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, 342 insertions, 0 deletions

diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
new file mode 100644
index 000000000..2f7564f26
--- /dev/null
+++ b/drivers/media/rc/bpf-lirc.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: GPL-2.0
+// bpf-lirc.c - handles bpf
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/bpf_lirc.h>
+#include "rc-core-priv.h"
+
+#define lirc_rcu_dereference(p)						\
+	rcu_dereference_protected(p, lockdep_is_held(&ir_raw_handler_lock))
+
+/*
+ * BPF interface for raw IR
+ */
+const struct bpf_prog_ops lirc_mode2_prog_ops = {
+};
+
+BPF_CALL_1(bpf_rc_repeat, u32*, sample)
+{
+	struct ir_raw_event_ctrl *ctrl;
+
+	ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample);
+
+	rc_repeat(ctrl->dev);
+
+	return 0;
+}
+
+static const struct bpf_func_proto rc_repeat_proto = {
+	.func	   = bpf_rc_repeat,
+	.gpl_only  = true, /* rc_repeat is EXPORT_SYMBOL_GPL */
+	.ret_type  = RET_INTEGER,
+	.arg1_type = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_4(bpf_rc_keydown, u32*, sample, u32, protocol, u64, scancode,
+	   u32, toggle)
+{
+	struct ir_raw_event_ctrl *ctrl;
+
+	ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample);
+
+	rc_keydown(ctrl->dev, protocol, scancode, toggle != 0);
+
+	return 0;
+}
+
+static const struct bpf_func_proto rc_keydown_proto = {
+	.func	   = bpf_rc_keydown,
+	.gpl_only  = true, /* rc_keydown is EXPORT_SYMBOL_GPL */
+	.ret_type  = RET_INTEGER,
+	.arg1_type = ARG_PTR_TO_CTX,
+	.arg2_type = ARG_ANYTHING,
+	.arg3_type = ARG_ANYTHING,
+	.arg4_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_rc_pointer_rel, u32*, sample, s32, rel_x, s32, rel_y)
+{
+	struct ir_raw_event_ctrl *ctrl;
+
+	ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample);
+
+	input_report_rel(ctrl->dev->input_dev, REL_X, rel_x);
+	input_report_rel(ctrl->dev->input_dev, REL_Y, rel_y);
+	input_sync(ctrl->dev->input_dev);
+
+	return 0;
+}
+
+static const struct bpf_func_proto rc_pointer_rel_proto = {
+	.func	   = bpf_rc_pointer_rel,
+	.gpl_only  = true,
+	.ret_type  = RET_INTEGER,
+	.arg1_type = ARG_PTR_TO_CTX,
+	.arg2_type = ARG_ANYTHING,
+	.arg3_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_rc_repeat:
+		return &rc_repeat_proto;
+	case BPF_FUNC_rc_keydown:
+		return &rc_keydown_proto;
+	case BPF_FUNC_rc_pointer_rel:
+		return &rc_pointer_rel_proto;
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_map_push_elem:
+		return &bpf_map_push_elem_proto;
+	case BPF_FUNC_map_pop_elem:
+		return &bpf_map_pop_elem_proto;
+	case BPF_FUNC_map_peek_elem:
+		return &bpf_map_peek_elem_proto;
+	case BPF_FUNC_ktime_get_ns:
+		return &bpf_ktime_get_ns_proto;
+	case BPF_FUNC_ktime_get_boot_ns:
+		return &bpf_ktime_get_boot_ns_proto;
+	case BPF_FUNC_tail_call:
+		return &bpf_tail_call_proto;
+	case BPF_FUNC_get_prandom_u32:
+		return &bpf_get_prandom_u32_proto;
+	case BPF_FUNC_trace_printk:
+		if (bpf_token_capable(prog->aux->token, CAP_PERFMON))
+			return bpf_get_trace_printk_proto();
+		fallthrough;
+	default:
+		return NULL;
+	}
+}
+
+static bool lirc_mode2_is_valid_access(int off, int size,
+				       enum bpf_access_type type,
+				       const struct bpf_prog *prog,
+				       struct bpf_insn_access_aux *info)
+{
+	/* We have one field of u32 */
+	return type == BPF_READ && off == 0 && size == sizeof(u32);
+}
+
+const struct bpf_verifier_ops lirc_mode2_verifier_ops = {
+	.get_func_proto  = lirc_mode2_func_proto,
+	.is_valid_access = lirc_mode2_is_valid_access
+};
+
+#define BPF_MAX_PROGS 64
+
+static int lirc_bpf_attach(struct rc_dev *rcdev, struct bpf_prog *prog)
+{
+	struct bpf_prog_array *old_array;
+	struct bpf_prog_array *new_array;
+	struct ir_raw_event_ctrl *raw;
+	int ret;
+
+	if (rcdev->driver_type != RC_DRIVER_IR_RAW)
+		return -EINVAL;
+
+	ret = mutex_lock_interruptible(&ir_raw_handler_lock);
+	if (ret)
+		return ret;
+
+	raw = rcdev->raw;
+	if (!raw) {
+		ret = -ENODEV;
+		goto unlock;
+	}
+
+	old_array = lirc_rcu_dereference(raw->progs);
+	if (old_array && bpf_prog_array_length(old_array) >= BPF_MAX_PROGS) {
+		ret = -E2BIG;
+		goto unlock;
+	}
+
+	ret = bpf_prog_array_copy(old_array, NULL, prog, 0, &new_array);
+	if (ret < 0)
+		goto unlock;
+
+	rcu_assign_pointer(raw->progs, new_array);
+	bpf_prog_array_free(old_array);
+
+unlock:
+	mutex_unlock(&ir_raw_handler_lock);
+	return ret;
+}
+
+static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog)
+{
+	struct bpf_prog_array *old_array;
+	struct bpf_prog_array *new_array;
+	struct ir_raw_event_ctrl *raw;
+	int ret;
+
+	if (rcdev->driver_type != RC_DRIVER_IR_RAW)
+		return -EINVAL;
+
+	ret = mutex_lock_interruptible(&ir_raw_handler_lock);
+	if (ret)
+		return ret;
+
+	raw = rcdev->raw;
+	if (!raw) {
+		ret = -ENODEV;
+		goto unlock;
+	}
+
+	old_array = lirc_rcu_dereference(raw->progs);
+	ret = bpf_prog_array_copy(old_array, prog, NULL, 0, &new_array);
+	/*
+	 * Do not use bpf_prog_array_delete_safe() as we would end up
+	 * with a dummy entry in the array, and the we would free the
+	 * dummy in lirc_bpf_free()
+	 */
+	if (ret)
+		goto unlock;
+
+	rcu_assign_pointer(raw->progs, new_array);
+	bpf_prog_array_free(old_array);
+	bpf_prog_put(prog);
+unlock:
+	mutex_unlock(&ir_raw_handler_lock);
+	return ret;
+}
+
+void lirc_bpf_run(struct rc_dev *rcdev, u32 sample)
+{
+	struct ir_raw_event_ctrl *raw = rcdev->raw;
+
+	raw->bpf_sample = sample;
+
+	if (raw->progs) {
+		rcu_read_lock();
+		bpf_prog_run_array(rcu_dereference(raw->progs),
+				   &raw->bpf_sample, bpf_prog_run);
+		rcu_read_unlock();
+	}
+}
+
+/*
+ * This should be called once the rc thread has been stopped, so there can be
+ * no concurrent bpf execution.
+ *
+ * Should be called with the ir_raw_handler_lock held.
+ */
+void lirc_bpf_free(struct rc_dev *rcdev)
+{
+	struct bpf_prog_array_item *item;
+	struct bpf_prog_array *array;
+
+	array = lirc_rcu_dereference(rcdev->raw->progs);
+	if (!array)
+		return;
+
+	for (item = array->items; item->prog; item++)
+		bpf_prog_put(item->prog);
+
+	bpf_prog_array_free(array);
+}
+
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct rc_dev *rcdev;
+	int ret;
+
+	if (attr->attach_flags)
+		return -EINVAL;
+
+	rcdev = rc_dev_get_from_fd(attr->target_fd, true);
+	if (IS_ERR(rcdev))
+		return PTR_ERR(rcdev);
+
+	ret = lirc_bpf_attach(rcdev, prog);
+
+	put_device(&rcdev->dev);
+
+	return ret;
+}
+
+int lirc_prog_detach(const union bpf_attr *attr)
+{
+	struct bpf_prog *prog;
+	struct rc_dev *rcdev;
+	int ret;
+
+	if (attr->attach_flags)
+		return -EINVAL;
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd,
+				 BPF_PROG_TYPE_LIRC_MODE2);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	rcdev = rc_dev_get_from_fd(attr->target_fd, true);
+	if (IS_ERR(rcdev)) {
+		bpf_prog_put(prog);
+		return PTR_ERR(rcdev);
+	}
+
+	ret = lirc_bpf_detach(rcdev, prog);
+
+	bpf_prog_put(prog);
+	put_device(&rcdev->dev);
+
+	return ret;
+}
+
+int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	struct bpf_prog_array *progs;
+	struct rc_dev *rcdev;
+	u32 cnt, flags = 0;
+	int ret;
+
+	if (attr->query.query_flags)
+		return -EINVAL;
+
+	rcdev = rc_dev_get_from_fd(attr->query.target_fd, false);
+	if (IS_ERR(rcdev))
+		return PTR_ERR(rcdev);
+
+	if (rcdev->driver_type != RC_DRIVER_IR_RAW) {
+		ret = -EINVAL;
+		goto put;
+	}
+
+	ret = mutex_lock_interruptible(&ir_raw_handler_lock);
+	if (ret)
+		goto put;
+
+	progs = lirc_rcu_dereference(rcdev->raw->progs);
+	cnt = progs ? bpf_prog_array_length(progs) : 0;
+
+	if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) {
+		ret = -EFAULT;
+		goto unlock;
+	}
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) {
+		ret = -EFAULT;
+		goto unlock;
+	}
+
+	if (attr->query.prog_cnt != 0 && prog_ids && cnt)
+		ret = bpf_prog_array_copy_to_user(progs, prog_ids,
+						  attr->query.prog_cnt);
+
+unlock:
+	mutex_unlock(&ir_raw_handler_lock);
+put:
+	put_device(&rcdev->dev);
+
+	return ret;
+}