From ea60ed6fcf29eebc78f2ce91491e6309ee005a01 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Fri, 25 Oct 2019 14:05:24 +0100 Subject: [PATCH 1/6] ceph: fix use-after-free in __ceph_remove_cap() KASAN reports a use-after-free when running xfstest generic/531, with the following trace: [ 293.903362] kasan_report+0xe/0x20 [ 293.903365] rb_erase+0x1f/0x790 [ 293.903370] __ceph_remove_cap+0x201/0x370 [ 293.903375] __ceph_remove_caps+0x4b/0x70 [ 293.903380] ceph_evict_inode+0x4e/0x360 [ 293.903386] evict+0x169/0x290 [ 293.903390] __dentry_kill+0x16f/0x250 [ 293.903394] dput+0x1c6/0x440 [ 293.903398] __fput+0x184/0x330 [ 293.903404] task_work_run+0xb9/0xe0 [ 293.903410] exit_to_usermode_loop+0xd3/0xe0 [ 293.903413] do_syscall_64+0x1a0/0x1c0 [ 293.903417] entry_SYSCALL_64_after_hwframe+0x44/0xa9 This happens because __ceph_remove_cap() may queue a cap release (__ceph_queue_cap_release) which can be scheduled before that cap is removed from the inode list with rb_erase(&cap->ci_node, &ci->i_caps); And, when this finally happens, the use-after-free will occur. This can be fixed by removing the cap from the inode list before being removed from the session list, and thus eliminating the risk of an UAF. Cc: stable@vger.kernel.org Signed-off-by: Luis Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index d3b9c9d5c1bd..f5a38910a82b 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1058,6 +1058,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode); + /* remove from inode's cap rbtree, and clear auth cap */ + rb_erase(&cap->ci_node, &ci->i_caps); + if (ci->i_auth_cap == cap) + ci->i_auth_cap = NULL; + /* remove from session list */ spin_lock(&session->s_cap_lock); if (session->s_cap_iterator == cap) { @@ -1091,11 +1096,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) spin_unlock(&session->s_cap_lock); - /* remove from inode list */ - rb_erase(&cap->ci_node, &ci->i_caps); - if (ci->i_auth_cap == cap) - ci->i_auth_cap = NULL; - if (removed) ceph_put_cap(mdsc, cap); From aa8dd816732b2bab28c54bc4d2ccf3fc8a6e0892 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 29 Oct 2019 13:50:19 +0000 Subject: [PATCH 2/6] ceph: fix RCU case handling in ceph_d_revalidate() For RCU case ->d_revalidate() is called with rcu_read_lock() and without pinning the dentry passed to it. Which means that it can't rely upon ->d_inode remaining stable; that's the reason for d_inode_rcu(), actually. Make sure we don't reload ->d_inode there. Cc: stable@vger.kernel.org Signed-off-by: Al Viro Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/dir.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4ca0b8ff9a72..d17a789fd856 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1553,36 +1553,37 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) { int valid = 0; struct dentry *parent; - struct inode *dir; + struct inode *dir, *inode; if (flags & LOOKUP_RCU) { parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) return -ECHILD; + inode = d_inode_rcu(dentry); } else { parent = dget_parent(dentry); dir = d_inode(parent); + inode = d_inode(dentry); } dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry, - dentry, d_inode(dentry), ceph_dentry(dentry)->offset); + dentry, inode, ceph_dentry(dentry)->offset); /* always trust cached snapped dentries, snapdir dentry */ if (ceph_snap(dir) != CEPH_NOSNAP) { dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry, - dentry, d_inode(dentry)); + dentry, inode); valid = 1; - } else if (d_really_is_positive(dentry) && - ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) { + } else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) { valid = 1; } else { valid = dentry_lease_is_valid(dentry, flags); if (valid == -ECHILD) return valid; if (valid || dir_lease_is_valid(dir, dentry)) { - if (d_really_is_positive(dentry)) - valid = ceph_is_any_caps(d_inode(dentry)); + if (inode) + valid = ceph_is_any_caps(inode); else valid = 1; } From 1f08529c84cfecaf1261ed9b7e17fab18541c58f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 29 Oct 2019 13:53:29 +0000 Subject: [PATCH 3/6] ceph: add missing check in d_revalidate snapdir handling We should not play with dcache without parent locked... Cc: stable@vger.kernel.org Signed-off-by: Al Viro Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9f135624ae47..c07407586ce8 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1434,6 +1434,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) dout(" final dn %p\n", dn); } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP || req->r_op == CEPH_MDS_OP_MKSNAP) && + test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) && !