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, 188 insertions, 0 deletions

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
new file mode 100644
index 000000000..6e172d0f6
--- /dev/null
+++ b/include/net/busy_poll.h
@@ -0,0 +1,188 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * net busy poll support
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * Author: Eliezer Tamir
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ */
+
+#ifndef _LINUX_NET_BUSY_POLL_H
+#define _LINUX_NET_BUSY_POLL_H
+
+#include <linux/netdevice.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/signal.h>
+#include <net/ip.h>
+#include <net/xdp.h>
+
+/*		0 - Reserved to indicate value not set
+ *     1..NR_CPUS - Reserved for sender_cpu
+ *  NR_CPUS+1..~0 - Region available for NAPI IDs
+ */
+#define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
+
+static inline bool napi_id_valid(unsigned int napi_id)
+{
+	return napi_id >= MIN_NAPI_ID;
+}
+
+#define BUSY_POLL_BUDGET 8
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+struct napi_struct;
+extern unsigned int sysctl_net_busy_read __read_mostly;
+extern unsigned int sysctl_net_busy_poll __read_mostly;
+
+static inline bool net_busy_loop_on(void)
+{
+	return READ_ONCE(sysctl_net_busy_poll);
+}
+
+static inline bool sk_can_busy_loop(const struct sock *sk)
+{
+	return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current);
+}
+
+bool sk_busy_loop_end(void *p, unsigned long start_time);
+
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+
+void napi_suspend_irqs(unsigned int napi_id);
+void napi_resume_irqs(unsigned int napi_id);
+
+#else /* CONFIG_NET_RX_BUSY_POLL */
+static inline unsigned long net_busy_loop_on(void)
+{
+	return 0;
+}
+
+static inline bool sk_can_busy_loop(struct sock *sk)
+{
+	return false;
+}
+
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+static inline unsigned long busy_loop_current_time(void)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	return (unsigned long)(ktime_get_ns() >> 10);
+#else
+	return 0;
+#endif
+}
+
+/* in poll/select we use the global sysctl_net_ll_poll value */
+static inline bool busy_loop_timeout(unsigned long start_time)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll);
+
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	}
+#endif
+	return true;
+}
+
+static inline bool sk_busy_loop_timeout(struct sock *sk,
+					unsigned long start_time)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec);
+
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	}
+#endif
+	return true;
+}
+
+static inline void sk_busy_loop(struct sock *sk, int nonblock)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
+
+	if (napi_id_valid(napi_id))
+		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk,
+			       READ_ONCE(sk->sk_prefer_busy_poll),
+			       READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET);
+#endif
+}
+
+/* used in the NIC receive handler to mark the skb */
+static inline void __skb_mark_napi_id(struct sk_buff *skb,
+				      const struct gro_node *gro)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* If the skb was already marked with a valid NAPI ID, avoid overwriting
+	 * it.
+	 */
+	if (!napi_id_valid(skb->napi_id))
+		skb->napi_id = gro->cached_napi_id;
+#endif
+}
+
+static inline void skb_mark_napi_id(struct sk_buff *skb,
+				    const struct napi_struct *napi)
+{
+	__skb_mark_napi_id(skb, &napi->gro);
+}
+
+/* used in the protocol handler to propagate the napi_id to the socket */
+static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id))
+		WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+#endif
+	sk_rx_queue_update(sk, skb);
+}
+
+/* Variant of sk_mark_napi_id() for passive flow setup,
+ * as sk->sk_napi_id and sk->sk_rx_queue_mapping content
+ * needs to be set.
+ */
+static inline void sk_mark_napi_id_set(struct sock *sk,
+				       const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+#endif
+	sk_rx_queue_set(sk, skb);
+}
+
+static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (!READ_ONCE(sk->sk_napi_id))
+		WRITE_ONCE(sk->sk_napi_id, napi_id);
+#endif
+}
+
+/* variant used for unconnected sockets */
+static inline void sk_mark_napi_id_once(struct sock *sk,
+					const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	__sk_mark_napi_id_once(sk, skb->napi_id);
+#endif
+}
+
+#endif /* _LINUX_NET_BUSY_POLL_H */