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, 113 insertions, 0 deletions

diff --git a/drivers/clk/sprd/common.c b/drivers/clk/sprd/common.c
new file mode 100644
index 000000000..0f2181617
--- /dev/null
+++ b/drivers/clk/sprd/common.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Spreadtrum clock infrastructure
+//
+// Copyright (C) 2017 Spreadtrum, Inc.
+// Author: Chunyan Zhang <chunyan.zhang@spreadtrum.com>
+
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "common.h"
+
+static const struct regmap_config sprdclk_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.fast_io	= true,
+};
+
+static void sprd_clk_set_regmap(const struct sprd_clk_desc *desc,
+			 struct regmap *regmap)
+{
+	int i;
+	struct sprd_clk_common *cclk;
+
+	for (i = 0; i < desc->num_clk_clks; i++) {
+		cclk = desc->clk_clks[i];
+		if (!cclk)
+			continue;
+
+		cclk->regmap = regmap;
+	}
+}
+
+int sprd_clk_regmap_init(struct platform_device *pdev,
+			 const struct sprd_clk_desc *desc)
+{
+	void __iomem *base;
+	struct device *dev = &pdev->dev;
+	struct device_node *node = dev->of_node, *np;
+	struct regmap *regmap;
+	struct resource *res;
+	struct regmap_config reg_config = sprdclk_regmap_config;
+
+	if (of_property_present(node, "sprd,syscon")) {
+		regmap = syscon_regmap_lookup_by_phandle(node, "sprd,syscon");
+		if (IS_ERR(regmap)) {
+			pr_err("%s: failed to get syscon regmap\n", __func__);
+			return PTR_ERR(regmap);
+		}
+	} else if (of_device_is_compatible(np =	of_get_parent(node), "syscon") ||
+		   (of_node_put(np), 0)) {
+		regmap = device_node_to_regmap(np);
+		of_node_put(np);
+		if (IS_ERR(regmap)) {
+			dev_err(dev, "failed to get regmap from its parent.\n");
+			return PTR_ERR(regmap);
+		}
+	} else {
+		base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+		if (IS_ERR(base))
+			return PTR_ERR(base);
+
+		reg_config.max_register = resource_size(res) - reg_config.reg_stride;
+
+		regmap = devm_regmap_init_mmio(&pdev->dev, base,
+					       &reg_config);
+		if (IS_ERR(regmap)) {
+			pr_err("failed to init regmap\n");
+			return PTR_ERR(regmap);
+		}
+	}
+
+	sprd_clk_set_regmap(desc, regmap);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sprd_clk_regmap_init);
+
+int sprd_clk_probe(struct device *dev, struct clk_hw_onecell_data *clkhw)
+{
+	int i, ret;
+	struct clk_hw *hw;
+
+	for (i = 0; i < clkhw->num; i++) {
+		const char *name;
+
+		hw = clkhw->hws[i];
+		if (!hw)
+			continue;
+
+		name = hw->init->name;
+		ret = devm_clk_hw_register(dev, hw);
+		if (ret) {
+			dev_err(dev, "Couldn't register clock %d - %s\n",
+				i, name);
+			return ret;
+		}
+	}
+
+	ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clkhw);
+	if (ret)
+		dev_err(dev, "Failed to add clock provider\n");
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sprd_clk_probe);
+
+MODULE_DESCRIPTION("Spreadtrum clock infrastructure");
+MODULE_LICENSE("GPL v2");