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, 250 insertions, 0 deletions

diff --git a/drivers/clk/clk-bulk.c b/drivers/clk/clk-bulk.c
new file mode 100644
index 000000000..acd9dff30
--- /dev/null
+++ b/drivers/clk/clk-bulk.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2017 NXP
+ *
+ * Dong Aisheng <aisheng.dong@nxp.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+
+static int __must_check of_clk_bulk_get(struct device *dev,
+					struct device_node *np, int num_clks,
+					struct clk_bulk_data *clks)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < num_clks; i++) {
+		clks[i].id = NULL;
+		clks[i].clk = NULL;
+	}
+
+	for (i = 0; i < num_clks; i++) {
+		of_property_read_string_index(np, "clock-names", i, &clks[i].id);
+		clks[i].clk = of_clk_get(np, i);
+		if (IS_ERR(clks[i].clk)) {
+			ret = PTR_ERR(clks[i].clk);
+			dev_err_probe(dev, ret, "%pOF: Failed to get clk index: %d (%s)\n",
+				      np, i, clks[i].id);
+			clks[i].clk = NULL;
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	clk_bulk_put(i, clks);
+
+	return ret;
+}
+
+static int __must_check of_clk_bulk_get_all(struct device *dev,
+					    struct device_node *np,
+					    struct clk_bulk_data **clks)
+{
+	struct clk_bulk_data *clk_bulk;
+	int num_clks;
+	int ret;
+
+	num_clks = of_clk_get_parent_count(np);
+	if (!num_clks)
+		return 0;
+
+	clk_bulk = kmalloc_objs(*clk_bulk, num_clks);
+	if (!clk_bulk)
+		return -ENOMEM;
+
+	ret = of_clk_bulk_get(dev, np, num_clks, clk_bulk);
+	if (ret) {
+		kfree(clk_bulk);
+		return ret;
+	}
+
+	*clks = clk_bulk;
+
+	return num_clks;
+}
+
+void clk_bulk_put(int num_clks, struct clk_bulk_data *clks)
+{
+	while (--num_clks >= 0) {
+		clk_put(clks[num_clks].clk);
+		clks[num_clks].clk = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(clk_bulk_put);
+
+static int __clk_bulk_get(struct device *dev, int num_clks,
+			  struct clk_bulk_data *clks, bool optional)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < num_clks; i++)
+		clks[i].clk = NULL;
+
+	for (i = 0; i < num_clks; i++) {
+		clks[i].clk = clk_get(dev, clks[i].id);
+		if (IS_ERR(clks[i].clk)) {
+			ret = PTR_ERR(clks[i].clk);
+			clks[i].clk = NULL;
+
+			if (ret == -ENOENT && optional)
+				continue;
+
+			dev_err_probe(dev, ret,
+				      "Failed to get clk '%s'\n",
+				      clks[i].id);
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	clk_bulk_put(i, clks);
+
+	return ret;
+}
+
+int __must_check clk_bulk_get(struct device *dev, int num_clks,
+			      struct clk_bulk_data *clks)
+{
+	return __clk_bulk_get(dev, num_clks, clks, false);
+}
+EXPORT_SYMBOL(clk_bulk_get);
+
+int __must_check clk_bulk_get_optional(struct device *dev, int num_clks,
+				       struct clk_bulk_data *clks)
+{
+	return __clk_bulk_get(dev, num_clks, clks, true);
+}
+EXPORT_SYMBOL_GPL(clk_bulk_get_optional);
+
+void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks)
+{
+	if (IS_ERR_OR_NULL(clks))
+		return;
+
+	clk_bulk_put(num_clks, clks);
+
+	kfree(clks);
+}
+EXPORT_SYMBOL(clk_bulk_put_all);
+
+int __must_check clk_bulk_get_all(struct device *dev,
+				  struct clk_bulk_data **clks)
+{
+	struct device_node *np = dev_of_node(dev);
+
+	if (!np)
+		return 0;
+
+	return of_clk_bulk_get_all(dev, np, clks);
+}
+EXPORT_SYMBOL(clk_bulk_get_all);
+
+#ifdef CONFIG_HAVE_CLK_PREPARE
+
+/**
+ * clk_bulk_unprepare - undo preparation of a set of clock sources
+ * @num_clks: the number of clk_bulk_data
+ * @clks: the clk_bulk_data table being unprepared
+ *
+ * clk_bulk_unprepare may sleep, which differentiates it from clk_bulk_disable.
+ * Returns 0 on success, -EERROR otherwise.
+ */
+void clk_bulk_unprepare(int num_clks, const struct clk_bulk_data *clks)
+{
+	while (--num_clks >= 0)
+		clk_unprepare(clks[num_clks].clk);
+}
+EXPORT_SYMBOL_GPL(clk_bulk_unprepare);
+
+/**
+ * clk_bulk_prepare - prepare a set of clocks
+ * @num_clks: the number of clk_bulk_data
+ * @clks: the clk_bulk_data table being prepared
+ *
+ * clk_bulk_prepare may sleep, which differentiates it from clk_bulk_enable.
+ * Returns 0 on success, -EERROR otherwise.
+ */
+int __must_check clk_bulk_prepare(int num_clks,
+				  const struct clk_bulk_data *clks)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < num_clks; i++) {
+		ret = clk_prepare(clks[i].clk);
+		if (ret) {
+			pr_err("Failed to prepare clk '%s': %d\n",
+				clks[i].id, ret);
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	clk_bulk_unprepare(i, clks);
+
+	return  ret;
+}
+EXPORT_SYMBOL_GPL(clk_bulk_prepare);
+
+#endif /* CONFIG_HAVE_CLK_PREPARE */
+
+/**
+ * clk_bulk_disable - gate a set of clocks
+ * @num_clks: the number of clk_bulk_data
+ * @clks: the clk_bulk_data table being gated
+ *
+ * clk_bulk_disable must not sleep, which differentiates it from
+ * clk_bulk_unprepare. clk_bulk_disable must be called before
+ * clk_bulk_unprepare.
+ */
+void clk_bulk_disable(int num_clks, const struct clk_bulk_data *clks)
+{
+
+	while (--num_clks >= 0)
+		clk_disable(clks[num_clks].clk);
+}
+EXPORT_SYMBOL_GPL(clk_bulk_disable);
+
+/**
+ * clk_bulk_enable - ungate a set of clocks
+ * @num_clks: the number of clk_bulk_data
+ * @clks: the clk_bulk_data table being ungated
+ *
+ * clk_bulk_enable must not sleep
+ * Returns 0 on success, -EERROR otherwise.
+ */
+int __must_check clk_bulk_enable(int num_clks, const struct clk_bulk_data *clks)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < num_clks; i++) {
+		ret = clk_enable(clks[i].clk);
+		if (ret) {
+			pr_err("Failed to enable clk '%s': %d\n",
+				clks[i].id, ret);
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	clk_bulk_disable(i, clks);
+
+	return  ret;
+}
+EXPORT_SYMBOL_GPL(clk_bulk_enable);