From: Josh Poimboeuf <jpoimboe@kernel.org>
Cache the results of the unwind to ensure the unwind is only performed
once, even when called by multiple tracers.
The cache nr_entries gets cleared every time the task exits the kernel.
When a stacktrace is requested, nr_entries gets set to the number of
entries in the stacktrace. If another stacktrace is requested, if
nr_entries is not zero, then it contains the same stacktrace that would be
retrieved so it is not processed again and the entries is given to the
caller.
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
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>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
include/linux/entry-common.h | 2 ++
include/linux/unwind_deferred.h | 8 +++++++
include/linux/unwind_deferred_types.h | 7 +++++-
kernel/unwind/deferred.c | 31 +++++++++++++++++++++------
4 files changed, 40 insertions(+), 8 deletions(-)
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index f94f3fdf15fc..8908b8eeb99b 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -12,6 +12,7 @@
#include <linux/resume_user_mode.h>
#include <linux/tick.h>
#include <linux/kmsan.h>
+#include <linux/unwind_deferred.h>
#include <asm/entry-common.h>
#include <asm/syscall.h>
@@ -362,6 +363,7 @@ static __always_inline void exit_to_user_mode(void)
lockdep_hardirqs_on_prepare();
instrumentation_end();
+ unwind_reset_info();
user_enter_irqoff();
arch_exit_to_user_mode();
lockdep_hardirqs_on(CALLER_ADDR0);
diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index a5f6e8f8a1a2..baacf4a1eb4c 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -12,6 +12,12 @@ void unwind_task_free(struct task_struct *task);
int unwind_user_faultable(struct unwind_stacktrace *trace);
+static __always_inline void unwind_reset_info(void)
+{
+ if (unlikely(current->unwind_info.cache))
+ current->unwind_info.cache->nr_entries = 0;
+}
+
#else /* !CONFIG_UNWIND_USER */
static inline void unwind_task_init(struct task_struct *task) {}
@@ -19,6 +25,8 @@ static inline void unwind_task_free(struct task_struct *task) {}
static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; }
+static inline void unwind_reset_info(void) {}
+
#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
index aa32db574e43..db5b54b18828 100644
--- a/include/linux/unwind_deferred_types.h
+++ b/include/linux/unwind_deferred_types.h
@@ -2,8 +2,13 @@
#ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H
#define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
+struct unwind_cache {
+ unsigned int nr_entries;
+ unsigned long entries[];
+};
+
struct unwind_task_info {
- unsigned long *entries;
+ struct unwind_cache *cache;
};
#endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index a0badbeb3cc1..96368a5aa522 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -4,10 +4,13 @@
*/
#include <linux/kernel.h>
#include <linux/sched.h>
+#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/unwind_deferred.h>
-#define UNWIND_MAX_ENTRIES 512
+/* Make the cache fit in a 4K page */
+#define UNWIND_MAX_ENTRIES \
+ ((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long))
/**
* unwind_user_faultable - Produce a user stacktrace in faultable context
@@ -24,6 +27,7 @@
int unwind_user_faultable(struct unwind_stacktrace *trace)
{
struct unwind_task_info *info = ¤t->unwind_info;
+ struct unwind_cache *cache;
/* Should always be called from faultable context */
might_fault();
@@ -31,17 +35,30 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
if (current->flags & PF_EXITING)
return -EINVAL;
- if (!info->entries) {
- info->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long),
- GFP_KERNEL);
- if (!info->entries)
+ if (!info->cache) {
+ info->cache = kzalloc(struct_size(cache, entries, UNWIND_MAX_ENTRIES),
+ GFP_KERNEL);
+ if (!info->cache)
return -ENOMEM;
}
+ cache = info->cache;
+ trace->entries = cache->entries;
+
+ if (cache->nr_entries) {
+ /*
+ * The user stack has already been previously unwound in this
+ * entry context. Skip the unwind and use the cache.
