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, 246 insertions, 0 deletions

diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
new file mode 100644
index 000000000..24f42175a
--- /dev/null
+++ b/drivers/mfd/tps65090.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Core driver for TI TPS65090 PMIC family
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * Author: Venu Byravarasu <vbyravarasu@nvidia.com>
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/tps65090.h>
+#include <linux/of.h>
+#include <linux/err.h>
+
+#define NUM_INT_REG 2
+
+#define TPS65090_INT1_MASK_VAC_STATUS_CHANGE		1
+#define TPS65090_INT1_MASK_VSYS_STATUS_CHANGE		2
+#define TPS65090_INT1_MASK_BAT_STATUS_CHANGE		3
+#define TPS65090_INT1_MASK_CHARGING_STATUS_CHANGE	4
+#define TPS65090_INT1_MASK_CHARGING_COMPLETE		5
+#define TPS65090_INT1_MASK_OVERLOAD_DCDC1		6
+#define TPS65090_INT1_MASK_OVERLOAD_DCDC2		7
+#define TPS65090_INT2_MASK_OVERLOAD_DCDC3		0
+#define TPS65090_INT2_MASK_OVERLOAD_FET1		1
+#define TPS65090_INT2_MASK_OVERLOAD_FET2		2
+#define TPS65090_INT2_MASK_OVERLOAD_FET3		3
+#define TPS65090_INT2_MASK_OVERLOAD_FET4		4
+#define TPS65090_INT2_MASK_OVERLOAD_FET5		5
+#define TPS65090_INT2_MASK_OVERLOAD_FET6		6
+#define TPS65090_INT2_MASK_OVERLOAD_FET7		7
+
+static const struct resource charger_resources[] = {
+	{
+		.start  = TPS65090_IRQ_VAC_STATUS_CHANGE,
+		.end    = TPS65090_IRQ_VAC_STATUS_CHANGE,
+		.flags  = IORESOURCE_IRQ,
+	}
+};
+
+enum tps65090_cells {
+	PMIC = 0,
+	CHARGER = 1,
+};
+
+static struct mfd_cell tps65090s[] = {
+	[PMIC] = {
+		.name = "tps65090-pmic",
+	},
+	[CHARGER] = {
+		.name = "tps65090-charger",
+		.num_resources = ARRAY_SIZE(charger_resources),
+		.resources = &charger_resources[0],
+		.of_compatible = "ti,tps65090-charger",
+	},
+};
+
+static const struct regmap_irq tps65090_irqs[] = {
+	/* INT1 IRQs*/
+	[TPS65090_IRQ_VAC_STATUS_CHANGE] = {
+		.mask = TPS65090_INT1_MASK_VAC_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_VSYS_STATUS_CHANGE] = {
+		.mask = TPS65090_INT1_MASK_VSYS_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_BAT_STATUS_CHANGE] = {
+		.mask = TPS65090_INT1_MASK_BAT_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_CHARGING_STATUS_CHANGE] = {
+		.mask = TPS65090_INT1_MASK_CHARGING_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_CHARGING_COMPLETE] = {
+		.mask = TPS65090_INT1_MASK_CHARGING_COMPLETE,
+	},
+	[TPS65090_IRQ_OVERLOAD_DCDC1] = {
+		.mask = TPS65090_INT1_MASK_OVERLOAD_DCDC1,
+	},
+	[TPS65090_IRQ_OVERLOAD_DCDC2] = {
+		.mask = TPS65090_INT1_MASK_OVERLOAD_DCDC2,
+	},
+	/* INT2 IRQs*/
+	[TPS65090_IRQ_OVERLOAD_DCDC3] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_DCDC3,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET1] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_FET1,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET2] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_FET2,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET3] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_FET3,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET4] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_FET4,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET5] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_FET5,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET6] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_FET6,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET7] = {
