OpenCloudOS-Kernel/net/unix/diag.c

343 lines
7.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/sock_diag.h>
#include <linux/unix_diag.h>
#include <linux/skbuff.h>
#include <linux/module.h>
#include <linux/uidgid.h>
#include <net/netlink.h>
#include <net/af_unix.h>
#include <net/tcp_states.h>
#include <net/sock.h>
static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
{
/* might or might not have a hash table lock */
missing barriers in some of unix_sock ->addr and ->path accesses Several u->addr and u->path users are not holding any locks in common with unix_bind(). unix_state_lock() is useless for those purposes. u->addr is assign-once and *(u->addr) is fully set up by the time we set u->addr (all under unix_table_lock). u->path is also set in the same critical area, also before setting u->addr, and any unix_sock with ->path filled will have non-NULL ->addr. So setting ->addr with smp_store_release() is all we need for those "lockless" users - just have them fetch ->addr with smp_load_acquire() and don't even bother looking at ->path if they see NULL ->addr. Users of ->addr and ->path fall into several classes now: 1) ones that do smp_load_acquire(u->addr) and access *(u->addr) and u->path only if smp_load_acquire() has returned non-NULL. 2) places holding unix_table_lock. These are guaranteed that *(u->addr) is seen fully initialized. If unix_sock is in one of the "bound" chains, so's ->path. 3) unix_sock_destructor() using ->addr is safe. All places that set u->addr are guaranteed to have seen all stores *(u->addr) while holding a reference to u and unix_sock_destructor() is called when (atomic) refcount hits zero. 4) unix_release_sock() using ->path is safe. unix_bind() is serialized wrt unix_release() (normally - by struct file refcount), and for the instances that had ->path set by unix_bind() unix_release_sock() comes from unix_release(), so they are fine. Instances that had it set in unix_stream_connect() either end up attached to a socket (in unix_accept()), in which case the call chain to unix_release_sock() and serialization are the same as in the previous case, or they never get accept'ed and unix_release_sock() is called when the listener is shut down and its queue gets purged. In that case the listener's queue lock provides the barriers needed - unix_stream_connect() shoves our unix_sock into listener's queue under that lock right after having set ->path and eventual unix_release_sock() caller picks them from that queue under the same lock right before calling unix_release_sock(). 5) unix_find_other() use of ->path is pointless, but safe - it happens with successful lookup by (abstract) name, so ->path.dentry is guaranteed to be NULL there. earlier-variant-reviewed-by: "Paul E. McKenney" <paulmck@linux.ibm.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-16 04:09:35 +08:00
struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
if (!addr)
return 0;
return nla_put(nlskb, UNIX_DIAG_NAME,
addr->len - offsetof(struct sockaddr_un, sun_path),
addr->name->sun_path);
}
static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
{
struct dentry *dentry = unix_sk(sk)->path.dentry;
if (dentry) {
struct unix_diag_vfs uv = {
.udiag_vfs_ino = d_backing_inode(dentry)->i_ino,
.udiag_vfs_dev = dentry->d_sb->s_dev,
};
return nla_put(nlskb, UNIX_DIAG_VFS, sizeof(uv), &uv);
}
return 0;
}
static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
{
struct sock *peer;
int ino;
peer = unix_peer_get(sk);
if (peer) {
unix_state_lock(peer);
ino = sock_i_ino(peer);
unix_state_unlock(peer);
sock_put(peer);
return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino);
}
return 0;
}
static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
{
struct sk_buff *skb;
struct nlattr *attr;
u32 *buf;
int i;
if (sk->sk_state == TCP_LISTEN) {
spin_lock(&sk->sk_receive_queue.lock);
attr = nla_reserve(nlskb, UNIX_DIAG_ICONS,
sk->sk_receive_queue.qlen * sizeof(u32));
if (!attr)
goto errout;
buf = nla_data(attr);
i = 0;
skb_queue_walk(&sk->sk_receive_queue, skb) {
struct sock *req, *peer;
req = skb->sk;
/*
* The state lock is outer for the same sk's
* queue lock. With the other's queue locked it's
* OK to lock the state.
*/
unix_state_lock_nested(req);
peer = unix_sk(req)->peer;
buf[i++] = (peer ? sock_i_ino(peer) : 0);
unix_state_unlock(req);
}
spin_unlock(&sk->sk_receive_queue.lock);
}
return 0;
errout:
spin_unlock(&sk->sk_receive_queue.lock);
return -EMSGSIZE;
}
static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
{
struct unix_diag_rqlen rql;
if (sk->sk_state == TCP_LISTEN) {
rql.udiag_rqueue = sk->sk_receive_queue.qlen;
rql.udiag_wqueue = sk->sk_max_ack_backlog;
} else {
rql.udiag_rqueue = (u32) unix_inq_len(sk);
rql.udiag_wqueue = (u32) unix_outq_len(sk);
}
return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql);
}
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
static int sk_diag_dump_uid(struct sock *sk, struct sk_buff *nlskb,
struct user_namespace *user_ns)
{
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
uid_t uid = from_kuid_munged(user_ns, sock_i_uid(sk));
return nla_put(nlskb, UNIX_DIAG_UID, sizeof(uid_t), &uid);
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
struct user_namespace *user_ns,
u32 portid, u32 seq, u32 flags, int sk_ino)
{
struct nlmsghdr *nlh;
struct unix_diag_msg *rep;
nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
flags);
if (!nlh)
return -EMSGSIZE;
rep = nlmsg_data(nlh);
rep->udiag_family = AF_UNIX;
rep->udiag_type = sk->sk_type;
rep->udiag_state = sk->sk_state;
rep->pad = 0;
rep->udiag_ino = sk_ino;
sock_diag_save_cookie(sk, rep->udiag_cookie);
if ((req->udiag_show & UDIAG_SHOW_NAME) &&
sk_diag_dump_name(sk, skb))
goto out_nlmsg_trim;
if ((req->udiag_show & UDIAG_SHOW_VFS) &&
sk_diag_dump_vfs(sk, skb))
goto out_nlmsg_trim;
if ((req->udiag_show & UDIAG_SHOW_PEER) &&
sk_diag_dump_peer(sk, skb))
goto out_nlmsg_trim;
if ((req->udiag_show & UDIAG_SHOW_ICONS) &&
sk_diag_dump_icons(sk, skb))
goto out_nlmsg_trim;
if ((req->udiag_show & UDIAG_SHOW_RQLEN) &&
sk_diag_show_rqlen(sk, skb))
goto out_nlmsg_trim;
if ((req->udiag_show & UDIAG_SHOW_MEMINFO) &&
sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO))
goto out_nlmsg_trim;
if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
goto out_nlmsg_trim;
if ((req->udiag_show & UDIAG_SHOW_UID) &&
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
sk_diag_dump_uid(sk, skb, user_ns))
goto out_nlmsg_trim;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
out_nlmsg_trim:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
struct user_namespace *user_ns,
u32 portid, u32 seq, u32 flags)
{
int sk_ino;
unix_state_lock(sk);
sk_ino = sock_i_ino(sk);
unix_state_unlock(sk);
if (!sk_ino)
return 0;
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
return sk_diag_fill(sk, skb, req, user_ns, portid, seq, flags, sk_ino);
}
static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
int num, s_num, slot, s_slot;
struct unix_diag_req *req;
req = nlmsg_data(cb->nlh);
s_slot = cb->args[0];
num = s_num = cb->args[1];
for (slot = s_slot; slot < UNIX_HASH_SIZE; s_num = 0, slot++) {
struct sock *sk;
num = 0;
spin_lock(&net->unx.table.locks[slot]);
sk_for_each(sk, &net->unx.table.buckets[slot]) {
if (num < s_num)
goto next;
if (!(req->udiag_states & (1 << sk->sk_state)))
goto next;
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
af_unix: Replace the big lock with small locks. The hash table of AF_UNIX sockets is protected by the single lock. This patch replaces it with per-hash locks. The effect is noticeable when we handle multiple sockets simultaneously. Here is a test result on an EC2 c5.24xlarge instance. It shows latency (under 10us only) in unix_insert_unbound_socket() while 64 CPUs creating 1024 sockets for each in parallel. Without this patch: nsec : count distribution 0 : 179 | | 500 : 3021 |********* | 1000 : 6271 |******************* | 1500 : 6318 |******************* | 2000 : 5828 |***************** | 2500 : 5124 |*************** | 3000 : 4426 |************* | 3500 : 3672 |*********** | 4000 : 3138 |********* | 4500 : 2811 |******** | 5000 : 2384 |******* | 5500 : 2023 |****** | 6000 : 1954 |***** | 6500 : 1737 |***** | 7000 : 1749 |***** | 7500 : 1520 |**** | 8000 : 1469 |**** | 8500 : 1394 |**** | 9000 : 1232 |*** | 9500 : 1138 |*** | 10000 : 994 |*** | With this patch: nsec : count distribution 0 : 1634 |**** | 500 : 13170 |****************************************| 1000 : 13156 |*************************************** | 1500 : 9010 |*************************** | 2000 : 6363 |******************* | 2500 : 4443 |************* | 3000 : 3240 |********* | 3500 : 2549 |******* | 4000 : 1872 |***** | 4500 : 1504 |**** | 5000 : 1247 |*** | 5500 : 1035 |*** | 6000 : 889 |** | 6500 : 744 |** | 7000 : 634 |* | 7500 : 498 |* | 8000 : 433 |* | 8500 : 355 |* | 9000 : 336 |* | 9500 : 284 | | 10000 : 243 | | Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-11-24 10:14:30 +08:00
NLM_F_MULTI) < 0) {
spin_unlock(&net->unx.table.locks[slot]);
goto done;
af_unix: Replace the big lock with small locks. The hash table of AF_UNIX sockets is protected by the single lock. This patch replaces it with per-hash locks. The effect is noticeable when we handle multiple sockets simultaneously. Here is a test result on an EC2 c5.24xlarge instance. It shows latency (under 10us only) in unix_insert_unbound_socket() while 64 CPUs creating 1024 sockets for each in parallel. Without this patch: nsec : count distribution 0 : 179 | | 500 : 3021 |********* | 1000 : 6271 |******************* | 1500 : 6318 |******************* | 2000 : 5828 |***************** | 2500 : 5124 |*************** | 3000 : 4426 |************* | 3500 : 3672 |*********** | 4000 : 3138 |********* | 4500 : 2811 |******** | 5000 : 2384 |******* | 5500 : 2023 |****** | 6000 : 1954 |***** | 6500 : 1737 |***** | 7000 : 1749 |***** | 7500 : 1520 |**** | 8000 : 1469 |**** | 8500 : 1394 |**** | 9000 : 1232 |*** | 9500 : 1138 |*** | 10000 : 994 |*** | With this patch: nsec : count distribution 0 : 1634 |**** | 500 : 13170 |****************************************| 1000 : 13156 |*************************************** | 1500 : 9010 |*************************** | 2000 : 6363 |******************* | 2500 : 4443 |************* | 3000 : 3240 |********* | 3500 : 2549 |******* | 4000 : 1872 |***** | 4500 : 1504 |**** | 5000 : 1247 |*** | 5500 : 1035 |*** | 6000 : 889 |** | 6500 : 744 |** | 7000 : 634 |* | 7500 : 498 |* | 8000 : 433 |* | 8500 : 355 |* | 9000 : 336 |* | 9500 : 284 | | 10000 : 243 | | Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-11-24 10:14:30 +08:00
}
next:
num++;
}
spin_unlock(&net->unx.table.locks[slot]);
}
done:
cb->args[0] = slot;
cb->args[1] = num;
return skb->len;
}
static struct sock *unix_lookup_by_ino(struct net *net, unsigned int ino)
{
struct sock *sk;
af_unix: Replace the big lock with small locks. The hash table of AF_UNIX sockets is protected by the single lock. This patch replaces it with per-hash locks. The effect is noticeable when we handle multiple sockets simultaneously. Here is a test result on an EC2 c5.24xlarge instance. It shows latency (under 10us only) in unix_insert_unbound_socket() while 64 CPUs creating 1024 sockets for each in parallel. Without this patch: nsec : count distribution 0 : 179 | | 500 : 3021 |********* | 1000 : 6271 |******************* | 1500 : 6318 |******************* | 2000 : 5828 |***************** | 2500 : 5124 |*************** | 3000 : 4426 |************* | 3500 : 3672 |*********** | 4000 : 3138 |********* | 4500 : 2811 |******** | 5000 : 2384 |******* | 5500 : 2023 |****** | 6000 : 1954 |***** | 6500 : 1737 |***** | 7000 : 1749 |***** | 7500 : 1520 |**** | 8000 : 1469 |**** | 8500 : 1394 |**** | 9000 : 1232 |*** | 9500 : 1138 |*** | 10000 : 994 |*** | With this patch: nsec : count distribution 0 : 1634 |**** | 500 : 13170 |****************************************| 1000 : 13156 |*************************************** | 1500 : 9010 |*************************** | 2000 : 6363 |******************* | 2500 : 4443 |************* | 3000 : 3240 |********* | 3500 : 2549 |******* | 4000 : 1872 |***** | 4500 : 1504 |**** | 5000 : 1247 |*** | 5500 : 1035 |*** | 6000 : 889 |** | 6500 : 744 |** | 7000 : 634 |* | 7500 : 498 |* | 8000 : 433 |* | 8500 : 355 |* | 9000 : 336 |* | 9500 : 284 | | 10000 : 243 | | Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-11-24 10:14:30 +08:00
int i;
for (i = 0; i < UNIX_HASH_SIZE; i++) {
spin_lock(&net->unx.table.locks[i]);
sk_for_each(sk, &net->unx.table.buckets[i]) {
if (ino == sock_i_ino(sk)) {
sock_hold(sk);
spin_unlock(&net->unx.table.locks[i]);
return sk;
}
}
spin_unlock(&net->unx.table.locks[i]);
}
return NULL;
}
static int unix_diag_get_exact(struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
