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, 123 insertions, 0 deletions

diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c
new file mode 100644
index 000000000..81ae35b37
--- /dev/null
+++ b/net/sunrpc/timer.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/net/sunrpc/timer.c
+ *
+ * Estimate RPC request round trip time.
+ *
+ * Based on packet round-trip and variance estimator algorithms described
+ * in appendix A of "Congestion Avoidance and Control" by Van Jacobson
+ * and Michael J. Karels (ACM Computer Communication Review; Proceedings
+ * of the Sigcomm '88 Symposium in Stanford, CA, August, 1988).
+ *
+ * This RTT estimator is used only for RPC over datagram protocols.
+ *
+ * Copyright (C) 2002 Trond Myklebust <trond.myklebust@fys.uio.no>
+ */
+
+#include <asm/param.h>
+
+#include <linux/types.h>
+#include <linux/unistd.h>
+#include <linux/module.h>
+
+#include <linux/sunrpc/clnt.h>
+
+#define RPC_RTO_MAX (60*HZ)
+#define RPC_RTO_INIT (HZ/5)
+#define RPC_RTO_MIN (HZ/10)
+
+/**
+ * rpc_init_rtt - Initialize an RPC RTT estimator context
+ * @rt: context to initialize
+ * @timeo: initial timeout value, in jiffies
+ *
+ */
+void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo)
+{
+	unsigned long init = 0;
+	unsigned int i;
+
+	rt->timeo = timeo;
+
+	if (timeo > RPC_RTO_INIT)
+		init = (timeo - RPC_RTO_INIT) << 3;
+	for (i = 0; i < 5; i++) {
+		rt->srtt[i] = init;
+		rt->sdrtt[i] = RPC_RTO_INIT;
+		rt->ntimeouts[i] = 0;
+	}
+}
+EXPORT_SYMBOL_GPL(rpc_init_rtt);
+
+/**
+ * rpc_update_rtt - Update an RPC RTT estimator context
+ * @rt: context to update
+ * @timer: timer array index (request type)
+ * @m: recent actual RTT, in jiffies
+ *
+ * NB: When computing the smoothed RTT and standard deviation,
+ *     be careful not to produce negative intermediate results.
+ */
+void rpc_update_rtt(struct rpc_rtt *rt, unsigned int timer, long m)
+{
+	long *srtt, *sdrtt;
+
+	if (timer-- == 0)
+		return;
+
+	/* jiffies wrapped; ignore this one */
+	if (m < 0)
+		return;
+
+	if (m == 0)
+		m = 1L;
+
+	srtt = (long *)&rt->srtt[timer];
+	m -= *srtt >> 3;
+	*srtt += m;
+
+	if (m < 0)
+		m = -m;
+
+	sdrtt = (long *)&rt->sdrtt[timer];
+	m -= *sdrtt >> 2;
+	*sdrtt += m;
+
+	/* Set lower bound on the variance */
+	if (*sdrtt < RPC_RTO_MIN)
+		*sdrtt = RPC_RTO_MIN;
+}
+EXPORT_SYMBOL_GPL(rpc_update_rtt);
+
+/**
+ * rpc_calc_rto - Provide an estimated timeout value
+ * @rt: context to use for calculation
+ * @timer: timer array index (request type)
+ *
+ * Estimate RTO for an NFS RPC sent via an unreliable datagram.  Use
+ * the mean and mean deviation of RTT for the appropriate type of RPC
+ * for frequently issued RPCs, and a fixed default for the others.
+ *
+ * The justification for doing "other" this way is that these RPCs
+ * happen so infrequently that timer estimation would probably be
+ * stale.  Also, since many of these RPCs are non-idempotent, a
+ * conservative timeout is desired.
+ *
+ * getattr, lookup,
+ * read, write, commit     - A+4D
+ * other                   - timeo
+ */
+unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned int timer)
+{
+	unsigned long res;
+
+	if (timer-- == 0)
+		return rt->timeo;
+
+	res = ((rt->srtt[timer] + 7) >> 3) + rt->sdrtt[timer];
+	if (res > RPC_RTO_MAX)
+		res = RPC_RTO_MAX;
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(rpc_calc_rto);