aboutsummaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/addr.c3
-rw-r--r--fs/ceph/debugfs.c1
-rw-r--r--fs/ceph/dir.c46
-rw-r--r--fs/ceph/file.c74
-rw-r--r--fs/ceph/inode.c15
-rw-r--r--fs/ceph/ioctl.c3
-rw-r--r--fs/ceph/mds_client.c23
-rw-r--r--fs/ceph/snap.c18
-rw-r--r--fs/ceph/super.c3
-rw-r--r--fs/ceph/super.h10
-rw-r--r--fs/ceph/xattr.c1
11 files changed, 92 insertions, 105 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8b67304e4b80..452e71a1b753 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1184,6 +1184,9 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
loff_t size, len;
int ret;
+ /* Update time before taking page lock */
+ file_update_time(vma->vm_file);
+
size = i_size_read(inode);
if (off + PAGE_CACHE_SIZE <= size)
len = PAGE_CACHE_SIZE;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index fb962efdacee..6d59006bfa27 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -201,6 +201,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
int err = -ENOMEM;
dout("ceph_fs_debugfs_init\n");
+ BUG_ON(!fsc->client->debugfs_dir);
fsc->debugfs_congestion_kb =
debugfs_create_file("writeback_congestion_kb",
0600,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 3e8094be4604..e5b77319c97b 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -51,8 +51,7 @@ int ceph_init_dentry(struct dentry *dentry)
goto out_unlock;
}
- if (dentry->d_parent == NULL || /* nfs fh_to_dentry */
- ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
+ if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
d_set_d_op(dentry, &ceph_dentry_ops);
else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
@@ -79,7 +78,7 @@ struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
return NULL;
spin_lock(&dentry->d_lock);
- if (dentry->d_parent) {
+ if (!IS_ROOT(dentry)) {
inode = dentry->d_parent->d_inode;
ihold(inode);
}
@@ -576,7 +575,7 @@ static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
* the MDS so that it gets our 'caps wanted' value in a single op.
*/
static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -594,14 +593,6 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
if (err < 0)
return ERR_PTR(err);
- /* open (but not create!) intent? */
- if (nd &&
- (nd->flags & LOOKUP_OPEN) &&
- !(nd->intent.open.flags & O_CREAT)) {
- int mode = nd->intent.open.create_mode & ~current->fs->umask;
- return ceph_lookup_open(dir, dentry, nd, mode, 1);
- }
-
/* can we conclude ENOENT locally? */
if (dentry->d_inode == NULL) {
struct ceph_inode_info *ci = ceph_inode(dir);
@@ -648,7 +639,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
*/
int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
{
- struct dentry *result = ceph_lookup(dir, dentry, NULL);
+ struct dentry *result = ceph_lookup(dir, dentry, 0);
if (result && !IS_ERR(result)) {
/*
@@ -700,25 +691,9 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
}
static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
- dout("create in dir %p dentry %p name '%.*s'\n",
- dir, dentry, dentry->d_name.len, dentry->d_name.name);
-
- if (ceph_snap(dir) != CEPH_NOSNAP)
- return -EROFS;
-
- if (nd) {
- BUG_ON((nd->flags & LOOKUP_OPEN) == 0);
- dentry = ceph_lookup_open(dir, dentry, nd, mode, 0);
- /* hrm, what should i do here if we get aliased? */
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
- return 0;
- }
-
- /* fall back to mknod */
- return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0);
+ return ceph_mknod(dir, dentry, mode, 0);
}
static int ceph_symlink(struct inode *dir, struct dentry *dentry,
@@ -1028,12 +1003,12 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
/*
* Check if cached dentry can be trusted.
*/
-static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int valid = 0;
struct inode *dir;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
@@ -1080,7 +1055,7 @@ static void ceph_d_release(struct dentry *dentry)
}
static int ceph_snapdir_d_revalidate(struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
/*
* Eventually, we'll want to revalidate snapped metadata
@@ -1140,7 +1115,7 @@ static void ceph_d_prune(struct dentry *dentry)
dout("ceph_d_prune %p\n", dentry);
/* do we have a valid parent? */
- if (!dentry->d_parent || IS_ROOT(dentry))
+ if (IS_ROOT(dentry))
return;
/* if we are not hashed, we don't affect D_COMPLETE */
@@ -1357,6 +1332,7 @@ const struct inode_operations ceph_dir_iops = {
.rmdir = ceph_unlink,
.rename = ceph_rename,
.create = ceph_create,
+ .atomic_open = ceph_atomic_open,
};
const struct dentry_operations ceph_dentry_ops = {
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 988d4f302e48..ecebbc09bfc7 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -4,6 +4,7 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/file.h>
+#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/writeback.h>
@@ -106,9 +107,6 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
}
/*
- * If the filp already has private_data, that means the file was
- * already opened by intent during lookup, and we do nothing.
- *
* If we already have the requisite capabilities, we can satisfy
* the open request locally (no need to request new caps from the
* MDS). We do, however, need to inform the MDS (asynchronously)
@@ -207,36 +205,34 @@ out:
/*
- * Do a lookup + open with a single request.
