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, 148 insertions, 0 deletions

diff --git a/drivers/mfd/tps65086.c b/drivers/mfd/tps65086.c
new file mode 100644
index 000000000..54832e932
--- /dev/null
+++ b/drivers/mfd/tps65086.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/
+ *	Andrew F. Davis <afd@ti.com>
+ *
+ * Based on the TPS65912 driver
+ */
+
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+
+#include <linux/mfd/tps65086.h>
+
+static const struct mfd_cell tps65086_cells[] = {
+	{ .name = "tps65086-regulator", },
+	{ .name = "tps65086-gpio", },
+	{ .name = "tps65086-reset", },
+};
+
+static const struct regmap_range tps65086_yes_ranges[] = {
+	regmap_reg_range(TPS65086_IRQ, TPS65086_IRQ),
+	regmap_reg_range(TPS65086_PMICSTAT, TPS65086_SHUTDNSRC),
+	regmap_reg_range(TPS65086_GPOCTRL, TPS65086_GPOCTRL),
+	regmap_reg_range(TPS65086_PG_STATUS1, TPS65086_OC_STATUS),
+};
+
+static const struct regmap_access_table tps65086_volatile_table = {
+	.yes_ranges = tps65086_yes_ranges,
+	.n_yes_ranges = ARRAY_SIZE(tps65086_yes_ranges),
+};
+
+static const struct regmap_config tps65086_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.cache_type = REGCACHE_MAPLE,
+	.volatile_table = &tps65086_volatile_table,
+	.max_register = TPS65086_OC_STATUS,
+};
+
+static const struct regmap_irq tps65086_irqs[] = {
+	REGMAP_IRQ_REG(TPS65086_IRQ_DIETEMP, 0, TPS65086_IRQ_DIETEMP_MASK),
+	REGMAP_IRQ_REG(TPS65086_IRQ_SHUTDN, 0, TPS65086_IRQ_SHUTDN_MASK),
+	REGMAP_IRQ_REG(TPS65086_IRQ_FAULT, 0, TPS65086_IRQ_FAULT_MASK),
+};
+
+static const struct regmap_irq_chip tps65086_irq_chip = {
+	.name = "tps65086",
+	.status_base = TPS65086_IRQ,
+	.mask_base = TPS65086_IRQ_MASK,
+	.ack_base = TPS65086_IRQ,
+	.init_ack_masked = true,
+	.num_regs = 1,
+	.irqs = tps65086_irqs,
+	.num_irqs = ARRAY_SIZE(tps65086_irqs),
+};
+
+static const struct of_device_id tps65086_of_match_table[] = {
+	{ .compatible = "ti,tps65086", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, tps65086_of_match_table);
+
+static int tps65086_probe(struct i2c_client *client)
+{
+	struct tps65086 *tps;
+	unsigned int version;
+	int ret;
+
+	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
+	if (!tps)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, tps);
+	tps->dev = &client->dev;
+	tps->irq = client->irq;
+
+	tps->regmap = devm_regmap_init_i2c(client, &tps65086_regmap_config);
+	if (IS_ERR(tps->regmap)) {
+		dev_err(tps->dev, "Failed to initialize register map\n");
+		return PTR_ERR(tps->regmap);
+	}
+
+	/* Store device ID to load regulator configuration that fit to IC variant */
+	ret = regmap_read(tps->regmap, TPS65086_DEVICEID1, &tps->chip_id);
+	if (ret) {
+		dev_err(tps->dev, "Failed to read revision register 1\n");
+		return ret;
+	}
+
+	ret = regmap_read(tps->regmap, TPS65086_DEVICEID2, &version);
+	if (ret) {
+		dev_err(tps->dev, "Failed to read revision register 2\n");
+		return ret;
+	}
+
+	dev_info(tps->dev, "Device: TPS65086%01lX, OTP: %c, Rev: %ld\n",
+		 (version & TPS65086_DEVICEID2_PART_MASK),
+		 (char)((version & TPS65086_DEVICEID2_OTP_MASK) >> 4) + 'A',
+		 (version & TPS65086_DEVICEID2_REV_MASK) >> 6);
+
+	if (tps->irq > 0) {
+		ret = regmap_add_irq_chip(tps->regmap, tps->irq, IRQF_ONESHOT, 0,
+					  &tps65086_irq_chip, &tps->irq_data);
+		if (ret) {
+			dev_err(tps->dev, "Failed to register IRQ chip\n");
+			return ret;
+		}
+	}
+
+	ret = mfd_add_devices(tps->dev, PLATFORM_DEVID_AUTO, tps65086_cells,
+			      ARRAY_SIZE(tps65086_cells), NULL, 0,
+			      regmap_irq_get_domain(tps->irq_data));
+	if (ret && tps->irq > 0)
+		regmap_del_irq_chip(tps->irq, tps->irq_data);
+
+	return ret;
+}
+
+static void tps65086_remove(struct i2c_client *client)
+{
+	struct tps65086 *tps = i2c_get_clientdata(client);
+
+	if (tps->irq > 0)
+		regmap_del_irq_chip(tps->irq, tps->irq_data);
+}
+
+static const struct i2c_device_id tps65086_id_table[] = {
+	{ "tps65086" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, tps65086_id_table);
+
+static struct i2c_driver tps65086_driver = {
+	.driver		= {
+		.name	= "tps65086",
+		.of_match_table = tps65086_of_match_table,
+	},
+	.probe		= tps65086_probe,
+	.remove		= tps65086_remove,
+	.id_table       = tps65086_id_table,
+};
+module_i2c_driver(tps65086_driver);
+
+MODULE_AUTHOR("Andrew F. Davis <afd@ti.com>");
+MODULE_DESCRIPTION("TPS65086 PMIC Driver");
+MODULE_LICENSE("GPL v2");