+ */
+ trace->nr = cache->nr_entries;
+ return 0;
+ }
+
trace->nr = 0;
- trace->entries = info->entries;
unwind_user(trace, UNWIND_MAX_ENTRIES);
+ cache->nr_entries = trace->nr;
+
return 0;
}
@@ -56,5 +73,5 @@ void unwind_task_free(struct task_struct *task)
{
struct unwind_task_info *info = &task->unwind_info;
- kfree(info->entries);
+ kfree(info->cache);
}
--
2.47.2
On 7/29/25 11:23 AM, Steven Rostedt wrote:
> From: Josh Poimboeuf <jpoimboe@kernel.org>
>
> Cache the results of the unwind to ensure the unwind is only performed
> once, even when called by multiple tracers.
>
> The cache nr_entries gets cleared every time the task exits the kernel.
> When a stacktrace is requested, nr_entries gets set to the number of
> entries in the stacktrace. If another stacktrace is requested, if
> nr_entries is not zero, then it contains the same stacktrace that would be
> retrieved so it is not processed again and the entries is given to the
> caller.
>
> Reviewed-by: Jens Remus <jremus@linux.ibm.com>
> 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>
> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
> ---
> include/linux/entry-common.h | 2 ++
> include/linux/unwind_deferred.h | 8 +++++++
> include/linux/unwind_deferred_types.h | 7 +++++-
> kernel/unwind/deferred.c | 31 +++++++++++++++++++++------
> 4 files changed, 40 insertions(+), 8 deletions(-)
>
> diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
> index f94f3fdf15fc..8908b8eeb99b 100644
> --- a/include/linux/entry-common.h
> +++ b/include/linux/entry-common.h
> @@ -12,6 +12,7 @@
> #include <linux/resume_user_mode.h>
> #include <linux/tick.h>
> #include <linux/kmsan.h>
> +#include <linux/unwind_deferred.h>
>
> #include <asm/entry-common.h>
> #include <asm/syscall.h>
> @@ -362,6 +363,7 @@ static __always_inline void exit_to_user_mode(void)
> lockdep_hardirqs_on_prepare();
> instrumentation_end();
>
> + unwind_reset_info();
> user_enter_irqoff();
> arch_exit_to_user_mode();
> lockdep_hardirqs_on(CALLER_ADDR0);
> diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
> index a5f6e8f8a1a2..baacf4a1eb4c 100644
> --- a/include/linux/unwind_deferred.h
> +++ b/include/linux/unwind_deferred.h
> @@ -12,6 +12,12 @@ void unwind_task_free(struct task_struct *task);
>
> int unwind_user_faultable(struct unwind_stacktrace *trace);
>
> +static __always_inline void unwind_reset_info(void)
> +{
> + if (unlikely(current->unwind_info.cache))
> + current->unwind_info.cache->nr_entries = 0;
> +}
Should the entries[] items upto nr_entries (stack trace info from the
previous request) also be reset to 0 here ?
> +
> #else /* !CONFIG_UNWIND_USER */
>
> static inline void unwind_task_init(struct task_struct *task) {}
> @@ -19,6 +25,8 @@ static inline void unwind_task_free(struct task_struct *task) {}
>
> static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; }
>
> +static inline void unwind_reset_info(void) {}
> +
> #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
> index aa32db574e43..db5b54b18828 100644
> --- a/include/linux/unwind_deferred_types.h
> +++ b/include/linux/unwind_deferred_types.h
> @@ -2,8 +2,13 @@
> #ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H
> #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
>
> +struct unwind_cache {
> + unsigned int nr_entries;
> + unsigned long entries[];
> +};
> +
Should we use __counted_by ?
> struct unwind_task_info {
> - unsigned long *entries;
> + struct unwind_cache *cache;
> };
>
> #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
> diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
> index a0badbeb3cc1..96368a5aa522 100644
> --- a/kernel/unwind/deferred.c
> +++ b/kernel/unwind/deferred.c
> @@ -4,10 +4,13 @@
> */
> #include <linux/kernel.h>
> #include <linux/sched.h>
> +#include <linux/sizes.h>
> #include <linux/slab.h>
> #include <linux/unwind_deferred.h>
>
> -#define UNWIND_MAX_ENTRIES 512
> +/* Make the cache fit in a 4K page */
> +#define UNWIND_MAX_ENTRIES \
> + ((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long))
>
> /**
> * unwind_user_faultable - Produce a user stacktrace in faultable context
> @@ -24,6 +27,7 @@
> int unwind_user_faultable(struct unwind_stacktrace *trace)
> {
> struct unwind_task_info *info = ¤t->unwind_info;
> + struct unwind_cache *cache;
>
> /* Should always be called from faultable context */
> might_fault();
> @@ -31,17 +35,30 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
> if (current->flags & PF_EXITING)
> return -EINVAL;
>
> - if (!info->entries) {
> - info->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long),
> - GFP_KERNEL);
> - if (!info->entries)
> + if (!info->cache) {
> + info->cache = kzalloc(struct_size(cache, entries, UNWIND_MAX_ENTRIES),
> + GFP_KERNEL);
> + if (!info->cache)
> return -ENOMEM;
> }
>
> + cache = info->cache;
> + trace->entries = cache->entries;
> +
> + if (cache->nr_entries) {
> + /*
> + * The user stack has already been previously unwound in this
> + * entry context. Skip the unwind and use the cache.