- *
- * If this succeeds, but some subsequent check in the vfs
- * may_open() fails, the struct *file gets cleaned up (i.e.
- * ceph_release gets called). So fear not!
+ * Do a lookup + open with a single request. If we get a non-existent
+ * file or symlink, return 1 so the VFS can retry.
*/
-/*
- * flags
- * path_lookup_open -> LOOKUP_OPEN
- * path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE
- */
-struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd, int mode,
- int locked_dir)
+int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
- struct file *file;
struct ceph_mds_request *req;
- struct dentry *ret;
+ struct dentry *dn;
int err;
- int flags = nd->intent.open.flags;
- dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n",
- dentry, dentry->d_name.len, dentry->d_name.name, flags, mode);
+ dout("atomic_open %p dentry %p '%.*s' %s flags %d mode 0%o\n",
+ dir, dentry, dentry->d_name.len, dentry->d_name.name,
+ d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
+
+ if (dentry->d_name.len > NAME_MAX)
+ return -ENAMETOOLONG;
+
+ err = ceph_init_dentry(dentry);
+ if (err < 0)
+ return err;
/* do the open */
req = prepare_open_request(dir->i_sb, flags, mode);
if (IS_ERR(req))
- return ERR_CAST(req);
+ return PTR_ERR(req);
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
if (flags & O_CREAT) {
@@ -248,20 +244,32 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
err = ceph_handle_snapdir(req, dentry, err);
- if (err)
- goto out;
- if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
+ if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
+
+ if (d_unhashed(dentry)) {
+ dn = ceph_finish_lookup(req, dentry, err);
+ if (IS_ERR(dn))
+ err = PTR_ERR(dn);
+ } else {
+ /* we were given a hashed negative dentry */
+ dn = NULL;
+ }
if (err)
- goto out;
- file = lookup_instantiate_filp(nd, req->r_dentry, ceph_open);
- if (IS_ERR(file))
- err = PTR_ERR(file);
-out:
- ret = ceph_finish_lookup(req, dentry, err);
+ goto out_err;
+ if (dn || dentry->d_inode == NULL || S_ISLNK(dentry->d_inode->i_mode)) {
+ /* make vfs retry on splice, ENOENT, or symlink */
+ dout("atomic_open finish_no_open on dn %p\n", dn);
+ err = finish_no_open(file, dn);
+ } else {
+ dout("atomic_open finish_open on dn %p\n", dn);
+ err = finish_open(file, dentry, ceph_open, opened);
+ }
+
+out_err:
ceph_mdsc_put_request(req);
- dout("ceph_lookup_open result=%p\n", ret);
- return ret;
+ dout("atomic_open result=%d\n", err);
+ return err;
}
int ceph_release(struct inode *inode, struct file *file)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9fff9f3b17e4..4b5762ef7c2b 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -992,11 +992,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
if (rinfo->head->is_dentry) {
struct inode *dir = req->r_locked_dir;
- err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
- session, req->r_request_started, -1,
- &req->r_caps_reservation);
- if (err < 0)
- return err;
+ if (dir) {
+ err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
+ session, req->r_request_started, -1,
+ &req->r_caps_reservation);
+ if (err < 0)
+ return err;
+ } else {
+ WARN_ON_ONCE(1);
+ }
}
/*
@@ -1004,6 +1008,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
* will have trouble splicing in the virtual snapdir later
*/
if (rinfo->head->is_dentry && !req->r_aborted &&
+ req->r_locked_dir &&
(rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
fsc->mount_options->snapdir_name,
req->r_dentry->d_name.len))) {
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 8e3fb69fbe62..1396ceb46797 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -42,7 +42,8 @@ static long __validate_layout(struct ceph_mds_client *mdsc,
/* validate striping parameters */
if ((l->object_size & ~PAGE_MASK) ||
(l->stripe_unit & ~PAGE_MASK) ||
- ((unsigned)l->object_size % (unsigned)l->stripe_unit))
+ (l->stripe_unit != 0 &&
+ ((unsigned)l->object_size % (unsigned)l->stripe_unit)))
return -EINVAL;
/* make sure it's a valid data pool */
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 200bc87eceb1..a5a735422aa7 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -10,6 +10,7 @@
#include "super.h"
#include "mds_client.h"
+#include <linux/ceph/ceph_features.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/pagelist.h>
@@ -394,11 +395,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
s->s_seq = 0;
mutex_init(&s->s_mutex);
- ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
- s->s_con.private = s;
- s->s_con.ops = &mds_con_ops;
- s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
- s->s_con.peer_name.num = cpu_to_le64(mds);
+ ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr);
spin_lock_init(&s->s_gen_ttl_lock);
s->s_cap_gen = 0;
@@ -440,7 +437,8 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
mdsc->sessions[mds] = s;
atomic_inc(&s->s_ref); /* one ref to sessions[], one to caller */
- ceph_con_open(&s->s_con, ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
+ ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
+ ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
return s;
@@ -1472,11 +1470,6 @@ retry:
else
len += 1 + temp->d_name.len;
temp = temp->d_parent;
- if (temp == NULL) {
- rcu_read_unlock();
- pr_err("build_path corrupt dentry %p\n", dentry);
- return ERR_PTR(-EINVAL);
- }
}
rcu_read_unlock();
if (len)
@@ -1513,12 +1506,6 @@ retry:
if (pos)
path[--pos] = '/';
temp = temp->d_parent;
- if (temp == NULL) {
- rcu_read_unlock();
- pr_err("build_path corrupt dentry\n");
- kfree(path);
- return ERR_PTR(-EINVAL);
- }
}
rcu_read_unlock();
if (pos != 0 || read_seqretry(&rename_lock, seq)) {
@@ -2531,7 +2518,9 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
session->s_state = CEPH_MDS_SESSION_RECONNECTING;
session->s_seq = 0;
+ ceph_con_close(&session->s_con);
ceph_con_open(&session->s_con,
+ CEPH_ENTITY_TYPE_MDS, mds,
ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
/* replay unsafe requests */
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index e5206fc76562..cbb2f54a3019 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -296,8 +296,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
struct ceph_snap_realm *parent = realm->parent;
struct ceph_snap_context *snapc;
int err = 0;
- int i;
- int num = realm->num_prior_parent_snaps + realm->num_snaps;
+ u32 num = realm->num_prior_parent_snaps + realm->num_snaps;
/*
* build parent context, if it hasn't been built.
