From 4cc0473d7754d387680bdf0728eb29f0ec8834bf Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Mon, 7 Oct 2024 22:49:05 +0800 Subject: [PATCH] get rid of __get_task_comm() Patch series "Improve the copy of task comm", v8. Using {memcpy,strncpy,strcpy,kstrdup} to copy the task comm relies on the length of task comm. Changes in the task comm could result in a destination string that is overflow. Therefore, we should explicitly ensure the destination string is always NUL-terminated, regardless of the task comm. This approach will facilitate future extensions to the task comm. As suggested by Linus [0], we can identify all relevant code with the following git grep command: git grep 'memcpy.*->comm\>' git grep 'kstrdup.*->comm\>' git grep 'strncpy.*->comm\>' git grep 'strcpy.*->comm\>' PATCH #2~#4: memcpy PATCH #5~#6: kstrdup PATCH #7: strcpy Please note that strncpy() is not included in this series as it is being tracked by another effort. [1] This patch (of 7): 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 Link: https://lkml.kernel.org/r/20241007144911.27693-1-laoar.shao@gmail.com Link: https://lkml.kernel.org/r/20241007144911.27693-2-laoar.shao@gmail.com 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/ Link: https://lore.kernel.org/all/CAHk-=wjAmmHUg6vho1KjzQi2=psR30+CogFd4aXrThr2gsiS4g@mail.gmail.com/ [0] Link: https://github.com/KSPP/linux/issues/90 [1] Signed-off-by: Yafang Shao Suggested-by: Linus Torvalds Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Cc: Eric Biederman Cc: Kees Cook Cc: Alexei Starovoitov Cc: Matus Jokay Cc: Alejandro Colomar Cc: "Serge E. Hallyn" Cc: Catalin Marinas Cc: Justin Stitt Cc: Steven Rostedt (Google) Cc: Tetsuo Handa Cc: Andy Shevchenko Cc: Daniel Vetter Cc: David Airlie Cc: Eric Paris Cc: James Morris Cc: Maarten Lankhorst Cc: Matthew Wilcox Cc: Maxime Ripard Cc: Ondrej Mosnacek Cc: Paul Moore Cc: Quentin Monnet Cc: Simon Horman Cc: Stephen Smalley Cc: Thomas Zimmermann Signed-off-by: Andrew Morton --- 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 --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 bb343136ddd0..67718d5591dd 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 9bb36897b6c6..a5ac612b1609 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; }