From 262b73ef442e68e53220b9d6fc5a0d08b557fa42 Mon Sep 17 00:00:00 2001 From: Chunjie Zhu Date: Sat, 12 Apr 2025 21:15:55 -0500 Subject: smb3 client: fix open hardlink on deferred close file error The following Python script results in unexpected behaviour when run on a CIFS filesystem against a Windows Server: # Create file fd = os.open('test', os.O_WRONLY|os.O_CREAT) os.write(fd, b'foo') os.close(fd) # Open and close the file to leave a pending deferred close fd = os.open('test', os.O_RDONLY|os.O_DIRECT) os.close(fd) # Try to open the file via a hard link os.link('test', 'new') newfd = os.open('new', os.O_RDONLY|os.O_DIRECT) The final open returns EINVAL due to the server returning STATUS_INVALID_PARAMETER. The root cause of this is that the client caches lease keys per inode, but the spec requires them to be related to the filename which causes problems when hard links are involved: From MS-SMB2 section 3.3.5.9.11: "The server MUST attempt to locate a Lease by performing a lookup in the LeaseTable.LeaseList using the LeaseKey in the SMB2_CREATE_REQUEST_LEASE_V2 as the lookup key. If a lease is found, Lease.FileDeleteOnClose is FALSE, and Lease.Filename does not match the file name for the incoming request, the request MUST be failed with STATUS_INVALID_PARAMETER" On client side, we first check the context of file open, if it hits above conditions, we first close all opening files which are belong to the same inode, then we do open the hard link file. Cc: stable@vger.kernel.org Signed-off-by: Chunjie Zhu Signed-off-by: Steve French --- fs/smb/client/cifsproto.h | 2 ++ fs/smb/client/file.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index cfcc07905bdf..59f6fdfe560e 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -163,6 +163,8 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool); extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, struct cifsFileInfo **ret_file); +extern int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, + struct file *file); extern unsigned int smbCalcSize(void *buf); extern int decode_negTokenInit(unsigned char *security_blob, int length, struct TCP_Server_Info *server); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 8407fb108664..9e8f404b9e56 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1007,6 +1007,11 @@ int cifs_open(struct inode *inode, struct file *file) } else { _cifsFileInfo_put(cfile, true, false); } + } else { + /* hard link on the defeered close file */ + rc = cifs_get_hardlink_path(tcon, inode, file); + if (rc) + cifs_close_deferred_file(CIFS_I(inode)); } if (server->oplocks) @@ -2071,6 +2076,29 @@ cifs_move_llist(struct list_head *source, struct list_head *dest) list_move(li, dest); } +int +cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, + struct file *file) +{ + struct cifsFileInfo *open_file = NULL; + struct cifsInodeInfo *cinode = CIFS_I(inode); + int rc = 0; + + spin_lock(&tcon->open_file_lock); + spin_lock(&cinode->open_file_lock); + + list_for_each_entry(open_file, &cinode->openFileList, flist) { + if (file->f_flags == open_file->f_flags) { + rc = -EINVAL; + break; + } + } + + spin_unlock(&cinode->open_file_lock); + spin_unlock(&tcon->open_file_lock); + return rc; +} + void cifs_free_llist(struct list_head *llist) { -- cgit v1.2.3 From c707193a17128fae2802d10cbad7239cc57f0c95 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 2 Apr 2025 13:26:47 -0700 Subject: Revert "smb: client: Fix netns refcount imbalance causing leaks and use-after-free" This reverts commit 4e7f1644f2ac6d01dc584f6301c3b1d5aac4eaef. The commit e9f2517a3e18 ("smb: client: fix TCP timers deadlock after rmmod") is not only a bogus fix for LOCKDEP null-ptr-deref but also introduces a real issue, TCP sockets leak, which will be explained in detail in the next revert. Also, CNA assigned CVE-2024-54680 to it but is rejecting it. [0] Thus, we are reverting the commit and its follow-up commit 4e7f1644f2ac ("smb: client: Fix netns refcount imbalance causing leaks and use-after-free"). Link: https://lore.kernel.org/all/2025040248-tummy-smilingly-4240@gregkh/ #[0] Fixes: 4e7f1644f2ac ("smb: client: Fix netns refcount imbalance causing leaks and use-after-free") Signed-off-by: Kuniyuki Iwashima Cc: stable@vger.kernel.org Signed-off-by: Steve French --- fs/smb/client/connect.