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, 465 insertions, 0 deletions

diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
new file mode 100644
index 000000000..11842bce5
--- /dev/null
+++ b/drivers/clk/clk-composite.c
@@ -0,0 +1,465 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2013 NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+static u8 clk_composite_get_parent(struct clk_hw *hw)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *mux_ops = composite->mux_ops;
+	struct clk_hw *mux_hw = composite->mux_hw;
+
+	__clk_hw_set_clk(mux_hw, hw);
+
+	return mux_ops->get_parent(mux_hw);
+}
+
+static int clk_composite_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *mux_ops = composite->mux_ops;
+	struct clk_hw *mux_hw = composite->mux_hw;
+
+	__clk_hw_set_clk(mux_hw, hw);
+
+	return mux_ops->set_parent(mux_hw, index);
+}
+
+static unsigned long clk_composite_recalc_rate(struct clk_hw *hw,
+					    unsigned long parent_rate)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *rate_ops = composite->rate_ops;
+	struct clk_hw *rate_hw = composite->rate_hw;
+
+	__clk_hw_set_clk(rate_hw, hw);
+
+	return rate_ops->recalc_rate(rate_hw, parent_rate);
+}
+
+static int clk_composite_determine_rate_for_parent(struct clk_hw *rate_hw,
+						   struct clk_rate_request *req,
+						   struct clk_hw *parent_hw,
+						   const struct clk_ops *rate_ops)
+{
+	req->best_parent_hw = parent_hw;
+	req->best_parent_rate = clk_hw_get_rate(parent_hw);
+
+	return rate_ops->determine_rate(rate_hw, req);
+}
+
+static int clk_composite_determine_rate(struct clk_hw *hw,
+					struct clk_rate_request *req)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *rate_ops = composite->rate_ops;
+	const struct clk_ops *mux_ops = composite->mux_ops;
+	struct clk_hw *rate_hw = composite->rate_hw;
+	struct clk_hw *mux_hw = composite->mux_hw;
+	struct clk_hw *parent;
+	unsigned long rate_diff;
+	unsigned long best_rate_diff = ULONG_MAX;
+	unsigned long best_rate = 0;
+	int i, ret;
+
+	if (rate_hw && rate_ops && rate_ops->determine_rate &&
+	    mux_hw && mux_ops && mux_ops->set_parent) {
+		req->best_parent_hw = NULL;
+
+		if (clk_hw_get_flags(hw) & CLK_SET_RATE_NO_REPARENT) {
+			struct clk_rate_request tmp_req;
+
+			parent = clk_hw_get_parent(mux_hw);
+
+			clk_hw_forward_rate_request(hw, req, parent, &tmp_req, req->rate);
+			ret = clk_composite_determine_rate_for_parent(rate_hw,
+								      &tmp_req,
+								      parent,
+								      rate_ops);
+			if (ret)
+				return ret;
+
+			req->rate = tmp_req.rate;
+			req->best_parent_hw = tmp_req.best_parent_hw;
+			req->best_parent_rate = tmp_req.best_parent_rate;
+
+			return 0;
+		}
+
+		for (i = 0; i < clk_hw_get_num_parents(mux_hw); i++) {
+			struct clk_rate_request tmp_req;
+
+			parent = clk_hw_get_parent_by_index(mux_hw, i);
+			if (!parent)
+				continue;
+
+			clk_hw_forward_rate_request(hw, req, parent, &tmp_req, req->rate);
+			ret = clk_composite_determine_rate_for_parent(rate_hw,
+								      &tmp_req,
+								      parent,
+								      rate_ops);
+			if (ret)
+				continue;
+
+			if (req->rate >= tmp_req.rate)
+				rate_diff = req->rate - tmp_req.rate;
+			else
+				rate_diff = tmp_req.rate - req->rate;
+
+			if (!rate_diff || !req->best_parent_hw
+				       || best_rate_diff > rate_diff) {
+				req->best_parent_hw = parent;
+				req->best_parent_rate = tmp_req.best_parent_rate;
+				best_rate_diff = rate_diff;
+				best_rate = tmp_req.rate;
+			}
+
+			if (!rate_diff)
+				return 0;
+		}
+
+		req->rate = best_rate;
+		return 0;
+	} else if (rate_hw && rate_ops && rate_ops->determine_rate) {
+		__clk_hw_set_clk(rate_hw, hw);
+		return rate_ops->determine_rate(rate_hw, req);
+	} else if (mux_hw && mux_ops && mux_ops->determine_rate) {
+		__clk_hw_set_clk(mux_hw, hw);
+		return mux_ops->determine_rate(mux_hw, req);
+	} else {
+		pr_err("clk: clk_composite_determine_rate function called, but no mux or rate callback set!\n");
+		return -EINVAL;
+	}
+}
+
+static int clk_composite_set_rate(struct clk_hw *hw, unsigned long rate,
+			       unsigned long parent_rate)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *rate_ops = composite->rate_ops;
+	struct clk_hw *rate_hw = composite->rate_hw;
+
+	__clk_hw_set_clk(rate_hw, hw);
+
+	return rate_ops->set_rate(rate_hw, rate, parent_rate);
+}
+
+static int clk_composite_set_rate_and_parent(struct clk_hw *hw,
+					     unsigned long rate,
+					     unsigned long parent_rate,
+					     u8 index)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *rate_ops = composite->rate_ops;
+	const struct clk_ops *mux_ops = composite->mux_ops;
+	struct clk_hw *rate_hw = composite->rate_hw;
+	struct clk_hw *mux_hw = composite->mux_hw;
+	unsigned long temp_rate;
+
+	__clk_hw_set_clk(rate_hw, hw);
+	__clk_hw_set_clk(mux_hw, hw);
+
+	temp_rate = rate_ops->recalc_rate(rate_hw, parent_rate);
+	if (temp_rate > rate) {
+		rate_ops->set_rate(rate_hw, rate, parent_rate);
+		mux_ops->set_parent(mux_hw, index);
+	} else {
+		mux_ops->set_parent(mux_hw, index);
+		rate_ops->set_rate(rate_hw, rate, parent_rate);
+	}
+
+	return 0;
+}
+
+static int clk_composite_is_enabled(struct clk_hw *hw)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *gate_ops = composite->gate_ops;
+	struct clk_hw *gate_hw = composite->gate_hw;
+
+	__clk_hw_set_clk(gate_hw, hw);
+
+	return gate_ops->is_enabled(gate_hw);
+}
+
+static int clk_composite_enable(struct clk_hw *hw)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *gate_ops = composite->gate_ops;
+	struct clk_hw *gate_hw = composite->gate_hw;
+
+	__clk_hw_set_clk(gate_hw, hw);
+
+	return gate_ops->enable(gate_hw);
+}
+
+static void clk_composite_disable(struct clk_hw *hw)
+{
+	struct clk_composite *composite = to_clk_composite(hw);
+	const struct clk_ops *gate_ops = composite->gate_ops;
+	struct clk_hw *gate_hw = composite->gate_hw;
+
+	__clk_hw_set_clk(gate_hw, hw);
+
+	gate_ops->disable(gate_hw);
+}
+
+static struct clk_hw *__clk_hw_register_composite(struct device *dev,
+			const char *name, const char * const *parent_names,
+			const struct clk_parent_data *pdata, int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	struct clk_hw *hw;
+	struct clk_init_data init = {};
+	struct clk_composite *composite;
+	struct clk_ops *clk_composite_ops;
+	int ret;
+
+	composite = kzalloc_obj(*composite);
+	if (!composite)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.flags = flags;
+	if (parent_names)
+		init.parent_names = parent_names;
+	else
+		init.parent_data = pdata;
+	init.num_parents = num_parents;
+	hw = &composite->hw;
+
+	clk_composite_ops = &composite->ops;
+
+	if (mux_hw && mux_ops) {
+		if (!mux_ops->get_parent) {
+			hw = ERR_PTR(-EINVAL);
+			goto err;
+		}
+
+		composite->mux_hw = mux_hw;
+		composite->mux_ops = mux_ops;
+		clk_composite_ops->get_parent = clk_composite_get_parent;
+		if (mux_ops->set_parent)
+			clk_composite_ops->set_parent = clk_composite_set_parent;
+		if (mux_ops->determine_rate)
+			clk_composite_ops->determine_rate = clk_composite_determine_rate;
+	}
+
+	if (rate_hw && rate_ops) {
+		if (!rate_ops->recalc_rate) {
+			hw = ERR_PTR(-EINVAL);
+			goto err;
+		}
+		clk_composite_ops->recalc_rate = clk_composite_recalc_rate;
+
+		if (rate_ops->determine_rate)
+			clk_composite_ops->determine_rate =
+				clk_composite_determine_rate;
+
+		/* .set_rate requires .determine_rate */
+		if (rate_ops->set_rate) {
+			if (rate_ops->determine_rate)
+				clk_composite_ops->set_rate =
+						clk_composite_set_rate;
+			else
+				WARN(1, "%s: missing determine_rate op is required\n",
+						__func__);
+		}
+
+		composite->rate_hw = rate_hw;
+		composite->rate_ops = rate_ops;
+	}
+
+	if (mux_hw && mux_ops && rate_hw && rate_ops) {
+		if (mux_ops->set_parent && rate_ops->set_rate)
+			clk_composite_ops->set_rate_and_parent =
+			clk_composite_set_rate_and_parent;
+	}
+
+	if (gate_hw && gate_ops) {
+		if (!gate_ops->is_enabled || !gate_ops->enable ||
+		    !gate_ops->disable) {
