diff options
| author | Josh Poimboeuf <jpoimboe@kernel.org> | 2025-07-29 21:23:08 +0300 |
|---|---|---|
| committer | Steven Rostedt (Google) <rostedt@goodmis.org> | 2025-07-31 17:20:10 +0300 |
| commit | 2dffa355f6c279e7d2e574abf9446c41a631c9e5 (patch) | |
| tree | 671cedcf45eeff3e1fee729ab799df5d014ae85c /include/linux | |
| parent | b9c73524106e1c0c857006fb9ff2e5a510dc4021 (diff) | |
| download | linux-2dffa355f6c279e7d2e574abf9446c41a631c9e5.tar.xz | |
unwind_user/deferred: Add deferred unwinding interface
Add an interface for scheduling task work to unwind the user space stack
before returning to user space. This solves several problems for its
callers:
- Ensure the unwind happens in task context even if the caller may be
running in interrupt context.
- Avoid duplicate unwinds, whether called multiple times by the same
caller or by different callers.
- Create a "context cookie" which allows trace post-processing to
correlate kernel unwinds/traces with the user unwind.
A concept of a "cookie" is created to detect when the stacktrace is the
same. A cookie is generated the first time a user space stacktrace is
requested after the task enters the kernel. As the stacktrace is saved on
the task_struct while the task is in the kernel, if another request comes
in, if the cookie is still the same, it will use the saved stacktrace,
and not have to regenerate one.
The cookie is passed to the caller on request, and when the stacktrace is
generated upon returning to user space, it calls the requester's callback
with the cookie as well as the stacktrace. The cookie is cleared
when it goes back to user space. Note, this currently adds another
conditional to the unwind_reset_info() path that is always called
returning to user space, but future changes will put this back to a single
conditional.
A global list is created and protected by a global mutex that holds
tracers that register with the unwind infrastructure. The number of
registered tracers will be limited in future changes. Each perf program or
ftrace instance will register its own descriptor to use for deferred
unwind stack traces.
Note, in the function unwind_deferred_task_work() that gets called when
returning to user space, it uses a global mutex for synchronization which
will cause a big bottleneck. This will be replaced by SRCU, but that
change adds some complex synchronization that deservers its own commit.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182405.488066537@kernel.org
Co-developed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/unwind_deferred.h | 24 | ||||
| -rw-r--r-- | include/linux/unwind_deferred_types.h | 24 |
2 files changed, 48 insertions, 0 deletions
diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index baacf4a1eb4c..14efd8c027aa 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -2,9 +2,19 @@ #ifndef _LINUX_UNWIND_USER_DEFERRED_H #define _LINUX_UNWIND_USER_DEFERRED_H +#include <linux/task_work.h> #include <linux/unwind_user.h> #include <linux/unwind_deferred_types.h> +struct unwind_work; + +typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stacktrace *trace, u64 cookie); + +struct unwind_work { + struct list_head list; + unwind_callback_t func; +}; + #ifdef CONFIG_UNWIND_USER void unwind_task_init(struct task_struct *task); @@ -12,8 +22,19 @@ void unwind_task_free(struct task_struct *task); int unwind_user_faultable(struct unwind_stacktrace *trace); +int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func); +int unwind_deferred_request(struct unwind_work *work, u64 *cookie); +void unwind_deferred_cancel(struct unwind_work *work); + static __always_inline void unwind_reset_info(void) { + if (unlikely(current->unwind_info.id.id)) + current->unwind_info.id.id = 0; + /* + * As unwind_user_faultable() can be called directly and + * depends on nr_entries being cleared on exit to user, + * this needs to be a separate conditional. + */ if (unlikely(current->unwind_info.cache)) current->unwind_info.cache->nr_entries = 0; } @@ -24,6 +45,9 @@ 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; } +static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { return -ENOSYS; } +static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; } +static inline void unwind_deferred_cancel(struct unwind_work *work) {} static inline void unwind_reset_info(void) {} diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h index db5b54b18828..104c477d5609 100644 --- a/include/linux/unwind_deferred_types.h +++ b/include/linux/unwind_deferred_types.h @@ -7,8 +7,32 @@ struct unwind_cache { unsigned long entries[]; }; +/* + * The unwind_task_id is a unique identifier that maps to a user space + * stacktrace. It is generated the first time a deferred user space + * stacktrace is requested after a task has entered the kerenl and + * is cleared to zero when it exits. The mapped id will be a non-zero + * number. + * + * To simplify the generation of the 64 bit number, 32 bits will be + * the CPU it was generated on, and the other 32 bits will be a per + * cpu counter that gets incremented by two every time a new identifier + * is generated. The LSB will always be set to keep the value + * from being zero. + */ +union unwind_task_id { + struct { + u32 cpu; + u32 cnt; + }; + u64 id; +}; + struct unwind_task_info { struct unwind_cache *cache; + struct callback_head work; + union unwind_task_id id; + int pending; }; #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ |
