diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 2b184563cd32e8ca6c45ffbad4dcad1626429194..405b66e0904021531eba4050242ff7a9187f4571 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -2662,7 +2662,7 @@ static int rbd_img_fill_nodata(struct rbd_img_request *img_req,
u64 off, u64 len)
{
struct ceph_file_extent ex = { off, len };
- union rbd_img_fill_iter dummy;
+ union rbd_img_fill_iter dummy = {};
struct rbd_img_fill_ctx fctx = {
.pos_type = OBJ_REQUEST_NODATA,
.pos = &dummy,
@@ -7143,7 +7143,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
if (rc)
goto err_out_image_lock;
- add_disk(rbd_dev->disk);
+ device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL);
/* see rbd_init_disk() */
blk_put_queue(rbd_dev->disk->queue);
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index c1da294418d14b86ea77feaa7027ea880b605ed3..0a0823d378dbb059698bd81ffaf82de0e7f3865c 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_CEPH_FS) += ceph.o
ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
export.o caps.o snap.o xattr.o quota.o io.o \
mds_client.o mdsmap.o strings.o ceph_frag.o \
- debugfs.o
+ debugfs.o util.o
ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index aa55f412a6e35c01d6024b62f2031b619a0e3a08..26be6520d3fb1ec43799ff42bf7541f9a6ffa282 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -222,8 +222,8 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
if (err)
goto out_err;
- err = ceph_pagelist_encode_string(pagelist,
- XATTR_NAME_POSIX_ACL_DEFAULT, len);
+ ceph_pagelist_encode_string(pagelist,
+ XATTR_NAME_POSIX_ACL_DEFAULT, len);
err = posix_acl_to_xattr(&init_user_ns, default_acl,
tmp_buf, val_size2);
if (err < 0)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 9d09bb53c1ab4a36268eb583690ef37b2f08387c..28ae0c1347004c46be89a15ec8d28693e6866f0d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -908,7 +908,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
ci_node);
if (!__cap_is_valid(cap))
continue;
- __touch_cap(cap);
+ if (cap->issued & mask)
+ __touch_cap(cap);
}
}
return 1;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index c281f32b54f7b6121de9dda389bca07fb9395042..fb7cabd98e7bb0cc3c44f028824206a9676bba21 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -33,7 +33,7 @@ static int mdsmap_show(struct seq_file *s, void *p)
seq_printf(s, "max_mds %d\n", mdsmap->m_max_mds);
seq_printf(s, "session_timeout %d\n", mdsmap->m_session_timeout);
seq_printf(s, "session_autoclose %d\n", mdsmap->m_session_autoclose);
- for (i = 0; i < mdsmap->m_num_mds; i++) {
+ for (i = 0; i < mdsmap->possible_max_rank; i++) {
struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr;
int state = mdsmap->m_info[i].state;
seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 2e4764fd187271856086274fe6234389e04172a2..d0cd0aba584328945feba4c428a8e3d54629e1b1 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1186,7 +1186,7 @@ void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di)
struct dentry *dn = di->dentry;
struct ceph_mds_client *mdsc;
- dout("dentry_dir_lease_touch %p %p '%pd' (offset %lld)\n",
+ dout("dentry_dir_lease_touch %p %p '%pd' (offset 0x%llx)\n",
di, dn, dn, di->offset);
if (!list_empty(&di->lease_list)) {
@@ -1567,7 +1567,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
inode = d_inode(dentry);
}
- dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
+ dout("d_revalidate %p '%pd' inode %p offset 0x%llx\n", dentry,
dentry, inode, ceph_dentry(dentry)->offset);
/* always trust cached snapped dentries, snapdir dentry */
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 11929d2bb594c8d5f3d68c7a93946a8966da836f..c3b8e8e0bf17d52c1c2bd90ba093813e22d71906 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1974,6 +1974,9 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
return -EOPNOTSUPP;
+ if (!src_fsc->have_copy_from2)
+ return -EOPNOTSUPP;
+
/*
* Striped file layouts require that we copy partial objects, but the
* OSD copy-from operation only supports full-object copies. Limit
@@ -2101,8 +2104,14 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
CEPH_OSD_OP_FLAG_FADVISE_NOCACHE,
&dst_oid, &dst_oloc,
CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
- CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, 0);
+ CEPH_OSD_OP_FLAG_FADVISE_DONTNEED,
+ dst_ci->i_truncate_seq, dst_ci->i_truncate_size,
+ CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ);
if (err) {
+ if (err == -EOPNOTSUPP) {
+ src_fsc->have_copy_from2 = false;
+ pr_notice("OSDs don't support copy-from2; disabling copy offload\n");
+ }
dout("ceph_osdc_copy_from returned %d\n", err);
if (!ret)
ret = err;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index c07407586ce873f236a1cf61d0ea48efa27590c4..d01710a16a4afa857bf5fac45e1a2ce02eb91525 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -55,11 +55,9 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);
if (!inode)
return ERR_PTR(-ENOMEM);
- if (inode->i_state & I_NEW) {
+ if (inode->i_state & I_NEW)
dout("get_inode created new inode %p %llx.%llx ino %llx\n",
inode, ceph_vinop(inode), (u64)inode->i_ino);
- unlock_new_inode(inode);
- }
dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,
vino.snap, inode);
@@ -88,6 +86,10 @@ struct inode *ceph_get_snapdir(struct inode *parent)
inode->i_fop = &ceph_snapdir_fops;
ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
ci->i_rbytes = 0;
+
+ if (inode->i_state & I_NEW)
+ unlock_new_inode(inode);
+
return inode;
}
