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, 297 insertions, 0 deletions

diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c
new file mode 100644
index 000000000..6a3efd782
--- /dev/null
+++ b/drivers/devfreq/event/exynos-nocp.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * exynos-nocp.c - Exynos NoC (Network On Chip) Probe support
+ *
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ * Author : Chanwoo Choi <cw00.choi@samsung.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/devfreq-event.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "exynos-nocp.h"
+
+struct exynos_nocp {
+	struct devfreq_event_dev *edev;
+	struct devfreq_event_desc desc;
+
+	struct device *dev;
+
+	struct regmap *regmap;
+	struct clk *clk;
+};
+
+/*
+ * The devfreq-event ops structure for nocp probe.
+ */
+static int exynos_nocp_set_event(struct devfreq_event_dev *edev)
+{
+	struct exynos_nocp *nocp = devfreq_event_get_drvdata(edev);
+	int ret;
+
+	/* Disable NoC probe */
+	ret = regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+				NOCP_MAIN_CTL_STATEN_MASK, 0);
+	if (ret < 0) {
+		dev_err(nocp->dev, "failed to disable the NoC probe device\n");
+		return ret;
+	}
+
+	/* Set a statistics dump period to 0 */
+	ret = regmap_write(nocp->regmap, NOCP_STAT_PERIOD, 0x0);
+	if (ret < 0)
+		goto out;
+
+	/* Set the IntEvent fields of *_SRC */
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_0_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_BYTE_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_1_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_CHAIN_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_2_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_CYCLE_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_3_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_CHAIN_MASK);
+	if (ret < 0)
+		goto out;
+
+
+	/* Set an alarm with a max/min value of 0 to generate StatALARM */
+	ret = regmap_write(nocp->regmap, NOCP_STAT_ALARM_MIN, 0x0);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_write(nocp->regmap, NOCP_STAT_ALARM_MAX, 0x0);
+	if (ret < 0)
+		goto out;
+
+	/* Set AlarmMode */
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_0_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_1_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_2_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_3_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	/* Enable the measurements by setting AlarmEn and StatEn */
+	ret = regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+			NOCP_MAIN_CTL_STATEN_MASK | NOCP_MAIN_CTL_ALARMEN_MASK,
+			NOCP_MAIN_CTL_STATEN_MASK | NOCP_MAIN_CTL_ALARMEN_MASK);
+	if (ret < 0)
+		goto out;
+
+	/* Set GlobalEN */
+	ret = regmap_update_bits(nocp->regmap, NOCP_CFG_CTL,
+				NOCP_CFG_CTL_GLOBALEN_MASK,
+				NOCP_CFG_CTL_GLOBALEN_MASK);
+	if (ret < 0)
+		goto out;
+
+	/* Enable NoC probe */
+	ret = regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+				NOCP_MAIN_CTL_STATEN_MASK,
+				NOCP_MAIN_CTL_STATEN_MASK);
+	if (ret < 0)
+		goto out;
+
+	return 0;
+
+out:
+	/* Reset NoC probe */
+	if (regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+				NOCP_MAIN_CTL_STATEN_MASK, 0)) {
+		dev_err(nocp->dev, "Failed to reset NoC probe device\n");
+	}
+
+	return ret;
+}
+
+static int exynos_nocp_get_event(struct devfreq_event_dev *edev,
+				struct devfreq_event_data *edata)
+{
+	struct exynos_nocp *nocp = devfreq_event_get_drvdata(edev);
+	unsigned int counter[4];
+	int ret;
+
+	/* Read cycle count */
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_0_VAL, &counter[0]);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_1_VAL, &counter[1]);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_2_VAL, &counter[2]);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_3_VAL, &counter[3]);
+	if (ret < 0)
+		goto out;
+
+	edata->load_count = ((counter[1] << 16) | counter[0]);
+	edata->total_count = ((counter[3] << 16) | counter[2]);
+
+	dev_dbg(&edev->dev, "%s (event: %ld/%ld)\n", edev->desc->name,
+					edata->load_count, edata->total_count);
+
+	return 0;
+
+out:
+	dev_err(nocp->dev, "Failed to read the counter of NoC probe device\n");
+
+	return ret;
+}
+
+static const struct devfreq_event_ops exynos_nocp_ops = {
+	.set_event = exynos_nocp_set_event,
+	.get_event = exynos_nocp_get_event,
+};
+
+static const struct of_device_id exynos_nocp_id_match[] = {
+	{ .compatible = "samsung,exynos5420-nocp", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, exynos_nocp_id_match);
+
+static struct regmap_config exynos_nocp_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = NOCP_COUNTERS_3_VAL,
+};
+
+static int exynos_nocp_parse_dt(struct platform_device *pdev,
+				struct exynos_nocp *nocp)
+{
+	struct device *dev = nocp->dev;
+	struct device_node *np = dev->of_node;
+	struct resource *res;
+	void __iomem *base;
+
+	if (!np) {
+		dev_err(dev, "failed to find devicetree node\n");
+		return -EINVAL;
+	}
+
+	nocp->clk = devm_clk_get(dev, "nocp");
+	if (IS_ERR(nocp->clk))
+		nocp->clk = NULL;
+
+	/* Maps the memory mapped IO to control nocp register */
+	base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	exynos_nocp_regmap_config.max_register = resource_size(res) - 4;
+
+	nocp->regmap = devm_regmap_init_mmio(dev, base,
+					&exynos_nocp_regmap_config);
+	if (IS_ERR(nocp->regmap)) {
+		dev_err(dev, "failed to initialize regmap\n");
+		return PTR_ERR(nocp->regmap);
+	}
+
+	return 0;
+}
+
+static int exynos_nocp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct exynos_nocp *nocp;
+	int ret;
+
+	nocp = devm_kzalloc(&pdev->dev, sizeof(*nocp), GFP_KERNEL);
+	if (!nocp)
+		return -ENOMEM;
+
+	nocp->dev = &pdev->dev;
+
+	/* Parse dt data to get resource */
+	ret = exynos_nocp_parse_dt(pdev, nocp);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"failed to parse devicetree for resource\n");
+		return ret;
+	}
+
+	/* Add devfreq-event device to measure the bandwidth of NoC */
+	nocp->desc.ops = &exynos_nocp_ops;
+	nocp->desc.driver_data = nocp;
+	nocp->desc.name = np->full_name;
+	nocp->edev = devm_devfreq_event_add_edev(&pdev->dev, &nocp->desc);
+	if (IS_ERR(nocp->edev)) {
+		dev_err(&pdev->dev,
+			"failed to add devfreq-event device\n");
+		return PTR_ERR(nocp->edev);
+	}
+	platform_set_drvdata(pdev, nocp);
+
+	ret = clk_prepare_enable(nocp->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to prepare ppmu clock\n");
+		return ret;
+	}
+
+	pr_info("exynos-nocp: new NoC Probe device registered: %s\n",
+			dev_name(dev));
+
+	return 0;
+}
+
+static void exynos_nocp_remove(struct platform_device *pdev)
+{
+	struct exynos_nocp *nocp = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(nocp->clk);
+}
+
+static struct platform_driver exynos_nocp_driver = {
+	.probe	= exynos_nocp_probe,
+	.remove = exynos_nocp_remove,
+	.driver = {
+		.name	= "exynos-nocp",
+		.of_match_table = exynos_nocp_id_match,
+	},
+};
+module_platform_driver(exynos_nocp_driver);
+
+MODULE_DESCRIPTION("Exynos NoC (Network on Chip) Probe driver");
+MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
+MODULE_LICENSE("GPL");