From: Steven Rostedt Date: Tue, 29 Jul 2025 18:23:06 +0000 (-0400) Subject: unwind_user/deferred: Add unwind_user_faultable() X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=5e32d0f15cc5c843a4115c4644d984d42524c794;p=thirdparty%2Flinux.git unwind_user/deferred: Add unwind_user_faultable() Add a new API to retrieve a user space callstack called unwind_user_faultable(). The difference between this user space stack tracer from the current user space stack tracer is that this must be called from faultable context as it may use routines to access user space data that needs to be faulted in. It can be safely called from entering or exiting a system call as the code can still be faulted in there. This code is based on work by Josh Poimboeuf's deferred unwinding code: Link: https://lore.kernel.org/all/6052e8487746603bdb29b65f4033e739092d9925.1737511963.git.jpoimboe@kernel.org/ Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182405.147896868@kernel.org Reviewed-by: Jens Remus Signed-off-by: Steven Rostedt (Google) --- diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f78a64beb52c..59fdf7d9bb1ea 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -46,6 +46,7 @@ #include #include #include +#include #include /* task_struct member predeclarations (sorted alphabetically): */ @@ -1654,6 +1655,10 @@ struct task_struct { struct user_event_mm *user_event_mm; #endif +#ifdef CONFIG_UNWIND_USER + struct unwind_task_info unwind_info; +#endif + /* CPU-specific state of this task: */ struct thread_struct thread; diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h new file mode 100644 index 0000000000000..a5f6e8f8a1a2f --- /dev/null +++ b/include/linux/unwind_deferred.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNWIND_USER_DEFERRED_H +#define _LINUX_UNWIND_USER_DEFERRED_H + +#include +#include + +#ifdef CONFIG_UNWIND_USER + +void unwind_task_init(struct task_struct *task); +void unwind_task_free(struct task_struct *task); + +int unwind_user_faultable(struct unwind_stacktrace *trace); + +#else /* !CONFIG_UNWIND_USER */ + +static inline void unwind_task_init(struct task_struct *task) {} +static inline void unwind_task_free(struct task_struct *task) {} + +static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; } + +#endif /* !CONFIG_UNWIND_USER */ + +#endif /* _LINUX_UNWIND_USER_DEFERRED_H */ diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h new file mode 100644 index 0000000000000..aa32db574e43d --- /dev/null +++ b/include/linux/unwind_deferred_types.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H +#define _LINUX_UNWIND_USER_DEFERRED_TYPES_H + +struct unwind_task_info { + unsigned long *entries; +}; + +#endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 1ee8eb11f38ba..3341d50c61f22 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -105,6 +105,7 @@ #include #include #include +#include #include #include @@ -732,6 +733,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); + unwind_task_free(tsk); sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); @@ -2135,6 +2137,8 @@ __latent_entropy struct task_struct *copy_process( p->bpf_ctx = NULL; #endif + unwind_task_init(p); + /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) diff --git a/kernel/unwind/Makefile b/kernel/unwind/Makefile index 349ce36775268..eae37bea54fdb 100644 --- a/kernel/unwind/Makefile +++ b/kernel/unwind/Makefile @@ -1 +1 @@ - obj-$(CONFIG_UNWIND_USER) += user.o + obj-$(CONFIG_UNWIND_USER) += user.o deferred.o diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c new file mode 100644 index 0000000000000..a0badbeb3cc1b --- /dev/null +++ b/kernel/unwind/deferred.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Deferred user space unwinding + */ +#include +#include +#include +#include + +#define UNWIND_MAX_ENTRIES 512 + +/** + * unwind_user_faultable - Produce a user stacktrace in faultable context + * @trace: The descriptor that will store the user stacktrace + * + * This must be called in a known faultable context (usually when entering + * or exiting user space). Depending on the available implementations + * the @trace will be loaded with the addresses of the user space stacktrace + * if it can be found. + * + * Return: 0 on success and negative on error + * On success @trace will contain the user space stacktrace + */ +int unwind_user_faultable(struct unwind_stacktrace *trace) +{ + struct unwind_task_info *info = ¤t->unwind_info; + + /* Should always be called from faultable context */ + might_fault(); + + if (current->flags & PF_EXITING) + return -EINVAL; + + if (!info->entries) { + info->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long), + GFP_KERNEL); + if (!info->entries) + return -ENOMEM; + } + + trace->nr = 0; + trace->entries = info->entries; + unwind_user(trace, UNWIND_MAX_ENTRIES); + + return 0; +} + +void unwind_task_init(struct task_struct *task) +{ + struct unwind_task_info *info = &task->unwind_info; + + memset(info, 0, sizeof(*info)); +} + +void unwind_task_free(struct task_struct *task) +{ + struct unwind_task_info *info = &task->unwind_info; + + kfree(info->entries); +}