linux-kernel - [PATCH v2 4/5] x86/shstk: don't create the shadow stack for PF_USER

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: <20250822153702.GA27153@redhat.com>
Date: Fri, 22 Aug 2025 17:37:02 +0200
From: Oleg Nesterov <oleg@...hat.com>
To: Borislav Petkov <bp@...en8.de>,
	Dave Hansen <dave.hansen@...ux.intel.com>,
	Deepak Gupta <debug@...osinc.com>, "H. Peter Anvin" <hpa@...or.com>,
	Ingo Molnar <mingo@...nel.org>, Mark Brown <broonie@...nel.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Rick Edgecombe <rick.p.edgecombe@...el.com>,
	Sohil Mehta <sohil.mehta@...el.com>,
	Thomas Gleixner <tglx@...utronix.de>
Cc: linux-kernel@...r.kernel.org, x86@...nel.org
Subject: [PATCH v2 4/5] x86/shstk: don't create the shadow stack for
 PF_USER_WORKERs

If a features_enabled(ARCH_SHSTK_SHSTK) userspace thread creates a
PF_USER_WORKER thread, shstk_alloc_thread_stack() allocates the shadow
stack for no reason, the new (kernel) thread will never return to usermode.

Plus the current code doesn't even look correct, in this case fpu_clone()
won't call update_fpu_shstk().

Add the new "bool minimal = !!args->fn" argument (which matches that of
fpu_clone()) to shstk_alloc_thread_stack() and change it to check this
argument along with CLONE_VFORK.

With this patch ssp_get() -> ssp_active(target) should never return true
if target->flags & PF_USER_WORKER.

Signed-off-by: Oleg Nesterov <oleg@...hat.com>
---
 arch/x86/include/asm/shstk.h | 4 ++--
 arch/x86/kernel/process.c    | 2 +-
 arch/x86/kernel/shstk.c      | 9 +++++++--
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index ba6f2fe43848..a4ee2baab51c 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -17,7 +17,7 @@ struct thread_shstk {
 long shstk_prctl(struct task_struct *task, int option, unsigned long arg2);
 void reset_thread_features(void);
 unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clone_flags,
-				       unsigned long stack_size);
+				       bool minimal, unsigned long stack_size);
 void shstk_free(struct task_struct *p);
 int setup_signal_shadow_stack(struct ksignal *ksig);
 int restore_signal_shadow_stack(void);
@@ -28,7 +28,7 @@ static inline long shstk_prctl(struct task_struct *task, int option,
 			       unsigned long arg2) { return -EINVAL; }
 static inline void reset_thread_features(void) {}
 static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p,
-						     unsigned long clone_flags,
+						     unsigned long clone_flags, bool minimal,
 						     unsigned long stack_size) { return 0; }
 static inline void shstk_free(struct task_struct *p) {}
 static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 1b7960cf6eb0..e932e0e53972 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -209,7 +209,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	 * is disabled, new_ssp will remain 0, and fpu_clone() will know not to
 	 * update it.
 	 */
-	new_ssp = shstk_alloc_thread_stack(p, clone_flags, args->stack_size);
+	new_ssp = shstk_alloc_thread_stack(p, clone_flags, args->fn, args->stack_size);
 	if (IS_ERR_VALUE(new_ssp))
 		return PTR_ERR((void *)new_ssp);
 
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 2ddf23387c7e..6c8c4593e202 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -192,7 +192,7 @@ void reset_thread_features(void)
 }
 
 unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long clone_flags,
-				       unsigned long stack_size)
+				       bool minimal, unsigned long stack_size)
 {
 	struct thread_shstk *shstk = &tsk->thread.shstk;
 	unsigned long addr, size;
@@ -208,8 +208,13 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long cl
 	 * For CLONE_VFORK the child will share the parents shadow stack.
 	 * Make sure to clear the internal tracking of the thread shadow
 	 * stack so the freeing logic run for child knows to leave it alone.
+	 *
+	 * If minimal == true, the new kernel thread cloned from userspace
+	 * thread will never return to usermode.
 	 */
-	if (clone_flags & CLONE_VFORK) {
+	if ((clone_flags & CLONE_VFORK) || minimal) {
+		if (minimal)
+			tsk->thread.features &= ~ARCH_SHSTK_SHSTK;
 		shstk->base = 0;
 		shstk->size = 0;
 		return 0;
-- 
2.25.1.362.g51ebf55