From 29a0cfbf91ba997591535a4f7246835ce8328141 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 18 Sep 2017 12:21:37 +0200 Subject: [PATCH 1/2] libceph: don't allow bidirectional swap of pg-upmap-items This reverts most of commit f53b7665c8ce ("libceph: upmap semantic changes"). We need to prevent duplicates in the final result. For example, we can currently take [1,2,3] and apply [(1,2)] and get [2,2,3] or [1,2,3] and apply [(3,2)] and get [1,2,2] The rest of the system is not prepared to handle duplicates in the result set like this. The reverted piece was intended to allow [1,2,3] and [(1,2),(2,1)] to get [2,1,3] to reorder primaries. First, this bidirectional swap is hard to implement in a way that also prevents dups. For example, [1,2,3] and [(1,4),(2,3),(3,4)] would give [4,3,4] but would we just drop the last step we'd have [4,3,3] which is also invalid, etc. Simpler to just not handle bidirectional swaps. In practice, they are not needed: if you just want to choose a different primary then use primary_affinity, or pg_upmap (not pg_upmap_items). Cc: stable@vger.kernel.org # 4.13 Link: http://tracker.ceph.com/issues/21410 Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- net/ceph/osdmap.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index f358d0bfa76b..79d14d70b7ea 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -2445,19 +2445,34 @@ static void apply_upmap(struct ceph_osdmap *osdmap, pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid); if (pg) { - for (i = 0; i < raw->size; i++) { - for (j = 0; j < pg->pg_upmap_items.len; j++) { - int from = pg->pg_upmap_items.from_to[j][0]; - int to = pg->pg_upmap_items.from_to[j][1]; + /* + * Note: this approach does not allow a bidirectional swap, + * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1]. + */ + for (i = 0; i < pg->pg_upmap_items.len; i++) { + int from = pg->pg_upmap_items.from_to[i][0]; + int to = pg->pg_upmap_items.from_to[i][1]; + int pos = -1; + bool exists = false; - if (from == raw->osds[i]) { - if (!(to != CRUSH_ITEM_NONE && - to < osdmap->max_osd && - osdmap->osd_weight[to] == 0)) - raw->osds[i] = to; + /* make sure replacement doesn't already appear */ + for (j = 0; j < raw->size; j++) { + int osd = raw->osds[j]; + + if (osd == to) { + exists = true; break; } + /* ignore mapping if target is marked out */ + if (osd == from && pos < 0 && + !(to != CRUSH_ITEM_NONE && + to < osdmap->max_osd && + osdmap->osd_weight[to] == 0)) { + pos = j; + } } + if (!exists && pos >= 0) + raw->osds[pos] = to; } } } From 717e6f2893eb35ce6728c3cacdc297b78d371b31 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 11 Sep 2017 12:10:08 +0800 Subject: [PATCH 2/2] ceph: avoid panic in create_session_open_msg() if utsname() returns NULL utsname() can return NULL while process is exiting. Kernel releases file locks during process exits. We send request to mds when releasing file lock. So it's possible that we open mds session while process is exiting. utsname() is called in create_session_open_msg(). Link: http://tracker.ceph.com/issues/21275 Signed-off-by: "Yan, Zheng" Reviewed-by: Jeff Layton [idryomov@gmail.com: drop utsname.h include from mds_client.c] Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 7 ++++--- fs/ceph/mds_client.h | 3 +++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 9dd6b836ac9e..84edfc60d87a 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include "super.h" @@ -884,8 +883,8 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 void *p; const char* metadata[][2] = { - {"hostname", utsname()->nodename}, - {"kernel_version", utsname()->release}, + {"hostname", mdsc->nodename}, + {"kernel_version", init_utsname()->release}, {"entity_id", opt->name ? : ""}, {"root", fsopt->server_path ? : "/"}, {NULL, NULL} @@ -3539,6 +3538,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) init_rwsem(&mdsc->pool_perm_rwsem); mdsc->pool_perm_tree = RB_ROOT; + strncpy(mdsc->nodename, utsname()->nodename, + sizeof(mdsc->nodename) - 1); return 0; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index db57ae98ed34..636d6b2ec49c 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -368,6 +369,8 @@ struct ceph_mds_client { struct rw_semaphore pool_perm_rwsem; struct rb_root pool_perm_tree; + + char nodename[__NEW_UTS_LEN + 1]; }; extern const char *ceph_mds_op_name(int op);