From bd3884a204c3b507e6baa9a4091aa927f9af5404 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 7 Jan 2026 22:37:55 +0100 Subject: rbd: check for EOD after exclusive lock is ensured to be held Similar to commit 870611e4877e ("rbd: get snapshot context after exclusive lock is ensured to be held"), move the "beyond EOD" check into the image request state machine so that it's performed after exclusive lock is ensured to be held. This avoids various race conditions which can arise when the image is shrunk under I/O (in practice, mostly readahead). In one such scenario rbd_assert(objno < rbd_dev->object_map_size); can be triggered if a close-to-EOD read gets queued right before the shrink is initiated and the EOD check is performed against an outdated mapping_size. After the resize is done on the server side and exclusive lock is (re)acquired bringing along the new (now shrunk) object map, the read starts going through the state machine and rbd_obj_may_exist() gets invoked on an object that is out of bounds of rbd_dev->object_map array. Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang --- drivers/block/rbd.c | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index af0e21149dbc..8f441eb8b192 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3495,11 +3495,29 @@ static void rbd_img_object_requests(struct rbd_img_request *img_req) rbd_assert(!need_exclusive_lock(img_req) || __rbd_is_lock_owner(rbd_dev)); - if (rbd_img_is_write(img_req)) { - rbd_assert(!img_req->snapc); + if (test_bit(IMG_REQ_CHILD, &img_req->flags)) { + rbd_assert(!rbd_img_is_write(img_req)); + } else { + struct request *rq = blk_mq_rq_from_pdu(img_req); + u64 off = (u64)blk_rq_pos(rq) << SECTOR_SHIFT; + u64 len = blk_rq_bytes(rq); + u64 mapping_size; + down_read(&rbd_dev->header_rwsem); - img_req->snapc = ceph_get_snap_context(rbd_dev->header.snapc); + mapping_size = rbd_dev->mapping.size; + if (rbd_img_is_write(img_req)) { + rbd_assert(!img_req->snapc); + img_req->snapc = + ceph_get_snap_context(rbd_dev->header.snapc); + } up_read(&rbd_dev->header_rwsem); + + if (unlikely(off + len > mapping_size)) { + rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)", + off, len, mapping_size); + img_req->pending.result = -EIO; + return; + } } for_each_obj_request(img_req, obj_req) { @@ -4725,7 +4743,6 @@ static void rbd_queue_workfn(struct work_struct *work) struct request *rq = blk_mq_rq_from_pdu(img_request); u64 offset = (u64)blk_rq_pos(rq) << SECTOR_SHIFT; u64 length = blk_rq_bytes(rq); - u64 mapping_size; int result; /* Ignore/skip any zero-length requests */ @@ -4738,17 +4755,9 @@ static void rbd_queue_workfn(struct work_struct *work) blk_mq_start_request(rq); down_read(&rbd_dev->header_rwsem); - mapping_size = rbd_dev->mapping.size; rbd_img_capture_header(img_request); up_read(&rbd_dev->header_rwsem); - if (offset + length > mapping_size) { - rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)", offset, - length, mapping_size); - result = -EIO; - goto err_img_request; - } - dout("%s rbd_dev %p img_req %p %s %llu~%llu\n", __func__, rbd_dev, img_request, obj_op_name(op_type), offset, length); -- cgit v1.2.3 From bc8dedae022ce3058659c3addef3ec4b41d15e00 Mon Sep 17 00:00:00 2001 From: Daniel Vogelbacher Date: Sun, 1 Feb 2026 09:34:01 +0100 Subject: ceph: fix oops due to invalid pointer for kfree() in parse_longname() This fixes a kernel oops when reading ceph snapshot directories (.snap), for example by simply running `ls /mnt/my_ceph/.snap`. The variable str is guarded by __free(kfree), but advanced by one for skipping the initial '_' in snapshot names. Thus, kfree() is called with an invalid pointer. This patch removes the need for advancing the pointer so kfree() is called with correct memory pointer. Steps to reproduce: 1. Create snapshots on a cephfs volume (I've 63 snaps in my testcase) 2. Add cephfs mount to fstab $ echo "samba-fileserver@.files=/volumes/datapool/stuff/3461082b-ecc9-4e82-8549-3fd2590d3fb6 /mnt/test/stuff ceph acl,noatime,_netdev 0 0" >> /etc/fstab 3. Reboot the system $ systemctl reboot 4. Check if it's really mounted $ mount | grep stuff 5. List snapshots (expected 63 snapshots on my system) $ ls /mnt/test/stuff/.snap Now ls hangs forever and the kernel log shows the oops. Cc: stable@vger.kernel.org Fixes: 101841c38346 ("[ceph] parse_longname(): strrchr() expects NUL-terminated string") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220807 Suggested-by: Helge Deller Signed-off-by: Daniel Vogelbacher Reviewed-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/crypto.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index 0ea4db650f85..9a115282f67d 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -166,12 +166,13 @@ static struct inode *parse_longname(const struct inode *parent, struct ceph_vino vino = { .snap = CEPH_NOSNAP }; char *name_end, *inode_number; int ret = -EIO; - /* NUL-terminate */ - char *str __free(kfree) = kmemdup_nul(name, *name_len, GFP_KERNEL); + /* Snapshot name must start with an underscore */ + if (*name_len <= 0 || name[0] != '_') + return ERR_PTR(-EIO); + /* Skip initial '_' and NUL-terminate */ + char *str __free(kfree) = kmemdup_nul(name + 1, *name_len - 1, GFP_KERNEL); if (!str) return ERR_PTR(-ENOMEM); - /* Skip initial '_' */ - str++; name_end = strrchr(str, '_'); if (!name_end) { doutc(cl, "failed to parse long snapshot name: %s\n", str); -- cgit v1.2.3 From 7987cce375ac8ce98e170a77aa2399f2cf6eb99f Mon Sep 17 00:00:00 2001 From: Viacheslav Dubeyko Date: Tue, 3 Feb 2026 14:54:46 -0800 Subject: ceph: fix NULL pointer dereference in ceph_mds_auth_match() The CephFS kernel client has regression starting from 6.18-rc1. We have issue in ceph_mds_auth_match() if fs_name == NULL: const char fs_name = mdsc->fsc->mount_options->mds_namespace; ... if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) { / fsname mismatch, try next one */ return 0; } Patrick Donnelly suggested that: In summary, we should definitely start decoding `fs_name` from the MDSMap and do strict authorizations checks against it. Note that the `-o mds_namespace=foo` should only be used for selecting the file system to mount and nothing else. It's possible no mds_namespace is specified but the kernel will mount the only file system that exists which may have name "foo". This patch reworks ceph_mdsmap_decode() and namespace_equals() with the goal of supporting the suggested concept. Now struct ceph_mdsmap contains m_fs_name field that receives copy of extracted FS name by ceph_extract_encoded_string(). For the case of "old" CephFS file systems, it is used "cephfs" name. [ idryomov: replace redundant %*pE with %s in ceph_mdsmap_decode(), get rid of a series of strlen() calls in ceph_namespace_match(), drop changes to namespace_equals() body to avoid treating empty mds_namespace as equal, drop changes to ceph_mdsc_handle_fsmap() as namespace_equals() isn't an equivalent substitution there ] Cc: stable@vger.kernel.org Fixes: 22c73d52a6d0 ("ceph: fix multifs mds auth caps issue") Link: https://tracker.ceph.com/issues/73886 Signed-off-by: Viacheslav Dubeyko Reviewed-by: Patrick Donnelly Tested-by: Patrick Donnelly Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 5 +++-- fs/ceph/mdsmap.c | 26 +++++++++++++++++++------- fs/ceph/mdsmap.h | 1 + fs/ceph/super.h | 16 ++++++++++++++-- include/linux/ceph/ceph_fs.h | 6 ++++++ 5 files changed, 43 insertions(+), 11 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 7e4eab824dae..c45bd19d4b1c 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5671,7 +5671,7 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid); u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid); struct