diff mbox series

[v9,1/7] Get rid of __get_task_comm()

Message ID 20241007144911.27693-2-laoar.shao@gmail.com (mailing list archive)
State New
Headers show
Series Improve the copy of task comm | expand

Commit Message

Yafang Shao Oct. 7, 2024, 2:49 p.m. UTC
We want to eliminate the use of __get_task_comm() for the following
reasons:

- The task_lock() is unnecessary
  Quoted from Linus [0]:
  : Since user space can randomly change their names anyway, using locking
  : was always wrong for readers (for writers it probably does make sense
  : to have some lock - although practically speaking nobody cares there
  : either, but at least for a writer some kind of race could have
  : long-term mixed results

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/all/CAHk-=wivfrF0_zvf+oj6==Sh=-npJooP8chLPEfaFV0oNYTTBA@mail.gmail.com [0]
Link: https://lore.kernel.org/all/CAHk-=whWtUC-AjmGJveAETKOMeMFSTwKwu99v7+b6AyHMmaDFA@mail.gmail.com/
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Matus Jokay <matus.jokay@stuba.sk>
Cc: Alejandro Colomar <alx@kernel.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
---
 fs/exec.c             | 10 ----------
 fs/proc/array.c       |  2 +-
 include/linux/sched.h | 28 ++++++++++++++++++++++------
 kernel/kthread.c      |  2 +-
 4 files changed, 24 insertions(+), 18 deletions(-)
diff mbox series

Patch

diff --git a/fs/exec.c b/fs/exec.c
index 6c53920795c2..77364806b48d 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1189,16 +1189,6 @@  static int unshare_sighand(struct task_struct *me)
 	return 0;
 }
 
-char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk)
-{
-	task_lock(tsk);
-	/* Always NUL terminated and zero-padded */
-	strscpy_pad(buf, tsk->comm, buf_size);
-	task_unlock(tsk);
-	return buf;
-}
-EXPORT_SYMBOL_GPL(__get_task_comm);
-
 /*
  * These functions flushes out all traces of the currently running executable
  * so that a new one can be started
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 34a47fb0c57f..55ed3510d2bb 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -109,7 +109,7 @@  void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape)
 	else if (p->flags & PF_KTHREAD)
 		get_kthread_comm(tcomm, sizeof(tcomm), p);
 	else
-		__get_task_comm(tcomm, sizeof(tcomm), p);
+		get_task_comm(tcomm, p);
 
 	if (escape)
 		seq_escape_str(m, tcomm, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e6ee4258169a..28f92c637abf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1121,9 +1121,12 @@  struct task_struct {
 	/*
 	 * executable name, excluding path.
 	 *
-	 * - normally initialized setup_new_exec()
-	 * - access it with [gs]et_task_comm()
-	 * - lock it with task_lock()
+	 * - normally initialized begin_new_exec()
+	 * - set it with set_task_comm()
+	 *   - strscpy_pad() to ensure it is always NUL-terminated and
+	 *     zero-padded
+	 *   - task_lock() to ensure the operation is atomic and the name is
+	 *     fully updated.
 	 */
 	char				comm[TASK_COMM_LEN];
 
@@ -1938,10 +1941,23 @@  static inline void set_task_comm(struct task_struct *tsk, const char *from)
 	__set_task_comm(tsk, from, false);
 }
 
-extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk);
+/*
+ * - Why not use task_lock()?
+ *   User space can randomly change their names anyway, so locking for readers
+ *   doesn't make sense. For writers, locking is probably necessary, as a race
+ *   condition could lead to long-term mixed results.
+ *   The strscpy_pad() in __set_task_comm() can ensure that the task comm is
+ *   always NUL-terminated and zero-padded. Therefore the race condition between
+ *   reader and writer is not an issue.
+ *
+ * - BUILD_BUG_ON() can help prevent the buf from being truncated.
+ *   Since the callers don't perform any return value checks, this safeguard is
+ *   necessary.
+ */
 #define get_task_comm(buf, tsk) ({			\
-	BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN);	\
-	__get_task_comm(buf, sizeof(buf), tsk);		\
+	BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN);	\
+	strscpy_pad(buf, (tsk)->comm);			\
+	buf;						\
 })
 
 #ifdef CONFIG_SMP
diff --git a/kernel/kthread.c b/kernel/kthread.c
index db4ceb0f503c..74d20f46fa30 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -101,7 +101,7 @@  void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
 	struct kthread *kthread = to_kthread(tsk);
 
 	if (!kthread || !kthread->full_name) {
-		__get_task_comm(buf, buf_size, tsk);
+		strscpy(buf, tsk->comm, buf_size);
 		return;
 	}