+			hw = ERR_PTR(-EINVAL);
+			goto err;
+		}
+
+		composite->gate_hw = gate_hw;
+		composite->gate_ops = gate_ops;
+		clk_composite_ops->is_enabled = clk_composite_is_enabled;
+		clk_composite_ops->enable = clk_composite_enable;
+		clk_composite_ops->disable = clk_composite_disable;
+	}
+
+	init.ops = clk_composite_ops;
+	composite->hw.init = &init;
+
+	ret = clk_hw_register(dev, hw);
+	if (ret) {
+		hw = ERR_PTR(ret);
+		goto err;
+	}
+
+	if (composite->mux_hw)
+		composite->mux_hw->clk = hw->clk;
+
+	if (composite->rate_hw)
+		composite->rate_hw->clk = hw->clk;
+
+	if (composite->gate_hw)
+		composite->gate_hw->clk = hw->clk;
+
+	return hw;
+
+err:
+	kfree(composite);
+	return hw;
+}
+
+struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name,
+			const char * const *parent_names, int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	return __clk_hw_register_composite(dev, name, parent_names, NULL,
+					   num_parents, mux_hw, mux_ops,
+					   rate_hw, rate_ops, gate_hw,
+					   gate_ops, flags);
+}
+EXPORT_SYMBOL_GPL(clk_hw_register_composite);
+
+struct clk_hw *clk_hw_register_composite_pdata(struct device *dev,
+			const char *name,
+			const struct clk_parent_data *parent_data,
+			int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	return __clk_hw_register_composite(dev, name, NULL, parent_data,
+					   num_parents, mux_hw, mux_ops,
+					   rate_hw, rate_ops, gate_hw,
+					   gate_ops, flags);
+}
+
+struct clk *clk_register_composite(struct device *dev, const char *name,
+			const char * const *parent_names, int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	struct clk_hw *hw;
+
+	hw = clk_hw_register_composite(dev, name, parent_names, num_parents,
+			mux_hw, mux_ops, rate_hw, rate_ops, gate_hw, gate_ops,
+			flags);
+	if (IS_ERR(hw))
+		return ERR_CAST(hw);
+	return hw->clk;
+}
+EXPORT_SYMBOL_GPL(clk_register_composite);
+
+struct clk *clk_register_composite_pdata(struct device *dev, const char *name,
+			const struct clk_parent_data *parent_data,
+			int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	struct clk_hw *hw;
+
+	hw = clk_hw_register_composite_pdata(dev, name, parent_data,
+			num_parents, mux_hw, mux_ops, rate_hw, rate_ops,
+			gate_hw, gate_ops, flags);
+	if (IS_ERR(hw))
+		return ERR_CAST(hw);
+	return hw->clk;
+}
+
+void clk_unregister_composite(struct clk *clk)
+{
+	struct clk_composite *composite;
+	struct clk_hw *hw;
+
+	hw = __clk_get_hw(clk);
+	if (!hw)
+		return;
+
+	composite = to_clk_composite(hw);
+
+	clk_unregister(clk);
+	kfree(composite);
+}
+
+void clk_hw_unregister_composite(struct clk_hw *hw)
+{
+	struct clk_composite *composite;
+
+	composite = to_clk_composite(hw);
+
+	clk_hw_unregister(hw);
+	kfree(composite);
+}
+EXPORT_SYMBOL_GPL(clk_hw_unregister_composite);
+
+static void devm_clk_hw_release_composite(struct device *dev, void *res)
+{
+	clk_hw_unregister_composite(*(struct clk_hw **)res);
+}
+
+static struct clk_hw *__devm_clk_hw_register_composite(struct device *dev,
+			const char *name, const char * const *parent_names,
+			const struct clk_parent_data *pdata, int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	struct clk_hw **ptr, *hw;
+
+	ptr = devres_alloc(devm_clk_hw_release_composite, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	hw = __clk_hw_register_composite(dev, name, parent_names, pdata,
+					 num_parents, mux_hw, mux_ops, rate_hw,
+					 rate_ops, gate_hw, gate_ops, flags);
+
+	if (!IS_ERR(hw)) {
+		*ptr = hw;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return hw;
+}
+
+struct clk_hw *devm_clk_hw_register_composite_pdata(struct device *dev,
+			const char *name,
+			const struct clk_parent_data *parent_data,
+			int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	return __devm_clk_hw_register_composite(dev, name, NULL, parent_data,
+						num_parents, mux_hw, mux_ops,
+						rate_hw, rate_ops, gate_hw,
+						gate_ops, flags);
+}
+EXPORT_SYMBOL_GPL(devm_clk_hw_register_composite_pdata);