> + */
> + trace->nr = cache->nr_entries;
> + return 0;
> + }
> +
> trace->nr = 0;
> - trace->entries = info->entries;
> unwind_user(trace, UNWIND_MAX_ENTRIES);
>
> + cache->nr_entries = trace->nr;
> +
> return 0;
> }
>
> @@ -56,5 +73,5 @@ void unwind_task_free(struct task_struct *task)
> {
> struct unwind_task_info *info = &task->unwind_info;
>
> - kfree(info->entries);
> + kfree(info->cache);
> }
On Tue, 29 Jul 2025 21:55:39 -0700
Indu Bhagat <indu.bhagat@oracle.com> wrote:
> > diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
> > index a5f6e8f8a1a2..baacf4a1eb4c 100644
> > --- a/include/linux/unwind_deferred.h
> > +++ b/include/linux/unwind_deferred.h
> > @@ -12,6 +12,12 @@ void unwind_task_free(struct task_struct *task);
> >
> > int unwind_user_faultable(struct unwind_stacktrace *trace);
> >
> > +static __always_inline void unwind_reset_info(void)
> > +{
> > + if (unlikely(current->unwind_info.cache))
> > + current->unwind_info.cache->nr_entries = 0;
> > +}
>
> Should the entries[] items upto nr_entries (stack trace info from the
> previous request) also be reset to 0 here ?
This is in a critical path, there's no reason to reset to zero. The data will
just be stale. Nothing should care about anything over nr_entries.
> > diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
> > index aa32db574e43..db5b54b18828 100644
> > --- a/include/linux/unwind_deferred_types.h
> > +++ b/include/linux/unwind_deferred_types.h
> > @@ -2,8 +2,13 @@
> > #ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H
> > #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
> >
> > +struct unwind_cache {
> > + unsigned int nr_entries;
> > + unsigned long entries[];
> > +};
> > +
>
> Should we use __counted_by ?
The size of entries[] is not determined by nr_entries. It is allocated on
the first use, and not freed until the task exits. It's a fixed size
defined by:
/* Make the cache fit in a 4K page */
#define UNWIND_MAX_ENTRIES \
((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long))
-- Steve
On 7/30/25 6:32 AM, Steven Rostedt wrote:
> On Tue, 29 Jul 2025 21:55:39 -0700
> Indu Bhagat <indu.bhagat@oracle.com> wrote:
>
>>> diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
>>> index a5f6e8f8a1a2..baacf4a1eb4c 100644
>>> --- a/include/linux/unwind_deferred.h
>>> +++ b/include/linux/unwind_deferred.h
>>> @@ -12,6 +12,12 @@ void unwind_task_free(struct task_struct *task);
>>>
>>> int unwind_user_faultable(struct unwind_stacktrace *trace);
>>>
>>> +static __always_inline void unwind_reset_info(void)
>>> +{
>>> + if (unlikely(current->unwind_info.cache))
>>> + current->unwind_info.cache->nr_entries = 0;
>>> +}
>>
>> Should the entries[] items upto nr_entries (stack trace info from the
>> previous request) also be reset to 0 here ?
>
> This is in a critical path, there's no reason to reset to zero. The data will
> just be stale. Nothing should care about anything over nr_entries.
>
OK.
Reviewed-By: Indu Bhagat <indu.bhagat@oracle.com>
© 2016 - 2026 Red Hat, Inc.