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/mfd/syscon.c | 362 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 362 insertions(+) create mode 100644 drivers/mfd/syscon.c (limited to 'drivers/mfd/syscon.c') diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c new file mode 100644 index 000000000..21a7fcdd2 --- /dev/null +++ b/drivers/mfd/syscon.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * System Control Driver + * + * Copyright (C) 2012 Freescale Semiconductor, Inc. + * Copyright (C) 2012 Linaro Ltd. + * + * Author: Dong Aisheng + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_MUTEX(syscon_list_lock); +static LIST_HEAD(syscon_list); + +struct syscon { + struct device_node *np; + struct regmap *regmap; + struct reset_control *reset; + struct list_head list; +}; + +static const struct regmap_config syscon_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, +}; + +static struct syscon *of_syscon_register(struct device_node *np, bool check_res) +{ + struct clk *clk; + struct regmap *regmap; + void __iomem *base; + u32 reg_io_width; + int ret; + struct regmap_config syscon_config = syscon_regmap_config; + struct resource res; + struct reset_control *reset; + resource_size_t res_size; + + WARN_ON(!mutex_is_locked(&syscon_list_lock)); + + struct syscon *syscon __free(kfree) = kzalloc_obj(*syscon); + if (!syscon) + return ERR_PTR(-ENOMEM); + + if (of_address_to_resource(np, 0, &res)) + return ERR_PTR(-ENOMEM); + + base = of_iomap(np, 0); + if (!base) + return ERR_PTR(-ENOMEM); + + /* Parse the device's DT node for an endianness specification */ + if (of_property_read_bool(np, "big-endian")) + syscon_config.val_format_endian = REGMAP_ENDIAN_BIG; + else if (of_property_read_bool(np, "little-endian")) + syscon_config.val_format_endian = REGMAP_ENDIAN_LITTLE; + else if (of_property_read_bool(np, "native-endian")) + syscon_config.val_format_endian = REGMAP_ENDIAN_NATIVE; + + /* + * search for reg-io-width property in DT. If it is not provided, + * default to 4 bytes. regmap_init_mmio will return an error if values + * are invalid so there is no need to check them here. + */ + ret = of_property_read_u32(np, "reg-io-width", ®_io_width); + if (ret) + reg_io_width = 4; + + ret = of_hwspin_lock_get_id(np, 0); + if (ret > 0 || (IS_ENABLED(CONFIG_HWSPINLOCK) && ret == 0)) { + syscon_config.use_hwlock = true; + syscon_config.hwlock_id = ret; + syscon_config.hwlock_mode = HWLOCK_IRQSTATE; + } else if (ret < 0) { + switch (ret) { + case -ENOENT: + /* Ignore missing hwlock, it's optional. */ + break; + default: + pr_err("Failed to retrieve valid hwlock: %d\n", ret); + fallthrough; + case -EPROBE_DEFER: + goto err_regmap; + } + } + + res_size = resource_size(&res); + if (res_size < reg_io_width) { + ret = -EFAULT; + goto err_regmap; + } + + syscon_config.name = kasprintf(GFP_KERNEL, "%pOFn@%pa", np, &res.start); + if (!syscon_config.name) { + ret = -ENOMEM; + goto err_regmap; + } + syscon_config.reg_stride = reg_io_width; + syscon_config.val_bits = reg_io_width * 8; + syscon_config.max_register = res_size - reg_io_width; + if (!syscon_config.max_register) + syscon_config.max_register_is_0 = true; + + regmap = regmap_init_mmio(NULL, base, &syscon_config); + kfree(syscon_config.name); + if (IS_ERR(regmap)) { + pr_err("regmap init failed\n"); + ret = PTR_ERR(regmap); + goto err_regmap; + } + + if (check_res) { + clk = of_clk_get(np, 0); + if (IS_ERR(clk)) { + ret = PTR_ERR(clk); + /* clock is optional */ + if (ret != -ENOENT) + goto err_clk; + } else { + ret = regmap_mmio_attach_clk(regmap, clk); + if (ret) + goto err_attach_clk; + } + + reset = of_reset_control_get_optional_exclusive(np, NULL); + if (IS_ERR(reset)) { + ret = PTR_ERR(reset); + goto err_attach_clk; + } + + ret = reset_control_deassert(reset); + if (ret) + goto err_reset; + } + + syscon->regmap = regmap; + syscon->np = np; + + list_add_tail(&syscon->list, &syscon_list); + + return_ptr(syscon); + +err_reset: + reset_control_put(reset); +err_attach_clk: + if (!IS_ERR(clk)) + clk_put(clk); +err_clk: + regmap_exit(regmap); +err_regmap: + iounmap(base); + return ERR_PTR(ret); +} + +static struct regmap *device_node_get_regmap(struct device_node *np, + bool create_regmap, + bool check_res) +{ + struct syscon *entry, *syscon = NULL; + + mutex_lock(&syscon_list_lock); + + list_for_each_entry(entry, &syscon_list, list) + if (entry->np == np) { + syscon = entry; + break; + } + + if (!syscon) { + if (create_regmap) + syscon = of_syscon_register(np, check_res); + else + syscon = ERR_PTR(-EPROBE_DEFER); + } + mutex_unlock(&syscon_list_lock); + + if (IS_ERR(syscon)) + return