@@ -728,8 +730,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
static int fill_inode(struct inode *inode, struct page *locked_page,
struct ceph_mds_reply_info_in *iinfo,
struct ceph_mds_reply_dirfrag *dirinfo,
- struct ceph_mds_session *session,
- unsigned long ttl_from, int cap_fmode,
+ struct ceph_mds_session *session, int cap_fmode,
struct ceph_cap_reservation *caps_reservation)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
@@ -754,8 +755,11 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
info_caps = le32_to_cpu(info->cap.caps);
/* prealloc new cap struct */
- if (info_caps && ceph_snap(inode) == CEPH_NOSNAP)
+ if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) {
new_cap = ceph_get_cap(mdsc, caps_reservation);
+ if (!new_cap)
+ return -ENOMEM;
+ }
/*
* prealloc xattr data, if it looks like we'll need it. only
@@ -1237,7 +1241,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
if (dir) {
err = fill_inode(dir, NULL,
&rinfo->diri, rinfo->dirfrag,
- session, req->r_request_started, -1,
+ session, -1,
&req->r_caps_reservation);
if (err < 0)
goto done;
@@ -1302,18 +1306,22 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
err = PTR_ERR(in);
goto done;
}
- req->r_target_inode = in;
err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
- session, req->r_request_started,
+ session,
(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
- rinfo->head->result == 0) ? req->r_fmode : -1,
+ rinfo->head->result == 0) ? req->r_fmode : -1,
&req->r_caps_reservation);
if (err < 0) {
pr_err("fill_inode badness %p %llx.%llx\n",
in, ceph_vinop(in));
+ if (in->i_state & I_NEW)
+ discard_new_inode(in);
goto done;
}
+ req->r_target_inode = in;
+ if (in->i_state & I_NEW)
+ unlock_new_inode(in);
}
/*
@@ -1493,12 +1501,18 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
continue;
}
rc = fill_inode(in, NULL, &rde->inode, NULL, session,
- req->r_request_started, -1,
- &req->r_caps_reservation);
+ -1, &req->r_caps_reservation);
if (rc < 0) {
pr_err("fill_inode badness on %p got %d\n", in, rc);
err = rc;
+ if (in->i_state & I_NEW) {
+ ihold(in);
+ discard_new_inode(in);
+ }
+ } else if (in->i_state & I_NEW) {
+ unlock_new_inode(in);
}
+
/* avoid calling iput_final() in mds dispatch threads */
ceph_async_iput(in);
}
@@ -1694,19 +1708,24 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
}
ret = fill_inode(in, NULL, &rde->inode, NULL, session,
- req->r_request_started, -1,
- &req->r_caps_reservation);
+ -1, &req->r_caps_reservation);
if (ret < 0) {
pr_err("fill_inode badness on %p\n", in);
if (d_really_is_negative(dn)) {
/* avoid calling iput_final() in mds
* dispatch threads */
+ if (in->i_state & I_NEW) {
+ ihold(in);
+ discard_new_inode(in);
+ }
ceph_async_iput(in);
}
d_drop(dn);
err = ret;
goto next_item;
}
+ if (in->i_state & I_NEW)
+ unlock_new_inode(in);
if (d_really_is_negative(dn)) {
if (ceph_security_xattr_deadlock(in)) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 21ada2c4a88c61e9c501d9b02b280ee515f70963..bbbbddf71326b1cf59ff589c9dcc2ddd93e854f0 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -9,6 +9,7 @@
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/ratelimit.h>
+#include <linux/bits.h>
#include "super.h"
#include "mds_client.h"
@@ -530,6 +531,7 @@ const char *ceph_session_state_name(int s)
case CEPH_MDS_SESSION_OPEN: return "open";
case CEPH_MDS_SESSION_HUNG: return "hung";
case CEPH_MDS_SESSION_CLOSING: return "closing";
+ case CEPH_MDS_SESSION_CLOSED: return "closed";
case CEPH_MDS_SESSION_RESTARTING: return "restarting";
case CEPH_MDS_SESSION_RECONNECTING: return "reconnecting";
case CEPH_MDS_SESSION_REJECTED: return "rejected";
@@ -537,7 +539,7 @@ const char *ceph_session_state_name(int s)
}
}
-static struct ceph_mds_session *get_session(struct ceph_mds_session *s)
+struct ceph_mds_session *ceph_get_mds_session(struct ceph_mds_session *s)
{
if (refcount_inc_not_zero(&s->s_ref)) {
dout("mdsc get_session %p %d -> %d\n", s,
@@ -568,7 +570,7 @@ struct ceph_mds_session *__ceph_lookup_mds_session(struct ceph_mds_client *mdsc,
{
if (mds >= mdsc->max_sessions || !mdsc->sessions[mds])
return NULL;
- return get_session(mdsc->sessions[mds]);
+ return ceph_get_mds_session(mdsc->sessions[mds]);
}
static bool __have_session(struct ceph_mds_client *mdsc, int mds)
@@ -597,7 +599,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
{
struct ceph_mds_session *s;
- if (mds >= mdsc->mdsmap->m_num_mds)
+ if (mds >= mdsc->mdsmap->possible_max_rank)
return ERR_PTR(-EINVAL);
s = kzalloc(sizeof(*s), GFP_NOFS);
@@ -674,7 +676,6 @@ static void __unregister_session(struct ceph_mds_client *mdsc,
dout("__unregister_session mds%d %p\n", s->s_mds, s);
BUG_ON(mdsc->sessions[s->s_mds] != s);
mdsc->sessions[s->s_mds] = NULL;
- s->s_state = 0;
ceph_con_close(&s->s_con);
ceph_put_mds_session(s);
atomic_dec(&mdsc->num_sessions);
@@ -878,7 +879,8 @@ static struct inode *get_nonsnap_parent(struct dentry *dentry)
* Called under mdsc->mutex.
*/
static int __choose_mds(struct ceph_mds_client *mdsc,
- struct ceph_mds_request *req)
+ struct ceph_mds_request *req,
+ bool *random)
{
struct inode *inode;
struct ceph_inode_info *ci;
@@ -888,6 +890,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
u32 hash = req->r_direct_hash;
bool is_hash = test_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags);
+ if (random)
+ *random = false;
+
/*
* is there a specific mds we should try? ignore hint if we have
* no session and the mds is not up (active or recovering).
