[PATCH 3/4] mm: synchronize saved_auxv access with arg_lock
Andrei Vagin <[email protected]> Mon, 23 Mar 2026 17:53:39 +0000
| Newsgroups | dev.linux.lists.criu,org.infradead.lists.linux-arm-kernel,org.kernel.vger.linux-fsdevel,org.kernel.vger.linux-kernel,org.kvack.linux-mm |
|---|---|
| Message-ID | <[email protected]> |
The mm->saved_auxv array stores the auxiliary vector, which can be modified via prctl(PR_SET_MM_AUXV) or prctl(PR_SET_MM_MAP). Previously, accesses to saved_auxv were not synchronized. This was a intentional trade-off, as the vector was only used to provide information to userspace via /proc/PID/auxv or prctl(PR_GET_AUXV), and consistency between the auxv values left to userspace. With the introduction of hardware capability (HWCAP) inheritance during execve, the kernel now relies on the contents of saved_auxv to configure the execution environment of new processes. An unsynchronized read during execve could result in a new process inheriting an inconsistent set of capabilities if the parent process updates its auxiliary vector concurrently. While it is still not strictly required to guarantee the consistency of auxv values on the kernel side, doing so is relatively straightforward. This change implements synchronization using arg_lock. Reviewed-by: Alexander Mikhalitsyn <[email protected]> Reviewed-by: Cyrill Gorcunov <[email protected]> Reviewed-by: Michal Koutný <[email protected]> Signed-off-by: Andrei Vagin <[email protected]> --- fs/exec.c | 2 ++ fs/proc/base.c | 12 +++++++++--- include/linux/mm_types.h | 1 - kernel/fork.c | 7 ++++++- kernel/sys.c | 29 ++++++++++++++--------------- 5 files changed, 31 insertions(+), 20 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index 1cd7d87a0e79..dea868d058fa 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1791,6 +1791,7 @@ static void inherit_hwcap(struct linux_binprm *bprm) n = 1; #endif + spin_lock(&mm->arg_lock); for (i = 0; n && i < AT_VECTOR_SIZE; i += 2) { unsigned long type, val; @@ -1831,6 +1832,7 @@ static void inherit_hwcap(struct linux_binprm *bprm) n--; } done: + spin_unlock(&mm->arg_lock); mm_flags_set(MMF_USER_HWCAP, bprm->mm); } diff --git a/fs/proc/base.c b/fs/proc/base.c index 4c863d17dfb4..b5496cec888e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1083,14 +1083,20 @@ static ssize_t auxv_read(struct file *file, char __user *buf, { struct mm_struct *mm = file->private_data; unsigned int nwords = 0; + unsigned long saved_auxv[AT_VECTOR_SIZE]; if (!mm) return 0; + + spin_lock(&mm->arg_lock); + memcpy(saved_auxv, mm->saved_auxv, sizeof(saved_auxv)); + spin_unlock(&mm->arg_lock); + do { nwords += 2; - } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ - return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv, - nwords * sizeof(mm->saved_auxv[0])); + } while (saved_auxv[nwords - 2] != 0); /* AT_NULL */ + return simple_read_from_buffer(buf, count, ppos, saved_auxv, + nwords * sizeof(saved_auxv[0])); } static const struct file_operations proc_auxv_operations = { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 62dde645f469..10351af5851b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1255,7 +1255,6 @@ struct mm_struct { unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; - unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ #ifdef CONFIG_ARCH_HAS_ELF_CORE_EFLAGS diff --git a/kernel/fork.c b/kernel/fork.c index 2ac277aa078c..3880ce0d44f9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1106,8 +1106,13 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, __mm_flags_overwrite_word(mm, mmf_init_legacy_flags(flags)); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; - if (mm_flags_test(MMF_USER_HWCAP, current->mm)) + if (mm_flags_test(MMF_USER_HWCAP, current->mm)) { + spin_lock(¤t->mm->arg_lock); mm_flags_set(MMF_USER_HWCAP, mm); + memcpy(mm->saved_auxv, current->mm->saved_auxv, + sizeof(mm->saved_auxv)); + spin_unlock(¤t->mm->arg_lock); + } } else { __mm_flags_overwrite_word(mm, default_dump_filter); mm->def_flags = 0; diff --git a/kernel/sys.c b/kernel/sys.c index e4b0fa2f6845..c679b5797e73 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2147,20 +2147,11 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; - spin_unlock(&mm->arg_lock); - - /* - * Note this update of @saved_auxv is lockless thus - * if someone reads this member in procfs while we're - * updating -- it may get partly updated results. It's - * known and acceptable trade off: we leave it as is to - * not introduce additional locks here making the kernel - * more complex. - */ if (prctl_map.auxv_size) { - memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); mm_flags_set(MMF_USER_HWCAP, mm); + memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); } + spin_unlock(&mm->arg_lock); mmap_read_unlock(mm); return 0; @@ -2190,10 +2181,10 @@ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr, BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); - task_lock(current); - memcpy(mm->saved_auxv, user_auxv, len); + spin_lock(&mm->arg_lock); mm_flags_set(MMF_USER_HWCAP, mm); - task_unlock(current); + memcpy(mm->saved_auxv, user_auxv, len); + spin_unlock(&mm->arg_lock); return 0; } @@ -2481,9 +2472,17 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, static int prctl_get_auxv(void __user *addr, unsigned long len) { struct mm_struct *mm = current->mm; + unsigned long auxv[AT_VECTOR_SIZE]; unsigned long size = min_t(unsigned long, sizeof(mm->saved_auxv), len); - if (size && copy_to_user(addr, mm->saved_auxv, size)) + if (!size) + return sizeof(mm->saved_auxv); + + spin_lock(&mm->arg_lock); + memcpy(auxv, mm->saved_auxv, size); + spin_unlock(&mm->arg_lock); + + if (copy_to_user(addr, auxv, size)) return -EFAULT; return sizeof(mm->saved_auxv); } -- 2.53.0.983.g0bb29b3bc5-goog