October 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] mptcp: prevent MPC handshake on port-based signal endpoints" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 3d041393ea8c815f773020fb4a995331a69c0139 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101816-ripping-veggie-2a69@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 3d041393ea8c815f773020fb4a995331a69c0139 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Mon, 14 Oct 2024 16:06:00 +0200 Subject: [PATCH] mptcp: prevent MPC handshake on port-based signal endpoints Syzkaller reported a lockdep splat: ============================================ WARNING: possible recursive locking detected 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Not tainted -------------------------------------------- syz-executor364/5113 is trying to acquire lock: ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 but task is already holding lock: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-slock-AF_INET); lock(k-slock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 7 locks held by syz-executor364/5113: #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline] #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg+0x153/0x1b10 net/mptcp/protocol.c:1806 #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline] #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg_fastopen+0x11f/0x530 net/mptcp/protocol.c:1727 #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x5f/0x1b80 net/ipv4/ip_output.c:470 #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1390 net/ipv4/ip_output.c:228 #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: local_lock_acquire include/linux/local_lock_internal.h:29 [inline] #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: process_backlog+0x33b/0x15b0 net/core/dev.c:6104 #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_local_deliver_finish+0x230/0x5f0 net/ipv4/ip_input.c:232 #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 stack backtrace: CPU: 0 UID: 0 PID: 5113 Comm: syz-executor364 Not tainted 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119 check_deadlock kernel/locking/lockdep.c:3061 [inline] validate_chain+0x15d3/0x5900 kernel/locking/lockdep.c:3855 __lock_acquire+0x137a/0x2040 kernel/locking/lockdep.c:5142 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5759 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 mptcp_sk_clone_init+0x32/0x13c0 net/mptcp/protocol.c:3279 subflow_syn_recv_sock+0x931/0x1920 net/mptcp/subflow.c:874 tcp_check_req+0xfe4/0x1a20 net/ipv4/tcp_minisocks.c:853 tcp_v4_rcv+0x1c3e/0x37f0 net/ipv4/tcp_ipv4.c:2267 ip_protocol_deliver_rcu+0x22e/0x440 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x341/0x5f0 net/ipv4/ip_input.c:233 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 __netif_receive_skb_one_core net/core/dev.c:5661 [inline] __netif_receive_skb+0x2bf/0x650 net/core/dev.c:5775 process_backlog+0x662/0x15b0 net/core/dev.c:6108 __napi_poll+0xcb/0x490 net/core/dev.c:6772 napi_poll net/core/dev.c:6841 [inline] net_rx_action+0x89b/0x1240 net/core/dev.c:6963 handle_softirqs+0x2c4/0x970 kernel/softirq.c:554 do_softirq+0x11b/0x1e0 kernel/softirq.c:455 </IRQ> <TASK> __local_bh_enable_ip+0x1bb/0x200 kernel/softirq.c:382 local_bh_enable include/linux/bottom_half.h:33 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:908 [inline] __dev_queue_xmit+0x1763/0x3e90 net/core/dev.c:4450 dev_queue_xmit include/linux/netdevice.h:3105 [inline] neigh_hh_output include/net/neighbour.h:526 [inline] neigh_output include/net/neighbour.h:540 [inline] ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:235 ip_local_out net/ipv4/ip_output.c:129 [inline] __ip_queue_xmit+0x118c/0x1b80 net/ipv4/ip_output.c:535 __tcp_transmit_skb+0x2544/0x3b30 net/ipv4/tcp_output.c:1466 tcp_rcv_synsent_state_process net/ipv4/tcp_input.c:6542 [inline] tcp_rcv_state_process+0x2c32/0x4570 net/ipv4/tcp_input.c:6729 tcp_v4_do_rcv+0x77d/0xc70 net/ipv4/tcp_ipv4.c:1934 sk_backlog_rcv include/net/sock.h:1111 [inline] __release_sock+0x214/0x350 net/core/sock.c:3004 release_sock+0x61/0x1f0 net/core/sock.c:3558 mptcp_sendmsg_fastopen+0x1ad/0x530 net/mptcp/protocol.c:1733 mptcp_sendmsg+0x1884/0x1b10 net/mptcp/protocol.c:1812 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597 ___sys_sendmsg net/socket.c:2651 [inline] __sys_sendmmsg+0x3b2/0x740 net/socket.c:2737 __do_sys_sendmmsg net/socket.c:2766 [inline] __se_sys_sendmmsg net/socket.c:2763 [inline] __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2763 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f04fb13a6b9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 01 1a 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd651f42d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f04fb13a6b9 RDX: 0000000000000001 RSI: 0000000020000d00 RDI: 0000000000000004 RBP: 00007ffd651f4310 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000020000080 R11: 0000000000000246 R12: 00000000000f4240 R13: 00007f04fb187449 R14: 00007ffd651f42f4 R15: 00007ffd651f4300 </TASK> As noted by Cong Wang, the splat is false positive, but the code path leading to the report is an unexpected one: a client is attempting an MPC handshake towards the in-kernel listener created by the in-kernel PM for a port based signal endpoint. Such connection will be never accepted; many of them can make the listener queue full and preventing the creation of MPJ subflow via such listener - its intended role. Explicitly detect this scenario at initial-syn time and drop the incoming MPC request. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Cc: stable(a)vger.kernel.org Reported-by: syzbot+f4aacdfef2c6a6529c3e(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=f4aacdfef2c6a6529c3e Cc: Cong Wang <cong.wang(a)bytedance.com> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://patch.msgid.link/20241014-net-mptcp-mpc-port-endp-v2-1-7faea8e6b6ae… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index ad88bd3c58df..19eb9292bd60 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -17,6 +17,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK), SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP), SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED), + SNMP_MIB_ITEM("MPCapableEndpAttempt", MPTCP_MIB_MPCAPABLEENDPATTEMPT), SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT), SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 3206cdda8bb1..128282982843 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -12,6 +12,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */ MPTCP_MIB_MPCAPABLEACTIVEDROP, /* Client-side fallback due to a MPC drop */ MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */ + MPTCP_MIB_MPCAPABLEENDPATTEMPT, /* Prohibited MPC to port-based endp */ MPTCP_MIB_TOKENFALLBACKINIT, /* Could not init/allocate token */ MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index f6f0a38a0750..1a78998fe1f4 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1121,6 +1121,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, */ inet_sk_state_store(newsk, TCP_LISTEN); lock_sock(ssk); + WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true); err = __inet_listen_sk(ssk, backlog); if (!err) mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 74417aae08d0..568a72702b08 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -535,6 +535,7 @@ struct mptcp_subflow_context { __unused : 8; bool data_avail; bool scheduled; + bool pm_listener; /* a listener managed by the kernel PM? */ u32 remote_nonce; u64 thmac; u32 local_nonce; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 25dde81bcb75..6170f2fff71e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -132,6 +132,13 @@ static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason) } } +static int subflow_reset_req_endp(struct request_sock *req, struct sk_buff *skb) +{ + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEENDPATTEMPT); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); + return -EPERM; +} + /* Init mptcp request socket. * * Returns an error code if a JOIN has failed and a TCP reset @@ -165,6 +172,8 @@ static int subflow_check_req(struct request_sock *req, if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); + if (unlikely(listener->pm_listener)) + return subflow_reset_req_endp(req, skb); if (opt_mp_join) return 0; } else if (opt_mp_join) { @@ -172,6 +181,8 @@ static int subflow_check_req(struct request_sock *req, if (mp_opt.backup) SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); + } else if (unlikely(listener->pm_listener)) { + return subflow_reset_req_endp(req, skb); } if (opt_mp_capable && listener->request_mptcp) {

