linux-kernel - [PATCH v8 08/18] unwind_user/deferred: Add unwind cache

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250509165154.958107663@goodmis.org>
Date: Fri, 09 May 2025 12:45:32 -0400
From: Steven Rostedt <rostedt@...dmis.org>
To: linux-kernel@...r.kernel.org,
 linux-trace-kernel@...r.kernel.org,
 bpf@...r.kernel.org,
 x86@...nel.org
Cc: Masami Hiramatsu <mhiramat@...nel.org>,
 Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
 Josh Poimboeuf <jpoimboe@...nel.org>,
 Peter Zijlstra <peterz@...radead.org>,
 Ingo Molnar <mingo@...nel.org>,
 Jiri Olsa <jolsa@...nel.org>,
 Namhyung Kim <namhyung@...nel.org>
Subject: [PATCH v8 08/18] unwind_user/deferred: Add unwind cache

From: Josh Poimboeuf <jpoimboe@...nel.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@...dmis.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@...nel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@...dmis.org>
---
Changes since v7: https://lore.kernel.org/20250502165008.734340489@goodmis.org

- Allocate unwind_cache as a structure and not just its entries
  (Ingo Molnar)

- Fixed white space issues
  (Ingo Molnar)

 include/linux/entry-common.h          |  2 ++
 include/linux/unwind_deferred.h       |  8 ++++++++
 include/linux/unwind_deferred_types.h |  7 ++++++-
 kernel/unwind/deferred.c              | 26 ++++++++++++++++++++------
 4 files changed, 36 insertions(+), 7 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..7d6cb2ffd084 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_deferred_trace(struct unwind_stacktrace *trace);
 
+static __always_inline void unwind_exit_to_user_mode(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_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..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 0bafb95e6336..e3913781c8c6 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -24,6 +24,7 @@
 int unwind_deferred_trace(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 +32,30 @@ 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)
+	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 +70,5 @@ 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