From 8f5ac172abb79171eac9ecb7bedc071b56630097 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Thu, 12 Jul 2018 16:45:08 +0800 Subject: [PATCH 01/25] ceph: delete redundant douts in con_get/put() We print session's refcount in debug message inside ceph_put_mds_session() and get_session(), so we don't have to print it in con_get()/__ceph_lookup_mds_session()/con_put(). Signed-off-by: Chengguang Xu Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 145d46ba25ae..69631d145265 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4609,11 +4609,8 @@ 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 (get_session(s)) return con; - } - dout("mdsc con_get %p FAIL\n", s); return NULL; } @@ -4621,7 +4618,6 @@ 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); } From d80865bff5201cc56bc247989ebbab6169b3a101 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Fri, 17 Aug 2018 22:05:31 +0800 Subject: [PATCH 02/25] ceph: remove unnecessary assignment in ceph_pre_init_acls() ceph_pagelist_encode_string() will not fail in reserved case, also, we do not check err code here, so remove unnecessary assignment. Signed-off-by: Chengguang Xu Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/acl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index aa55f412a6e3..26be6520d3fb 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) From 4d7ace02ba5c6ef1f8eeb32a86fef7c528bd7f36 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 26 Nov 2019 07:24:21 -0500 Subject: [PATCH 03/25] ceph: fix mdsmap cluster available check based on laggy number In case the max_mds > 1 in MDS cluster and there is no any standby MDS and all the max_mds MDSs are in up:active state, if one of the up:active MDSs is dead, the m->m_num_laggy in kclient will be 1. Then the mount will fail without considering other healthy MDSs. There manybe some MDSs still "in" the cluster but not in up:active state, we will ignore them. Only when all the up:active MDSs in the cluster are laggy will treat the cluster as not be available. In case decreasing the max_mds, the cluster will not stop the extra up:active MDSs immediately and there will be a latency. During it the up:active MDS number will be larger than the max_mds, so later the m_info memories will 100% be reallocated. Here will pick out the up:active MDSs as the m_num_mds and allocate the needed memories once. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mdsmap.c | 48 +++++++++++++++++++++---------------- include/linux/ceph/mdsmap.h | 5 ++-- 2 files changed, 30 insertions(+), 23 deletions(-) diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 471bac335fae..7a925e025c0a 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -113,6 +113,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) int err; u8 mdsmap_v, mdsmap_cv; u16 mdsmap_ev; + u32 possible_max_rank; m = kzalloc(sizeof(*m), GFP_NOFS); if (!m) @@ -138,14 +139,30 @@ 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; + + /* + * pick out the active nodes as the m_num_mds, the m_num_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_mds = n = ceph_decode_32(p); + m->m_num_active_mds = m->m_num_mds; + + /* + * the possible max rank, it maybe larger than the m->m_num_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->m_num_mds. + */ + possible_max_rank = max((u32)m->m_num_mds, m->m_max_mds); m->m_info = kcalloc(m->m_num_mds, 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 +232,15 @@ 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 >= 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 +261,6 @@ 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); @@ -396,7 +402,7 @@ 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++) { if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE) diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 0067d767c9ae..3a66f4f926ce 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 */ + int m_num_active_mds; /* actual up:active mds number */ + int m_num_mds; /* size of m_info array */ struct ceph_mds_info *m_info; /* which object pools file data can be stored in */ From 5d47648fe95412beffe2089d6d6484adb5ea0f96 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 26 Nov 2019 07:24:22 -0500 Subject: [PATCH 04/25] ceph: only choose one MDS who is in up:active state without laggy Even the MDS is in up:active state, but it also maybe laggy. Here will skip the laggy MDSs. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 13 +++++++++---- fs/ceph/mdsmap.c | 30 +++++++++++++++++++++++------- 2 files changed, 32 insertions(+), 11 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 69631d145265..1b53aceb54bd 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -974,14 +974,14 @@ static int __choose_mds(struct ceph_mds_client *mdsc, 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; @@ -989,9 +989,14 @@ static int __choose_mds(struct ceph_mds_client *mdsc, "frag %u mds%d (auth)\n", 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; } } diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 7a925e025c0a..a77e0ecb9a6b 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -13,22 +13,24 @@ #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 */ + /* + * special case for one mds, no matter it is laggy or + * not we have no choice + */ 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) + if (CEPH_MDS_IS_READY(i, ignore_laggy)) n++; if (n == 0) return -1; @@ -36,7 +38,7 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m) /* pick */ n = prandom_u32() % n; for (j = 0, i = 0; i < m->m_num_mds; i++) { - if (m->m_info[i].state > 0) + if (CEPH_MDS_IS_READY(i, ignore_laggy)) j++; if (j > n) break; @@ -45,6 +47,20 @@ 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->m_num_mds || mds == -1) + mds = __mdsmap_get_random_mds(m, true); + + return mds == m->m_num_mds ? -1 : mds; +} + #define __decode_and_drop_type(p, end, type, bad) \ do { \ if (*p + sizeof(type) > end) \ From 07edc0571ef1b13e124b462aca8d09f79809d6dd Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 4 Dec 2019 01:27:18 -0500 Subject: [PATCH 05/25] ceph: fix possible long time wait during umount During umount, if there has no any unsafe request in the mdsc and some requests still in-flight and not got reply yet, and if the rest requets are all safe ones, after that even all of them in mdsc are unregistered, the umount must wait until after mount_timeout seconds anyway. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1b53aceb54bd..6dca3b4d03a9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2884,6 +2884,10 @@ 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 @@ -2894,9 +2898,6 @@ 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; } From 57c219948245cb1e8970040a365058baab450316 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 4 Dec 2019 15:28:17 -0500 Subject: [PATCH 06/25] ceph: drop unused ttl_from parameter from fill_inode Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/inode.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index c07407586ce8..5bdc1afc2bee 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -728,8 +728,7 @@ 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; @@ -1237,7 +1236,7 @@ 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; @@ -1305,9 +1304,9 @@ retry_lookup: 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", @@ -1493,8 +1492,7 @@ 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; @@ -1694,8 +1692,7 @@ retry_lookup: } 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)) { From 9a6bed4fe0c8bf57785cbc4db9f86086cb9b193d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 5 Dec 2019 08:41:25 -0500 Subject: [PATCH 07/25] ceph: ensure we have a new cap before continuing in fill_inode If the caller passes in a NULL cap_reservation, and we can't allocate one then ensure that we fail gracefully. Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/inode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 5bdc1afc2bee..b5f068582970 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -753,8 +753,11 @@ 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 From 9cf54563b090f52db10ae6ebdca29dcc76bc7f34 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 5 Dec 2019 20:50:21 -0500 Subject: [PATCH 08/25] ceph: add __send_request helper Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 47 +++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 22 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 6dca3b4d03a9..627cf0326b97 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2522,6 +2522,26 @@ 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. */ @@ -2611,11 +2631,7 @@ 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); @@ -3217,7 +3233,6 @@ bad: return; } - /* * called under session->mutex. */ @@ -3226,18 +3241,12 @@ 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 @@ -3252,14 +3261,8 @@ 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); } From 4d681c2f9141cf50261eef85b3233151c83d068b Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 5 Dec 2019 22:35:51 -0500 Subject: [PATCH 09/25] ceph: keep the session state until it is released When reconnecting the session but if it is denied by the MDS due to client was in blacklist or something else, kclient will receive a session close reply, and we will never see the important log: "ceph: mds%d reconnect denied" And with the confusing log: "ceph: handle_session mds0 close 0000000085804730 state ??? seq 0" Let's keep the session state until its memories is released. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 3 ++- fs/ceph/mds_client.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 627cf0326b97..18fa8f866eef 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -530,6 +530,7 @@ 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"; @@ -674,7 +675,6 @@ 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); @@ -3166,6 +3166,7 @@ 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 */ diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 14c7e8c49970..fe085e06adf5 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -151,7 +151,8 @@ 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 { From 97820058fb2831a4b203981fa2566ceaaa396103 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 10 Dec 2019 20:29:40 -0500 Subject: [PATCH 10/25] ceph: check availability of mds cluster on mount after wait timeout If all the MDS daemons are down for some reason, then the first mount attempt will fail with EIO after the mount request times out. A mount attempt will also fail with EIO if all of the MDS's are laggy. This patch changes the code to return -EHOSTUNREACH in these situations and adds a pr_info error message to help the admin determine the cause. URL: https://tracker.ceph.com/issues/4386 Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 3 +-- fs/ceph/super.c | 5 +++++ 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 18fa8f866eef..e1902663f8b8 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2583,8 +2583,7 @@ 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; } } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 29a795f975df..430dcf329723 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1070,6 +1070,11 @@ 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; From c4853e9776caefbd2f59739ce1a75798a2b4b7a5 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Mon, 9 Dec 2019 07:47:15 -0500 Subject: [PATCH 11/25] ceph: retry the same mds later after the new session is opened If max_mds > 1 and a request is submitted that chooses a random mds rank, and the relating session is not opened yet, the request will wait until the session has been opened and resend again. Every time the request goes through __do_request, it will release the req->session first and choose a random one again, which may be a completely different rank than the one it just waited on. In the worst case, it will open all the mds sessions one by one just before the request can be successfully sent out. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index e1902663f8b8..07ecdfc8438d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -878,7 +878,8 @@ 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 +889,9 @@ 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). @@ -1023,6 +1027,9 @@ out: return mds; random: + if (random) + *random = true; + mds = ceph_mdsmap_get_random_mds(mdsc->mdsmap); dout("choose_mds chose random mds%d\n", mds); return mds; @@ -2551,6 +2558,7 @@ 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)) @@ -2590,7 +2598,7 @@ static void __do_request(struct ceph_mds_client *mdsc, 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"); @@ -2618,8 +2626,12 @@ 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; } @@ -2883,7 +2895,7 @@ 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); From 893e456b2c0bae61e172d2600a89c96abf9b3daf Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 11 Dec 2019 15:21:24 -0500 Subject: [PATCH 12/25] ceph: don't clear I_NEW until inode metadata is fully populated Currently, we could have an open-by-handle (or NFS server) call into the filesystem and start working with an inode before it's properly filled out. Don't clear I_NEW until we have filled out the inode, and discard it properly if that fails. Note that we occasionally take an extra reference to the inode to ensure that we don't put the last reference in discard_new_inode, but rather leave it for ceph_async_iput. Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/inode.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index b5f068582970..d01710a16a4a 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; } @@ -1304,7 +1306,6 @@ retry_lookup: err = PTR_ERR(in); goto done; } - req->r_target_inode = in; err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL, session, @@ -1314,8 +1315,13 @@ retry_lookup: 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); } /* @@ -1499,7 +1505,14 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req, 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); } @@ -1701,12 +1714,18 @@ retry_lookup: 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)) { From 9f8b72b3a9485d659410989c6daf5467ebe264ea Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Mon, 16 Dec 2019 00:12:07 -0500 Subject: [PATCH 13/25] ceph: only touch the caps which have the subset mask requested For the caps having no any subset mask requested we shouldn't touch them. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 9d09bb53c1ab..28ae0c134700 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; From 0eb308531f0776fc87f7a7eb4a8efe943d98ab8c Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 18 Dec 2019 21:15:18 -0500 Subject: [PATCH 14/25] ceph: print dentry offset in hex and fix xattr_version type In the debug logs about the di->offset or ctx->pos it is in hex format, but some others are using the dec format. It is a little hard to read. For the xattr version, it is u64 type, using a shorter type may truncate it. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/dir.c | 4 ++-- fs/ceph/xattr.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 2e4764fd1872..d0cd0aba5843 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/xattr.c b/fs/ceph/xattr.c index cb18ee637cb7..98a9a3101cda 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; From b38c9eb4757d5bac1eb8634a9516ef918fca2525 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 4 Dec 2019 06:57:39 -0500 Subject: [PATCH 15/25] ceph: add possible_max_rank and make the code more readable The m_num_mds here is actually the number for MDSs which are in up:active status, and it will be duplicated to m_num_active_mds, so remove it. Add possible_max_rank to the mdsmap struct and this will be the correctly possible largest rank boundary. Remove the special case for one mds in __mdsmap_get_random_mds(), because the validate mds rank may not always be 0. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/debugfs.c | 2 +- fs/ceph/mds_client.c | 10 ++++---- fs/ceph/mdsmap.c | 49 +++++++++++++++---------------------- include/linux/ceph/mdsmap.h | 10 ++++---- 4 files changed, 31 insertions(+), 40 deletions(-) diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index c281f32b54f7..fb7cabd98e7b 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/mds_client.c b/fs/ceph/mds_client.c index 07ecdfc8438d..aba7a56d055d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -598,7 +598,7 @@ 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); @@ -1231,7 +1231,7 @@ 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]; @@ -3785,7 +3785,7 @@ 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]; @@ -3799,7 +3799,7 @@ 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); __unregister_session(mdsc, s); @@ -3856,7 +3856,7 @@ 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; diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index a77e0ecb9a6b..889627817e52 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -14,22 +14,15 @@ #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)) + (m->m_info[i].state > 0 && ignore_laggy ? true : !m->m_info[i].laggy) static int __mdsmap_get_random_mds(struct ceph_mdsmap *m, bool ignore_laggy) { int n = 0; int i, j; - /* - * special case for one mds, no matter it is laggy or - * not we have no choice - */ - if (1 == m->m_num_mds && m->m_info[0].state > 0) - return 0; - /* count */ - for (i = 0; i < m->m_num_mds; i++) + for (i = 0; i < m->possible_max_rank; i++) if (CEPH_MDS_IS_READY(i, ignore_laggy)) n++; if (n == 0) @@ -37,7 +30,7 @@ static int __mdsmap_get_random_mds(struct ceph_mdsmap *m, bool ignore_laggy) /* pick */ n = prandom_u32() % n; - for (j = 0, i = 0; i < m->m_num_mds; i++) { + for (j = 0, i = 0; i < m->possible_max_rank; i++) { if (CEPH_MDS_IS_READY(i, ignore_laggy)) j++; if (j > n) @@ -55,10 +48,10 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m) int mds; mds = __mdsmap_get_random_mds(m, false); - if (mds == m->m_num_mds || mds == -1) + if (mds == m->possible_max_rank || mds == -1) mds = __mdsmap_get_random_mds(m, true); - return mds == m->m_num_mds ? -1 : mds; + return mds == m->possible_max_rank ? -1 : mds; } #define __decode_and_drop_type(p, end, type, bad) \ @@ -129,7 +122,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) int err; u8 mdsmap_v, mdsmap_cv; u16 mdsmap_ev; - u32 possible_max_rank; m = kzalloc(sizeof(*m), GFP_NOFS); if (!m) @@ -157,24 +149,23 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) m->m_max_mds = ceph_decode_32(p); /* - * pick out the active nodes as the m_num_mds, the m_num_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. + * 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_mds = n = ceph_decode_32(p); - m->m_num_active_mds = m->m_num_mds; + m->m_num_active_mds = n = ceph_decode_32(p); /* - * the possible max rank, it maybe larger than the m->m_num_mds, + * 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->m_num_mds. + * and the mds rank >= m_num_active_mds. */ - possible_max_rank = max((u32)m->m_num_mds, m->m_max_mds); + m->possible_max_rank = max(m->m_num_active_mds, m->m_max_mds); - m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS); + m->m_info = kcalloc(m->possible_max_rank, sizeof(*m->m_info), GFP_NOFS); if (!m->m_info) goto nomem; @@ -248,7 +239,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) ceph_mds_state_name(state), laggy ? "(laggy)" : ""); - if (mds < 0 || mds >= possible_max_rank) { + if (mds < 0 || mds >= m->possible_max_rank) { pr_warn("mdsmap_decode got incorrect mds(%d)\n", mds); continue; } @@ -318,14 +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); @@ -333,7 +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 */ @@ -404,7 +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); @@ -420,7 +411,7 @@ bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m) return false; 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/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 3a66f4f926ce..35d385296fbb 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -26,8 +26,8 @@ struct ceph_mdsmap { u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; u32 m_max_mds; /* expected up:active mds number */ - int m_num_active_mds; /* actual up:active mds number */ - int m_num_mds; /* size of m_info array */ + 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 */ @@ -43,7 +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; } @@ -51,14 +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; } From 4fbc0c711b2464ee1551850b85002faae0b775d5 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Fri, 20 Dec 2019 09:34:04 -0500 Subject: [PATCH 16/25] ceph: remove the extra slashes in the server path It's possible to pass the mount helper a server path that has more than one contiguous slash character. For example: $ mount -t ceph 192.168.195.165:40176:/// /mnt/cephfs/ In the MDS server side the extra slashes of the server path will be treated as snap dir, and then we can get the following debug logs: ceph: mount opening path // ceph: open_root_inode opening '//' ceph: fill_trace 0000000059b8a3bc is_dentry 0 is_target 1 ceph: alloc_inode 00000000dc4ca00b ceph: get_inode created new inode 00000000dc4ca00b 1.ffffffffffffffff ino 1 ceph: get_inode on 1=1.ffffffffffffffff got 00000000dc4ca00b And then when creating any new file or directory under the mount point, we can hit the following BUG_ON in ceph_fill_trace(): BUG_ON(ceph_snap(dir) != dvino.snap); Have the client ignore the extra slashes in the server path when mounting. This will also canonicalize the path, so that identical mounts can be consilidated. 1) "//mydir1///mydir//" 2) "/mydir1/mydir" 3) "/mydir1/mydir/" Regardless of the internal treatment of these paths, the kernel still stores the original string including the leading '/' for presentation to userland. URL: https://tracker.ceph.com/issues/42771 Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/super.c | 122 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 102 insertions(+), 20 deletions(-) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 430dcf329723..112927dbd2f2 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: * [,...]:[] @@ -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; @@ -788,7 +869,6 @@ 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 +948,6 @@ out: return root; } - - - /* * mount: join the ceph cluster, and open root directory. */ @@ -885,7 +962,7 @@ 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 +974,22 @@ 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; From 5b3248c6772459a0737afe0c85bb45ee3ba79eeb Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 19 Dec 2019 19:44:09 -0500 Subject: [PATCH 17/25] ceph: rename get_session and switch to use ceph_get_mds_session Just in case the session's refcount reach 0 and is releasing, and if we get the session without checking it, we may encounter kernel crash. Rename get_session to ceph_get_mds_session and make it global. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 16 ++++++++-------- fs/ceph/mds_client.h | 9 ++------- 2 files changed, 10 insertions(+), 15 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index aba7a56d055d..f7c9a56514f9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -538,7 +538,7 @@ 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, @@ -569,7 +569,7 @@ 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) @@ -1979,7 +1979,7 @@ 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"); @@ -2615,7 +2615,7 @@ 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)); @@ -3139,7 +3139,7 @@ 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 */ @@ -3801,7 +3801,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, 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); @@ -4402,7 +4402,7 @@ 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); @@ -4630,7 +4630,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; - if (get_session(s)) + if (ceph_get_mds_session(s)) return con; return NULL; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index fe085e06adf5..c021df5f50ce 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -452,15 +452,10 @@ 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, From 9ba1e224538a021b989302bb2777abc7a3b3ec79 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 8 Jan 2020 05:17:31 -0500 Subject: [PATCH 18/25] ceph: allocate the correct amount of extra bytes for the session features The total bytes may potentially be larger than 8. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 20 ++++++++++++++------ fs/ceph/mds_client.h | 23 ++++++++++++++++------- 2 files changed, 30 insertions(+), 13 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index f7c9a56514f9..c839664f86c6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "super.h" #include "mds_client.h" @@ -1057,20 +1058,21 @@ 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); @@ -1091,6 +1093,7 @@ 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] = { @@ -1108,8 +1111,13 @@ 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, @@ -1129,7 +1137,7 @@ 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 * - * 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); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index c021df5f50ce..c950f8f88f58 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -17,22 +17,31 @@ #include /* 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, -#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \ + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_MULTI_RECONNECT, +}; + +/* + * 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: * From a55e601b2f02df5db7070e9a37bd655c9c576a52 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 7 Jan 2020 22:01:04 +0100 Subject: [PATCH 19/25] rbd: work around -Wuninitialized warning gcc -O3 warns about a dummy variable that is passed down into rbd_img_fill_nodata without being initialized: drivers/block/rbd.c: In function 'rbd_img_fill_nodata': drivers/block/rbd.c:2573:13: error: 'dummy' is used uninitialized in this function [-Werror=uninitialized] fctx->iter = *fctx->pos; Since this is a dummy, I assume the warning is harmless, but it's better to initialize it anyway and avoid the warning. Fixes: mmtom ("init/Kconfig: enable -O3 for all arches") Signed-off-by: Arnd Bergmann Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- drivers/block/rbd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 2b184563cd32..38dcb39051a7 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, From 045100cd79f503487b95a1d11e96b221fe50693c Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 15 Nov 2019 09:13:59 -0500 Subject: [PATCH 20/25] ceph: close holes in structs ceph_mds_session and ceph_mds_request Move s_ref up to plug a 4 byte hole, which plugs another. Move r_kref to shave 8 bytes off per request on x86_64. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index c950f8f88f58..27a7446e10d3 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -184,6 +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; @@ -198,7 +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 */ }; @@ -234,6 +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? */ @@ -304,7 +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; From 78beb0ff2feceb1d7568333f93195e1a4d95a49a Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Wed, 8 Jan 2020 10:03:53 +0000 Subject: [PATCH 21/25] ceph: use copy-from2 op in copy_file_range Instead of using the copy-from operation, switch copy_file_range to the new copy-from2 operation, which allows to send the truncate_seq and truncate_size parameters. If an OSD does not support the copy-from2 operation it will return -EOPNOTSUPP. In that case, the kernel client will stop trying to do remote object copies for this fs client and will always use the generic VFS copy_file_range. Signed-off-by: Luis Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/file.c | 11 ++++++++++- fs/ceph/super.c | 1 + fs/ceph/super.h | 2 ++ include/linux/ceph/osd_client.h | 1 + include/linux/ceph/rados.h | 2 ++ net/ceph/osd_client.c | 18 ++++++++++++------ 6 files changed, 28 insertions(+), 7 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 11929d2bb594..c3b8e8e0bf17 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/super.c b/fs/ceph/super.c index 112927dbd2f2..bfb8aead0555 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -718,6 +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); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 3bf1a01cd536..1e456a9011bb 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/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index eaffbdddf89a..5a62dbd3f4c2 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 3eb0e55665b4..59bdfd470100 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/osd_client.c b/net/ceph/osd_client.c index ba45b074a362..b68b376d8c2f 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; From 3c802092dab69351b1c2e52a2250f47d5bf60253 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 1 Jan 2020 22:09:37 -0500 Subject: [PATCH 22/25] ceph: print r_direct_hash in hex in __choose_mds() dout It's hard to read, especially when it is: ceph: __choose_mds 00000000b7bc9c15 is_hash=1 (-271041095) mode 0 At the same time, switch to __func__ to get rid of the checkpatch warning. Signed-off-by: Xiubo Li Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index c839664f86c6..011c779e4c76 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -900,7 +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; } @@ -918,7 +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 */ @@ -938,7 +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); @@ -954,8 +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); @@ -973,11 +973,9 @@ 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_mdsmap_is_laggy(mdsc->mdsmap, mds)) @@ -990,9 +988,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc, 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) { if (mode == USE_ANY_MDS && @@ -1017,7 +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); @@ -1032,7 +1030,7 @@ 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; } From d36e0b620aa53d9a33c739f0368e85707a997430 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 7 Jan 2020 13:12:57 -0500 Subject: [PATCH 23/25] ceph: print name of xattr in __ceph_{get,set}xattr() douts Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/xattr.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 98a9a3101cda..7b8a070a782d 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -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 @@ retry: } } - 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); From 24604f7e2bde5e6458812c3e9ee2a0d60c8c99fe Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 6 Jan 2020 19:05:19 -0500 Subject: [PATCH 24/25] ceph: move net/ceph/ceph_fs.c to fs/ceph/util.c All of these functions are only called from CephFS, so move them into ceph.ko, and drop the exports. Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/Makefile | 2 +- net/ceph/ceph_fs.c => fs/ceph/util.c | 4 ---- net/ceph/Makefile | 2 +- 3 files changed, 2 insertions(+), 6 deletions(-) rename net/ceph/ceph_fs.c => fs/ceph/util.c (94%) diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile index c1da294418d1..0a0823d378db 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/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 756a2dc10d27..2c34875675bf 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/net/ceph/Makefile b/net/ceph/Makefile index 59d0ba2072de..ce09bb4fb249 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 From 3325322f773bae68b20d8fa0e9e8ebb005271db5 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 23 Jan 2020 13:44:33 +0100 Subject: [PATCH 25/25] rbd: set the 'device' link in sysfs The rbd driver already provides additional information in sysfs under /sys/bus/rbd, so we should set the 'device' link in the block device to reference this information. Signed-off-by: Hannes Reinecke Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- drivers/block/rbd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 38dcb39051a7..405b66e09040 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -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);