From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Josh Poimboeuf <jpoimboe@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
x86@kernel.org, Jiri Olsa <jolsa@kernel.org>,
Namhyung Kim <namhyung@kernel.org>
Subject: [PATCH v7 08/17] unwind_user/deferred: Add unwind cache
Date: Fri, 02 May 2025 12:47:54 -0400 [thread overview]
Message-ID: <20250502165008.734340489@goodmis.org> (raw)
In-Reply-To: 20250502164746.178864972@goodmis.org
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.
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>
---
include/linux/entry-common.h | 2 ++
include/linux/unwind_deferred.h | 7 +++++++
include/linux/unwind_deferred_types.h | 7 ++++++-
kernel/unwind/deferred.c | 27 ++++++++++++++++++++-------
4 files changed, 35 insertions(+), 8 deletions(-)
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index f94f3fdf15fc..6e850c9d3f0c 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_exit_to_user_mode();
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 5064ebe38c4f..c2d760e5e257 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -12,6 +12,11 @@ void unwind_task_free(struct task_struct *task);
int unwind_deferred_trace(struct unwind_stacktrace *trace);
+static __always_inline void unwind_exit_to_user_mode(void)
+{
+ current->unwind_info.cache.nr_entries = 0;
+}
+
#else /* !CONFIG_UNWIND_USER */
static inline void unwind_task_init(struct task_struct *task) {}
@@ -19,6 +24,8 @@ static inline void unwind_task_free(struct task_struct *task) {}
static inline int unwind_deferred_trace(struct unwind_stacktrace *trace) { return -ENOSYS; }
+static inline void unwind_exit_to_user_mode(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..b3b7389ee6eb 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_task_info {
+struct unwind_cache {
unsigned long *entries;
+ unsigned int nr_entries;
+};
+
+struct unwind_task_info {
+ struct unwind_cache cache;
};
#endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index 5a3789e38c00..89ed04b1c527 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -12,6 +12,7 @@
int unwind_deferred_trace(struct unwind_stacktrace *trace)
{
struct unwind_task_info *info = ¤t->unwind_info;
+ struct unwind_cache *cache = &info->cache;
/* Should always be called from faultable context */
might_fault();
@@ -19,17 +20,29 @@ int unwind_deferred_trace(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)
- return -ENOMEM;
+ if (!cache->entries) {
+ cache->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long),
+ GFP_KERNEL);
+ if (!cache->entries)
+ return -ENOMEM;
+ }
+
+ 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;
}
@@ -44,5 +57,5 @@ void unwind_task_free(struct task_struct *task)
{
struct unwind_task_info *info = &task->unwind_info;
- kfree(info->entries);
+ kfree(info->cache.entries);
}
--
2.47.2
next prev parent reply other threads:[~2025-05-02 16:50 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-02 16:47 [PATCH v7 00/17] unwind_user: perf: x86: Deferred unwinding infrastructure Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 01/17] unwind_user: Add user space unwinding API Steven Rostedt
2025-05-04 9:30 ` Ingo Molnar
2025-05-04 16:43 ` Steven Rostedt
2025-05-04 17:53 ` Josh Poimboeuf
2025-05-02 16:47 ` [PATCH v7 02/17] unwind_user: Add frame pointer support Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 03/17] unwind_user/x86: Enable frame pointer unwinding on x86 Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 04/17] perf/x86: Rename and move get_segment_base() and make it global Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 05/17] unwind_user: Add compat mode frame pointer support Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 06/17] unwind_user/x86: Enable compat mode frame pointer unwinding on x86 Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 07/17] unwind_user/deferred: Add unwind_deferred_trace() Steven Rostedt
2025-05-02 16:47 ` Steven Rostedt [this message]
2025-05-04 9:37 ` [PATCH v7 08/17] unwind_user/deferred: Add unwind cache Ingo Molnar
2025-05-04 16:21 ` Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 09/17] unwind_user/deferred: Add deferred unwinding interface Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 10/17] unwind_user/deferred: Make unwind deferral requests NMI-safe Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 11/17] unwind deferred: Use bitmask to determine which callbacks to call Steven Rostedt
2025-05-09 1:36 ` Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 12/17] unwind deferred: Use SRCU unwind_deferred_task_work() Steven Rostedt
2025-05-02 16:47 ` [PATCH v7 13/17] perf: Remove get_perf_callchain() init_nr argument Steven Rostedt
2025-05-02 16:48 ` [PATCH v7 14/17] perf: Have get_perf_callchain() return NULL if crosstask and user are set Steven Rostedt
2025-05-02 16:48 ` [PATCH v7 15/17] perf: Use current->flags & PF_KTHREAD instead of current->mm == NULL Steven Rostedt
2025-05-02 16:48 ` [PATCH v7 16/17] perf: Simplify get_perf_callchain() user logic Steven Rostedt
2025-05-02 16:48 ` [PATCH v7 17/17] perf: Skip user unwind if the task is a kernel thread Steven Rostedt
2025-05-04 9:41 ` [PATCH v7 00/17] unwind_user: perf: x86: Deferred unwinding infrastructure Ingo Molnar
2025-05-04 16:32 ` Steven Rostedt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250502165008.734340489@goodmis.org \
--to=rostedt@goodmis.org \
--cc=jolsa@kernel.org \
--cc=jpoimboe@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox