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, 215 insertions, 0 deletions

diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
new file mode 100644
index 000000000..1e59072d4
--- /dev/null
+++ b/net/mptcp/sched.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2022, SUSE.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include "protocol.h"
+
+static DEFINE_SPINLOCK(mptcp_sched_list_lock);
+static LIST_HEAD(mptcp_sched_list);
+
+static int mptcp_sched_default_get_send(struct mptcp_sock *msk)
+{
+	struct sock *ssk;
+
+	ssk = mptcp_subflow_get_send(msk);
+	if (!ssk)
+		return -EINVAL;
+
+	mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+	return 0;
+}
+
+static int mptcp_sched_default_get_retrans(struct mptcp_sock *msk)
+{
+	struct sock *ssk;
+
+	ssk = mptcp_subflow_get_retrans(msk);
+	if (!ssk)
+		return -EINVAL;
+
+	mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+	return 0;
+}
+
+static struct mptcp_sched_ops mptcp_sched_default = {
+	.get_send	= mptcp_sched_default_get_send,
+	.get_retrans	= mptcp_sched_default_get_retrans,
+	.name		= "default",
+	.owner		= THIS_MODULE,
+};
+
+/* Must be called with rcu read lock held */
+struct mptcp_sched_ops *mptcp_sched_find(const char *name)
+{
+	struct mptcp_sched_ops *sched, *ret = NULL;
+
+	list_for_each_entry_rcu(sched, &mptcp_sched_list, list) {
+		if (!strcmp(sched->name, name)) {
+			ret = sched;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/* Build string with list of available scheduler values.
+ * Similar to tcp_get_available_congestion_control()
+ */
+void mptcp_get_available_schedulers(char *buf, size_t maxlen)
+{
+	struct mptcp_sched_ops *sched;
+	size_t offs = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sched, &mptcp_sched_list, list) {
+		offs += snprintf(buf + offs, maxlen - offs,
+				 "%s%s",
+				 offs == 0 ? "" : " ", sched->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
+	}
+	rcu_read_unlock();
+}
+
+int mptcp_validate_scheduler(struct mptcp_sched_ops *sched)
+{
+	if (!sched->get_send) {
+		pr_err("%s does not implement required ops\n", sched->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+{
+	int ret;
+
+	ret = mptcp_validate_scheduler(sched);
+	if (ret)
+		return ret;
+
+	spin_lock(&mptcp_sched_list_lock);
+	if (mptcp_sched_find(sched->name)) {
+		spin_unlock(&mptcp_sched_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&sched->list, &mptcp_sched_list);
+	spin_unlock(&mptcp_sched_list_lock);
+
+	pr_debug("%s registered\n", sched->name);
+	return 0;
+}
+
+void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
+{
+	if (sched == &mptcp_sched_default)
+		return;
+
+	spin_lock(&mptcp_sched_list_lock);
+	list_del_rcu(&sched->list);
+	spin_unlock(&mptcp_sched_list_lock);
+}
+
+void mptcp_sched_init(void)
+{
+	mptcp_register_scheduler(&mptcp_sched_default);
+}
+
+int mptcp_init_sched(struct mptcp_sock *msk,
+		     struct mptcp_sched_ops *sched)
+{
+	if (!sched)
+		sched = &mptcp_sched_default;
+
+	if (!bpf_try_module_get(sched, sched->owner))
+		return -EBUSY;
+
+	msk->sched = sched;
+	if (msk->sched->init)
+		msk->sched->init(msk);
+
+	pr_debug("sched=%s\n", msk->sched->name);
+
+	return 0;
+}
+
+void mptcp_release_sched(struct mptcp_sock *msk)
+{
+	struct mptcp_sched_ops *sched = msk->sched;
+
+	if (!sched)
+		return;
+
+	msk->sched = NULL;
+	if (sched->release)
+		sched->release(msk);
+
+	bpf_module_put(sched, sched->owner);
+}
+
+void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
+				 bool scheduled)
+{
+	WRITE_ONCE(subflow->scheduled, scheduled);
+}
+
+int mptcp_sched_get_send(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	msk_owned_by_me(msk);
+
+	/* the following check is moved out of mptcp_subflow_get_send */
+	if (__mptcp_check_fallback(msk)) {
+		if (msk->first &&
+		    __tcp_can_send(msk->first) &&
+		    sk_stream_memory_free(msk->first)) {
+			mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true);
+			return 0;
+		}
+		return -EINVAL;
+	}
+
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled))
+			return 0;
+	}
+
+	if (msk->sched == &mptcp_sched_default || !msk->sched)
+		return mptcp_sched_default_get_send(msk);
+	return msk->sched->get_send(msk);
+}
+
+int mptcp_sched_get_retrans(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	msk_owned_by_me(msk);
+
+	/* the following check is moved out of mptcp_subflow_get_retrans */
+	if (__mptcp_check_fallback(msk))
+		return -EINVAL;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled))
+			return 0;
+	}
+
+	if (msk->sched == &mptcp_sched_default || !msk->sched)
+		return mptcp_sched_default_get_retrans(msk);
+	if (msk->sched->get_retrans)
+		return msk->sched->get_retrans(msk);
+	return msk->sched->get_send(msk);
+}