6 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mptcp: prevent MPC handshake on port-based signal endpoints" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 3d041393ea8c815f773020fb4a995331a69c0139 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101814-postal-swarm-0080@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 3d041393ea8c815f773020fb4a995331a69c0139 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Mon, 14 Oct 2024 16:06:00 +0200 Subject: [PATCH] mptcp: prevent MPC handshake on port-based signal endpoints Syzkaller reported a lockdep splat: ============================================ WARNING: possible recursive locking detected 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Not tainted -------------------------------------------- syz-executor364/5113 is trying to acquire lock: ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 but task is already holding lock: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-slock-AF_INET); lock(k-slock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 7 locks held by syz-executor364/5113: #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline] #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg+0x153/0x1b10 net/mptcp/protocol.c:1806 #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline] #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg_fastopen+0x11f/0x530 net/mptcp/protocol.c:1727 #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x5f/0x1b80 net/ipv4/ip_output.c:470 #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1390 net/ipv4/ip_output.c:228 #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: local_lock_acquire include/linux/local_lock_internal.h:29 [inline] #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: process_backlog+0x33b/0x15b0 net/core/dev.c:6104 #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_local_deliver_finish+0x230/0x5f0 net/ipv4/ip_input.c:232 #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 stack backtrace: CPU: 0 UID: 0 PID: 5113 Comm: syz-executor364 Not tainted 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119 check_deadlock kernel/locking/lockdep.c:3061 [inline] validate_chain+0x15d3/0x5900 kernel/locking/lockdep.c:3855 __lock_acquire+0x137a/0x2040 kernel/locking/lockdep.c:5142 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5759 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 mptcp_sk_clone_init+0x32/0x13c0 net/mptcp/protocol.c:3279 subflow_syn_recv_sock+0x931/0x1920 net/mptcp/subflow.c:874 tcp_check_req+0xfe4/0x1a20 net/ipv4/tcp_minisocks.c:853 tcp_v4_rcv+0x1c3e/0x37f0 net/ipv4/tcp_ipv4.c:2267 ip_protocol_deliver_rcu+0x22e/0x440 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x341/0x5f0 net/ipv4/ip_input.c:233 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 __netif_receive_skb_one_core net/core/dev.c:5661 [inline] __netif_receive_skb+0x2bf/0x650 net/core/dev.c:5775 process_backlog+0x662/0x15b0 net/core/dev.c:6108 __napi_poll+0xcb/0x490 net/core/dev.c:6772 napi_poll net/core/dev.c:6841 [inline] net_rx_action+0x89b/0x1240 net/core/dev.c:6963 handle_softirqs+0x2c4/0x970 kernel/softirq.c:554 do_softirq+0x11b/0x1e0 kernel/softirq.c:455 </IRQ> <TASK> __local_bh_enable_ip+0x1bb/0x200 kernel/softirq.c:382 local_bh_enable include/linux/bottom_half.h:33 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:908 [inline] __dev_queue_xmit+0x1763/0x3e90 net/core/dev.c:4450 dev_queue_xmit include/linux/netdevice.h:3105 [inline] neigh_hh_output include/net/neighbour.h:526 [inline] neigh_output include/net/neighbour.h:540 [inline] ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:235 ip_local_out net/ipv4/ip_output.c:129 [inline] __ip_queue_xmit+0x118c/0x1b80 net/ipv4/ip_output.c:535 __tcp_transmit_skb+0x2544/0x3b30 net/ipv4/tcp_output.c:1466 tcp_rcv_synsent_state_process net/ipv4/tcp_input.c:6542 [inline] tcp_rcv_state_process+0x2c32/0x4570 net/ipv4/tcp_input.c:6729 tcp_v4_do_rcv+0x77d/0xc70 net/ipv4/tcp_ipv4.c:1934 sk_backlog_rcv include/net/sock.h:1111 [inline] __release_sock+0x214/0x350 net/core/sock.c:3004 release_sock+0x61/0x1f0 net/core/sock.c:3558 mptcp_sendmsg_fastopen+0x1ad/0x530 net/mptcp/protocol.c:1733 mptcp_sendmsg+0x1884/0x1b10 net/mptcp/protocol.c:1812 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597 ___sys_sendmsg net/socket.c:2651 [inline] __sys_sendmmsg+0x3b2/0x740 net/socket.c:2737 __do_sys_sendmmsg net/socket.c:2766 [inline] __se_sys_sendmmsg net/socket.c:2763 [inline] __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2763 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f04fb13a6b9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 01 1a 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd651f42d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f04fb13a6b9 RDX: 0000000000000001 RSI: 0000000020000d00 RDI: 0000000000000004 RBP: 00007ffd651f4310 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000020000080 R11: 0000000000000246 R12: 00000000000f4240 R13: 00007f04fb187449 R14: 00007ffd651f42f4 R15: 00007ffd651f4300 </TASK> As noted by Cong Wang, the splat is false positive, but the code path leading to the report is an unexpected one: a client is attempting an MPC handshake towards the in-kernel listener created by the in-kernel PM for a port based signal endpoint. Such connection will be never accepted; many of them can make the listener queue full and preventing the creation of MPJ subflow via such listener - its intended role. Explicitly detect this scenario at initial-syn time and drop the incoming MPC request. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Cc: stable(a)vger.kernel.org Reported-by: syzbot+f4aacdfef2c6a6529c3e(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=f4aacdfef2c6a6529c3e Cc: Cong Wang <cong.wang(a)bytedance.com> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://patch.msgid.link/20241014-net-mptcp-mpc-port-endp-v2-1-7faea8e6b6ae… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index ad88bd3c58df..19eb9292bd60 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -17,6 +17,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK), SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP), SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED), + SNMP_MIB_ITEM("MPCapableEndpAttempt", MPTCP_MIB_MPCAPABLEENDPATTEMPT), SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT), SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 3206cdda8bb1..128282982843 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -12,6 +12,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */ MPTCP_MIB_MPCAPABLEACTIVEDROP, /* Client-side fallback due to a MPC drop */ MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */ + MPTCP_MIB_MPCAPABLEENDPATTEMPT, /* Prohibited MPC to port-based endp */ MPTCP_MIB_TOKENFALLBACKINIT, /* Could not init/allocate token */ MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index f6f0a38a0750..1a78998fe1f4 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1121,6 +1121,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, */ inet_sk_state_store(newsk, TCP_LISTEN); lock_sock(ssk); + WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true); err = __inet_listen_sk(ssk, backlog); if (!err) mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 74417aae08d0..568a72702b08 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -535,6 +535,7 @@ struct mptcp_subflow_context { __unused : 8; bool data_avail; bool scheduled; + bool pm_listener; /* a listener managed by the kernel PM? */ u32 remote_nonce; u64 thmac; u32 local_nonce; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 25dde81bcb75..6170f2fff71e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -132,6 +132,13 @@ static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason) } } +static int subflow_reset_req_endp(struct request_sock *req, struct sk_buff *skb) +{ + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEENDPATTEMPT); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); + return -EPERM; +} + /* Init mptcp request socket. * * Returns an error code if a JOIN has failed and a TCP reset @@ -165,6 +172,8 @@ static int subflow_check_req(struct request_sock *req, if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); + if (unlikely(listener->pm_listener)) + return subflow_reset_req_endp(req, skb); if (opt_mp_join) return 0; } else if (opt_mp_join) { @@ -172,6 +181,8 @@ static int subflow_check_req(struct request_sock *req, if (mp_opt.backup) SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); + } else if (unlikely(listener->pm_listener)) { + return subflow_reset_req_endp(req, skb); } if (opt_mp_capable && listener->request_mptcp) {