struct unix_diag_req *req)
{
struct net *net = sock_net(in_skb->sk);
unsigned int extra_len;
struct sk_buff *rep;
struct sock *sk;
int err;
err = -EINVAL;
if (req->udiag_ino == 0)
goto out_nosk;
sk = unix_lookup_by_ino(net, req->udiag_ino);
err = -ENOENT;
if (sk == NULL)
goto out_nosk;
err = sock_diag_check_cookie(sk, req->udiag_cookie);
if (err)
goto out;
extra_len = 256;
again:
err = -ENOMEM;
rep = nlmsg_new(sizeof(struct unix_diag_msg) + extra_len, GFP_KERNEL);
if (!rep)
goto out;
af_unix: Get user_ns from in_skb in unix_diag_get_exact(). Wei Chen reported a NULL deref in sk_user_ns() [0][1], and Paolo diagnosed the root cause: in unix_diag_get_exact(), the newly allocated skb does not have sk. [2] We must get the user_ns from the NETLINK_CB(in_skb).sk and pass it to sk_diag_fill(). [0]: BUG: kernel NULL pointer dereference, address: 0000000000000270 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 12bbce067 P4D 12bbce067 PUD 12bc40067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 27942 Comm: syz-executor.0 Not tainted 6.1.0-rc5-next-20221118 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_user_ns include/net/sock.h:920 [inline] RIP: 0010:sk_diag_dump_uid net/unix/diag.c:119 [inline] RIP: 0010:sk_diag_fill+0x77d/0x890 net/unix/diag.c:170 Code: 89 ef e8 66 d4 2d fd c7 44 24 40 00 00 00 00 49 8d 7c 24 18 e8 54 d7 2d fd 49 8b 5c 24 18 48 8d bb 70 02 00 00 e8 43 d7 2d fd <48> 8b 9b 70 02 00 00 48 8d 7b 10 e8 33 d7 2d fd 48 8b 5b 10 48 8d RSP: 0018:ffffc90000d67968 EFLAGS: 00010246 RAX: ffff88812badaa48 RBX: 0000000000000000 RCX: ffffffff840d481d RDX: 0000000000000465 RSI: 0000000000000000 RDI: 0000000000000270 RBP: ffffc90000d679a8 R08: 0000000000000277 R09: 0000000000000000 R10: 0001ffffffffffff R11: 0001c90000d679a8 R12: ffff88812ac03800 R13: ffff88812c87c400 R14: ffff88812ae42210 R15: ffff888103026940 FS: 00007f08b4e6f700(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000270 CR3: 000000012c58b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> unix_diag_get_exact net/unix/diag.c:285 [inline] unix_diag_handler_dump+0x3f9/0x500 net/unix/diag.c:317 __sock_diag_cmd net/core/sock_diag.c:235 [inline] sock_diag_rcv_msg+0x237/0x250 net/core/sock_diag.c:266 netlink_rcv_skb+0x13e/0x250 net/netlink/af_netlink.c:2564 sock_diag_rcv+0x24/0x40 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4697f9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f08b4e6ec48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 000000000077bf80 RCX: 00000000004697f9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 00000000004d29e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000077bf80 R13: 0000000000000000 R14: 000000000077bf80 R15: 00007ffdb36bc6c0 </TASK> Modules linked in: CR2: 0000000000000270 [1]: https://lore.kernel.org/netdev/CAO4mrfdvyjFpokhNsiwZiP-wpdSD0AStcJwfKcKQdAALQ9_2Qw@mail.gmail.com/ [2]: https://lore.kernel.org/netdev/e04315e7c90d9a75613f3993c2baf2d344eef7eb.camel@redhat.com/ Fixes: cae9910e7344 ("net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics.") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Wei Chen <harperchen1110@gmail.com> Diagnosed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-11-27 09:24:11 +08:00
err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, req->udiag_ino);
if (err < 0) {
nlmsg_free(rep);
extra_len += 256;
if (extra_len >= PAGE_SIZE)
goto out;
goto again;
}
err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
out:
if (sk)
sock_put(sk);
out_nosk:
return err;
}
static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
{
int hdrlen = sizeof(struct unix_diag_req);
if (nlmsg_len(h) < hdrlen)
return -EINVAL;
if (h->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = unix_diag_dump,
};
return netlink_dump_start(sock_net(skb->sk)->diag_nlsk, skb, h, &c);
} else
return unix_diag_get_exact(skb, h, nlmsg_data(h));
}
static const struct sock_diag_handler unix_diag_handler = {
.family = AF_UNIX,
.dump = unix_diag_handler_dump,
};
static int __init unix_diag_init(void)
{
return sock_diag_register(&unix_diag_handler);
}
static void __exit unix_diag_exit(void)
{
sock_diag_unregister(&unix_diag_handler);
}
module_init(unix_diag_init);
module_exit(unix_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */);