino(parent),
.snap = CEPH_SNAPDIR,
};
- struct inode *inode = ceph_get_inode(parent->i_sb, vino);
+ struct inode *inode = ceph_get_inode(parent->i_sb, vino, NULL);
struct ceph_inode_info *ci = ceph_inode(inode);
BUG_ON(!S_ISDIR(parent->i_mode));
@@ -1322,7 +1374,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
- in = ceph_get_inode(sb, tvino);
+ in = ceph_get_inode(sb, tvino, xchg(&req->r_new_inode, NULL));
if (IS_ERR(in)) {
err = PTR_ERR(in);
goto done;
@@ -1516,7 +1568,7 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
vino.ino = le64_to_cpu(rde->inode.in->ino);
vino.snap = le64_to_cpu(rde->inode.in->snapid);
- in = ceph_get_inode(req->r_dentry->d_sb, vino);
+ in = ceph_get_inode(req->r_dentry->d_sb, vino, NULL);
if (IS_ERR(in)) {
err = PTR_ERR(in);
dout("new_inode badness got %d\n", err);
@@ -1720,7 +1772,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
if (d_really_is_positive(dn)) {
in = d_inode(dn);
} else {
- in = ceph_get_inode(parent->d_sb, tvino);
+ in = ceph_get_inode(parent->d_sb, tvino, NULL);
if (IS_ERR(in)) {
dout("new_inode badness\n");
d_drop(dn);
@@ -820,6 +820,7 @@ void ceph_mdsc_release_request(struct kref *kref)
ceph_async_iput(req->r_parent);
}
ceph_async_iput(req->r_target_inode);
+ ceph_async_iput(req->r_new_inode);
if (req->r_dentry)
dput(req->r_dentry);
if (req->r_old_dentry)
@@ -260,6 +260,7 @@ struct ceph_mds_request {
struct inode *r_parent; /* parent dir inode */
struct inode *r_target_inode; /* resulting inode */
+ struct inode *r_new_inode; /* new inode (for creates) */
#define CEPH_MDS_R_DIRECT_IS_HASH (1) /* r_direct_hash is valid */
#define CEPH_MDS_R_ABORTED (2) /* call was aborted */
@@ -936,6 +936,7 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
/* inode.c */
struct ceph_mds_reply_info_in;
struct ceph_mds_reply_dirfrag;
+struct ceph_acl_sec_ctx;
extern const struct inode_operations ceph_file_iops;
@@ -943,8 +944,10 @@ extern struct inode *ceph_alloc_inode(struct super_block *sb);
extern void ceph_evict_inode(struct inode *inode);
extern void ceph_free_inode(struct inode *inode);
+struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
+ umode_t *mode, struct ceph_acl_sec_ctx *as_ctx);
extern struct inode *ceph_get_inode(struct super_block *sb,
- struct ceph_vino vino);
+ struct ceph_vino vino, struct inode *new);
extern struct inode *ceph_get_snapdir(struct inode *parent);
extern int ceph_fill_file_size(struct inode *inode, int issued,
u32 truncate_seq, u64 truncate_size, u64 size);
When creating a new inode, we need to determine the crypto context before we can transmit the RPC. The fscrypt API has a routine for getting a crypto context before a create occurs, but it requires an inode. Change the ceph code to preallocate an inode in advance of a create of any sort (open(), mknod(), symlink(), etc). Move the existing code that generates the ACL and SELinux blobs into this routine since that's mostly common across all the different codepaths. In most cases, we just want to allow ceph_fill_trace to use that inode after the reply comes in, so add a new field to the MDS request for it (r_new_inode). The async create codepath is a bit different though. In that case, we want to hash the inode in advance of the RPC so that it can be used before the reply comes in. If the call subsequently fails with -EJUKEBOX, then just put the references and clean up the as_ctx. Note that with this change, we now need to regenerate the as_ctx when this occurs, but it's quite rare for it to happen. Signed-off-by: Jeff Layton <jlayton@kernel.org> --- fs/ceph/dir.c | 49 ++++++++++++++++++-------------- fs/ceph/file.c | 56 +++++++++++++++++++++++-------------- fs/ceph/inode.c | 66 +++++++++++++++++++++++++++++++++++++++----- fs/ceph/mds_client.c | 1 + fs/ceph/mds_client.h | 1 + fs/ceph/super.h | 5 +++- 6 files changed, 130 insertions(+), 48 deletions(-)