+		.reg_offset = 1,
+		.mask = TPS65090_INT2_MASK_OVERLOAD_FET7,
+	},
+};
+
+static const struct regmap_irq_chip tps65090_irq_chip = {
+	.name = "tps65090",
+	.irqs = tps65090_irqs,
+	.num_irqs = ARRAY_SIZE(tps65090_irqs),
+	.num_regs = NUM_INT_REG,
+	.status_base = TPS65090_REG_INTR_STS,
+	.unmask_base = TPS65090_REG_INTR_MASK,
+};
+
+static bool is_volatile_reg(struct device *dev, unsigned int reg)
+{
+	/* Nearly all registers have status bits mixed in, except a few */
+	switch (reg) {
+	case TPS65090_REG_INTR_MASK:
+	case TPS65090_REG_INTR_MASK2:
+	case TPS65090_REG_CG_CTRL0:
+	case TPS65090_REG_CG_CTRL1:
+	case TPS65090_REG_CG_CTRL2:
+	case TPS65090_REG_CG_CTRL3:
+	case TPS65090_REG_CG_CTRL4:
+	case TPS65090_REG_CG_CTRL5:
+		return false;
+	}
+	return true;
+}
+
+static const struct regmap_config tps65090_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = TPS65090_MAX_REG,
+	.num_reg_defaults_raw = TPS65090_NUM_REGS,
+	.cache_type = REGCACHE_MAPLE,
+	.volatile_reg = is_volatile_reg,
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id tps65090_of_match[] = {
+	{ .compatible = "ti,tps65090",},
+	{},
+};
+#endif
+
+static int tps65090_i2c_probe(struct i2c_client *client)
+{
+	struct tps65090_platform_data *pdata = dev_get_platdata(&client->dev);
+	int irq_base = 0;
+	struct tps65090 *tps65090;
+	int ret;
+
+	if (!pdata && !client->dev.of_node) {
+		dev_err(&client->dev,
+			"tps65090 requires platform data or of_node\n");
+		return -EINVAL;
+	}
+
+	if (pdata)
+		irq_base = pdata->irq_base;
+
+	tps65090 = devm_kzalloc(&client->dev, sizeof(*tps65090), GFP_KERNEL);
+	if (!tps65090)
+		return -ENOMEM;
+
+	tps65090->dev = &client->dev;
+	i2c_set_clientdata(client, tps65090);
+
+	tps65090->rmap = devm_regmap_init_i2c(client, &tps65090_regmap_config);
+	if (IS_ERR(tps65090->rmap)) {
+		ret = PTR_ERR(tps65090->rmap);
+		dev_err(&client->dev, "regmap_init failed with err: %d\n", ret);
+		return ret;
+	}
+
+	if (client->irq) {
+		ret = regmap_add_irq_chip(tps65090->rmap, client->irq,
+					  IRQF_ONESHOT | IRQF_TRIGGER_LOW, irq_base,
+					  &tps65090_irq_chip, &tps65090->irq_data);
+		if (ret) {
+			dev_err(&client->dev,
+				"IRQ init failed with err: %d\n", ret);
+			return ret;
+		}
+	} else {
+		/* Don't tell children they have an IRQ that'll never fire */
+		tps65090s[CHARGER].num_resources = 0;
+	}
+
+	ret = mfd_add_devices(tps65090->dev, -1, tps65090s,
+			      ARRAY_SIZE(tps65090s), NULL,
+			      0, regmap_irq_get_domain(tps65090->irq_data));
+	if (ret) {
+		dev_err(&client->dev, "add mfd devices failed with err: %d\n",
+			ret);
+		goto err_irq_exit;
+	}
+
+	return 0;
+
+err_irq_exit:
+	if (client->irq)
+		regmap_del_irq_chip(client->irq, tps65090->irq_data);
+	return ret;
+}
+
+
+static const struct i2c_device_id tps65090_id_table[] = {
+	{ "tps65090" },
+	{ }
+};
+
+static struct i2c_driver tps65090_driver = {
+	.driver	= {
+		.name	= "tps65090",
+		.suppress_bind_attrs = true,
+		.of_match_table = of_match_ptr(tps65090_of_match),
+	},
+	.probe		= tps65090_i2c_probe,
+	.id_table	= tps65090_id_table,
+};
+
+static int __init tps65090_init(void)
+{
+	return i2c_add_driver(&tps65090_driver);
+}
+subsys_initcall(tps65090_init);