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, 170 insertions, 0 deletions

diff --git a/include/net/strparser.h b/include/net/strparser.h
new file mode 100644
index 000000000..0ed73e364
--- /dev/null
+++ b/include/net/strparser.h
@@ -0,0 +1,170 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Stream Parser
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ */
+
+#ifndef __NET_STRPARSER_H_
+#define __NET_STRPARSER_H_
+
+#include <linux/skbuff.h>
+#include <net/sock.h>
+
+#define STRP_STATS_ADD(stat, count) ((stat) += (count))
+#define STRP_STATS_INCR(stat) ((stat)++)
+
+struct strp_stats {
+	unsigned long long msgs;
+	unsigned long long bytes;
+	unsigned int mem_fail;
+	unsigned int need_more_hdr;
+	unsigned int msg_too_big;
+	unsigned int msg_timeouts;
+	unsigned int bad_hdr_len;
+};
+
+struct strp_aggr_stats {
+	unsigned long long msgs;
+	unsigned long long bytes;
+	unsigned int mem_fail;
+	unsigned int need_more_hdr;
+	unsigned int msg_too_big;
+	unsigned int msg_timeouts;
+	unsigned int bad_hdr_len;
+	unsigned int aborts;
+	unsigned int interrupted;
+	unsigned int unrecov_intr;
+};
+
+struct strparser;
+
+/* Callbacks are called with lock held for the attached socket */
+struct strp_callbacks {
+	int (*parse_msg)(struct strparser *strp, struct sk_buff *skb);
+	void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb);
+	int (*read_sock)(struct strparser *strp, read_descriptor_t *desc,
+			 sk_read_actor_t recv_actor);
+	int (*read_sock_done)(struct strparser *strp, int err);
+	void (*abort_parser)(struct strparser *strp, int err);
+	void (*lock)(struct strparser *strp);
+	void (*unlock)(struct strparser *strp);
+};
+
+struct strp_msg {
+	int full_len;
+	int offset;
+};
+
+struct _strp_msg {
+	/* Internal cb structure. struct strp_msg must be first for passing
+	 * to upper layer.
+	 */
+	struct strp_msg strp;
+	int accum_len;
+};
+
+struct sk_skb_cb {
+#define SK_SKB_CB_PRIV_LEN 20
+	unsigned char data[SK_SKB_CB_PRIV_LEN];
+	/* align strp on cache line boundary within skb->cb[] */
+	unsigned char pad[4];
+	struct _strp_msg strp;
+
+	/* strp users' data follows */
+	struct tls_msg {
+		u8 control;
+	} tls;
+	/* temp_reg is a temporary register used for bpf_convert_data_end_access
+	 * when dst_reg == src_reg.
+	 */
+	u64 temp_reg;
+};
+
+static inline struct strp_msg *strp_msg(struct sk_buff *skb)
+{
+	return (struct strp_msg *)((void *)skb->cb +
+		offsetof(struct sk_skb_cb, strp));
+}
+
+/* Structure for an attached lower socket */
+struct strparser {
+	struct sock *sk;
+
+	u32 stopped : 1;
+	u32 paused : 1;
+	u32 aborted : 1;
+	u32 interrupted : 1;
+	u32 unrecov_intr : 1;
+
+	struct sk_buff **skb_nextp;
+	struct sk_buff *skb_head;
+	unsigned int need_bytes;
+	struct delayed_work msg_timer_work;
+	struct work_struct work;
+	struct strp_stats stats;
+	struct strp_callbacks cb;
+};
+
+/* Must be called with lock held for attached socket */
+static inline void strp_pause(struct strparser *strp)
+{
+	strp->paused = 1;
+}
+
+/* May be called without holding lock for attached socket */
+void strp_unpause(struct strparser *strp);
+
+static inline void save_strp_stats(struct strparser *strp,
+				   struct strp_aggr_stats *agg_stats)
+{
+	/* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat +=		\
+				 strp->stats._stat)
+	SAVE_PSOCK_STATS(msgs);
+	SAVE_PSOCK_STATS(bytes);
+	SAVE_PSOCK_STATS(mem_fail);
+	SAVE_PSOCK_STATS(need_more_hdr);
+	SAVE_PSOCK_STATS(msg_too_big);
+	SAVE_PSOCK_STATS(msg_timeouts);
+	SAVE_PSOCK_STATS(bad_hdr_len);
+#undef SAVE_PSOCK_STATS
+
+	if (strp->aborted)
+		agg_stats->aborts++;
+	if (strp->interrupted)
+		agg_stats->interrupted++;
+	if (strp->unrecov_intr)
+		agg_stats->unrecov_intr++;
+}
+
+static inline void aggregate_strp_stats(struct strp_aggr_stats *stats,
+					struct strp_aggr_stats *agg_stats)
+{
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat)
+	SAVE_PSOCK_STATS(msgs);
+	SAVE_PSOCK_STATS(bytes);
+	SAVE_PSOCK_STATS(mem_fail);
+	SAVE_PSOCK_STATS(need_more_hdr);
+	SAVE_PSOCK_STATS(msg_too_big);
+	SAVE_PSOCK_STATS(msg_timeouts);
+	SAVE_PSOCK_STATS(bad_hdr_len);
+	SAVE_PSOCK_STATS(aborts);
+	SAVE_PSOCK_STATS(interrupted);
+	SAVE_PSOCK_STATS(unrecov_intr);
+#undef SAVE_PSOCK_STATS
+
+}
+
+void strp_done(struct strparser *strp);
+void strp_stop(struct strparser *strp);
+void strp_check_rcv(struct strparser *strp);
+int strp_init(struct strparser *strp, struct sock *sk,
+	      const struct strp_callbacks *cb);
+void strp_data_ready(struct strparser *strp);
+int strp_process(struct strparser *strp, struct sk_buff *orig_skb,
+		 unsigned int orig_offset, size_t orig_len,
+		 size_t max_msg_size, long timeo);
+
+#endif /* __NET_STRPARSER_H_ */