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, 229 insertions, 0 deletions

diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
new file mode 100644
index 000000000..65444ff14
--- /dev/null
+++ b/net/ipv4/tcp_bic.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Binary Increase Congestion control for TCP
+ * Home page:
+ *      http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC
+ * This is from the implementation of BICTCP in
+ * Lison-Xu, Kahaled Harfoush, and Injong Rhee.
+ *  "Binary Increase Congestion Control for Fast, Long Distance
+ *  Networks" in InfoComm 2004
+ * Available from:
+ *  http://netsrv.csc.ncsu.edu/export/bitcp.pdf
+ *
+ * Unless BIC is enabled and congestion window is large
+ * this behaves the same as the original Reno.
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <net/tcp.h>
+
+#define BICTCP_BETA_SCALE    1024	/* Scale factor beta calculation
+					 * max_cwnd = snd_cwnd * beta
+					 */
+#define BICTCP_B		4	 /*
+					  * In binary search,
+					  * go to point (max+min)/N
+					  */
+
+static int fast_convergence = 1;
+static int max_increment = 16;
+static int low_window = 14;
+static int beta = 819;		/* = 819/1024 (BICTCP_BETA_SCALE) */
+static int initial_ssthresh;
+static int smooth_part = 20;
+
+module_param(fast_convergence, int, 0644);
+MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence");
+module_param(max_increment, int, 0644);
+MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search");
+module_param(low_window, int, 0644);
+MODULE_PARM_DESC(low_window, "lower bound on congestion window (for TCP friendliness)");
+module_param(beta, int, 0644);
+MODULE_PARM_DESC(beta, "beta for multiplicative increase");
+module_param(initial_ssthresh, int, 0644);
+MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
+module_param(smooth_part, int, 0644);
+MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wmax-B to Wmax");
+
+/* BIC TCP Parameters */
+struct bictcp {
+	u32	cnt;		/* increase cwnd by 1 after ACKs */
+	u32	last_max_cwnd;	/* last maximum snd_cwnd */
+	u32	last_cwnd;	/* the last snd_cwnd */
+	u32	last_time;	/* time when updated last_cwnd */
+	u32	epoch_start;	/* beginning of an epoch */
+#define ACK_RATIO_SHIFT	4
+	u32	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
+};
+
+static inline void bictcp_reset(struct bictcp *ca)
+{
+	ca->cnt = 0;
+	ca->last_max_cwnd = 0;
+	ca->last_cwnd = 0;
+	ca->last_time = 0;
+	ca->epoch_start = 0;
+	ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
+}
+
+static void bictcp_init(struct sock *sk)
+{
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	bictcp_reset(ca);
+
+	if (initial_ssthresh)
+		WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, initial_ssthresh);
+}
+
+/*
+ * Compute congestion window to use.
+ */
+static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
+{
+	if (ca->last_cwnd == cwnd &&
+	    (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32)
+		return;
+
+	ca->last_cwnd = cwnd;
+	ca->last_time = tcp_jiffies32;
+
+	if (ca->epoch_start == 0) /* record the beginning of an epoch */
+		ca->epoch_start = tcp_jiffies32;
+
+	/* start off normal */
+	if (cwnd <= low_window) {
+		ca->cnt = cwnd;
+		return;
+	}
+
+	/* binary increase */
+	if (cwnd < ca->last_max_cwnd) {
+		__u32	dist = (ca->last_max_cwnd - cwnd)
+			/ BICTCP_B;
+
+		if (dist > max_increment)
+			/* linear increase */
+			ca->cnt = cwnd / max_increment;
+		else if (dist <= 1U)
+			/* binary search increase */
+			ca->cnt = (cwnd * smooth_part) / BICTCP_B;
+		else
+			/* binary search increase */
+			ca->cnt = cwnd / dist;
+	} else {
+		/* slow start AMD linear increase */
+		if (cwnd < ca->last_max_cwnd + BICTCP_B)
+			/* slow start */
+			ca->cnt = (cwnd * smooth_part) / BICTCP_B;
+		else if (cwnd < ca->last_max_cwnd + max_increment*(BICTCP_B-1))
+			/* slow start */
+			ca->cnt = (cwnd * (BICTCP_B-1))
+				/ (cwnd - ca->last_max_cwnd);
+		else
+			/* linear increase */
+			ca->cnt = cwnd / max_increment;
+	}
+
+	/* if in slow start or link utilization is very low */
+	if (ca->last_max_cwnd == 0) {
+		if (ca->cnt > 20) /* increase cwnd 5% per RTT */
+			ca->cnt = 20;
+	}
+
+	ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
+	if (ca->cnt == 0)			/* cannot be zero */
+		ca->cnt = 1;
+}
+
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	if (!tcp_is_cwnd_limited(sk))
+		return;
+
+	if (tcp_in_slow_start(tp)) {
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
+	bictcp_update(ca, tcp_snd_cwnd(tp));
+	tcp_cong_avoid_ai(tp, ca->cnt, acked);
+}
+
+/*
+ *	behave like Reno until low_window is reached,
+ *	then increase congestion window slowly
+ */
+static u32 bictcp_recalc_ssthresh(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	ca->epoch_start = 0;	/* end of epoch */
+
+	/* Wmax and fast convergence */
+	if (tcp_snd_cwnd(tp) < ca->last_max_cwnd && fast_convergence)
+		ca->last_max_cwnd = (tcp_snd_cwnd(tp) * (BICTCP_BETA_SCALE + beta))
+			/ (2 * BICTCP_BETA_SCALE);
+	else
+		ca->last_max_cwnd = tcp_snd_cwnd(tp);
+
+	if (tcp_snd_cwnd(tp) <= low_window)
+		return max(tcp_snd_cwnd(tp) >> 1U, 2U);
+	else
+		return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U);
+}
+
+static void bictcp_state(struct sock *sk, u8 new_state)
+{
+	if (new_state == TCP_CA_Loss)
+		bictcp_reset(inet_csk_ca(sk));
+}
+
+/* Track delayed acknowledgment ratio using sliding window
+ * ratio = (15*ratio + sample) / 16
+ */
+static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ca_state == TCP_CA_Open) {
+		struct bictcp *ca = inet_csk_ca(sk);
+
+		ca->delayed_ack += sample->pkts_acked -
+			(ca->delayed_ack >> ACK_RATIO_SHIFT);
+	}
+}
+
+static struct tcp_congestion_ops bictcp __read_mostly = {
+	.init		= bictcp_init,
+	.ssthresh	= bictcp_recalc_ssthresh,
+	.cong_avoid	= bictcp_cong_avoid,
+	.set_state	= bictcp_state,
+	.undo_cwnd	= tcp_reno_undo_cwnd,
+	.pkts_acked     = bictcp_acked,
+	.owner		= THIS_MODULE,
+	.name		= "bic",
+};
+
+static int __init bictcp_register(void)
+{
+	BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE);
+	return tcp_register_congestion_control(&bictcp);
+}
+
+static void __exit bictcp_unregister(void)
+{
+	tcp_unregister_congestion_control(&bictcp);
+}
+
+module_init(bictcp_register);
+module_exit(bictcp_unregister);
+
+MODULE_AUTHOR("Stephen Hemminger");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("BIC TCP");