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 4a0b2d220fe8..370b79b2eaa6 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -300,7 +300,6 @@ cifs_abort_connection(struct TCP_Server_Info *server) server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; - put_net(cifs_net_ns(server)); } server->sequence_number = 0; server->session_estab = false; @@ -3369,12 +3368,8 @@ generic_ip_connect(struct TCP_Server_Info *server) /* * Grab netns reference for the socket. * - * This reference will be released in several situations: - * - In the failure path before the cifsd thread is started. - * - In the all place where server->socket is released, it is - * also set to NULL. - * - Ultimately in clean_demultiplex_info(), during the final - * teardown. + * It'll be released here, on error, or in clean_demultiplex_info() upon server + * teardown. */ get_net(net); @@ -3390,8 +3385,10 @@ generic_ip_connect(struct TCP_Server_Info *server) } rc = bind_socket(server); - if (rc < 0) + if (rc < 0) { + put_net(cifs_net_ns(server)); return rc; + } /* * Eventually check for other socket options to change from @@ -3446,6 +3443,9 @@ generic_ip_connect(struct TCP_Server_Info *server) (server->rfc1001_sessinit == -1 && sport == htons(RFC1001_PORT))) rc = ip_rfc1001_connect(server); + if (rc < 0) + put_net(cifs_net_ns(server)); + return rc; } -- cgit v1.2.3 From 95d2b9f693ff2a1180a23d7d59acc0c4e72f4c41 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 2 Apr 2025 13:26:48 -0700 Subject: Revert "smb: client: fix TCP timers deadlock after rmmod" This reverts commit e9f2517a3e18a54a3943c098d2226b245d488801. Commit e9f2517a3e18 ("smb: client: fix TCP timers deadlock after rmmod") is intended to fix a null-ptr-deref in LOCKDEP, which is mentioned as CVE-2024-54680, but is actually did not fix anything; The issue can be reproduced on top of it. [0] Also, it reverted the change by commit ef7134c7fc48 ("smb: client: Fix use-after-free of network namespace.") and introduced a real issue by reviving the kernel TCP socket. When a reconnect happens for a CIFS connection, the socket state transitions to FIN_WAIT_1. Then, inet_csk_clear_xmit_timers_sync() in tcp_close() stops all timers for the socket. If an incoming FIN packet is lost, the socket will stay at FIN_WAIT_1 forever, and such sockets could be leaked up to net.ipv4.tcp_max_orphans. Usually, FIN can be retransmitted by the peer, but if the peer aborts the connection, the issue comes into reality. I warned about this privately by pointing out the exact report [1], but the bogus fix was finally merged. So, we should not stop the timers to finally kill the connection on our side in that case, meaning we must not use a kernel socket for TCP whose sk->sk_net_refcnt is 0. The kernel socket does not have a reference to its netns to make it possible to tear down netns without cleaning up every resource in it. For example, tunnel devices use a UDP socket internally, but we can destroy netns without removing such devices and let it complete during exit. Otherwise, netns would be leaked when the last application died. However, this is problematic for TCP sockets because TCP has timers to close the connection gracefully even after the socket is close()d. The lifetime of the socket and its netns is different from the lifetime of the underlying connection. If the socket user does not maintain the netns lifetime, the timer could be fired after the socket is close()d and its netns is freed up, resulting in use-after-free. Actually, we have seen so many similar issues and converted such sockets to have a reference to netns. That's why I converted the CIFS client socket to have a reference to netns (sk->sk_net_refcnt == 1), which is somehow mentioned as out-of-scope of CIFS and technically wrong in e9f2517a3e18, but **is in-scope and right fix**. Regarding the LOCKDEP issue, we can prevent the module unload by bumping the module refcount when switching the LOCKDDEP key in sock_lock_init_class_and_name(). [2] For a while, let's revert the bogus fix. Note that now we can use sk_net_refcnt_upgrade() for the socket conversion, but I'll do so later separately to make backport easy. Link: https://lore.kernel.org/all/20250402020807.28583-1-kuniyu@amazon.com/ #[0] Link: https://lore.kernel.org/netdev/c08bd5378da647a2a4c16698125d180a@huawei.com/ #[1] Link: https://lore.kernel.org/lkml/20250402005841.19846-1-kuniyu@amazon.com/ #[2] Fixes: e9f2517a3e18 ("smb: client: fix TCP timers deadlock after rmmod") Signed-off-by: Kuniyuki Iwashima Cc: stable@vger.kernel.org Signed-off-by: Steve French --- fs/smb/client/connect.c | 36 ++++++++++-------------------------- 1 file changed, 10 insertions(+), 26 deletions(-) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 370b79b2eaa6..df976ce6aed9 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1073,13 +1073,9 @@ clean_demultiplex_info(struct TCP_Server_Info *server) msleep(125); if (cifs_rdma_enabled(server)) smbd_destroy(server); - if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; - - /* Release netns reference for the socket. */ - put_net(cifs_net_ns(server)); } if (!list_empty(&server->pending_mid_q)) { @@ -1127,7 +1123,6 @@ clean_demultiplex_info(struct TCP_Server_Info *server) */ } - /* Release netns reference for this server. */ put_net(cifs_net_ns(server)); kfree(server->leaf_fullpath); kfree(server->hostname); @@ -1773,8 +1768,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; - - /* Grab netns reference for this server. */ cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->sign = ctx->sign; @@ -1902,7 +1895,6 @@ smbd_connected: out_err_crypto_release: cifs_crypto_secmech_release(tcp_ses); - /* Release netns reference for this server. */ put_net(cifs_net_ns(tcp_ses)); out_err: @@ -1911,10 +1903,8 @@ out_err: cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); kfree(tcp_ses->leaf_fullpath); - if (tcp_ses->ssocket) { + if (tcp_ses->ssocket) sock_release(tcp_ses->ssocket); - put_net(cifs_net_ns(tcp_ses)); - } kfree(tcp_ses); } return ERR_PTR(rc); @@ -3358,20 +3348,20 @@ generic_ip_connect(struct TCP_Server_Info *server) socket = server->ssocket; } else { struct net *net = cifs_net_ns(server); + struct sock *sk; - rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket); + rc = __sock_create(net, sfamily, SOCK_STREAM, + IPPROTO_TCP, &server->ssocket, 1); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); return rc; } - /* - * Grab netns reference for the socket. - * - * It'll be released here, on error, or in clean_demultiplex_info() upon server - * teardown. - */ - get_net(net); + sk = server->ssocket->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); @@ -3385,10 +3375,8 @@ generic_ip_connect(struct TCP_Server_Info *server) } rc = bind_socket(server); - if (rc < 0) { - put_net(cifs_net_ns(server)); + if (rc < 0) return rc; - } /* * Eventually check for other socket options to change from @@ -3425,7 +3413,6 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc); - put_net(cifs_net_ns(server)); sock_release(socket); server->ssocket = NULL; return rc; @@ -3443,9 +3430,6 @@ generic_ip_connect(struct TCP_Server_Info *server) (server->rfc1001_sessinit == -1 && sport == htons(RFC1001_PORT))) rc = ip_rfc1001_connect(server); - if (rc < 0) - put_net(cifs_net_ns(server)); - return rc; } -- cgit v1.2.3