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, 203 insertions, 0 deletions

diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c
new file mode 100644
index 000000000..90c6902d5
--- /dev/null
+++ b/drivers/mfd/altera-sysmgr.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2018-2019, Intel Corporation.
+ *  Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *  Copyright (C) 2012 Linaro Ltd.
+ *
+ *  Based on syscon driver.
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/mfd/altera-sysmgr.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+/**
+ * struct altr_sysmgr - Altera SOCFPGA System Manager
+ * @regmap: the regmap used for System Manager accesses.
+ */
+struct altr_sysmgr {
+	struct regmap   *regmap;
+};
+
+static struct platform_driver altr_sysmgr_driver;
+
+/**
+ * s10_protected_reg_write
+ * Write to a protected SMC register.
+ * @base: Base address of System Manager
+ * @reg:  Address offset of register
+ * @val:  Value to write
+ * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
+ *	   INTEL_SIP_SMC_REG_ERROR on error
+ *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
+ */
+static int s10_protected_reg_write(void *base,
+				   unsigned int reg, unsigned int val)
+{
+	struct arm_smccc_res result;
+	unsigned long sysmgr_base = (unsigned long)base;
+
+	arm_smccc_smc(INTEL_SIP_SMC_REG_WRITE, sysmgr_base + reg,
+		      val, 0, 0, 0, 0, 0, &result);
+
+	return (int)result.a0;
+}
+
+/**
+ * s10_protected_reg_read
+ * Read the status of a protected SMC register
+ * @base: Base address of System Manager.
+ * @reg:  Address of register
+ * @val:  Value read.
+ * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
+ *	   INTEL_SIP_SMC_REG_ERROR on error
+ *	   INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
+ */
+static int s10_protected_reg_read(void *base,
+				  unsigned int reg, unsigned int *val)
+{
+	struct arm_smccc_res result;
+	unsigned long sysmgr_base = (unsigned long)base;
+
+	arm_smccc_smc(INTEL_SIP_SMC_REG_READ, sysmgr_base + reg,
+		      0, 0, 0, 0, 0, 0, &result);
+
+	*val = (unsigned int)result.a1;
+
+	return (int)result.a0;
+}
+
+static struct regmap_config altr_sysmgr_regmap_cfg = {
+	.name = "altr_sysmgr",
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+	.use_single_read = true,
+	.use_single_write = true,
+};
+
+/**
+ * altr_sysmgr_regmap_lookup_by_phandle
+ * Find the sysmgr previous configured in probe() and return regmap property.
+ * Return: regmap if found or error if not found.
+ *
+ * @np: Pointer to device's Device Tree node
+ * @property: Device Tree property name which references the sysmgr
+ */
+struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np,
+						    const char *property)
+{
+	struct device *dev;
+	struct altr_sysmgr *sysmgr;
+	struct device_node *sysmgr_np;
+
+	if (property)
+		sysmgr_np = of_parse_phandle(np, property, 0);
+	else
+		sysmgr_np = np;
+
+	if (!sysmgr_np)
+		return ERR_PTR(-ENODEV);
+
+	dev = driver_find_device_by_of_node(&altr_sysmgr_driver.driver,
+					    (void *)sysmgr_np);
+	if (property)
+		of_node_put(sysmgr_np);
+
+	if (!dev)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	sysmgr = dev_get_drvdata(dev);
+
+	put_device(dev);
+
+	return sysmgr->regmap;
+}
+EXPORT_SYMBOL_GPL(altr_sysmgr_regmap_lookup_by_phandle);
+
+static int sysmgr_probe(struct platform_device *pdev)
+{
+	struct altr_sysmgr *sysmgr;
+	struct regmap *regmap;
+	struct resource *res;
+	struct regmap_config sysmgr_config = altr_sysmgr_regmap_cfg;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	void __iomem *base;
+
+	sysmgr = devm_kzalloc(dev, sizeof(*sysmgr), GFP_KERNEL);
+	if (!sysmgr)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOENT;
+
+	sysmgr_config.max_register = resource_size(res) -
+				     sysmgr_config.reg_stride;
+	if (of_device_is_compatible(np, "altr,sys-mgr-s10")) {
+		sysmgr_config.reg_read = s10_protected_reg_read;
+		sysmgr_config.reg_write = s10_protected_reg_write;
+
+		/* Need physical address for SMCC call */
+		regmap = devm_regmap_init(dev, NULL,
+					  (void *)(uintptr_t)res->start,
+					  &sysmgr_config);
+	} else {
+		base = devm_ioremap(dev, res->start, resource_size(res));
+		if (!base)
+			return -ENOMEM;
+
+		sysmgr_config.max_register = resource_size(res) - 4;
+		regmap = devm_regmap_init_mmio(dev, base, &sysmgr_config);
+	}
+
+	if (IS_ERR(regmap)) {
+		pr_err("regmap init failed\n");
+		return PTR_ERR(regmap);
+	}
+
+	sysmgr->regmap = regmap;
+
+	platform_set_drvdata(pdev, sysmgr);
+
+	return 0;
+}
+
+static const struct of_device_id altr_sysmgr_of_match[] = {
+	{ .compatible = "altr,sys-mgr" },
+	{ .compatible = "altr,sys-mgr-s10" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, altr_sysmgr_of_match);
+
+static struct platform_driver altr_sysmgr_driver = {
+	.probe =  sysmgr_probe,
+	.driver = {
+		.name = "altr,system_manager",
+		.of_match_table = altr_sysmgr_of_match,
+	},
+};
+
+static int __init altr_sysmgr_init(void)
+{
+	return platform_driver_register(&altr_sysmgr_driver);
+}
+core_initcall(altr_sysmgr_init);
+
+static void __exit altr_sysmgr_exit(void)
+{
+	platform_driver_unregister(&altr_sysmgr_driver);
+}
+module_exit(altr_sysmgr_exit);
+
+MODULE_AUTHOR("Thor Thayer <>");
+MODULE_DESCRIPTION("SOCFPGA System Manager driver");