x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 179 insertions, 0 deletions

diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c
new file mode 100644
index 000000000..520b666fd
--- /dev/null
+++ b/net/smc/smc_inet.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Definitions for the IPPROTO_SMC (socket related)
+ *
+ *  Copyright IBM Corp. 2016, 2018
+ *  Copyright (c) 2024, Alibaba Inc.
+ *
+ *  Author: D. Wythe <alibuda@linux.alibaba.com>
+ */
+
+#include <net/protocol.h>
+#include <net/sock.h>
+
+#include "smc_inet.h"
+#include "smc.h"
+#include "smc_close.h"
+
+static int smc_inet_init_sock(struct sock *sk);
+static void smc_inet_destroy_sock(struct sock *sk);
+
+static struct proto smc_inet_prot = {
+	.name		= "INET_SMC",
+	.owner		= THIS_MODULE,
+	.init		= smc_inet_init_sock,
+	.destroy	= smc_inet_destroy_sock,
+	.hash		= smc_hash_sk,
+	.unhash		= smc_unhash_sk,
+	.release_cb	= smc_release_cb,
+	.obj_size	= sizeof(struct smc_sock),
+	.h.smc_hash	= &smc_v4_hashinfo,
+	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
+};
+
+static const struct proto_ops smc_inet_stream_ops = {
+	.family		= PF_INET,
+	.owner		= THIS_MODULE,
+	.release	= smc_release,
+	.bind		= smc_bind,
+	.connect	= smc_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= smc_accept,
+	.getname	= smc_getname,
+	.poll		= smc_poll,
+	.ioctl		= smc_ioctl,
+	.listen		= smc_listen,
+	.shutdown	= smc_shutdown,
+	.setsockopt	= smc_setsockopt,
+	.getsockopt	= smc_getsockopt,
+	.sendmsg	= smc_sendmsg,
+	.recvmsg	= smc_recvmsg,
+	.mmap		= sock_no_mmap,
+	.splice_read	= smc_splice_read,
+};
+
+static struct inet_protosw smc_inet_protosw = {
+	.type		= SOCK_STREAM,
+	.protocol	= IPPROTO_SMC,
+	.prot		= &smc_inet_prot,
+	.ops		= &smc_inet_stream_ops,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+struct smc6_sock {
+	struct smc_sock		smc;
+	struct ipv6_pinfo	inet6;
+};
+
+static struct proto smc_inet6_prot = {
+	.name		= "INET6_SMC",
+	.owner		= THIS_MODULE,
+	.init		= smc_inet_init_sock,
+	.destroy	= smc_inet_destroy_sock,
+	.hash		= smc_hash_sk,
+	.unhash		= smc_unhash_sk,
+	.release_cb	= smc_release_cb,
+	.obj_size	= sizeof(struct smc6_sock),
+	.h.smc_hash	= &smc_v6_hashinfo,
+	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
+	.ipv6_pinfo_offset	= offsetof(struct smc6_sock, inet6),
+};
+
+static const struct proto_ops smc_inet6_stream_ops = {
+	.family		= PF_INET6,
+	.owner		= THIS_MODULE,
+	.release	= smc_release,
+	.bind		= smc_bind,
+	.connect	= smc_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= smc_accept,
+	.getname	= smc_getname,
+	.poll		= smc_poll,
+	.ioctl		= smc_ioctl,
+	.listen		= smc_listen,
+	.shutdown	= smc_shutdown,
+	.setsockopt	= smc_setsockopt,
+	.getsockopt	= smc_getsockopt,
+	.sendmsg	= smc_sendmsg,
+	.recvmsg	= smc_recvmsg,
+	.mmap		= sock_no_mmap,
+	.splice_read	= smc_splice_read,
+};
+
+static struct inet_protosw smc_inet6_protosw = {
+	.type		= SOCK_STREAM,
+	.protocol	= IPPROTO_SMC,
+	.prot		= &smc_inet6_prot,
+	.ops		= &smc_inet6_stream_ops,
+};
+#endif /* CONFIG_IPV6 */
+
+static int smc_inet_init_sock(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+
+	/* init common smc sock */
+	smc_sk_init(net, sk, IPPROTO_SMC);
+	/* create clcsock */
+	return smc_create_clcsk(net, sk, sk->sk_family);
+}
+
+static void smc_inet_destroy_sock(struct sock *sk)
+{
+	/* The sock is hashed and smc_diag dumps dereference smc->clcsock
+	 * without clcsock_release_lock, while sk_common_release() calls
+	 * .destroy before .unhash. Unhash first, as __smc_release() does,
+	 * so no dump can observe the clcsock being released; the second
+	 * unhash is a no-op.
+	 */
+	sk->sk_prot->unhash(sk);
+	smc_clcsock_release(smc_sk(sk));
+}
+
+int __init smc_inet_init(void)
+{
+	int rc;
+
+	rc = proto_register(&smc_inet_prot, 1);
+	if (rc) {
+		pr_err("%s: proto_register smc_inet_prot fails with %d\n",
+		       __func__, rc);
+		return rc;
+	}
+	/* no return value */
+	inet_register_protosw(&smc_inet_protosw);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	rc = proto_register(&smc_inet6_prot, 1);
+	if (rc) {
+		pr_err("%s: proto_register smc_inet6_prot fails with %d\n",
+		       __func__, rc);
+		goto out_inet6_prot;
+	}
+	rc = inet6_register_protosw(&smc_inet6_protosw);
+	if (rc) {
+		pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n",
+		       __func__, rc);
+		goto out_inet6_protosw;
+	}
+	return rc;
+out_inet6_protosw:
+	proto_unregister(&smc_inet6_prot);
+out_inet6_prot:
+	inet_unregister_protosw(&smc_inet_protosw);
+	proto_unregister(&smc_inet_prot);
+#endif /* CONFIG_IPV6 */
+	return rc;
+}
+
+void smc_inet_exit(void)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	inet6_unregister_protosw(&smc_inet6_protosw);
+	proto_unregister(&smc_inet6_prot);
+#endif /* CONFIG_IPV6 */
+	inet_unregister_protosw(&smc_inet_protosw);
+	proto_unregister(&smc_inet_prot);
+}