ERR_CAST(syscon); + + return syscon->regmap; +} + +/** + * of_syscon_register_regmap() - Register regmap for specified device node + * @np: Device tree node + * @regmap: Pointer to regmap object + * + * Register an externally created regmap object with syscon for the specified + * device tree node. This regmap will then be returned to client drivers using + * the syscon_regmap_lookup_by_phandle() API. + * + * Return: 0 on success, negative error code on failure. + */ +int of_syscon_register_regmap(struct device_node *np, struct regmap *regmap) +{ + struct syscon *entry, *syscon = NULL; + int ret; + + if (!np || !regmap) + return -EINVAL; + + syscon = kzalloc_obj(*syscon); + if (!syscon) + return -ENOMEM; + + /* check if syscon entry already exists */ + mutex_lock(&syscon_list_lock); + + list_for_each_entry(entry, &syscon_list, list) + if (entry->np == np) { + ret = -EEXIST; + goto err_unlock; + } + + syscon->regmap = regmap; + syscon->np = np; + + /* register the regmap in syscon list */ + list_add_tail(&syscon->list, &syscon_list); + mutex_unlock(&syscon_list_lock); + + return 0; + +err_unlock: + mutex_unlock(&syscon_list_lock); + kfree(syscon); + return ret; +} +EXPORT_SYMBOL_GPL(of_syscon_register_regmap); + +/** + * device_node_to_regmap() - Get or create a regmap for specified device node + * @np: Device tree node + * + * Get a regmap for the specified device node. If there's not an existing + * regmap, then one is instantiated. This function should not be used if the + * device node has a custom regmap driver or has resources (clocks, resets) to + * be managed. Use syscon_node_to_regmap() instead for those cases. + * + * Return: regmap ptr on success, negative error code on failure. + */ +struct regmap *device_node_to_regmap(struct device_node *np) +{ + return device_node_get_regmap(np, true, false); +} +EXPORT_SYMBOL_GPL(device_node_to_regmap); + +/** + * syscon_node_to_regmap() - Get or create a regmap for specified syscon device node + * @np: Device tree node + * + * Get a regmap for the specified device node. If there's not an existing + * regmap, then one is instantiated if the node is a generic "syscon". This + * function is safe to use for a syscon registered with + * of_syscon_register_regmap(). + * + * Return: regmap ptr on success, negative error code on failure. + */ +struct regmap *syscon_node_to_regmap(struct device_node *np) +{ + return device_node_get_regmap(np, of_device_is_compatible(np, "syscon"), true); +} +EXPORT_SYMBOL_GPL(syscon_node_to_regmap); + +struct regmap *syscon_regmap_lookup_by_compatible(const char *s) +{ + struct device_node *syscon_np; + struct regmap *regmap; + + syscon_np = of_find_compatible_node(NULL, NULL, s); + if (!syscon_np) + return ERR_PTR(-ENODEV); + + regmap = syscon_node_to_regmap(syscon_np); + of_node_put(syscon_np); + + return regmap; +} +EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_compatible); + +struct regmap *syscon_regmap_lookup_by_phandle(struct device_node *np, + const char *property) +{ + struct device_node *syscon_np; + struct regmap *regmap; + + if (property) + syscon_np = of_parse_phandle(np, property, 0); + else + syscon_np = np; + + if (!syscon_np) + return ERR_PTR(-ENODEV); + + regmap = syscon_node_to_regmap(syscon_np); + + if (property) + of_node_put(syscon_np); + + return regmap; +} +EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle); + +struct regmap *syscon_regmap_lookup_by_phandle_args(struct device_node *np, + const char *property, + int arg_count, + unsigned int *out_args) +{ + struct device_node *syscon_np; + struct of_phandle_args args; + struct regmap *regmap; + unsigned int index; + int rc; + + rc = of_parse_phandle_with_fixed_args(np, property, arg_count, + 0, &args); + if (rc) + return ERR_PTR(rc); + + syscon_np = args.np; + if (!syscon_np) + return ERR_PTR(-ENODEV); + + regmap = syscon_node_to_regmap(syscon_np); + for (index = 0; index < arg_count; index++) + out_args[index] = args.args[index]; + of_node_put(syscon_np); + + return regmap; +} +EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle_args); + +/* + * It behaves the same as syscon_regmap_lookup_by_phandle() except where + * there is no regmap phandle. In this case, instead of returning -ENODEV, + * the function returns NULL. + */ +struct regmap *syscon_regmap_lookup_by_phandle_optional(struct device_node *np, + const char *property) +{ + struct regmap *regmap; + + regmap = syscon_regmap_lookup_by_phandle(np, property); + if (IS_ERR(regmap) && PTR_ERR(regmap) == -ENODEV) + return NULL; + + return regmap; +} +EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle_optional); -- cgit v1.3.1