linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
	bpf@vger.kernel.org, x86@kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Josh Poimboeuf <jpoimboe@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Andrii Nakryiko <andrii@kernel.org>,
	Indu Bhagat <indu.bhagat@oracle.com>,
	"Jose E. Marchesi" <jemarch@gnu.org>,
	Beau Belgrave <beaub@linux.microsoft.com>,
	Jens Remus <jremus@linux.ibm.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Jens Axboe <axboe@kernel.dk>
Subject: [PATCH v11 05/14] unwind_user/deferred: Add unwind cache
Date: Wed, 25 Jun 2025 18:56:05 -0400	[thread overview]
Message-ID: <20250625225715.657143263@goodmis.org> (raw)
In-Reply-To: 20250625225600.555017347@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>
---
Changes since v10: https://lore.kernel.org/20250611010428.603778772@goodmis.org

- Rename unwind_exit_to_user_mode() to unwind_reset_info() as it is called
  in a noinstr section and the current name looks like it does
  instrumentation (Peter Zijlstra)

- Make the allocated cache fit inside a 4K page. (Peter Zijlstra)

 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 = &current->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



  parent reply	other threads:[~2025-06-25 22:57 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-25 22:56 [PATCH v11 00/14] unwind_user: x86: Deferred unwinding infrastructure Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 01/14] unwind_user: Add user space unwinding API Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 02/14] unwind_user: Add frame pointer support Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 03/14] unwind_user: Add compat mode " Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 04/14] unwind_user/deferred: Add unwind_user_faultable() Steven Rostedt
2025-06-25 22:56 ` Steven Rostedt [this message]
2025-06-25 22:56 ` [PATCH v11 06/14] unwind_user/deferred: Add deferred unwinding interface Steven Rostedt
2025-06-26 16:48   ` Steven Rostedt
2025-06-26 20:34     ` Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 07/14] unwind_user/deferred: Make unwind deferral requests NMI-safe Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 08/14] unwind deferred: Use bitmask to determine which callbacks to call Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 09/14] unwind deferred: Use SRCU unwind_deferred_task_work() Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 10/14] unwind: Clear unwind_mask on exit back to user space Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 11/14] unwind: Finish up unwind when a task exits Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 12/14] unwind_user/x86: Enable frame pointer unwinding on x86 Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 13/14] perf/x86: Rename and move get_segment_base() and make it global Steven Rostedt
2025-06-26  8:44   ` Ingo Molnar
2025-06-26 12:13     ` Steven Rostedt
2025-06-26 13:07   ` Peter Zijlstra
2025-06-26 15:13     ` Steven Rostedt
2025-06-25 22:56 ` [PATCH v11 14/14] unwind_user/x86: Enable compat mode frame pointer unwinding on x86 Steven Rostedt
2025-06-26  8:33   ` Ingo Molnar
2025-06-26 12:12     ` Steven Rostedt
2025-06-27 14:01       ` Steven Rostedt
2025-06-27 16:23         ` Linus Torvalds
2025-06-30 12:50 ` [PATCH v11 00/14] unwind_user: x86: Deferred unwinding infrastructure Florian Weimer
2025-06-30 16:35   ` Namhyung Kim
2025-06-30 17:30   ` Steven Rostedt
2025-07-02 11:44   ` Sam James
2025-07-02 16:15     ` Steven Rostedt
2025-07-02 17:14       ` Namhyung Kim
2025-07-03  4:01         ` Sam James
2025-07-02 17:10     ` Namhyung Kim

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=20250625225715.657143263@goodmis.org \
    --to=rostedt@goodmis.org \
    --cc=akpm@linux-foundation.org \
    --cc=andrii@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=beaub@linux.microsoft.com \
    --cc=bpf@vger.kernel.org \
    --cc=indu.bhagat@oracle.com \
    --cc=jemarch@gnu.org \
    --cc=jolsa@kernel.org \
    --cc=jpoimboe@kernel.org \
    --cc=jremus@linux.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mhiramat@kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.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;
as well as URLs for NNTP newsgroup(s).