6 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mptcp: prevent MPC handshake on port-based signal endpoints" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 3d041393ea8c815f773020fb4a995331a69c0139 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101811-faction-extruding-ca04@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 3d041393ea8c815f773020fb4a995331a69c0139 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Mon, 14 Oct 2024 16:06:00 +0200 Subject: [PATCH] mptcp: prevent MPC handshake on port-based signal endpoints Syzkaller reported a lockdep splat: ============================================ WARNING: possible recursive locking detected 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Not tainted -------------------------------------------- syz-executor364/5113 is trying to acquire lock: ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 but task is already holding lock: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-slock-AF_INET); lock(k-slock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 7 locks held by syz-executor364/5113: #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline] #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg+0x153/0x1b10 net/mptcp/protocol.c:1806 #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline] #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg_fastopen+0x11f/0x530 net/mptcp/protocol.c:1727 #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x5f/0x1b80 net/ipv4/ip_output.c:470 #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1390 net/ipv4/ip_output.c:228 #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: local_lock_acquire include/linux/local_lock_internal.h:29 [inline] #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: process_backlog+0x33b/0x15b0 net/core/dev.c:6104 #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline] #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline] #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_local_deliver_finish+0x230/0x5f0 net/ipv4/ip_input.c:232 #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 stack backtrace: CPU: 0 UID: 0 PID: 5113 Comm: syz-executor364 Not tainted 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119 check_deadlock kernel/locking/lockdep.c:3061 [inline] validate_chain+0x15d3/0x5900 kernel/locking/lockdep.c:3855 __lock_acquire+0x137a/0x2040 kernel/locking/lockdep.c:5142 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5759 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328 mptcp_sk_clone_init+0x32/0x13c0 net/mptcp/protocol.c:3279 subflow_syn_recv_sock+0x931/0x1920 net/mptcp/subflow.c:874 tcp_check_req+0xfe4/0x1a20 net/ipv4/tcp_minisocks.c:853 tcp_v4_rcv+0x1c3e/0x37f0 net/ipv4/tcp_ipv4.c:2267 ip_protocol_deliver_rcu+0x22e/0x440 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x341/0x5f0 net/ipv4/ip_input.c:233 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 __netif_receive_skb_one_core net/core/dev.c:5661 [inline] __netif_receive_skb+0x2bf/0x650 net/core/dev.c:5775 process_backlog+0x662/0x15b0 net/core/dev.c:6108 __napi_poll+0xcb/0x490 net/core/dev.c:6772 napi_poll net/core/dev.c:6841 [inline] net_rx_action+0x89b/0x1240 net/core/dev.c:6963 handle_softirqs+0x2c4/0x970 kernel/softirq.c:554 do_softirq+0x11b/0x1e0 kernel/softirq.c:455 </IRQ> <TASK> __local_bh_enable_ip+0x1bb/0x200 kernel/softirq.c:382 local_bh_enable include/linux/bottom_half.h:33 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:908 [inline] __dev_queue_xmit+0x1763/0x3e90 net/core/dev.c:4450 dev_queue_xmit include/linux/netdevice.h:3105 [inline] neigh_hh_output include/net/neighbour.h:526 [inline] neigh_output include/net/neighbour.h:540 [inline] ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:235 ip_local_out net/ipv4/ip_output.c:129 [inline] __ip_queue_xmit+0x118c/0x1b80 net/ipv4/ip_output.c:535 __tcp_transmit_skb+0x2544/0x3b30 net/ipv4/tcp_output.c:1466 tcp_rcv_synsent_state_process net/ipv4/tcp_input.c:6542 [inline] tcp_rcv_state_process+0x2c32/0x4570 net/ipv4/tcp_input.c:6729 tcp_v4_do_rcv+0x77d/0xc70 net/ipv4/tcp_ipv4.c:1934 sk_backlog_rcv include/net/sock.h:1111 [inline] __release_sock+0x214/0x350 net/core/sock.c:3004 release_sock+0x61/0x1f0 net/core/sock.c:3558 mptcp_sendmsg_fastopen+0x1ad/0x530 net/mptcp/protocol.c:1733 mptcp_sendmsg+0x1884/0x1b10 net/mptcp/protocol.c:1812 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597 ___sys_sendmsg net/socket.c:2651 [inline] __sys_sendmmsg+0x3b2/0x740 net/socket.c:2737 __do_sys_sendmmsg net/socket.c:2766 [inline] __se_sys_sendmmsg net/socket.c:2763 [inline] __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2763 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f04fb13a6b9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 01 1a 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd651f42d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f04fb13a6b9 RDX: 0000000000000001 RSI: 0000000020000d00 RDI: 0000000000000004 RBP: 00007ffd651f4310 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000020000080 R11: 0000000000000246 R12: 00000000000f4240 R13: 00007f04fb187449 R14: 00007ffd651f42f4 R15: 00007ffd651f4300 </TASK> As noted by Cong Wang, the splat is false positive, but the code path leading to the report is an unexpected one: a client is attempting an MPC handshake towards the in-kernel listener created by the in-kernel PM for a port based signal endpoint. Such connection will be never accepted; many of them can make the listener queue full and preventing the creation of MPJ subflow via such listener - its intended role. Explicitly detect this scenario at initial-syn time and drop the incoming MPC request. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Cc: stable(a)vger.kernel.org Reported-by: syzbot+f4aacdfef2c6a6529c3e(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=f4aacdfef2c6a6529c3e Cc: Cong Wang <cong.wang(a)bytedance.com> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://patch.msgid.link/20241014-net-mptcp-mpc-port-endp-v2-1-7faea8e6b6ae… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index ad88bd3c58df..19eb9292bd60 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -17,6 +17,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK), SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP), SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED), + SNMP_MIB_ITEM("MPCapableEndpAttempt", MPTCP_MIB_MPCAPABLEENDPATTEMPT), SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT), SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 3206cdda8bb1..128282982843 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -12,6 +12,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */ MPTCP_MIB_MPCAPABLEACTIVEDROP, /* Client-side fallback due to a MPC drop */ MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */ + MPTCP_MIB_MPCAPABLEENDPATTEMPT, /* Prohibited MPC to port-based endp */ MPTCP_MIB_TOKENFALLBACKINIT, /* Could not init/allocate token */ MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index f6f0a38a0750..1a78998fe1f4 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1121,6 +1121,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, */ inet_sk_state_store(newsk, TCP_LISTEN); lock_sock(ssk); + WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true); err = __inet_listen_sk(ssk, backlog); if (!err) mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 74417aae08d0..568a72702b08 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -535,6 +535,7 @@ struct mptcp_subflow_context { __unused : 8; bool data_avail; bool scheduled; + bool pm_listener; /* a listener managed by the kernel PM? */ u32 remote_nonce; u64 thmac; u32 local_nonce; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 25dde81bcb75..6170f2fff71e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -132,6 +132,13 @@ static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason) } } +static int subflow_reset_req_endp(struct request_sock *req, struct sk_buff *skb) +{ + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEENDPATTEMPT); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); + return -EPERM; +} + /* Init mptcp request socket. * * Returns an error code if a JOIN has failed and a TCP reset @@ -165,6 +172,8 @@ static int subflow_check_req(struct request_sock *req, if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); + if (unlikely(listener->pm_listener)) + return subflow_reset_req_endp(req, skb); if (opt_mp_join) return 0; } else if (opt_mp_join) { @@ -172,6 +181,8 @@ static int subflow_check_req(struct request_sock *req, if (mp_opt.backup) SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); + } else if (unlikely(listener->pm_listener)) { + return subflow_reset_req_endp(req, skb); } if (opt_mp_capable && listener->request_mptcp) {

6 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] arm64: probes: Fix uprobes for big-endian kernels" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101825-oaf-glaucoma-1d13@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 Mon Sep 17 00:00:00 2001 From: Mark Rutland <mark.rutland(a)arm.com> Date: Tue, 8 Oct 2024 16:58:48 +0100 Subject: [PATCH] arm64: probes: Fix uprobes for big-endian kernels The arm64 uprobes code is broken for big-endian kernels as it doesn't convert the in-memory instruction encoding (which is always little-endian) into the kernel's native endianness before analyzing and simulating instructions. This may result in a few distinct problems: * The kernel may may erroneously reject probing an instruction which can safely be probed. * The kernel may erroneously erroneously permit stepping an instruction out-of-line when that instruction cannot be stepped out-of-line safely. * The kernel may erroneously simulate instruction incorrectly dur to interpretting the byte-swapped encoding. The endianness mismatch isn't caught by the compiler or sparse because: * The arch_uprobe::{insn,ixol} fields are encoded as arrays of u8, so the compiler and sparse have no idea these contain a little-endian 32-bit value. The core uprobes code populates these with a memcpy() which similarly does not handle endianness. * While the uprobe_opcode_t type is an alias for __le32, both arch_uprobe_analyze_insn() and arch_uprobe_skip_sstep() cast from u8[] to the similarly-named probe_opcode_t, which is an alias for u32. Hence there is no endianness conversion warning. Fix this by changing the arch_uprobe::{insn,ixol} fields to __le32 and adding the appropriate __le32_to_cpu() conversions prior to consuming the instruction encoding. The core uprobes copies these fields as opaque ranges of bytes, and so is unaffected by this change. At the same time, remove MAX_UINSN_BYTES and consistently use AARCH64_INSN_SIZE for clarity. Tested with the following: | #include <stdio.h> | #include <stdbool.h> | | #define noinline __attribute__((noinline)) | | static noinline void *adrp_self(void) | { | void *addr; | | asm volatile( | " adrp %x0, adrp_self\n" | " add %x0, %x0, :lo12:adrp_self\n" | : "=r" (addr)); | } | | | int main(int argc, char *argv) | { | void *ptr = adrp_self(); | bool equal = (ptr == adrp_self); | | printf("adrp_self => %p\n" | "adrp_self() => %p\n" | "%s\n", | adrp_self, ptr, equal ? "EQUAL" : "NOT EQUAL"); | | return 0; | } .... where the adrp_self() function was compiled to: | 00000000004007e0 <adrp_self>: | 4007e0: 90000000 adrp x0, 400000 <__ehdr_start> | 4007e4: 911f8000 add x0, x0, #0x7e0 | 4007e8: d65f03c0 ret Before this patch, the ADRP is not recognized, and is assumed to be steppable, resulting in corruption of the result: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0xffffffffff7e0 | NOT EQUAL After this patch, the ADRP is correctly recognized and simulated: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL Fixes: 9842ceae9fa8 ("arm64: Add uprobe support") Cc: stable(a)vger.kernel.org Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will(a)kernel.org> Link: https://lore.kernel.org/r/20241008155851.801546-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will(a)kernel.org> diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 2b09495499c6..014b02897f8e 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -10,11 +10,9 @@ #include <asm/insn.h> #include <asm/probes.h> -#define MAX_UINSN_BYTES AARCH64_INSN_SIZE - #define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE -#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES +#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE typedef __le32 uprobe_opcode_t; @@ -23,8 +21,8 @@ struct arch_uprobe_task { struct arch_uprobe { union { - u8 insn[MAX_UINSN_BYTES]; - u8 ixol[MAX_UINSN_BYTES]; + __le32 insn; + __le32 ixol; }; struct arch_probe_insn api; bool simulate; diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index d49aef2657cd..a2f137a595fc 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); switch (arm_probe_decode_insn(insn, &auprobe->api)) { case INSN_REJECTED: @@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (!auprobe->simulate) return false; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); addr = instruction_pointer(regs); if (auprobe->api.handler)

6 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] arm64: probes: Fix uprobes for big-endian kernels" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101822-deplored-dictator-689d@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 Mon Sep 17 00:00:00 2001 From: Mark Rutland <mark.rutland(a)arm.com> Date: Tue, 8 Oct 2024 16:58:48 +0100 Subject: [PATCH] arm64: probes: Fix uprobes for big-endian kernels The arm64 uprobes code is broken for big-endian kernels as it doesn't convert the in-memory instruction encoding (which is always little-endian) into the kernel's native endianness before analyzing and simulating instructions. This may result in a few distinct problems: * The kernel may may erroneously reject probing an instruction which can safely be probed. * The kernel may erroneously erroneously permit stepping an instruction out-of-line when that instruction cannot be stepped out-of-line safely. * The kernel may erroneously simulate instruction incorrectly dur to interpretting the byte-swapped encoding. The endianness mismatch isn't caught by the compiler or sparse because: * The arch_uprobe::{insn,ixol} fields are encoded as arrays of u8, so the compiler and sparse have no idea these contain a little-endian 32-bit value. The core uprobes code populates these with a memcpy() which similarly does not handle endianness. * While the uprobe_opcode_t type is an alias for __le32, both arch_uprobe_analyze_insn() and arch_uprobe_skip_sstep() cast from u8[] to the similarly-named probe_opcode_t, which is an alias for u32. Hence there is no endianness conversion warning. Fix this by changing the arch_uprobe::{insn,ixol} fields to __le32 and adding the appropriate __le32_to_cpu() conversions prior to consuming the instruction encoding. The core uprobes copies these fields as opaque ranges of bytes, and so is unaffected by this change. At the same time, remove MAX_UINSN_BYTES and consistently use AARCH64_INSN_SIZE for clarity. Tested with the following: | #include <stdio.h> | #include <stdbool.h> | | #define noinline __attribute__((noinline)) | | static noinline void *adrp_self(void) | { | void *addr; | | asm volatile( | " adrp %x0, adrp_self\n" | " add %x0, %x0, :lo12:adrp_self\n" | : "=r" (addr)); | } | | | int main(int argc, char *argv) | { | void *ptr = adrp_self(); | bool equal = (ptr == adrp_self); | | printf("adrp_self => %p\n" | "adrp_self() => %p\n" | "%s\n", | adrp_self, ptr, equal ? "EQUAL" : "NOT EQUAL"); | | return 0; | } .... where the adrp_self() function was compiled to: | 00000000004007e0 <adrp_self>: | 4007e0: 90000000 adrp x0, 400000 <__ehdr_start> | 4007e4: 911f8000 add x0, x0, #0x7e0 | 4007e8: d65f03c0 ret Before this patch, the ADRP is not recognized, and is assumed to be steppable, resulting in corruption of the result: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0xffffffffff7e0 | NOT EQUAL After this patch, the ADRP is correctly recognized and simulated: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL Fixes: 9842ceae9fa8 ("arm64: Add uprobe support") Cc: stable(a)vger.kernel.org Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will(a)kernel.org> Link: https://lore.kernel.org/r/20241008155851.801546-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will(a)kernel.org> diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 2b09495499c6..014b02897f8e 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -10,11 +10,9 @@ #include <asm/insn.h> #include <asm/probes.h> -#define MAX_UINSN_BYTES AARCH64_INSN_SIZE - #define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE -#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES +#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE typedef __le32 uprobe_opcode_t; @@ -23,8 +21,8 @@ struct arch_uprobe_task { struct arch_uprobe { union { - u8 insn[MAX_UINSN_BYTES]; - u8 ixol[MAX_UINSN_BYTES]; + __le32 insn; + __le32 ixol; }; struct arch_probe_insn api; bool simulate; diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index d49aef2657cd..a2f137a595fc 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); switch (arm_probe_decode_insn(insn, &auprobe->api)) { case INSN_REJECTED: @@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (!auprobe->simulate) return false; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); addr = instruction_pointer(regs); if (auprobe->api.handler)