@@ -895,7 +900,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
if (req->r_resend_mds >= 0 &&
(__have_session(mdsc, req->r_resend_mds) ||
ceph_mdsmap_get_state(mdsc->mdsmap, req->r_resend_mds) > 0)) {
- dout("choose_mds using resend_mds mds%d\n",
+ dout("%s using resend_mds mds%d\n", __func__,
req->r_resend_mds);
return req->r_resend_mds;
}
@@ -913,7 +918,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
rcu_read_lock();
inode = get_nonsnap_parent(req->r_dentry);
rcu_read_unlock();
- dout("__choose_mds using snapdir's parent %p\n", inode);
+ dout("%s using snapdir's parent %p\n", __func__, inode);
}
} else if (req->r_dentry) {
/* ignore race with rename; old or new d_parent is okay */
@@ -933,7 +938,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
/* direct snapped/virtual snapdir requests
* based on parent dir inode */
inode = get_nonsnap_parent(parent);
- dout("__choose_mds using nonsnap parent %p\n", inode);
+ dout("%s using nonsnap parent %p\n", __func__, inode);
} else {
/* dentry target */
inode = d_inode(req->r_dentry);
@@ -949,8 +954,8 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
rcu_read_unlock();
}
- dout("__choose_mds %p is_hash=%d (%d) mode %d\n", inode, (int)is_hash,
- (int)hash, mode);
+ dout("%s %p is_hash=%d (0x%x) mode %d\n", __func__, inode, (int)is_hash,
+ hash, mode);
if (!inode)
goto random;
ci = ceph_inode(inode);
@@ -968,30 +973,33 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
get_random_bytes(&r, 1);
r %= frag.ndist;
mds = frag.dist[r];
- dout("choose_mds %p %llx.%llx "
- "frag %u mds%d (%d/%d)\n",
- inode, ceph_vinop(inode),
- frag.frag, mds,
- (int)r, frag.ndist);
+ dout("%s %p %llx.%llx frag %u mds%d (%d/%d)\n",
+ __func__, inode, ceph_vinop(inode),
+ frag.frag, mds, (int)r, frag.ndist);
if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
- CEPH_MDS_STATE_ACTIVE)
+ CEPH_MDS_STATE_ACTIVE &&
+ !ceph_mdsmap_is_laggy(mdsc->mdsmap, mds))
goto out;
}
/* since this file/dir wasn't known to be
* replicated, then we want to look for the
* authoritative mds. */
- mode = USE_AUTH_MDS;
if (frag.mds >= 0) {
/* choose auth mds */
mds = frag.mds;
- dout("choose_mds %p %llx.%llx "
- "frag %u mds%d (auth)\n",
- inode, ceph_vinop(inode), frag.frag, mds);
+ dout("%s %p %llx.%llx frag %u mds%d (auth)\n",
+ __func__, inode, ceph_vinop(inode),
+ frag.frag, mds);
if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
- CEPH_MDS_STATE_ACTIVE)
- goto out;
+ CEPH_MDS_STATE_ACTIVE) {
+ if (mode == USE_ANY_MDS &&
+ !ceph_mdsmap_is_laggy(mdsc->mdsmap,
+ mds))
+ goto out;
+ }
}
+ mode = USE_AUTH_MDS;
}
}
@@ -1007,7 +1015,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
goto random;
}
mds = cap->session->s_mds;
- dout("choose_mds %p %llx.%llx mds%d (%scap %p)\n",
+ dout("%s %p %llx.%llx mds%d (%scap %p)\n", __func__,
inode, ceph_vinop(inode), mds,
cap == ci->i_auth_cap ? "auth " : "", cap);
spin_unlock(&ci->i_ceph_lock);
@@ -1018,8 +1026,11 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
return mds;
random:
+ if (random)
+ *random = true;
+
mds = ceph_mdsmap_get_random_mds(mdsc->mdsmap);
- dout("choose_mds chose random mds%d\n", mds);
+ dout("%s chose random mds%d\n", __func__, mds);
return mds;
}
@@ -1045,20 +1056,21 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq)
return msg;
}
+static const unsigned char feature_bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED;
+#define FEATURE_BYTES(c) (DIV_ROUND_UP((size_t)feature_bits[c - 1] + 1, 64) * 8)
static void encode_supported_features(void **p, void *end)
{
- static const unsigned char bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED;
- static const size_t count = ARRAY_SIZE(bits);
+ static const size_t count = ARRAY_SIZE(feature_bits);
if (count > 0) {
size_t i;
- size_t size = ((size_t)bits[count - 1] + 64) / 64 * 8;
+ size_t size = FEATURE_BYTES(count);
BUG_ON(*p + 4 + size > end);
ceph_encode_32(p, size);
memset(*p, 0, size);
for (i = 0; i < count; i++)
- ((unsigned char*)(*p))[i / 8] |= 1 << (bits[i] % 8);
+ ((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8);
*p += size;
} else {
BUG_ON(*p + 4 > end);
@@ -1079,6 +1091,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
int metadata_key_count = 0;
struct ceph_options *opt = mdsc->fsc->client->options;
struct ceph_mount_options *fsopt = mdsc->fsc->mount_options;
+ size_t size, count;
void *p, *end;
const char* metadata[][2] = {
@@ -1096,8 +1109,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
strlen(metadata[i][1]);
metadata_key_count++;
}
+
/* supported feature */
- extra_bytes += 4 + 8;
+ size = 0;
+ count = ARRAY_SIZE(feature_bits);
+ if (count > 0)
+ size = FEATURE_BYTES(count);
+ extra_bytes += 4 + size;
/* Allocate the message */
msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes,
@@ -1117,7 +1135,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
* Serialize client metadata into waiting buffer space, using
* the format that userspace expects for map<string, string>
*
- * ClientSession messages with metadata are v2
+ * ClientSession messages with metadata are v3
*/
msg->hdr.version = cpu_to_le16(3);
msg->hdr.compat_version = cpu_to_le16(1);
@@ -1219,7 +1237,7 @@ static void __open_export_target_sessions(struct ceph_mds_client *mdsc,
struct ceph_mds_session *ts;
int i, mds = session->s_mds;
- if (mds >= mdsc->mdsmap->m_num_mds)
+ if (mds >= mdsc->mdsmap->possible_max_rank)
return;
mi = &mdsc->mdsmap->m_info[mds];
@@ -1967,7 +1985,7 @@ void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
if (mdsc->stopping)
return;
- get_session(session);
+ ceph_get_mds_session(session);
if (queue_work(mdsc->fsc->cap_wq,
&session->s_cap_release_work)) {
dout("cap release work queued\n");
@@ -2515,6 +2533,26 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
return 0;
}
+/*
+ * called under mdsc->mutex
+ */
+static int __send_request(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session,
+ struct ceph_mds_request *req,
+ bool drop_cap_releases)
+{
+ int err;
+
+ err = __prepare_send_request(mdsc, req, session->s_mds,
+ drop_cap_releases);
+ if (!err) {
+ ceph_msg_get(req->r_request);
+ ceph_con_send(&session->s_con, req->r_request);
+ }
+
+ return err;
+}
+
/*
* send request, or put it on the appropriate wait list.
*/
@@ -2524,6 +2562,7 @@ static void __do_request(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session = NULL;
int mds = -1;
int err = 0;
+ bool random;
if (req->r_err || test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags))
@@ -2556,15 +2595,14 @@ static void __do_request(struct ceph_mds_client *mdsc,
if (!(mdsc->fsc->mount_options->flags &
CEPH_MOUNT_OPT_MOUNTWAIT) &&
!ceph_mdsmap_is_cluster_available(mdsc->mdsmap)) {
- err = -ENOENT;
- pr_info("probably no mds server is up\n");
+ err = -EHOSTUNREACH;
goto finish;
}
}
put_request_session(req);
- mds = __choose_mds(mdsc, req);
+ mds = __choose_mds(mdsc, req, &random);
if (mds < 0 ||
ceph_mdsmap_get_state(mdsc->mdsmap, mds) < CEPH_MDS_STATE_ACTIVE) {
dout("do_request no mds or not active, waiting for map\n");
@@ -2581,7 +2619,7 @@ static void __do_request(struct ceph_mds_client *mdsc,
goto finish;
}
}
- req->r_session = get_session(session);
+ req->r_session = ceph_get_mds_session(session);
dout("do_request mds%d session %p state %s\n", mds, session,
ceph_session_state_name(session->s_state));
@@ -2592,8 +2630,12 @@ static void __do_request(struct ceph_mds_client *mdsc,
goto out_session;
}
if (session->s_state == CEPH_MDS_SESSION_NEW ||
- session->s_state == CEPH_MDS_SESSION_CLOSING)
+ session->s_state == CEPH_MDS_SESSION_CLOSING) {
__open_session(mdsc, session);
+ /* retry the same mds later */
+ if (random)
+ req->r_resend_mds = mds;
+ }
list_add(&req->r_wait, &session->s_waiting);
goto out_session;
}
@@ -2604,11 +2646,7 @@ static void __do_request(struct ceph_mds_client *mdsc,
if (req->r_request_started == 0) /* note request start time */
req->r_request_started = jiffies;
- err = __prepare_send_request(mdsc, req, mds, false);
- if (!err) {
- ceph_msg_get(req->r_request);
- ceph_con_send(&session->s_con, req->r_request);
- }
+ err = __send_request(mdsc, session, req, false);
out_session:
ceph_put_mds_session(session);
@@ -2861,7 +2899,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
mutex_unlock(&mdsc->mutex);
goto out;
} else {
- int mds = __choose_mds(mdsc, req);
+ int mds = __choose_mds(mdsc, req, NULL);
if (mds >= 0 && mds != req->r_session->s_mds) {
dout("but auth changed, so resending\n");
__do_request(mdsc, req);
@@ -2877,6 +2915,10 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
set_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags);
__unregister_request(mdsc, req);
+ /* last request during umount? */
+ if (mdsc->stopping && !__get_oldest_req(mdsc))
+ complete_all(&mdsc->safe_umount_waiters);
+
if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
/*
* We already handled the unsafe response, now do the
@@ -2887,9 +2929,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
*/
dout("got safe reply %llu, mds%d\n", tid, mds);
- /* last unsafe request during umount? */
- if (mdsc->stopping && !__get_oldest_req(mdsc))
- complete_all(&mdsc->safe_umount_waiters);
mutex_unlock(&mdsc->mutex);
goto out;
}
@@ -3104,7 +3143,7 @@ static void handle_session(struct ceph_mds_session *session,
mutex_lock(&mdsc->mutex);
if (op == CEPH_SESSION_CLOSE) {
- get_session(session);
+ ceph_get_mds_session(session);
__unregister_session(mdsc, session);
}
/* FIXME: this ttl calculation is generous */
@@ -3142,6 +3181,7 @@ static void handle_session(struct ceph_mds_session *session,
case CEPH_SESSION_CLOSE:
if (session->s_state == CEPH_MDS_SESSION_RECONNECTING)
pr_info("mds%d reconnect denied\n", session->s_mds);
+ session->s_state = CEPH_MDS_SESSION_CLOSED;
cleanup_session_requests(mdsc, session);
remove_session_caps(session);
wake = 2; /* for good measure */
@@ -3209,7 +3249,6 @@ static void handle_session(struct ceph_mds_session *session,
return;
}
-
/*
* called under session->mutex.
*/
@@ -3218,18 +3257,12 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
{
struct ceph_mds_request *req, *nreq;
struct rb_node *p;
- int err;
dout("replay_unsafe_requests mds%d\n", session->s_mds);
mutex_lock(&mdsc->mutex);
- list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item) {
- err = __prepare_send_request(mdsc, req, session->s_mds, true);
- if (!err) {
- ceph_msg_get(req->r_request);
- ceph_con_send(&session->s_con, req->r_request);
- }
- }
+ list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item)
+ __send_request(mdsc, session, req, true);
/*
* also re-send old requests when MDS enters reconnect stage. So that MDS
@@ -3244,14 +3277,8 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
if (req->r_attempts == 0)
continue; /* only old requests */
if (req->r_session &&
- req->r_session->s_mds == session->s_mds) {
- err = __prepare_send_request(mdsc, req,
- session->s_mds, true);
- if (!err) {
- ceph_msg_get(req->r_request);
- ceph_con_send(&session->s_con, req->r_request);
- }
- }
+ req->r_session->s_mds == session->s_mds)
+ __send_request(mdsc, session, req, true);
}
mutex_unlock(&mdsc->mutex);
}
@@ -3762,7 +3789,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
dout("check_new_map new %u old %u\n",
newmap->m_epoch, oldmap->m_epoch);
- for (i = 0; i < oldmap->m_num_mds && i < mdsc->max_sessions; i++) {
+ for (i = 0; i < oldmap->possible_max_rank && i < mdsc->max_sessions; i++) {
if (!mdsc->sessions[i])
continue;
s = mdsc->sessions[i];
@@ -3776,9 +3803,9 @@ static void check_new_map(struct ceph_mds_client *mdsc,
ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
ceph_session_state_name(s->s_state));
- if (i >= newmap->m_num_mds) {
+ if (i >= newmap->possible_max_rank) {
/* force close session for stopped mds */
- get_session(s);
+ ceph_get_mds_session(s);
__unregister_session(mdsc, s);
__wake_requests(mdsc, &s->s_waiting);
mutex_unlock(&mdsc->mutex);
@@ -3833,7 +3860,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
}
}
- for (i = 0; i < newmap->m_num_mds && i < mdsc->max_sessions; i++) {
+ for (i = 0; i < newmap->possible_max_rank && i < mdsc->max_sessions; i++) {
s = mdsc->sessions[i];
if (!s)
continue;
@@ -4379,7 +4406,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
mutex_lock(&mdsc->mutex);
for (i = 0; i < mdsc->max_sessions; i++) {
if (mdsc->sessions[i]) {
- session = get_session(mdsc->sessions[i]);
+ session = ceph_get_mds_session(mdsc->sessions[i]);
__unregister_session(mdsc, session);
mutex_unlock(&mdsc->mutex);
mutex_lock(&session->s_mutex);
@@ -4607,11 +4634,8 @@ static struct ceph_connection *con_get(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
- if (get_session(s)) {
- dout("mdsc con_get %p ok (%d)\n", s, refcount_read(&s->s_ref));
+ if (ceph_get_mds_session(s))
return con;
- }
- dout("mdsc con_get %p FAIL\n", s);
return NULL;
}
@@ -4619,7 +4643,6 @@ static void con_put(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
- dout("mdsc con_put %p (%d)\n", s, refcount_read(&s->s_ref) - 1);
ceph_put_mds_session(s);
}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 14c7e8c49970adb914ff311c14906e4c84cda1d4..27a7446e10d3aa6b861a4b828185a71777081b11 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -17,22 +17,31 @@
#include <linux/ceph/auth.h>
/* The first 8 bits are reserved for old ceph releases */
-#define CEPHFS_FEATURE_MIMIC 8
-#define CEPHFS_FEATURE_REPLY_ENCODING 9
-#define CEPHFS_FEATURE_RECLAIM_CLIENT 10
-#define CEPHFS_FEATURE_LAZY_CAP_WANTED 11
-#define CEPHFS_FEATURE_MULTI_RECONNECT 12
+enum ceph_feature_type {
+ CEPHFS_FEATURE_MIMIC = 8,
+ CEPHFS_FEATURE_REPLY_ENCODING,
+ CEPHFS_FEATURE_RECLAIM_CLIENT,
+ CEPHFS_FEATURE_LAZY_CAP_WANTED,
+ CEPHFS_FEATURE_MULTI_RECONNECT,
+
+ CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_MULTI_RECONNECT,
+};
-#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \
+/*
+ * This will always have the highest feature bit value
+ * as the last element of the array.