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) { struct inode *dir = req->r_parent; From 5bb5e6ee6f5c557dcd19822eccd7bcced1e1a410 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 30 Oct 2019 12:15:10 -0400 Subject: [PATCH 4/6] ceph: don't try to handle hashed dentries in non-O_CREAT atomic_open If ceph_atomic_open is handed a !d_in_lookup dentry, then that means that it already passed d_revalidate so we *know* that it's negative (or at least was very recently). Just return -ENOENT in that case. This also addresses a subtle bug in dentry handling. Non-O_CREAT opens call atomic_open with the parent's i_rwsem shared, but calling d_splice_alias on a hashed dentry requires the exclusive lock. If ceph_atomic_open receives a hashed, negative dentry on a non-O_CREAT open, and another client were to race in and create the file before we issue our OPEN, ceph_fill_trace could end up calling d_splice_alias on the dentry with the new inode with insufficient locks. Cc: stable@vger.kernel.org Reported-by: Al Viro Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/file.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d277f71abe0b..d2854cd2f4f5 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -462,6 +462,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, err = ceph_security_init_secctx(dentry, mode, &as_ctx); if (err < 0) goto out_ctx; + } else if (!d_in_lookup(dentry)) { + /* If it's not being looked up, it's negative */ + return -ENOENT; } /* do the open */ From a3a0819388b2bf15e7eafe38ff6aacfc27b12df0 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Thu, 31 Oct 2019 11:49:39 +0000 Subject: [PATCH 5/6] ceph: don't allow copy_file_range when stripe_count != 1 copy_file_range tries to use the OSD 'copy-from' operation, which simply performs a full object copy. Unfortunately, the implementation of this system call assumes that stripe_count is always set to 1 and doesn't take into account that the data may be striped across an object set. If the file layout has stripe_count different from 1, then the destination file data will be corrupted. For example: Consider a 8 MiB file with 4 MiB object size, stripe_count of 2 and stripe_size of 2 MiB; the first half of the file will be filled with 'A's and the second half will be filled with 'B's: 0 4M 8M Obj1 Obj2 +------+------+ +----+ +----+ file: | AAAA | BBBB | | AA | | AA | +------+------+ |----| |----| | BB | | BB | +----+ +----+ If we copy_file_range this file into a new file (which needs to have the same file layout!), then it will start by copying the object starting at file offset 0 (Obj1). And then it will copy the object starting at file offset 4M -- which is Obj1 again. Unfortunately, the solution for this is to not allow remote object copies to be performed when the file layout stripe_count is not 1 and simply fallback to the default (VFS) copy_file_range implementation. Cc: stable@vger.kernel.org Signed-off-by: Luis Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/file.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d2854cd2f4f5..bd77adb64bfd 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1959,10 +1959,18 @@ 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; + /* + * Striped file layouts require that we copy partial objects, but the + * OSD copy-from operation only supports full-object copies. Limit + * this to non-striped file layouts for now. + */ if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) || - (src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) || - (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) + (src_ci->i_layout.stripe_count != 1) || + (dst_ci->i_layout.stripe_count != 1) || + (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) { + dout("Invalid src/dst files layout\n"); return -EOPNOTSUPP; + } if (len < src_ci->i_layout.object_size) return -EOPNOTSUPP; /* no remote copy will be done */ From ff29fde84d1fc82f233c7da0daa3574a3942bec7 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 7 Nov 2019 09:39:32 -0500 Subject: [PATCH 6/6] ceph: return -EINVAL if given fsc mount option on kernel w/o support If someone requests fscache on the mount, and the kernel doesn't support it, it should fail the mount. [ Drop ceph prefix -- it's provided by pr_err. ] Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/super.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index edfd643a8205..b47f43fc2d68 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -268,6 +268,7 @@ static int parse_fsopt_token(char *c, void *private) } break; case Opt_fscache_uniq: +#ifdef CONFIG_CEPH_FSCACHE kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = kstrndup(argstr[0].from, argstr[0].to-argstr[0].from, @@ -276,7 +277,10 @@ static int parse_fsopt_token(char *c, void *private) return -ENOMEM; fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; break; - /* misc */ +#else + pr_err("fscache support is disabled\n"); + return -EINVAL; +#endif case Opt_wsize: if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE) return -EINVAL; @@ -353,10 +357,15 @@ static int parse_fsopt_token(char *c, void *private) fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; case Opt_fscache: +#ifdef CONFIG_CEPH_FSCACHE fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = NULL; break; +#else + pr_err("fscache support is disabled\n"); + return -EINVAL; +#endif case Opt_nofscache: fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq);