From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions 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) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- drivers/regulator/userspace-consumer.c | 225 +++++++++++++++++++++++++++++++++ 1 file changed, 225 insertions(+) create mode 100644 drivers/regulator/userspace-consumer.c (limited to 'drivers/regulator/userspace-consumer.c') diff --git a/drivers/regulator/userspace-consumer.c b/drivers/regulator/userspace-consumer.c new file mode 100644 index 000000000..72bb5ffb4 --- /dev/null +++ b/drivers/regulator/userspace-consumer.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * userspace-consumer.c + * + * Copyright 2009 CompuLab, Ltd. + * + * Author: Mike Rapoport + * + * Based of virtual consumer driver: + * Copyright 2008 Wolfson Microelectronics PLC. + * Author: Mark Brown + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +struct userspace_consumer_data { + const char *name; + + struct mutex lock; + bool enabled; + bool no_autoswitch; + + int num_supplies; + struct regulator_bulk_data *supplies; +}; + +static ssize_t name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct userspace_consumer_data *data = dev_get_drvdata(dev); + + return sprintf(buf, "%s\n", data->name); +} + +static ssize_t state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct userspace_consumer_data *data = dev_get_drvdata(dev); + + if (data->enabled) + return sprintf(buf, "enabled\n"); + + return sprintf(buf, "disabled\n"); +} + +static ssize_t state_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct userspace_consumer_data *data = dev_get_drvdata(dev); + bool enabled; + int ret; + + /* + * sysfs_streq() doesn't need the \n's, but we add them so the strings + * will be shared with show_state(), above. + */ + if (sysfs_streq(buf, "enabled\n") || sysfs_streq(buf, "1")) + enabled = true; + else if (sysfs_streq(buf, "disabled\n") || sysfs_streq(buf, "0")) + enabled = false; + else { + dev_err(dev, "Configuring invalid mode\n"); + return count; + } + + mutex_lock(&data->lock); + if (enabled != data->enabled) { + if (enabled) + ret = regulator_bulk_enable(data->num_supplies, + data->supplies); + else + ret = regulator_bulk_disable(data->num_supplies, + data->supplies); + + if (ret == 0) + data->enabled = enabled; + else + dev_err(dev, "Failed to configure state: %d\n", ret); + } + mutex_unlock(&data->lock); + + return count; +} + +static DEVICE_ATTR_RO(name); +static DEVICE_ATTR_RW(state); + +static struct attribute *attributes[] = { + &dev_attr_name.attr, + &dev_attr_state.attr, + NULL, +}; + +static umode_t attr_visible(struct kobject *kobj, struct attribute *attr, int idx) +{ + struct device *dev = kobj_to_dev(kobj); + struct userspace_consumer_data *data = dev_get_drvdata(dev); + + /* If a name hasn't been set, don't bother with the attribute */ + if (attr == &dev_attr_name.attr && !data->name) + return 0; + + return attr->mode; +} + +static const struct attribute_group attr_group = { + .attrs = attributes, + .is_visible = attr_visible, +}; + +static int regulator_userspace_consumer_probe(struct platform_device *pdev) +{ + struct regulator_userspace_consumer_data tmpdata; + struct regulator_userspace_consumer_data *pdata; + struct userspace_consumer_data *drvdata; + int ret; + + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + if (!pdev->dev.of_node) + return -EINVAL; + + pdata = &tmpdata; + memset(pdata, 0, sizeof(*pdata)); + + pdata->no_autoswitch = true; + pdata->num_supplies = 1; + pdata->supplies = devm_kzalloc(&pdev->dev, sizeof(*pdata->supplies), GFP_KERNEL); + if (!pdata->supplies) + return -ENOMEM; + pdata->supplies[0].supply = "vout"; + } + + if (pdata->num_supplies < 1) { + dev_err(&pdev->dev, "At least one supply required\n"); + return -EINVAL; + } + + drvdata = devm_kzalloc(&pdev->dev, + sizeof(struct userspace_consumer_data), + GFP_KERNEL); + if (drvdata == NULL) + return -ENOMEM; + + drvdata->name = pdata->name; + drvdata->num_supplies = pdata->num_supplies; + drvdata->supplies = pdata->supplies; + drvdata->no_autoswitch = pdata->no_autoswitch; + + mutex_init(&drvdata->lock); + + ret = devm_regulator_bulk_get_exclusive(&pdev->dev, drvdata->num_supplies, + drvdata->supplies); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to get supplies\n"); + + platform_set_drvdata(pdev, drvdata); + + ret = sysfs_create_group(&pdev->dev.kobj, &attr_group); + if (ret != 0) + return ret; + + if (pdata->init_on && !pdata->no_autoswitch) { + ret = regulator_bulk_enable(drvdata->num_supplies, + drvdata->supplies); + if (ret) { + dev_err(&pdev->dev, + "Failed to set initial state: %d\n", ret); + goto err_enable; + } + } + + ret = regulator_is_enabled(pdata->supplies[0].consumer); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to get regulator status\n"); + goto err_enable; + } + drvdata->enabled = !!ret; + + return 0; + +err_enable: + sysfs_remove_group(&pdev->dev.kobj, &attr_group); + + return ret; +} + +static void regulator_userspace_consumer_remove(struct platform_device *pdev) +{ + struct userspace_consumer_data *data = platform_get_drvdata(pdev); + + sysfs_remove_group(&pdev->dev.kobj, &attr_group); + + if (data->enabled && !data->no_autoswitch) + regulator_bulk_disable(data->num_supplies, data->supplies); +} + +static const struct of_device_id regulator_userspace_consumer_of_match[] = { + { .compatible = "regulator-output", }, + {}, +}; +MODULE_DEVICE_TABLE(of, regulator_userspace_consumer_of_match); + +static struct platform_driver regulator_userspace_consumer_driver = { + .probe = regulator_userspace_consumer_probe, + .remove = regulator_userspace_consumer_remove, + .driver = { + .name = "reg-userspace-consumer", + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .of_match_table = regulator_userspace_consumer_of_match, + }, +}; + +module_platform_driver(regulator_userspace_consumer_driver); + +MODULE_AUTHOR("Mike Rapoport "); +MODULE_DESCRIPTION("Userspace consumer for voltage and current regulators"); +MODULE_LICENSE("GPL"); -- cgit v1.3.1