+ */
+#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \
0, 1, 2, 3, 4, 5, 6, 7, \
CEPHFS_FEATURE_MIMIC, \
CEPHFS_FEATURE_REPLY_ENCODING, \
CEPHFS_FEATURE_LAZY_CAP_WANTED, \
CEPHFS_FEATURE_MULTI_RECONNECT, \
+ \
+ CEPHFS_FEATURE_MAX, \
}
#define CEPHFS_FEATURES_CLIENT_REQUIRED {}
-
/*
* Some lock dependencies:
*
@@ -151,7 +160,8 @@ enum {
CEPH_MDS_SESSION_RESTARTING = 5,
CEPH_MDS_SESSION_RECONNECTING = 6,
CEPH_MDS_SESSION_CLOSING = 7,
- CEPH_MDS_SESSION_REJECTED = 8,
+ CEPH_MDS_SESSION_CLOSED = 8,
+ CEPH_MDS_SESSION_REJECTED = 9,
};
struct ceph_mds_session {
@@ -174,6 +184,7 @@ struct ceph_mds_session {
/* protected by s_cap_lock */
spinlock_t s_cap_lock;
+ refcount_t s_ref;
struct list_head s_caps; /* all caps issued by this session */
struct ceph_cap *s_cap_iterator;
int s_nr_caps;
@@ -188,7 +199,6 @@ struct ceph_mds_session {
unsigned long s_renew_requested; /* last time we sent a renew req */
u64 s_renew_seq;
- refcount_t s_ref;
struct list_head s_waiting; /* waiting requests */
struct list_head s_unsafe; /* unsafe requests */
};
@@ -224,6 +234,7 @@ struct ceph_mds_request {
struct rb_node r_node;
struct ceph_mds_client *r_mdsc;
+ struct kref r_kref;
int r_op; /* mds op code */
/* operation on what? */
@@ -294,7 +305,6 @@ struct ceph_mds_request {
int r_resend_mds; /* mds to resend to next, if any*/
u32 r_sent_on_mseq; /* cap mseq request was sent at*/
- struct kref r_kref;
struct list_head r_wait;
struct completion r_completion;
struct completion r_safe_completion;
@@ -451,15 +461,10 @@ extern const char *ceph_mds_op_name(int op);
extern struct ceph_mds_session *
__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
-static inline struct ceph_mds_session *
-ceph_get_mds_session(struct ceph_mds_session *s)
-{
- refcount_inc(&s->s_ref);
- return s;
-}
-
extern const char *ceph_session_state_name(int s);
+extern struct ceph_mds_session *
+ceph_get_mds_session(struct ceph_mds_session *s);
extern void ceph_put_mds_session(struct ceph_mds_session *s);
extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 471bac335fae6ed51b8db1f289e7ec3b94244450..889627817e52b2d0e0dc2bbcd7a59188edf7768a 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -13,30 +13,25 @@
#include "super.h"
+#define CEPH_MDS_IS_READY(i, ignore_laggy) \
+ (m->m_info[i].state > 0 && ignore_laggy ? true : !m->m_info[i].laggy)
-/*
- * choose a random mds that is "up" (i.e. has a state > 0), or -1.
- */
-int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
+static int __mdsmap_get_random_mds(struct ceph_mdsmap *m, bool ignore_laggy)
{
int n = 0;
int i, j;
- /* special case for one mds */
- if (1 == m->m_num_mds && m->m_info[0].state > 0)
- return 0;
-
/* count */
- for (i = 0; i < m->m_num_mds; i++)
- if (m->m_info[i].state > 0)
+ for (i = 0; i < m->possible_max_rank; i++)
+ if (CEPH_MDS_IS_READY(i, ignore_laggy))
n++;
if (n == 0)
return -1;
/* pick */
n = prandom_u32() % n;
- for (j = 0, i = 0; i < m->m_num_mds; i++) {
- if (m->m_info[i].state > 0)
+ for (j = 0, i = 0; i < m->possible_max_rank; i++) {
+ if (CEPH_MDS_IS_READY(i, ignore_laggy))
j++;
if (j > n)
break;
@@ -45,6 +40,20 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
return i;
}
+/*
+ * choose a random mds that is "up" (i.e. has a state > 0), or -1.
+ */
+int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
+{
+ int mds;
+
+ mds = __mdsmap_get_random_mds(m, false);
+ if (mds == m->possible_max_rank || mds == -1)
+ mds = __mdsmap_get_random_mds(m, true);
+
+ return mds == m->possible_max_rank ? -1 : mds;
+}
+
#define __decode_and_drop_type(p, end, type, bad) \
do { \
if (*p + sizeof(type) > end) \
@@ -138,14 +147,29 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
m->m_session_autoclose = ceph_decode_32(p);
m->m_max_file_size = ceph_decode_64(p);
m->m_max_mds = ceph_decode_32(p);
- m->m_num_mds = m->m_max_mds;
- m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS);
+ /*
+ * pick out the active nodes as the m_num_active_mds, the
+ * m_num_active_mds maybe larger than m_max_mds when decreasing
+ * the max_mds in cluster side, in other case it should less
+ * than or equal to m_max_mds.
+ */
+ m->m_num_active_mds = n = ceph_decode_32(p);
+
+ /*
+ * the possible max rank, it maybe larger than the m_num_active_mds,
+ * for example if the mds_max == 2 in the cluster, when the MDS(0)
+ * was laggy and being replaced by a new MDS, we will temporarily
+ * receive a new mds map with n_num_mds == 1 and the active MDS(1),
+ * and the mds rank >= m_num_active_mds.
+ */
+ m->possible_max_rank = max(m->m_num_active_mds, m->m_max_mds);
+
+ m->m_info = kcalloc(m->possible_max_rank, sizeof(*m->m_info), GFP_NOFS);
if (!m->m_info)
goto nomem;
/* pick out active nodes from mds_info (state > 0) */
- n = ceph_decode_32(p);
for (i = 0; i < n; i++) {
u64 global_id;
u32 namelen;
@@ -215,18 +239,15 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
ceph_mds_state_name(state),
laggy ? "(laggy)" : "");
- if (mds < 0 || state <= 0)
+ if (mds < 0 || mds >= m->possible_max_rank) {
+ pr_warn("mdsmap_decode got incorrect mds(%d)\n", mds);
continue;
+ }
- if (mds >= m->m_num_mds) {
- int new_num = max(mds + 1, m->m_num_mds * 2);
- void *new_m_info = krealloc(m->m_info,
- new_num * sizeof(*m->m_info),
- GFP_NOFS | __GFP_ZERO);
- if (!new_m_info)
- goto nomem;
- m->m_info = new_m_info;
- m->m_num_mds = new_num;
+ if (state <= 0) {
+ pr_warn("mdsmap_decode got incorrect state(%s)\n",
+ ceph_mds_state_name(state));
+ continue;
}
info = &m->m_info[mds];
@@ -247,14 +268,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
info->export_targets = NULL;
}
}
- if (m->m_num_mds > m->m_max_mds) {
- /* find max up mds */
- for (i = m->m_num_mds; i >= m->m_max_mds; i--) {
- if (i == 0 || m->m_info[i-1].state > 0)
- break;
- }
- m->m_num_mds = i;
- }
/* pg_pools */
ceph_decode_32_safe(p, end, n, bad);
@@ -296,14 +309,14 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
for (i = 0; i < n; i++) {
s32 mds = ceph_decode_32(p);
- if (mds >= 0 && mds < m->m_num_mds) {
+ if (mds >= 0 && mds < m->possible_max_rank) {
if (m->m_info[mds].laggy)
num_laggy++;
}
}
m->m_num_laggy = num_laggy;
- if (n > m->m_num_mds) {
+ if (n > m->possible_max_rank) {
void *new_m_info = krealloc(m->m_info,
n * sizeof(*m->m_info),
GFP_NOFS | __GFP_ZERO);
@@ -311,7 +324,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
goto nomem;
m->m_info = new_m_info;
}
- m->m_num_mds = n;
+ m->possible_max_rank = n;
}
/* inc */
@@ -382,7 +395,7 @@ void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
{
int i;
- for (i = 0; i < m->m_num_mds; i++)
+ for (i = 0; i < m->possible_max_rank; i++)
kfree(m->m_info[i].export_targets);
kfree(m->m_info);
kfree(m->m_data_pg_pools);
@@ -396,9 +409,9 @@ bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m)
return false;
if (m->m_damaged)
return false;
- if (m->m_num_laggy > 0)
+ if (m->m_num_laggy == m->m_num_active_mds)
return false;
- for (i = 0; i < m->m_num_mds; i++) {
+ for (i = 0; i < m->possible_max_rank; i++) {
if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE)
nr_active++;
}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 29a795f975dfa346e62aa29b004c792a9d830ace..bfb8aead0555b930d0c32442796947ce9afac6d9 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -107,7 +107,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
return 0;
}
-
static int ceph_sync_fs(struct super_block *sb, int wait)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
@@ -211,7 +210,6 @@ struct ceph_parse_opts_ctx {
/*
* Parse the source parameter. Distinguish the server list from the path.
- * Internally we do not include the leading '/' in the path.
*
* The source will look like:
* <server_spec>[,<server_spec>...]:[<path>]
@@ -232,12 +230,15 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc)
dev_name_end = strchr(dev_name, '/');
if (dev_name_end) {
- if (strlen(dev_name_end) > 1) {
- kfree(fsopt->server_path);
- fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
- if (!fsopt->server_path)
- return -ENOMEM;
- }
+ kfree(fsopt->server_path);
+
+ /*
+ * The server_path will include the whole chars from userland
+ * including the leading '/'.