ceph_client *cl = mdsc->fsc->client; - const char *fs_name = mdsc->fsc->mount_options->mds_namespace; + const char *fs_name = mdsc->mdsmap->m_fs_name; const char *spath = mdsc->fsc->mount_options->server_path; bool gid_matched = false; u32 gid, tlen, len; @@ -5679,7 +5679,8 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, doutc(cl, "fsname check fs_name=%s match.fs_name=%s\n", fs_name, auth->match.fs_name ? auth->match.fs_name : ""); - if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) { + + if (!ceph_namespace_match(auth->match.fs_name, fs_name)) { /* fsname mismatch, try next one */ return 0; } diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 2c7b151a7c95..b228e5ecfb92 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -353,22 +353,33 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 8) { - u32 fsname_len; + size_t fsname_len; + /* enabled */ ceph_decode_8_safe(p, end, m->m_enabled, bad_ext); + /* fs_name */ - ceph_decode_32_safe(p, end, fsname_len, bad_ext); + m->m_fs_name = ceph_extract_encoded_string(p, end, + &fsname_len, + GFP_NOFS); + if (IS_ERR(m->m_fs_name)) { + m->m_fs_name = NULL; + goto nomem; + } /* validate fsname against mds_namespace */ - if (!namespace_equals(mdsc->fsc->mount_options, *p, + if (!namespace_equals(mdsc->fsc->mount_options, m->m_fs_name, fsname_len)) { - pr_warn_client(cl, "fsname %*pE doesn't match mds_namespace %s\n", - (int)fsname_len, (char *)*p, + pr_warn_client(cl, "fsname %s doesn't match mds_namespace %s\n", + m->m_fs_name, mdsc->fsc->mount_options->mds_namespace); goto bad; } - /* skip fsname after validation */ - ceph_decode_skip_n(p, end, fsname_len, bad); + } else { + m->m_enabled = false; + m->m_fs_name = kstrdup(CEPH_OLD_FS_NAME, GFP_NOFS); + if (!m->m_fs_name) + goto nomem; } /* damaged */ if (mdsmap_ev >= 9) { @@ -430,6 +441,7 @@ void ceph_mdsmap_destroy(struct ceph_mdsmap *m) kfree(m->m_info); } kfree(m->m_data_pg_pools); + kfree(m->m_fs_name); kfree(m); } diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h index 1f2171dd01bf..d48d07c3516d 100644 --- a/fs/ceph/mdsmap.h +++ b/fs/ceph/mdsmap.h @@ -45,6 +45,7 @@ struct ceph_mdsmap { bool m_enabled; bool m_damaged; int m_num_laggy; + char *m_fs_name; }; static inline struct ceph_entity_addr * diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a1f781c46b41..29a980e22dc2 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -104,14 +104,26 @@ struct ceph_mount_options { struct fscrypt_dummy_policy dummy_enc_policy; }; +#define CEPH_NAMESPACE_WILDCARD "*" + +static inline bool ceph_namespace_match(const char *pattern, + const char *target) +{ + if (!pattern || !pattern[0] || + !strcmp(pattern, CEPH_NAMESPACE_WILDCARD)) + return true; + + return !strcmp(pattern, target); +} + /* * Check if the mds namespace in ceph_mount_options matches * the passed in namespace string. First time match (when * ->mds_namespace is NULL) is treated specially, since * ->mds_namespace needs to be initialized by the caller. */ -static inline int namespace_equals(struct ceph_mount_options *fsopt, - const char *namespace, size_t len) +static inline bool namespace_equals(struct ceph_mount_options *fsopt, + const char *namespace, size_t len) { return !(fsopt->mds_namespace && (strlen(fsopt->mds_namespace) != len || diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index c7f2c63b3bc3..08e5dbe15ca4 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -31,6 +31,12 @@ #define CEPH_INO_CEPH 2 /* hidden .ceph dir */ #define CEPH_INO_GLOBAL_SNAPREALM 3 /* global dummy snaprealm */ +/* + * name for "old" CephFS file systems, + * see ceph.git e2b151d009640114b2565c901d6f41f6cd5ec652 + */ +#define CEPH_OLD_FS_NAME "cephfs" + /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 -- cgit v1.2.3