@@ -321,11 +320,11 @@ static int build_snap_context(struct ceph_snap_realm *realm)
realm->cached_context->seq == realm->seq &&
(!parent ||
realm->cached_context->seq >= parent->cached_context->seq)) {
- dout("build_snap_context %llx %p: %p seq %lld (%d snaps)"
+ dout("build_snap_context %llx %p: %p seq %lld (%u snaps)"
" (unchanged)\n",
realm->ino, realm, realm->cached_context,
realm->cached_context->seq,
- realm->cached_context->num_snaps);
+ (unsigned int) realm->cached_context->num_snaps);
return 0;
}
@@ -342,6 +341,8 @@ static int build_snap_context(struct ceph_snap_realm *realm)
num = 0;
snapc->seq = realm->seq;
if (parent) {
+ u32 i;
+
/* include any of parent's snaps occurring _after_ my
parent became my parent */
for (i = 0; i < parent->cached_context->num_snaps; i++)
@@ -361,8 +362,9 @@ static int build_snap_context(struct ceph_snap_realm *realm)
sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL);
snapc->num_snaps = num;
- dout("build_snap_context %llx %p: %p seq %lld (%d snaps)\n",
- realm->ino, realm, snapc, snapc->seq, snapc->num_snaps);
+ dout("build_snap_context %llx %p: %p seq %lld (%u snaps)\n",
+ realm->ino, realm, snapc, snapc->seq,
+ (unsigned int) snapc->num_snaps);
if (realm->cached_context)
ceph_put_snap_context(realm->cached_context);
@@ -402,9 +404,9 @@ static void rebuild_snap_realms(struct ceph_snap_realm *realm)
* helper to allocate and decode an array of snapids. free prior
* instance, if any.
*/
-static int dup_array(u64 **dst, __le64 *src, int num)
+static int dup_array(u64 **dst, __le64 *src, u32 num)
{
- int i;
+ u32 i;
kfree(*dst);
if (num) {
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 1e67dd7305a4..b982239f38f9 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -18,6 +18,7 @@
#include "super.h"
#include "mds_client.h"
+#include <linux/ceph/ceph_features.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/auth.h>
@@ -871,7 +872,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
if (ceph_test_opt(fsc->client, NOSHARE))
compare_super = NULL;
- sb = sget(fs_type, compare_super, ceph_set_super, fsc);
+ sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc);
if (IS_ERR(sb)) {
res = ERR_CAST(sb);
goto out;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fc35036d258d..66ebe720e40d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -612,9 +612,9 @@ struct ceph_snap_realm {
u64 parent_since; /* snapid when our current parent became so */
u64 *prior_parent_snaps; /* snaps inherited from any parents we */
- int num_prior_parent_snaps; /* had prior to parent_since */
+ u32 num_prior_parent_snaps; /* had prior to parent_since */
u64 *snaps; /* snaps specific to this realm */
- int num_snaps;
+ u32 num_snaps;
struct ceph_snap_realm *parent;
struct list_head children; /* list of child realms */
@@ -806,9 +806,9 @@ extern int ceph_copy_from_page_vector(struct page **pages,
loff_t off, size_t len);
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
extern int ceph_open(struct inode *inode, struct file *file);
-extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd, int mode,
- int locked_dir);
+extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened);
extern int ceph_release(struct inode *inode, struct file *filp);
/* dir.c */
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 785cb3057c95..2c2ae5be9902 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -457,6 +457,7 @@ start:
for (i = 0; i < numattr; i++)
kfree(xattrs[i]);
kfree(xattrs);
+ xattrs = NULL;
goto start;
}
err = -EIO;
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-30 14:11:43 +0000