+ */
+ fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
+ if (!fsopt->server_path)
+ return -ENOMEM;
} else {
dev_name_end = dev_name + strlen(dev_name);
}
@@ -461,6 +462,73 @@ static int strcmp_null(const char *s1, const char *s2)
return strcmp(s1, s2);
}
+/**
+ * path_remove_extra_slash - Remove the extra slashes in the server path
+ * @server_path: the server path and could be NULL
+ *
+ * Return NULL if the path is NULL or only consists of "/", or a string
+ * without any extra slashes including the leading slash(es) and the
+ * slash(es) at the end of the server path, such as:
+ * "//dir1////dir2///" --> "dir1/dir2"
+ */
+static char *path_remove_extra_slash(const char *server_path)
+{
+ const char *path = server_path;
+ const char *cur, *end;
+ char *buf, *p;
+ int len;
+
+ /* if the server path is omitted */
+ if (!path)
+ return NULL;
+
+ /* remove all the leading slashes */
+ while (*path == '/')
+ path++;
+
+ /* if the server path only consists of slashes */
+ if (*path == '\0')
+ return NULL;
+
+ len = strlen(path);
+
+ buf = kmalloc(len + 1, GFP_KERNEL);
+ if (!buf)
+ return ERR_PTR(-ENOMEM);
+
+ end = path + len;
+ p = buf;
+ do {
+ cur = strchr(path, '/');
+ if (!cur)
+ cur = end;
+
+ len = cur - path;
+
+ /* including one '/' */
+ if (cur != end)
+ len += 1;
+
+ memcpy(p, path, len);
+ p += len;
+
+ while (cur <= end && *cur == '/')
+ cur++;
+ path = cur;
+ } while (path < end);
+
+ *p = '\0';
+
+ /*
+ * remove the last slash if there has and just to make sure that
+ * we will get something like "dir1/dir2"
+ */
+ if (*(--p) == '/')
+ *p = '\0';
+
+ return buf;
+}
+
static int compare_mount_options(struct ceph_mount_options *new_fsopt,
struct ceph_options *new_opt,
struct ceph_fs_client *fsc)
@@ -468,6 +536,7 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
struct ceph_mount_options *fsopt1 = new_fsopt;
struct ceph_mount_options *fsopt2 = fsc->mount_options;
int ofs = offsetof(struct ceph_mount_options, snapdir_name);
+ char *p1, *p2;
int ret;
ret = memcmp(fsopt1, fsopt2, ofs);
@@ -480,9 +549,21 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace);
if (ret)
return ret;
- ret = strcmp_null(fsopt1->server_path, fsopt2->server_path);
+
+ p1 = path_remove_extra_slash(fsopt1->server_path);
+ if (IS_ERR(p1))
+ return PTR_ERR(p1);
+ p2 = path_remove_extra_slash(fsopt2->server_path);
+ if (IS_ERR(p2)) {
+ kfree(p1);
+ return PTR_ERR(p2);
+ }
+ ret = strcmp_null(p1, p2);
+ kfree(p1);
+ kfree(p2);
if (ret)
return ret;
+
ret = strcmp_null(fsopt1->fscache_uniq, fsopt2->fscache_uniq);
if (ret)
return ret;
@@ -637,6 +718,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
fsc->sb = NULL;
fsc->mount_state = CEPH_MOUNT_MOUNTING;
fsc->filp_gen = 1;
+ fsc->have_copy_from2 = true;
atomic_long_set(&fsc->writeback_count, 0);
@@ -788,7 +870,6 @@ static void destroy_caches(void)
ceph_fscache_unregister();
}
-
/*
* ceph_umount_begin - initiate forced umount. Tear down down the
* mount, skipping steps that may hang while waiting for server(s).
@@ -868,9 +949,6 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
return root;
}
-
-
-
/*
* mount: join the ceph cluster, and open root directory.
*/
@@ -885,7 +963,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
mutex_lock(&fsc->client->mount_mutex);
if (!fsc->sb->s_root) {
- const char *path;
+ const char *path, *p;
err = __ceph_open_session(fsc->client, started);
if (err < 0)
goto out;
@@ -897,17 +975,22 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
goto out;
}
- if (!fsc->mount_options->server_path) {
- path = "";
- dout("mount opening path \\t\n");
- } else {
- path = fsc->mount_options->server_path + 1;
- dout("mount opening path %s\n", path);
+ p = path_remove_extra_slash(fsc->mount_options->server_path);
+ if (IS_ERR(p)) {
+ err = PTR_ERR(p);
+ goto out;
}
+ /* if the server path is omitted or just consists of '/' */
+ if (!p)
+ path = "";
+ else
+ path = p;
+ dout("mount opening path '%s'\n", path);
ceph_fs_debugfs_init(fsc);
root = open_root_dentry(fsc, path, started);
+ kfree(p);
if (IS_ERR(root)) {
err = PTR_ERR(root);
goto out;
@@ -1070,6 +1153,11 @@ static int ceph_get_tree(struct fs_context *fc)
return 0;
out_splat:
+ if (!ceph_mdsmap_is_cluster_available(fsc->mdsc->mdsmap)) {
+ pr_info("No mds server is up or the cluster is laggy\n");
+ err = -EHOSTUNREACH;
+ }
+
ceph_mdsc_close_sessions(fsc->mdsc);
deactivate_locked_super(sb);
goto out_final;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3bf1a01cd536dcf1330fec6d7d8a89102c5f6c77..1e456a9011bb73f5717a08cfe4128ae41bda1f59 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -106,6 +106,8 @@ struct ceph_fs_client {
unsigned long last_auto_reconnect;
bool blacklisted;
+ bool have_copy_from2;
+
u32 filp_gen;
loff_t max_file_size;
diff --git a/net/ceph/ceph_fs.c b/fs/ceph/util.c
similarity index 94%
rename from net/ceph/ceph_fs.c
rename to fs/ceph/util.c
index 756a2dc10d274be5efda8262296944ef2077d4d3..2c34875675bfdab0e3372ce4f815d6533d475be8 100644
--- a/net/ceph/ceph_fs.c
+++ b/fs/ceph/util.c
@@ -39,7 +39,6 @@ void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
fl->stripe_count == 0 && fl->object_size == 0)
fl->pool_id = -1;
}
-EXPORT_SYMBOL(ceph_file_layout_from_legacy);
void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
struct ceph_file_layout_legacy *legacy)
@@ -52,7 +51,6 @@ void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
else
legacy->fl_pg_pool = 0;
}
-EXPORT_SYMBOL(ceph_file_layout_to_legacy);
int ceph_flags_to_mode(int flags)
{
@@ -82,7 +80,6 @@ int ceph_flags_to_mode(int flags)
return mode;
}
-EXPORT_SYMBOL(ceph_flags_to_mode);
int ceph_caps_for_mode(int mode)
{
@@ -101,4 +98,3 @@ int ceph_caps_for_mode(int mode)
return caps;
}
-EXPORT_SYMBOL(ceph_caps_for_mode);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index cb18ee637cb7b66ee37221ceb9e521c852eec4b1..7b8a070a782d3f530c2f8673d865bad3b9b57d8e 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -655,7 +655,7 @@ static int __build_xattrs(struct inode *inode)
u32 len;
const char *name, *val;
struct ceph_inode_info *ci = ceph_inode(inode);
- int xattr_version;
+ u64 xattr_version;
struct ceph_inode_xattr **xattrs = NULL;
int err = 0;
int i;
@@ -851,7 +851,7 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
req_mask = __get_request_mask(inode);
spin_lock(&ci->i_ceph_lock);
- dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
+ dout("getxattr %p name '%s' ver=%lld index_ver=%lld\n", inode, name,
ci->i_xattrs.version, ci->i_xattrs.index_version);
if (ci->i_xattrs.version == 0 ||
@@ -1078,7 +1078,8 @@ int __ceph_setxattr(struct inode *inode, const char *name,
}
}
- dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
+ dout("setxattr %p name '%s' issued %s\n", inode, name,
+ ceph_cap_string(issued));
__build_xattrs(inode);
required_blob_size = __get_required_blob_size(ci, name_len, val_len);
diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
index 0067d767c9ae03b25a4a03e5f915262f0f6b34c2..35d385296fbbaba819418deb38997c6db3672147 100644
--- a/include/linux/ceph/mdsmap.h
+++ b/include/linux/ceph/mdsmap.h
@@ -25,8 +25,9 @@ struct ceph_mdsmap {
u32 m_session_timeout; /* seconds */
u32 m_session_autoclose; /* seconds */
u64 m_max_file_size;
- u32 m_max_mds; /* size of m_addr, m_state arrays */
- int m_num_mds;
+ u32 m_max_mds; /* expected up:active mds number */
+ u32 m_num_active_mds; /* actual up:active mds number */
+ u32 possible_max_rank; /* possible max rank index */
struct ceph_mds_info *m_info;
/* which object pools file data can be stored in */
@@ -42,7 +43,7 @@ struct ceph_mdsmap {
static inline struct ceph_entity_addr *
ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
{
- if (w >= m->m_num_mds)
+ if (w >= m->possible_max_rank)
return NULL;
return &m->m_info[w].addr;
}
@@ -50,14 +51,14 @@ ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
{
BUG_ON(w < 0);
- if (w >= m->m_num_mds)
+ if (w >= m->possible_max_rank)
return CEPH_MDS_STATE_DNE;
return m->m_info[w].state;
}
static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
{
- if (w >= 0 && w < m->m_num_mds)
+ if (w >= 0 && w < m->possible_max_rank)
return m->m_info[w].laggy;
return false;
}
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index eaffbdddf89ad864efe4fd69ec90eca52de7b60f..5a62dbd3f4c26ce84b44f78810d82e8abbea276c 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -534,6 +534,7 @@ int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
struct ceph_object_id *dst_oid,
struct ceph_object_locator *dst_oloc,
u32 dst_fadvise_flags,
+ u32 truncate_seq, u64 truncate_size,
u8 copy_from_flags);
/* watch/notify */
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 3eb0e55665b4c5344a04d652b42307219d6589c0..59bdfd470100e99516746cd8b17374872d88b81e 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -256,6 +256,7 @@ extern const char *ceph_osd_state_name(int s);
\
/* tiering */ \
f(COPY_FROM, __CEPH_OSD_OP(WR, DATA, 26), "copy-from") \
+ f(COPY_FROM2, __CEPH_OSD_OP(WR, DATA, 45), "copy-from2") \
f(COPY_GET_CLASSIC, __CEPH_OSD_OP(RD, DATA, 27), "copy-get-classic") \
f(UNDIRTY, __CEPH_OSD_OP(WR, DATA, 28), "undirty") \
f(ISDIRTY, __CEPH_OSD_OP(RD, DATA, 29), "isdirty") \
@@ -446,6 +447,7 @@ enum {
CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to
* cloneid */
CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */
+ CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ = 32, /* send truncate_{seq,size} */
};
enum {
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index 59d0ba2072deb1c8c3b3ae7527de32e86ae304c1..ce09bb4fb2499dfac943ca504d0e49a3317c2d0d 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -13,5 +13,5 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
auth.o auth_none.o \
crypto.o armor.o \
auth_x.o \
- ceph_fs.o ceph_strings.o ceph_hash.o \
+ ceph_strings.o ceph_hash.o \
pagevec.o snapshot.o string_table.o
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ba45b074a362857f18a688fddf5459cf487cbd5f..b68b376d8c2f60b015cc6eae8dcae058a50dbc26 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -402,7 +402,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
case CEPH_OSD_OP_LIST_WATCHERS:
ceph_osd_data_release(&op->list_watchers.response_data);
break;
- case CEPH_OSD_OP_COPY_FROM:
+ case CEPH_OSD_OP_COPY_FROM2:
ceph_osd_data_release(&op->copy_from.osd_data);
break;
default:
@@ -697,7 +697,7 @@ static void get_num_data_items(struct ceph_osd_request *req,
case CEPH_OSD_OP_SETXATTR:
case CEPH_OSD_OP_CMPXATTR:
case CEPH_OSD_OP_NOTIFY_ACK:
- case CEPH_OSD_OP_COPY_FROM:
+ case CEPH_OSD_OP_COPY_FROM2:
*num_request_data_items += 1;
break;
@@ -1029,7 +1029,7 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
case CEPH_OSD_OP_CREATE:
case CEPH_OSD_OP_DELETE:
break;
- case CEPH_OSD_OP_COPY_FROM:
+ case CEPH_OSD_OP_COPY_FROM2:
dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid);
dst->copy_from.src_version =
cpu_to_le64(src->copy_from.src_version);
@@ -1966,7 +1966,7 @@ static void setup_request_data(struct ceph_osd_request *req)
ceph_osdc_msg_data_add(request_msg,
&op->notify_ack.request_data);
break;
- case CEPH_OSD_OP_COPY_FROM:
+ case CEPH_OSD_OP_COPY_FROM2:
ceph_osdc_msg_data_add(request_msg,
&op->copy_from.osd_data);
break;
@@ -5315,6 +5315,7 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
struct ceph_object_locator *src_oloc,
u32 src_fadvise_flags,
u32 dst_fadvise_flags,
+ u32 truncate_seq, u64 truncate_size,
u8 copy_from_flags)
{
struct ceph_osd_req_op *op;
@@ -5325,7 +5326,8 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
if (IS_ERR(pages))
return PTR_ERR(pages);
- op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM, dst_fadvise_flags);
+ op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2,
+ dst_fadvise_flags);
op->copy_from.snapid = src_snapid;
op->copy_from.src_version = src_version;
op->copy_from.flags = copy_from_flags;
@@ -5335,6 +5337,8 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
end = p + PAGE_SIZE;
ceph_encode_string(&p, end, src_oid->name, src_oid->name_len);
encode_oloc(&p, end, src_oloc);
+ ceph_encode_32(&p, truncate_seq);
+ ceph_encode_64(&p, truncate_size);
op->indata_len = PAGE_SIZE - (end - p);
ceph_osd_data_pages_init(&op->copy_from.osd_data, pages,
@@ -5350,6 +5354,7 @@ int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
struct ceph_object_id *dst_oid,
struct ceph_object_locator *dst_oloc,
u32 dst_fadvise_flags,
+ u32 truncate_seq, u64 truncate_size,
u8 copy_from_flags)
{
struct ceph_osd_request *req;
@@ -5366,7 +5371,8 @@ int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid,
src_oloc, src_fadvise_flags,
- dst_fadvise_flags, copy_from_flags);
+ dst_fadvise_flags, truncate_seq,
+ truncate_size, copy_from_flags);
if (ret)
goto out;