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, 175 insertions, 0 deletions

diff --git a/drivers/xen/time.c b/drivers/xen/time.c
new file mode 100644
index 000000000..a2be0a4d4
--- /dev/null
+++ b/drivers/xen/time.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Xen stolen ticks accounting.
+ */
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/math64.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/static_call.h>
+#include <linux/sched/cputime.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/events.h>
+#include <xen/features.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/vcpu.h>
+#include <xen/xen-ops.h>
+
+/* runstate info updated by Xen */
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
+
+static DEFINE_PER_CPU(u64[4], old_runstate_time);
+
+/* return an consistent snapshot of 64-bit time/counter value */
+static u64 get64(const u64 *p)
+{
+	u64 ret;
+
+	if (BITS_PER_LONG < 64) {
+		u32 *p32 = (u32 *)p;
+		u32 h, l, h2;
+
+		/*
+		 * Read high then low, and then make sure high is
+		 * still the same; this will only loop if low wraps
+		 * and carries into high.
+		 * XXX some clean way to make this endian-proof?
+		 */
+		do {
+			h = READ_ONCE(p32[1]);
+			l = READ_ONCE(p32[0]);
+			h2 = READ_ONCE(p32[1]);
+		} while(h2 != h);
+
+		ret = (((u64)h) << 32) | l;
+	} else
+		ret = READ_ONCE(*p);
+
+	return ret;
+}
+
+static void xen_get_runstate_snapshot_cpu_delta(
+			      struct vcpu_runstate_info *res, unsigned int cpu)
+{
+	u64 state_time;
+	struct vcpu_runstate_info *state;
+
+	BUG_ON(preemptible());
+
+	state = per_cpu_ptr(&xen_runstate, cpu);
+
+	do {
+		state_time = get64(&state->state_entry_time);
+		rmb();	/* Hypervisor might update data. */
+		*res = __READ_ONCE(*state);
+		rmb();	/* Hypervisor might update data. */
+	} while (get64(&state->state_entry_time) != state_time ||
+		 (state_time & XEN_RUNSTATE_UPDATE));
+}
+
+static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
+					  unsigned int cpu)
+{
+	int i;
+
+	xen_get_runstate_snapshot_cpu_delta(res, cpu);
+
+	for (i = 0; i < 4; i++)
+		res->time[i] += per_cpu(old_runstate_time, cpu)[i];
+}
+
+void xen_manage_runstate_time(int action)
+{
+	static struct vcpu_runstate_info *runstate_delta;
+	struct vcpu_runstate_info state;
+	int cpu, i;
+
+	switch (action) {
+	case -1: /* backup runstate time before suspend */
+		if (unlikely(runstate_delta))
+			pr_warn_once("%s: memory leak as runstate_delta is not NULL\n",
+					__func__);
+
+		runstate_delta = kmalloc_objs(*runstate_delta,
+					      num_possible_cpus(), GFP_ATOMIC);
+		if (unlikely(!runstate_delta)) {
+			pr_warn("%s: failed to allocate runstate_delta\n",
+					__func__);
+			return;
+		}
+
+		for_each_possible_cpu(cpu) {
+			xen_get_runstate_snapshot_cpu_delta(&state, cpu);
+			memcpy(runstate_delta[cpu].time, state.time,
+					sizeof(runstate_delta[cpu].time));
+		}
+
+		break;
+
+	case 0: /* backup runstate time after resume */
+		if (unlikely(!runstate_delta)) {
+			pr_warn("%s: cannot accumulate runstate time as runstate_delta is NULL\n",
+					__func__);
+			return;
+		}
+
+		for_each_possible_cpu(cpu) {
+			for (i = 0; i < 4; i++)
+				per_cpu(old_runstate_time, cpu)[i] +=
+					runstate_delta[cpu].time[i];
+		}
+
+		break;
+
+	default: /* do not accumulate runstate time for checkpointing */
+		break;
+	}
+
+	if (action != -1 && runstate_delta) {
+		kfree(runstate_delta);
+		runstate_delta = NULL;
+	}
+}
+
+/* return true when a vcpu could run but has no real cpu to run on */
+bool xen_vcpu_stolen(int vcpu)
+{
+	return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
+}
+
+u64 xen_steal_clock(int cpu)
+{
+	struct vcpu_runstate_info state;
+
+	xen_get_runstate_snapshot_cpu(&state, cpu);
+	return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline];
+}
+
+void xen_setup_runstate_info(int cpu)
+{
+	struct vcpu_register_runstate_memory_area area;
+
+	area.addr.v = &per_cpu(xen_runstate, cpu);
+
+	if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
+			       xen_vcpu_nr(cpu), &area))
+		BUG();
+}
+
+void __init xen_time_setup_guest(void)
+{
+	bool xen_runstate_remote;
+
+	xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable,
+					VMASST_TYPE_runstate_update_flag);
+
+	static_call_update(pv_steal_clock, xen_steal_clock);
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (xen_runstate_remote)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+}