6 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] arm64: probes: Fix uprobes for big-endian kernels" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101820-delirious-wrongful-e7f1@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 Mon Sep 17 00:00:00 2001 From: Mark Rutland <mark.rutland(a)arm.com> Date: Tue, 8 Oct 2024 16:58:48 +0100 Subject: [PATCH] arm64: probes: Fix uprobes for big-endian kernels The arm64 uprobes code is broken for big-endian kernels as it doesn't convert the in-memory instruction encoding (which is always little-endian) into the kernel's native endianness before analyzing and simulating instructions. This may result in a few distinct problems: * The kernel may may erroneously reject probing an instruction which can safely be probed. * The kernel may erroneously erroneously permit stepping an instruction out-of-line when that instruction cannot be stepped out-of-line safely. * The kernel may erroneously simulate instruction incorrectly dur to interpretting the byte-swapped encoding. The endianness mismatch isn't caught by the compiler or sparse because: * The arch_uprobe::{insn,ixol} fields are encoded as arrays of u8, so the compiler and sparse have no idea these contain a little-endian 32-bit value. The core uprobes code populates these with a memcpy() which similarly does not handle endianness. * While the uprobe_opcode_t type is an alias for __le32, both arch_uprobe_analyze_insn() and arch_uprobe_skip_sstep() cast from u8[] to the similarly-named probe_opcode_t, which is an alias for u32. Hence there is no endianness conversion warning. Fix this by changing the arch_uprobe::{insn,ixol} fields to __le32 and adding the appropriate __le32_to_cpu() conversions prior to consuming the instruction encoding. The core uprobes copies these fields as opaque ranges of bytes, and so is unaffected by this change. At the same time, remove MAX_UINSN_BYTES and consistently use AARCH64_INSN_SIZE for clarity. Tested with the following: | #include <stdio.h> | #include <stdbool.h> | | #define noinline __attribute__((noinline)) | | static noinline void *adrp_self(void) | { | void *addr; | | asm volatile( | " adrp %x0, adrp_self\n" | " add %x0, %x0, :lo12:adrp_self\n" | : "=r" (addr)); | } | | | int main(int argc, char *argv) | { | void *ptr = adrp_self(); | bool equal = (ptr == adrp_self); | | printf("adrp_self => %p\n" | "adrp_self() => %p\n" | "%s\n", | adrp_self, ptr, equal ? "EQUAL" : "NOT EQUAL"); | | return 0; | } .... where the adrp_self() function was compiled to: | 00000000004007e0 <adrp_self>: | 4007e0: 90000000 adrp x0, 400000 <__ehdr_start> | 4007e4: 911f8000 add x0, x0, #0x7e0 | 4007e8: d65f03c0 ret Before this patch, the ADRP is not recognized, and is assumed to be steppable, resulting in corruption of the result: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0xffffffffff7e0 | NOT EQUAL After this patch, the ADRP is correctly recognized and simulated: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL Fixes: 9842ceae9fa8 ("arm64: Add uprobe support") Cc: stable(a)vger.kernel.org Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will(a)kernel.org> Link: https://lore.kernel.org/r/20241008155851.801546-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will(a)kernel.org> diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 2b09495499c6..014b02897f8e 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -10,11 +10,9 @@ #include <asm/insn.h> #include <asm/probes.h> -#define MAX_UINSN_BYTES AARCH64_INSN_SIZE - #define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE -#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES +#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE typedef __le32 uprobe_opcode_t; @@ -23,8 +21,8 @@ struct arch_uprobe_task { struct arch_uprobe { union { - u8 insn[MAX_UINSN_BYTES]; - u8 ixol[MAX_UINSN_BYTES]; + __le32 insn; + __le32 ixol; }; struct arch_probe_insn api; bool simulate; diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index d49aef2657cd..a2f137a595fc 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); switch (arm_probe_decode_insn(insn, &auprobe->api)) { case INSN_REJECTED: @@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (!auprobe->simulate) return false; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); addr = instruction_pointer(regs); if (auprobe->api.handler)

6 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] arm64: probes: Fix uprobes for big-endian kernels" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101818-tying-implement-f714@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 Mon Sep 17 00:00:00 2001 From: Mark Rutland <mark.rutland(a)arm.com> Date: Tue, 8 Oct 2024 16:58:48 +0100 Subject: [PATCH] arm64: probes: Fix uprobes for big-endian kernels The arm64 uprobes code is broken for big-endian kernels as it doesn't convert the in-memory instruction encoding (which is always little-endian) into the kernel's native endianness before analyzing and simulating instructions. This may result in a few distinct problems: * The kernel may may erroneously reject probing an instruction which can safely be probed. * The kernel may erroneously erroneously permit stepping an instruction out-of-line when that instruction cannot be stepped out-of-line safely. * The kernel may erroneously simulate instruction incorrectly dur to interpretting the byte-swapped encoding. The endianness mismatch isn't caught by the compiler or sparse because: * The arch_uprobe::{insn,ixol} fields are encoded as arrays of u8, so the compiler and sparse have no idea these contain a little-endian 32-bit value. The core uprobes code populates these with a memcpy() which similarly does not handle endianness. * While the uprobe_opcode_t type is an alias for __le32, both arch_uprobe_analyze_insn() and arch_uprobe_skip_sstep() cast from u8[] to the similarly-named probe_opcode_t, which is an alias for u32. Hence there is no endianness conversion warning. Fix this by changing the arch_uprobe::{insn,ixol} fields to __le32 and adding the appropriate __le32_to_cpu() conversions prior to consuming the instruction encoding. The core uprobes copies these fields as opaque ranges of bytes, and so is unaffected by this change. At the same time, remove MAX_UINSN_BYTES and consistently use AARCH64_INSN_SIZE for clarity. Tested with the following: | #include <stdio.h> | #include <stdbool.h> | | #define noinline __attribute__((noinline)) | | static noinline void *adrp_self(void) | { | void *addr; | | asm volatile( | " adrp %x0, adrp_self\n" | " add %x0, %x0, :lo12:adrp_self\n" | : "=r" (addr)); | } | | | int main(int argc, char *argv) | { | void *ptr = adrp_self(); | bool equal = (ptr == adrp_self); | | printf("adrp_self => %p\n" | "adrp_self() => %p\n" | "%s\n", | adrp_self, ptr, equal ? "EQUAL" : "NOT EQUAL"); | | return 0; | } .... where the adrp_self() function was compiled to: | 00000000004007e0 <adrp_self>: | 4007e0: 90000000 adrp x0, 400000 <__ehdr_start> | 4007e4: 911f8000 add x0, x0, #0x7e0 | 4007e8: d65f03c0 ret Before this patch, the ADRP is not recognized, and is assumed to be steppable, resulting in corruption of the result: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0xffffffffff7e0 | NOT EQUAL After this patch, the ADRP is correctly recognized and simulated: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL Fixes: 9842ceae9fa8 ("arm64: Add uprobe support") Cc: stable(a)vger.kernel.org Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will(a)kernel.org> Link: https://lore.kernel.org/r/20241008155851.801546-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will(a)kernel.org> diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 2b09495499c6..014b02897f8e 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -10,11 +10,9 @@ #include <asm/insn.h> #include <asm/probes.h> -#define MAX_UINSN_BYTES AARCH64_INSN_SIZE - #define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE -#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES +#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE typedef __le32 uprobe_opcode_t; @@ -23,8 +21,8 @@ struct arch_uprobe_task { struct arch_uprobe { union { - u8 insn[MAX_UINSN_BYTES]; - u8 ixol[MAX_UINSN_BYTES]; + __le32 insn; + __le32 ixol; }; struct arch_probe_insn api; bool simulate; diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index d49aef2657cd..a2f137a595fc 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); switch (arm_probe_decode_insn(insn, &auprobe->api)) { case INSN_REJECTED: @@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (!auprobe->simulate) return false; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); addr = instruction_pointer(regs); if (auprobe->api.handler)

6 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] arm64: probes: Fix uprobes for big-endian kernels" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101815-chapped-decibel-91ed@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 13f8f1e05f1dc36dbba6cba0ae03354c0dafcde7 Mon Sep 17 00:00:00 2001 From: Mark Rutland <mark.rutland(a)arm.com> Date: Tue, 8 Oct 2024 16:58:48 +0100 Subject: [PATCH] arm64: probes: Fix uprobes for big-endian kernels The arm64 uprobes code is broken for big-endian kernels as it doesn't convert the in-memory instruction encoding (which is always little-endian) into the kernel's native endianness before analyzing and simulating instructions. This may result in a few distinct problems: * The kernel may may erroneously reject probing an instruction which can safely be probed. * The kernel may erroneously erroneously permit stepping an instruction out-of-line when that instruction cannot be stepped out-of-line safely. * The kernel may erroneously simulate instruction incorrectly dur to interpretting the byte-swapped encoding. The endianness mismatch isn't caught by the compiler or sparse because: * The arch_uprobe::{insn,ixol} fields are encoded as arrays of u8, so the compiler and sparse have no idea these contain a little-endian 32-bit value. The core uprobes code populates these with a memcpy() which similarly does not handle endianness. * While the uprobe_opcode_t type is an alias for __le32, both arch_uprobe_analyze_insn() and arch_uprobe_skip_sstep() cast from u8[] to the similarly-named probe_opcode_t, which is an alias for u32. Hence there is no endianness conversion warning. Fix this by changing the arch_uprobe::{insn,ixol} fields to __le32 and adding the appropriate __le32_to_cpu() conversions prior to consuming the instruction encoding. The core uprobes copies these fields as opaque ranges of bytes, and so is unaffected by this change. At the same time, remove MAX_UINSN_BYTES and consistently use AARCH64_INSN_SIZE for clarity. Tested with the following: | #include <stdio.h> | #include <stdbool.h> | | #define noinline __attribute__((noinline)) | | static noinline void *adrp_self(void) | { | void *addr; | | asm volatile( | " adrp %x0, adrp_self\n" | " add %x0, %x0, :lo12:adrp_self\n" | : "=r" (addr)); | } | | | int main(int argc, char *argv) | { | void *ptr = adrp_self(); | bool equal = (ptr == adrp_self); | | printf("adrp_self => %p\n" | "adrp_self() => %p\n" | "%s\n", | adrp_self, ptr, equal ? "EQUAL" : "NOT EQUAL"); | | return 0; | } .... where the adrp_self() function was compiled to: | 00000000004007e0 <adrp_self>: | 4007e0: 90000000 adrp x0, 400000 <__ehdr_start> | 4007e4: 911f8000 add x0, x0, #0x7e0 | 4007e8: d65f03c0 ret Before this patch, the ADRP is not recognized, and is assumed to be steppable, resulting in corruption of the result: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0xffffffffff7e0 | NOT EQUAL After this patch, the ADRP is correctly recognized and simulated: | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL | # | # echo 'p /root/adrp-self:0x007e0' > /sys/kernel/tracing/uprobe_events | # echo 1 > /sys/kernel/tracing/events/uprobes/enable | # ./adrp-self | adrp_self => 0x4007e0 | adrp_self() => 0x4007e0 | EQUAL Fixes: 9842ceae9fa8 ("arm64: Add uprobe support") Cc: stable(a)vger.kernel.org Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will(a)kernel.org> Link: https://lore.kernel.org/r/20241008155851.801546-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will(a)kernel.org> diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 2b09495499c6..014b02897f8e 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -10,11 +10,9 @@ #include <asm/insn.h> #include <asm/probes.h> -#define MAX_UINSN_BYTES AARCH64_INSN_SIZE - #define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE -#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES +#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE typedef __le32 uprobe_opcode_t; @@ -23,8 +21,8 @@ struct arch_uprobe_task { struct arch_uprobe { union { - u8 insn[MAX_UINSN_BYTES]; - u8 ixol[MAX_UINSN_BYTES]; + __le32 insn; + __le32 ixol; }; struct arch_probe_insn api; bool simulate; diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index d49aef2657cd..a2f137a595fc 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); switch (arm_probe_decode_insn(insn, &auprobe->api)) { case INSN_REJECTED: @@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (!auprobe->simulate) return false; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); addr = instruction_pointer(regs); if (auprobe->api.handler)

6 months, 1 week

1
0
0 0

[PATCH 6.1 00/19] Fix NULL pointer dereference for corrupted UDF filesystems

by Thadeu Lima de Souza Cascardo

UDF filesystems which have relocated blocks past the end of the device may lead to a dcache without an inode that would lead to a NULL pointer dereference, like this: [ 65.938826] repro: attempt to access beyond end of device [ 65.938826] loop0: rw=2049, sector=2052, nr_sectors = 2 limit=2048 [ 65.939476] Buffer I/O error on dev loop0, logical block 1026, lost async page write [ 65.940426] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 65.940894] #PF: supervisor read access in kernel mode [ 65.941280] #PF: error_code(0x0000) - not-present page [ 65.941552] PGD 8691067 P4D 8691067 PUD 84cb067 PMD 0 [ 65.941830] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 65.942069] CPU: 0 PID: 460 Comm: repro Not tainted 6.1.113-rc2-00792-g7e3aa874350e #618 [ 65.942490] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 [ 65.942906] RIP: 0010:path_openat+0x3ae/0x5db [ 65.943136] Code: 89 c0 b8 eb ff ff ff 45 84 c0 0f 85 50 ff ff ff 83 3d da 24 3d 01 00 48 8b 4a 70 44 8b ad e4 00 00 00 8b 95 e0 00 00 00 75 0c <8b> 01 66 25 00 f0 66 3d 00 10 74 95 83 3d b0 24 3d 01 00 75 0c 8b [ 65.944078] RSP: 0018:ffffc900001c7d50 EFLAGS: 00010246 [ 65.944387] RAX: 00000000ffffffeb RBX: ffffc900001c7edc RCX: 0000000000000000 [ 65.945072] RDX: 0000000000000000 RSI: 0000000000000132 RDI: 0000000000000000 [ 65.945948] RBP: ffffc900001c7dc0 R08: 000000000622c100 R09: 0000000000000000 [ 65.946412] R10: ffffc900001c7b30 R11: 0000000000000002 R12: ffff888009533a00 [ 65.946833] R13: 00000000000041ed R14: 0000000000008241 R15: ffffffff82450ca0 [ 65.947257] FS: 00007c48054c4740(0000) GS:ffff88803ea00000(0000) knlGS:0000000000000000 [ 65.947702] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 65.947997] CR2: 0000000000000000 CR3: 0000000008c40000 CR4: 0000000000750ef0 [ 65.948361] PKRU: 55555554 [ 65.948503] Call Trace: [ 65.948631] <TASK> [ 65.948799] ? __die_body+0x1a/0x5d [ 65.949079] ? page_fault_oops+0x2ca/0x358 [ 65.949370] ? exc_page_fault+0x15f/0x18b [ 65.949654] ? asm_exc_page_fault+0x26/0x30 [ 65.949953] ? path_openat+0x3ae/0x5db [ 65.950228] do_filp_open+0x52/0xb3 [ 65.950480] ? lock_release+0x17a/0x25f [ 65.950759] ? _raw_spin_unlock+0x1e/0x32 [ 65.951044] do_sys_openat2+0x6d/0xe0 [ 65.951305] do_sys_open+0x39/0x57 [ 65.951479] do_syscall_64+0x71/0x88 [ 65.951660] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 65.951913] RIP: 0033:0x7c48055ecc7d [ 65.952100] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 81 0d 00 f7 d8 64 89 01 48 [ 65.953002] RSP: 002b:00007fff38c48918 EFLAGS: 00000202 ORIG_RAX: 0000000000000055 [ 65.953378] RAX: ffffffffffffffda RBX: 00007fff38c48a48 RCX: 00007c48055ecc7d [ 65.953733] RDX: 00007c48055ecc7d RSI: 0000000000000000 RDI: 0000000020000d00 [ 65.954128] RBP: 00007fff38c48930 R08: 0000000000000000 R09: 0000000000000000 [ 65.954492] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000 [ 65.955122] R13: 00007fff38c48a58 R14: 00005661cd1ccd10 R15: 00007c480572d000 [ 65.955666] </TASK> [ 65.955843] Modules linked in: [ 65.956054] CR2: 0000000000000000 [ 65.956285] ---[ end trace 0000000000000000 ]--- [ 65.956610] RIP: 0010:path_openat+0x3ae/0x5db [ 65.956886] Code: 89 c0 b8 eb ff ff ff 45 84 c0 0f 85 50 ff ff ff 83 3d da 24 3d 01 00 48 8b 4a 70 44 8b ad e4 00 00 00 8b 95 e0 00 00 00 75 0c <8b> 01 66 25 00 f0 66 3d 00 10 74 95 83 3d b0 24 3d 01 00 75 0c 8b [ 65.957973] RSP: 0018:ffffc900001c7d50 EFLAGS: 00010246 [ 65.958255] RAX: 00000000ffffffeb RBX: ffffc900001c7edc RCX: 0000000000000000 [ 65.958636] RDX: 0000000000000000 RSI: 0000000000000132 RDI: 0000000000000000 [ 65.959111] RBP: ffffc900001c7dc0 R08: 000000000622c100 R09: 0000000000000000 [ 65.959601] R10: ffffc900001c7b30 R11: 0000000000000002 R12: ffff888009533a00 [ 65.960095] R13: 00000000000041ed R14: 0000000000008241 R15: ffffffff82450ca0 [ 65.960539] FS: 00007c48054c4740(0000) GS:ffff88803ea00000(0000) knlGS:0000000000000000 [ 65.960971] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 65.961283] CR2: 0000000000000000 CR3: 0000000008c40000 CR4: 0000000000750ef0 [ 65.961664] PKRU: 55555554 [ 65.961820] Kernel panic - not syncing: Fatal exception Jan Kara (19): udf: New directory iteration code udf: Convert udf_expand_dir_adinicb() to new directory iteration udf: Move udf_expand_dir_adinicb() to its callsite udf: Implement searching for directory entry using new iteration code udf: Provide function to mark entry as deleted using new directory iteration code udf: Convert udf_rename() to new directory iteration code udf: Convert udf_readdir() to new directory iteration udf: Convert udf_lookup() to use new directory iteration code udf: Convert udf_get_parent() to new directory iteration code udf: Convert empty_dir() to new directory iteration code udf: Convert udf_rmdir() to new directory iteration code udf: Convert udf_unlink() to new directory iteration code udf: Implement adding of dir entries using new iteration code udf: Convert udf_add_nondir() to new directory iteration udf: Convert udf_mkdir() to new directory iteration code udf: Convert udf_link() to new directory iteration code udf: Remove old directory iteration code udf: Handle error when expanding directory udf: Don't return bh from udf_expand_dir_adinicb() fs/udf/dir.c | 148 ++----- fs/udf/directory.c | 564 ++++++++++++++++++------ fs/udf/inode.c | 90 ---- fs/udf/namei.c | 1049 +++++++++++++++----------------------------- fs/udf/udfdecl.h | 45 +- 5 files changed, 823 insertions(+), 1073 deletions(-) -- 2.34.1

6 months, 1 week

2
20
0 0

[PATCH v2 01/13] media: v4l2-ctrls-api: fix error handling for v4l2_g_ctrl()

by Mauro Carvalho Chehab

As detected by Coverity, the error check logic at get_ctrl() is broken: if ptr_to_user() fails to fill a control due to an error, no errors are returned and v4l2_g_ctrl() returns success on a failed operation, which may cause applications to fail. Add an error check at get_ctrl() and ensure that it will be returned to userspace without filling the control value if get_ctrl() fails. Fixes: 71c689dc2e73 ("media: v4l2-ctrls: split up into four source files") Cc: stable(a)vger.kernel.org Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org> --- drivers/media/v4l2-core/v4l2-ctrls-api.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/media/v4l2-core/v4l2-ctrls-api.c b/drivers/media/v4l2-core/v4l2-ctrls-api.c index e5a364efd5e6..a0de7eeaf085 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-api.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-api.c @@ -753,9 +753,10 @@ static int get_ctrl(struct v4l2_ctrl *ctrl, struct v4l2_ext_control *c) for (i = 0; i < master->ncontrols; i++) cur_to_new(master->cluster[i]); ret = call_op(master, g_volatile_ctrl); - new_to_user(c, ctrl); + if (!ret) + ret = new_to_user(c, ctrl); } else { - cur_to_user(c, ctrl); + ret = cur_to_user(c, ctrl); } v4l2_ctrl_unlock(master); return ret; @@ -770,7 +771,10 @@ int v4l2_g_ctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_control *control) if (!ctrl || !ctrl->is_int) return -EINVAL; ret = get_ctrl(ctrl, &c); - control->value = c.value; + + if (!ret) + control->value = c.value; + return ret; } EXPORT_SYMBOL(v4l2_g_ctrl); @@ -811,10 +815,12 @@ static int set_ctrl_lock(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, int ret; v4l2_ctrl_lock(ctrl); - user_to_new(c, ctrl); + ret = user_to_new(c, ctrl); + if (ret) + return ret; ret = set_ctrl(fh, ctrl, 0); if (!ret) - cur_to_user(c, ctrl); + ret = cur_to_user(c, ctrl); v4l2_ctrl_unlock(ctrl); return ret; } -- 2.47.0

6 months, 1 week

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024